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

doi:10.1007/s11431-021-2068-8

CORC > 力学研究所 > 中国科学院力学研究所 > 非线性力学国家重点实验室

	A computational method for the load spectra of large-scale structures with a data-driven learning algorithm
	Chen, XianJia 3; Yuan, Zheng 2; Li, Qiang 2; Sun, ShouGuang 2; Wei, YuJie 1,3
刊名	SCIENCE CHINA-TECHNOLOGICAL SCIENCES
	2022-12-26
页码	14
关键词	load spectrum computational mechanics deep learning data-driven modeling gated recurrent unit neural network
ISSN号	1674-7321
DOI	10.1007/s11431-021-2068-8
通讯作者	Wei, YuJie(yujie_wei@lnm.imech.ac.cn)
英文摘要	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 long-term 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.
资助项目	Basic Science Center of the National Natural Science Foundation of China for Multiscale Problems in Non-linear Mechanics[11988102] ; National Key Research and Development Program of China[2017YFB0202800] ; National Key Research and Development Program of China[2016YFB1200602] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB22020200] ; Science Challenge Project[TZ2018002]
WOS关键词	NEURAL-NETWORKS ; DEEP ; ESTABLISHMENT ; PREDICTION
WOS研究方向	Engineering ; Materials Science
语种	英语
WOS记录号	WOS:000907092900007
资助机构	Basic Science Center of the National Natural Science Foundation of China for Multiscale Problems in Non-linear Mechanics ; National Key Research and Development Program of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Science Challenge Project
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/91436]
专题	力学研究所_非线性力学国家重点实验室
通讯作者	Wei, YuJie
作者单位	1.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China 2.Beijing Jiaotong Univ, Sch Mech Elect & Control Engn, Beijing 100044, Peoples R China 3.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Chen, XianJia,Yuan, Zheng,Li, Qiang,et al. A computational method for the load spectra of large-scale structures with a data-driven learning algorithm[J]. SCIENCE CHINA-TECHNOLOGICAL SCIENCES,2022:14.
APA	Chen, XianJia,Yuan, Zheng,Li, Qiang,Sun, ShouGuang,&Wei, YuJie.(2022).A computational method for the load spectra of large-scale structures with a data-driven learning algorithm.SCIENCE CHINA-TECHNOLOGICAL SCIENCES,14.
MLA	Chen, XianJia,et al."A computational method for the load spectra of large-scale structures with a data-driven learning algorithm".SCIENCE CHINA-TECHNOLOGICAL SCIENCES (2022):14.