Michel Reniers
Eindhoven University of Technology (TU/e), the Netherlands
Bio: Michel Reniers is currently an Associate Professor in model-based engineering of supervisory control at the Department of Mechanical Engineering at TU/e. He has received both his master and PhD degrees from the Department of Mathematics and Computer Science from TU/e. He has authored over 200 journal and conference papers. He is an associate editor of Automatica, Journal of Discrete Event Dynamic Systems, Robots and Automation Letters, and Open Journal of Control Systems. He is general chair of WoDES 20206, which is the premium venue for research in Discrete Event Systems.
His research portfolio ranges from discrete event systems for model-based systems engineering and performance evaluation to novel approaches for supervisory control synthesis. Applications of this work are mostly in the areas of cyber-physical systems and manufacturing systems. Recently he has become interested in simulation-based design & layout optimization of manufacturing systems possibly using artificial intelligence.
Michel is a main contributor to the (theoretical) developments underlying the open source Eclipse project ESCET (Eclipse Supervisory Control Engineering Toolkit) that is used both in academia and industry for developing supervisory controllers in a synthesis-based approach, with notable applications in infrastructural systems and lithography.
KEYNOTE: Simulation-based optimization of a production system topology - a neural network-assisted genetic algorithm
Abstract: There is an abundance of prior research on the optimization of production systems, but there is a research gap when it comes to optimizing which components should be included in a design, and how they should be connected. To overcome this gap, a novel approach is presented for topology optimization of production systems using a genetic algorithm (GA). This GA employs similarity-based mutation and recombination for the creation of offspring, and discrete-event simulation for fitness evaluation. To reduce computational cost, an extension to the GA is presented in which a neural network functions as a surrogate model for simulation. Three types of neural networks are compared, and the type most effective as a surrogate model is chosen based on its optimization performance and computational cost.
Both the unassisted GA and neural network-assisted GA are applied to an industrial case study and a scalability case study. These show that both approaches are effective at finding the optimal solution in industrial settings, and both scale well as the number of potential solutions increases, with the neural network-assisted GA having the better scalability of the two.