Generative modeling of turbulence

被引:25
|
作者
Drygala, C. [1 ,2 ]
Winhart, B. [3 ]
di Mare, F. [3 ]
Gottschalk, H. [1 ,2 ]
机构
[1] Univ Wuppertal, Sch Math & Nat Sci, IMACM, Wuppertal, Germany
[2] Univ Wuppertal, Sch Math & Nat Sci, IZMD, Wuppertal, Germany
[3] Ruhr Univ Bochum, Dept Mech Engn, Chair Thermal Turbomachines & Aero Engines, Bochum, Germany
关键词
CIRCULAR-CYLINDER; MACHINE; FLOWS; PROOF; FIELD;
D O I
10.1063/5.0082562
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
We present a mathematically well-founded approach for the synthetic modeling of turbulent flows using generative adversarial networks (GAN). Based on the analysis of chaotic, deterministic systems in terms of ergodicity, we outline a mathematical proof that GAN can actually learn to sample state snapshots from the invariant measure of the chaotic system. Based on this analysis, we study a hierarchy of chaotic systems starting with the Lorenz attractor and then carry on to the modeling of turbulent flows with GAN. As training data, we use fields of velocity fluctuations obtained from large-eddy simulations (LES). Two architectures are investigated in detail: we use a deep, convolutional GAN (DCGAN) to synthesize the turbulent flow around a cylinder. We furthermore simulate the flow around a low-pressure turbine stator using the pix2pixHD architecture for a conditional DCGAN being conditioned on the position of a rotating wake in front of the stator. The settings of adversarial training and the effects of using specific GAN architectures are explained. We thereby show that GAN are efficient in simulating turbulence in technically challenging flow problems on the basis of a moderate amount of training data. GAN training and inference times significantly fall short when compared with classical numerical methods, in particular, LES, while still providing turbulent flows in high resolution. We furthermore analyze the statistical properties of the synthesized and LES flow fields, which agree excellently. We also show the ability of the conditional GAN to generalize over changes of geometry by generating turbulent flow fields for positions of the wake that are not included in the training data.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] Deep Generative Modeling: From Probabilistic Framework to Generative AI
    Tomczak, Jakub M.
    ENTROPY, 2025, 27 (03)
  • [32] Turbulence scaling from deep learning diffusion generative models
    Whittaker, Tim
    Janik, Romuald A.
    Oz, Yaron
    JOURNAL OF COMPUTATIONAL PHYSICS, 2024, 514
  • [33] TURBULENCE IMAGE RECOVERY BASED ON IMPROVED GENERATIVE ADVERSARIAL NETWORKS
    Bin, Wei
    Houbu, Li
    Nan, Ding
    Shi, Zhaoyang
    Zhao, Enguo
    Tao, Rong
    Fang, Yao
    UKRAINIAN JOURNAL OF PHYSICAL OPTICS, 2024, 25 (03) : 3040 - 3050
  • [34] Generative-machine-learning surrogate model of plasma turbulence
    Clavier, B.
    Zarzoso, D.
    del-Castillo-Negrete, D.
    Frenod, E.
    PHYSICAL REVIEW E, 2025, 111 (01)
  • [35] Local turbulence generation using conditional generative adversarial networks toward Reynolds-averaged Navier-Stokes modeling
    Yan, Chongyang
    Zhang, Yufei
    PHYSICS OF FLUIDS, 2023, 35 (10)
  • [36] Fairness in Generative Modeling: do it Unsupervised!
    Zameshina, M.
    Teytaud, O.
    Teytaud, Fabien
    Hosu, Vlad
    Carraz, Nathanael
    Najman, Laurent
    Wagner, Markus
    PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, 2022, : 320 - 323
  • [37] Generative Design for Building Information Modeling
    Ferreira, Bruno
    Leitao, Antonio
    ECAADE 2015: REAL TIME - EXTENDING THE REACH OF COMPUTATION, VOL 1, 2015, : 635 - 644
  • [38] TURBULENCE MODELING FOR COMPUTATIONAL AERODYNAMICS
    MARVIN, JG
    AIAA JOURNAL, 1983, 21 (07) : 941 - 955
  • [39] TURBULENCE MODELING IN A HYPERSONIC INLET
    NG, WF
    AJMANI, K
    TAYLOR, AC
    AIAA JOURNAL, 1989, 27 (10) : 1354 - 1360
  • [40] Basic issues of turbulence modeling
    Germano, M
    FUNDAMENTAL PROBLEMATIC ISSUES IN TURBULENCE, 1999, : 213 - 219