Physics-guided neural networks for inversion-based feedforward control applied to hybrid stepper motors

TL;DR

This paper introduces a physics-guided neural network (PGNN) for feedforward control of hybrid stepper motors, improving tracking accuracy by learning parasitic effects from data, demonstrated through experiments in printing applications.

Contribution

The paper presents a novel PGNN-based feedforward controller that learns inverse dynamics effects, enhancing control performance over traditional methods.

Findings

PGNN reduces mean-absolute tracking error in experiments.

Experimental validation on industrial HSMs shows improved accuracy.

Outperforms conventional benchmark controllers.

Abstract

Rotary motors, such as hybrid stepper motors (HSMs), are widely used in industries varying from printing applications to robotics. The increasing need for productivity and efficiency without increasing the manufacturing costs calls for innovative control design. Feedforward control is typically used in tracking control problems, where the desired reference is known in advance. In most applications, this is the case for HSMs, which need to track a periodic angular velocity and angular position reference. Performance achieved by feedforward control is limited by the accuracy of the available model describing the inverse system dynamics. In this work, we develop a physics-guided neural network (PGNN) feedforward controller for HSMs, which can learn the effect of parasitic forces from data and compensate for it, resulting in improved accuracy. Indeed, experimental results on an HSM used in printing industry show that the PGNN outperforms conventional benchmarks in terms of the mean-absolute tracking error.