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 effects of process conditions on Fischer–Tropsch Synthesis (FTS) product distributions were studied using a fixed-bed microreactor and a Co–Mn/CNT catalyst. Cobalt and Manganese, supported on Carbon Nanotubes (CNT) catalyst were prepared by a Strong Electrostatic Adsorption (SEA) method. CNT supports were initially acid and thermally treated in order to functionalize support to uptake more Co clusters. Catalyst samples were characterized by Transmitted Electron Microscope (TEM), particle size analyzer, and Thermal Gravimetric Analysis (TGA). TEM images showed catalyst metal particle intake on CNT support with different Co and Mn loading percentage. Performance test of Co–Mn/CNT in Fischer–Tropsch synthesis (FTS) was carried out in a fixed-bed micro-reactor at different pressures (from 1 atm to 25 atm), H2/CO ratio (0.5–2.5), and reduction temperature and duration. The reactor was connected to the online Gas Chromatograph (GC) for product analysis. It was found that the reaction conditions have the dominant effect on product selectivity. Cobalt catalyst supported on acid and thermal pre-treated CNT at optimum reaction condition resulted in CO conversion of 58.7% and C5+ selectivity of 59.1%.

The effect of reaction temperature, syngas space velocity, and catalyst stability on Fischer-Tropsch reaction was investigated using a fixed-bed microreactor. Cobalt and Manganese bimetallic catalysts on carbon nanotubes (CNT) support (Co-Mn/CNT) were synthesized via the strong electrostatic adsorption (SEA) method. For testing the performance of the catalyst, Co-Mn/CNT catalysts with four different manganese percentages (0, 5, 10, 15, and 20%) were synthesized. Synthesized catalysts were then analyzed by TEM, FESEM, atomic absorption spectrometry (AAS), and zeta potential sizer. In this study, the temperature was varied from 200 to 280 °C and syngas space velocity was varied from 0.5 to 4.5 L/g.h. Results showed an increasing reaction temperature from 200 °C to 280 °C with reaction pressure of 20 atm, the Space velocity of 2.5 L/h.g and H₂/CO ratio of 2, lead to the rise of CO % conversion from 59.5% to 88.2% and an increase for C₅₊ selectivity from 83.2% to 85.8%. When compared to the other catalyst formulation, the catalyst sample with 95% cobalt and 5% manganese on CNT support (95Co5Mn/CNT) performed more stable for 48 h on stream.