Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence
The subgrid-scale (SGS) stress and SGS heat flux are modeled by using an artificial neural network (ANN) for large eddy simulation (LES) of compressible turbulence. The input features of ANN model are based on the first-order and second-order derivatives of filtered velocity and temperature at diffe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-01-01
|
| Series: | Theoretical and Applied Mechanics Letters |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095034920300064 |
| _version_ | 1818308040657469440 |
|---|---|
| author | Chenyue Xie Jianchun Wang Hui Li Minping Wan Shiyi Chen |
| author_facet | Chenyue Xie Jianchun Wang Hui Li Minping Wan Shiyi Chen |
| author_sort | Chenyue Xie |
| collection | DOAJ |
| description | The subgrid-scale (SGS) stress and SGS heat flux are modeled by using an artificial neural network (ANN) for large eddy simulation (LES) of compressible turbulence. The input features of ANN model are based on the first-order and second-order derivatives of filtered velocity and temperature at different spatial locations. The proposed spatial artificial neural network (SANN) model gives much larger correlation coefficients and much smaller relative errors than the gradient model in an a priori analysis. In an a posteriori analysis, the SANN model performs better than the dynamic mixed model (DMM) in the prediction of spectra and statistical properties of velocity and temperature, and the instantaneous flow structures. Keywords: Compressible turbulence, Large eddy simulation, Artificial neural network |
| first_indexed | 2024-12-13T07:07:57Z |
| format | Article |
| id | doaj.art-7d02540f2389422d9ccde7c38488b9a7 |
| institution | Directory Open Access Journal |
| issn | 2095-0349 |
| language | English |
| last_indexed | 2024-12-13T07:07:57Z |
| publishDate | 2020-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Theoretical and Applied Mechanics Letters |
| spelling | doaj.art-7d02540f2389422d9ccde7c38488b9a72022-12-21T23:55:45ZengElsevierTheoretical and Applied Mechanics Letters2095-03492020-01-011012732Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulenceChenyue Xie0Jianchun Wang1Hui Li2Minping Wan3Shiyi Chen4Shenzhen Key Laboratory of Complex Aerospace Flows, Center for Complex Flows and Soft Matter Research, Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, China; School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaShenzhen Key Laboratory of Complex Aerospace Flows, Center for Complex Flows and Soft Matter Research, Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, China; Corresponding authorSchool of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaShenzhen Key Laboratory of Complex Aerospace Flows, Center for Complex Flows and Soft Matter Research, Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, ChinaShenzhen Key Laboratory of Complex Aerospace Flows, Center for Complex Flows and Soft Matter Research, Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, China; State Key Laboratory of Turbulence and Complex Systems, Peking University, Beijing 100871, ChinaThe subgrid-scale (SGS) stress and SGS heat flux are modeled by using an artificial neural network (ANN) for large eddy simulation (LES) of compressible turbulence. The input features of ANN model are based on the first-order and second-order derivatives of filtered velocity and temperature at different spatial locations. The proposed spatial artificial neural network (SANN) model gives much larger correlation coefficients and much smaller relative errors than the gradient model in an a priori analysis. In an a posteriori analysis, the SANN model performs better than the dynamic mixed model (DMM) in the prediction of spectra and statistical properties of velocity and temperature, and the instantaneous flow structures. Keywords: Compressible turbulence, Large eddy simulation, Artificial neural networkhttp://www.sciencedirect.com/science/article/pii/S2095034920300064 |
| spellingShingle | Chenyue Xie Jianchun Wang Hui Li Minping Wan Shiyi Chen Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence Theoretical and Applied Mechanics Letters |
| title | Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence |
| title_full | Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence |
| title_fullStr | Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence |
| title_full_unstemmed | Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence |
| title_short | Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulence |
| title_sort | spatial artificial neural network model for subgrid scale stress and heat flux of compressible turbulence |
| url | http://www.sciencedirect.com/science/article/pii/S2095034920300064 |
| work_keys_str_mv | AT chenyuexie spatialartificialneuralnetworkmodelforsubgridscalestressandheatfluxofcompressibleturbulence AT jianchunwang spatialartificialneuralnetworkmodelforsubgridscalestressandheatfluxofcompressibleturbulence AT huili spatialartificialneuralnetworkmodelforsubgridscalestressandheatfluxofcompressibleturbulence AT minpingwan spatialartificialneuralnetworkmodelforsubgridscalestressandheatfluxofcompressibleturbulence AT shiyichen spatialartificialneuralnetworkmodelforsubgridscalestressandheatfluxofcompressibleturbulence |