Modeling capability of the artificial neural network (ANN) to predict the effect of the hot deformation parameters on the strength of Al-base metal matrix composites

Abstract The aim of this paper is to investigate the capability of the artificial neural network (ANN) to predict the effect of the hot deformation parameters on the strength of Al-base Metal Matrix Composites by comparing the results of the ANN predictions to the results of predictions by the RBF approach in our previous work. The experimental results of the hot deformation of 12 vol.% Al 2 O 3 Aluminum matrix composites under a range of temperatures and a range of strain rates were used in this investigation to be able to recognize the powerfulness of ANN against the RBF approach. The results showed that the filtrated ANN approach gives better results than RBF approach.