Linear servo motor control using adaptive neural networks

Abstract

A novel approach for designing and realizing a wavelet basis function network learning controller for a linear motor control system is considered. A new condition ensuring stability robustness of a closed-loop system including a neuro controller is derived. The proposed controller deals mainly with non-linear disturbances, especially viscous friction and force ripples that occur in motion control of linear synchronous motors. It consists of two parts: the feedback controller is designed on the basis of a simple linear model, and the learning feedback component is a wavelet neuro controller. A real-time simulation scheme on a recently developed high speed, multiple input-output, digital signal processing control board is constructed to realize and evaluate the proposed design. Mathematical and real-time simulations and an experimental study are performed to validate the proposed approach.