Utilization of Improved Machine Learning Method Based on Artificial Hummingbird Algorithm to Predict the Tribological Behavior of Cu-Al2O3 Nanocomposites Synthesized by In Situ Method

This paper presents a machine learning model to predict the effect of Al2O3 nanoparticles content on the wear rates in Cu-Al2O3 nanocomposite prepared using in situ chemical technique. The model developed is a modification of the random vector functional link (RVFL) algorithm using artificial hummingbird algorithm (AHA). The objective of using AHA is used to find the optimal configuration of RVFL to enhance the prediction of Al2O3 nanoparticles. The preparation of the composite was done using aluminum nitrate that was added to a solution containing scattered copper nitrate. After that, the powders of CuO and Al2O3 were obtained, and the leftover liquid was removed using a thermal treatment at 850 degrees C for 1 h. The powders were consolidated using compaction and sintering processes. The microhardness of the nanocomposite with 12.5% Al2O3 content is 2.03-fold times larger than the pure copper, while the wear rate of the same composite is reduced, reaching 55% lower than pure copper. These improved properties are attributed to the presence of Al2O3 nanoparticles and their homogenized distributions inside the matrix. The developed RVFl-AHA model was able to predict the wear rates of all the prepared composites at different wear load and speed, with very good accuracy, reaching nearly 100% and 99.5% using training and testing, respectively, in terms of coefficient of determination R-2.

Automated summary

This paper presents a machine learning model using the artificial hummingbird algorithm to predict the effect of Al2O3 nanoparticles content on the wear rates in Cu-Al2O3 nanocomposite. The experimental results show that the addition of Al2O3 nanoparticles can improve the microhardness of the composite and reduce its wear rate. The developed model is able to accurately predict the wear rates under different wear conditions.