Investigation of wear behaviour of magnesium reinforced with boron nitride nanocomposite using ANN

Abstract

The present study aims to study the wear behaviour of Mg reinforced with boron nitride nanocomposite. The dry sliding wear behaviour of Mg reinforced with boron nitride (0.5 wt.%) is reviewed by following ASTM standards G99, i.e., dry sliding on pin-on-disk wear test apparatus. Three wear parameters, namely load, sliding speed, and sliding distance, were considered in this study. The experiments for wear rate have been conducted as per ASTM standards G99. The wear rate obtained for Mg reinforced with boron nitride (0.5 wt.%) is predicted by the ANN toolbox of Matlab R2021a using the Levenberg-Marquardt (trainlm) algorithm, which trains the feed-forward neural network having 3-5-1 (three input neurons, five hidden neurons in the single hidden layer and one output neuron). Experimental data sets obtained from the pin-on-disk wear test have been utilized to develop ANN. The results concluded that the error for wear loss of Mg reinforced with boron nitride (0.5 wt.%) lies within 20%, with an average percentage error of 2.6% between experimental values and ANN predicted values.