Unifying Model-Based and Neural Network Feedforward

Physics-Guided Neural Networks with Linear Autoregressive Dynamics

Conference paper (2022)

Authors

Johan Kon Eindhoven University of Technology
Dennis Bruijnen Philips Engineering Solutions
Marcel Heertjes Eindhoven University of Technology
T.A.E. Oomen Team Jan-Willem van Wingerden - Mechanical, Maritime and Materials Engineering , Eindhoven University of Technology
Research Group
Team Jan-Willem van Wingerden (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2022 Johan Kon, Dennis Bruijnen, Jeroen van de Wijdeven, Marcel Heertjes, T.A.E. Oomen
DOI
help_outline
https://doi.org/10.1109/CDC51059.2022.9992511
Optimization Friction Feedforward neural networks Nonlinear dynamical systems Task analysis Feedforward systems
More Info
expand_more

Published Date

2022

Language

English

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.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Delft Center for Systems and Control

Research Group

Team Jan-Willem van Wingerden

Abstract

Unknown nonlinear dynamics often limit the tracking performance of feedforward control. The aim of this paper is to develop a feedforward control framework that can compensate these unknown nonlinear dynamics using universal function approximators. The feedforward controller is parametrized as a parallel combination of a physics-based model and a neural network, where both share the same linear autoregressive (AR) dynamics. This parametrization allows for efficient output-error optimization through Sanathanan-Koerner (SK) iterations. Within each SK-iteration, the output of the neural network is penalized in the subspace of the physicsbased model through orthogonal projection-based regularization, such that the neural network captures only the unmodelled dynamics, resulting in interpretable models.