Machinability evaluation and multi‐objective optimization of Al‐Cu‐SiC‐graphene nano‐platelets hybrid composite using water jet machining and machine learning approaches

This study investigates the mechanical behavior and machinability of a novel hybrid metal matrix composite comprising aluminum–copper alloy reinforced with 5 weight‐% silicon carbide and 5 weight‐% graphene nanoplatelets. The composite was fabricated using the stir casting technique and subjected to mechanical testing, which revealed significant improvements in tensile strength, compressive strength, and hardness compared to the unreinforced aluminum–copper matrix. Abrasive water jet machining was employed to evaluate the machinability of the composite under varying process parameters jet pressure (1500 bar – 3000 bar), standoff distance (1 mm – 3 mm), and traverse speed (50 mm/min – 200 mm/min) using a taguchi L27 orthogonal array. Key output responses such as kerf width, material removal rate, and surface roughness were analyzed through analysis of variance, which identified jet pressure as the most significant factor affecting kerf formation. Machine learning models including artificial neural networks, random forest regression, and decision trees were developed to predict machining performance. Among these, the artificial neural networks model achieved the highest prediction accuracy (coefficient of determination (R 2 ) > 0.98), effectively captu r ing nonlinear dependencies. Multi‐objective optimization using a desirability function identified the optimal abrasive water jet machining parameters to be 2700 bar jet pressure, 2 mm standoff distance, and 50 mm/min traverse speed. The study demonstrates that the integration of ceramic and nano‐reinforcements significantly enhances both mechanical and machinability performance, while machine learning models provide reliable real‐time predictive capabilities. The findings support the adoption of intelligent, high‐precision machining strategies for advanced hybrid composites in aerospace and structural applications.