Enhanced random vector functional link based on artificial protozoa optimizer to predict wear characteristics of Cu-ZrO₂ nanocomposites

Owing to the absence of scientific methods for predicting nanocomposites' wear rates, a freshly updated machine learning method that uses an Artificial Protozoa Optimizer (APO) to forecast the tribological performance of Cu-ZrO₂ nanocomposites was proposed. The updated model was used to predict the coefficients of friction and wear rates of Cu-ZrO₂ nanocomposites produced in this work. Copper-zirconia nanocomposite powders were fabricated utilizing the ball milling process, varying in milling time and ZrO₂ weight percentage. The effect of reinforcement percentage and milling time on the morphology and microstructure of the copper composite powders was characterized. The study concentrated on the effects of high-energy ball milling on the morphology, microstructure, and microhardness of the resulting composites. After cold compaction at 700 MPa of pressure, the resultant powders were sintered for 2 h at 950 °C in a hydrogen atmosphere. Based on the results, a 20-h milling time is the best option for creating a Cu-ZrO₂ nanocomposite with evenly distributed reinforcement. The microhardness and wear rate of the Cu-15%ZrO₂ nanocomposites are improved by 66.2 %, and 81.1 %, respectively, when compared to pure copper. The crystallite size decreases significantly with the addition of ZrO₂, reaching 32.5 and 11.1 nm for samples containing 5 and 15 % weight percent ZrO₂. That is why there is a rise in wear and mechanical properties. For Cu-ZrO₂ nanocomposites with reinforcement content up to 15 %, the model constructed using the APO method demonstrated excellent forecasting of the wear rate and coefficient of friction.