Data analytics approach to predict the hardness of the copper matrix composites

Copper matrix composite materials have exhibited a high potential in applications where excellent conductivity and mechanical properties are required. In this study, the machine learning models have been applied to predict the hardness of the copper matrix composite materials (CuMCs) produced via the powder metallurgy technique. Six different machine learning regression models were employed. The observed CuMCs were reinforced with two different volume fractions (2 vol.% and 7vol.%) of ZrB2 particles. Based on experimental work, we extracted the independent variables (features) like the milling time (MT, Hours), dislocation density (DD, m-2), average particle size (PS, μm), density (ρ, g/cm3), and yield stress (σ, MPa) while the Vickers hardness (MPa) was used as the dependent variable. Feature selection was performed by calculation the Pearson correlation coefficient (PCC) between the independent and dependent variables. The predictive accuracy higher than 80% was achieved for Cu-7vol.% ZrB2 and lower for the Cu-2vol.% ZrB2.