Study on dry sliding wear behavior and machine learning models for wear rate prediction of nano hybrid 2219 MMCs reinforced with n-B4C \& MoS2

This study examines the dry sliding wear behaviour of stir-cast Aluminium 2219 nano composites reinforced with nano boron carbide and a hybrid combination of nano boron carbide \& Molybdenum disulfide particles. The wear properties were analyzed under varying conditions of sliding speed (0.65-13.0 m per second), applied load (5-100 N), and sliding distance (250-5000 m). Key factors such as nanoparticle dispersion, density, hardness, and wear resistance were investigated. The results reveal that adding nanoparticles enhances wear resistance, which correlates with increased hardness. Both Aluminium 2219 composites reinforced with nano boron carbide and hybrid (nano boron carbide \& Molybdenum disulfide) reinforcements exhibit similar wear behaviour trends. However, the hybrid composites (nano boron carbide \& Molybdenum disulfide) demonstrate significantly improved wear resistance across all tested conditions, with MoS 2 inclusion playing a crucial role in further enhancing wear resistance. The particular wear rate of Aluminium 2219 was predicted using machine learning models, including Linear Regression, Ridge Regression, Lasso Regression, Support Vector Regression, K-Nearest Neighbors, Option Tree, Random Forest, and Gradient Boosting. The primary input parameters, applied load, sliding speed, and sliding distance, were analyzed to determine their impact on wear rate. Several criteria were used to assess the performance of various machine learning models. Ensemble models such as Random Forest, Decision Tree, and Gradient Boosting, along with K-Nearest Neighbors, exhibited minimal deviations and demonstrated robust predictive accuracy.