Close Search Advanced
Journals
Resources
About Us
Open Access

Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields Using Convolutional Neural Networks

Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields Using Convolutional Neural Networks
Read Now
Download (PDF)

Year:    2019

Communications in Computational Physics, Vol. 25 (2019), Iss. 3 : pp. 625–650

Abstract

Feature identification is an important task in many fluid dynamics applications and diverse methods have been developed for this purpose. These methods are based on a physical understanding of the underlying behavior of the flow in the vicinity of the feature. Particularly, they require the definition of suitable criteria (i.e. point-based or neighborhood-based derived properties) and proper selection of thresholds. However, these methods rely on creative visualization of physical idiosyncrasies of specific features and flow regimes, making them non-universal and requiring significant effort to develop. Here we present a physics-based, data-driven method capable of identifying any flow feature it is trained to. We use convolutional neural networks, a machine learning approach developed for image recognition, and adapt it to the problem of identifying flow features. This provides a general method and removes the large burden placed on identifying new features. The method was tested using mean flow fields from numerical simulations, where the recirculation region and boundary layer were identified in several two-dimensional flows through a convergent-divergent channel, and the horseshoe vortex was identified in three-dimensional flow over a wing-body junction.

Submit Article

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/cicp.OA-2018-0035

Communications in Computational Physics, Vol. 25 (2019), Iss. 3 : pp. 625–650

Published online:    2019-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    26

Keywords:    Machine learning feature identification fluid dynamics convolutional neural network.

  1. Prediction of airfoil dynamic stall response using convolutional neural networks

    Miotto, Renato F. | Wolf, William

    AIAA AVIATION 2023 Forum, (2023),

    https://doi.org/10.2514/6.2023-4362 [Citations: 0]

  2. A CNN-based vortex identification method

    Deng, Liang | Wang, Yueqing | Liu, Yang | Wang, Fang | Li, Sikun | Liu, Jie

    Journal of Visualization, Vol. 22 (2019), Iss. 1 P.65

    https://doi.org/10.1007/s12650-018-0523-1 [Citations: 55]

  3. Transformer condition prediction based on data and physical models

    Guo, Zhenyu | Ma, Huan | Liu, Xin | Li, QiYue | Wu, LiuBing

    Mathematical Foundations of Computing, Vol. 0 (2024), Iss. 0 P.0

    https://doi.org/10.3934/mfc.2024029 [Citations: 0]

  4. Flow imaging as an alternative to non-intrusive measurements and surrogate models through vision transformers and convolutional neural networks

    Miotto, Renato F. | Wolf, William R.

    Physics of Fluids, Vol. 35 (2023), Iss. 4

    https://doi.org/10.1063/5.0144700 [Citations: 4]

  5. Unveiling Latent Chemical Mechanisms: Hybrid Modeling for Estimating Spatiotemporally Varying Parameters in Moving Boundary Problems

    Pahari, Silabrata | Shah, Parth | Sang-Il Kwon, Joseph

    Industrial & Engineering Chemistry Research, Vol. 63 (2024), Iss. 3 P.1501

    https://doi.org/10.1021/acs.iecr.3c03531 [Citations: 15]

  6. A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data Using Unstructured Spatial Discretizations

    Tencer, John | Potter, Kevin

    SIAM Journal on Scientific Computing, Vol. 43 (2021), Iss. 4 P.A2581

    https://doi.org/10.1137/20M1344263 [Citations: 8]

  7. Seeing macro-dispersivity from hydraulic conductivity field with convolutional neural network

    Zhou, Zhengkun | Shi, Liangsheng | Zha, Yuanyuan

    Advances in Water Resources, Vol. 138 (2020), Iss. P.103545

    https://doi.org/10.1016/j.advwatres.2020.103545 [Citations: 11]

  8. Vortex-U-Net: An efficient and effective vortex detection approach based on U-Net structure

    Deng, Liang | Bao, Wenchun | Wang, Yueqing | Yang, Zhigong | Zhao, Dan | Wang, Fang | Bi, Chongke | Guo, Yang

    Applied Soft Computing, Vol. 115 (2022), Iss. P.108229

    https://doi.org/10.1016/j.asoc.2021.108229 [Citations: 9]

  9. Comparative studies of predictive models for unsteady flow fields based on deep learning and proper orthogonal decomposition

    Xu, Yuhang | Sha, Yangyang | Wang, Cong | Cao, Wei | Wei, Yingjie

    Ocean Engineering, Vol. 272 (2023), Iss. P.113935

    https://doi.org/10.1016/j.oceaneng.2023.113935 [Citations: 11]

  10. A data-driven deep learning approach for predicting separation-induced transition of submarines

    Xuan, Yang | Lyu, Hongqiang | An, Wei | Liu, Jianhua | Liu, Xuejun

    Physics of Fluids, Vol. 34 (2022), Iss. 2

    https://doi.org/10.1063/5.0079648 [Citations: 9]

  11. Fast Prediction of Two-Dimensional Flowfields with Fuel Injection into Supersonic Crossflow via Deep Learning

    AKIYAMA, Kento | OGAWA, Hideaki

    TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES, Vol. 66 (2023), Iss. 5 P.164

    https://doi.org/10.2322/tjsass.66.164 [Citations: 1]

  12. MVU-Net: a multi-view U-Net architecture for weakly supervised vortex detection

    Deng, Liang | Chen, Jianqiang | Wang, Yueqing | Chen, Xinhai | Wang, Fang | Liu, Jie

    Engineering Applications of Computational Fluid Mechanics, Vol. 16 (2022), Iss. 1 P.1567

    https://doi.org/10.1080/19942060.2022.2104930 [Citations: 4]

  13. Prediction of wall-pressure fluctuations for separating/reattaching flows applied to space launchers using zonal detached eddy simulation-based convolutional neural networks

    Lecler, S. | Weiss, P. E. | Deck, S.

    Physics of Fluids, Vol. 35 (2023), Iss. 6

    https://doi.org/10.1063/5.0146358 [Citations: 7]

  14. A clustering-based approach to vortex extraction

    Deng, Liang | Wang, Yueqing | Chen, Cheng | Liu, Yang | Wang, Fang | Liu, Jie

    Journal of Visualization, Vol. 23 (2020), Iss. 3 P.459

    https://doi.org/10.1007/s12650-020-00636-z [Citations: 11]

  15. PCA-based SVM classification for simulated ice floes in front of sluice gates

    Liang, Naisheng | Tuo, Youcai | Deng, Yun | He, Tianfu

    Polar Science, Vol. 34 (2022), Iss. P.100839

    https://doi.org/10.1016/j.polar.2022.100839 [Citations: 8]

  16. A Fluid Flow Data Set for Machine Learning and its Application to Neural Flow Map Interpolation

    Jakob, Jakob | Gross, Markus | Gunther, Tobias

    IEEE Transactions on Visualization and Computer Graphics, Vol. 27 (2021), Iss. 2 P.1279

    https://doi.org/10.1109/TVCG.2020.3028947 [Citations: 24]
  17. Handbook of Cancer and Immunology

    Integrating Computational Approaches in Cancer Immunotherapy

    Mohammed, Eman Abd-Elnasser | Ali, Hend Montaseb | Farouk, Warda Mohammed | Arafa, Reem K.

    2024

    https://doi.org/10.1007/978-3-030-80962-1_418-1 [Citations: 0]

  18. ANN-based deep collocation method for natural convection in porous media

    Kumar, Sumant | Kumar, B. V. Rathish | Murthy, S. V. S. S. N. V. G. Krishna

    Neural Computing and Applications, Vol. 36 (2024), Iss. 11 P.6067

    https://doi.org/10.1007/s00521-023-09385-0 [Citations: 0]

  19. Towards a new paradigm in intelligence-driven computational fluid dynamics simulations

    Chen, Xinhai | Wang, Zhichao | Deng, Liang | Yan, Junjun | Gong, Chunye | Yang, Bo | Wang, Qinglin | Zhang, Qingyang | Yang, Lihua | Pang, Yufei | Liu, Jie

    Engineering Applications of Computational Fluid Mechanics, Vol. 18 (2024), Iss. 1

    https://doi.org/10.1080/19942060.2024.2407005 [Citations: 0]

  20. Reconstruction of natural convection within an enclosure using deep neural network

    Wang, Tongsheng | Huang, Zhu | Sun, Zhongguo | Xi, Guang

    International Journal of Heat and Mass Transfer, Vol. 164 (2021), Iss. P.120626

    https://doi.org/10.1016/j.ijheatmasstransfer.2020.120626 [Citations: 28]

  21. A graph neural network-based framework to identify flow phenomena on unstructured meshes

    Wang, L. | Fournier, Y. | Wald, J. F. | Mesri, Y.

    Physics of Fluids, Vol. 35 (2023), Iss. 7

    https://doi.org/10.1063/5.0156975 [Citations: 10]

  22. Integrated Framework for Smart Adaptive Mesh Refinement and Mesh Motion with NEMoSys

    Patel, Akash A. | Mehrabadi, Mohammad | Gondolo, Alessandro

    AIAA SCITECH 2022 Forum, (2022),

    https://doi.org/10.2514/6.2022-0974 [Citations: 0]

  23. Applications of machine learning to the analysis of engine in-cylinder flow and thermal process: A review and outlook

    Zhao, Fengnian | Hung, David L.S.

    Applied Thermal Engineering, Vol. 220 (2023), Iss. P.119633

    https://doi.org/10.1016/j.applthermaleng.2022.119633 [Citations: 8]

  24. Using machine learning to detect the turbulent region in flow past a circular cylinder

    Li, Binglin | Yang, Zixuan | Zhang, Xing | He, Guowei | Deng, Bing-Qing | Shen, Lian

    Journal of Fluid Mechanics, Vol. 905 (2020), Iss.

    https://doi.org/10.1017/jfm.2020.725 [Citations: 48]

  25. Overview Frequency Principle/Spectral Bias in Deep Learning

    Xu, Zhi-Qin John | Zhang, Yaoyu | Luo, Tao

    Communications on Applied Mathematics and Computation, Vol. (2024), Iss.

    https://doi.org/10.1007/s42967-024-00398-7 [Citations: 2]

  26. Interactive Visualization of Time-Varying Flow Fields Using Particle Tracing Neural Networks

    Han, Mengjiao | Li, Jixian | Sane, Sudhanshu | Gupta, Shubham | Wang, Bei | Petruzza, Steve | Johnson, Chris R.

    2024 IEEE 17th Pacific Visualization Conference (PacificVis), (2024), P.52

    https://doi.org/10.1109/PacificVis60374.2024.00015 [Citations: 0]

  27. Application of fully convolutional neural networks for feature extraction in fluid flow

    Kashir, Babak | Ragone, Marco | Ramasubramanian, Ajaykrishna | Yurkiv, Vitaliy | Mashayek, Farzad

    Journal of Visualization, Vol. 24 (2021), Iss. 4 P.771

    https://doi.org/10.1007/s12650-020-00732-0 [Citations: 14]

  28. Construction of reduced-order models for fluid flows using deep feedforward neural networks

    Lui, Hugo F. S. | Wolf, William R.

    Journal of Fluid Mechanics, Vol. 872 (2019), Iss. P.963

    https://doi.org/10.1017/jfm.2019.358 [Citations: 126]

  29. Flow time history representation and reconstruction based on machine learning

    Zhan, Qingliang | Bai, Chunjin | Ge, Yaojun | Sun, Xiannian

    Physics of Fluids, Vol. 35 (2023), Iss. 8

    https://doi.org/10.1063/5.0160296 [Citations: 1]

  30. Reconstruction of hydrofoil cavitation flow based on the chain-style physics-informed neural network

    Ouyang, Hanqing | Zhu, Zhicheng | Chen, Kuangqi | Tian, Beichen | Huang, Biao | Hao, Jia

    Engineering Applications of Artificial Intelligence, Vol. 119 (2023), Iss. P.105724

    https://doi.org/10.1016/j.engappai.2022.105724 [Citations: 13]

  31. Sound pressure level spectrum analysis by combination of 4D PTV and ANFIS method around automotive side-view mirror models

    Kim, Dong | Safdari, Arman | Kim, Kyung Chun

    Scientific Reports, Vol. 11 (2021), Iss. 1

    https://doi.org/10.1038/s41598-021-90734-1 [Citations: 3]

  32. Self-adaptive and time divide-and-conquer physics-informed neural networks for two-phase flow simulations using interface tracking methods

    Zhou, Wen | Miwa, Shuichiro | Okamoto, Koji

    Physics of Fluids, Vol. 36 (2024), Iss. 7

    https://doi.org/10.1063/5.0214646 [Citations: 0]

  33. Data-driven modeling for boiling heat transfer: Using deep neural networks and high-fidelity simulation results

    Liu, Yang | Dinh, Nam | Sato, Yohei | Niceno, Bojan

    Applied Thermal Engineering, Vol. 144 (2018), Iss. P.305

    https://doi.org/10.1016/j.applthermaleng.2018.08.041 [Citations: 91]

  34. POD-Enhanced Deep Learning-Based Reduced Order Models for the Real-Time Simulation of Cardiac Electrophysiology in the Left Atrium

    Fresca, Stefania | Manzoni, Andrea | Dedè, Luca | Quarteroni, Alfio

    Frontiers in Physiology, Vol. 12 (2021), Iss.

    https://doi.org/10.3389/fphys.2021.679076 [Citations: 26]

  35. A rapid vortex identification method using fully convolutional segmentation network

    Wang, Yueqing | Deng, Liang | Yang, Zhigong | Zhao, Dan | Wang, Fang

    The Visual Computer, Vol. 37 (2021), Iss. 2 P.261

    https://doi.org/10.1007/s00371-020-01797-6 [Citations: 15]

  36. Deep Regression Network-Assisted Efficient Streamline Generation Method

    Lee, Joong-Youn | Park, Jinah

    IEEE Access, Vol. 9 (2021), Iss. P.111704

    https://doi.org/10.1109/ACCESS.2021.3100127 [Citations: 5]