Parametric Analysis, Modeling, and Optimization of Vibration-Assisted Electrical Arc Machining of Advanced Engineering Materials

Abstract

Electrical Arc Machining (EAM) has emerged as a promising unconventional machining process capable of machining advanced materials with high Material Removal Rates (MRR). This research presents a comprehensive investigation of Vibration-Assisted Electrical Arc Machining (VEAM) applied to Aluminum-Boron Carbide (Al-B₄C) Metal Matrix Composite (MMC) and Ti-6Al-4V alloy. An innovative VEAM setup was developed, incorporating a mechanical motion arc-breaking mechanism with tool vibration capabilities. The study involved parametric analysis using Box-Behnken design of experiments, mathematical modeling using Response Surface Methodology (RSM) and Artificial Neural Networks (ANN), and optimization using hybrid ANN-evolutionary algorithms. For Al-B₄C MMC machining, the Sine Cosine Algorithm (SCA) demonstrated superior performance, achieving MRR improvements of 40% and Tool Wear Rate (TWR) improvements of 12%, respectively. During Ti-6Al-4V alloy machining, the Rao-3 algorithm provided optimal results with 7.4% improvement in MRR and 9.93% reduction in TWR. ANN models proved significantly more accurate than regression models, with correlation coefficients exceeding 0.98 and negligible mean square error. The developed VEAM process achieves MRR approximately 50 times higher than conventional electrical discharge machining, establishing it as a viable alternative for precision machining of advanced materials. This research contributes critical knowledge regarding vibration-assisted unconventional machining, artificial intelligence-based modeling, and evolutionary optimization of complex manufacturing processes.