Surface profile prediction and analysis applied to turning process

Abstract

An approach for the prediction of surface profile in turning process using Radial Basis Function (RBF) neural networks is presented. The input parameters of the RBF networks are cutting speed, depth of cut and feed rate. The output parameters are Fast Fourier Transform (FFT) vector of surface profile for the prediction of surface profile. The RBF networks are trained with adaptive optimal training parameters related to cutting parameters and predict surface profile using the corresponding optimal network topology for each new cutting condition. A very good performance of surface profile prediction, in terms of agreement with experimental data, was achieved with high accuracy, low cost and high speed. It is found that the RBF networks have the advantage over Back Propagation (BP) neural networks. Furthermore, a new group of training and testing data were also used to analyse the influence of tool wear and chip formation on prediction accuracy using RBF neural networks.