Application of Triboinformatics Approach in Tribological Studies of Aluminum Alloys and Aluminum-Graphite Metal Matrix Composites

Aluminum-graphite (Al/Gr) metal matrix composites (MMC) have shown reduced friction, wear, and resistance to seizure. Triboinformatics or the data-driven approach is promising in predicting the tribological behavior of metal alloys and metal matrix composites (MMC). Five Machine Learning (ML) models: Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Random Forest (RF) have been applied to predict the coefficient of friction (COF) and wear rate of aluminum (Al) alloys and Al/Gr MMCs using material and tribological variables. The performance metrics indicate that the graphite incorporation as a solid lubricant makes the friction and wear behavior more consistent and predictable. Feature importance analysis shows that graphite content is the most significant variable in both wear rate and COF prediction of Al/Gr composites while tribological variables are found significant for aluminum alloys. Additionally, material hardness is found important in friction and wear prediction for both aluminum alloys and Al/Gr MMCs.