ABSTRACT
Electro-discharge machining (EDM) is a well-known nontraditional machining operation frequently employed by engineers especially in mold and automobile industries. As a hard material, Inconel 718 superalloy is highly utilized in various industries due to its excellent mechanical properties. Therefore, the EDM process of this alloy provides some technical benefits. Rough surface quality and long process time are two important challenges with respect to the EDM operation. There are several adjustable parameters in EDM that affect process conditions significantly, and unlike the previous studies, only experimental evaluation of process parameters cannot lead to optimal and comprehensive results. In this regard, new strategies such as evolutionary optimization algorithms can be efficiently used to optimize the process conditions. Therefore, the purpose of the present study is to perform experimental investigation and to use efficient intelligent methods based on artificial neural networks and nondominated sorting genetic algorithm for simultaneously optimizing the EDM process of Inconel 718 alloy. Based on this, the influence of process parameters including gap voltage, pulse-on time, peak current, and pulse-off time was studied on material removal rate and surface quality. In addition, the optimal process conditions were successfully obtained using the hybrid strategy.