Data-driven analysis and machine learning (ML) algorithms can offer novel insights into tribological phenomena by establishing correlations between material and tribological properties. We developed ML algorithms using tribological data available in the literature for predicting the coefficient of friction (COF) and wear-rate of self-lubricating aluminum graphite (Al/Gr) composites. We collected data on effects of material variables (graphite content, hardness, ductility, yield strength, silicon carbide content, and tensile strength), processing procedure, heat treatment and tribological test variables (normal load, sliding speed, and sliding distance) on tribological properties and established two-parameter relationships. These data are analyzed using several ML algorithms: artificial neural network (ANN), K nearest neighbor (KNN), support vector machine (SVM), gradient boosting machine (GBM), and random forest (RF). The trained ML models can predict the tribological behavior from material variables and test conditions, beyond what is possible from two-parameter correlations. GBM outperformed other ML algorithms in predicting friction behavior, while RF had the best prediction of the wear behavior. ML analysis identified graphite content and hardness and as the most significant variables in predicting the COF, while graphite content and sliding speed were the most dominant variables for wear-rates.

The tribological behavior of graphene and graphite as additives in canola oil was investigated with a pin-on-disk tribometer. The wear surfaces of the aluminum pins lubricated with the additive-containing canola oil were analyzed by scanning electron microscopy (SEM). It was found that graphene and graphite as additives in oil show a lower coefficient of friction and wear rate in comparison with neat canola oil. The graphene sheets are more effective than graphite flakes to reduce friction and wear. In addition, there is a proper concentration where the coefficient of friction (COF) and wear are in minimum value. The optimal concentration of the additive in canola oil is about 0.7 wt %. Therefore, the load-carrying capacity and antiwear ability of the lubricating oil are improved. Moreover, the worn surface of aluminum pins is smother in the presence of solid lubricant rather than neat oil.

In the present work, the effect of graphite nanoplatelets (GNPs) on tribological properties of the aluminum (Al), and Al/alumina (Al₂O₃) composite are studied. GNPs are multilayer graphene sheets which were used as a solid lubricant material. Two sets of composites, Al/GNPs and Al/GNPs/Al₂O₃ with varying amounts of reinforcements, were synthesized by powder metallurgy that involves cold compaction followed by hot compaction. The hardness of the composites increased with the addition of GNPs and Al₂O₃. The Al/GNPs composite with 1 wt.% of GNPs (Al/1GNPs) showed a 20% increase in hardness whereas Al/GNPs/ Al₂O₃ composite with 1 wt.% GNPs and 2 wt.% Al₂O₃ (Al/1GNPs/2Al₂O₃) showed 27% increases in hardness compared to the pure Al. The coefficient of friction measured at 20 N was observed to be 22% and 53% lesser for Al/1GNPs and Al/1GNPs/2Al₂O₃, respectively, compared to corresponding alloys without graphene Al. The X-ray diffraction and scanning electron microscopy analysis revealed the presence of GNPs at the worn surface after the tribology tests. The wear rate was also reduced significantly. In comparison with pure Al, the Al/1GNPs and Al/1GNPs/2Al₂O₃ composites resulted in 5- and 20-times lesser wear rate, respectively. The addition of Al₂O₃ caused reduction in wear rate due to higher hardness and load carrying ability, whereas composites with more than 1 wt.% GNPs showed higher wear rate due to lower hardness and higher porosity. The Al/1GNPs/2Al₂O₃ composite exhibited the least coefficient of friction (0.2–0.25) and wear rate (1 × 10⁻⁶–4 × 10⁻⁶ mm³/N.m) compared to other GNPs and Al₂O₃ reinforced Al composites. The worn surfaces were further analyzed to understand the wear mechanism by Raman spectroscopy, transmission electron microscopy, and x-ray diffraction to detect the Al₄C₃ phase formation, chemical bonding, and defect formation in graphene.

Graphite nanoplatelets (GNPs) as an oil nano additive has gained importance to enhance the lubrication properties of renewable lubricants, such as vegetable oils. Using appropriately processed GNPs is necessary to gain the required tribological advantage. The present study investigated ball-milled GNPs, to understand the effect of GNPs concentration, and applied load on tribological behavior. Pin-on-disk tests were employed, to investigate the tribological performance of the nano-additive oil-based lubricant in the boundary lubrication regime. In order gain an understanding of the lubrication mechanism, Scanning Electron Microscope (SEM), Energy-Dispersive X-ray Spectroscopy (EDX), and Raman Spectroscopy were performed for characterization. The study found that there is a critical concentration of GNPs, below and above which a reduced wear rate is not sustained. It is found that the tribological enhancements at the optimum concentration of GNP in boundary lubrication condition are a result of reduced direct metal–metal contact area at the interface. This phenomenon, along with the reduced shear strength of the ball-milled GNPs, is indicated to reduce the formation of asperity junctions at the interface and enhance tribological properties of the nano-additive oil-based lubricant.