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
  • [31] SUBGRID-SCALE ALGEBRAIC STRESS MODEL OF TURBULENCE
    SHIMOMURA, Y
    JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN, 1994, 63 (01) : 5 - 9
  • [32] A dynamic nonlinear subgrid-scale stress model
    Wang, BC
    Bergstrom, DJ
    PHYSICS OF FLUIDS, 2005, 17 (03) : 035109 - 1
  • [33] Machine Learning for Microarchitecture Power Modeling and Design Space Exploration: A Survey
    Zhai, Jianwang
    Ling, Zichao
    Bai, Chen
    Zhao, Kang
    Yu, Bei
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2024, 61 (06): : 1351 - 1369
  • [34] Robust Cooperative Exploration With a Switching Strategy
    Wu, Wencen
    Zhang, Fumin
    IEEE TRANSACTIONS ON ROBOTICS, 2012, 28 (04) : 828 - 839
  • [35] A Switching Strategy for Robust Cooperative Exploration
    Wu, Wencen
    Zhang, Fumin
    49TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2010, : 5493 - 5498
  • [36] Machine learning applications in genome-scale metabolic modeling
    Kim, Yeji
    Kim, Gi Bae
    Lee, Sang Yup
    CURRENT OPINION IN SYSTEMS BIOLOGY, 2021, 25 : 42 - 49
  • [37] Fault Modeling of Extreme Scale Applications using Machine Learning
    Vishnu, Abhinav
    van Dam, Hubertus
    Tallent, Nathan R.
    Kerbyson, Darren J.
    Hoisie, Adolfy
    2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2016), 2016, : 222 - 231
  • [38] Machine learning-assisted multi-scale modeling
    Weinan, E.
    Lei, Huan
    Xie, Pinchen
    Zhang, Linfeng
    JOURNAL OF MATHEMATICAL PHYSICS, 2023, 64 (07)
  • [39] Machine learning for the advancement of genome-scale metabolic modeling
    Kundu, Pritam
    Beura, Satyajit
    Mondal, Suman
    Das, Amit Kumar
    Ghosh, Amit
    BIOTECHNOLOGY ADVANCES, 2024, 74
  • [40] Subgrid-scale scalar flux modelling based on optimal estimation theory and machine-learning procedures
    Vollant, A.
    Balarac, G.
    Corre, C.
    JOURNAL OF TURBULENCE, 2017, 18 (09): : 854 - 878