Modelling of tool wear and surface roughness in hard turning using regression and artificial neural network

Abstract

The objective of this paper is to study the effect of tool wear on surface roughness in hard turning. Tool wear prediction plays an important role in industry for higher productivity, and product quality. This paper focuses on two different models, namely Regression and Artificial Neural Network (ANN) models for predicting tool wear and surface roughness taking cutting speed, feed and depth of cut as input parameters. Experiments have been conducted for measuring tool wear and surface roughness based on Design of Experiments (DOE) technique in a PSG 110 CNC Lathe on machining of AISI H13 steel bars using Cubic Boron Nitride (CBN) content inserted tool. The experimental values are used in Six Sigma software for finding the coefficients to develop the Regression model. The experimentally measured values are also used to train the feed forward back propagation ANN for prediction of tool wear and surface roughness. The performance of the trained ANN model has been tested with experimental data, and found to be better predictions for tool flank wear and surface roughness within the range that they had been trained.