Modeling subgrid-scale forces by spatial artificial neural networks in large eddy simulation of turbulence

2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Chenyue Xie ◽  
Jianchun Wang ◽  
Weinan E
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Large Eddy Simulation ◽  
Subgrid Scale ◽  
Eddy Simulation ◽  
Large Eddy ◽  
Artificial Neural

scholarly journals Large eddy simulation of spray combustion using flamelet generated manifolds combined with artificial neural networks

Energy and AI ◽  
2020 ◽  
Vol 2 ◽  
pp. 100021 ◽  
Author(s):  
Yan Zhang ◽  
Shijie Xu ◽  
Shenghui Zhong ◽  
Xue-Song Bai ◽  
Hu Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Large Eddy Simulation ◽  
Spray Combustion ◽  
Eddy Simulation ◽  
Large Eddy ◽  
Artificial Neural

scholarly journals Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow

2021 ◽  
Vol 14 (6) ◽  
pp. 3769-3788
Author(s):  
Robin Stoffer ◽  
Caspar M. van Leeuwen ◽  
Damian Podareanu ◽  
Valeriu Codreanu ◽  
Menno A. Veerman ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Large Eddy Simulation ◽  
Finite Volume ◽  
Channel Flow ◽  
Turbulent Channel Flow ◽  
Spatial Discretization ◽  
Eddy Simulation ◽  
Large Eddy ◽  
Discretization Errors

Abstract. Atmospheric boundary layers and other wall-bounded flows are often simulated with the large-eddy simulation (LES) technique, which relies on subgrid-scale (SGS) models to parameterize the smallest scales. These SGS models often make strong simplifying assumptions. Also, they tend to interact with the discretization errors introduced by the popular LES approach where a staggered finite-volume grid acts as an implicit filter. We therefore developed an alternative LES SGS model based on artificial neural networks (ANNs) for the computational fluid dynamics MicroHH code (v2.0). We used a turbulent channel flow (with friction Reynolds number Reτ=590) as a test case. The developed SGS model has been designed to compensate for both the unresolved physics and instantaneous spatial discretization errors introduced by the staggered finite-volume grid. We trained the ANNs based on instantaneous flow fields from a direct numerical simulation (DNS) of the selected channel flow. In general, we found excellent agreement between the ANN-predicted SGS fluxes and the SGS fluxes derived from DNS for flow fields not used during training. In addition, we demonstrate that our ANN SGS model generalizes well towards other coarse horizontal resolutions, especially when these resolutions are located within the range of the training data. This shows that ANNs have potential to construct highly accurate SGS models that compensate for spatial discretization errors. We do highlight and discuss one important challenge still remaining before this potential can be successfully leveraged in actual LES simulations: we observed an artificial buildup of turbulence kinetic energy when we directly incorporated our ANN SGS model into a LES simulation of the selected channel flow, eventually resulting in numeric instability. We hypothesize that error accumulation and aliasing errors are both important contributors to the observed instability. We finally make several suggestions for future research that may alleviate the observed instability.

scholarly journals Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow

2020 ◽  
Author(s):  
Robin Stoffer ◽  
Caspar M. van Leeuwen ◽  
Damian Podareanu ◽  
Valeriu Codreanu ◽  
Menno A. Veerman ◽  
...  
Keyword(s):  
Numerical Simulation ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Large Eddy Simulation ◽  
Direct Numerical Simulation ◽  
Channel Flow ◽  
Turbulent Channel Flow ◽  
Eddy Simulation ◽  
Large Eddy ◽  
Simplifying Assumptions

Abstract. Atmospheric boundary layers and other wall-bounded flows are often simulated with the large-eddy simulation (LES) technique, which relies on subgrid-scale (SGS) models to parameterize the smallest scales. These SGS models often make strong simplifying assumptions. Also, they tend to interact with the discretization errors introduced by the popular LES approach where a staggered finite-volume grid acts as an implicit filter. We therefore developed an alternative LES SGS model based on artificial neural networks (ANNs) for the computational fluid dynamics code MicroHH (v2.0), which can be run in direct numerical simulation (DNS) and LES mode. We used a turbulent channel flow (with a friction Reynolds number Reτ = 590) as a test case. The developed SGS model has been designed to require fewer simplifying assumptions, and to compensate for the instantaneous discretization errors introduced by the staggered finite-volume grid. We trained the ANNs based on instantaneous flow fields from a direct numerical simulation (DNS) of the selected channel flow. In general, we found excellent agreement between the ANN predicted SGS fluxes and the SGS fluxes derived from DNS for flow fields not used during training (with the correlation coefficient ρ mostly varying between 0.6 and 1.0), showing the potential ANNs may have to construct highly accurate SGS models. However, we observed an artificial build-up of turbulence kinetic energy at high wave modes when we directly incorporated our ANN SGS model into a LES simulation of the selected channel flow, eventually resulting in numeric instability. We hypothesized that error accumulation and aliasing errrors, were both important contributors to the observed instability. Several obstacles therefore remain before the a priori promise of our ANN LES SGS model, can be successfully leveraged in practical applications.

Large eddy simulation with flamelet progress variable approach combined with artificial neural network acceleration

2021 ◽  
Author(s):  
Lorenzo Angelilli ◽  
Pietro Paolo Ciottoli ◽  
Riccardo Malpica Galassi ◽  
Francisco E. Hernandez Perez ◽  
Mattia Soldan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Large Eddy Simulation ◽  
Progress Variable ◽  
Eddy Simulation ◽  
Variable Approach ◽  
Large Eddy ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document