Characterization of Al/SiC nanocomposite prepared by mechanical alloying process using artificial neural network model

An artificial neural network model was developed for modeling of the effects of mechanical alloying process parameters including milling time, milling speed, and ball-to-powder weight ratio on the crystallite size and lattice strain of the aluminum for Al/SiC nanocomposite powders. A Multilayer Perceptron (MLP) and Radial Basis Function (RBF) networks were used. It was found that MLP network yields better results compared to RBF network with a high correlation coefficients. The neural network model in agreement with other experimental results and theories was shown the variations of the crystallite size and lattice strain of the aluminum against the process parameters.