Prediction of Wear Behavior of Epoxy-MWCNTS Nanocomposites Using Artificial Neural Networks

Abstract

The potential of using Artificial Neural Networks (ANN) for predicting the dry sliding wear behavior of Multiwall Carbon Nanotubes (MWCNTs) reinforced epoxy material was investigated in this work.  The effects of reinforcement content 0.1%, 0.5%, 1.25%, 2.5% and 5% weight fraction of MWCNTs nanocomposites wear properties were determined by the pin on disc machine. A polymer nanocomposite was investigated using a measured datasets of 80 independent dry sliding tests of pure epoxy and epoxy-MWCNTs.  It was tested under various testing conditions of applied loads of 30N and 60N, sliding speed and time is 200rpm and 30min respectively. Based on measured datasets of epoxy-MWCNTs nanocomposites, specific wear rate was successfully calculated through well trained artificial neural network. Feed forward back propagation neural network (FFBN), radial basis neural network (RBNN), pattern recognition neural network (PRNN) and general regression neural network (GRNN) algorithm models were investigated in order to predict the optimum method that simulates the wear under such parameters.  The experimental results were trained in an ANN and the results were compared with experimental values. The GRNN network demonstrated that the average value of relative error is <1% and prediction quality 99% and it is quite suitable tool for prediction of wear in composites.
Copyright © 2013 Praise Worthy Prize - All rights reserved.