Real-time identification of material parameters for quadrangle parts intelligent bending

Real-time identification of material parameters is one of the most important elements in the process of intelligent bending control for quadrangle parts, the duration of real-time identification and the level of generalization accuracy would directly affect the realization of intelligent control. The scheme of control system of quadrangle parts intelligent bending has been advanced in this paper by using numerical simulation, database and neural network technology synthetically in order to control the springback of sheet metal effectively, and the real-time identification of material parameters as key technology was also researched. The feed forward neural network of real-time identification for material performance parameters and friction coefficient of quadrangle parts was established, which could real-time identify the needed material performance parameters through the real-time monitoring variable, and predict the optimal process parameters, which has achieved the satisfactory convergence precision. The experiment results of quadrangle parts intelligent bending show that the network model has a higher recognition and generalization accuracy, which could satisfy the requirements of intelligent control.