Physics-guided neural networks for feedforward control with input-to-state-stability guarantees

M. Bolderman (Corresponding author), Hans Butler, Sjirk H. Koekebakker, Eelco P. van Horssen, Ramidin Kamidi, Theresa Spaan-Burke, Nard W.A. Strijbosch, Mircea Lazar

Research output: Contribution to journalArticleAcademicpeer-review

59 Downloads (Pure)

Abstract

The increasing demand on precision and throughput within high-precision mechatronics industries requires a new generation of feedforward controllers with higher accuracy than existing, physics-based feedforward controllers. As neural networks are universal approximators, they can in principle yield feedforward controllers with a higher accuracy, but suffer from bad extrapolation outside the training data set, which makes them unsafe for implementation in industry. Motivated by this, we develop a novel physics-guided neural network (PGNN) architecture that structurally merges a physics-based layer and a black-box neural layer in a single model. The parameters of the two layers are simultaneously identified, while a novel regularization cost function is used to prevent competition among layers and to preserve consistency of the physics-based parameters. Moreover, in order to ensure stability of PGNN feedforward controllers, we develop sufficient conditions for analyzing or imposing (during training) input-to-state stability of PGNNs, based on novel, less conservative Lipschitz bounds for neural networks. The developed PGNN feedforward control framework is validated on a real-life, high-precision industrial linear motor used in lithography machines, where it reaches a factor 2 improvement with respect to physics-based mass–friction feedforward and it significantly outperforms alternative neural network based feedforward controllers.
Original languageEnglish
Article number105851
Number of pages14
JournalControl Engineering Practice
Volume145
DOIs
Publication statusPublished - Apr 2024

Funding

This work is supported by the NWO, The Netherlands research project PGN Mechatronics, project number 17973 .

FundersFunder number
Nederlandse Organisatie voor Wetenschappelijk Onderzoek17973

    Keywords

    • feedforward control
    • neural networks
    • nonlinear system identification
    • high-precision mechatronics
    • linear motors
    • Neural networks
    • Linear motors
    • Nonlinear system identification
    • Feedforward control
    • High-precision mechatronics

    Fingerprint

    Dive into the research topics of 'Physics-guided neural networks for feedforward control with input-to-state-stability guarantees'. Together they form a unique fingerprint.

    Cite this