Parameter-Varying Feedforward Control: A Kernel-Based Learning Approach

TL;DR

This paper introduces a kernel-based, data-driven method for learning parameter-varying feedforward control to improve tracking accuracy in linear systems with changing parameters.

Contribution

It presents a novel approach combining kernel regularization and iterative learning for direct data-driven control of parameter-varying systems.

Findings

Achieves high tracking performance in linear parameter-varying systems.

Validated on an industrial belt-driven carriage setup.

Demonstrates flexibility for varying reference tasks.

Abstract

The increasing demands for high accuracy in mechatronic systems necessitate the incorporation of parameter variations in feedforward control. The aim of this paper is to develop a data-driven approach for direct learning of parameter-varying feedforward control to increase tracking performance. The developed approach is based on kernel-regularized function estimation in conjunction with iterative learning to directly learn parameter-varying feedforward control from data. This approach enables high tracking performance for feedforward control of linear parameter-varying dynamics, providing flexibility to varying reference tasks. The developed framework is validated on a benchmark industrial experimental setup featuring a belt-driven carriage.