Exploration of robust machine learning strategy for subgrid scale stress modeling

Author:

Abekawa A.1ORCID,Minamoto Y.1ORCID,Osawa K.2ORCID,Shimamoto H.1,Tanahashi M.1

Affiliation:

1. School of Engineering, Tokyo Institute of Technology 1 , Ookayama, Meguro, Tokyo 152-8550, Japan

2. School of Aeronautics, Universidad Politécnica de Madrid 2 , 28040 Madrid, Spain

Abstract

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.

Funder

Japan Science and Technology Agency

Publisher

AIP Publishing

Subject

Condensed Matter Physics,Fluid Flow and Transfer Processes,Mechanics of Materials,Computational Mechanics,Mechanical Engineering

Reference48 articles.

1. General circulation experiments with the primitive equations;Mon. Weather Rev.,1963

2. On turbulent flow near a wall;J. Aeronaut. Sci.,1956

3. Sub-grid scale stress modelling based on the square of the velocity gradient tensor;Flow, Turbul. Combust.,1999

4. A dynamic subgrid-scale eddy viscosity model;Phys. Fluids A,1991

5. J. Bardina, “Improved turbulence models based on large eddy simulation of homogeneous, incompressible turbulent flows,” Ph.D. thesis (Stanford University, Stanford, CA, 1983).

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3