A computational method for the load spectra of large-scale structures with a data-driven learning algorithm

作     者：CHEN XianJia YUAN Zheng LI Qiang SUN ShouGuang WEI YuJie 

作者机构：The State Key Laboratory of Nonlinear MechanicsInstitute of MechanicsChinese Academy of SciencesBejing 100190China School of MechanicalElectronic and Control EngineeringBeijing Jiaotong UniversityBejing 100044China School of Enginering SciencesUniversity of Chinese Academy of SciencesBeijing 100049China 

出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)

年 卷 期：2023年第66卷第1期

页      面：141-154页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 

基　　金：supported by the Basic Science Center of the National Natural Science Foundation of China for “Multiscale Problems in Nonlinear Mechanics”(Grant No. 11988102) the National Key Research and Development Program of China (Grant Nos. 2017YFB0202800 and2016YFB1200602) the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No. XDB22020200) the Science Challenge Project (Grant No. TZ2018002) 

主　　题：load spectrum computational mechanics deep learning data-driven modeling gated recurrent unit neural network 

摘      要：For complex engineering systems, such as trains, planes, and offshore oil platforms, load spectra are cornerstone of their safety designs and fault diagnoses. We demonstrate in this study that well-orchestrated machine learning modeling, in combination with limited experimental data, can effectively reproduce the high-fidelity, history-dependent load spectra in critical sites of complex engineering systems, such as high-speed trains. To meet the need for in-service monitoring, we propose a segmentation and randomization strategy for long-duration historical data processing to improve the accuracy of our data-driven model for longterm load-time history prediction. Results showed the existence of an optimal length of subsequence, which is associated with the characteristic dissipation time of the dynamic system. Moreover, the data-driven model exhibits an excellent generalization capability to accurately predict the load spectra for different levels of passenger-dedicated lines. In brief, we pave the way, from data preprocessing, hyperparameter selection, to learning strategy, on how to capture the nonlinear responses of such a dynamic system, which may then provide a unifying framework that could enable the synergy of computation and in-field experiments to save orders of magnitude of expenses for the load spectrum monitoring of complex engineering structures in service and prevent catastrophic fatigue and fracture in those solids.