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

TL;DR

This paper introduces a physics-guided neural network framework for inversion-based feedforward control of linear motors, embedding physical knowledge to improve accuracy and convergence, achieving significantly reduced tracking errors in simulation.

Contribution

The paper presents a novel PGNN-based inversion feedforward control method that incorporates physical laws, outperforming traditional approaches in linear motor applications.

Findings

Achieves twenty times smaller mean average tracking error than traditional methods.

Improves training convergence by embedding physical knowledge.

Validated through simulation on industrial linear motors.

Abstract

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 industrial feedforward controllers. Motivated by this problem, in this paper we develop a general framework for inversion-based feedforward controller design using physics-guided neural networks (PGNNs). In contrast with black-box neural networks, the developed PGNNs embed prior physical knowledge in the input and hidden layers, which results in improved training convergence and learning of underlying physical laws. The PGNN inversion-based feedforward control framework is validated in simulation on an industrial linear motor, for which it achieves a mean average tracking error twenty times smaller than mass-acceleration feedforward in simulation.