Use of artificial neural network and multi-objective genetic algorithm approach to predict and ascertain stable cutting zone in conventional turning process

Abstract

This article is focused on the investigation of stable cutting zone in turning operation. Experiments have been conducted to acquire raw chatter signals. Generally, raw chatter signals are contaminated with ambient noise. Wavelet transform has been used for pre-processing and denoising these signals. In order to predict the severity of tool chatter, a new parameter denoted as chatter index has been evaluated considering the aforesaid denoised signals. In the present work, mathematical models have been developed for chatter index and metal removal rate using feedforward backpropagation–based artificial neural network considering three activation functions: TANSIG, LOGSIG and PURELIN. Furthermore, multi-objective genetic algorithm technique has been applied to evaluate stable cutting zones with maximized metal removal rate. TANSIG activation function found to be best option to achieve the aforesaid objectives. Good correlation between the artificial neural network predicted results and experimental ones validate the developed technique.