Prediction of tribological behavior of aluminum-copper based composite using artificial neural network

The potential of using neural network in prediction of wear loss quantities of some aluminum-copper-silicon carbide composite materials has been studied in the present work. Effects of addition of copper as alloying element and silicon carbide as reinforcement particles to Al-4 wt.%Mg metal matrix have been investigated. Different Al-Cu alloys and composites were subjected to dry sliding wear test using pin-on-disk apparatus under 40 N normal load with rotational speed of counter face disk of 150 rpm at room conditions (∼20 °C and ∼50% relative humidity). The experimental results were firstly coded prior to training in a feed forward back propagation artificial neural network (ANN) and the results were compared with experimental results. The average value of absolute relative error of un-coded values reaches 2.40%.