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

作者：Wang, Ning^*; Tu, Shan-Tung; Xuan, Fu-Zhen

来源：Engineering Failure Analysis, 2013, 31: 302-310.

DOI：10.1016/j.engfailanal.2013.01.026

• Creep
• Creep rupture
• Life prediction

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.

• 出版日期2013-7
• 单位华东理工大学