Creep Deformation Constitutive Model of BSTMUF601 Superalloy Using BP Neural Network Method

被引：0

作者：

Wang, Chunhui ^{[1
,2
]}

Sun, Zhihui ^{[1
,2
]}

Zhao, Jiaqing ^{[3
]}

Sun, Chaoyang ^{[1
,2
]}

Wang, Wenrui ^{[1
,2
]}

Zhang, Jiaming ^{[1
,2
]}

机构：

[1] School of Mechanical Engineering, University of Science and Technology Beijing, Beijing,100083, China

[2] Beijing Key Laboratory of Lightweight Metal Forming, Beijing,100083, China

[3] Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education, Tsinghua University, Beijing,100084, China

来源：

Xiyou Jinshu Cailiao Yu Gongcheng/Rare Metal Materials and Engineering | 2020年 / 49卷 / 06期

关键词：

Superalloys;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

A series of creep tests of BSTMUF601 superalloy were carried out at different loads and temperatures to investigate creep behaviors at actual service environment. The constitutive parameters of θ projection creep model were calibrated reversely by BP neural network method with back-propagation learning algorithm based on the collected stress and strain evaluated from a diameter correction method under constant load conditions. The results show that the predicted values coincide well with experimental results and the maximum relative error is 11.8% compared with 20.9% from multivariate nonlinear regression on the initial and stable creep stages. Both the apparent creep stress exponent estimated by θ model and the transmission electron microscope (TEM) images indicate the creep deformation mechanism may be dislocation climb, further indicating the BP neural network method can describe efficiently the non-linear and complex relationship of BSTMUF601 superalloy. Copyright © 2020, Northwest Institute for Nonferrous Metal Research. Published by Science Press. All rights reserved.

引用

页码：1885 / 1893