SBLMD–ANN–MOPSO-based hybrid approach for determining optimum parameter in CNC milling

Abstract

In the recent decades, researchers have proposed various techniques to mitigate chatter effects in milling operation. Still a robust methodology is yet to be developed that can suggest stability bounds pertaining to higher metal removal rate (MRR). In the present work, experimentally acquired acoustic signals in milling operation have been processed using a modified Spline Based Local Mean Decomposition (SBLMD) technique in order to extract tool chatter features. Further, six artificial neural network (ANN) training algorithms viz.Resilient Propagation (RP), Conjugate Gradient Based (CGP and SCG), Quasi-Newton Based (BFGS and OSS) and Levenberg-Marquardt Algorithm (LM) has been used to train the acquired chatter vibration and metal removal rate data set. Over-fitting or under-fitting issues may arise from the random selection of a number of hidden neurons. The solution to these problems is also proposed in this paper. Among these training algorithms, suitable one has been selected and further invoked to develop prediction models of chatter severity and metal removal rate. Finally, multi-objective particle swarm optimization (MOPSO) has been applied to optimize developed prediction models for obtaining an optimal range of input parameters pertaining to stable milling with higher productivity.