Research of Self-learning of Johnson-Cook Models Parameters based on Genetic Algorithm

摘要

The Johnson-Cook models parameters of deformation resistance determine the prediction accuracy of rolling force during hot rolling. According to the influencing factors analysis of rolling force calculation error, the genetic algorithm was introduced into the self-learning method of Johnson-Cook models parameters, and searches the models optimal value on the basic of space exploration and optimization ability of genetic algorithm. The decision variable selection, the coding and decoding, the fitness evaluation and the terminal conditions process were implemented during development process of self-learning system. The results show that the optimization accuracy and speed can meet industrial production requirement.