Prediction model of microstructure variable during semi-solid compression of Al-4Cu-Mg alloy

Microstructure characterization of the Al-4Cu-Mg alloys during the semi-solid compression has been investigated. A prediction model of microstructure evolution has been established based on the fuzzy-neural network. The present model uses deformation temperature, height reduction and strain rate as input parameters, and grain size or fractal dimension as output parameters. The results show that the prediction results are in excellent agreement with the experimental data. Therefore, the fuzzy-neural network model could be used to predict the microstructure evolution during the semi-solid forming of the Al-4Cu-Mg alloy and to optimize the deformation process parameters.