Prediction of cutting process parameters in boring operations using artificial neural networks

This study deals with the development of displacement of the tool (amplitude of vibration), cutting temperature and tool wear prediction model for boring process using artificial neural networks (ANNs). The experiments have been conducted using full factorial design on an all-geared head lathes with the experimental setup. The adequacy of the developed model is verified by using the neural network model, which has been developed using the feed-forward back propagation algorithm using training data and tested using test data. To judge the ability of the model to predict displacement of the tool (amplitude of vibration), cutting temperature and tool wear values, the percentage deviation and average absolute percentage deviation have been used. The predicted ANN model values are very close to the experimental results.