The use of artificial neural network for the prediction of wear loss of aluminium-magnesium alloys

Abstract

This paper reports on the effectiveness of a back–propagation artificial neural network model that predicts the wear loss of Al–Mg alloys samples. Artificial neural networks (ANNs) have the capacity to eliminate the need for expensive and difficult experimental investigation in testing and manufacturing processes. This paper shows that ANN can be employed for optimising the process parameters of aluminium alloys. The ANN predictions show very good agreement with experimental values with correlation coefficient of 0.823, thus ANN can be considered an excellent tool for modelling complex processes that have many variables.