Neural network contour error predictor in CNC control systems

Abstract

This article presents a method for predicting contour error using artificial neural networks. Contour error is defined as the minimum distance between actual position and reference toolpath and is commonly used to measure machining precision of Computerized Numerically Controlled (CNC) machine tools. Offline trained Nonlinear Autoregressive networks with exogenous inputs (NARX) are used to predict following error in each axis. These values and information about toolpath geometry obtained from the interpolator are then used to compute the contour error. The method used for effective off-line training of the dynamic recurrent NARX neural networks is presented. Tests are performed that verify the contour error prediction accuracy using a biaxial CNC machine in a real-time CNC control system. The presented neural network based contour error predictor was used in a predictive feedrate optimization algorithm with constrained contour error.