Exploration of robust machine learning strategy for subgrid scale stress modeling

被引:4
|
作者
Abekawa, A. [1 ]
Minamoto, Y. [1 ]
Osawa, K. [2 ]
Shimamoto, H. [1 ]
Tanahashi, M. [1 ]
机构
[1] Tokyo Inst Technol, Sch Engn, Ookayama, Meguro, Tokyo 1528550, Japan
[2] Univ Politecn Madrid, Sch Aeronaut, Madrid 28040, Spain
关键词
TURBULENT; FLOW; SIMULATION; EDDIES;
D O I
10.1063/5.0134471
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
Various aspects of machine learning (ML) are explored to resolve limitations appearing in current ML-based subgrid scale (SGS) stress modeling. Graph neural network (GNN), applied in the present study, allows flexible and rigorous use of spatial convolution regardless of the proximity to physical boundaries and mesh uniformity. Along with GNN, the proposed feature scaling method relies only on the local quantities and can be applied for a range of flow configurations. A data augmentation method is also proposed to consider the rotational invariant. All these techniques are implemented in the present model, and the model is compared with versions of corresponding ML-based models including a typical multilayer perceptron (MLP) for various flow configurations. The results showed that both GNN and MLP models yield reasonable prediction overall. However, GNN shows superior performance near-wall due to spatial convolution. Although the present method implements the rotational invariant discretely, the augmentation method is found to produce consistent performance for any rotated coordinates. The minimal flow configuration, which can train a model to predict a range of flow configurations, is also explored. It is found that a model trained based on turbulent channel flows alone yields a close level of prediction robustness to the ones trained with multiple flow configurations. The developed GNN model is implemented in OpenFOAM, and large eddy simulation (LES) results are compared with corresponding direct numerical simulation data. With these proposed techniques, ML-based SGS models can be improved in terms of robustness and usability for a range of LES applications.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Subgrid scale modeling for turbulence in rotating reference frames
    Tsubokura, Makoto
    Kobayashi, Toshio
    Taniguchi, Nobuyuki
    Kogaki, Tetsuya
    Journal of Wind Engineering and Industrial Aerodynamics, 1999, 81 (1-4): : 361 - 375
  • [22] SUBGRID-SCALE MODELING OF COMPRESSIBLE TURBULENT FLOWS
    YOSHIZAWA, A
    PHYSICS OF FLUIDS A-FLUID DYNAMICS, 1991, 3 (04): : 714 - 716
  • [23] Multifractal scale-similarity in subgrid-scale turbulence modeling
    Burton, GC
    Dahm, WJA
    Dowling, DR
    Powell, KG
    ADVANCES IN TURBULENCE VIII, 2000, : 523 - 526
  • [24] SUBGRID-SCALE MODELING SUGGESTED BY A 2-SCALE DIA
    YOSHIZAWA, A
    JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS, 1993, 46-7 : 69 - 76
  • [25] A NOTE ON SUBGRID-SCALE PROCESSES IN PHOTOCHEMICAL MODELING
    HESS, GD
    COPE, ME
    ATMOSPHERIC ENVIRONMENT, 1989, 23 (12) : 2857 - 2860
  • [26] Subgrid-scale modeling for turbulent reacting flows
    Cook, AW
    Riley, JJ
    COMBUSTION AND FLAME, 1998, 112 (04) : 593 - 606
  • [27] ON THE APPLICATION OF THE GERMANO IDENTITY TO SUBGRID-SCALE MODELING
    RONCHI, C
    YPMA, M
    CANUTO, VM
    PHYSICS OF FLUIDS A-FLUID DYNAMICS, 1992, 4 (12): : 2927 - 2929
  • [28] Implicit subgrid-scale modeling by adaptive deconvolution
    Adams, NA
    Hickel, S
    Franz, S
    JOURNAL OF COMPUTATIONAL PHYSICS, 2004, 200 (02) : 412 - 431
  • [29] On the topology of the eigenframe of the subgrid-scale stress tensor
    Yang, Zixuan
    Wang, Bing-Chen
    JOURNAL OF FLUID MECHANICS, 2016, 798 : 598 - 627
  • [30] AN IMPROVED DYNAMIC SUBGRID-SCALE STRESS MODEL
    Tang Xue-ling
    Qian Zhong-dong
    Wu Yu-lin
    Liu Shu-hong
    Yang Fan
    JOURNAL OF HYDRODYNAMICS, 2004, 16 (03) : 276 - 282