Control-relevant neural networks for feedforward control with preview: Applied to an industrial flatbed printer

被引：1

作者：

Aarnoudse, Leontine ^{[1
]}

Kon, Johan ^{[1
]}

Ohnishi, Wataru ^{[2
]}

Poot, Maurice ^{[1
]}

Tacx, Paul ^{[1
]}

Strijbosch, Nard ^{[1
]}

Oomen, Tom ^{[1
,3
]}

机构：

[1] Eindhoven Univ Technol, Dept Mech Engn, Control Syst Technol, Eindhoven, Netherlands

[2] Univ Tokyo, Grad Sch Engn, Tokyo, Japan

[3] Delft Univ Technol, Delft Ctr Syst & Control, Delft, Netherlands

来源：

IFAC JOURNAL OF SYSTEMS AND CONTROL | 2024年 / 27卷

关键词：

Feedforward control; Neural networks; Iterative learning control; ITERATIVE LEARNING CONTROL;

D O I：

10.1016/j.ifacsc.2024.100241

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The performance of feedforward control depends strongly on its ability to compensate for reproducible disturbances. The aim of this paper is to develop a systematic framework for artificial neural networks (ANN) for feedforward control. The method involves three aspects: a new criterion that emphasizes the closed -loop control objective, inclusion of preview to deal with delays and non -minimum phase dynamics, and enabling the use of an iterative learning algorithm to generate training data in view of addressing generalization errors. The approach is illustrated through simulations and experiments on an industrial flatbed printer. (c) 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

引用

页数：11

共 46 条

[1] Control-Relevant Neural Networks for Intelligent Motion Feedforward
Aarnoudse, Leontine
Ohnishi, Wataru
Poot, Maurice
Tacx, Paul
Strijbosch, Nard
Oomen, Tom
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS (ICM), 2021,
[2] Andersson C, 2019, IEEE DECIS CONTR P, P3670, DOI [10.1109/cdc40024.2019.9030219, 10.1109/CDC40024.2019.9030219]
[3] Kernel-based identification of non-causal systems with application to inverse model control
Blanken, Lennart
Oomen, Tom
[J]. AUTOMATICA, 2020, 114
[4] Batch-to-Batch Rational Feedforward Control: From Iterative Learning to Identification Approaches, With Application to a Wafer Stage
Blanken, Lennart
Boeren, Frank
Bruijnen, Dennis
Oomen, Tom
[J]. IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2017, 22 (02) : 826 - 837
[5] Blanken Lennart, 2018, AM CONTROL C
[6] Optimal Estimation of Rational Feedforward Control via Instrumental Variables: With Application to a Wafer Stage
Boeren, Frank
Blanken, Lennart
Bruijnen, Dennis
Oomen, Tom
[J]. ASIAN JOURNAL OF CONTROL, 2018, 20 (03) : 975 - 992
[7] Iterative motion feedforward tuning: A data-driven approach based on instrumental variable identification
Boeren, Frank
Oomen, Tom
Steinbuch, Maarten
[J]. CONTROL ENGINEERING PRACTICE, 2015, 37 : 11 - 19
[8] Data-driven multivariable ILC: enhanced performance by eliminating L and Q filters
Bolder, Joost
Kleinendorst, Stephan
Oomen, Tom
[J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2018, 28 (12) : 3728 - 3751
[9] Rational Basis Functions in Iterative Learning Control-With Experimental Verification on a Motion System
Bolder, Joost
Oomen, Tom
[J]. IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2015, 23 (02) : 722 - 729
[10] Weighting matrix design for robust monotonic convergence in Norm Optimal iterative learning control
Bristow, Douglas A.
[J]. 2008 AMERICAN CONTROL CONFERENCE, VOLS 1-12, 2008, : 4554 - 4560

← 1 2 3 4 5 →