PREDICTION OF SURFACE ROUGHNESS IN WIRE ELECTRICAL DISCHARGE MACHINING USING DESIGN OF EXPERIMENTS AND NEURAL NETWORKS

Wire erosion discharge machining (WEDM) is a modification of electro discharge machining (EDM) and has been widely used for a long time for cutting punches and dies, shaped pockets and other machine parts on conductive work materials. The surface finish of the machined surface mainly depends on the pulse duration, open voltage, wire speed and dielectric flushing pressure. In the present work, two of the techniques, namely factorial design and neural network (NN) were used for modeling and predicting the surface roughness of AISI 4340 steel. Surface roughness was taken as a response variable measured after WEDM and pulse duration, open voltage, wire speed and dielectric flushing pressure were taken as input parameters. Relationships between surface roughness and WEDM cutting parameters have been investigated. The level of importance of the WEDM cutting parameters on the surface roughness was determined by using the analysis of variance method (ANDVA). The mathematical relation between the workpiece surface roughness and WEDM cutting parameters were established by regression analysis method. This mathematical model may be used in estimating the surface roughness without performing any experiments. Finally, predicted values of surface roughness by techniques, NN and regression analysis, were compared with the experimental values and their closeness with the experimental values determined. Results show that, NN is a good alternative to empirical modeling based on full factorial design.