文献类型：期刊文献

英文题名：Machine learning assisted probabilistic creep-fatigue damage assessment

作者：Gu, Hang-Hang[1];Wang, Run-Zi[1,2];Zhu, Shun-Peng[3];Wang, Xiao-Wei[4];Wang, Dong-Ming[1];Zhang, Guo-Dong[5];Fan, Zhi-Chao[6];Zhang, Xian-Cheng[1];Tu, Shan-Tung[1]

机构：[1]East China Univ Sci & Technol, Key Lab Pressure Syst & Safety, Minist Educ, Shanghai 200237, Peoples R China;[2]Tohoku Univ, Grad Sch Engn, Fracture & Reliabil Res Inst, Sendai, Miyagi 9808579, Japan;[3]Univ Elect Sci & Technol China, Sch Mech & Elect Engn, Chengdu 611731, Peoples R China;[4]Nanjing Tech Univ, Sch Mech & Power Engn, Nanjing 211816, Peoples R China;[5]Suzhou Nucl Power Res Inst, Suzhou 215004, Peoples R China;[6]Hefei Gen Machinery Res Inst Co Ltd, Hefei 230031, Peoples R China

年份：2022

卷号：156

外文期刊名：INTERNATIONAL JOURNAL OF FATIGUE

收录：;EI(收录号：20215011309642);WOS:【SCI-EXPANDED(收录号:WOS:000789651400002)】；

基金：This work was supported financially by the National Natural Science Foundation of China (Nos. 52005185, 51725503 and 11972110) , China Postdoctoral Science Foundation (2020M681200) and 111 Project. Wang RZ also gratefully acknowledges the support of the Postdoctoral Fellowships for Research in Japan (FY2020 P20350) by the Japan So-ciety for the Promotion of Science (JSPS) .

语种：英文

外文关键词：Creep-fatigue; Machine learning; Divide-and-conquer; Probabilistic damage assessment

摘要：In order to investigate the probabilistic damage distribution under creep-fatigue interaction, machine learning framework with the divide-and-conquer methodology is proposed to expand the creep-fatigue life sample size of each load condition. The optimized deterministic life prediction model, strain energy density exhaustion model (SEDE), is selected to take material variability into account. Subsequently, random accumulated creep and fa-tigue damage are obtained by the combination of probabilistic SEDE life model and creep-fatigue life distribu-tions through the Latin hypercube sampling (LHS) simulation. A relative scatter factor depicted in the creep-fatigue interaction diagram is introduced to reveal the dominance of scatter in creep/fatigue on life scatter. Consequently, a probabilistic creep-fatigue damage assessment diagram with involving probabilistic equipo-tential line for safety evaluations is established. Such probabilistic damage assessment may provide reference and has promising potential in the further creep-fatigue life design for reliability.