Artificial neural network based response surface for data-driven dimensional analysis
文献类型:期刊论文
作者 | Xu, Zhaoyue1,2; Zhang, Xinlei1,2; Wang, Shizhao1,2; He, Guowei1,2; He GW(何国威); Wang SZ(王士召) |
刊名 | JOURNAL OF COMPUTATIONAL PHYSICS |
出版日期 | 2022-06-15 |
卷号 | 459页码:19 |
ISSN号 | 0021-9991 |
关键词 | Artificial neural network Response surface Data-driven dimensional analysis Machine learning Fluid-structure interaction |
DOI | 10.1016/j.jcp.2022.111145 |
通讯作者 | Wang, Shizhao(wangsz@lnm.imech.ac.cn) |
英文摘要 | The classical dimensional analysis method has limitations in determining the uniqueness and relative importance of the dimensionless quantities. A machine-learning based dimensional analysis method is proposed to address the limitations. The proposed method identifies unique and relevant dimensionless quantities by combining an artificial neural network with the data-driven dimensional analysis. We employ a fully connected neural network to construct the ridge function for the response surface in a physical system. The gradient of the response surface for active subspace analysis is computed based on a finite difference approximation. An effective approach is proposed to determine the independent variables of experimental measurements or numerical simulations for computing the gradient of the response surface. The proposed method is validated by analyzing benchmark pipe flows and a fluid-structure interaction system. The dominant dimensionless quantities obtained by the proposed method are consistent with those reported in the literature. The proposed method has the advantage of identifying the relatively important dimensionless quantities without referring to the complex theoretical equations. (C)& nbsp;2022 Elsevier Inc. All rights reserved. |
WOS关键词 | METHODOLOGY ; DRAG |
资助项目 | NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics'[11988102] ; National Natural Science Foundation of China[11922214] ; National Natural Science Foundation of China[91752118] ; National Natural Science Foundation of China[91952301] |
WOS研究方向 | Computer Science ; Physics |
语种 | 英语 |
WOS记录号 | WOS:000793406800008 |
资助机构 | NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics' ; National Natural Science Foundation of China |
源URL | [http://dspace.imech.ac.cn/handle/311007/89552] |
专题 | 力学研究所_非线性力学国家重点实验室 |
通讯作者 | Wang, Shizhao |
作者单位 | 1.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Xu, Zhaoyue,Zhang, Xinlei,Wang, Shizhao,et al. Artificial neural network based response surface for data-driven dimensional analysis[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2022,459:19. |
APA | Xu, Zhaoyue,Zhang, Xinlei,Wang, Shizhao,He, Guowei,何国威,&王士召.(2022).Artificial neural network based response surface for data-driven dimensional analysis.JOURNAL OF COMPUTATIONAL PHYSICS,459,19. |
MLA | Xu, Zhaoyue,et al."Artificial neural network based response surface for data-driven dimensional analysis".JOURNAL OF COMPUTATIONAL PHYSICS 459(2022):19. |
入库方式: OAI收割
来源:力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。