Fourier neural operator for large eddy simulation of compressible Rayleigh–Taylor turbulence
- 1 July 2024
- journal article
- research article
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (7)
Abstract
The Fourier neural operator (FNO) framework is applied to the large eddy simulation (LES) of three-dimensional compressible Rayleigh–Taylor turbulence with miscible fluids at Atwood number At=0.5, stratification parameter Sr = 1.0, and Reynolds numbers Re = 10 000 and 30 000. The FNO model is first used for predicting three-dimensional compressible turbulence. The different magnitudes of physical fields are normalized using root mean square values for an easier training of FNO models. In the a posteriori tests, the FNO model outperforms the velocity gradient model, the dynamic Smagorinsky model, and implicit large eddy simulation in predicting various statistical quantities and instantaneous structures, and is particularly superior to traditional LES methods in predicting temperature fields and velocity divergence. Moreover, the computational efficiency of the FNO model is much higher than that of traditional LES methods. FNO models trained with short-time, low Reynolds number data exhibit a good generalization performance on longer-time predictions and higher Reynolds numbers in the a posteriori tests.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (12172161)
- National Natural Science Foundation of China (92052301)
- National Natural Science Foundation of China (12161141017)
- National Natural Science Foundation of China (91952104)
- NSFC Basic Science Center Program (11988102)
- Shenzhen Science and Technology Program (KQTD20180411143441009)
- Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (GML2019ZD0103)
- Department of Science and Technology of Guangdong Province (2019B21203001)
- Department of Science and Technology of Guangdong Province (2020B1212030001)
- Department of Science and Technology of Guangdong Province (2023B1212060001)
- Center for Computational Science and Engineering of Southern University of Science and Technology
- National Center for Applied Mathematics Shenzhen
This publication has 106 references indexed in Scilit:
- Fourier neural operator for real-time simulation of 3D dynamic urban microclimateBuilding and Environment, 2023
- Temporal predictions of periodic flows using a mesh transformation and deep learning-based strategyAerospace Science and Technology, 2022
- Data-driven nonlinear K-L turbulent mixing model via gene expression programming methodActa Mechanica Sinica, 2022
- Learning deep Implicit Fourier Neural Operators (IFNOs) with applications to heterogeneous material modelingComputer Methods in Applied Mechanics and Engineering, 2022
- U-FNO—An enhanced Fourier neural operator-based deep-learning model for multiphase flowAdvances in Water Resources, 2022
- Physics-informed neural networks (PINNs) for fluid mechanics: a reviewActa Mechanica Sinica, 2021
- Subgrid-Scale Models for Compressible Large-Eddy SimulationsTheoretical and Computational Fluid Dynamics, 2000
- Accurate computation of convective transport in transient two‐phase flowInternational Journal for Numerical Methods in Fluids, 1995
- Compact finite difference schemes with spectral-like resolutionJournal of Computational Physics, 1992
- Efficient implementation of essentially non-oscillatory shock-capturing schemesJournal of Computational Physics, 1988