Modeling the mechanical behavior of Al 7010/SiC nanocomposites using artificial neural networks

Abstract In this study, the wear properties of three different composite formulations (T1, T2, and T3), which are highly important for aeronautical applications, are examined. The structural approach from Taguchi (L27 experimental design) is employed. To analyze the critical performance parameters, cf, such as specific wear rate (SWR) and frictional force (Ff), the Taguchi Signal-to-noise ratio approach is used. The input variables compound, applied load, rotating Speed, and sliding distance reveal significant correlations between the observed results. The optimal parameter combination of 5% composition, 15 N applied force, 160 rpm rotating Speed, and 41 M Sliding distance Showed subtle interactions that enhanced the wear resistance of the composite materials. The application of ANN-based predictions in this Study achieved an impressive accuracy of 99.72% in correlating predicted results with actual testing outcomes. This achievement facilitates the swift refinement of composite materials to meet the demanding standards of aerospace applications. This research plays a significant role in improving wear analysis and prediction methods while also fostering the development of specialized composites that offer enhanced reliability, performance, and durability for aeronautical purposes.