Optimization of wire electrical discharge machining of pure tungsten using neural network and response surface methodology

Abstract

The present study analysed the dependence of the material removal rate and workpiece surface finish on process parameters during the manufacture of pure tungsten profiles by wire electrical discharge machining (WEDM). A hybrid method including a back-propagation neural network (BPNN), a genetic algorithm (GA), and response surface methodology (RSM) was proposed to determine optimal parameter settings of the WEDM process. Specimens were prepared under different WEDM processing conditions based on a Taguchi orthogonal array table. The results of 18 experimental runs were utilized to train the BPNN to predict the material removal rate and roughness average properties. Simultaneously, the RSM and GA approaches were individually applied to search for an optimal setting. In addition, analysis of variance was implemented to identify significant factors for the WEDM process parameters, and results from the BPNN with integrated GA were compared with those from the RSM approach. The results show that the RSM and BPNN/GA methods are both effective tools for the optimization of WEDM process parameters.