Effects of processing parameters on microstructure of semi-solid slurry prepared by mechanical stirring were investigated. The optimized model of processing parameters in mechanical stirring was established by means of artificial neural network in which the solid fraction and solid phase size of the semi-solid structure are taken as input parameters and stirring velocity

stirring time

holding time and pouring temperature as output parameters based on orthogonal testing to prepare desirable semi-solid slurry. The optimized results are well in agreement with experimental ones. Therefore

the artificial neural network model can be used to optimize the processing of the slurring-making during the semi-solid forming. In addition

the model can be used for different slurry-making with altering input parameters.