Prediction of turbulent channel flow using Fourier neural operator-based machine-learning strategy
The implicit U-Net enhanced Fourier neural operator (IUFNO) combines the loop structure of implicit FNO (IFNO) with U-Net, leading to enhanced long-term predictive ability in the large-eddy simulations (LES) of turbulent channel flow. It is found that the IUFNO outperforms the traditional dynamic Smagorinsky model (DSM) and the wall-adapted local eddy-viscosity (WALE) model at coarse LES grids. The predictions of both the mean and fluctuating quantities by IUFNO are closer to the filtered direct numerical simulation (fDNS) benchmark compared to the traditional LES models, while the computational cost of IUFNO is much lower.
Authors
- Wenhui Peng (ORCID: https://orcid.org/0000-0001-8967-042X)
- Zelong Yuan (ORCID: https://orcid.org/0000-0003-0279-111X)
- Jianchun Wang (ORCID: https://orcid.org/0000-0001-5101-7791)
- Zhijie Li (ORCID: https://orcid.org/0000-0002-5885-5154)
- Yunpeng Wang (ORCID: https://orcid.org/0000-0002-9359-5327)
- Tianyuan Liu (ORCID: https://orcid.org/0000-0001-7367-8128)
Institutions
- Hong Kong Polytechnic University (HK)
- Harbin Engineering University (CN)
- Peking University (CN)
- Southern University of Science and Technology (CN)
Publication Details
- Journal
- Physical Review Fluids
- Published
- 2024-08-12
- DOI
- https://doi.org/10.1103/physrevfluids.9.084604
- Citations
- 29
- Primary Topic
- Fluid Dynamics and Turbulent Flows
- Type
- article
- Field-Weighted Citation Impact
- 10.87
Funders
- National Natural Science Foundation of China
- Guangdong Science and Technology Department
- Southern University of Science and Technology
- Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)