Hybrid Optimization Approach for Improving Surface Roughness and MRR in MMC Non-Conventional Machining

Metal Matrix Composites (MMCs) are widely utilized in aerospace, automotive, and defence sectors due to their high strength-to-weight ratio, thermal stability, and superior wear resistance. However, these properties also present significant challenges during machining, making non-conventional machining (NCM) techniques the preferred choice. This study proposes a hybrid optimization framework that integrates Response Surface Methodology (RSM) with a meta-heuristic algorithm to jointly enhance surface roughness (Ra) and material removal rate (MRR) during the NCM of MMCs. A structured experimental design was implemented to examine the influence of critical parameters such as discharge current, pulse-on time, pulse-off time, and electrode type. The hybrid RSM–GA/PSO model delivered improved prediction accuracy and outperformed individual optimization methods by generating a superior Pareto-based multi-objective solution. Experimental validation revealed that the optimized parameter combination achieved an average 22–30% reduction in surface roughness and a 15–25% enhancement in MRR, demonstrating the effectiveness of the proposed hybrid approach. The findings contribute a robust, industry-ready decision-support mechanism for optimizing machinability in advanced MMC materials and pave the way for high-performance non-conventional machining strategies.