Fourier neural operator for large eddy simulation of compressible Rayleigh-Taylor turbulence

Luo, Tengfei1,2,3; Li, Zhijie1,2,3; Yuan, Zelong4; Peng, Wenhui5; Liu, Tianyuan6; Wang, Liangzhu (Leon)7; Wang, Jianchun1,2,3

2024-07-01

10.1063/5.0213412

PHYSICS OF FLUIDS   影响因子和分区

1070-6631

1089-7666

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 A(t) = 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.

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of China10.13039/501100001809["12172161","92052301","12161141017","91952104"] ; National Natural Science Foundation of China[11988102] ; NSFC Basic Science Center Program[KQTD20180411143441009] ; Shenzhen Science and Technology Program[GML2019ZD0103] ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)["2019B21203001","2020B1212030001","2023B1212060001"]

Mechanics ; Physics

Mechanics ; Physics, Fluids & Plasmas

WOS:001281820900012

AIP Publishing

20243016751380

Computational efficiency ; Forecasting ; Reynolds number ; Turbulence

Fluid Flow:631 ; Fluid Flow, General:631.1 ; Mathematics:921

PHYSICS

Web of Science

1.Southern Univ Sci & Technol, Dept Mech & Aerosp Engn, Shenzhen 518055, Peoples R China
2.Southern Univ Sci & Technol, Guangdong Hong Kong Macao Joint Lab Data Driven F, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Dept Mech & Aerosp Engn, Guangdong Prov Key Lab Turbulence Res & Applicat, Shenzhen 518055, Peoples R China
4.Harbin Engn Univ, Qingdao Innovat & Dev Base, Qingdao 266000, Peoples R China
5.Hong Kong Polytech Univ, Dept Appl Math, Hong Kong 999077, Peoples R China
6.Peking Univ, Coll Engn, Beijing 100091, Peoples R China
7.Concordia Univ, Ctr Zero Energy Bldg Studies, Dept Bldg Civil & Environm Engn, Montreal, PQ H3G 1M8, Canada

Luo, Tengfei,Li, Zhijie,Yuan, Zelong,et al. Fourier neural operator for large eddy simulation of compressible Rayleigh-Taylor turbulence[J]. PHYSICS OF FLUIDS,2024,36(7).

Luo, Tengfei.,Li, Zhijie.,Yuan, Zelong.,Peng, Wenhui.,Liu, Tianyuan.,...&Wang, Jianchun.(2024).Fourier neural operator for large eddy simulation of compressible Rayleigh-Taylor turbulence.PHYSICS OF FLUIDS,36(7).

Luo, Tengfei,et al."Fourier neural operator for large eddy simulation of compressible Rayleigh-Taylor turbulence".PHYSICS OF FLUIDS 36.7(2024).