Prediction of Effect of Reinforcement Size and Volume Fraction on the Abrasive Wear Behavior of AA2014/B4Cp MMCs Using Artificial Neural Network

Abstract

In this study, an artificial neural network (ANN) approach was used to predict the abrasive wear behavior of AA2014 aluminum alloy matrix composites reinforced with B4C particles. The abrasive wear properties of varying volume fraction of particles up to 12 % B4C particle reinforced AA2014MMCS produced by stir casting method were investigated using a block-on-disc wear tester. Wear tests were performed under 92 N against the abrasive suspension mixture with a novel three body abrasive. For wear behavior, the volume loss, specific wear rate and surface roughness of the composites were measured. The effect of sliding time and content of B4C particles on the abrasive wear behavior were analyzed in detail. As a result of this study, the ANN was found to be successful for predicting the volume loss, specific wear rate and surface roughness of AA2014/B4C composites. The mean absolute percentage error (MAPE) for the predicted values did not exceed 4.1 %. The results have shown that ANN is an effective technique in the prediction of the properties of MMCs, and quite useful instead of time-consuming experimental processes.