Optimization of Tribological Parameters of Aluminum Alloy Nanocomposite Based on Response Surface Methodology and Artificial Neural Network Process

This study addressed the growing need for high-performance lightweight materials with reduced friction and wear behavior for automotive, aerospace, and structural components. This study uses an artificial neural network (ANN) and response surface methods to examine the friction and wear of A7075 aluminum alloy containing copper oxide (CuO) nanoparticles. The composites were prepared via liquid processing and with varying CuO nanoparticle concentrations. Wear of the pin was analyzed using a pin-on-disc tribometer to determine how nanoparticle concentration, load, and sliding speed affect tribological behavior. The analysis of variance showed that nanoparticle concentration affected both responses more than sliding speed. The average relative error between experimental results and ANN predictions was 0.72% for friction and 0.315% for wear. The response surface approach produced 13.71% friction and 1.38% wear. The friction and wear coefficients are well-fitted in the model.