Neural network contour error prediction of a bi-axial linear motor positioning system

Abstract

In the article a method of predicting contour error using artificial neural network for a bi-axial positioning system is presented. The machine consists of two linear stages with permanent magnet linear motors controlled by servo drives. The drives are controlled from a PC with real-time operating system via EtherCAT fieldbus. A randomly generated Non-Uniform Rational B-Spline (NURBS) trajectory is used to train offline a NARX-type artificial neural network for each axis. These networks allow prediction of following errors and contour errors of the motion trajectory. Experimental results are presented that validate the viability of the neural network based contour error prediction. The presented contour error predictor will be used in predictive control and velocity optimization algorithms of linear motor based CNC machines.