Prediction of tool wear in high speed machining using acoustic emission technique and neural network

Abstract

High speed machining (HSM) provides a lot of perks like higher productivity, better surface finish and good accuracy but with the limitation of rapid tool wear rate. On-line tool wear monitoring is therefore essential for a fully automated high speed machining process. Acoustic emission (AE) technique has proven to be a better tool wear monitoring method owing to its sensitivity, quick response time and consistency. This work deals with the formulation of methodology and conduct experiments for predicting the tool wear in high speed machining using acoustic emission technique and artificial neural network (ANN). Taguchi’s design of experiments has been used to optimize the number of experiment. The experimental observations are used to train an artificial neural network to predict the progressive tool wear. The outcome of the work includes the selection of optimum cutting parameters for minimum tool wear, identification of the percentage contribution of individual parameters towards tool wear and the prediction of tool wear using artificial neural network with a maximum deviation of 4%.