Triboinformatic Approaches for Composite Coatings on Titanium Alloys

Ti-6Al-4 V is an (α + β) titanium alloy that has been most widely used in automotive, aerospace, and biomedical applications due to the extensive material properties of high strength, toughness, high strength-to-weight ratio, and biocompatibility. Machine learning (ML) algorithms of data-driven methods provide a better understanding of the correlation between material properties and tribological properties. Correlations of tribological test variables (sliding speed, sliding distance, and normal load) with the tribological properties (coefficient of friction and wear rate) were studied using machine learning algorithms. A total of 41 data points based on the Ti-6Al-4 V alloy coating were divided into training and testing sets in the ratio of 80:20. The ML-based algorithms, which include Decision Tree (DT) and Random Forest (RF) algorithms, have been studied to predict the wear rates and coefficient of friction. The evaluation metrics like MAE, MSE, and RMSE are used to find the best suitable algorithm for the predictions. Using the data analysis, the coefficient of friction and wear rates have been satisfactorily predicted from the considered data sets.