On feedforward control using physics–guided neural networks: Training cost regularization and optimized initialization

Autor: Max Bolderman, Mircea Lazar, Hans Butler

Publikováno v: 2022 European Control Conference, ECC 2022, 1403-1408
STARTPAGE=1403;ENDPAGE=1408;TITLE=2022 European Control Conference, ECC 2022

Performance of model–based feedforward controllers is typically limited by the accuracy of the model describing the inverse system dynamics. Physics–guided neural networks (PGNN), where a known physical model cooperates in parallel with a neural

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c39c91c7ead10392df55d0bfa8a5ddd5
https://doi.org/10.23919/ecc55457.2022.9838217

Generalization of ILC for fixed order reference trajectories using interpolation

Autor: Max Bolderman, Gerben Erens, Mircea Lazar, Hans Butler

Publikováno v: 2022 IEEE 17th International Conference on Advanced Motion Control (AMC), 294-299
STARTPAGE=294;ENDPAGE=299;TITLE=2022 IEEE 17th International Conference on Advanced Motion Control (AMC)

The increasing demands for motion accuracy in high–precision mechatronics call for intelligent solutions to feedforward controller design. Iterative learning control (ILC) produces data–driven feedforward signals that give high accuracy for repea

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1f73d746d29bee62b23e78e304a05ae
https://doi.org/10.1109/amc51637.2022.9729275

On the Use of the Smith-McMillan Form in Decoupling System Dynamics

Autor: Hans Butler, Clarisse Petua Bosman Barros, Roland Tóth

Publikováno v: 2021 American Control Conference (ACC), 2069-2074
STARTPAGE=2069;ENDPAGE=2074;TITLE=2021 American Control Conference (ACC)
ACC

In this paper, the use of the Smith-McMillan form in decoupling multiple-input multiple-output system dynamics is analyzed. In short, from a transfer matrix plant model one can obtain a decoupling compensator which leads to a decoupled plant that con

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7edd36a3eefb976cb8d9b0c5ad25aa3
https://research.tue.nl/en/publications/78f468f4-03d9-4065-9055-f2e32d03cfb9

Mixed feedback and feedforward control design for multi-axis vibration isolation systems

Autor: MA Michiel Beijen, MF Marcel Heertjes, M Maarten Steinbuch, Hans Butler

Publikováno v: Mechatronics, 61, 106-116. Elsevier

This paper proposes a multi-loop single-input single-output control strategy for multi-axis vibration isolation systems. In this strategy, a combination of acceleration feedback and relative position feedback is used to improve the suppression of dis

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2750379e911388b46bc9bc2efaeb3f16
https://research.tue.nl/en/publications/8f734aaa-c00f-4432-a9a0-21df1e96e591

Physics-Guided Neural Networks for Inversion-based Feedforward Control applied to Linear Motors

Autor: Max Bolderman, Mircea Lazar, Hans Butler

Publikováno v: CCTA 2021-5th IEEE Conference on Control Technology and Applications, 1115-1120
STARTPAGE=1115;ENDPAGE=1120;TITLE=CCTA 2021-5th IEEE Conference on Control Technology and Applications

Ever-increasing throughput specifications in semiconductor manufacturing require operating high-precision mechatronics, such as linear motors, at higher accelerations. In turn this creates higher nonlinear parasitic forces that cannot be handled by i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f80061f0cfb213235ebaec801c29116