Enhancing wear resistance of E-glass/Copper composites: a machine learning approach to graphene filler optimization

Wear resistance is a critical requirement for materials used in automotive, aerospace, and electronic components operating under severe mechanical and thermal conditions. Although copper is extensively utilized due to its superior electrical and thermal conductivity, its poor wear resistance limits its tribological applications. The present study introduces a novel hybrid copper matrix composite reinforced simultaneously with graphene and E-glass fibers, fabricated via a scalable stir casting route. The wear behavior of Graphene/E-glass fiber/Copper composites was systematically evaluated by varying graphene content from 0.5 to 1.5 wt.% and E-glass fiber content from 3 to 7 wt.%. The results demonstrate a significant reduction in wear rate with increasing reinforcement concentration, primarily due to the formation of a protective tribolayer, reduced metal-to-metal contact, and the inherent self-lubricating behavior of graphene. The composite containing 1.5 wt.% graphene and 5 wt.% E-glass fiber exhibited the minimum wear rate, outperforming both lower-reinforced composites and monolithic copper under dry sliding conditions. The novelty of this work lies in the synergistic hybrid reinforcement strategy combined with machine-learning-assisted optimization, enabling efficient identification of optimal compositions. From a practical standpoint, this approach offers a cost-effective and scalable pathway for designing next-generation, wear-resistant copper composites suitable for high-speed, high-load tribological applications in automotive, aerospace, and advanced electronic systems.