Application of Machine Learning to Mechanical Properties of Copper Graphene Composites

While copper-graphene (Cu/Gr) composites have been promising materials due to their theoretically high strength and conductivity, their design has been hampered by the large number of variables affecting their properties. We applied four different Machine Learning (ML) models to manually collected datasets compiling the yield strength and ultimate tensile strength of graphene-reinforced copper composites processed with powder metallurgy techniques. Our results indicate that ML models can predict the mechanical properties of Cu/Gr composites with satisfactory accuracy. Feature analysis provided new insights into the most important factors that affect these properties.