Print Email Facebook Twitter Unifying Model-Based and Neural Network Feedforward Title Unifying Model-Based and Neural Network Feedforward: Physics-Guided Neural Networks with Linear Autoregressive Dynamics Author Kon, Johan (Eindhoven University of Technology) Bruijnen, Dennis (Philips Engineering Solutions) van de Wijdeven, Jeroen (ASML) Heertjes, Marcel (Eindhoven University of Technology) Oomen, T.A.E. (TU Delft Team Jan-Willem van Wingerden; Eindhoven University of Technology) Date 2022 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. Subject FrictionFeedforward neural networksNonlinear dynamical systemsFeedforward systemsTask analysisOptimization To reference this document use: http://resolver.tudelft.nl/uuid:35a2f77c-51c1-4044-845e-8626397c0625 DOI https://doi.org/10.1109/CDC51059.2022.9992511 Publisher IEEE Embargo date 2023-07-10 ISBN 978-1-6654-6761-2 Source Proceedings of the IEEE 61st Conference on Decision and Control (CDC 2022) Event IEEE 61st Conference on Decision and Control (CDC 2022), 2022-12-06 → 2022-12-09, Cancún, Mexico Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2022 Johan Kon, Dennis Bruijnen, Jeroen van de Wijdeven, Marcel Heertjes, T.A.E. Oomen Files PDF Unifying_Model_Based_and_ ... namics.pdf 1.17 MB Close viewer /islandora/object/uuid:35a2f77c-51c1-4044-845e-8626397c0625/datastream/OBJ/view