2020/02/24 by Somesh Kr. Bhattacharya, Bhattacharya, Somesh Kr., Ryoji Sahara +5
Engineering · Materials Science · #Aluminum Alloy Microstructure Properties #Aluminum Alloys Composites Properties #Applied Physics (physics.app-ph) #FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci) #Microstructure and mechanical properties
paper · pdf · doi:10.48550/arxiv.2002.10649
openalex publication_date 2020/02/24 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Copper matrix composite materials have exhibited a high potential in\napplications where excellent conductivity and mechanical properties are\nrequired. In this study, the machine learning models have been applied to\npredict the hardness of the copper matrix composite materials produced via\npowder metallurgy technique. Two particular composites were considered in this\nwork. From experiments, we extracted the independent variables (features) like\nthe milling time (MT, Hours), dislocation density (DD, 1/m2 ), average particle\nsize (PS,nm), density (gm/cm3 ) and yield stress (MPa) while the Vickers\nHardness (MPa) was used as the dependent variable. Feature selection was\nperformed by calculation the Pearson correlation coefficient (PCC) between the\nindependent and dependent variables. We employed six different machine learning\nregression models to predict the hardness for the two matrix composites.\n