Parameter-Varying Feedforward Control: A Kernel-Based Learning Approach

Max van Haren; Lennart Blanken; Tom Oomen

doi:10.1016/j.mechatronics.2025.103337

Parameter-Varying Feedforward Control: A Kernel-Based Learning Approach

Max van Haren (Corresponding author)
, Lennart Blanken
, Tom Oomen

Onderzoeksoutput: Bijdrage aan tijdschrift › Tijdschriftartikel › Academic › peer review

107 Downloads (Pure)

Samenvatting

The increasing demands for high accuracy in mechatronic systems necessitate the incorporation of parameter variations in feedforward control. The aim of this paper is to develop a data-driven approach for direct learning of parameter-varying feedforward control to increase tracking performance. The developed approach is based on kernel-regularized function estimation in conjunction with iterative learning to directly learn parameter-varying feedforward control from data. This approach enables high tracking performance for feedforward control of linear parameter-varying dynamics, providing flexibility to varying reference tasks. The developed framework is validated on a benchmark industrial experimental setup featuring a belt-driven carriage.

Originele taal-2	Engels
Artikelnummer	103337
Aantal pagina's	9
Tijdschrift	Mechatronics
Volume	109
DOI's	https://doi.org/10.1016/j.mechatronics.2025.103337
Status	Gepubliceerd - aug 2025

Financiering

This work is part of the research programme VIDI with project number 15698, which is (partly) financed by, The Netherlands Organisation for Scientific Research (NWO) . This research has received funding from the ECSEL Joint Undertaking under grant agreement 101007311 (IMOCO4.E). The Joint Undertaking receives support from the European Union Horizon 2020 research and innovation programme .

Trefwoorden

eess.SY
cs.SY

Toegang tot document

10.1016/j.mechatronics.2025.103337Licentie: CC BY

LPV_ILCFinale auteursversie , 6,9 MBLicentie: CC BY-NC-ND
pdfDefinitieve gepubliceerde versie, 2,22 MBLicentie: CC BY

Andere bestanden en links

Link naar publicatie in Scopus

Citeer dit

@article{f657280283d04972a6d45fa5d08542fe,

title = "Parameter-Varying Feedforward Control: A Kernel-Based Learning Approach",

abstract = "The increasing demands for high accuracy in mechatronic systems necessitate the incorporation of parameter variations in feedforward control. The aim of this paper is to develop a data-driven approach for direct learning of parameter-varying feedforward control to increase tracking performance. The developed approach is based on kernel-regularized function estimation in conjunction with iterative learning to directly learn parameter-varying feedforward control from data. This approach enables high tracking performance for feedforward control of linear parameter-varying dynamics, providing flexibility to varying reference tasks. The developed framework is validated on a benchmark industrial experimental setup featuring a belt-driven carriage.",

keywords = "eess.SY, cs.SY, Feedforward control, Iterative learning control (ILC), Kernel regularization, Mechatronic systems, Linear parameter-varying, Motion control, Iterative learning control",

author = "\{van Haren\}, Max and Lennart Blanken and Tom Oomen",

year = "2025",

month = aug,

doi = "10.1016/j.mechatronics.2025.103337",

language = "English",

volume = "109",

journal = "Mechatronics",

issn = "0957-4158",

publisher = "Elsevier",

}

TY - JOUR

T1 - Parameter-Varying Feedforward Control

T2 - A Kernel-Based Learning Approach

AU - van Haren, Max

AU - Blanken, Lennart

AU - Oomen, Tom

PY - 2025/8

Y1 - 2025/8

N2 - The increasing demands for high accuracy in mechatronic systems necessitate the incorporation of parameter variations in feedforward control. The aim of this paper is to develop a data-driven approach for direct learning of parameter-varying feedforward control to increase tracking performance. The developed approach is based on kernel-regularized function estimation in conjunction with iterative learning to directly learn parameter-varying feedforward control from data. This approach enables high tracking performance for feedforward control of linear parameter-varying dynamics, providing flexibility to varying reference tasks. The developed framework is validated on a benchmark industrial experimental setup featuring a belt-driven carriage.

AB - The increasing demands for high accuracy in mechatronic systems necessitate the incorporation of parameter variations in feedforward control. The aim of this paper is to develop a data-driven approach for direct learning of parameter-varying feedforward control to increase tracking performance. The developed approach is based on kernel-regularized function estimation in conjunction with iterative learning to directly learn parameter-varying feedforward control from data. This approach enables high tracking performance for feedforward control of linear parameter-varying dynamics, providing flexibility to varying reference tasks. The developed framework is validated on a benchmark industrial experimental setup featuring a belt-driven carriage.

KW - eess.SY

KW - cs.SY

KW - Feedforward control

KW - Iterative learning control (ILC)

KW - Kernel regularization

KW - Mechatronic systems

KW - Linear parameter-varying

KW - Motion control

KW - Iterative learning control

UR - https://www.scopus.com/pages/publications/105004409916

U2 - 10.1016/j.mechatronics.2025.103337

DO - 10.1016/j.mechatronics.2025.103337

M3 - Article

SN - 0957-4158

VL - 109

JO - Mechatronics

JF - Mechatronics

M1 - 103337

ER -

Parameter-Varying Feedforward Control: A Kernel-Based Learning Approach

Samenvatting

Financiering

Trefwoorden

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit