The AI-driven Factory: Optimizing Industrial Performance
Are you a production company aiming to automate operations, digitize processes end-to-end, or improve the performance of your industrial machines? Or are you a machine builder looking to integrate AI into next-generation industrial machinery? Join us at Vandewiele in Kortrijk for a free half-day session showcasing how AI is driving tangible impact in Flanders’ manufacturing sector.
Practical information:
Want to register?
- Register until: 05 Jun 2025
- Price: Free
Organised by:
Programme
14.00 - 14.30 Welcome & Introduction
Vandewiele Group, FAIR & VAIA
14.30 - 15.00 AI in Action: Transforming Manufacturing for the Digital Age
Abdellatif Bey-Temsamani (Flanders Make)
15.00 - 15.30 Infinity – Straight-through-Digitalization in manufacturing and beyond
Bert Pluymers (KU Leuven)
15.30 - 15.45 Coffee break
15.45 - 16.15 Classical control meets AI - Combining the best of both worlds
Jeroen De Maeyer (UGent)
16.15 - 16.45 Multi-view data exploration recipes for making sense of multi-source data originating from fleets of industrial Assets
Elena Tsiporkova (Sirris)
16.45 - 17.05 Ambitions and applications of AI today
Steven Thielemans (Vandewiele Group)
17.05 - 18.05 Networking reception
AI in Action: Transforming Manufacturing for the Digital Age
By Abdellatif Bey-Temsamani (Flanders Make)
Production optimization, smart machines, and autonomous production floors are becoming increasingly accessible and cost-effective in the era of Digital Transition and Artificial Intelligence. The convergence of advanced data analytics, machine learning, and edge computing is enabling manufacturers to rethink traditional processes and unlock new levels of efficiency, flexibility, and responsiveness. In this presentation, we provide a comprehensive overview of industry-inspired use cases where AI technologies have been effectively applied to enhance existing production systems by embedding intelligence at various levels. These solutions are particularly aimed at managing and adapting to variability—whether it involves dynamic tasks, fluctuating asset conditions, product customization, or changing operational environments. Through real-world examples, we will illustrate how AI-driven systems can enable predictive maintenance, real-time quality control, autonomous decision-making, and intelligent operator support, thereby transforming conventional factories into smart, adaptive, and future-ready production environments.
Infinity – Straight-through-Digitalization in manufacturing and beyond
By Bert Pluymers (KU Leuven)
Leveraging on the concept of Digital Twins, the manufacturing industry is at the verge of fully exploiting Industry 4.0’s digitalization potential. Digital information (digitized knowledge, simulation models, test data, production data, etc.) is becoming available in potentially large amounts during the different stages of product design and manufacturing: from early concept design, over detailed design and analysis, virtual and physical prototyping, product validation, commissioning, production and assembly, quality control, the operational product in‐use stage, and even the end‐of‐life (re‐use, re‐cycling, re‐manufacturing) stages.
Digital Twins enable collecting and comprehensively managing all digital information linked to a unique product asset (from the different product design, manufacturing stages and operational usages). They allow to connect information from the stage where it is created to other stages and to generate added value by digitally connecting these stages in a closed loop. As such, the amount of available information and knowledge substantially increases and more optimized and effective decisions can be taken; for instance O&M strategies not only exploit online operational data, but also manufacturing quality data from when individual components were manufactured, quality control data capturing possibly minor quality issues, and even physical behavioral models from the product design stage exploited now for performing virtual scenario analyses to find the most optimal future operational regimes.
Beyond applications in mechanical engineering, the developed Digital Twin concepts are also being introduced in other fields such as sustainable chemistry and health applications.
Classical control meets AI - Combining the best of both worlds
By Jeroen De Maeyer (UGent)
As today’s industrial processes become more complex, controllers used in drivetrains for vehicles, machines, robots, process facilities, and other physical dynamic systems face increasing challenges with respect to e.g. efficiency and quality. In an industry 4.0 setting, a higher level of adaptivity and automation is required. Meanwhile, artificial intelligence (AI) is a promising enabling technology. However, examples wherein AI techniques such as reinforcement learning (RL) are directly in control of (high) power (up to kW) and (highly) dynamic (down to (m)s)) physical systems to improve energy efficiency and performance remain very limited.
Going beyond the fixed but safe structure of classical controllers and embracing the RL framework provides the ability to learn and adapt. While doing so, expensive trials and unsafe experimentation on real systems as is common in RL need to be avoided.
We have been working on a fundamentally new approach residing at the intersection of classical control and RL (CTRLxAI). Besides offering increased efficiency and performance (thrust) of the adaptive and autonomous controllers, we will strengthen the trustworthiness (trust) in terms of sample-efficiency, robustness, safety and explainability; critical capabilities for widespread industrial adoption. As such, we will realise our vision CTRLxAI=T(H)RUST.
Multi-View Data Exploration Recipes for Making Sense of Multi-Source Data Originating from Fleets of Industrial Assets
By Elena Tsiporkova (Sirris)
Fleets of industrial assets, such as wind turbines, compressors, pumps or heavy-duty vehicles, generate large data streams which can be used for different purposes, e.g., condition monitoring, anomaly detection and ultimately, prediction of eminent failures. However, making sense of real-world industrial data is challenging as it typically originates from different, highly heterogeneous sources, such as sensor measurements, configuration settings, and/or log records stemming from different components and assets. Applying off-the-shelf data modeling strategies and artificial intelligence (AI) algorithms does not necessarily yield relevant insights, as these methods struggle to handle the complexity, variability, and domain-specific constraints of such industrial multi-source data. In this talk, we will demonstrate how to bridge this gap, by outlining three multi-view data exploration recipes able to effectively integrate, analyze, and derive actionable insights from multi-source data originating from fleets of industrial assets.
How to bring value using AI as machine builder
By Steven Thielemans (Vandewiele)
Data and using data in AI algorithms open up a whole world of possibilities and opportunities. As possibilities seem endless, choices have to be made and priorities need to be defined. What is the solution to offer to our customers? What brings value and where can this bring revenue to Vandewiele? A short introduction in our journey of defining the AI projects in Vandewiele.
Teachers/speakers
Elena Tsiporkova
Elena Tsiporkova is presently leading the EluciDATA Lab by Sirris. Elena is in the unique position to have extensive R&D experience, both in an academic and an industrial environment. She holds a PhD in Applied Mathematics from UGent and her academic career of almost 15 years includes diverse research assignments (e.g. assistant-professor, research scholar, postdoctoral fellow, …) at universities in Bulgaria, Belgium, Austria, Germany and the UK. Subsequently, she has worked for several years in an industrial context before starting at Sirris, which as an industrial research centre is the perfect marriage between academic and industrial research. Elena has played a key role as the main initiator and driving force behind the creation and establishment of The Data and AI Competence Lab, which she presently leads. Elena has been active for more than 30 years in the fields of data analytics and AI in very diverse application domains e.g. speech processing, bioinformatics, knowledge engineering and multimedia. She has authored more than 100 scientific publications.
Abdellatif Bey-Temsamani
Abdellatif Bey-Temsamani is an engineer and a researcher specializing in artificial intelligence, computer vision, and Industry 4.0 technologies. He holds a PhD in Applied Sciences from the Vrije Universiteit Brussel, where he focused on underwater acoustics. Currently a senior project leader and AI team leader at Flanders Make, he leads industrial research projects aimed at developing intelligent machines, smart vehicles, and advanced production systems. With over 50 scientific publications, his work covers machine learning for process monitoring, 3D pose estimation, and synthetic data generation. He has also contributed to innovative machining technologies, including vibration-assisted drilling and smart clamping systems, particularly for aerospace manufacturing. He is recognized for his impactful role in bringing AI-driven solutions to modern industrial challenges.
Bert Pluymers
Dr. Ir. Bert Pluymers is appointed as Senior Industrial Research Manager at KU Leuven, where he is the contact and interface person for technology transfer for the division LMSD (Leuven Mecha(tro)nic System Dynamics). In this role he is a bridge-builder between industry and academia. He is also the coordinator of the Flanders Make @ KU Leuven Community, i.e. the KU Leuven participation within the Flemish strategic research centre for the manufacturing industry – Flanders Make. He is active in European research platforms such as EARPA (European Automotive Research Partners Association), 2Zero (Towards zero emission road transport co-programmed partnership), CCAM (European partnership on Cooperative, Connected and Automated Mobility), EFFRA (the European Factories of the Future Research Association) and the new Virtual Worlds Public-Private-Partnership. He is one of the driving forces behind the Straight-through-Digitalization in manufacturing concept, which also shapes one of the industry Use Cases within FAIR. Linked to this concept, he is one of the initiators of the brand-new KU Leuven/Vives Infinity Lab in Kortrijk.
Jeroen De Maeyer
As a business development manager I work together with 200 researchers (of which +/-30 professors) in the field of electromechanical, industrial systems engineering and industrial economics working on smart motion products and smart production systems. My specific role is to define and follow up actions to bring our research into real life i.e. commercialisation, by setting up interactions with the (regional and international) industry and/or through the creation of spin-offs. #motion #production #industry40. I am employed at Ghent University and affiliated as well to Flanders Make.
Steven Thielemans
Steven Thielemans is R&D Manager Technology at Vandewiele nv. He is responsible for introducing new technologies in the carpet weaving machines and tufting machines developed and produced by Vandewiele. In this role he manages the mechatronics and software teams in Vandewiele and sets up collaboration with academic and research partners in Flanders. Steven has a background in control theory and electrical energy and holds a PhD in electrical energy from Ghent University.
Highway: connecting industry with state of the art in AI research
The highway sessions of VAIA bring state of the art of research in artificial intelligence towards the Flemish industry. Joins us for these seminars and stay up to date with the research of today.
Related courses
Practical AI for time series, small data and engineering design
study day on the state of the art in Flemish research - Gent - Flanders AI Research, VAIA, delaware
Artificial Intelligence in Business and Industry
Postgraduate - Kortrijk - KU Leuven, PUC - KU Leuven Continue, VAIA