Investigation and Optimization of the Tribological Parameters of Hypoeutectic A356/Gr/Sn Metal Matrix Composites Using Grey-Fuzzy and ANN Modeling Methods

The present work deals with the influence of the graphite and tin particles in the wear behavior of A356 alloy-based composites. The A356 alloy consists of 92% aluminum and 7% silicon. The A356/Gr/Sn composites were fabricated with the proportion of 10 wt.% Gr and varying wt.% of Sn (0, 5, and 10 wt.%) particles through the bottom pouring stir casting route. The inclusion of Sn with Gr in A356 alloy matrix took significant improvement in the wear characteristics of the composites. Process parameters such as wt.% of tin, normal load, and sliding speed have been considered for performing the wear test. The Box–Behnken design in response surface methodology was chosen for conducting the wear study because of its ability to efficiently explore the response surface with fewer experiments, ensuring statistical rigor in optimizing multiple variables within a balanced experimental domain. Grey relational analysis (GRA) has been used to optimize the wear study parameters. Grey-fuzzy reasoning grade analysis was used to check the uncertainty in the GRA results. The study used main effect plots to analyze the GFRG values for the various input variables. An artificial neural network model was created to create the relationship model between the input conditions and output responses. Scanning electron microscope micrographs were used to test the worn samples’ surfaces.