USING OF ARTIFICIAL NEURAL NETWORKS FOR MODELLING WEAR BEHAVIOUR OF AGED 2024 and 6063 ALUMINIUM ALLOY

Abstract

This paper reports on the effectiveness of a back-propagation artificial neural network model that predicts the wear loss of 2024 and 6063 Al Alloy samples which have been aged different temperatures (140°C, 180 °C, 220 °C) and different aging time. 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 ANNs can be employed for optimizing the process parameters of aluminum alloys. Predicted values from the model and experimental values are in close agreement and this indicates the usefulness of applying ANNs in predicting wear loss results