| Physics-enhanced data-driven turbulence model for flow around submerged bodies | |
Zhang,Zhen1,2,3; Li,Haohan1; Ye SR(叶舒然)4; Wang JZ(王静竹)5; Wang YW(王一伟)5 ; Chu,Xuesen6,7,8; Liu,Qingkuan1,2,3
| |
| Corresponding Author | Wang, Jingzhu([email protected]) ; Chu, Xuesen([email protected]) |
| Source Publication | OCEAN ENGINEERING
 |
| 2025 | |
| Volume | 315Pages:13 |
| ISSN | 0029-8018 |
| Abstract | Data-driven turbulence modeling is regarded as an effective approach to enhance the predictive performance of Reynolds-Averaged Navier-Stokes (RANS) models. However, the stability and accuracy of such methods still require further improvement. Therefore, we propose a novel modified model based on a combined neural network. Within this framework, we construct a fully connected neural network to predict the eddy viscosity coefficient in the RANS equations, thereby achieving an implicit solution for the linear part of the Reynolds stress. Additionally, we introduce a tensor basis neural network to predict the higher-order eddy viscosity relationships between unclosed quantities and analytical quantities. Furthermore, the model incorporates pressure gradients and turbulent kinetic energy gradients as inputs, fully considering the influence of pressure gradients and strong non-equilibrium effects in turbulence, thereby enhancing the physical foundation of the model. To evaluate the performance of the constructed model in different-dimensional flow fields with higher Reynolds numbers, we conduct validation analyzes on a two-dimensional NACA0012 model and a threedimensional SUBOFF model without appendages. The results indicate that the modified model consistently outperforms the RANS model, particularly in predicting the velocity field near the leading edge of the NACA0012 hydrofoil. The predictions of the modified model are closer to those of large eddy simulation (LES) results. Specifically, the root mean square error (RMSE) of the interpolated and extrapolated modified models is reduced by 49.2% and 33.3%, respectively, compared to the RMSE of the RANS model. When applied to three-dimensional isolated SUBOFF flows, the modified model's predictions for the average velocity field and pressure coefficients at both ends of the SUBOFF are in high agreement with LES results, but the prediction accuracy in the middle section is slightly insufficient. Nevertheless, the prediction errors of the interpolated and extrapolated modified models are reduced by 69.5% and 63.6%, respectively, compared to the baseline RANS model, which fully demonstrates the high accuracy of the modified model in predicting the overall pressure distribution of the SUBOFF. The methods developed in this study provide valuable insights into high-precision intelligent modeling for two-dimensional and three-dimensional flows. |
| Keyword | Data-driven Physical enhancement Turbulence model Combined neural network |
| DOI | 10.1016/j.oceaneng.2024.119779 |
| Indexed By | SCI ; EI |
| Language | 英语 |
| WOS ID | WOS:001368027200001 |
| WOS Keyword | REYNOLDS STRESS ; SIMULATION |
| WOS Research Area | Engineering ; Oceanography |
| WOS Subject | Engineering, Marine ; Engineering, Civil ; Engineering, Ocean ; Oceanography |
| Funding Project | National Natural Science Foundation of China (NSFC)[12202291] ; National Natural Science Foundation of China (NSFC)[12302514] ; National Natural Science Foundation of China (NSFC)[12293003] ; National Natural Science Foundation of China (NSFC)[12122214] ; National Natural Science Foundation of China (NSFC)[12293000] ; National Natural Science Foundation of China (NSFC)[12293004] ; Science and Technology Project of Hebei Education Department[BJK2024177] ; Youth Innovation Promotion Association CAS[2022019] |
| Funding Organization | National Natural Science Foundation of China (NSFC) ; Science and Technology Project of Hebei Education Department ; Youth Innovation Promotion Association CAS |
| Classification | 一类 |
| Ranking | 1 |
| Contributor | Wang, Jingzhu ; Chu, Xuesen |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://dspace.imech.ac.cn/handle/311007/97616 |
| Collection | 流固耦合系统力学重点实验室 |
| Affiliation | 1.Shijiazhuang Tiedao Univ, Sch Civil Engn, Shijiazhuang 050043, Peoples R China; 2.Minist Educ, Key Lab Rd & Railway Engn Safety Control, Shijiazhuang 050043, Peoples R China; 3.Innovat Ctr Wind Engn & Wind Energy Technol Hebei, Shijiazhuang 050043, Peoples R China; 4.Chinese Acad Sci, Anhui Inst Opt & Fine Mech, Hefei Inst Phys Sci, Key Lab Atmospher Opt, Hefei 230031, Peoples R China; 5.Chinese Acad Sci, Key Lab Mech Fluid Solid Coupling Syst, Inst Mech, Beijing 100190, Peoples R China; 6.China Ship Sci Res Ctr, Wuxi 214082, Peoples R China; 7.Taihu Lake Lab Deep Sea Technol & Sci, Wuxi 214082, Peoples R China; 8.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China |
| Recommended Citation GB/T 7714 | Zhang,Zhen,Li,Haohan,Ye SR,et al. Physics-enhanced data-driven turbulence model for flow around submerged bodies[J]. OCEAN ENGINEERING,2025,315:13.Rp_Au:Wang, Jingzhu, Chu, Xuesen |
| APA | Zhang,Zhen.,Li,Haohan.,叶舒然.,王静竹.,王一伟.,...&Liu,Qingkuan.(2025).Physics-enhanced data-driven turbulence model for flow around submerged bodies.OCEAN ENGINEERING,315,13. |
| MLA | Zhang,Zhen,et al."Physics-enhanced data-driven turbulence model for flow around submerged bodies".OCEAN ENGINEERING 315(2025):13. |
| 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