基于代理模型的板料成形优化技术进展

综述了板料成形优化技术现状,针对优化中计算成本高的问题,提出了基于代理模型的优化技术,包括可立格模型、响应面模型、神经网络模型等。从实验设计、代理模型的建立,以及优化求解等方面进行了阐述。针对产品设计中因素的随机性和不确定性,为减小目标函数对设计变量的敏感性,将稳健设计理论应用于板料成形优化中,以提高产品的可靠性和稳健性。

Recent advances of sheet metal forming optimization based on meta modeling

The present status of sheet metal forming optimization is summarized in this paper. In order to reduce the time in optimization, the optimization methods based on meta modeling are used, including Kriging model, response surface method (RSM), neural network (NN), and so on. Design of experiment, formation of meta modeling and algorithm of optimization, etc, are described. Because of randomness and uncertainty of factors in the products, and the sensitivity of the objective to design variables, the robust design is applied to the sheet metal forming, so that the reliability and robustness of products can be improved.