Comparison of online identification methods of material parameters in press straightening process

More and more automatic pressure straighteners are used on the manufacturing industry because of their high productivity and good quality. When the technologic parameters are calculated, the precision of results will be influenced by the part´s material performance parameters. In this paper, three online identification methods of performance parameters were studied. They were BP neural network method, RBF neural network method and the support vector machine method. Then their identification effects were compared. It was shown that all three methods can be used to identify material performance parameters in straightening process. But later two methods have better identification precision and shorter response time than BP neural network method.