Projects AnSyMo
Ongoing projects
AI for Software Engineering + Software engineering for AI
Abstract
From the early days of artificial intelligence (AI), software engineering was considered a promising application field. Already in 1987, the Programmer's Apprentice Project formulated the idea of an expert system supporting software engineers in routine tasks. Over the last decades this idea has grown into a driving force with top conferences like "Automated Software Engineering" (ASE) and "Mining Software Repositories" (MSR). The recent impulse created by generative AI only aggravated this research. Conversely, research in AI can benefit a lot from modern software engineering practices. Today's AI systems are data-hungry; the data processing pipelines are coded in a mixture of high-level scripting languages. However, subtle changes in the underlying program code may affect the results in unpredictable ways. Advanced software engineering techniques like fault injection and resilience testing should help in making these data processing pipelines robust. In this exploratory project, we intend to investigate how both disciplines can reinforce one another.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Classical Automated Reasoning for Knowledge Representation in Quantum Systems
Abstract
Quantumcomputing werd oorspronkelijk bedacht als een middel om kwantumsystemen te simuleren, maar zelfs zonder grootschalige kwantumhardware blijft de uitdaging om dergelijke systemen te modelleren en analyseren fundamenteel voor domeinen zoals kwantumalgoritmen, veeldeeltjesfysica, materiaalkunde en kwantumchemie. Dit project stelt dat deze uitdagingen effectief kunnen worden aangepakt met klassieke computationele methoden, met name via technieken uit Knowledge Representation and Reasoning (KRR), een kerngebied binnen de kunstmatige intelligentie dat zich richt op het structureren en beredeneren van complexe informatie. Hoewel KRR zeer succesvol is gebleken bij het oplossen van moeilijke combinatorische en probabilistische problemen, is het niet direct geschikt voor de unieke eigenschappen van kwantumsystemen. Kwantumtoestanden worden gekenmerkt door complexwaardige amplitudes, interferentie-effecten, omkeerbaarheid en hoge mate van verstrengeling, waardoor bestaande representatiemethoden inefficiënt worden en huidige redeneertechnieken tekortschieten. Bovendien zijn verbanden tussen datastructuren uit de fysica, zoals tensornetwerken, en uit de informatica, zoals beslissingsdiagrammen, nog onvoldoende onderzocht. Dit project heeft als doel een nieuw, klassiek gefundeerd raamwerk te ontwikkelen voor het representeren en beredeneren van kwantumsystemen. Het introduceert hybride datastructuren die ideeën uit tensornetwerken, beslissingsdiagrammen en automatentheorie combineren om complexe kwantumtoestanden efficiënt vast te leggen. Daarnaast worden redeneer- en modeltelalgoritmen herontworpen voor de kwantumcontext, en worden nieuwe methoden voor kwantumcircuit-synthese ontwikkeld op basis van algebraïsche en automatentheoretische inzichten, die geavanceerde optimalisatietechnieken mogelijk maken. Door de kloof tussen AI-gebaseerde redeneermethoden en de kwantumtheorie te overbruggen, beoogt het project huidige schaalbaarheidsbeperkingen te doorbreken en krachtige klassieke hulpmiddelen te bieden voor de analyse en het ontwerp van kwantumsystemen, met brede impact op wetenschap en technologie.Researcher(s)
- Promoter: Perez Guillermo Alberto
Research team(s)
Project type(s)
- Research Project
Modelling hybrid quantum graph neural networks.
Abstract
Problems such as urban transportation networks require dynamic routing optimization that adapts to rapidly changing traffic conditions caused by congestion, accidents, and demand fluctuations. Classical routing algorithms such as Dijkstra and A* are computationally efficient but require complete path re-computation with each change, making them unsuitable for real-time dynamic environments. Classical Graph Neural Networks (GNNs) capture spatial dependencies effectively but encounter the over-smoothing problem, where increasing network depth to model long-range dependencies causes node representations to become increasingly similar, resulting in loss of discriminative information necessary for effective routing decisions. This PhD research addresses these fundamental limitations through the development of Hybrid Quantum Graph Neural Networks (HQGNNs) that leverage quantum entanglement to capture non-local correlations across the network without requiring deep message-passing architectures. By embedding graph signals into quantum state space, HQGNNs enable the representation of complex long-range congestion propagation patterns while preserving local discriminability—a combination that is fundamentally difficult to achieve in purely classical architectures. The resulting framework in the scope of this thesis will be evaluated with City of Antwerp data. The city of Antwerp, with its dense urban core and complex multi-modal transportation infrastructure, serves as an ideal testbed for evaluating HQGNN performance in real-world scenarios. Antwerp's network exhibits characteristic challenges including recurring bottlenecks at key intersections, variable traffic patterns influenced by port activity, and the need for coordination between private vehicles, public transit, and commercial freight. Applying HQGNNs to Antwerp's transportation system enables validation of the proposed approach against traffic data while demonstrating practical scalability and adaptability to actual urban routing constraints.Researcher(s)
- Promoter: Challenger Moharram
- Fellow: Gholipour Hamed
Research team(s)
Project type(s)
- Research Project
KR2IQS: Knowledge Representation and Reasoning in Quantum Systems.
Abstract
In this research, we explore how classical artificial intelligence (AI) techniques can help overcome key challenges in quantum computing. While quantum computers have the potential to revolutionize fields like chemistry and materials science, they face computational problems that remain difficult to solve with existing methods. We propose leveraging Knowledge Representation and Reasoning (KRR)—a branch of AI that helps machines structure, store, and reason with information—to improve quantum computing techniques. KRR has been highly effective in classical computing, but applying it to quantum systems presents unique challenges due to quantum properties like negative "probabilities" (amplitudes) and highly entangled states. To address these issues, we focus on two key directions: 1. Developing new ways to represent quantum states using mathematical tools such as tensor networks and decision diagrams. 2. Redesigning reasoning algorithms to efficiently handle quantum circuits, drawing on advanced techniques from AI and computer science. Our work aims to advance quantum circuit simulation and optimization while also exploring broader applications in physics. Ultimately, we hope our approach will lead to new breakthroughs in quantum computing and provide fresh insights into complex quantum systems.Researcher(s)
- Promoter: Perez Guillermo Alberto
Research team(s)
Project type(s)
- Research Project
Intelligent Model Management.
Abstract
With data science entering various domains, new branches are emerging due to the extraction of latent knowledge from each domain's data. Model-based engineering and modeling are no exceptions. Now is the time to open a new chapter in this field by leveraging advanced artificial intelligence techniques. As the number and complexity of models increase, NP-complete problems arise that cannot be effectively addressed through deterministic management solutions. An effective way to address these challenges is by applying non-deterministic intelligent methodologies and data science-derived solutions. The increasing number of models and the formation of large model repositories necessitate intelligent model management, which aims to recognize hidden patterns and knowledge within these repositories using data science, machine learning techniques, and statistical and probabilistic methods for reuse. Despite the progress made in this area, both theoretically and practically, intelligent model management has not yet secured a prominent place in the body of knowledge of model-driven engineering. In this project, we aim to handle the management of large number of structural models, under intelligent model management, using machine learning algorithms. This objective will pave the way to capture knowledge from legacy models and re-use this knowledge in the new design, leading to sustainability and performance increase .Researcher(s)
- Promoter: Challenger Moharram
- Fellow: Khalilipour Alireza
Research team(s)
Project type(s)
- Research Project
A Multi-Paradigm Foundation for Experiment Modelling, Execution and Re-use.
Abstract
The repeatability and replicability of experiments are central notions of the scientific method. Physical experiments were the backbone of science and engineering. In today's development of complex, engineered systems, experiments are increasingly peformed in-silico, that is, through simulation. In order to reduce effort and expense, engineers use (computer) simulations of "models" of complex systems to investigate what-if scenarios and identify design flaws earlier. Modern engineered systems rely heavily on modelling and simulation. Over the past few decades, significant advances have been made in multi-formalism, multi-abstraction, and multi-view modelling. However, these developments have not been matched by comparable progress in the foundational methods for constructing and managing simulation experiments, nor in the systematic treatment of model validity. Without precise insight in the validity range of a model, no guarantees can be provided about the utility of the simulation results, which can often lead to costly mistakes. This is especially critical in the context of digital twins, where real-time decision-making relies on the validity of the simulated model to represent its real-world (cyber-physical) counterpart. Validity of models is ascertained by performing experiments in the real and simulated world and comparing their results. Repeatability and replicability are highly desirable of experiments experiments, ensuring that findings remain robust across independent trials and withstand the test of time. On further investigation, it became clear that repeatability and replicability require the ability to create, manage, and share reusable descriptions/specifications/models of said experiments. However, a general framework to model experiments (real or virtual), in order to reason about their properties like repeatability and replicability, and ultimately, the validity of models, is currently lacking. These reusable experiment models, that we call experiment specifications, serve as a basis for logical reasoning about the properties and conditions of (validation) experiments. They also enable reasoning about the contextual validity of models, where the validity of a model is not a single universal truth value, but instead a function of the experimental conditions specified in the experiment specification, called a validity frame. Furthermore, reusable experiment specifications can enhance efficiency by reducing the need to perform identical or similar experiments multiple times, allowing resources to be allocated toward exploring new experimental conditions. This project develops the foundations for specification, execution and (re-)use of experiment and validity frames.Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Mittal Rakshit
Research team(s)
Project type(s)
- Research Project
Embedding Models and Knowledge Graphs for a Technical Chatbot (TechTalk_IRVA)
Abstract
Service engineers often need to access technical data with which they are unfamiliar, as they were not involved in the design of the product. This challenge is exacerbated in the manufacturing and engineering sectors, where vast amounts of technical data exist in diverse formats such as databases, service manuals, and technical schemes. Companies managing products that operate 24/7 face the challenge of minimizing downtime while ensuring continuous operations. Efficient access to technical data is essential but often hampered by current systems' inability to integrate diverse sources effectively. Additionally, product-specific knowledge—held by engineers involved in the design process or (personal) insights gained through resolving similar issues in the past—is often inaccessible, limiting the ability to provide accurate and context-aware support. The goal of this project is to develop a proof-of-concept technical chatbot, supporting service engineers in querying technical data sources using natural language prompts. This will be achieved by creating a hybrid data integration framework, leveraging Retrieval-Augmented Generation (RAG) pipelines, that seamlessly combines unstructured and (semi-)structured data with tacit knowledge from domain experts. For the latter, a Knowledge Graph (KG) will serve as a repository of formalized knowledge, capturing relationships between data sources. By combining RAG pipelines with knowledge graphs, TechTalk aims to generate context-aware responses to user queries, achieving an accuracy of up to 90%.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Prediction & management of the 'reverse' remanufacturing supply chain (REMASC).
Abstract
Driven by sustainability, companies and customers alike are looking to set up a closed loop supply chain whereby products are returned to be 'remanufactured' (i.e., process to retain the usefulness of the product or the components). These product returns trigger a reverse manufacturing supply chain (REMASC). Companies are in need for tools that support both operational aspects, as well as strategic decision making related to the management of its remanufacturing activities. In this SBO project, Flanders Make will develop tools linked to three innovation goals: 1. To support strategic decision making related to the characteristics of product(family)-customer relationships required for product returns to be(come) a profitable business model. To this end REMASC will analyse and propose rewarding strategies. 2. To forecast (based on product type and customer profiles) the volume, reason for return, … of these product returns in order to organize the product inbound. It will provide tools to trigger fast decision making related to the quality of the product returned, i.e., deciding on 'waste' vs. defining the steps needed for the actual remanufacturing of the collected 'core'. 3. To efficiently manage the remanufacturing of returned products. This includes task generation, planning and scheduling of the remanufacturing activities; inventory management; needs for quality assessment and the potential integration of these remanufacturing activities in a classical manufacturing site. Enabled by industry 4.0 principles (such as digital product passports) and driven by sustainability, tools for managing the reverse manufacturing supply chain will benefit both end-users (OEM, TIER-1, TIER-2 and material providers), as well as service solutions providers (supply chain support, data analysis, logistics, ERP/MES integrators, operator support systems).Researcher(s)
- Promoter: Challenger Moharram
Research team(s)
Project type(s)
- Research Project
New Techniques & Tools to Improve robustness Of Cyber-Physical testing systems (TTRUST)
Abstract
In railway, as in many industries, new solutions result in increasingly complex Cyber-physical Systems, integrated in bigger systems, composed of many different sub-systems, and customized to the customer's needs. Manually writing tests for the ever-increasing number of variants and products is becoming impossible. In addition, the complexity of these interconnected systems increases the number of bugs discovered during functional, robustness and integration testing. Bugs found at this late stage of development are very expensive to solve. Therefore, companies are challenged to automatically test as early in the development cycle as possible. The objective of the TTRUST industrial research project is to improve the testing process and move bug detection and fixing earlier into the design process. During the project, two Rail representative use cases (from Televic and Alstom) will be used as a guideline and benchmark to design the new concepts related to software testing of complex systems. The TTRUST project aims to design and develop an efficient testing framework that automates and facilitates testing of complex, interconnected cyber-physical systems with a wide variety of inputs and parameters. To realize this goal, the project focusses on two research challenges, addressed in a holistic way: (i) Automated and high coverage Functional and robustness test generation (ii) Automated module isolation for failed integration tests.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Synthesis of reactive systems from formal specifications and examples.
Abstract
The goal of synthesis is to automatically generate a program from a high-level specification of *what* it has to do, rather than *how* it must do it. Synthesis is difficult to realise for general purpose programming languages, and researchers have targeted application-specific domains, such as reactive systems. Reactive systems are programs in continuous interaction with their environment, and must react in a timely fashion to its inputs by producing some control actions. Their automatic synthesis is an ambitious challenge: the uncontrollable nature of the environment makes synthesis methods algorithmically demanding. However, important progresses have been made in the last decade, during which efficient synthesis tools have been developed. This algorithmic prowess has not been followed by a methodological shift in reactive system design. SynthEx identifies an important reason: synthesis methods do not offer easy solutions to control the quality of the synthesis systems. To get high-quality programs, current approaches need precise specifications which include both high-level critical properties and low-level implementational details. Writing such precise specifications is difficult even for experts. SynthEx proposes a new methodology where only the high-level critical properties must be provided, together with some examples of execution scenarios. Its goal is to provide theoretical foundations supporting this new methodology and experimentally assess it.Researcher(s)
- Promoter: Perez Guillermo Alberto
Research team(s)
Project type(s)
- Research Project
Analog Computer Reboot.
Abstract
Today's engineered systems are modelled, simulated, and optimized extensively before they are built. Hardware in the Loop (HiL) simulation in particular replaces physical systems by a real-time simulator. Model compilers translate high-level models, notably Differential Algebraic Equations (DAEs), into accurate and efficient simulation code running on the HiL hardware. Digital HiL systems are expensive and power-hungry. Analog computers are an attractive alternative for low power simulation, even of non-linear models, typically an issue on digital computers. The analog computers from the past were bulky, sensitive to environmental conditions, and above all hard to (re-)configure. This project will come up with novel analog computer designs using FPAAs (Field Programmable Analog Arrays), for solving (HiL) simulation and optimization problems for multi-physics systems with relatively low frequencies (kHz range), modelled using DAEs. Our analog computer will be a cheaper and less energy-hungry alternative for HiL devices. Modellers will use the Equation-based Object-Oriented Language Modelica for the modular description of their systems. We develop a compiler to automatically synthesize the connection topology of the analog electronic components in the FPAA. An extensive study of the trade-offs between numerical accuracy, (scaled) real-time performance and energy consumption will be made. The extension to hybrid discrete-continuous models will be investigated.Researcher(s)
- Promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
BaseCamp Zero - Towards Zero-Touch Testing.
Abstract
The DevOps approach combined with a cloud-native application offers disruptive businesses (e.g., Netflix, Spotify, Zalando, Amazon, Uber) the strategic advantage to deploy their services rapidly and world-wide. Other software-intensive organisations will undoubtedly follow suit. Despite this strategic advantage, cloud-native applications imply a major risk. Their testability is hampered by non-determinism in the distributed and event-driven behavior that characterises their dominant architectural styles (i.e., micro-services and serverless), which is exacerbated by the dynamic cloud environment in which they operate. Assuring the quality of a cloud-native application therefore remains ––even with DevOps–– a major challenge. The key to DevOps quality assurance lies in automated test suites that scrutinize each code change before it is deployed into production. These give rise to an emerging research field named "zero-touch testing": enable a system to decide for itself what, when, where, and how testing should be performed. The Basecamp Zero project aims to advance the state-of-the-art towards the dream of fully autonomous (= "zero-touch") software testing. The project will build upon recent advances in test generation and test amplification to enrich them in the context of a cloud-native application. An advisory board consisting of ten representative industrial partners will oversee the application potential. The tool prototypes resulting from the Basecamp Zero project will first be tested on a carefully selected suite of open source systems (TRL 3). Promising results will be further explored with the DevOps teams part of the advisory board via realistic pilot-cases (TRL 4). Dissemination activities will solicit follow-up projects with industrial partners in Flanders and Europe. Tool licensing (possibly exploited by means of a spin-off company) is a long term potential avenue for valorisation.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Nexor - Cyber-Physical Systems for the Industry 4.0 era
Abstract
The fourth industrial revolution (Industry 4.0 as it is commonly referred to) is driven by extreme digitalization, enabled by tremendous computing capacity, smart collaborating machines and wireless computer networks. In the last six years, Nexor — a multi-disciplinary research consortium blending expertise from four Antwerp research labs — has built up a solid track record therein. We are currently strengthening the consortium in order to establish our position in the European eco-system. This project proposal specifies our 2021 - 2026 roadmap, with the explicit aim to empower industrial partners to tackle their industry 4.0 challenges. We follow a demand driven approach, convincing industrial partners to pick up our innovative research ideas, either by means of joint research projects (TRL 5—7) or via technology licenses.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Challenger Moharram
- Co-promoter: Chevalier Amélie
- Co-promoter: Daems Walter
- Co-promoter: De Meulenaere Paul
- Co-promoter: Denil Joachim
- Co-promoter: Derammelaere Stijn
- Co-promoter: Minnaert Ben
- Co-promoter: Peremans Herbert
- Co-promoter: Perez Guillermo Alberto
- Co-promoter: Steckel Jan
- Co-promoter: Vangheluwe Hans
- Co-promoter: Vanlanduit Steve
- Co-promoter: Verlinden Jouke Casper
- Fellow: Bozyigit Fatma
- Fellow: De Mey Fons
Research team(s)
Project website
Project type(s)
- Research Project
Dotation for the structural collaboration with Flanders Make.
Abstract
Flanders Make's mission is to strengthen the international competitiveness of the Flemish manufacturing industry on the long term through industry-driven, precompetitive, excellent research in the field of mechatronics, product development methods and advanced production technologies and by maximizing valorisation in these areas.Researcher(s)
- Promoter: Challenger Moharram
- Co-promoter: Daems Walter
- Co-promoter: De Meulenaere Paul
- Co-promoter: Demeyer Serge
- Co-promoter: Denil Joachim
- Co-promoter: Derammelaere Stijn
- Co-promoter: Perez Guillermo Alberto
- Co-promoter: Steckel Jan
- Co-promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
Past projects
Software Product Line Testing with Transition Models.
Abstract
In software product lines, ensuring the correct behavior of each deployable configuration is becoming increasingly important, but this is often impractical in real-world environments. The primary challenge is scalability: building separate behavioral models for model-based verification for a vast number of configurations is infeasible, and sampling approaches may overlook faults that occur only in specific configurations. To resolve this, we propose a unified "Model Once, Generate Any" event-based approach that captures product family behavior in a single structure, allowing for the automatic derivation of executable test suites for any valid configuration. This approach decouples test coverage from modeling costs, enabling rigorous behavioral verification across diverse domains, as demonstrated on large-scale industrial systems, including Tesla's web configurator and Siemens Healthineers' syngo.via.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Advancing MUT4SLX: Towards Industrial Adoption of Mutation Testing for Simulink Models.
Abstract
Mutation testing is a recommended practice in industrial standards for functional safety, such as ISO 26262 and IEC 61508, which are common in model-based embedded system development. The main purpose of mutation testing is to diagnose and treat weaknesses in software test suites typically encoded in textual programming languages like C++. This method intentionally injects faults (mutants) into the code or model and measures how many are detected by the test suite, producing a mutant score that reflects the suite's quality. MUT4SLX is the first tool that supports mutant generation and execution for the graphical modelling languages Simulink and Stateflow. It is a proof-of-concept tool developed in close collaboration with an industrial partner as a deliverable of a Flanders Make project. MUT4SLX's unique selling proposition (USP) stems from its customisable mutation operators, which are modelled after realistic faults mined from an industrial bug database. These mutation operators can be expanded and adapted to new partners' needs. The Proof-of-Concept project proposed here aims to prepare MUT4SLX for industrial adoption by incorporating (i) requirement traceability and (ii) integration in DevOps pipelines. Based on feedback from our partners, we identified those two features as necessary preconditions for industrial adoption. After completing this POC-DEVELOP project, we plan to apply for a VLAIO Innovation mandate to establish a SPIN-OFF company. These are needed to deploy MUT4SLX in our target market, which includes safety-critical software-intensive systems where Simulink and Stateflow are commonly used (automotive, aerospace, railway, robotics, and energy industries). During the project, we will validate MUT4SLX with three potential users (a letter of intent is provided in the appendix) to increase the technology readiness level to 5 (validated in the relevant environment) and the commercial readiness level to 4 (value proposition). Our team currently consists of one chief technology officer (Onur Kilincceker), two software developers (Halim Ceylan and Remzi Bulutlu), and two senior persons (Serge Demeyer and Fatma Bozyigit) on the advisory board.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Kilincceker Onur
Research team(s)
Project type(s)
- Research Project
Modularization of modeling and simulation languages and their tools through explicit modeling of language fragments.
Abstract
Cyber-Physical Systems (CPSs) are engineered systems of interacting computational and physical processes. Their engineering typically involves collaboration between multiple stakeholders from different domains, leading to complex concurrent workflows. The ever-increasing complexity of CPSs (more functionality, stricter energy, cost, safety requirements) is currently addressed by modeling and simulation. Modeling and simulation tools used in industry today are developed in a code-centric manner. This makes it impossible to reason at a higher level about complex, yet recurring features, such as the embedding of languages, debugging and live modeling. As a result, the implementation of such features becomes increasingly difficult, as they continue to evolve and combine legacy code. Central to this proposal is the Multi-Paradigm Modeling (MPM) approach, which advocates explicit modeling of all aspects of not only the system being engineered, but also of expected engineering workflows and, most importantly, of the modeling languages themselves. I want to advance MPM by enabling modularity of modelling languages, through the creation of a language fragment language and composition operators, for syntax and semantics. This will allow synthesis of modelling environments for new (e.g. hybrid) modelling languages, as well as de- and re-construction of existing languages.Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Exelmans Joeri
Research team(s)
Project type(s)
- Research Project
Automatic assisted design for assembly (AssistedDfA_icon).
Abstract
The design of mechanical assembly products has become a complex task in which design engineers have to rely on Computer Aided Design, software to correctly assess pricing and performance of their product. However, unlike performance and cost, assembly-related knowledge is hard to formalize and current commercial CAD tools do not provide adequate support to evaluate assemblability in an accurate and company specific way. This means companies still have to rely on iterative interactions between the designers and assembly experts, during which the assemblability of a product is evaluated manually based on check lists and expert knowledge. Due to this iterative process, assembly issues in the design result in an increased development cost and time, which is detrimental for company competitiveness. This problem is especially relevant with the ever-increasing complexity of assembly products and the current tendency of mixing human operators and collaborative robots (cobots) in the assembly processes, in which design flaws become more likely, further emphasizing the need for supporting tools. The goal of the project is to substantially reduce the time to market and development cost of mechanical assembly products by incorporating automated assemblability evaluation in the early stages of product design. This goal will be achieved by investigating and implementing algorithmic methods capable of interact with the designer by means of CAD software and 3D visualization tools. By allowing the designer to evaluate the assemblability in the early stages, the number of design re-iterations will be strongly reduced. AnSyMo Group (MICSS Lab) in Department of Computer Science, University of Antwerp is responsible for work package 2. The goal of this work package is to address the lack of a standardized model to capture assembly knowledge by developing a framework and methodology to formalize assembly information into a knowledge-base. AnSyMo and CodesignS will collect requirements from the manufacturing partners (Daikin, Voxdale, Alberts and Siemens) with the aim to extend the meta-model developed in the PACo SBO project to enable the formalization of assembly knowledge across the three levels of the technical strategy. Additionally, AnSyMo will develop a programmatic interface (API) to make the knowledge-base accessible from within a CAD environment and provide a Domain-specific Language (DSL) to define custom DfA rules programmatically (via the API).Researcher(s)
- Promoter: Challenger Moharram
Research team(s)
Project type(s)
- Research Project
Efficient testing of control software (EFFECTS_ICON).
Abstract
The time and effort in the verification & validation of control software drastically increases, especially in the later stages. Many bugs are found late in the development lifecycle, companies face a high-level of regression, huge time losses for root-cause analysis, bug fixes, and retesting. As a result companies miss important time-to-market deadlines. The solution is well known: companies need to adopt the "shift left" ideology and frontload testing earlier in the development cycle where tests are easier to automate. While the benefits are well described, and many automation tools are available, companies fail to transition to a "shift left" test approach. To solve this, the EFFECTS projects aims to develop a holistic transition approach that works on two fronts, (i) a reduction of the current effort spent on testing to allow additional testing at earlier development phases, (ii) efficient creation of new tests well targeted to identified weak spots. The resulting framework will allow companies to smoothly transition to a "shift-left" test strategy.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Smart Port 2025: improving and accelerating the operational efficiency of a harbour eco-system through the application of intelligent technologies.
Abstract
The Smart Port COOCK-project aims to improve operational efficiency in a harbour context, through the application of intelligent techniques. The project is mainly aimed at SMEs, but also at large corportations. Together, they form the value-chain of the harbour. The digital maturity of these actors will be increased by model (and "digital twins") and data-driven digitization. The project brings together both technology users and providers/integratorsResearcher(s)
- Promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
SATIMAIR, SATellite IMage analysis for AIR quality on ships: an exploratory investigation.
Abstract
Sensor-based measuring campaigns in the accommodations of ships are able to identify numerous events. Unfortunately, the data do not contain enough information to identify the cause of these events. Some of the causes must be found in the immediate surroundings of the ship. Examples of such external causes are the ship entering a harbour where the air quality is worse, an inland ship passing by a factory that is emitting pollution, or a cue of ships that is waiting in front or inside a lock while all the engines are running. A huge amount of open data is generated by the satellites of the Copernicus-program. They can be used to analyse the surroundings of a ship along its journey and to find explanations for the events that are detected by air quality measuring campaigns performed inside the accommodations of ships.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Curriculum Development - Technical English for SPARK's Jobs & Perspectives Program with universities Iraq.
Abstract
As part of a development program for a renewed computer science curriculum in two universities in Iran we jointly develop a project centric approach towards introductory programming. We use python as development langiuage and state of the art tooling.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Collaborative Design Facility (CDF-Infra).
Abstract
With the evolution towards smart, interconnected products and production systems, the design of physical systems becomes more complex. Traditionally, the design process is rather sequential: engineers from different domains work on their own specific challenges and results are passed to the next group in the development process. This often leads to lengthy iterations. To solve this, companies are shifting to concurrent and multidisciplinary collaboration where engineers from different disciplines work in parallel on the same design. The organization and management of this concurrent process, without suitable HW and SW infrastructure support, requires time and resources which are drawn away from the core engineering tasks. The complexity increases further when the engineers are distributed across multiple locations and/or when different companies (OEMs, Tier1, …) are involved in the collaboration. The facility developed in this project will support collaborative model-based design.Researcher(s)
- Promoter: Vangheluwe Hans
- Co-promoter: Denil Joachim
Research team(s)
Project type(s)
- Research Project
Framework for systematic design of digital twins (DTDesign).
Abstract
This project aims at developing a framework, comprising a methodology and supporting tools, for the systematic and efficient design of Digital Twins providing answers to two question types: (i) production parameters - product performance correlation and (ii) faults detection and diagnosis. The purpose of the framework is to support the user in choosing which data sets and models to combine and how to deploy them (Digital Twin implementation) to get an answer to the posed questions based on application specific requirements and criteria. The final goal is to use the developed framework to efficiently design Digital Twins and implement them for seven industrial use cases.Researcher(s)
- Promoter: Vangheluwe Hans
- Co-promoter: De Meulenaere Paul
- Co-promoter: Denil Joachim
Research team(s)
Project type(s)
- Research Project
SAILor: Safe Artificial Intelligence and Learning for Verification.
Abstract
Reactive synthesis is the act of automatically implementing a reactive system from a given formal specification so as to guarantee correctness by construction. It is especially useful when the desired system is safety critical, e.g. embedded controllers used in cars and ai lanes. Unfortunately, reactive synthesis is computationally hard and current synthesis tools are still not efficient enough to be used in practically relevant applications. Furthermore, systems obtained in this fashion tend to be overly pessimistic: since they must be correct regardless of what their environment does, they consider the environment to be fully antagonistic. This abstraction of reality is often too conservative. Recently, there has been a boom in the number of efficient artificial intelligence techniques applied to problems which are (theoretically) hard or even undecidable, while usually no formal correctness guarantees are given. These shortcomings raise the following question: Can we leverage machine learning techniques to implement better, more efficient synthesis tools? We propose to answer this question in two steps. First, we will study learning algorithms with formal correctness guarantees as well as the assumptions under which these guarantees are valid. Second, we will implement those algorithms and compare them against each other and the state-of-the-art synthesis tools based on automata and logic.Researcher(s)
- Promoter: Perez Guillermo Alberto
Research team(s)
Project type(s)
- Research Project
CAST: Counter-Automata Algorithms for Software Verification Tools.
Abstract
Formal verification of reactive systems is an increasingly important research area of computer science. Modern systems now include features which make their design difficult and verifying their correctness very demanding. Companies such as Facebook and Amazon have teams dedicated to formally verifying their systems while, in academia, works on verification have already been lauded with two Turing awards in the last twenty years. As systems become more complex, more intricate models are required in order to capture their behaviour. Counter automata result from adding integer-valued counters to the widely studied model of finite automata. The formal verification community has found several uses for different classes of counter automata. This project aims at (i) contributing to the theory of automatic software verification --- in particular, model checking various classes of one-counter automata, (ii) translating those model-checking algorithms into semi-decision procedures implementable in existing interactive software verification tools, and (iii) guiding the development of the theory based on the limitations and capabilities of such tools.Researcher(s)
- Promoter: Perez Guillermo Alberto
- Fellow: Leys Tim
Research team(s)
Project type(s)
- Research Project
Meaningful and scaleable reuse and composition of models, with frames.
Abstract
The engineered systems , such as autonomous self-driving vehicles, that we (want to) design and build, are characterized by an ever increasing complexity , offering ever more advanced functionality and comfort. At the same time, the demands on energy efficiency and cost, but also on safety and reliability of those systems, become more stringent, in a quest for some form of optimal, fit-for-purpose designs. Furthermore, in a circular economy, we wish to take into account not only the product, but an ecosystem, spanning entire families of related products, over their entire life-cycle, including production, maintenance, and recycling. The fact that such advanced systems can be built today is largely thanks to the ubiquitous use of models . Models, encoding (for reuse) our knowledge about various aspects of a system or system component, can namely be used for "virtual experimentation" : to perform computer simulations to answer "what if" questions. Such questions allow us to explore different design alternatives. It is this capability that is fueling the fourth industrial revolution. Models in complex engineered systems vary widely in nature and purpose. They may describe structure and behaviour of systems in different domains such as mechanical, electrical, software, and networks, or different views on the systems such as the stability/control view, the safety view, and the cost/efficiency view, at different levels of abstraction/detail/fidelity. They may also be used to describe and even prescribe (for automation purposes) the complex, concurrent development processes. Process models can be used for "what if" analysis of the engineering processes themselves, leading not only to optimal products, but also to optimal time-to-market. When "what if" analysis is automated , exploring billions of alternatives efficiently in a computer, reaching optimal products/production designs can be accelerated, taking a matter of days or weeks on a cloud computing infrastructure as opposed to the decades required for organic convergence over generations of human engineering improvements. Engineering is however hitting a wall, keeping us from a truly exponential leap in complex systems development . Though advanced computer support exists in the form of modelling languages, model management tools, simulators, etc. for "what if" analysis, managing the meaningful and correct (re)use of models is still a mostly human enterprise, for which no rigorous foundations nor advanced tooling exist. Being constrained by human capabilities, it is costly, slow, and error prone. In some important, yet restricted, areas such as Electronic Design Automation, such foundations and tooling do exist (and fuel a thriving billion $ market). For truly complex, multi-domain systems, knowledge is scattered, often either in experts' minds, or in the best case in text documents and spreadsheets. In this project, we propose to develop a foundational framework as well as prototype tooling for the computer-assisted/automated meaningful (re)use of models . The key to our approach is that we will "eat our own dog food" : we will now apply advanced modelling language engineering, model transformation, property specification, modelling and simulation techniques we have helped develop over the last decades, to explicitly model and reason about the context in which models can be meaningfully (re)used. We call such models "frames" after the original, but incomplete "experimental frames" idea proposed by Bernard Zeigler in the 1980s. Concretely, we will start by using our experience with the modelling language Modelica (for physical systems) and DEVS (for discrete-event modelling of software and networks) to develop the theoretical foundations and application of frames, initially on a representative autonomous vehicle case .Researcher(s)
- Promoter: Vangheluwe Hans
- Co-promoter: Denil Joachim
Research team(s)
Project type(s)
- Research Project
Mutation testing: fewer, smarter and faster.
Abstract
Software updates are omnipresent in today's society and every year ICT companies release faster. Tesla for example loads new software in its cars once every month; amazon goes even faster and pushes changes to its servers every 12 seconds! With such fast release cycles the need for effective quality gates is rising: software teams must take all possible steps to prevent that defects slip into production. In this project proposal we will investigate three different ways to improve mutation testing, which is the state of the art technique to verify the fault detection capacity of a test suite. We will pursue three different angles for improvement (fewer, smarter, and faster) to make mutation testing effective, even with such rapid release cycles.Researcher(s)
- Promoter: Demeyer Serge
- Fellow: Vercammen Sten
Research team(s)
Project website
Project type(s)
- Research Project
Next level mutation testing: fewer, smarter & faster (NEXT-O-TEST).
Abstract
Software-updates are omnipresent in today's digital era and the release cycles within ICT companies are getting faster and faster. Tesla for example loads new software in its cars once every month; Amazon goes even faster and pushes changes to its servers every 12 seconds! With such fast release cycles the need for effective quality assurance is rising: software teams must take all possible steps to prevent defects from slipping into production. Today, mutation testing is the state-of-the-art technique to fully automatically assess the fault detection capacity of a software test suite. The approach is too slow for industrial adoption however. Therefore, the NEXT–O–TEST project will investigate three different ways to improve upon the state-of-the-art (fewer, smarter, and faster) to make mutation testing effective even in the presence of rapid release cycles. As such, NEXT–O–TEST will allow the NEXOR Consortium to strengthen its expertise on "quality control and test automation" and reinforce its position as a core lab within the Flanders Make research centre.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Proof of concept for a decision support system to reduce the occupational risks of seafarers due to air quality.
Abstract
This project aims to explore the basic principles of a decision support system that allows the continuous monitoring of the working conditions of seafarers. For this purpose, it wants to (1) measure several environmental parameters simultaneously (e.g., temperature, light, NO2, O3, etc.), (2) convert the measurements into a global air quality, and (3) visualize the evolution in air quality so that seafarers can easily evaluate the working conditions. The system will be tested on a real-life case study.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Storme Patrick
Research team(s)
Project type(s)
- Research Project
Automated Assistance for Developing Software in Ecosystems of the Future (SECO-ASSIST).
Abstract
Software ecosystems are the most promising avenue for organising the software needs of the digital era. Jointly funded by F.R.S.-FNRS and FWO-Vlaanderen, the four-year Excellence of Science Project SECO-ASSIST aims to realise a scientific breakthrough to nurture the ecosystems of the future, by providing novel software recommendation techniques that address the resilience, evolvability, heterogeneity, and social interaction. To achieve this the project partners will combine their expertise in social networks (UMONS), software testing (¶¶Òõ¶ÌÊÓƵ), software reuse (VUB) and database evolution (UNamur).Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project website
Project type(s)
- Research Project
Mutation testing: fewer, smarter and faster.
Abstract
Software updates are omnipresent in today's society and every year ICT companies release faster. Tesla for example loads new software in its cars once every month; amazon goes even faster and pushes changes to its servers every 12 seconds! With such fast release cycles the need for effective quality gates is rising: software teams must take all possible steps to prevent that defects slip into production. In this project we will investigate three different ways to improve mutation testing, which is the state of the art technique to verify the fault detection capacity of a test suite. We will pursue three different angles for improvement (fewer, smarter, and faster) to make mutation testing effective, even with such rapid release cycles.Researcher(s)
- Promoter: Demeyer Serge
- Fellow: Vercammen Sten
Research team(s)
Project type(s)
- Research Project
EMPHYSIS - Embedded systems with physical model in the production code software.
Abstract
The major goal of the project is to enhance production code of embedded control systems in automotive vehicles in order to improve the performance of the underlying system: faster and safer operation, reduced energy consumption, reduced emission and reduced maintenance costs. Additionally, cost and time for the software development of these embedded systems shall be reduced. This is achieved by providing physics-based models from modelling and simulation tools in an automated and standardized way on electronic control units (ECU). By this approach physical models predicting the behaviour of the whole operating region of the target system are used in observers/virtual sensors, model-based diagnosis, or in advanced control algorithms (e.g., inverse models, non-linear dynamic inversion, model-predictive control) on ECUs to achieve significantly better vehicle performance.Researcher(s)
- Promoter: Denil Joachim
- Co-promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
BOF Sabbatical Leave- Prof. Demeyer.
Abstract
During this sabbatical leave Prof. Serge Demeyer will test two algorithms under development in his research lab under realistic circumstances. He wil use the unique constellation available in the host institution in Sweden: a combination of data, infrastructure, research methods and industrial contacts. This projects prepares the nest step in his research concerning test automation: from TRL4 (technology validated in lab) naar TRL5 (technology validated in relevant environment). This step is critical for the continuing growth of the NEXOR IOF consortium en will ultimately contribute to the European Research theme "Industry 4.0".Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project website
Project type(s)
- Research Project
A Multi-Paradigm Modeling Foundation for Collaborative Multi-view Model/System Development.
Abstract
The complexity of current engineered systems has increased drastically over the last decades. The heterogeneity and the complex interplay between physical, software, and network components requires modeling these systems before they are built. These many models must be kept consistent, especially when multiple modelers collaborate on the development of a single system. Inconsistencies arise due to the semantic overlaps between elements in various models. By investigating inconsistencies at a high level of abstraction, it soon becomes clear that they are due to the complexity of the design processes. Humans can no longer comprehend the many relationships between models and their elements. The aim of this PhD project is to identify the causes of inconsistencies in the design of complex heterogeneous systems; to propose the most appropriate analysis and resolution techniques for detecting and fixing inconsistencies, respectively; and finally, to enable the (quantitative or qualitative) assessment of the consequences of applying one resolution technique or another. The work is validated, in collaboration with Flanders Make researchers, using an industrial case study of an "Automated Guided Vehicle" (AGV).Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: David Istvan
Research team(s)
Project website
Project type(s)
- Research Project
Efficient Controller Software Variant Development and Validation (ECoVaDeVa_ICON).
Abstract
Challenge Companies that design and manufacture products face an increasing market demand for small series of customised products, resulting in a huge variability of the product portfolio and especially of the embedded controller software. Today, the development and validation of these controller software variants require a lot of manual effort. This results in long "time-to-market" cycles whenever a new variant is created and, in turn, to some reluctance to bring new product variants to the market, thereby missing business opportunities. Project goals This project aims at providing software product line methods, techniques and tools for the development of mechatronic software controller variants in view of significantly reducing the required development and validation time of new variants. More specifically, the project goals are as follows: For the development and validation of variants that can be built by selecting, combining and configuring existing software components, this project will deliver: 1.The necessary configuration tools to enable application engineers to build and validate industrial-size mechatronic software variants without requiring detailed knowledge of the software, plant and test architectures and of the modelling tools used by the different disciplines. 2.A methodology and toolbox that mechatronic companies can use to set up their mechatronic variant development and validation process, taking into account the specific requirements of each company. For the development and validation of variants that require modifications or additions to the various models involved in the development and validation of new variants, this project will create a prototype of a configurable inconsistency detection tool than can be customised by the different companies for their particular variant design process and tools. This tool allows to detect inconsistencies early in the development stage.Researcher(s)
- Promoter: Vangheluwe Hans
Research team(s)
Project website
Project type(s)
- Research Project
A scaleable foundation for multi-paradigm modelling.
Abstract
This research aims to build a foundation for Multi-Paradigm Modelling in the form of the ModelVerse, a conceptual framework and a repository of multi-paradigm models. This forms the basis for distributed, collaborative modelling of systems as well as of the modelling languages used. To explicitly model modelling languages, their concrete and abstract syntax needs to be modelled (the latter in the form of meta-models), as well as their semantics. For semantics, either an interpreter/simulator needs to be provided or a mapping (transformation) to an already known formalism needs to be specified. The ModelVerse supports model manipulations such as documentation, analysis, simulation, (software) synthesis and evolution. All are based on model transformation. This project is funded by the Fonds Wetenschappelijk Onderzoek - Vlaanderen (FWO).Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Van Tendeloo Yentl
Research team(s)
Project type(s)
- Research Project
Optimising continuous delivery for small software teams.
Abstract
Continuous delivery is the production process currently in use within Facebook and Google, notorious for its ultra-fast yet ultra reliable release cycle. On the surface, continuous delivery is an ideal solution for small technology companies, since it allows them to rapidly respond to specialized needs of demanding customers. However, the particular nature of small software teams raises a few challenges, which we seek to address by advanced tooling infrastructure (i.e. change-based mutation testing, penetration testing).Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
ITEA 15010 REVAMP2: Reverse engineering and variability management platform and process.
Abstract
This project aims to construct the ReVAMP2 Tool Chain, a round-trip engineering platform with tool support for extracting features from existing assets. This tool chain will be supported by guidelines and lessons learned drawn from cases coming from a multitude of industry domains.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Foundations for Co-Simulation.
Abstract
The engineered systems of today are characterized by an ever increasing complexity. This complexity is often due, not only to a large number of compontents, but above all to heterogeneity of their components. To deal with this heterogeneity, and with the need to protect Intellectual Property (IP) of the authors of the components, co-simulation proposes to not expose the models inside components, but rather to orchestrate their simulation, using the minimal information necessary from the components to guarantee overall correct simulation. This thesis will work on the following problems: 1. To ensure correctness of the developed co-simulation protocols, automata models (for example, in UPPAAL) will be built of these protocols which are amenable to model checking. 2. The further development of the Functional Mockup Interface (FMI) co-simulation standard by investigating exactly what information needs to be exposed to allow for correct and efficient co-simulation. Both the mapping onto know formalisms (such as DEVS) and semantic adaptation will be investigated. The relationship with the High-Level Architecture (HLA) for distributed discrete-event simulation will be investigated. This, and the link with DEVS may lead to new features such as hierarchical co-simulation. 3. The briding of the continuous-discrete gap. This is an issue in so-called hybrid models, where continuous-time models such as differential equations are combined with discrete-time or discrete-event models. These typically result from the modelling of a physical system in its interaction with a software controller and possibly a network. In hybrid models, numerical approximations are made when discretizing continuous models to make them computable on digital devices. Furthermore, modelling constructs and techniques allowing state-event location are necessary. In this research, the primitives for modelling and co-simulation of hybrid models will be investitgated.Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Gonçalves Gomes Claudio
Research team(s)
Project website
Project type(s)
- Research Project
Next generation of heterogeneous sensor networks (NEXOR).
Abstract
This project represents a research contract awarded by the University of Antwerp. The supervisor provides the Antwerp University research mentioned in the title of the project under the conditions stipulated by the university.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Blondia Chris
- Co-promoter: De Meulenaere Paul
- Co-promoter: Hellinckx Peter
- Co-promoter: Latré Steven
- Co-promoter: Peremans Herbert
- Co-promoter: Steckel Jan
- Co-promoter: Steenackers Gunther
- Co-promoter: Vangheluwe Hans
- Co-promoter: Vanlanduit Steve
- Co-promoter: Weyn Maarten
- Fellow: De Mey Fons
- Fellow: Hristoskova Anna
Research team(s)
Project type(s)
- Research Project
Multi-Paradigm Modelling for Cyber-Physical Systems (MPM4CPS).
Abstract
The main objective of the action is to enhance the quality, visibility and impact of Europeanresearch and industrial adoption in the transdisciplinary area of Cyber-Physical Systems (CPS) by unification through Multi-Paradigm Modelling.Researcher(s)
- Promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
A scaleable foundation for multi-paradigm modelling.
Abstract
This research aims to build a foundation for Multi-Paradigm Modelling in the form of the ModelVerse, a conceptual framework and a repository of multi-paradigm models. This forms the basis for distributed, collaborative modelling of systems as well as of the modelling languages used. To explicitly model modelling languages, their concrete and abstract syntax needs to be modelled (the latter in the form of meta-models), as well as their semantics. For semantics, either an interpreter/simulator needs to be provided or a mapping (transformation) to an already known formalism needs to be specified. The ModelVerse supports model manipulations such as documentation, analysis, simulation, (software) synthesis and evolution. All are based on model transformation. This project is funded by the Fonds Wetenschappelijk Onderzoek - Vlaanderen (FWO).Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Van Tendeloo Yentl
Research team(s)
Project website
Project type(s)
- Research Project
Dotation for the structural collaboration with Flanders Make.
Abstract
Flanders Make's mission is to strengthen the international competitiveness of the Flemish manufacturing industry on the long term through industry-driven, precompetitive, excellent research in the field of mechatronics, product development methods and advanced production technologies and by maximizing valorisation in these areas.Researcher(s)
- Promoter: Vangheluwe Hans
- Co-promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
MBSE4 Mechatronics.
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
Explicit modelling of model debugging and experimentation
Abstract
The Modelling and Simulation (M&S) approach to systems design can only be successful if the modeller (often a domain expert, such as an automotive engineer) has access to advanced tools which enable the creation of models and provide the necessary framework for performing simulation and deployment of models onto hardware. The environment should allow the modeller to have sufficient control over the simulation execution. During this project, I will transpose current best-practices in code debugging to the M&S world and explicitly model simulation environments for a number of distinct modelling formalisms, as well as for their combinations. This will result in a number of prototype implementations, which I will validate using industrial case studies.Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Van Mierlo Simon
Research team(s)
Project website
Project type(s)
- Research Project
Air Identification Registration for Cultural Heritage: Enhancing Climate Quality (AIRCHECQ).
Abstract
This project represents a formal research agreement between UA and on the other hand the Federal Public Service. UA provides the Federal Public Service research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Testing of rule-based model transformations.
Abstract
The research objectives of this project are threefold: (1) to formalize model transformation requirements, (2) to automatically generate a set of input test models for a rule-based transformation, capable of revealing errors in a transformation and (3) to develop a novel oracle function, to test the implementation of a model transformation specification.Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Van Mierlo Simon
Research team(s)
Project website
Project type(s)
- Research Project
Change-centric Quality Assurance (Cha-Q) (Changes as First Class Citizens during Software Development).
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Concurrency in a machine model supporting multidimensional separation of concerns.
Abstract
This project aims to explore concurrency features within the research area of languages that support "multidimensional separation of concerns" (MDSOC), such as aspect-, context- or feature-oriented languages. The addition of MDSOC mechanisms that take into account concurrency will result in MDSOC languages being more expressive and potentially having better performance, which in turn make MDSOC languages a more attractive means to develop concurrent applications. Examples of such mechanisms include: the cflow pointcut, thread-local crosscutting modules and concurrent crosscutting modules. In order to provide a clear and elegant description of these mechanisms, a formal operational semantics is required. Instead of providing this semantics at the language level, an extended version of a virtual machine model called delMDSOC will be used, the semantics of which is specified in the form of graph rewrite rules. This model serves as a platform for a wide range of MDSOC languages. In this project, the semantics of different types of MDSOC languages, having different concurrency models, will be provided using the same extended delMDSOC virtual machine. Hence, it becomes possible to compare the differences and similarities in the added MDSOC mechanisms between different languages.Researcher(s)
- Promoter: Janssens Dirk
- Fellow: Molderez Tim
Research team(s)
Project type(s)
- Research Project
Optimization and parallellisation of real-time media processing on embedded systems by abstraction of software-and hardwarebehaviour.
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Temmerman Marijn
- Fellow: Mercelis Siegfried
Research team(s)
Project type(s)
- Research Project
¶¶Òõ¶ÌÊÓƵ of the interaction between automotive software and its environment by means of modeling and co-simulation.
Abstract
During the development of software-intensive systems, such as automative applications, simulation is required to test models and assumptions during each phase of the development process. This project investigates techniques to support efficient and correct co-simulation of model components. This focus is on the co-simulation of the software and its environment.Researcher(s)
- Promoter: Vangheluwe Hans
- Co-promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Impact analysis of software maintenance using software traceability.
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Demeyer Serge
- Fellow: Lamkanfi Ahmed
Research team(s)
Project type(s)
- Research Project
Concurrency in a machine model supporting multi-dimensional separation of concerns.
Abstract
This project aims to explore concurrency features within the research area of languages that support "multidimensional separation of concerns" (MDSOC), such as aspect-, context- or feature-oriented languages. The addition of MDSOC mechanisms that take into account concurrency will result in MDSOC languages being more expressive and potentially having better performance, which in turn make MDSOC languages a more attractive means to develop concurrent applications. Examples of such mechanisms include: the cflow pointcut, thread-local crosscutting modules and concurrent crosscutting modules. In order to provide a clear and elegant description of these mechanisms, a formal operational semantics is required. Instead of providing this semantics at the language level, an extended version of a virtual machine model called delMDSOC will be used, the semantics of which is specified in the form of graph rewrite rules. This model serves as a platform for a wide range of MDSOC languages. In this project, the semantics of different types of MDSOC languages, having different concurrency models, will be provided using the same extended delMDSOC virtual machine. Hence, it becomes possible to compare the differences and similarities in the added MDSOC mechanisms between different languages.Researcher(s)
- Promoter: Janssens Dirk
- Fellow: Molderez Tim
Research team(s)
Project type(s)
- Research Project
Impact analysis of software maintenance using software traceability.
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Demeyer Serge
- Fellow: Lamkanfi Ahmed
Research team(s)
Project type(s)
- Research Project
Evolution of Modelling Languages.
Abstract
In model-driven engineering, evolution is inevitable over the course of the complete life cycle of complex software-intensive systems and more importantly of entire product families. Not only instance models, but also entire modelling languages are subject to change. This is in particular true for domain-specific languages. Up to this day, modelling languages are evolved manually, with tedious and error-prone migration of artifacts such as instance models as a result. In this project, the different evolution scenarios for various kinds of modelling artifacts, such as instance models, meta-models and transformation models are researched. Subsequently, evolution is de-composed into four primitive scenarios such that all possible evolutions can be covered. This structured approach enables the design of solution for (semi-)automatic modelling language evolution.Researcher(s)
- Promoter: Vangheluwe Hans
- Fellow: Meyers Bart
Research team(s)
Project type(s)
- Research Project
Sources guidelines for critical embedded systems (KriCode).
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Refactoring in languages supporting multi-dimensional separation of concerns.
Abstract
This project aims to study refactoring for languages with support for "multi-dimensional separation of concerns" (MDSoC), such as aspect-oriented and context-oriented languages. MDSoC languages offer powerful constructions that provide a better way to divide software into a set of different concerns, making it easier to develop and maintain software.Researcher(s)
- Promoter: Janssens Dirk
- Fellow: Molderez Tim
Research team(s)
Project type(s)
- Research Project
Scientific mission on Mining Software Repositories at the University of Zurich.
¶¶Òõ¶ÌÊÓƵ of the technical impact of the AUTOSAR-standards on automotive software.
Abstract
In the area of automotive electronics, software is becoming increasingly more prominent. The AUTOSAR consortium aims to consolidate this, but the technical impact of their standards is not sufficiently known. Therefore, we will investigate the technical footprint of these standards. This will lead to a more efficient use of performance and memory in automotive embedded systems.Researcher(s)
- Promoter: Demeyer Serge
- Co-principal investigator: Catthoor Raf
- Fellow: Denil Joachim
Research team(s)
Project type(s)
- Research Project
Transforming Human Interface Designs via Model Driven Engineering.
Abstract
This research project is centred around three research questions: -Formal Semantics. What is the best way to formalise the semantics of a task modelling notation such as ConcurTaskTrees? -Correctness. Based on the formal semantics, can we prove the correctness of task model transformations? -Quality Properties. Can we identify and prove useful properties regarding these transformations?Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Janssens Dirk
Research team(s)
Project type(s)
- Research Project
Optimized MP-SoC Middleware for Event-driven Applications (OPTIMMA).
Abstract
The OptiMMA projects will enable the mapping of emerging, dynamic software applications on complex Multi-Processor Systems-on-Chip (MP-SoC). This will be achieved through the use of Middleware components, which will be able to mediate between embedded software and the hardware platforms. Thus, the manage -at run-tim- the memory storage, energy consumption, bandwidth and computation resources of the embedded system. Modeling and customization of the Middleware components is a key element of the OptiMMA project. It will creatie a broad user base and enable the valorization of the results among a wide body of economic actors in Flanders, including economic actors that specialize in multimedia and telecommunication applications on mobile devices, medical imaging devices, embedded software design, hardware platforms design, design tools, etc.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Janssens Dirk
Research team(s)
Project type(s)
- Research Project
From specific targeting to a generic target platform (VOLGES).
Fundamentele belangen in Software Engineering: Modelleren, Verifiërene en Evolueren van Software. (MoVES)
Abstract
Software-intensive systems are among the most complex artefacts ever built. In the development of such systems, the use of rigorous models and analysis methods is essential to make sure that the software satisfies its requirements and exhibits the desired properties (e.g., safety, security, reliability, consistency). At the same time, in order to adapt to the constantly changing requirements and technology, these systems must be able to evolve over time, without breaking their essential properties. This project combines the leading Belgian research teams in software engineering, with recognised scientific excellence in model-driven engineering (MDE), software evolution, formal modelling and verification (FMV) and aspect-oriented software development (AOSD). The project aims to advance the state of the art in each of these domains. The long term objective of our network is to strengthen existing collaborations and forge new links between those teams, and to leverage and disseminate our research expertise in this domain at a European level.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Janssens Dirk
- Co-promoter: Paredaens Jan
Research team(s)
Project type(s)
- Research Project
"Separation of Concerns" with High Level Software Models.
Abstract
Researcher(s)
- Promoter: Janssens Dirk
- Co-promoter: Demeyer Serge
- Fellow: Schippers Hans
Research team(s)
Project type(s)
- Research Project
Chair "Migration to Service Oriented Architectures".
Abstract
This project aims to exchange knowledge and experience concerning the migration towards service-oriented architectures. This project will result in a handbook documenting the experiences and a series of about 8 lectures organized by the University of Antwerp and the KBC-ICT.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Guidelines for Improving the Testprocess During Software Maintenance.
Abstract
The goal of this project is to develop an efficient process for the maintenance of software tests, where a given set of known problems in the test code (so called "test smells) will be tackled by means of test maintenance patterns. The primary scenario driving this research is the selective improvement of a particular piece of test code before implementing a change request.Researcher(s)
- Promoter: Demeyer Serge
- Fellow: Van Rompaey Bart
Research team(s)
Project type(s)
- Research Project
ITEA SERIOUS : Software evolution, refactoring of operational & usable systems.
Abstract
Embedded systems are becoming increasingly complex, more diverse, and are frequently expanded to include more features. As a consequence, the software is constantly changing: within Alcatel Bell rates of 10,000 lines of code changed per week are the norm. Unfortunately, high change rates inevitably erode a well-designed well-documented system and quickly turn it into a maintenance nightmare. Alcatel Bell's internal development processes are certified with CMM level 3. However these processes do not contribute to the long-term evolution of software. Indeed, the addition of new features sometimes introduces unexpected bugs, breaks design decisions, and distorts documentation. Consequently, it is hard to assess which software components should be refactored and to estimate the effort required to do so. Therefore, the SERIOUS project aims to develop methods, metrics and tools to maintain ---even increase--- the quality of the software during its evolution. In Belgium the project partners are Alcatel Bell (http://www.alcatel.be/) and the University of Antwerp, research group LORE (http://www.lore.ua.ac.be/). However, this local consortium participates in a larger ITEA context with other companies in Europe such as Philips and Nokia.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
International workshop on principles of software evolution.
Abstract
The International Workshop on Principles of Software Evolution (IWPSE) is the flagship workshop for research on software evolution and as such it is the prime candidate for publishing the end results of the RELEASE project. Several members of the RELEASE network are part of the organization committee and we agreed to have a special slots devoted solely to RELEASE results. Several members of the network submitted papers and six of them have been accepted after rigorous reviewing by the program committee. Therefore, we request to use RELEASE money for participating in what we see as the "grand finale" of the RELEASE network.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Workshop on Object-Oriented reengineering.
Abstract
The ability to reengineer object-oriented legacy systems has become a vital matter in today's software industry. Early adopters of the object-oriented programming paradigm are now facing the problems of transforming their object-oriented "legacy" systems into full-fledged frameworks. This Workshop on Object-Oriented Reengineering wants to gather people working on solutions for object-oriented legacy systems, and will be set up as a forum for exchanging experiences, discussing solutions, and exploring new ideas. We explicitly sollicit experience reports from the software industry as well as contributions from tool produces and methodology providers.Researcher(s)
- Promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Formal support for the transormation of software models.
Abstract
The software development process consists of a sequence of consecutive phases, such as requirement analysis, high level design, detailed design, implementation and validation [SommOO, Jacog9]. A typical characteristic of the software lifecycle is a gradual evolution from abstract, declarative models to concrete, computational ones. For each of the phases a well-founded theoretical basis is available, as well as a significant body of knowledge and experience [Gammg4, Jacog2, Wirf9O, Bind9g]. One of the major problems in the development of software systems is a lack of adequate support for evolution, i.e. evolution throughout the lifecycle as well as evolution in time [Lehm 85]. Consecutive models arl hardly related, so that in practice various phases of the development cycle are only marginally or not at all worked out. Moreover, a modification of a software system often requires manual changes to all of the models of the consecutive phases. Therefore, in practice, modifications are often carried through only at the lowest levels and nqt documented properly. This results in so-called legacy systems, that embody complex functionality, but that have lost their overall structure, making it possible to maintain them in a cost-efficient way.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Janssens Dirk
Research team(s)
Project type(s)
- Research Project
"Separation of Concerns" with High Level Software Models.
Abstract
Researcher(s)
- Promoter: Janssens Dirk
- Co-promoter: Demeyer Serge
- Fellow: Schippers Hans
Research team(s)
Project type(s)
- Research Project
Ebusiness in the Farmaceutical Care.
Development of energy conscious software refactoring techniques for embedded systems.
Abstract
The goal of the research project is the development of new heuristics and new software tools for the exploration and optimalisation of the power- and memory consumption of embedded software systems. De new heuristics and tools aim explicitly at a high abstraction level and will enable the exploration of the data structures used within the embedded software system.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Dhaene Tom
Research team(s)
Project type(s)
- Research Project
A Formal Foundation for Software Refactoring.
Abstract
The aim of the project is to provide a solid foundation for software refactoring by the development of a suitable formal model. We aim at a lightweight model, facilitating the investigation of basic properties of refactoring, as well as the design of tools supporting the refactoring process. In particular, the potential of graph rewriting as a basis for such a model will be explored. This should lead to, e.g., methods for the detection of conflicting refactorings, and methods for the optimization of refactoring processes. Thirdly, the question whether a given set of refactorings is allowable in the sense that it preserves program behaviour is obviously related to the characterization of graph properties that are preserved by the corresponding rewriting rules. Other important aspects are the complexity of refactorings, which can be studied in terms of the number of graph rewriting steps needed, perhaps in combination with the sizes of the graphs involved, and the issue of consistency between various levels of abstraction, which is related to work about hierarchical graphs.Researcher(s)
- Promoter: Janssens Dirk
- Co-promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
Syntactic and Semantic Integration of Visual Modelling Techniques. (SegraVis)
Abstract
Both in software engineering and in the more classical engineering disciplines, the use of visual notations, e.g. for documentation and communication with customers, has a long tradition. Driven by the increasing complexity of the problems such notations have become more elaborate, and have evolved towards tool-supported visual modeling techniques. Two of the most successful classes of visual modeling techniques are the main focus of the project: on the one hand UML, and on the other hand graph- and net-based techniques. A general paradigm for the classification and integration is required, which helps to make explicit semantic variations and to generate tools from formal language definitions. The aim of the project is to develop such a paradigm, to demonstrate its applicability, and to improve visual modeling techniques in specific application domains.Researcher(s)
- Promoter: Janssens Dirk
- Co-promoter: Demeyer Serge
Research team(s)
Project type(s)
- Research Project
ARRIBA : Architectural Resources for the Restructuring and Integration of Business Applications.
Abstract
The aim of this project is to provide a methodology and its associated tools in order to support the integration of disparate business applications that have not necessarily been designed to coexist. Inspiration comes from real concerns that are the result of an investigative effort on the part of some of the research partners in this consortium; the object of the investigation was the identification of mainstream ICT problems with a representative forum of Belgian enterprises (large and small) that rely on information technology for their critical business activities.Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Janssens Dirk
Research team(s)
Project type(s)
- Research Project
Network on Proposed Software Evolution. (RELEASE)
Abstract
The study of software evolution has become increasingly essential to ensure that IT systems perform well throughout their lifecycle, and this Network is creating the multidisciplinary framework needed to expand research on a pan-European basis. In particular, the network will (a) investigate an overall theory of software evolution (similar to the theories underlying other scientific disciplines); (b) develop benchmarks to improve the validity of scientific experiments. The Network builds on an existing smaller-scale research network on software evolution funded by the FWO (Fund for Scientific Research - Flanders, Belgium).Researcher(s)
- Promoter: Demeyer Serge
- Co-promoter: Janssens Dirk
Research team(s)
Project type(s)
- Research Project
Foundations of Software Evolution.
Projects Cosys-lab
Ongoing projects
EchoFORMER - Towards the construction of self-supervised acoustic world models for emergent spatial cognition
Abstract
EchoFORMER investigates whether spatial cognition and 3D localization can emerge purely from self-supervised learning on biomimetic sonar data. The central hypothesis is that a large-scale acoustic foundation model, trained only to predict its own sensory inputs during ego-motion, will spontaneously develop structured internal representations analogous to place cells, head-direction cells, boundary cells, and temporal sequence encoders, while implicitly learning to invert direction-dependent acoustic filtering (HRTFs). We will design and train an embodied acoustic transformer on large-scale echo streams combined with proprioceptive motion signals collected during controlled 2D and 3D robot motion. The model receives no supervision about position, orientation, or object identity. Learning is driven by predictive objectives such as future echo forecasting, masked spectrogram reconstruction, and cross-view prediction under simulated head rotations, enforcing spatial and temporal consistency in the latent space. Emergence will be quantified using neuroscience-inspired probing to identify spatially localized activations, directional tuning, boundary sensitivity, temporal dynamics, and implicit HRTF inversion supporting unsupervised 3D localization. Scientifically, the project tests whether predictive acoustic learning alone can yield structured spatial representations, bridging foundation models and biological spatial cognition. Technologically, it aims to establish a reusable acoustic world-model backbone for sonar-based robotics, reducing dependence on task-specific supervision and enabling transferable representations for navigation and perception in visually degraded environments.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
From Lung Sounds to Clinical Value: Advancing and Valorising Computer-Aided Lung Sound Analysis (CALSA)
Abstract
Computer-Aided Lung Sound Analysis (CALSA) has emerged as a promising solution to overcome the limitations of traditional auscultation, offering objective, repeatable, and non-invasive respiratory assessments suitable for both clinical and telemedicine environments. Our research group has developed state-of-the-art CALSA algorithms for breathing phase detection, crackle analysis, and spectral respiratory parameters, supported by a unique strategic lung sound database and a patented analysis method. Although these innovations substantially advance CALSA technology, key gaps remain that hinder clinical adoption and commercial valorisation. In particular, the absence of robust wheeze detection and analysis capabilities, critical for monitoring asthma and COPD (the most prevalent chronic respiratory diseases in Europe) limits clinical relevance, while a lack of structured insight into economically viable use cases constrains market entry. This IOF POC Develop project addresses these gaps through two major objectives. First, we will identify and validate the most promising target markets for CALSA by commissioning a comprehensive consultancy study, analysing diagnostic and follow-up workflows for common respiratory diseases, and conducting interviews with patients and healthcare providers. These results will directly be used for our first go-to-market strategy, allowing us to transition from TRL/CRL 3 to 5 and to refine the business model of our envisioned spin-off company. Second, we will develop and validate a complete wheeze analysis system. We will record a large, demographically diverse dataset of wheeze-containing lung sounds at the Antwerp University Hospital and label these recordings using our extensive annotation tools. Using this dataset and our advanced lung sound simulator, we will design deep learning-based wheeze separation algorithms and subsequent signal analysis methods capable of detecting, localising, and characterising mono- and polyphonic wheezes. This will complete our suite of CALSA algorithms and significantly enhance clinical utility for key user groups such as pulmonologists, respiratory physiotherapists, and at-home chronic patients. By simultaneously resolving core technological and valorisation barriers, this project forms a crucial step toward launching a spin-off offering CALSA software capable of improving respiratory care, supporting telemedicine initiatives, and reducing healthcare costs through early detection and continuous monitoring.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
- Co-promoter: Lapperre Therese
- Co-promoter: Verhulst Stijn
Research team(s)
Project type(s)
- Research Project
FlexIA – Flexible Industrial Automation
Abstract
Since the first industrial revolution, industrial automation has enabled improved performance, higher product quality, better worker ergonomics, and many other benefits across different industrial sectors. Over the past decades, electronic systems have become widely used in industrial automation, often as Programmable Logic Controllers (PLCs), which provide proven reliability for deterministic control tasks. Today, the growing demand for efficiency, adaptability, and intelligent decision-making is driving the integration of advanced algorithms, such as artificial intelligence, computer vision, and autonomous robotics. The shift towards this software-intensive automation introduces important challenges, including the integration of advanced algorithms into existing automation systems, limited hardware-software flexibility, and strong vendor lock-in. In the FlexIA projects, we address those challenges by a develop once, deploy anywhere paradigm for software-intensive industrial automation. Its primary objective is to achieve true hardware-software flexibility. This will be facilitated by developing and commercializing the FlexIA framework, that unifies design, implementation and deployment of advanced, software-intensive automation. In the preceding IOF-POC CREATE project, we have proven the technological concepts and have gathered feedback from five representative companies, resulting in a high-level feature list characterizing the future FlexIA-product. In the currently proposed IOF-POC DEVELOP, we aim for a continued interaction with those (and other) companies in a Company Interest Group (CIG). This CIG will be our sounding board steering the priorities of the FlexIA development, allowing us to raise the TRL from TRL3 to TRL5. Additionally, the current project will validate the FlexIA top features through pilot projects with the CIG, raising the CRL from CRL3 to CRL4. The current project will also prepare for an open-core IP valorisation strategy, complemented by in-house licensed tool extensions and customization.Researcher(s)
- Promoter: De Meulenaere Paul
- Co-promoter: Denil Joachim
- Co-promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
Magnetic core losses in power electronics (MMoMag).
Abstract
Power electronics is vital for efficient electrical energy control and conversion, leading to significant energy savings, reduced electronics volume, and improved efficiency in electricity production, distribution, and consumption, fostering a sustainable future. Magnetic components, like inductors and transformers, are key to power electronics, significantly impacting size, power loss, and cost. The main challenge is the lack of a reliable method to model magnetic core loss. The existing method, known as the Steimetz equations, is an empirical formula used to calculate core losses per unit volume in magnetic materials under sinusoidal magnetic flux. But it fails to consider factors like waveform shapes, temperature, and core geometries, leading to inaccurate predictions of magnetic core loss under various conditions. This SRN is established to tackle a fundamental bottleneck in power electronics: the inaccurate prediction of magnetic core loss. We will move beyond empirical Steinmetz equations by creating a collaborative, multidisciplinary framework to develop the first open-source, physics-informed machine learning model for core loss prediction. This model will incorporate the effects of DC bias, complex waveforms, temperature, and core geometry, aiming to reduce prediction errors from >30% to under 5%. The network unites world-leading experts in materials synthesis (Hasselt), electromagnetic design (Antwerp, Kassel), industrial manufacturing (SMA Magnetics， Sumida), and AI-driven modeling (KU Leuven) to achieve this ambitious goal. The commonly used model for magnetic core loss is based on the empirical Steinmetz Equation (SE) with the parameters 𝑘𝑘, 𝛼𝛼 and 𝛽𝛽 are derived empirically from the material's B-H hysteresis curve through data fitting. However, SE and its modifications only consider frequency and flux density under sinusoidal excitations and assume uniform flux within the magnetic material, which is inaccurate, especially at high switching frequencies. Moreover, in most power converters, magnetic components are excited by non-sinusoidal waveforms like sawtooth or trapezoidal shapes, leading to errors of up to 50% between calculated and actual magnetic characteristics. Additionally, magnetic characteristics depend heavily on direct current (DC) bias, temperature, core geometries, and duty cycle, resulting in inaccuracies in core-loss, winding-loss, inductance values, and B-H characteristics. Improving the SE-based model is crucial for advancing power converters and magnetic design. In recent years, machine learning has become an increasingly prevalent technique for generating black-box models to describe data. Research Objectives: To address the above shortcomings, we will develop novel physics-informed machine learning methods tailored for magnetics modelling in power electronics. Fitting data with a mathematical model is essential to discover the underlying physics, and it constitutes a type of inverse problem called data fitting. An accurate mathematical model can give valuable information on the physical power electronics system. We will develop novel inverse mathematical methods, integrating experimental measurement data and Finite Element Analysis (FEA) simulation data with machine learning techniques, to refine the SE-based model. This enhancement will enable the model to accurately predict magnetic core losses under various operating conditions such as temperature, core geometries, and actual waveforms with DC bias, enhancing power efficiency and reducing the size and cost of magnetic components. Through fitting data with a mathematical model, the project will also discover the underlying physics of magnetic materials, addressing the non-linear nature and variations in magnetic component behaviours due to material properties and manufacturing processes.Researcher(s)
- Promoter: Minnaert Ben
Research team(s)
Project type(s)
- Research Project
MULTI-CPT: Multi-Port Wireless Power Transfer Systems using Innovative Capacitive Approaches.
Abstract
Wireless power transfer using a magnetic field through inductive coupling is strongly entering the market in a broad range of applications. However, for certain applications, capacitive wireless power transfer using electric coupling is preferable. This technology is not yet available on the market, but given its potential, researchers have started studying its scientific and technical challenges. This project focuses on a capacitive wireless power transfer systems with multiple transmitters and multiple receivers (a "MIMO-system"). To date, no functional MIMO system in the kW range exists that allows for misalignment, due to some fundamental open research questions. Nevertheless, this novel technology is needed for easily powering future, often mobile, electrical applications that will soon be abundant due to the energy transition and accompanying electrification of society. Therefore, this project determines and implements innovative approaches, required for a MIMO system for up to 1 kW, including the influence of different media and new converter topologies. By modelling the fundamental properties of the system, and implementing the experimental setup, the project lays the scientific foundations for the introduction of capacitive wireless power transfer in future applications, such as vehicle-to-grid.Researcher(s)
- Promoter: Minnaert Ben
Research team(s)
Project type(s)
- Research Project
DarTwin – Foundations for the Systematic Evolution of Digital Twins.
Abstract
Digital twins (DTs) are virtual counterparts to cyber-physical systems (CPSs), enabling advanced DT services, including real-time simulation of what-if scenarios, predictive maintenance, and complex behavioural reasoning. When a digital twin system (DTS) is established, a single DT is created for an actual system (AS) to fulfil specific high-level goals, known as DT purposes. Throughout the DTS's lifecycle, various aspects (DT purposes, AS configuration or environment) evolve and thus require the addition of new DTs or the changing/removing of existing ones. For example, an energy-saving DT might be added to a DTS that controls heat and air quality, potentially adding opposing goals and conflicts (e.g., heating vs. saving energy). Currently, no methodology exists for the systematic evolution of DTSs and the discovery and management of conflicts. This project will develop MetaTwins as a concept that embraces the constant evolution of DTSs as core principle. MetaTwins are dedicated DTS representations, similar to DTs that represent an AS. They orchestrate evolution in the DTS by adding, removing, and modifying its DTs, while sustaining the DTS's purposes and validity. They provide essential services such as change discovery, impact analyses, and simulation of the interplay among DTs, and with the AS.Researcher(s)
- Promoter: Denil Joachim
- Co-promoter: Mertens Joost
Research team(s)
Project type(s)
- Research Project
Autonomous Quadrotor Flight through Biologically Inspired Echolocation.
Abstract
Echolocating bats demonstrate a high degree of agility in complex environments, using only sound as their main sensor modality. Inspired by their capabilities, this project aims to develop autonomous quadrotor UAVs that rely solely on echolocation for navigation and control. With only a small number of attempts to build sonar-guided UAVs exist, we aim to bridge the performance gap between the existing systems and the impressive performance of echolocating bats. Leveraging recent advances in lightweight embedded GPUs and biomimetic sonar systems, we will achieve this goal by combining these systems into a lightweight and agile flight platform. The project will focus on optimizing sensor architectures under strict weight and power constraints, developing robust spatial memory representations to counteract the sparsity of sonar data, and implementing adaptive control strategies for agile flight. Through a combination of high-fidelity simulations and real-world test platforms, we will ensure quantitative analysis and reproducible results. The project will contribute open datasets, software, and test environments to advance sonar-based robotics. By bridging the gap between biological and artificial echolocation, we aim to demonstrate fully autonomous UAV flight in dynamic, unstructured environments—paving the way for novel applications of this under-utilized sensor modality.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Virtual commissioning for motion control.
Abstract
Machine builders in Flanders are increasingly confronted with the challenge of developing energy-efficient, high-performance, and low-maintenance machines, preferably within the shortest possible production time. In the design process of such machines, a sequential strategy is still too often used, where the design process, the actual production of the machine, and the commissioning follow each other in sequence. As a result, design improvements are often identified too late, leading to machines that function but are not fully optimized. Recent advances in commercial controllers, the availability of CAD models, and optimization tools now make it possible to achieve up to a 75% reduction in commissioning time, while enabling better machine design and tuning. This project will unlock these functionalities for virtual commissioning for the Flemish machine-building sector. The concrete target group therefore includes Flemish machine builders, engineering consultants, and suppliers of drive components and CAD software. This project leverages the potential of Virtual Commissioning (VC) by combining dynamic multibody models (= motion simulations) with a Software- and Hardware-In-the-Loop (HiL) strategy, making use of the commercial drive itself, thereby avoiding additional hardware costs. The first objective is to evaluate whether open-source CAD motion simulation tools perform as well as commercial options. In addition, the motion simulations will focus on multi-axis systems, where synchronization of machine movements is crucial. The second objective is to use the models to achieve virtual commissioning. This involves using the commercial controllers that are already employed by machine builders. These controllers make it possible to run mechanical models. A key research question in this project is how a commercially hardcoded control system can effectively interact with a mechanical model. This would enable the performance of the fully virtual machine—including the mechanics, drivetrain, and control logic—to be evaluated, with the possibility of feeding the results back to the design phase if needed. To realize this objective, model reduction techniques will be applied to implement the models efficiently on the commercial controllers. The third project objective focuses on the optimization of control parameters and trajectory generation in multi-axis systems. Previous projects primarily focused on single-axis systems. New research results now make it possible to extend this to more complex systems. Here too, the motion simulation models are used in combination with the control loop to achieve an optimal setup.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
Modelling and Simulation of Cyber-Physical Systems.
Abstract
My research aims to improve the lifecycle of smart Cyber-physical System of Systems (sCPSoS) and increase their level of intelligence by using multi-agent systems. To this end, different layers with different abstraction levels are considered for these complex systems. This can be used in the analyzing phase (by modeling and simulating), development phase (by refinement of design models), and/or run-time phase (with adaptive abstraction).Researcher(s)
- Promoter: Challenger Moharram
- Fellow: Challenger Moharram
Research team(s)
Project type(s)
- Research Project
Flanders Make Infrastructure Research Agreement WP 8 Intralogistics Virtual.
Abstract
In this project, we aim to explore and develop innovative infrastructure to support both simulation and real-world implementation of intra-logistics systems. Our work encompasses various aspects of intra-logistics, including the deployment and utilization of autonomous mobile robots (AMRs) for efficient material handling and transportation within industrial environments. Additionally, we focus on the creation of large-scale simulation environments that allow for rigorous testing and evaluation of advanced learning-based approaches. These simulations enable us to assess the performance, scalability, and robustness of proposed solutions before their real-world deployment. By bridging the gap between simulation and physical implementation, this project seeks to advance the state of the art in intra-logistics, offering scalable, adaptable, and efficient solutions to meet the dynamic demands of modern industries.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
Flanders Make Infrastructure Research Agreement WP7 Intralogistics Physical.
Abstract
In this project, we aim to explore and develop innovative infrastructure to support both simulation and real-world implementation of intra-logistics systems. Our work encompasses various aspects of intra-logistics, including the deployment and utilization of autonomous mobile robots (AMRs) for efficient material handling and transportation within industrial environments. Additionally, we focus on the creation of large-scale simulation environments that allow for rigorous testing and evaluation of advanced learning-based approaches. These simulations enable us to assess the performance, scalability, and robustness of proposed solutions before their real-world deployment. By bridging the gap between simulation and physical implementation, this project seeks to advance the state of the art in intra-logistics, offering scalable, adaptable, and efficient solutions to meet the dynamic demands of modern industries.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
Flanders Chips Competence Center (FC3).
Abstract
The Flanders Chips Competence Centre (FC3), proposed under the European Chips Act, seeks to enhance the growth of Europe's semiconductor sector and to ensure a robust supply chain. It fits within the Chips for Europe Initiative, complementing the Pilot Lines, the Design Platform and the Chips Fund. The FC3 will be the first point of contact in Flanders to facilitate access to these infrastructures, and to technical expertise and experiments in the fields of chip development and system integration. It also aims to be instrumental in alleviating the talent shortage in the broad semiconductor ecosystem. To reach its goals, the FC3 will deploy five major activities: (1) providing skill development, mainly by organizing courses, (2) offering chip development and system integration services, both for mature technologies, as well as for upcoming technologies, (3) creating pathfinding demonstrators, as a means to showcase the potential of chip technology, (4) acting as a central contact point, functioning as a proactive front office towards all the stakeholders and potential clients of the center, and (5) outreach and dissemination, to have a bidirectional interaction between the center and the public. The focus area of the FC3 is the broad domain of analog, mixed-signal and digital chip design and development, photonic components, chips and technology, and electronic and photonic system integration. The FC3 consortium's expertise in skill development, chip design, and system integration, combined with its strong ties to industry, its world-class infrastructure, its innovative R&D models, its active support for entrepreneurship, and its well-developed relationships with the other stakeholders of the Flemish and the European chips ecosystems, positions it as the ideal consortium to implement the Flanders Chips Competence Center.Researcher(s)
- Promoter: Daems Walter
- Co-promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Online Global Motion Profile Optimizer.
Abstract
To address environmental concerns, researchers focus on reducing the energy use of industrial machinery. Position-controlled systems allow for energy savings by optimizing the position function between fixed user-defined start and endpoints, requiring only adjusted drive settings for easy and cost-effective implementation. State-of-the-art optimizers rely on complex, machine-specific models, deterring machine builders. Furthermore, mismatches between model and reality, and changes in machine behavior over time can render optimized motion profiles suboptimal in practice. This project proposes a novel solution by optimizing the motion profile online during machine operation. Moreover, a key issue is that existing algorithms often achieve only local optimum motion profiles, potentially missing up to 11.3% of energy savings compared to the global optimum. This project proposes two steps to achieve global optimum motion profiles. First, the use of a global optimization algorithm. Secondly, the motion profile's mathematical formulation, typically constrained to specific bases (e.g., polynomial, splines), can limit revealing the global optimum. This project will employ Gaussian Processes to describe motion profiles, allowing unconstrained optimization potential by not limiting the profile to a specific form. Only an online motion profile without pre-defined profile bases can result in a machine operation with an absolute minimal energy need.Researcher(s)
- Promoter: Derammelaere Stijn
- Co-promoter: Cuyt Annie
- Fellow: De Laet Robbe
Research team(s)
Project type(s)
- Research Project
Towards Runtime Assurance of AI Systems in Safety Critical Industrial Applications (SAIfety_SBO).
Abstract
Companies need to guarantee continuous system safety along the lifecycle of their industrial systems. Machine Learning (ML) techniques are increasingly being used for perception, navigation, and control functionality in industrial systems. Due to upcoming new legislation (e.g., under the impulse of the AI Act) and regulatory requirements, OEMs, integrators and AI technology providers will increasingly be pushed towards guaranteeing the overall system safety, including the respective ML models.  While conventional engineering safety standards are available to assure the safety of mechanical or electronic systems and (non-AI-related) software, these are not directly transferable for ML algorithm design. The main challenges include the non-deterministic behaviour of ML components, the dependency on the dataset on which the model is trained, and the corresponding dynamic and uncertain nature of the environment in which these models need to operate. Companies need methods and tools to support them in the design, development and runtime monitoring of the safety of integrated ML models in industrial systems. The overall objective of the SAIfety project is to increase the robustness of ML models integrated in safety-critical mechatronic systems. To this end, safety assurance aspects across the different phases of the ML model lifecycle will be addressed, including AI safety requirements specification, architectural design, the quantification of the model's uncertainty, and its monitoring at runtime. Specifically, this student will work on modelling the components' validity for using during design and operation of the system. In line with the focal areas of the companies within the target group and the current state of the art, SAIfety will focus on vision and time series analysis tasks, with primary attention for deep learning models. Overall, the outcome of this project will allow companies working on industrial safety-critical systems to increase robustness of the ML components integrated in their systems. As such, this not only contributes to the trustworthiness of the resulting products, but also increases the innovation potential to add value-added functionality into their digitized product offering.Researcher(s)
- Promoter: Denil Joachim
- Co-promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Combining the magnetic and electric channel for wireless power transfer.
Abstract
Wireless power transfer, especially in portable devices, offers the main advantage of improved convenience and user experience since there is no need to plug in a physical cable to charge or power the device. A novel method, called hybrid or dual-channel wireless power transfer, combines both the magnetic (inductive) and electric (capacitive) channel. In this project, a theoretical framework is developed that models the relationship between the coupling factor of dual-channel wireless power transfer and the lumped elements of the equivalent circuit representation. The effect of combining both the magnetic and electric channel on the characteristics of energy transfer and misalignment tolerance are determined. The results are validated by simulation and experiment, resulting in the essential coupling models needed to unlock the potential of dual-channel wireless power transfer.Researcher(s)
- Promoter: Minnaert Ben
- Fellow: Elst Baptist
Research team(s)
Project type(s)
- Research Project
DEO: Wireless power transfer.
Abstract
Wireless power transfer enhances the user experience of electrically powered devices, as it eliminates the need to connect a physical cable. It results in increased durability and robustness, facilitates automation and increases safety in hazardous industrial environments. However, many companies lack the resources to acquire the necessary knowledge to implement wireless power transfer, despite its strong global growth and the maturity of the technology. Limited knowledge of the principles and the limited application possibilities of the market standard prevent the application of wireless power transfer in atypical configurations. The overall goal of this project is to disseminate accessible and practice-oriented tools and knowledge for the implementation of wireless power transfer.Researcher(s)
- Promoter: Minnaert Ben
Research team(s)
Project type(s)
- Research Project
Automatic Sensor Pose Evaluation and Reconfiguration (ASORE-IRVA).
Abstract
Accurate sensor pose calibration and monitoring are essential for safe and effective autonomous vehicle operation. Current methods, relying on manual recalibration using artificial targets, increase costs and reduce vehicle availability. While state-of-the-art solutions exist, they require application-specific redesigns involving complex mathematical work. ASORE offers an automated approach, eliminating the need for users to handle the mathematical details of calibration. It generates expected sensor observations from a high-level use case description and links these to suitable sensor processing and calibration algorithms, available in the ASORE toolbox. Template models for vehicles, sensors, and landmarks simplify the creation of use cases. Delivered as a user-friendly software toolbox with a GUI, ASORE includes documentation and tutorials to streamline automated sensor calibration. This solution reduces development and maintenance costs, increases automation, and enhances flexibility for diverse applications, benefiting companies by improving the robustness of autonomous vehicle sensing systems.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
- Co-promoter: Huebel Nico
Research team(s)
Project type(s)
- Research Project
Situational aware navigation and mapping (SITANAV).
Abstract
SITANAV aims at increasing the reliability and robustness of Autonomous Vehicles (AV) operating in logistic, industrial and agricultural facilities by focusing on the following problems raised by companies in the consortium: 1) the limited flexibility of AVs in complex environments, 2) the high costs when localization requires additional infrastructure, 3) the high deployment and layout reconfiguration costs, and 4) the high memory footprint of discrete metric maps that hinders applications in large environments. SITANAV's key idea to overcome these problems is to increase the situational-awareness in navigation and mapping capabilities of autonomous vehicles. This will provide AVs with higher levels of self-adaptation based on the current situation through explainable decision-making via semantic maps and reasoning. There are three main technological barriers that SITANAV has to overcome: 1) lack of models fordescribing situations, 2) lack of capabilities to reason about objects and maps, and 3) lack of situational awareness in AVs' decision-making for navigation. The approach to remove these barriers is a framework that combines a metric-semantic map with situational models, which describe a set of relations that connect an AV's motion and perception capabilities to a particular situation. For example, when the AV can find the appropriate pieces of information to infer the current situation from the perceived environment, it can select and configure its perception and control behaviors (situational aware decision-making) to achieve the desired robustness and performance for the application at hand (e.g., detecting the situation of a partly blocked pathway and switching to a narrow-space navigation). The proposed method will extend existing graph-based models and tools with new features, reasoning, and query answering mechanisms, to gradually increase AVs' situational assessment capabilities. The improvements will be in small-scale iterations, following a continuous integration approach. This will be accomplished by two running demos (indoor and outdoor) with increasing complexity throughout the project. The SITANAV models and software are designed with forward compatibility in mind, because we can now already foresee many future extensions, such as new types of semantic features, memory and learning capabilities, and the integration of task planning.Researcher(s)
- Promoter: Daems Walter
- Co-promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Conditioned harsh outdoor environment for perception systems of autonomous applications (CAVE).
Abstract
Autonomous mobile systems might fail for many reasons, but one of them is when the harshness of the environment increases. It is difficult for OEMs, integrators, sensor and hardware components providers to design a robust autonomous mobile system based on traditional testing methods. Especially perception systems are challenged in realistic and relevant harsh conditions (e.g. rain, fog, direct sunlight). Currently, testing of perception systems is done by waiting for these conditions to happen in real-life – which can easily cost weeks of waiting. When an update is done on the hardware of the perception system (e.g. a coating on the lens is added) the exact same test is needed to verify an improvement. However, in real-life this exact same harsh condition cannot be reproduced. So, there is a need for a modular, validated testing facility that allows controllable and measurable conditions, to enable repeatable and controlled harsh conditions. CAVE_INFRA aims to develop a fixed perception test facility which can control and measure rain, snow, fog, illumination, dust and debris conditions, including its digital twin and a real-life validation. We aim to provide the following services: i) Sensing hardware (incl coatings/cleaning systems) and software performance evaluation in harsh conditions, including benchmarking to support sensor selection ii) Harsh condition model and/or sensor model derivation iii) Training or validation of AI models for objects / human detection and pose estimation iv) Degradation tests in harsh conditions v) Generate test data and scenarios that can be used for driving out own research but also for certification purposes and discussions with certification bodies such as TuV. To produce the harsh conditions in realistic scenarios, there are different actuation systems foreseen to respectively actuate the perception system under test, the target objects to be detected, and some of the generated conditions such as diverse illumination systems to create dynamic contrast.Researcher(s)
- Promoter: Daems Walter
- Co-promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
The role of the hip capsule in patient outcome after hip arthroplasty.
Abstract
Passive energy storage and return has long been recognized as one of the central mechanisms for minimizing the energy cost needed for terrestrial locomotion. Although the hip capsule resides the strongest ligaments in the body, its potential role in energy-efficient walking remains unexplored. Increasing our understanding of soft-tissue balancing following THA could help prevent instability and improve early and long-term hip function. Clearly, our understanding of the hip capsule and its role in human mechanics remains largely incomplete. This research proposal aims to address this important gap by investigating the active and passive role of the hip capsule in hip functioning by examining the impact of implant design, anatomical variance and surgical handling on the properties of the hip capsule. This research will inform the development of improved surgical techniques and implant designs that can optimize patient outcomes and enhance long-term performance following hip arthroplasty.Researcher(s)
- Promoter: Chevalier Amélie
Research team(s)
Project type(s)
- Research Project
Lower limb instability: the missing link between knee and ankle.
Abstract
Sport injuries account for 10-20% of all acute injuries treated in the emergency room. From this, the most common injuries are knee and ankle injuries. Injury-prevention techniques rely on understanding the injury mechanisms. The focus in this project will be on anterior-cruciate ligament (ACL) rupture in the knee joint and high ankle sprains (syndesmosis injury) as they are difficult to diagnose and often are misdiagnosed potentially leading to chronic instability. To improve diagnosis, a novel imaging technique, standing CT, is used as knee and ankle joints can be imaged under standing conditions rather than the currently used supine position. A novel medical device is developed to extend the standing CT from static testing to dynamic testing. The prototype allows for internal/external rotation and varus/valgus rotation in the ankle joint to simulate different positions of the foot. Kinematic measurements allow for measurement of the joint laxity in the knee and ankle, which has been focus of the PI's previous research. ACL deficient knees will be tested in-vitro to define when ACL rupture occurs. Ankle syndesmosis conditions will be simulated in an in-vitro test validating the new prototype. The final step in this research is a first-in-human test in the standing CT to evaluate if the position of the foot is inducing ACL rupture or high ankle sprains. As follow up of this project, an IOF project will be taken on to bring the device on the market.Researcher(s)
- Promoter: Chevalier Amélie
- Co-promoter: Van der Jeught Sam
- Fellow: Degrande Axel
Research team(s)
Project type(s)
- Research Project
Robotic Safe Adaptation In unprecedented Situations (RoboSAPIENS).
Abstract
The robots of tomorrow will be endowed with the ability to adapt to drastic and unpredicted changes in their environment including humans. Such adaptations can however not be boundless: the robot must stay trustworthy, i.e. the adaptations should not be just a recovery into a degraded functionality. Instead, it must be a true adaptation, meaning that the robot will change its behavior while maintaining or even increasing its expected performance, and stays at least as safe and robust as before. RoboSAPIENS will focus on autonomous robotic software adaptations and will lay the foundations for ensuring that such software adaptations are carried out in an intrinsically safe, trustworthy and efficient manner, thereby reconciling open-ended self-adaptation with safety by design. RoboSAPIENS will also transform these foundations into 'first time right'-design tools and robotic platforms, and will validate and demonstrate them up to TRL4. To achieve this over-all goal, RoboSAPIENS will extend the state of the art in four main objectives. 1. It will enable robotic open-ended self-adaptation in response to unprecedented system structural and environmental changes. 2. It will advance safety engineering techniques to assure robotic safety not only before, during and after adaptation. 3. It will advance deep learning techniques to actively reduce uncertainty in robotic self-adaptation. 4. It will assure trustworthiness of systems that use both deep-learning and computational architecturesfor robotic self-adaptation. To realise these objectives, RoboSAPIENS will extend techniquessuch as MAPE K (Monitor, Analyze, Plan, Execute, Knowledge) and Deep Learning to set up generic adaptation procedures and also use an SSH dimension. RoboSAPIENS will demonstrate this trustworthy robotic self-adaptation on four industry-scale use cases centered around an industrial disassembly robot, a warehouse robotic swarm, a prolonged hull of an autonomous vessel, and human-robotic interaction.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Multi-Port Wireless Power Transfer Systems via Electric Coupling.
Abstract
This research proposal focuses on a multi-port wireless power transfer system that applies electric coupling to transfer energy from one or more transmitters to one or more receivers. The fundamental research question is how novel optimization algorithms can keep the operating conditions of this capacitive system with an unpredictable electric coupling optimized, depending on the chosen optimization goal. This includes determining the suitable models and fundamental relationships between the system characteristics (including its unpredictable coupling) and the different optimization gains. An important aspect is the experimental validation of the models via a low power setup, containing a versatile driver in order to allow easy frequency adaptation. More specifically, the contributions of this project will be the following: (i) Development of a model describing quantitatively the fundamental relationships between varying couplings and the (relative) variation of the impedance compensation networks. (ii) Modelling the so called "frequency bifurcation phenomenon" for multi-port systems. (iii) Determining and applying optimization algorithms for different scenarios, i.e. applying impedance and frequency adaptations based on a feedback procedure in order to keep the multi-port system in its (near-to) optimal operating condition, and finally (iv) validation of the aforementioned models and algorithms by simulation and experiment.Researcher(s)
- Promoter: Minnaert Ben
- Fellow: van Ieperen Aris
Research team(s)
Project type(s)
- Research Project
Creating Harmony Between Prosthesis, User and Control Theory.
Abstract
Lower limb amputations often severely restrict patients when trying to perform activities of daily living, even when using prostheses. Active lower limb prostheses are a promising alternative to the more common passive prostheses but even those still have significant limitations and shortcomings. This project aims to overcome a number of those limitations and shortcomings through the development of a novel control strategy for active lower limb prostheses. The novel control strategy will be widely applicable and will consist of a novel classifier, a novel variable impedance control and novel 'amputee in the loop' learning algorithms. The strategy will be tested on two different hardware platforms and for varying activity patterns and contexts. Performance in each setting will be measured via well-designed evaluation processes with a focus on patient reported outcome measures (PROMs). The hypothesised outcomes with respect to the state-of-the-art are: a higher number of supported activity scenarios, high classification accuracy, a more natural switching of modes, high anti-interference capability, a reduced need for parameter tuning, increased system simplicity and reliability. This will bring significant improvements of the quality of life for active prosthesis users as well as socio-economic benefits in the prosthetics sector.Researcher(s)
- Promoter: Chevalier Amélie
Research team(s)
Project type(s)
- Research Project
Natural objects rendering for economic AI models (NORM.AI).
Abstract
Natural objects (vegetables, fruits, food, etc.) are omnipresent in different industrial applications: food sorting, vegetable spray treatments, precision & automated farming, etc. Automating these applications to deal with large variabilities of natural objects (object's detection, recognition, pose estimation, etc.), requires innovative technologies that are enabled by Artificial Intelligence (AI) that has the ability to generalize to variabilities. However, training these AI models would require thousands of images / videos with detailed annotations of different items. In the state of the art, one needs >10k images to (re-)train an AI model with an accuracy of >90%, when, in average one minute is needed to annotate one 'real' image, however these can increase drastically depending on the use case at hand and the variability around it. The more variability one wants to cover, the more training images are needed. These findings clearly indicate that in order to be able to deploy AI models in the industrial applications, innovative techniques are highly needed to remove the burdens of data annotations2. These techniques need also to be easily usable by end users to avoid large amount of manual work to update the proposed methodology to new applications. NORM.AI builds further on the successful results from PILS SBO3,4, where rendering techniques were applied to industrial products with CAD (Computer Aided Design) information, to retrieve AI (synthetic) training data from updated CAD with radiance models. While CAD facilitates synthetic data generation in PILS SBO by providing a reference model to start rendering from, the goal of NORM.AI project is to extend this research to Natural objects where no CAD is available. Therefore, defining a reference model to start rendering from, is part of the research in the project. Creating variations from the reference model that takes both spatial & time changes of the natural objects and the natural scenes, as well as finding a sweet spot between real data augmentation techniques & synthetic data generation techniques constitute another research challenge in the project. This research will allow to identify economic scenarios of training data generation, taking into account their effect into AI model's accuracy and robustness. The project focuses into three research applications: 1- Food sorting applications, where 2D images are used to detect & sort fruits & vegetables, as they are coming, for example, in a conveyor system. 2- Crop monitoring applications, where images from 2D cameras, for example, installed in a harvester, are used to detect vine's rows, crop distribution, etc. 3- Weed monitoring applications, where 2D images guide a spraying system to locally sprayweeds in a high precision.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
- Co-promoter: Huebel Nico
Research team(s)
Project type(s)
- Research Project
Sparse interpolation for high-dimensional mechatronic co-design.
Abstract
The design and engineering of electrically driven machine mechanisms increasingly rely on optimisation. This allows the minimisation of objectives such as the initial component cost or electrical energy required to drive these machines, all without compromising the performance. Heuristic optimisers, popular in mechatronics, often result in local optima and so leave a significant untapped optimisation potential. Different domains such as trajectory, geometry, and controller should be optimised simultaneously in a co-design approach to find the global minimum. Therefore, an explicit model of the design variable's impact on the objective is required. However, the data collection necessary for such a high-dimensional model, simultaneously considering all the design parameters, results in an explosion of the needed number of motion simulations. So, the co-design objective is only attainable if the model can be built from a minimal number of simulations. Through recent developments in multi-dimensional data fitting techniques, a practically feasible method for co-design in a high-dimensional setting may now become available for the first time.Researcher(s)
- Promoter: Derammelaere Stijn
- Co-promoter: Cuyt Annie
Research team(s)
Project type(s)
- Research Project
Capacitive Wireless Power Transfer for MIMO Configurations.
Abstract
Capacitive wireless power transfer (CPT) applies the electric field to transfer energy from a transmitter to a receiver without the need of physical connections. However, depending on the distance between transmitter and receiver, and their relative alignment, the system performance varies. A CPT system that automatically positions itself in the optimal working point, regardless the value of the unpredictable coupling, is therefore necessary. This is in particular challenging for a setup with multiple transmitters and multiple receivers, i.e., a Multiple Input – Multiple Output (MIMO) configuration. The objective of this project is to determine the necessary fundamental relationships to enable and implement algorithms to keep the operating conditions of a MIMO CPT system optimized.Researcher(s)
- Promoter: Minnaert Ben
- Co-promoter: Derammelaere Stijn
- Fellow: van Ieperen Aris
Research team(s)
Project type(s)
- Research Project
Portable Innovation Open Network for Efficiency and Emissions Reduction Solutions (PIONEERS).
Abstract
PIONEERS brings together four ports with different characteristics, but shared commitments towards meeting the Green Deal goals and Blue Growth socio-economic aims, in order to address the challenge for European ports of reducing GHG emissions while remaining competitive. In order to achieve these ambitions, the Ports of Antwerp, Barcelona, Venlo and Constanta will implement green port innovation demonstrations across four main pillars: clean energy production and supply, sustainable port design, modal shift and flows optimization, and digital transformation. Actions include: renewable energy generation and deployment of electric, hydrogen and methanol vehicles; building and heating networks retrofit for energy efficiency and implementation of circular economy approaches in infrastructure works; together with deployment of digital platforms (utilising AI and 5G technologies) to promote modal shift of passengers and freight, ensure optimised vehicle, vessel and container movements and allocations, and facilitate vehicle automation. These demonstrations form integrated packages aligned with other linked activities of the ports and their neighbouring city communities. Forming an Open Innovation Network for exchange, the ports, technology and support partners will progress through project phases of innovation demonstration, scale-up and cotransferability. Rigorous innovation and transfer processes will address technology evaluation and business case development for exploitation, as well as creating the institutional, regulatory and financial frameworks for green ports to flourish from technical innovation pilots to widespread solutions. These processes will inform and be undertaken in parallel with masterplan development and refinement, providing a Master Plan and roadmap for energy transition at the PIONEERS ports, and handbook to guide green port planning and implementation for different typologies of ports across Europe.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Embedded and distributed systems.
Abstract
Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. As the system has to operate in real environments using real sensors, the environment where the system operates in has to be included in the model as well. Simulating physical quantities and realistic environments can become very complex very quickly. The time that has to be invested for achieving accurate simulation results can become too much. Experimental setups can provide the data which is needed to avoid the need for complex simulations. Therefore, a Hardware-in-the-loop and Sensor-in-the-loop approach will be adopted to provide the relevant data at the right time of the modeling process. Strategies for the right spatio-temporal sampling and the right moment to apply HIL/SIL methods are important questions to answer. Once the complete system has been modeled using the realistic models and the platform-specific constraints, hardware generation (VHDL, analog schematics, etc.) and code generation (C-code for embedded processors) from the high-level model can be used to accelerate the design cycle. Large functional changes often translate to small changes in the high-level model, and results often in large changes in the low-level representation. Using the right type of code- and hardware-generation can accelerate the design cycle significantly. Code generation can also be used in the form of prototyping platforms such as large FPGA's to accelerate certain sub-models of the MBD-design. HIL/SIL systems also allow for real-time performance to give rise to sensor flow, which is very important in a wide range of applications.Researcher(s)
- Promoter: Steckel Jan
- Fellow: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Past projects
FlexIA – Flexible Industrial Automation.
Abstract
In the past, industrial automation predominantly relied on Programmable Logic Controllers (PLCs), offering an unparalleled reliability in controlling a wide range of manufacturing processes. The demand for increased efficiency, adaptability, and intelligent decision-making has propelled the integration of advanced algorithms in industrial automation projects. This shift towards such promising software-intensive automation poses some challenges. First, the integration of advanced algorithms, such as artificial intelligence (AI) models, with legacy installed automation infrastructures hits its limits when implemented in closed software-hardware ecosystems. Technology suppliers constrain their customers within the boundaries of their proprietary tools and hardware, thereby limiting hardware-software flexibility. Second, vendor-specific solutions do not support code reuse across different software-hardware suppliers, also called vendor lock-in. This results in costly redesigns when transitioning to different hardware platforms. The primary goal of the FlexIA Proof-of-Concept (PoC) project is to provide true hardware-software flexibility for the development of software-intensive automation systems by introducing the develop once, deploy anywhere strategy. This will be facilitated by developing and commercializing the FlexIA platform, a vendor-agnostic toolkit for developing and deploying software-intensive automation systems. The platform enables the creation and management of complex automation applications regardless of whether the hardware is realized on PLC or microcontroller. This contributes to the secondary goal of the project, namely reducing the vendor lock-in. Primary valorisation goal of this FlexIA PoC project is to conduct a thorough market study to determine the current and future needs of the relevant industrial stakeholders. This market study will help to determine an optimal go-to-market strategy to successfully commercialize the FlexIA platform. At the same time, it aligns the FlexIA technology features with the needs of the different stakeholders.Researcher(s)
- Promoter: De Meulenaere Paul
- Co-promoter: Denil Joachim
- Co-promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
ABN HaFreeS MVP Prototype.
Abstract
In this project we investigated during the first phase (IOF-POC ABN HaFrees Feasibility) whether it was possible to develop a hands-free kit for bicycles. The main goals here were ease of use and call quality at speeds above 10 to 15 km/h. To this end, we mapped the market, from which it became clear that the first focus should be on the functional user (i.e. the professional who wants to use his work-related commute by bike to call colleagues, customers, etc.). The first tests showed that a significant suppression of wind noise is possible using several techniques (selection of good microphones, the choice of an optimal arrangement of each individual microphone combined in an optimal configuration, appropriate shielding i.c.w. the right signal processing algorithms). The techniques on their own do not provide sufficient improvement, but the delta is sufficient so that the combination should allow for a quality conversation at 25km/h. In this second phase of the project, we want to develop a minium viable product (MVP) prototype, which should allow to (1) characterize the product on its main qualities, (2) benchmark the product against competing products, (3) set up tests in view of user feedback and (4) define the further direction of the valorization. An essential hurdle here is the intellectual protection of the technology.Researcher(s)
- Promoter: Daems Walter
- Co-promoter: Laurijssen Dennis
- Co-promoter: Steckel Jan
- Co-promoter: Verlinden Jouke Casper
Research team(s)
Project type(s)
- Research Project
Drive Line Concept Optimization (AnCoOpt).
Abstract
The AnCoOpt project developed and validated a workflow that translates customer requirements into energy-optimized machine concepts for electrically driven positioning applications. The methodology combines concept generation, motion simulations, and geometric and trajectory optimization. The project was carried out by Flanders Make, Ghent University, and the University of Antwerp, with active involvement from companies in the Flemish machine-building sector. During the project, 70% of participating companies demonstrated that the methodology is effectively applicable in their design practice. They also indicated that it can be applied to most of their customers, enabling the results to reach over 40 companies. Five industrial cases were developed — including a textile machine, a gripper mechanism, a ventilator, a pick-and-place unit, and an aircraft flap mechanism — validating the approach across diverse applications from compact drives to multi-axis mechanical systems. The combined geometry and motion optimization reduced torque requirements by up to 61%, directly lowering energy consumption, while the adaptive motion control strategy reduced position error by 67%. A total of 23 validations were performed (5 physical and 18 virtual), alongside three thematic workshops and a final seminar. The developed tools — Python scripts, CAD models, spreadsheets, and open documentation — were made freely available and are now integrated into the mechatronics curricula at Ghent University and the University of Antwerp.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
eMotioniser: Development of an online tool for optimal designing of electrically driven positioning applications.
Abstract
Designing an electrically driven positioning driveline involves lots of dimensioning and selection. Selecting the correct components and designing the motion profiles, machine geometries, and controllers, … all have a major impact on the initial component cost, required electrical energy to drive the application, and machine performance …. In other words, each selection and design choice can be considered a design parameter in an optimisation that maximises performance, such as machine throughput and simultaneously allows the minimisation of cost and required electrical energy. In 2017, our research group started developing algorithms to optimise the design of electrically driven machines. In cases where we applied our algorithms, it is not uncommon to see a reduction in required electrical energy of 67%, while at the same time, the component cost could be reduced by 30%. In other cases, we could improve the accuracy by 93% or improve the speed of the machines by 43%. All cases handled by our research group clearly show the potential benefits for industrial machine builders in terms of cost minimisation and performance maximisation. However, the algorithms we developed can only create value if we expand the scope of possible industrial usersinterested in applying our techniques beyond our local contacts with whom we regularly collaborate. Each machine builder in Europe and worldwide can benefit by applying our algorithms! To enable this European and worldwide outreach, an online tool which can be conveniently used by small up to international machine builders is envisaged. Such a tool should run our algorithms in the back with a graphical user interface that only requires machine parameters known or identifiable by the envisaged machine designers. This project contains two important parts. First of all, the concerned web tool should be developed. Secondly, the best path to a self-sustaining tool will be initiated.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
Hunting in the understory: Efficient foraging strategies of bats in acoustically complex environments.
Abstract
For the detection of their prey, echolocating bats produce ultrasonic calls and listen for echoes reflected off the insects. Gleaning bats hunt by taking resting prey from the vegetation. They hunt in an acoustically highly challenging and complex environment, such as the forest understory. As active flight is energetically very costly and the great majority of understory leaves do not hold resting prey, bats must have developed behavioural and acoustical strategies to efficiently check a vast amount of vegetation surfaces for the presence of prey. Here, I investigate which underlying foraging strategy echolocating bats use to efficiently search for resting prey in the forest understory. State-of-the art stereo high-speed video recordings synchronised with multi-microphone array recordings will be used to observe bats in a behavioural experiment searching for prey randomly placed on leaves of an artificial vegetation. To analyse the bats' 3D flight-paths and the corresponding echolocation behaviour I will train neural networks to perform automated pose tracking of the bats' foraging behaviour. The combination of detailed, three-dimensional behavioural and acoustic analysis will lead to a better understanding of the underlying mechanisms of efficient prey detection and foraging behaviour of bats in structurally and acoustically complex environments. Furthermore, the project will also offer the opportunity to inform and inspire biomimetic methods and applications for efficient acoustic object detection.Researcher(s)
- Promoter: Geipel Inga
Research team(s)
Project type(s)
- Research Project
Echo-acoustic signalling of aposematic and cryptic insects – A bat inspired modelling approach (EchoBug).
Abstract
In the arms race between prey and predators, diverse anti-predator defence mechanisms evolved. To avoid predation, many insects developed camouflage (crypsis) or chemicals that render them distasteful or toxic. To warn of their unpalatability, many insects evolved striking warning colours or patterns (aposematism). Insects comprise most of the diet of bats. Some of these nocturnal predators glean resting, silent, motionless diurnal insects from the vegetation. Instead of using vision during foraging, they produce ultrasonic calls and detect their prey through echolocation. Here, I want to research whether visually cryptic or aposematic insects also have cryptic or aposematic acoustic reflection properties, to hide from or signal their unpalatability to echolocating bats. I will use bio-inspired sensor systems to acquire echo-acoustic sonar recordings of selected insect species and conduct behavioural prey-detection and -capture experiments using live bats to explore the prevailing acoustic predator-prey interactions. Based on these experiments, I will apply neural network algorithms for classifying and analysing the distinguishing features in different insect echoes. This approach will allow an in-depth investigation of the underlying acoustic mechanisms of the interaction between prey and predators and will inform and inspire biomimetic applications for detecting and identifying objects by sonar. Further, the project will lead to synergism between the research fields of biology and engineering in the study of animal interactions and bio-inspired robotics.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Peremans Herbert
- Fellow: Geipel Inga
Research team(s)
Project type(s)
- Research Project
ABN HaFreeS Feasibility.
Abstract
In this project, we take the first steps in the development a novel hands-free communication set for use on bicycles. The main advantages of our solution in comparison to current solutions are call quality and convenience. Call quality is our main selling point: wind noise, traffic noise and contact noise impede comfortable calling at a speed above 10-15 km/h with the current available technology; we aim to overcome these shortcomings using technology building blocks available in Cosys-lab that have matured in other application domains. We mainly focus on showing technology feasibility, initiating a market study and perform initial user outreach activities. We will also start preparing the design of an MVP prototype. These activities are an essential first step to determine if it is worthwhile to pursue the end goal of commercializing the solution in a spin-off. If the technology is shown to work and the valorisation potential lives up to our expectations, we will undertake further steps in later projects to develop a deep market insight, a convincing MVP prototype and a solid value chain. These elements are necessary to reach the end goal of starting a VC-funding-free spin-off, bootstrapping with funding gathered in a crowdfunding campaign.Researcher(s)
- Promoter: Daems Walter
- Co-promoter: Laurijssen Dennis
- Co-promoter: Steckel Jan
- Co-promoter: Verlinden Jouke Casper
Research team(s)
Project type(s)
- Research Project
Wireless Power Transfer for building-integrated photovoltaics
Abstract
This research project aims at developing a module to wirelessly transport energy from photovoltaic solar cells in buildings. A crucial problem with building integrated photovoltaics (e.g. as a facade, or embedded in a window) is that with current technology, electrical cables still have to be pulled from the outside to the inside of the building, which has negative consequences for the insulation and water tightness of the building. Through prototypes, we test the efficiency and reliability of wireless energy transfer applied to the context of a building.Researcher(s)
- Promoter: Minnaert Ben
Research team(s)
Project type(s)
- Research Project
On-line optimization of ISOL@MYRRHA performance through an intelligent and automated control system.
Abstract
ISOL@MYRRHA is the Isotope Separation On Line facility to be constructed in the first phase of the MYRRHA project. It will be capable to produce a large variety of radioactive isotopes for applications in the field of nuclear physics, condensed-matter physics, biology, nuclear medicine and others. The quality (purity) and quantity (intensity) of the supplied RIB depends heavily on the proper tuning of the underlying process steps and their mutual interaction. From feedback of running ISOL facilities (ISOLDE/TRIUMF) it is known that the operation of an ISOL system needs constant intervention of an experienced operator/user. His job is to adjust the operational parameters of the system at a regular basis to compensate for effects likes ageing of the target and ion source, foiling of the extraction electrode, aligment issues due to temperature effects, etc ... . ISOL@MYRRHA aims at providing long uninterrupted beam times whichout compromising the quality and quantity of the beams to the users. An online optimization (retuning target, ion source and RIB transport parameters, ...) would unsure the continous delivery of the RIB to the users at optimal parameters and without interuptions. In this project, a control strategy will be developed to provide initial optimal selection of the control parameters as well as provide online tuning to keep the system continuously in the optimal operational regime.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
Flexible multi-domain design for mechatronic systems (Flexmosys_SBO).
Abstract
The Flexmosys project focusses on the co-design between multiple domains (such as structural component design, control design, software design, embedded design, …) for the development of mechatronic products. In order to develop improved mechatronic products (machines, vehicles, ...) in a shorter development time (by fewer iterations), this project aims at a cross-domain system model as the enabler for a more efficient collaboration environment between the different development teams. The project will therefore develop designer-centric methods and tools supporting the multi-domain development for these mechatronic systems. Starting from model-based design techniques available in the project team (such as ontological reasoning, co-simulation, parameter identification, sensitivity analysis and design space exploration), we will build methods and tools that will detect sensitivities of design choices from one domain to another, assure a consistent design across the involved development teams, and that allow for computationally efficient product optimization across the different engineering domains. The developed methods and tools will be validated on two industry-relevant demonstrators: an automotive electrical drivetrain and a high-performance drone. Eight companies have committed to participate in the Flexmosys user group. From the project results, they will ultimately benefit from fewer integration faults, a better overall design, visual information about the system's sensitivity on design choices, and more trustworthy system models and component models.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Goldilocks' Fusion: Adaptive and Robust Sensor Fusion in Resource-Constrained Robotic Systems.
Abstract
In recent years, autonomous robotic systems have gained lots of attention from the academic world and industry. The many applications in industrial fields going from manufacturing, mining and surveillance makes the study on autonomous systems interesting with lots of valorization potential. The cost of these autonomous systems is currently extremely high as expensive computational platforms and sensors suites are used to provide necessary levels of safety and autonomy. Using the measurements from different sensors, an environment representation is created to make navigational decisions. While the environment representation determines the complexity of the behavior that can be achieved, the detail stored in this representation is dependent on the available computational resources and sensor data. The goal of this research project is to enable an autonomous agent to select the optimal heterogenous set of sensors to create an environment representation of the appropriate complexity for the current situation. Resource awareness plays an important role in our research as we aim to reduce computational workloads on the autonomous vehicles, which means less expensive computational platforms can be used. Additionally, increased reliably and accuracy in environment perception will benefit the autonomy of these systems. Less expensive autonomous systems while being efficient in the use of resources will benefit and increase the adoption of autonomous vehicles.Researcher(s)
- Promoter: Mercelis Siegfried
- Promoter: Steckel Jan
- Co-promoter: Hellinckx Peter
- Co-promoter: Steckel Jan
- Fellow: Balemans Niels
Research team(s)
Project type(s)
- Research Project
Optimisation of the flexibility in a driveline through virtual engineering (OptiFlex).
Abstract
The OptiFlex project, executed by Ghent University, University of Antwerp, and KU Leuven, has developed rapid deployment methodologies and tools to quantify and simulate flexibility in drivetrains. As a result, flexibilities can be compensated by optimizing motion profiles and controller settings. This has led to notable successes, such as a speed enhancement of 52% in the cyclical motion of a loom machine and determining the impact of flexibility on the cutting accuracy of a plasma cutting table. These findings emphasize the significance of gaining knowledge about your drivetrain system and employing optimized motion controllers and motion profiles.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
Mixed absolute and relative localization (MARLOC).
Abstract
In this project, we will combine fixed infrastructure localization (markers, UWB) with relative localization perception (SLAM, odometry) to arrive at a highly accurate and robust location estimate for mobile robots. We will work on simulation models and performance prediction based on deep learning techniques to optimize the localization setup.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
Hydrophone Array Sensing as a Means for Subaqueous Monitoring.
Abstract
Over the last years CoSys Lab developed state of the art sonar sensors, sensor arrays, acoustic monitoring techniques and bioinspired sensing approaches, published them in high impact journals and successfully initiated industry collaborations. So far all the sensor systems were designed for airborne (ultra)sound, however, these systems can also be adapted to underwater acoustics and therefore broaden the field for applications both within research as in industrial collaborations. Therefore, we want to develop an underwater acoustics/sonar measuring device and need additional equipment (e.g. hydrophones, underwater speakers and data acquisition cards) that can provide us with ground truth benchmarking data in order to quantify the efficacy of our initial prototypes. We want to focus mainly on hydrophone arrays for bioacoustics research as we see here most potential for now, but in future our knowledge acquired in this project will help us to design 3D underwater sonar sensors.Researcher(s)
- Promoter: Laurijssen Dennis
Research team(s)
Project type(s)
- Research Project
ModAU - Modernized Auscultations for Remote Monitoring.
Abstract
In hospitals where there is a significant workload, performing auscultations can be a timeconsuming process, which also exposes the medical personnel to potentially contagious diseases. Current systems that allow remote auscultations are often not fit for use with large amounts of patients, long-term use, or are limited in terms of functionality. The major drawback in current remote auscultation systems is the relatively bulky acoustic coupler which makes part of the stethoscope assembly. This physical dimension reduces the applicability for long-term monitoring, because of the discomfort for the patient and the inherent risk of decubitus wounds. In this project, we will investigate the construction of thinner stethoscopes, increasing patient comfortResearcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
- Co-promoter: Jorens Philippe
- Co-promoter: Verhulst Stijn
Research team(s)
Project type(s)
- Research Project
Digital Twins for Continuous Deployment in Model-Based Systems Engineering of Cyber-Physical Systems.
Abstract
Cyber-Physical Systems (CPS) are required to operate over a longer lifetime. As such, the initial requirements can be changed, requiring the system to be updated continuously. These updates to the system must be rolled out continuously (Continuous Deployment) throughout the system's lifetime. The DevOps methodology provides a structured, quality assuring way to do so, as it integrates Development and Operations of a system in a continuous cycle. DevOps is generally applied in software development, however in the design of CPS, which follows a Model-Based Systems Engineering (MBSE) approach, it is not. This is because many challenges remain in the application of DevOps in MBSE. My focus is to create the foundations for continuous deployment of safety-critical CPS using digital twins of the CPS.Researcher(s)
- Promoter: Denil Joachim
- Fellow: Mertens Joost
Research team(s)
Project type(s)
- Research Project
Sparse interpolation potential in multidimensional optimisations.
Abstract
In engineering, simulations access the impact of design changes applied by engineers. Based on the simulation output, the engineer improves the design. Recently the engineer is replaced by an optimisation algorithm which adapts the design parameters to ensure optimal performance. Literature mentions case where applying these optimisation techniques leads to performance improvements up to 33%. However, current state-of-the-art very often relies on heuristic optimisation techniques. While they are easily applicable and suited for many applications, they cannot at all guarantee to find the global optimum. In contrast to local optima, the global optimum is the unique design which guarantees the best performance. Using optimisers which cannot guarantee the global optimum very often result in an untapped potential of up to 18%. Nevertheless, heuristic optimisers are still preferred in engineering as they do not require an exact mathematical model of the objective function. We propose to identify the mathematical model based on simulations standard in engineering practice. These simulations can deliver samples of the objective function based on specific settings for the design parameters. However, if the number of design parameters increases, providing an accurate grid of objective function samples becomes inconceivable as the number of necessary simulations explodes. Recent advances, obtained by the co-promotor, in multidimensional sparse interpolation will be a game-changer as it would reduce the number of necessary samples to an absolute minimum. By doing so, the underlying mathematical model we identify the objective function. This enables exact global optimisation. The research in this proposal will result in a generic workflow starting from commonly used simulations leading to a model via multidimensional sparse interpolation. The fact that such a model will enable global optimisation of engineering problems with multiple design parameters will be a genuinely fundamental novelty for the mechatronic state of the art.Researcher(s)
- Promoter: Derammelaere Stijn
- Fellow: Ben Yahya Abdelmajid
Research team(s)
Project type(s)
- Research Project
Intelligent Software Agents and Multi-agent Systems for the Lifecycle of Smart Cyber-physical System-of-Systems.
Abstract
AnSyMo (Antwerp Systems and Software Modeling) is a Computer Science research group investigating foundations, techniques, methods and tools for the design, analysis and maintenance of software-intensive systems. MICSS (Modeling Intelligente Complex Software and Systems) is a lab in AnSyMo group dedicated to the modeling of intelligent systems such as smart cyber-physical system of systems using intelligent agents and model driven engineering techniques. Cyber-Physical Systems (CPS) consist of tightly integrated and coordinated computational and physical elements. They are the evolution of embedded systems to a higher level of complexity, focusing on the interaction with highly uncertain physical environments (such as human interaction or wear & tear of devices). In these systems, embedded computers and networks monitor (through sensors) and control (through actuators) the physical processes, usually with feedback loops where physical processes and computations affect each other. The computational part of these systems plays a key role and needs to be developed in a way that can handle uncertain situations with the limited resources (including computational resource, memory resource, communication resource, and so on), mostly in real-time. With IoT and Industry 4.0 maturing, these systems are getting interconnected and making a complex larger system called the Cyber-physical System of Systems (CPSoS) to serve in more sophisticated tasks. In these systems, CPSs are working as part of a large system that is spatially distributed, has no central control, has autonomous subsystems, is dynamically configured, has emergent behaviour, and is continually evolving, even at runtime. A key point in CPSoS is to obtain knowledge out of the information that is collected by distributed monitoring of the environment, using artificial intelligence techniques. This knowledge can improve the control and feedback mechanism. Further, these capabilities lead to the smart systems of the future with timely and more accurate decisions and actions, called Smart CPSoS (sCPSoS), which can help to address a number of social, industrial, and environmental issues. This project aims to address the challenges of sCPSoS using intelligent agents and model-driven engineering techniques.Researcher(s)
- Promoter: Challenger Moharram
- Fellow: Karaduman Burak
Research team(s)
Project type(s)
- Research Project
Deterministic and inexpensive realizations of advanced control (DIRAC-SBO).
Abstract
The mechatronic machine building and manufacturing industry is currently facing various control challenges that simple PID controllers and alike fail to address: systems are increasingly complex, need to comply to constraints, need to account for economic objectives and effectively cope with valuable preview information. Model Predictive Control (MPC) is the only advanced control approach able to address all these challenges, and this thanks to its model-based and optimization-based nature. Yet MPC's optimization-based nature currently impedes wide adoption in industrial mechatronic systems: current MPC implementations are expensive in terms of computational and memory resources, computation time is non-deterministic and hence MPC algorithms cannot be certified to operate at a given sampling rate, MPC development and deployment is not straightforward and comes with a high engineering cost because proper tools are missing. The project "Deterministic and Inexpensive Realizations of Advanced Control" (DIRAC) aims for a breakthrough of MPC in the mechatronic/machine building/manufacturing industry by resolving all impeding elements through accomplishments that revolve around the three keywords in its title:  - Deterministic: Novel MPC algorithms and approaches will be developed that can run reliably at a given sampling rate as well as methods to verify their worst-case computation times and control performance.  - Inexpensive: Implementations will be created that approximate "full-blown" (=online nonlinear optimization with high fidelity models) MPC and hence can run on inexpensive computational hardware with a quantifiable impact on control performance that is computed upfront.  A modular MPC toolbox will be developed facilitating the development, tuning and validation of advanced control at manageable engineering cost. - Realizations: We will demonstrate the MPC toolbox and potential of MPC on industrially relevant demonstrators and validation cases in order to break the status-quo in control practices, foster take-up and inspire Flemish industry.  The overarching tangible reusable generic result of this project is a toolbox that simplifies design of nonlinear MPC controllers and brings methodological advances in solvers, approximations and validation techniques to the fingertips of control practitioners.Researcher(s)
- Promoter: Denil Joachim
- Co-promoter: Perez Guillermo Alberto
Research team(s)
Project type(s)
- Research Project
Modelling and Simulation of Cyber-Physical Systems
Abstract
Cyber-Physical Systems (CPS) consist of tightly integrated and coordinated computational and physical elements. They focus on interaction with highly uncertain environment with the limited resources. By introducing IoT and Industry 4.0, the CPSs are connected to each other to meet the emerging more complex requirements. These interconnected CPSs constitute complex systems called Cyber-physical System of Systems (CPSoS) in which there may be emergent behaviour, lack of central control, dynamic structure, and need for autonomy. Therefore, CPSoS cannot be designed and managed using theories and tools from only one single domain. A key point in a CPSoS is to obtain knowledge out of the information, collected by monitoring the environment. This knowledge can improve the control and feedback mechanism. This capability leads to the next generation of CPSoS with timely and more accurate decisions and actions called Smart CPSoS (sCPSoS). These smart systems can analyze a situation and make decisions based on the available data in an adaptive manner, to perform smart actions. However, such intelligent techniques put yet additional complexity to the systems, specifically to the computational part. Thus, these systems of the future have a high complexity (both from structural and behavioural points of view) throughout their lifecycle, including modeling & simulation, design & implementation, validation & verification, deployment, execution & monitoring, and maintenance & evolution. There is a need for new methodologies, architectures, process models, and frameworks to tackle this complexity. To overcome the challenges in the development and operation of sCPSoS, modeling techniques can be used for different aspect and various levels of abstraction in the system. To this end, appropriate modeling paradigms should be chosen for each aspect/level. These models and modeling paradigms will be integrated, hence called multi-paradigm modeling (MPM), to represent the whole system. Specifically, the idea is to integrate agent paradigm with the model-based system engineering (MBSE) for both modelling & simulation phase as well as execution and monitoring phase in the lifecycle of sCPSoS. Agent based system engineering (ABSE) uses software intelligent agents to successfully cross-fertilize the fields of systems engineering and artificial intelligence. In this way, the autonomy, dynamic behaviour and smart-ness of sCPSoS can be handled by intelligent agents, integrated with MBSE models.Researcher(s)
- Promoter: Challenger Moharram
- Fellow: Challenger Moharram
Research team(s)
Project type(s)
- Research Project
Foundations for Self-Adaptive Abstraction and Approximation in Real-time Cyber-Physical Systems (of Systems).
Abstract
Cyber-physical systems (CPS) are engineered systems that have a tight integration between the cyber part (computation and networking) and its physical components. Examples include but are not limited to industry 4.0, automotive and aerospace. To allow decisions to be made in a CPS (strategic control, tactical control and, low-level control), decision models are used. These models use input from sensors, but also from other supporting processes, e.g. predictions over the state of its contexts, to come to a control decision. The decision processes are implemented in software that runs on embedded hardware and is commonly real-time constrained, meaning that the time at which the decision is taken, is as import as the decision itself. In literature several techniques are available to reduce the computational cost of executing models by using abstraction and approximation (e.g. surrogate modelling). This reduced cost would make the process to come to a decision easier (scheduling) and would require less computational resources. However, we still need to be sure that the decision process is robust against approximations and uncertainties in these models. Furthermore, an approximated and/or abstracted model is most probable not valid in all the different contexts the system will be in. To enable this, the system should be able to switch at run-time between different abstractions and approximations. Therefore, this project will create the foundations to reason about dynamically adapting the decision models and prediction models with different abstractions and approximations depending on the context of the system. The project will result in a framework with supporting modelling languages, methods and proof-of-concept tools to reason on the trade-off between uncertainty (from the approximation) and the real-time behavior of the system.Researcher(s)
- Promoter: Denil Joachim
- Fellow: Biglari Raheleh
Research team(s)
Project type(s)
- Research Project
Echo-acoustic signalling of aposematic and cryptic insects – A bat inspired modelling approach (EchoBug).
Abstract
In this project we investigate acoustic aposematic signalling in insects. We combine acoustic measurements with computational bat behaviour modelling to gain insights into the effects of aposematic signalling on the bat's perception mechanisms.Researcher(s)
- Promoter: Steckel Jan
- Fellow: Geipel Inga
Research team(s)
Project type(s)
- Research Project
AutoRIO.
Abstract
In this project we develop robust navigation strategies for AGVs which need to operate in both indoor and outdoor conditions. We evaluate various sensor subsystems which can support the navigation applicationsResearcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
SmartFlush.
Abstract
In this project we develop smart flushing solutions together with our industrial partner, IPEE nv. We use advanced techniques to improve the processing of their proprietary sensor data. We also operationalize a deployement setup.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
EPSim - Embedded Platform Simulator.
Abstract
When designing a complex cyber-physical system, components of the system are often designed by different engineers, each with their own expertise in a particular domain, e.g. software, control, and mechanical engineering. In later design stages, the integration of the designed components into one system needs to be performed. This integration phase however often leads to unexpected problems such that the system does not function as it was intended. The goal of this project is to develop EPSim, an engineering tool which tackles an important integration problem between embedded engineering and control engineering. EPSim will focus on the particular problem that embedded platforms introduce time delays on the signal path that is used by the control engineers. Hereto, EPSim will allow for the virtual integration of embedded components into control loops already in early stages of the design process. This will ultimately lead to optimised design processes by reducing, or even avoiding, costly design iterations. The foundations of this idea have already been developed in our lab; the related method and tool is now situated at TRL 3. The current status is attracting attention from some mechatronic companies in the framework of an ICON-project, which is an appealing starting point for further valorisation. By means of this project, we intend to further develop the method and tool towards TRL 5.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
3D sonar sensing for inland shipping applications..
Abstract
In this project, we will evaluate the applicability of the eRTIS 3D sonar sensor in autonomous indoor shipping applications. We will collaborate with a supplier of indoor autonomous shipping solutions to provide an experimental platform which can be used to evaluate the sensing capabilities of the sensor setup. Furthermore, we will work on water-proofing of our technology, which is an important asset for the overall sensor performance.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Jansen Wouter
- Co-promoter: Kerstens Robin
- Co-promoter: Laurijssen Dennis
- Co-promoter: Verellen Thomas
Research team(s)
Project type(s)
- Research Project
Integration, deployment and operationalization of an experimental fluttering insect measurement sonar.
Abstract
In this project we operationalize an ensonification setup for fluttering insects. Through the implementation of a 32 channel phased microphone array in combination with a high-speed video camera we develop a multimodal setup which can record and localize echoes originating from fluttering insects. These echoes can be overlayed with high-speed video data.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Modelling and testing for total life cycle management in mechatronics.
Abstract
The complexity and intelligence of cyber-physical systems (CPS) are continually increasing. Developers and manufacturers of large systems such as industrial printing machines, many-sided agriculture machines, high-speed weaving looms, autonomous driving cars, up to highly safe commercial airplanes are confronted with common technical challenges that span the total product's life cycle from requirements capturing over design and validation up to product family management. In the current project, we will contribute to two main aspects of the mechatronics product life cycle: managing the complexity of evolvable CPS, and system level validation. We will therefore use state of the art model-based design techniques and mutation testing techniques. The objectives of the current project can be summarised as follows: - Becoming a partner in at least one European proposal related to the above topics. To this purpose, we will focus on dedicated networking activities with industry and academia in the European networks in close collaboration with the Nexor IOF valorisation manager. We will target projects in the Digital and Industry Cluster in Pillar 2 (Global Challenges and Industrial Competitiveness), mainly in the areas Key Digital Technologies, Artificial Intelligence and Robotics, Manufacturing Technologies, and Space, as well as in the Pathfinder grants of the European Innovation Council in Pillar 3 (Open Innovation). - Refining the AnSyMo and CoSys-Lab roadmap against the use cases defined by the problem owners within the European consortia we negotiate with. To this purpose, discussions with possible partners (see item above) must lead to better insights in the industrial needs for the upcoming CPS and to better insights in the objectives of the European project types. - At least one demonstrator showing the capabilities of the Ansymo and CoSys-Lab research groups on the related topics, i.e. on consistency management, orchestration, mutation testing, fault injection.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Towards optimal design, trajectories and control for repetitive movements.
Abstract
There is a strong desire to maximize the efficiency or speed of industrial machinery. Designers of machines, performing repetitive motions, often only define the position start- and endpoint of a movement and not the exact position function. This flexibility opens the opportunity to optimize the trajectory of the mechanism. Moreover, for the machine design itself, machine builders often rely on standard components and dimensions. The effect of the geometric design on the optimal trajectory and energy need of the system is very often neglected. The literature mentions cases where ad-hoc optimizations reduce energy usage up to 39% thanks to trajectory and geometric optimization. This project will use available CAD models and sparse interpolation to extract a closed mathematical system property description. This will enable using an interval optimization technique which can guarantee to find the one true global optimal geometric design and trajectory. The knowledge of the system properties will be used to design a robust controller to ensure the machine follows the desired trajectory. Finally, any mismatch between the virtual and real model will be detected with online tracking techniques to assure the machine operation remains optimal. The potential impact for machine builders is high as this project enables them to construct machines with a reduced total cost of ownership or allow them to perform a task as fast as possible purely based on their readily available CAD models.Researcher(s)
- Promoter: Derammelaere Stijn
- Co-promoter: Cuyt Annie
- Fellow: Van Oosterwyck Nick
Research team(s)
Project type(s)
- Research Project
Scientific chair 'Industrial Acoustic Condition Monitoring'.
Abstract
In this research chair we will investigate the efficacy of array signal processing for industrial condition monitoring. Through the combination of novel embedded systems technologies as well as advanced signal processing paradigms we will create an experimental setup with which advanced condition monitoring and predictive maintenance scenarios can be investigatedNResearcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Optimal machine design by means of virtual engineering (OPTIMOTION)
Abstract
The overarching objective of this project is to develop tools and train the members of the target group in their usage. These tools should allow the straightforward optimisation of the mechanical design of machines and their drive system. Optimizing the placement of essential machine parts and optimising the selection of drive components can minimize the drive torque required for a machine. This optimisation potential can be fully exploited if the motion controller that drives the whole is properly tuned. All Flemish companies involved in mechanical engineering operate in a competitive market and are under pressure to optimise their machine design. More specifically, this project is aimed at machine builders, engineering consultants and suppliers of drive components and CAD software.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
A Hybrid SLAM approach for autonomous mobile systems (HySLAM_SBO).
Abstract
In HySLAM,we will investigate the introduction of semantics in SLAM. We will introduce new probabilistic models which are based on scene understanding to increase the conditioning of the SLAM problem. Taking into account the underlying dynamics of the objects, and their effect on the perceptual scene, can help to increase the robustness of the SLAM algorithms. We will demonstrate the efficacy of the algorithm in a 2D and 3D test case.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
HR-RTIS: High-Resolution Real Time Imaging Sonar Sensor.
Abstract
For autonomous vehicles, sonar sensors can pose a real alternative to optical sensing techniques such as laser scanners and 3D cameras in situations where these optical techniques fail. The failure of these optical systems can be caused by medium distortions such as dust or fog, or sensor contaminations such as mud splashes. In the CoSys research group we develop advanced 3D sonar sensors for industrial applications, which are currently being validated in various industrial application niches. During this proposed STIMPRO project we propose to expose the uncover the dynamic range in the strengths of echoes created in relevant industrial environments and their spatial distribution in that environment. To this extend, we propose a high-resolution microphone array consisting of 1000 microphones, which will allow the creation of high-resolution and high dynamic range 3D sonar images. The sensor will provide us with essential insights into the reflective properties of relevant environments and will allow us to improve the low-cost sensors which we are famous for worldwide.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Development of a priori and online trajectory optimisation for repetitive motions.
Abstract
As global energy demand will continue to rise and man's negative impact on global warming is known to be a fact, there is a strong desire to minimise the energy usage of industrial machinery. A significant opportunity lies in optimisations which do not require any adaptations or investments in installed hardware such as trajectory optimisation. Machine builders and users often only define the time to move from one point to another and the position of start- and endpoint. The exact position as a function of the time, or position function, in between these two points is very often not an issue for machine users. This flexibility opens the opportunity to optimise the position function. The literature mentions cases where ad-hoc optimisations reduce the energy usage of machinery used for repetitive tasks up to 50% by choosing optimised trajectories over the usual standard movement profiles. However, there is no scientific consensus on a computationally efficient technique which can guarantee to find the global optimum for systems with position varying mechanical load properties. Therefore, this project will assess the use and implementation of direct calculus optimisation. Applying this pure mathematical technique based on symbolic methods of trajectory optimisation would be a genuinely fundamental novelty, especially for machines with position varying dynamics. For one thing, this would eliminate the necessity of time-consuming iterative optimisations. On the contrary, direct calculus methods would lead to closed mathematical functions for the position function. To enable the use of this direct calculus methods, closed mathematical equations, describing the position-varying mechanical load properties, will be necessary. Obtaining such functions can be done theoretically based on Lagrange formulations. However, such an approach is not feasible in practice where the complexity of the machinery hampers analytical analysis. On the other hand, machine builders increasingly rely on CAD multibody software to design their machines. The promotor has expertise in extracting data by applying specific simulations on these virtual CAD models. The sampled data, obtained in this way, can be translated to explicit formulas, based on the expertise of the co-promotor. Developing such a technique to transform the sampled data to closed mathematical equations will be a core challenge of the project and the major enabler to apply direct calculus optimisation. Furthermore, to guarantee the machine still operates at its optimum if machine behaviour changes during operation, an online tracking method is necessary. For this purpose, the knowledge of the promotor on tracking the position dependency of machine parameters online in the frequency domain is essential. The data samples obtained in this way will again be translated to a mathematical description to allow a re-optimisation of the trajectory. For this purpose, the direct calculus optimisation method will be advantageous as it defines the optimised path as a function of position varying parameters. This definition enables direct re-optimisation. Moreover, where the current state of the art focusses on offline a priori or online optimisation, facilitating online re-optimisation based on a priori offline determined information will be another fundamental novelty of this project.Researcher(s)
- Promoter: Derammelaere Stijn
- Co-promoter: Cuyt Annie
- Fellow: Van Oosterwyck Nick
Research team(s)
Project type(s)
- Research Project
Product-Assemby Co-Design (PACo).
Abstract
The Product-Assembly Co-Design (PACo) project is a project within the scope of the cluster Design & Optimisation of Flanders Make. The project aims at bridging the gap between product design and assembly system design by incorporating assembly knowledge into the early stages of the product development. Today, most companies consider assembly aspects later in the design process, often in a manual way, solely relying on the experience of assembly engineers. This leads to numerous design changes later on, causing significant extra costs. The current industrial context requires companies to aim at a first-time-right, down to lot size 1 at the cost of volume production strategy. Hence, considering assembly aspects too late or in a trial-and-error way is no longer an option. All companies involved in the user group of this project indicate a clear need to support their engineers with methods and software tools enabling assessment of assembly complexity in an early design stage, allowing co-optimization of product performance with ease-of-assembly in a quantitative way, and allowing trade-off analysis of various solutions. As these software tools are beyond the state-of-the-art, the research partners (FM-CodesignS, FM-ProductionS, AnSyMo/CoSys-lab, DMMS, and EEDT) will join forces to shift the state-of-the-art in product-assembly co-design, aiming at the following innovation goals: (1) a software environment for the formalization of assembly knowledge (e.g. Design-for-Assembly rules, assembly complexity metrics), (2) tools and algorithms for automated multi-objective optimization of the early-stage design of a product, taking into account the product performance and its assembly complexity, (3) tools and algorithms to automatically find the optimal assembly process (order of steps) and assembly system (resources allocation), for a given product design and a framework for the co-design of both product and its assembly system by combining both 1) and 2) in a semi-automated workflow.Researcher(s)
- Promoter: Denil Joachim
- Co-promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
High-efficiency Sensorless Control of a BLDC Motor using Sinusoidal Currents.
Abstract
A Brushless DC Machine (BLDC) is the optimal motor to use in applications where a more or less constant, controlled, high rotational speed is required. Typical examples include driving: the compressor of a cooling system including refrigerators and air-conditioning, the propellers of a drone, fans and pumps in general, …. The BLDC is responsible for the lion share energy usage of these applications. Moreover, cooling systems consume a lot of energy worldwide because of their ubiquitous presence. On the other hand, for battery fed systems such as drones there is strong desire for increased autonomy. This means there is a strong desire to reduce the energy usage of BLDC driven systems. BLDC motors are typically driven with a square wave current. On the other hand, using sine wave currents could result in an energy efficiency increase of 10%. However, typical BLDC algorithms lack feedback to drive the machine with sine waves. Using an encoder to obtain this position feedback would increase the cost and complexity of the drive system and can be impossible due to limited mounting space. Therefore, so-called sensorless algorithms which estimate feedback signals based on easily measurable voltage and current signals, are of interest. Consequently, the central research question of this STIMPRO is formulated as: Develop and implement a sensorless algorithm to provide feedback for a BLDC drive algorithm using sinusoidal current waveforms and validate its energy saving potential. As a starting point this STIMPRO will consider an estimation algorithm, developed by the promotor, for stepping motors, to use in BLDC drives. This STIMPRO will be used as a kick-start to initiate electrical motor control research at ¶¶Òõ¶ÌÊÓƵ. This project will serve as leverage to move the activities off the promotor in motor control, who started at ZAP at ¶¶Òõ¶ÌÊÓƵ the 1st of September 2018, previously established at UGent to ¶¶Òõ¶ÌÊÓƵ. To do so, the STIMPRO will be used to hire a researcher who will submit an FWO SB proposal. However, if FWO funding is rejected we will not finish this project empty handed. Given the work plan defined in the STIMPRO, and the experience of the promotor the project will certainly result in publications, a test bench, added experience for the hired researcher and the exploration of possible bilateral collaboration with Flemish companies on the subject. The work done in this STIMPRO will be beneficial for the Op3Mech research group as adding research on electrical motors is a vital in the broader robotics research. Moreover, the education on drivelines at the Faculty of Applied Engineering is currently not supported by academic research. Therefore, the research activities initiated in this STIMPRO are vital to continue education on these topics.Researcher(s)
- Promoter: Derammelaere Stijn
Research team(s)
Project type(s)
- Research Project
AirLeakSLAM: On-line detection of pressured-air leaks in industrial environments using passive and active ultrasonic sensing.
Abstract
A large amount of energy is lost annually due to leaks in compressed air networks. The combination of SLAM and 3D-ultrasonic measurement techniques enables to automate the measurement and registration of these leaks without requiring manpower. Therefore, measurements can be conducted in a continuous (on line) instead of an incidentally manner. The goal of the project is to demonstrate the power and the opportunities of the system for the user of the compressed air system, and to further quantify the value creation opportunity.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
Automated and simulation based functional safety engineering methodology (aSET_ICON).
Abstract
Due to the trend towards more complex safety-related products combining mechanics, electric components, electronics and software, their design and development become more complex, leading to longer development times and higher costs as well as higher risks on errors with highly manual safety engineering processes. The goal of the aSET-project to develop methodologies to automate the functional safety engineering process to make the process less error prone and to reduce the required design time and cost compared to the current manual state-of-the-practice. More specifically, the objectives of the project are: (i) the development of a Functional Safety Formal model implemented in a persistent way enabling the intrinsic coupling between all Functional Safety artefacts requested by ISO26262; (ii) the development of a method and demonstrator tooling for the translation of textual requirements into mathematical equations (that can serve as a design contract for the actual hardware design) that describe functionality of E/E/PE enabling the automation of HARA with the help of a functional E/E/PE model and plant model; (iii) the validation of these methods in a generic use case as well as in different industrial use cases demonstrating their functionality and the targeted design time and cost gains.Researcher(s)
- Promoter: Denil Joachim
- Co-promoter: Vangheluwe Hans
Research team(s)
Project type(s)
- Research Project
Avoidance of collisions and obstacles in narrow lanes (AVCON_ICON).
Abstract
In this project, we will investigate various methods for implementing obstacle avoidance in narrow corridors. We design a suite of sensors which provide the control algorithms with the required information.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Dotation for the structural collaboration with Flanders Make.
Abstract
Flanders Make's mission is to strengthen the international competitiveness of the Flemish manufacturing industry on the long term through industry-driven, precompetitive, excellent research in the field of mechatronics, product development methods and advanced production technologies and by maximizing valorisation in these areas.Researcher(s)
- Promoter: Denil Joachim
Research team(s)
Project type(s)
- Research Project
Concurrent design of control, embedded hardware and software for mechatronic and cyber-physical systems (CSE_codesign_ICON).
Abstract
General objective: The main goal of this project is to develop a design approach and the necessary computational tools that enable the concurrent design of application software, embedded software and hardware platforms, ensuring the targeted closed-loop performance of cyber physical systems. This with the aim to increase the efficiency of the design process and yet reducethe costs of the associated embedded software and hardware platforms. Concrete goals: More specifically, the innovation goals of this project are to: 1. Develop a methodology and software tools to support the concurrent design of application software and embedded platform for individual cyber-physical product variants: - enabling both control engineers and embedded platform engineers to perform a trade-off analysis between various design choices on application and platform level in an agile manner, i.e. without long iteration loops, thereby reducing the typical development time of an embedded control application with at least 25%. - improving the cost-effectiveness of embedded platforms by at least 10%, by considering stochastic delays instead of using 'worst case' response times and bus delays, without sacrificing the stability, performance and robustness of the closed-loop behaviour. 2. Investigate the feasibility of extending the above approach with design space exploration techniques that automatically select the most optimal design alternative in terms of application/platform design choices in the large space of possible solution alternatives. 3. Develop an approach and software tools to support trade-off analysis and design space exploration for the embedded platform selection and design in the case of complete mechatronic/cyber-physical controller product lines. Building further on these methods and tools, the company partners in this project aim to realize the following targets: Atlas Copco's main goal is to create an approach, a software framework and the accompanying development tools that support their designers responsible for implementing the compressor room control to select the most appropriate software and hardware platform deployment and configuration, guaranteeing the required compressor room performance under all circumstances. Picanol wants to increase the performance and quality of its weaving machines by improving the co-design between the control software and embedded platform engineers. More specifically, Picanol wants to deploy this co-design approach to the yarn insertion subsystem of all machine variants, thereby increasing the production capacity of these variants with 2% or reducing the air consumption with the same amount. Tenneco's main goal is to select a set of embedded and power electronics hardware platforms that cost-optimally cover their complete product line of electro-magnetic shock absorbers from low-end to high-end vehicles. The approach and tools that allows to select this set of platforms should also be applicable to other Tenneco product lines. Michel Van de Wiele (MVDW) wants to select a new, durable and modular embedded hardware and software platformthat is capable of controlling today's and tomorrow's weaving machinery. Specifically, for the same loom requirements a reduction of the hardware cost by at least 10 % is targeted or with the same hardware cost, the target is to realize an increase in machine speed of 10 to 50 % or being able to deal with at least 10 % more sensors / actuators. Next to this, MVDW also aims to update their design approach and tools such that designers can easily predict a priori if the embedded controller for a particular variantResearcher(s)
- Promoter: De Meulenaere Paul
- Co-promoter: Hellinckx Peter
Research team(s)
Project type(s)
- Research Project
INES - Innovation in the development of Electronic Systems for Aeronautics .
Abstract
The INES project, a project consortium with its Flemish component Siemens Industry Software (with its subcontractor Siemens CT) and University of Antwerp, and its Spanish component Boeing Research & Technology Europe (with its subcontractors GMV and Skylife), coordinated through the Eureka program, aims to develop a realistic, innovative and implementable MBSE process as well as identify a series of software tool innovations that cover the complete development and life cycle of avionics systems (understood as the electronic systems of the aircraft including its avionics controller algorithm, software and hardware), which would, within two years, offer an paradigm shift for the development of aircraft electronic systems (avionics), whose objective would be to achieve much higher levels of quality at a reduced development cost with respect to current technology.Researcher(s)
- Promoter: Denil Joachim
Research team(s)
Project type(s)
- Research Project
European initiative to enable validation for highly automated safe and secure systems (Enable S3).
Abstract
In this project, CoSys-Lab provides support for embedded realisations with AUTOSAR and Hardware-in-the-Loop testing. By means of practical case studies, best practices on the engineering methods and related tooling is collected. The application field is mechatronics and automotive engineering.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
RAAK-MBK program "COMBINE".
Abstract
In this project, we contribute to the technology transfer of Hardware-in-the-Loop test technology for embedded systems in automotive. The focus is on process modelling of the test strategies and demonstrating them in industry-relevant applications.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Biologically-inspired 3D radar sensor supporting intelligent robotic behavior in complex and cluttered environments.
Abstract
The goal of this research is to produce a compact, light-weight sensor which will enable an unmanned aerial vehicle to autonomously traverse trajectories through cluttered environments, such as a forest, while sensing and avoiding objects. The sensor is inspired by biological echolocation as performed by bats, which involves emitting an ultrasonic signal and closely listening to its reflections. By analyzing how each received echo differs from the emitted signal and how they mutually vary between its two ears, the bat can determine where the object which reflected the signal is located. Additionally, using sequences of these echoes makes is possible to determine the movement through the environment. We will mimic these features in our system to achieve the same results. For our application we use radio waves (radar) instead of sound (sonar), because these travel at a much greater speeds, while allowing the sensor to operate under circumstances where optical cameras would fail, such as at night, in rain, fog, smoke, etc. Furthermore, we propose a control scheme inspired by cognition, such as insect intelligence, to steer the robot. The idea is to implement a layered system of behavioral units, each with its own goal. Examples of these units include, stopping to avoid a collision, dodging an obstacle, and following a corridor. The system will then execute the behavior with the highest priority which is active at each given moment, creating an overall emergent intelligence.Researcher(s)
- Promoter: Steckel Jan
- Fellow: Schouten Girmi
Research team(s)
Project type(s)
- Research Project
Advanced array signal processing for industrial in-air sonar applications.
Abstract
This basic research project seeks to advance our knowledge of in-air sonar sensing towards new industrial applications where traditional sensing techniques (optical, radar) suffer from physical limitations such as the environment (dust, mist) or limited object reflectivity (RF penetration). The knowledge gaps, identified by previous industrial collaborations, are to be answered by a mix of algebraic analysis, numerical computations and experimental prototype engineering. The focus will be on the application of advanced array signal processing techniques and real-time embedded systems. The outcome of this project will be a strengthened knowledge of in-air sonar sensing and additional background IP for future projects concerning economic exploitation of our technology.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
TCO optimal system design for energy and power storage in dynamic load applications (EnPower_ICON)
Abstract
The goal of this project is to develop and validate a system design methodology for drivetrains and energy systems combining multiple energy sources and storages. The methodology will deliver an optimal system design in respect to TCO, Performance and Functional Safety cost.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Localization system for accurate tracking and navigation for autonomous operation (LOCATOR_ICON)
Abstract
In order to choose the right combination and placement of sensors to perform sensor-fusion based indoor localization in industrial environments, a framework for designing systems for global and relative localization can facilitate the development. To quantify the performance of various sensors in this operational context, models of these sensors need to be developed. These models will be probabilistic in nature in order to be used with the aforementioned sensor fusion techniques and to calculate confidence intervals where safety is an issue. The sensor models will be parametrized and will be able to incorporate in-situ experimental measurements to make the simulations more accurate.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
Scale-free passive acoustic localization using a wireless synchronized sensor network.
Abstract
During this project we will develop a framework which allows passive localization of acoustic sources using a synchronized wireless sensor network. Synchronization of the wireless microphone array will be performed using a distributed synchronization scheme absent of a master time representation. The framework will support automatic calibration of the microphone array with minimal human intervention. The location estimate of the acoustic sources will be performed using a probabilistic localization algorithm in combination with known statistics about the behavior of the acoustic source. The framework will be virtually scale-free, which means that the sensor network can be used for tracking a wide variety of acoustic sources in a wide variety of application domains.Researcher(s)
- Promoter: Steckel Jan
- Co-promoter: Daems Walter
- Fellow: Verreycken Erik
Research team(s)
Project type(s)
- Research Project
Model based force measurements (MoForM).
Abstract
Knowledge on (internal and external) dynamic forces and torques is of crucial importance, both during the prototype development phases of mechatronic products, machines and processes, as well as during their operational lifetimes. Measuring forces is a time consuming, error-prone, expensive and often intrusive process. Furthermore, it occurs regularly that force measurements at the desired locations are prohibited due to space limitations or too harsh circumstances. The main goal of the project is to develop a breakthrough force/torque measurement technology by adopting a virtual sensing strategy. This involves the evaluation and development of single (Kalman filter based) and multistep (Moving Horizon Estimation based) estimators that combine high-fidelity physical models and physically inspired grey box models with affordable non-intrusive sensors to retrieve unknown forces in a fast (possibly real-time), accurate, in-situ and on-line manner. The targeted performance is defined in cooperation with industry and spans from real-time in-situ force estimation with a 10 Hz bandwidth and a 20 dB dynamic range to on-line in-situ force estimation with a 200 Hz bandwidth and an 80 dB dynamic range. The estimation technologies should be able to account for the non-linear dynamic effects as encountered in mechatronic drivetrains and systems.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Embedded and distributed systems.
Abstract
Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. Distributed embedded systems play a very important role in everyday life, now and even more so in the near future. Many of these embedded systems have one or more sensors for measuring physical quantities like the room's temperature or the position of a person in the building. Due to the increasing functional complexity of the desired applications in combination with the intricate interplay between the components of the system, it can become difficult to optimize the overall performance manually. Furthermore, the current desire for quick time-to-market demands quick design processes focused on adaptability of the design. One way to achieve this quick time-to-market is the (partial) automation of the design process. As the system has to operate in real environments using real sensors, the environment where the system operates in has to be included in the model as well. Simulating physical quantities and realistic environments can become very complex very quickly. The time that has to be invested for achieving accurate simulation results can become too much. Experimental setups can provide the data which is needed to avoid the need for complex simulations. Therefore, a Hardware-in-the-loop and Sensor-in-the-loop approach will be adopted to provide the relevant data at the right time of the modeling process. Strategies for the right spatio-temporal sampling and the right moment to apply HIL/SIL methods are important questions to answer. Once the complete system has been modeled using the realistic models and the platform-specific constraints, hardware generation (VHDL, analog schematics, etc.) and code generation (C-code for embedded processors) from the high-level model can be used to accelerate the design cycle. Large functional changes often translate to small changes in the high-level model, and results often in large changes in the low-level representation. Using the right type of code- and hardware-generation can accelerate the design cycle significantly. Code generation can also be used in the form of prototyping platforms such as large FPGA's to accelerate certain sub-models of the MBD-design. HIL/SIL systems also allow for real-time performance to give rise to sensor flow, which is very important in a wide range of applications.Researcher(s)
- Promoter: Steckel Jan
- Fellow: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Timing Analysis for Real-Time Embedded Multicore Software.
Abstract
Multicore processors are increasingly used in mechatronic applications and need to endorse the realtime requirements of the related embedded software. In spite of their huge processing power, certain operational conditions may arise in which they show longer software execution times than reasonably expected. In this project, we will elaborate software timing analysis techniques which will lead to better configurations of multicore platforms with respect to the software execution time and more specifically to the unexpected outliers mentioned above. To this purpose, we will propose a modelling language that will allow for a formal description of the timing properties of real-time embedded multicore software. This modelling language will enable formal methods for schedulability analysis and design space exploration methods, such that timing outliers can be eliminated by suggesting alternative configurations for the multicore platform.Researcher(s)
- Promoter: De Meulenaere Paul
- Co-promoter: Denil Joachim
- Co-promoter: Hellinckx Peter
- Fellow: Li Haoxuan
Research team(s)
Project type(s)
- Research Project
Cost-effective vibroacoustic monitoring (vibmon_icon).
Abstract
The Cost effective vibroacoustic monitoring project will attempt to prove the technical and economic feasibility of cost effective vibroacoustic monitoring systems for continuous online condition and process monitoring of rotating machine elements in quasi stationary conditions. The project will make use of new opportunities enabled by the advent of cost effective sensors, like MEMS accelerometers, microphones, and microphone arrays, and cost effective embedded platforms that in combination can provide an efficient solution for continuous monitoring. The generic part of the project will assess the technical limitations of cost effective sensors compared with high-end ones and will overcome this limitations by develop novel digital signal processing algorithms for: • Automatic pre-processing and data cleaning of raw data recorded by cost-effective sensors in order to eliminate non-physical features present in the signals generated by certain cost effective sensors; • Feature extraction for fault detection and identification that can provide reliable diagnostic information and can deal the technical limitations of cost-effective sensors like limited bandwidth, high noise density, and lower sensitivity; • Online tachometer-less estimation of rotational speed in order to reduce the cost of the total solution by eliminating high precision speed sensors; • Reducing of the amount of data generated by the monitoring system while maximizing the amount of information to diminish the communication and data stream handling costs; The project will develop a technology validation platform for a cost effective vibroacoustic monitoring system including sensors, acquisition hardware, embedded processing unit and local digital signal processing software.Researcher(s)
- Promoter: De Meulenaere Paul
- Co-promoter: Daems Walter
- Co-promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Mobile Robotic Platform for Embodied Sensor Development
Abstract
This project aims at implementing a mobile robotic platform for supporting our research effort concentrated at the development of intelligent sensors for healthcare applications. The robotic platform will support our research effort by enabling the collection of large amounts of experimental data for extracting sensor models, calibration algorithms and in the development of sensors aimed at the application in autonomous robotic systems.Researcher(s)
- Promoter: Steckel Jan
Research team(s)
Project type(s)
- Research Project
Dotation for the structural collaboration with Flanders Make.
Abstract
Flanders Make's mission is to strengthen the international competitiveness of the Flemish manufacturing industry on the long term through industry-driven, precompetitive, excellent research in the field of mechatronics, product development methods and advanced production technologies and by maximizing valorisation in these areas.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project
Service/Reuse for Assistive technology Delivery/design (SeRenADe).
Abstract
This project represents a formal research agreement between UA and on the other hand Gouverneur Kinsbergen Centre. UA provides Gouverneur Kinsbergen Centreresearch results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: Daems Walter
Research team(s)
Project type(s)
- Research Project
MBSE4 Mechatronics.
Abstract
This project represents a research agreement between the UA and on the onther hand IWT. UA provides IWT research results mentioned in the title of the project under the conditions as stipulated in this contract.Researcher(s)
- Promoter: De Meulenaere Paul
Research team(s)
Project type(s)
- Research Project