On Line Robust Tool Wear Estimation during Turning of En31alloy Steel Using AE Sensor and Artificial Neural Network

Abstract

This paper describes on line tool wear toolwear estimation approach with a neural network modeling of cutting tool flank wear in order to estimate the performance of insert during of En31 alloy DNMX150608WM1525 steel. In the present work actual cutting tool flank wear data have been used and back propagation neural network model is developed to predict the flank wear turning. The experimental data were utilized to train artificial neural network model.Process parameters such as cutting speed, feed rate, and depth of cut are used as input and corresponding flank wear of this condition is output of the neural network model. The performance of train neural network has been tested with the experimental data. This investigation shows the effective use of fuzzy logic technique for tool wear monitoring in turning.