Prediction of angular errors on a vertical CNC milling machine

Abstract

The accuracy and precision of computer numerical control (CNC) machine tools directly affect the dimensional accuracy of machined parts. Accurate detection of machine tool errors with respect to positioning and orientation is imperative to the accuracy of the manufacturing process and, further, to eliminate errors through error compensation techniques. This paper presents a method to measure and determine angular errors resulting from drive axis out-of-straightness. Measurement of errors in discrete steps has been carried out via laser autocollimator and the method of neural networks (NN) has been employed to predict the amount of errors in the range between the steps. The results from this study can be used as a model for industrial applications to identify errors prior to the programming of the manufacturing process.