Prediction and optimisation of tool wear for end milling operation using artificial neural networks and simulated annealing algorithm

Abstract

This paper highlights the development of neural network model for predicting the tool wear and optimising the process parameters using simulated annealing algorithm. The process parameters chosen for this study are helix angle, spindle speed, feed rate, and depth of cut. The output parameter chosen was tool wear. The experiments were conducted based on design of experiments using fractional factorial with 125 runs. The material and tool selected for this study is AISI 304 austenitic stainless steel and uncoated solid carbide end mill cutter respectively. Using the experimental data, a feed-forward back propagation neural network model was developed and trained using the Levenberg-Marquardt algorithm. It was observed that the ANN model based on network 4-12-1 predicted tool wear more accurate. A mathematical model was also developed correlating the process parameters with tool wear for ensuring optimisation. The optimised process parameters gave a value of 0.093603 mm for tool wear.