Gaussian Process Position-Dependent Feedforward: With Application to a Wire Bonder

TL;DR

This paper introduces a Gaussian process-based framework to model and compensate for position-dependent effects in feedforward control, significantly improving performance in a wire bonding application.

Contribution

It develops a novel data-driven method combining Gaussian processes with feedforward parameter learning to address position-dependent control challenges.

Findings

Significant performance improvements on a commercial wire bonder.

Effective modeling of position-dependent effects using Gaussian processes.

Framework is fully data-driven and suitable for industrial applications.

Abstract

Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate for position-dependent effects by modeling feedforward parameters as a function of position. A framework to model and identify feedforward parameters as a continuous function of position is developed by combining Gaussian processes and feedforward parameter learning techniques. The framework results in a fully data-driven approach, which can be readily implemented for industrial control applications. The framework is experimentally validated and shows a significant performance increase on a commercial wire bonder.