Clustering based identification of piece-wise affine models for systems with friction

Abstract

This paper proposes an identification method of piece-wise affine(PWA) models for systems with friction. The friction compensation is generally based on a friction model. The identification method of conventional friction models requires many experiments for each parameters. The proposed method is able to identify PWA models from single experimental data using clustering methods. It’s known that PWA models have high approximation performance of not only hybrid systems but non-linear systems. The effectiveness of the proposed method and its comparison with the conventional method is illustrated by experiments using the linear drive unit equipped the ball screw.