Study of tool wear using acoustic emission and intelligent techniques

Abstract

One of the challenges in the manufacturing industries is the ability of the machines to change the tools automatically during its wear or damage In general tool failure contributes about 7 to the down time of the machining centers Therefore on line monitoring of tool wear is an important phenomenon in producing quality products at reasonable cost This also increases the production rate in the industries Tool condition monitoring using Acoustic Emission Technique is one of the best methods identified by researchers for on line quality assessment of machine tools Artificial Neural Network is an information processing system that has certain performance characteristics in common with biological neural networks The artificial neural network have been developed as generalisation of mathematical models of human neural biology The network is trained by initially selecting random weights and internal threshold and then presenting all training data Weights and thresholds are adjusted after every training until required output is obtained This technique is utilized to predict the expected tool wear during its operation