Analysis of Friction and Dry Sliding Wear Characteristics of Nano-Aluminium Metal Composite Using Machine Learning Through Linear Regression Algorithm

The aim of this research is to study the friction and dry sliding wear characteristics of nano-aluminium metal composite using machine learning through linear regression algorithm. Al 5182 alloy was used as a base material and SiC nano-particles were dispersed into the alloy through stir casting and ultra-sonic dispersion at different compositions (0.2, 0.4, 0.6, 0.8, and 1%) in order to analyze the effect of composition on friction and wear characteristics. L 25 alloy was used as a counter material in the experiments. The response variables, wear loss (Wl), were measured and the input parameters, composition, rotational speed, and sliding distance, were varied in the experiments. Signal to noise ratio was used to determine the best grouping of parameters that reduced wear loss. The results were then predicted using artificial neural network (ANN) and regression analysis. The derived equation for predicting the responses showed better accuracy in predicting the wear loss values. The study provides important insights into the resistance and wear characteristics of nano-aluminium composites, and the results can be used to improve the performance and life of these materials in various applications. Overall, this research provides a comprehensive analysis of the friction and wear behavior of nano-aluminium metal composites using machine learning through linear regression algorithm. The results obtained in this study can be used to design and optimize the production process of nano-aluminium metal composites for specific applications, leading to improved performance and longer life of the materials.