Abstract: A BP algorithmic model was established for the artificial neural network of the grain size of Al-alloy's solidification structure under the action of strong pulse electromagnetic field. The simulating results were in agreement with the experimental results. It was shown that this BP algorithmic model of artificial neural network could be used to control the parameters and predict the solidified grain size under the action of strong pulse electromagnetic field. It provides us with an easy and practical method and means for optimizing experimental design.

Key words: grain size of solidification structure, artificial neural network, BP arithmetic model