Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach

J.J. Kon; Dennis J.H. Bruijnen; Jeroen J.M. van de Wijdeven; Marcel F. Heertjes; Tom A.E. Oomen

doi:10.23919/ACC53348.2022.9867653

Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach

J.J. Kon
, Dennis J.H. Bruijnen
, Jeroen J.M. van de Wijdeven
, Marcel F. Heertjes
, Tom A.E. Oomen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

18 Citations (Scopus)

219 Downloads (Pure)

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.

Original language	English
Title of host publication	2022 American Control Conference (ACC)
Publisher	Institute of Electrical and Electronics Engineers
Pages	4377-4382
Number of pages	6
ISBN (Electronic)	978-1-6654-5196-3
DOIs	https://doi.org/10.23919/ACC53348.2022.9867653
Publication status	Published - 5 Sept 2022
Event	2022 American Control Conference, ACC 2022 - Atlanta, United States Duration: 8 Jun 2022 → 10 Jun 2022 https://acc2022.a2c2.org/

Conference

Conference	2022 American Control Conference, ACC 2022
Abbreviated title	ACC 2022
Country/Territory	United States
City	Atlanta
Period	8/06/22 → 10/06/22
Internet address	https://acc2022.a2c2.org/

Access to Document

10.23919/ACC53348.2022.9867653

KonBruijnenWijdevenHeertjesOomen_ACC2022Final author version , 343 KB

Cite this

@inproceedings{2f6b52d0485347229e9553ace9002d7f,

title = "Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach",

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.",

author = "J.J. Kon and Bruijnen, \{Dennis J.H.\} and \{van de Wijdeven\}, \{Jeroen J.M.\} and Heertjes, \{Marcel F.\} and Oomen, \{Tom A.E.\}",

year = "2022",

month = sep,

day = "5",

doi = "10.23919/ACC53348.2022.9867653",

language = "English",

pages = "4377--4382",

booktitle = "2022 American Control Conference (ACC)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2022 American Control Conference, ACC 2022, ACC 2022 ; Conference date: 08-06-2022 Through 10-06-2022",

url = "https://acc2022.a2c2.org/",

}

Kon, JJ, Bruijnen, DJH, van de Wijdeven, JJM, Heertjes, MF & Oomen, TAE 2022, Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach. in 2022 American Control Conference (ACC). Institute of Electrical and Electronics Engineers, pp. 4377-4382, 2022 American Control Conference, ACC 2022, Atlanta, Georgia, United States, 8/06/22. https://doi.org/10.23919/ACC53348.2022.9867653

Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach. / Kon, J.J.; Bruijnen, Dennis J.H.; van de Wijdeven, Jeroen J.M. et al.
2022 American Control Conference (ACC). Institute of Electrical and Electronics Engineers, 2022. p. 4377-4382.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach

AU - Kon, J.J.

AU - Bruijnen, Dennis J.H.

AU - van de Wijdeven, Jeroen J.M.

AU - Heertjes, Marcel F.

AU - Oomen, Tom A.E.

PY - 2022/9/5

Y1 - 2022/9/5

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85133681464

U2 - 10.23919/ACC53348.2022.9867653

DO - 10.23919/ACC53348.2022.9867653

M3 - Conference contribution

SP - 4377

EP - 4382

BT - 2022 American Control Conference (ACC)

PB - Institute of Electrical and Electronics Engineers

T2 - 2022 American Control Conference, ACC 2022

Y2 - 8 June 2022 through 10 June 2022

ER -

Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this