Prediction of surface roughness during wire electrical discharge machining of SiCp/6061 Al metal matrix composite

Abstract

In this work, response surface methodology (RSM) and artificial neural network (ANN) techniques were used for predicting the surface roughness during wire electrical discharge machining (WEDM) of SiCp/6061 Al metal matrix composite. Box-Behnken design approach has been used and totally 29 experiments were carried out using four process input variables, i.e. servo voltage, pulse-on time, pulse-off time and wire feed rate. The mathematical relationship between WEDM input process parameters and surface roughness was established to determine the value of surface roughness mathematically. The RSM predicted values and ANN predicted values of surface roughness were compared with the experimental values and their closeness with the experimental values was determined. Good agreement was observed between the predicted model results and experimental results. Finally, the ANN model and RSM model for surface roughness were compared with each other. © 2012 Inderscience Enterprises Ltd.