Analysis and Prediction of Wear Characteristics of Sustainable Metal Matrix Composites Using Machine Learning with Decision Making Algorithm

The goal of this research was to analyse and predict the wear characteristics of sustainable metal matrix composites using machine learning with a decision-making algorithm. The study used Al 7072 alloy with nano-particle SiC as an alloying element, which was added in three different compositions (0.3 %, 0.6%, and 0.9
^%
) through stir casting. The experiment was based on the Taguchi L27 orthogonal array and an Artificial Neural Network (ANN) was utilised as a machine learning approach to predict the responses with 100% accuracy. The input parameters were composition (C), load (R), and rotation speed (S), while the responses were the Specific wear rate (Spr) and friction coefficient (Fc), which were optimised using the Taguchi combined optimisation technique. The results showed that the ANN approach was effective in predicting the wear characteristics of the sustainable metal matrix composites and the Taguchi combined optimisation technique improved the wear resistance and friction coefficient. This study provides a valuable contribution to the field of sustainable materials, as the findings can be used to improve the design and production of sustainable metal matrix composites with improved wear characteristics, which can lead to a reduction in energy consumption and environmental impact.