期刊
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
卷 527, 期 23, 页码 6193-6199出版社
ELSEVIER SCIENCE SA
DOI: 10.1016/j.msea.2010.06.059
关键词
Ti-17 titanium alloy; Dynamic globularization; Artificial neural network; Finite element method
类别
资金
- State Key Foundational Research Plan [2007CB613807]
- Program for New Century Excellent Talents in University [NCET-07-0696]
Isothermal compression experiments were conducted on Ti-17 titanium alloy with initial lamellar microstructure. The fractions of dynamic globularization of the microstructure under various conditions of strain, strain rate and temperature were obtained by quantitative metallographic analysis. On the basis of these data, the prediction model for describing the non-linear relationship between the dynamic globularization fraction and the deformation strain, strain rate and temperature of Ti-17 alloy was developed with a back-propagation artificial neural network (ANN) method. This model was incorporated into rigid-viscoplastic thermo-coupled finite element method (FEM). The large-size cylinder compression of Ti-17 alloy was simulated and corresponding experimental research was performed, to verify the reliability and accuracy of the integration of FEM and ANN model. The well coincidence of the predicted results with measured ones showed that the model was able to reasonably predict the fractions of dynamic globularization of Ti-17 alloy with initial lamellar microstructure during hot deformation procedure. (C) 2010 Elsevier B.V. All rights reserved.
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