Physics-guided neural networks for feedforward control: From consistent identification to feedforward controller design

TL;DR

This paper introduces a noise-aware system identification approach using physics-guided neural networks for feedforward control, leading to improved motion tracking in industrial systems.

Contribution

It proposes a forward system identification method with PGNNs from noisy data and two novel inversion techniques for feedforward controller design, enhancing tracking accuracy.

Findings

Significant tracking performance improvements on a real industrial linear motor.

Effective noise handling in system identification with PGNNs.

Validated methods outperform direct inverse identification approaches.

Abstract

Model-based feedforward control improves tracking performance of motion systems, provided that the model describing the inverse dynamics is of sufficient accuracy. Model sets, such as neural networks (NNs) and physics-guided neural networks (PGNNs) are typically used as flexible parametrizations that enable accurate identification of the inverse system dynamics. Currently, these (PG)NNs are used to identify the inverse dynamics directly. However, direct identification of the inverse dynamics is sensitive to noise that is present in the training data, and thereby results in biased parameter estimates which limit the achievable tracking performance. In order to push performance further, it is therefore crucial to account for noise when performing the identification. To address this problem, this paper proposes the use of a forward system identification using (PG)NNs from noisy data. Afterwards, two methods are proposed for inverting PGNNs to design a feedforward controller for high-precision motion control. The developed methodology is validated on a real-life industrial linear motor, where it showed significant improvements in tracking performance with respect to the direct inverse identification.