Analysis of the friction and wear of graphene reinforced aluminum metal matrix composites using machine learning models. (June 2022)

• Record Type: Journal Article
• Authors: Hasan, Md Syam; Wong, Tien; Rohatgi, Pradeep K.; Nosonovsky, Michael
• Is Part Of: Tribology international. Volume 170(2022)
• Publication Date: 2022-06
• Subjects: Aluminum-graphene composite -- Graphene -- Triboinformatics -- Machine learning -- Solid lubricant; Tribology -- Periodicals; 621.89
• DOI: 10.1016/j.triboint.2022.107527
• Languages: English
• ISSNs: 0301-679X

Abstract

Abstract: The effect of graphene on the material properties, friction, and wear of self-lubricating aluminum-based metal matrix composites (MMC) was compared with the effect of graphite as the reinforcement. Notable enhancement of mechanical properties and friction and wear performance was observed with graphene addition. Statistical analysis suggested that a much lesser amount of graphene reinforcement can produce friction and wear performance similar to that of aluminum MMCs with a higher amount of graphite. Five machine learning (ML) regression models were developed to predict the wear rate and coefficient of friction (COF) of aluminum-graphene MMCs. ML study suggested that the weight percent of graphene, loading conditions, and hardness had the largest influence on the wear and friction of aluminum-graphene composites.