Unifying Model-Based and Neural Network Feedforward: Physics-Guided Neural Networks with Linear Autoregressive Dynamics

Johan Kon, Dennis Bruijnen, Jeroen van de Wijdeven, Marcel Heertjes, T.A.E. Oomen

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

1 Citation (Scopus)
53 Downloads (Pure)

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.
Original languageEnglish
Title of host publicationProceedings of the IEEE 61st Conference on Decision and Control (CDC 2022)
PublisherIEEE
Pages2475-2480
ISBN (Print)978-1-6654-6761-2
DOIs
Publication statusPublished - 2022
EventIEEE 61st Conference on Decision and Control (CDC 2022) - Cancún, Mexico
Duration: 6 Dec 20229 Dec 2022

Conference

ConferenceIEEE 61st Conference on Decision and Control (CDC 2022)
Country/TerritoryMexico
CityCancún
Period6/12/229/12/22

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.

Keywords

  • Friction
  • Feedforward neural networks
  • Nonlinear dynamical systems
  • Feedforward systems
  • Task analysis
  • Optimization

Fingerprint

Dive into the research topics of 'Unifying Model-Based and Neural Network Feedforward: Physics-Guided Neural Networks with Linear Autoregressive Dynamics'. Together they form a unique fingerprint.

Cite this