Modeling and analysis of surface roughness in steel turning using regression and neural networks

This study deals with the development of a surface roughness prediction model for machining EN-31 steel alloys using multiple regression and artificial neural networks . The experiments have been conducted using composite factorial design of experiments on heavy duty lathe turning machine with tungsten carbide cutting tools. A second order multiple regression model in terms of machining parameters have been developed for the prediction of surface roughness. The adequacy of the developed model is verified by using multiple regression coefficients of determination, analysis of variance technique and residual analysis and also the artificial neural net work model has been developed by using back propagation neural network (BPNN) algorithm using train data and tested using test data. The ANN has been designed on PC by using Mat lab7.0 software. The experimental results show, artificial neural network with back propagation model predicts high accuracy as compared with multiple regression models.