Physics-Guided Neural Networks for Feedforward Control

An Orthogonal Projection-Based Approach

Conference Paper (2022)
Author(s)

Johan Kon (Eindhoven University of Technology)

Dennis Bruijnen (Philips Research)

Jeroen van de Wijdeven (ASML)

Marcel Heertjes (ASML, Eindhoven University of Technology)

T. Oomen (TU Delft - Team Jan-Willem van Wingerden, Eindhoven University of Technology)

Research Group
Team Jan-Willem van Wingerden
Copyright
© 2022 Johan Kon, Dennis Bruijnen, Jeroen van de Wijdeven, Marcel Heertjes, T.A.E. Oomen
DOI related publication
https://doi.org/10.23919/ACC53348.2022.9867653
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Johan Kon, Dennis Bruijnen, Jeroen van de Wijdeven, Marcel Heertjes, T.A.E. Oomen
Research Group
Team Jan-Willem van Wingerden
Pages (from-to)
4377-4382
ISBN (print)
978-1-6654-5196-3
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Unknown nonlinear dynamics can limit the performance of model-based feedforward control. The aim of this paper is to develop a feedforward control framework for systems with unknown, typically nonlinear, dynamics. To address the unknown dynamics, a physics-based feedforward model is complemented by a neural network. The neural network output in the subspace of the model is penalized through orthogonal projection. This results in uniquely identifiable model coefficients, enabling increased performance and similar task flexibility with respect to the model-based controller. The feedforward framework is validated on a representative system with performance limiting nonlinear friction characteristics.

Files

Physics_Guided_Neural_Networks... (pdf)
(pdf | 0.487 Mb)
- Embargo expired in 05-03-2023
License info not available