| Ensemble variational method with adaptive covariance inflation for learning neural network-based turbulence models | |
Luo QY(罗清勇)1,2; Zhang XL(张鑫磊)1,2; He GW(何国威)1,2
| |
| Corresponding Author | Zhang, Xin-Lei([email protected]) ; He, Guowei([email protected]) |
| Source Publication | PHYSICS OF FLUIDS
 |
| 2024-03-01 | |
| Volume | 36Issue:3Pages:21 |
| ISSN | 1070-6631 |
| Abstract | This work introduces an ensemble variational method with adaptive covariance inflation for learning nonlinear eddy viscosity turbulence models where the Reynolds stress anisotropy is represented with tensor-basis neural networks. The ensemble-based method has emerged as an important alternative to data-driven turbulence modeling due to its merit of non-derivativeness. However, the training accuracy of the ensemble method can be affected by the linearization assumption and sample collapse issue. Given these difficulties, we introduce the hybrid ensemble variational method, which inherits the merits of the ensemble method in non-derivativeness and the variational method in nonlinear analysis. Moreover, a covariance inflation scheme is proposed based on convergence states to alleviate the detrimental effects of sample collapse. The capability of the ensemble variational method in model learning is tested for flows in a square duct, flows over periodic hills, and flows around the S809 airfoil, with increasing complexity in the training data from direct observation to sparse indirect observation. Our results show that the ensemble variational method can learn relatively accurate neural network-based turbulence models in scenarios of small ensemble size and sample variances, compared to the ensemble Kalman method. It highlights the superiority of the ensemble variational method in practical applications, since small ensemble sizes can reduce computational costs, and small sample variance can ensure the training robustness by avoiding nonphysical samples of Reynolds stresses. |
| DOI | 10.1063/5.0199175 |
| Indexed By | SCI ; EI |
| Language | 英语 |
| WOS ID | WOS:001190437000014 |
| WOS Keyword | IMPLEMENTATION ; OPTIMIZATION ; SCHEME ; FLOWS |
| WOS Research Area | Mechanics ; Physics |
| WOS Subject | Mechanics ; Physics, Fluids & Plasmas |
| Funding Project | National Natural Science Foundation of China10.13039/501100001809[11988102] ; NSFC Basic Science Center Program[12102435] ; National Natural Science Foundation of China[2021M690154] ; China Postdoctoral Science Foundation[2022QNRC001] ; Young Elite Scientists Sponsorship Program by CAST |
| Funding Organization | National Natural Science Foundation of China10.13039/501100001809 ; NSFC Basic Science Center Program ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; Young Elite Scientists Sponsorship Program by CAST |
| Classification | 一类/力学重要期刊 |
| Ranking | 1 |
| Contributor | Zhang, Xin-Lei ; He, Guowei |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://dspace.imech.ac.cn/handle/311007/94894 |
| Collection | 非线性力学国家重点实验室 |
| Affiliation | 1.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China; 2.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China |
| Recommended Citation GB/T 7714 | Luo QY,Zhang XL,He GW. Ensemble variational method with adaptive covariance inflation for learning neural network-based turbulence models[J]. PHYSICS OF FLUIDS,2024,36,3,:21.Rp_Au:Zhang, Xin-Lei, He, Guowei |
| APA | 罗清勇,张鑫磊,&何国威.(2024).Ensemble variational method with adaptive covariance inflation for learning neural network-based turbulence models.PHYSICS OF FLUIDS,36(3),21. |
| MLA | 罗清勇,et al."Ensemble variational method with adaptive covariance inflation for learning neural network-based turbulence models".PHYSICS OF FLUIDS 36.3(2024):21. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment