Prediction of Electric Discharge Machining Process Parameters Using Artificial Neural Network

Abstract

Electric Discharge Machining (EDM) has become more preferable and cost effective method for machining high hardened stainless steels. It is non-traditional machining process in which work piece and tool wear takes place through the process of spark generation between electrode and work-piece which are submerged in a insulated oil medium. Optimization of operating parameters is an important action in machining, particularly for unconventional electrical type machining procedures like EDM. A proper selection of machining parameters for the EDM process is heavily on the operator’s technologies and experience because of their numerous and diverse range. Machining parameters provided by the machine tool builder cannot meet the operator’s requirements. In this research work the effect of Pulse pause time (Toff), current (I), Pulse on time (Ton), and Tool lift time (TL) on response parameters like Material Removal Rate (MRR) and Tool Wear Rate (TWR) is studied. This work is done on 17-4 PH stainless steel as work piece and electrode as copper-tungsten. Design of experiments is done using Response surface method with Box – Behnken design and some of the experimental values are trained and validated using artificial neural network.