Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach

Johan Kon; Jeroen Van De Wijdeven; Dennis Bruijnen; Roland Tóth; Marcel Heertjes; Tom Oomen

doi:10.1109/CDC49753.2023.10383877

Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach

Johan Kon, Jeroen Van De Wijdeven, Dennis Bruijnen, Roland Tóth, Marcel Heertjes, Tom Oomen

Team Jan-Willem van Wingerden

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

1 Downloads (Pure)

Abstract

The performance of a feedforward controller is primarily determined by the extent to which it can capture the relevant dynamics of a system. The aim of this paper is to develop an input-output linear parameter-varying (LPV) feedforward parameterization and a corresponding data-driven estimation method in which the dependency of the coefficients on the scheduling signal are learned by a neural network. The use of a neural network enables the parameterization to compensate a wide class of constant relative degree LPV systems. Efficient optimization of the neural-network-based controller is achieved through a Levenberg-Marquardt approach with analytic gradients and a pseudolinear approach generalizing Sanathanan-Koerner to the LPV case. The performance of the developed feedforward learning method is validated in a simulation study of an LPV system showing excellent performance.

Original language	English
Title of host publication	Proceedings of the 62nd IEEE Conference on Decision and Control (CDC 2023)
Publisher	IEEE
Pages	3720-3725
Number of pages	6
ISBN (Electronic)	979-8-3503-0124-3
DOIs	https://doi.org/10.1109/CDC49753.2023.10383877
Publication status	Published - 2023
Event	62nd IEEE Conference on Decision and Control, CDC 2023 - Singapore, Singapore Duration: 13 Dec 2023 → 15 Dec 2023

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
ISSN (Print)	0743-1546
ISSN (Electronic)	2576-2370

Conference

Conference	62nd IEEE Conference on Decision and Control, CDC 2023
Country/Territory	Singapore
City	Singapore
Period	13/12/23 → 15/12/23

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.

Access to Document

10.1109/CDC49753.2023.10383877

Direct_Learning_for_Parameter-Varying_Feedforward_Control_A_Neural-Network_ApproachFinal published version, 939 KB

Cite this

Kon, J., Van De Wijdeven, J., Bruijnen, D., Tóth, R., Heertjes, M., & Oomen, T. (2023). Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach. In Proceedings of the 62nd IEEE Conference on Decision and Control (CDC 2023) (pp. 3720-3725). (Proceedings of the IEEE Conference on Decision and Control). IEEE. https://doi.org/10.1109/CDC49753.2023.10383877

@inproceedings{c5e54d3caee6494f8a71b1044512d415,

title = "Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach",

abstract = "The performance of a feedforward controller is primarily determined by the extent to which it can capture the relevant dynamics of a system. The aim of this paper is to develop an input-output linear parameter-varying (LPV) feedforward parameterization and a corresponding data-driven estimation method in which the dependency of the coefficients on the scheduling signal are learned by a neural network. The use of a neural network enables the parameterization to compensate a wide class of constant relative degree LPV systems. Efficient optimization of the neural-network-based controller is achieved through a Levenberg-Marquardt approach with analytic gradients and a pseudolinear approach generalizing Sanathanan-Koerner to the LPV case. The performance of the developed feedforward learning method is validated in a simulation study of an LPV system showing excellent performance.",

author = "Johan Kon and {Van De Wijdeven}, Jeroen and Dennis Bruijnen and Roland T{\'o}th and Marcel Heertjes and Tom Oomen",

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.; 62nd IEEE Conference on Decision and Control, CDC 2023 ; Conference date: 13-12-2023 Through 15-12-2023",

year = "2023",

doi = "10.1109/CDC49753.2023.10383877",

language = "English",

series = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "IEEE",

pages = "3720--3725",

booktitle = "Proceedings of the 62nd IEEE Conference on Decision and Control (CDC 2023)",

address = "United States",

}

Kon, J, Van De Wijdeven, J, Bruijnen, D, Tóth, R, Heertjes, M & Oomen, T 2023, Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach. in Proceedings of the 62nd IEEE Conference on Decision and Control (CDC 2023). Proceedings of the IEEE Conference on Decision and Control, IEEE, pp. 3720-3725, 62nd IEEE Conference on Decision and Control, CDC 2023, Singapore, Singapore, 13/12/23. https://doi.org/10.1109/CDC49753.2023.10383877

Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach. / Kon, Johan; Van De Wijdeven, Jeroen; Bruijnen, Dennis et al.
Proceedings of the 62nd IEEE Conference on Decision and Control (CDC 2023). IEEE, 2023. p. 3720-3725 (Proceedings of the IEEE Conference on Decision and Control).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Direct Learning for Parameter-Varying Feedforward Control

T2 - 62nd IEEE Conference on Decision and Control, CDC 2023

AU - Kon, Johan

AU - Van De Wijdeven, Jeroen

AU - Bruijnen, Dennis

AU - Tóth, Roland

AU - Heertjes, Marcel

AU - Oomen, Tom

N1 - 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.

PY - 2023

Y1 - 2023

N2 - The performance of a feedforward controller is primarily determined by the extent to which it can capture the relevant dynamics of a system. The aim of this paper is to develop an input-output linear parameter-varying (LPV) feedforward parameterization and a corresponding data-driven estimation method in which the dependency of the coefficients on the scheduling signal are learned by a neural network. The use of a neural network enables the parameterization to compensate a wide class of constant relative degree LPV systems. Efficient optimization of the neural-network-based controller is achieved through a Levenberg-Marquardt approach with analytic gradients and a pseudolinear approach generalizing Sanathanan-Koerner to the LPV case. The performance of the developed feedforward learning method is validated in a simulation study of an LPV system showing excellent performance.

AB - The performance of a feedforward controller is primarily determined by the extent to which it can capture the relevant dynamics of a system. The aim of this paper is to develop an input-output linear parameter-varying (LPV) feedforward parameterization and a corresponding data-driven estimation method in which the dependency of the coefficients on the scheduling signal are learned by a neural network. The use of a neural network enables the parameterization to compensate a wide class of constant relative degree LPV systems. Efficient optimization of the neural-network-based controller is achieved through a Levenberg-Marquardt approach with analytic gradients and a pseudolinear approach generalizing Sanathanan-Koerner to the LPV case. The performance of the developed feedforward learning method is validated in a simulation study of an LPV system showing excellent performance.

UR - http://www.scopus.com/inward/record.url?scp=85184811368&partnerID=8YFLogxK

U2 - 10.1109/CDC49753.2023.10383877

DO - 10.1109/CDC49753.2023.10383877

M3 - Conference contribution

AN - SCOPUS:85184811368

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 3720

EP - 3725

BT - Proceedings of the 62nd IEEE Conference on Decision and Control (CDC 2023)

PB - IEEE

Y2 - 13 December 2023 through 15 December 2023

ER -

Direct Learning for Parameter-Varying Feedforward Control: A Neural-Network Approach

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this