文献类型：期刊文献

英文题名：A novel prediction method of creep rupture life of 9-12% chromium ferritic steel based on abductive network

作者：Wang, Ning[1];Tu, Shan-Tung[1];Xuan, Fu-Zhen[1]

机构：[1]E China Univ Sci & Technol, Key Lab Pressure Syst & Safety, Minist Educ, Shanghai 200237, Peoples R China

年份：2013

卷号：31

起止页码：302

外文期刊名：ENGINEERING FAILURE ANALYSIS

收录：;EI(收录号：20131316150813);WOS:【SCI-EXPANDED(收录号:WOS:000318532600030)】；

基金：The authors would like to thank their colleagues who contributed to the research mentioned in the paper. The support provided by China National High-tech Research and Development Program (863 Program No. 2009AA044803) is also gratefully acknowledged.

语种：英文

外文关键词：Creep; Creep rupture; Life prediction

摘要：The creep rupture life of 9-12% chromium ferritic steel is predicted as a function of alloy composition, creep stress, and creep temperature. A database is made up from data in previous publications. A novel abductive network is constructed to predict creep rupture life. With a four-layer architecture, the network shows a precise prediction of creep rupture life of 9-12% chromium ferritic steel. Performance is examined and compared with backpropagation algorithm (BP) neural network. Results indicate that the proposed approach is more accurate than Larson-Miller parametric method and more efficient than that of BP neural network. Automatic relevance determination reveals that the influence of Cr and W on creep rupture life of 9-12% chromium ferritic steel are the greatest amongst the alloying elements. (C) 2013 Elsevier Ltd. All rights reserved.