Prediction of Wear Characteristics for Al-MnO2 Nanocomposites using Artificial Neural Network (ANN)

Abstract

An Artificial Neural Network (ANN) model was developed to investigate the impact of various ball milling parameters on the wear characteristics of Al-MnO2 nanocomposites. The process involved the synthesis of nano-sized particles through a high-energy planetary ball milling process, followed by the fabrication of nanocomposites using the stir casting method. The synthesized nanoparticles are characterized using X-Ray diffraction (XRD), and the nanocomposites are examined through scanning electron microscopy. To evaluate the wear behavior of the nanocomposites, a pin-on-disc test is conducted, generating a data set used for training the ANN model. The primary objective was to predict the wear rate of the synthesized Al-MnO2 nanocomposites using the ANN. Upon comparing the ANN's predictions with actual experimental results, it became evident that a well-trained ANN model proved to be a highly effective tool for estimating the wear rate of Al-MnO2 nanocomposites.