Experimental Investigation of the Influence of Various Wear Parameters on the Tribological Characteristics of AZ91 Hybrid Composites and their Machine Learning Modelling

Abstract In the current work, the AZ91 hybrid composites are fabricated through the utilization of the stir casting technique, incorporating aluminum oxide (Al2O3) and graphene (Gr) as reinforcing elements. Wear behavior of the AZ91/Gr/Al2O3 composites was examined with the pin-on-disc setup under dry conditions. In this study, the factors such as reinforcement percentage (R), load (L), velocity (V), and sliding distance (D) have been chosen to investigate their impact on the wear-rate (WR) and coefficient of friction (COF). This study utilizes a full factorial design to conduct experiments. The experimental data was critically analyzed to examine the impact of each wear parameter (i.e., R, L, V, and D) on the WR and COF of composites. The wear mechanisms at the extreme conditions of maximum and minimum wear rates are also investigated by utilizing the scanning electron microscope (SEM) images of specimen's surface. The SEM study revealed the presence of delamination, abrasion, oxidation, and adhesion mechanisms on the surface experiencing wear. Machine learning (ML) models, such as decision tree (DT), random forest (RF), and gradient boosting regression (GBR), are employed to create a robust prediction model for predicting output responses based on input variables. The prediction model was trained and tested with 95% and 5% experimental data points, respectively. It was noticed that among all the models, the GBR model exhibited superior performance in predicting WR, with mean square error (MSE) = 0.0398, root-mean-square error (RMSE) = 0.1996, mean absolute error (MAE) = 0.1673, and R2 = 98.89, surpassing the accuracy of other models.