TOOL-WEAR PREDICTION USING ARTIFICIAL NEURAL NETWORKS

A mixed-oxide ceramic cutting tool (type K090) has been used to machine grey cast iron (grade G-14) in a turning process. Different values of feed rate and cutting speed have been used for machining at a constant depth of cut. Tool life and failure mode have been recorded for each experiment and the associated data have been used to train an artificial neural network (multi-layer perceptron) using the back-propagation algorithm. The trained network has been used to predict tool lives and failure modes for experiments not used in training. The best results are 58.3% correct tool-life prediction (within 20% of the actual tool life) and 87.5% correct failure-mode prediction, but it was felt that these could be improved significantly if more real data was generated for the training of the neural network.