Deconvolutional artificial-neural-network framework for subfilter-scale models of compressible turbulence

Yuan, Zelong1,2; Wang, Yunpeng1,2; Xie, Chenyue1,2; Wang, Jianchun1,2

2022

10.1007/s10409-021-01150-7

ACTA MECHANICA SINICA   影响因子和分区

0567-7718

1614-3116

We establish a deconvolutional artificial-neural-network (D-ANN) approach in large-eddy simulation (LES) of compressible turbulent flow. Filtered variables in the neighboring locations are taken as the inputs of D-ANN to recover original (unfiltered) variables, including density, momentum and pressure. The scale-similarity form is adopted to reconstruct subfilter-scale (SFS) terms. The proposed D-ANN models can give better a priori predictions of the sub-filter stress and heat flux than the classical approximate-deconvolution method (ADM) and the velocity-gradient model (VGM). The predicted SFS terms with the D-ANN models have correlation coefficients larger than 98.4% and relative errors smaller than 18%. In the a posteriori analysis, the D-ANN model compares against the implicit LES (ILES), the dynamic-Smagorinsky model (DSM), and the dynamic-mixed model (DMM). The D-ANN model predicts better than these classical models for velocity spectra, statistical properties of SFS kinetic energy flux and velocity increments. The turbulence statistics and transient velocity divergence are also accurately reconstructed. The type of explicit filter and the impact of compressibility do not significantly affect a posteriori accuracy of the D-ANN model. Results show that the proposed D-ANN approach has a great potential in developing highly accurate SFS models for large-eddy simulation of complex compressible turbulent flow.

Subfilter-scale model Large-eddy simulation Artificial neural network Machine learning Compressible turbulence

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of China[91952104,92052301,91752201]

Engineering ; Mechanics

Engineering, Mechanical ; Mechanics

WOS:000745567800002

SPRINGER HEIDELBERG

20220511545319

Atmospheric thermodynamics ; Heat flux ; Kinetic energy ; Kinetics ; Large eddy simulation ; Machine learning ; Turbulence ; Turbulent flow ; Velocity

Atmospheric Properties:443.1 ; Fluid Flow:631 ; Fluid Flow, General:631.1 ; Thermodynamics:641.1 ; Heat Transfer:641.2 ; Mathematics:921 ; Classical Physics; Quantum Theory; Relativity:931

ENGINEERING

Web of Science

1.Southern Univ Sci & Technol, Dept Mech & Aerosp Engn, Guangdong Prov Key Lab Foundemental Turbulence Re, Ctr Complex Flows & Soft Matter Res, Shenzhen 518055, Peoples R China
2.Southern Univ Sci & Technol, Guangdong Hong Kong Macao Joint Lab Data Driven F, Shenzhen 518055, Peoples R China

Yuan, Zelong,Wang, Yunpeng,Xie, Chenyue,et al. Deconvolutional artificial-neural-network framework for subfilter-scale models of compressible turbulence[J]. ACTA MECHANICA SINICA,2022,37:1773-1785.

Yuan, Zelong,Wang, Yunpeng,Xie, Chenyue,&Wang, Jianchun.(2022).Deconvolutional artificial-neural-network framework for subfilter-scale models of compressible turbulence.ACTA MECHANICA SINICA,37,1773-1785.

Yuan, Zelong,et al."Deconvolutional artificial-neural-network framework for subfilter-scale models of compressible turbulence".ACTA MECHANICA SINICA 37(2022):1773-1785.