Thermal modelling and online heat transfer estimation using active learning grey-box approaches

This project is part of the Marie Skłodowska-Curie Actions (MSCA) Innovative Training Network (ITN) H2020-MSCA-ITN-2020 GREYDIENT: European Training Network on Grey-Box Models for Safe and Reliable Intelligent Mobility Systems. The aim of the research is to develop a generic methodology for the optimization of large-scale sensor arrays in production plants. This should make it possible to perform online process control via an optimal combination of simulation models with experimental data validated on the projection welding process. Objectives of this PhD project include: (1) To construct a production-process virtual twin consisting of an ensemble of data-driven black box approaches, surrogate models and full-scale, non-linear, finite-element computations, (2) to apply active learning to train this virtual twin, (3) to apply this virtual twin in combination with active learning to create an optimal sensor lay-out, (4) to apply the developed methodology on a projection welding machine at KU Leuven.