On-line monitoring of tool wear in turning using a neural network

Tool wear has long been identified as the most undesirable characteristic of the machining operations. Flank wear, in particular directly affects the workpiece dimensions and the surface quality. A reliable and sensitive technique for monitoring the tool wear without interrupting the process, is crucial in realization of the modern manufacturing concepts like unmanned machining centres, adaptive control optimization, etc. In this work an optoelectronic sensor is used in conjunction with a multilayered Neural Network for predicting the flank wear on the cutting tool. The gap sensing system consists of a bifurcated optical fibre, a laser source and a photodiode circuit. The output of the photodiode circuit is amplified and converted to the digital form using an A/D converter. The digitized sensor signal along with the cutting parameters form the inputs to a three layered, feed forward, fully connected Neural Network. The Neural Network, trained off-line using a backpropagation algorithm and the experimental data, is used to predict the flank wear. A geometrical relation is also used to correlate the flank wear on the cutting tool with the change in the workpiece dimension. The values predicted using the Neural Network and those calculated using the geometrical relation are compared with the actual values measured using a tool maker's microscope. Results showed the ability of the; Neural Network to accurately predict the flank wear. (C) 1998 Elsevier Science Ltd. All rights reserved.