Quantcast

A Neural-Repetitive Control Approach for High-Performance Motion Control of Piezo-Actuated Systems

Research paper by Chi-Ying Lin, Chien-Yao Li

Indexed on: 11 Mar '14Published on: 11 Mar '14Published in: Arabian Journal for Science and Engineering



Abstract

This paper presents a neural-repetitive approach to the precision control of piezo-actuated systems. Two neural controllers are used in the proposed control scheme. The first controller is a standard neural adaptive controller using a radial basis function network as a baseline for motion control. To eliminate non-zero periodic errors originating in the deterministic reference signals, an additional neural controller containing a discrete-time repetitive controller was added by introducing solutions of a transformed feedforward control problem constrained by a deterministic internal model. The proposed neural-repetitive controllers were applied to a piezo-actuated system to track periodic and complex motion profiles. The experimental results demonstrate that the proposed neural-repetitive controller improves control performance, showing good robustness pertaining to variations in plant parameters.