Predictions of Tool Wear in Hard Turning of AISI4140 Steel through Artificial Neural Network, Fuzzy Logic and Regression Models

Abstract

The tool wear is an unavoidable phenomenon when using coated carbide tools during hard turning of hardened steels. This work focuses on the prediction of tool wear using regression analysis and artificial neural network (ANN).The work piece taken into consideration is AISI4140 steel hardened to 47 HRC. The models are developed from the results of experiments, which are carried out based on Design of experiments (Response surface methodology). The cutting speed, feed and depth of cut are taken as the inputs and the wear is the output. The results reveal that the ANN provides better accuracy when compared to Regression analysis.