Modeling and Optimization of Material Removal Rate Based on Artificial Intelligence in Electrical Discharge Machining Using Super Alloy

Abstract

Because of its exceptional mechanical qualities, titanium superalloy is most commonly employed in aero planes, spacecraft, naval ships, missiles, and many other significant industries. The most effective production techniques for shaping these kinds of materials are unusual machining processes, or UMPs. One such thermal energy-based UMP that has gained widespread acceptance for the machining of titanium alloys is electrical discharge machining (EDM). In the current study, material removal rate (MRR) was assessed using EDM on Ti-6Al-4V alloy by adjusting peak current, pulse-on time, and pulse-off time. After developing an artificial neural network (ANN) model for MRR, a hybrid strategy combining ANN and genetic algorithms was used to optimise MRR for a single aim.