期刊
ENGINEERING FRACTURE MECHANICS
卷 257, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.engfracmech.2021.108027
关键词
AA6061 alloy; Thermal deformation behavior; Constitutive model; BP neural network; Genetic algorithm
类别
资金
- Natural Science Foundation of Hebei Province of China [E2018203254]
- Na-tional Natural Science Foundation of China [51705448]
A hybrid identification method based on BP neural network and GA is proposed to calibrate the parameters of a coupled viscoplastic-damage constitutive model, which shows higher accuracy compared to traditional inverse calibration methods.
The constitutive model based on the theoretical framework of coupled viscoplastic-damage involves calibration of multiple and high coupling parameters. The inverse calibration by genetic algorithm (GA) with global search ability has some challenges as the dependence on the selection of the initial population, massive computation, and convergence inconsistency. To obtain statistical knowledge from state data to avoid subjective experience, a hybrid identification method based on the BP neural network and GA is proposed. A coupled viscoplastic-damage constitutive model based on the thermal deformation and microstructure evolution is established. The parameters in the model are determined based on the hybrid identification method. Two types of aluminum alloy sheets are selected to test the generalization, and mean square errors (RMSE) are 2.46 and 4.89, respectively. The results indicate that this method has higher accuracy than the inverse calibration method based on single optimization algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据