Abstract
This study highlights the importance of Al–Fe–Si alloys in modern engineering for their enhanced hardness, strength, and wear resistance, improving fuel efficiency in the aerospace and automotive sectors. Data-driven analysis and machine learning methods can help understand tribological occurrences by identifying links between material characteristics and tribological behavior. The research examined TiC reinforcement in aluminum nanocomposites synthesized via ultrasonic-assisted stir casting, creating five composites with TiC weight percentages from 0% to 8%. Tests conducted using pin-on-disc equipment under various conditions, including loads of 5–15 N, sliding velocities of 0.5–1.5 m/s, sliding distances of 80–120 m, and abrasive grit sizes of 80–150 µm, revealed significant findings. The Al–6TiC nanocomposite demonstrated an 18% reduction in wear-rate at 80 µm, 28.2% at 120 µm, and 24.5% at 150 µm under a 15 N load and 120 m sliding distance compared to the pure alloy. There was also a 22% friction coefficient reduction with increased loads and grit sizes. Scanning electron microscope (SEM) analysis of the worn surfaces and abrasive papers was conducted. Wear-rate data were analyzed using six machine learning models, with the gradient boosting regressor (GBR) identified as the most accurate, achieving an R2 value of 0.95. This study emphasizes the impact of the TiC content, loading conditions, and hardness on wear and friction coefficient, and shows how machine learning techniques can predict and optimize advanced aluminum nanocomposite design for engineering applications.