Research on Turbulence Calculation Model based on Machine Learning

10.6919/ICJE.202205_8(5).0054

Chuangen Zheng；Likang Zhao；Haiquan Zhong；Li Lin；Zhiyu Xu

Machine Learning ； CFD ； Turbulence ； Model Building ； Accuracy

International Core Journal of Engineering

8卷5期（2022 / 05 / 01）

441 - 446

英文

With the continuous development of the information age, machine learning technology has been continuously improved and applied in various aspects. Especially in the petroleum industry, it has become common to use computational fluid dynamics (CFD) technology to study multiphase flow problems. Due to the great development of machine learning, the fitting speed and accuracy of this technology are accelerated in the process of modeling and analysis. CFD technology consists of pre-processing, solver and post-processing. The solver stage is the core of CFD technology, and turbulence model analysis is the most valuable part in this stage, which has great room for improvement. This paper starts from turbulence analysis, based on machine learning, adds filters before iterative values are introduced into turbulence model, extracts similar features, and removes redundancy, and also puts forward the prospect of machine learning and turbulence model research.

1. Johnson P L. A physics-inspired alternative to spatial filtering for large-eddy simulations of turbulent flows[J]. Journal of Fluid Mechanics, 2022, 934.
   連結：
2. Li X L, Fu D X, Ma Y W, et al. Direct numerical simulation of compressible turbulent flows[J]. Acta Mechanica Sinica, 2010, 26(6): 795-806.
   連結：
3. Ling J, Kurzawski A, Templeton J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance[J]. Journal of Fluid Mechanics, 2016, 807: 155-166.
   連結：
4. Duraisamy K, Iaccarino G, Xiao H. Turbulence modeling in the age of data[J]. Annual Review of Fluid Mechanics, 2019, 51: 357-377.
   連結：
5. Gamahara M, Hattori Y. Searching for turbulence models by artificial neural network[J]. Physical Review Fluids, 2017, 2(5): 054604.
   連結：
6. Maulik R, San O, Rasheed A, et al. Data-driven deconvolution for large eddy simulations of Kraichnan turbulence[J]. Physics of Fluids, 2018, 30(12): 125109.
   連結：
7. Dimiduk D M, Holm E A, Niezgoda S R. Perspectives on the impact of machine learning, deep learning, and artificial intelligence on materials, processes, and structures engineering[J]. Integrating Materials and Manufacturing Innovation, 2018, 7(3): 157-172.
   連結：
8. CHEN S,XIA Z,PEI S,et al.Reynolds-stress-constrained large-eddy simulation of wall-bounded turbulent flows[J]. Journal of Fluid Mechanics,2012,703:1-28.
   連結：
9. HE G,JIN G, YANG Y.Space-time correlations and dynamiccoupling in turbulent flows[J].Annual Review of Fluid Mechanics,2017,49:51-70.
   連結：
10. Guyon I, Elisseeff A. An introduction to feature extraction[M]. Feature extraction. Springer, Berlin, Heidelberg, 2006: 1-25.
    連結：
11. WU J L,XIAO H,SUN R,et al.Reynolds averaged Navier- Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned[J].Journal of Fluid Mechanics, 2019,869:553-586.
    連結：
12. Ma C, Wang J. Model reduction with memory and the machine learning of dynamical systems[J]. arXiv preprint arXiv:1808.04258, 2018.
13. Du Yu Perceptual computing of human pose and gesture based on deep learning [D] Zhejiang: Zhejiang University, 2017.
14. She zhensu, Tang fan, Xiao Structural ensemble dynamics theory for engineering turbulenc models [J] Acta Aerodynamica Sinica, 2019,37 (1): 1-18.
15. Zhang Weiwei, Zhu Linyang, Liu Yilang, et al. Progresses in the application of machine learning in turbulence modeling [J] Acta Aerodynamica Sinica, 2019,37 (03): 444-454.