Optimization of friction stir processing parameters of aluminum hybrid composites using genetic algorithm and RSM-CCD for enhanced wear and corrosion resistance

Aluminum hybrid metal matrix composites (HMMCs) possess a distinct combination of high strength, wear resistance, and corrosion stability. This research aims to bridge gap by producing and optimizing an AA2014 hybrid nanocomposite reinforced with silicon carbide (SiC) and hexagonal boron nitride (HBN) through FSP. This work integrates response surface methodology (RSM)–Central Composite Design (CCD) to develop predictive regression models and then applies the genetic algorithm (GA) to those models to determine the global optimal combination of process parameters. The novelty lies in coupling data-driven RSM predictions with GA optimization to achieve a simultaneous reduction in wear and corrosion rates. Experimental findings show that the addition of 6 wt.% reinforcement (3 wt.% SiC and 3 wt.% HBN) resulted in a decrease in wear rate and improvement in corrosion resistance. GA-based optimization determined the best FSP parameters as reinforcement content of 6 wt.%, tool rotational speed of 1100 RPM, and traverse speed of 45 mm/min, that led to wear rate of 0.0032 mm3 /m and corrosion rate of 0.56 mm/year, representing reductions of 64% and 58%, respectively, compared to the untreated alloy. The integrated RSM–GA framework demonstrates a reliable strategy for multi-objective optimization in FSP, enabling the design of high-performance aluminum nanocomposites with superior mechanical integrity and service life.