Physical interpretation of neural network-based nonlinear eddy viscosity models

doi:10.1016/j.ast.2023.108632

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

	Physical interpretation of neural network-based nonlinear eddy viscosity models
	Zhang, Xin-Lei 3,4; Xiao, Heng 2; Jee, Solkeun 1; He, Guowei 3,4
刊名	AEROSPACE SCIENCE AND TECHNOLOGY
	2023-11-01
卷号	142 页码:13
关键词	Machine learning Turbulence modeling Ensemble Kalman inversion Physical interpretability
ISSN号	1270-9638
DOI	10.1016/j.ast.2023.108632
通讯作者	Jee, Solkeun(sjee@gist.ac.kr)
英文摘要	Neural network-based turbulence modeling has gained significant success in improving turbulence predictions by incorporating high fidelity data. However, the interpretability of the learned model is often not fully analyzed, which has been one of the main criticisms of neural network-based turbulence modeling. Therefore, it is increasingly demanding to provide physical interpretation of the trained model, which is of significant interest for guiding the development of interpretable and unified turbulence models. The present work aims to interpret the predictive improvement of turbulence flows based on the behavior of the learned model, represented with tensor basis neural networks. The ensemble Kalman method is used for model learning from sparse observation data due to its ease of implementation and high training efficiency. Two cases, i.e., flow over the S809 airfoil and flow in a square duct, are used to demonstrate the physical interpretation of the ensemble-based turbulence modeling. For the flow over the S809 airfoil, our results show that the ensemble Kalman method learns an optimal linear eddy viscosity model, which improves the prediction of the aerodynamic lift by reducing the eddy viscosity in the upstream boundary layer and promoting the early onset of flow separation. For the square duct case, the method provides a nonlinear eddy viscosity model, which predicts well secondary flows by capturing the imbalance of the Reynolds normal stresses. The flexibility of the ensemble-based method is highlighted to capture characteristics of the flow separation and secondary flow by adjusting the nonlinearity of the turbulence model.(c) 2023 Elsevier Masson SAS. All rights reserved.
资助项目	NSFC Basic Science Center Program for Multiscale Problems in Nonlinear Mechanics[11988102] ; National Natural Science Foundation of China[12102435] ; China Postdoctoral Science Foundation[2021M690154] ; National Research Foundation of Korea[NRF-2021H1D3A2A01096296]
WOS关键词	TURBULENCE ; FLOWS
WOS研究方向	Engineering
语种	英语
WOS记录号	WOS:001086005400001
资助机构	NSFC Basic Science Center Program for Multiscale Problems in Nonlinear Mechanics ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; National Research Foundation of Korea
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/93237]
专题	力学研究所_非线性力学国家重点实验室
通讯作者	Jee, Solkeun
作者单位	1.Gwangju Inst Sci & Technol, Sch Mech Engn, Gwangju 61005, South Korea 2.Univ Stuttgart, Stuttgart Ctr Simulat Sci SC SimTech, Stuttgart, Germany 3.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Xin-Lei,Xiao, Heng,Jee, Solkeun,et al. Physical interpretation of neural network-based nonlinear eddy viscosity models[J]. AEROSPACE SCIENCE AND TECHNOLOGY,2023,142:13.
APA	Zhang, Xin-Lei,Xiao, Heng,Jee, Solkeun,&He, Guowei.(2023).Physical interpretation of neural network-based nonlinear eddy viscosity models.AEROSPACE SCIENCE AND TECHNOLOGY,142,13.
MLA	Zhang, Xin-Lei,et al."Physical interpretation of neural network-based nonlinear eddy viscosity models".AEROSPACE SCIENCE AND TECHNOLOGY 142(2023):13.