Modeling and optimization of VEAM of 10% B4C/Al metal matrix composite using ANN-SCA approach

Abstract

Shaping advanced materials such as superalloys and metal matrix composites is still a herculean task for the engineering fraternity. People are developing innovative manufacturing processes (MPs) to shape such kind of advanced materials. Electrical arc machining (EAM) is one such subtractive MP which is under development stage. The present paper discusses one newly developed advanced machining process named as vibration assisted EAM (VEAM). The machining on metal matrix composite has been performed using VEAM. Two of the performance indicators that are material removal rate (MRR) and tool wear rate has been explored during machining using VEAM. Experimental findings indicate that VEAM results in significantly enhanced MRR as compared to conventional EDM. At the last the single objective optimization has been done by using hybrid artificial neural network & four advanced optimization algorithms such as self-adaptive differential evolution, shuffled frog leaping algorithm, coordinated aggregation based particle swarm optimization and sine cosine algorithm (SCA). It has been observed that SCA demonstrate better performance as compared to its peers.