Neural network based modeling in wire electric discharge machining of SiC p/6061 aluminum metal matrix composite

Abstract

Wire electric discharge machining (WEDM) process is considered to be one of the most suitable processes for machining metal matrix composite (MMC) materials. Lot of research work has been done on WEDM process, but very few investigations have been done on WEDM of MMCs. The purpose of this research work is to develop the artificial neural network (ANN) model to predict the material removal rate (MRR) during WEDM of SiC p/6061 Al MMC. In this work four input parameters namely servo voltage, pulse-on time, pulse-off time and wire feed rate were used to develop the ANN model. The output parameter of the model was MRR. A Box-Behnken design (BBD) approach of response surface methodology (RSM) was used to generate the input output database required for the development of ANN model. Training of the neural network models were performed on 29 experimental data points. The predicted values obtained from ANN model show that model can predict MRR with reasonable accuracy. The good agreement is obtained between the ANN predicted values and experimental values. In the present case, the value of correlation coefficient (R) equal to 0.9968, is closer to unity for ANN model of MRR. This clearly indicates that prediction accuracy is higher for ANN model.