Abrasive Wear Behavior of Zr-Reinforced LM13 Composites: Experimental and Machine Learning Analysis

This study investigates the influence of sliding speed and zirconium (Zr) chill reinforcement on the wear behavior of LM13 alloy composites through experimental evaluation, microstructural analysis, and predictive modeling. Specimens were prepared according to ASTM standards and subjected to abrasive wear testing at varying speeds and reinforcement levels (0–12% Zr). The experimental results revealed that wear rate increased consistently with sliding speed, while the incorporation of Zr significantly reduced material loss, with 9–12% reinforcement demonstrating the highest wear resistance. Microstructural analysis using SEM confirmed the uniform dispersion of zircon particles within the LM13 matrix, enhancing hardness and load-bearing capacity, while delamination features indicated fatigue-induced wear at elevated speeds. XRD and EDS analyses further validated the crystalline structure and elemental composition, confirming the successful integration of Zr reinforcements. To complement experimental findings, machine learning techniques including Linear, Polynomial, Support Vector Regression (SVR), Decision Tree, and Random Forest models were employed to predict wear behavior. All models achieved high accuracy (R² >0.93), with Polynomial regression consistently providing the most reliable predictions, as supported by error and significance analysis. Sensitivity and feature importance studies identified Zr% as the dominant factor influencing wear resistance, while speed remained a critical contributor to wear intensification.