Prediction of tool chatter in turning using RSM and ANN

This paper presents a new technique to explore the mechanism of tool chatter in turning process using statistical approach along with signal pre-processing technique. In this paper, experiments have been conducted considering depth of cut, feed rate and spindle speed to acquire chatter signals. Further, wavelet transform (WT) has been used to process the acquire signals and a new parameter called chatter index (CI) has been calculate to quantify the chatter severity. Moreover, response surface methodology (RSM) and feed forward back propagation based artificial neural network (ANN) have been used to develop mathematical model for CI. Analysis of variance (ANOVA) and regression analysis has been done to check the adequacy of RSM and ANN model respectively. (C) 2018 Elsevier Ltd. All rights reserved. Selection and/or Peer-review under responsibility of International Conference on Advances in Materials and Manufacturing Applications [IConAMMA 2017].