| Citation: |
PAN J T, MA X Y, LIU Y H, et al. Experimental data-driven deep neural network modeling and prediction of separated flow[J]. Journal of Experiments in Fluid Mechanics, doi: 10.11729/syltlx20250015.
|
In this study, spanwise-aligned Vortex Generators (VGs) were used on the backward-facing step for flow separation control in a low-speed wind tunnel, and the downstream separated shear flow was measured by the single-probe hot-wire anemometer. Based on the experimental dataset, Deep Neural Network (DNN) models were established and trained. The input parameters included the heights and spacings of the vortex generators and the spatial coordinates within the separated shear layer, while the output parameters were time-averaged velocities and the root-mean-square of the turbulent fluctuations. The experimental datasets were used in the iterating and training process of the models. In the comparison of the model-predicted and measured results, the mean squared errors between the modeled mean velocities and fluctuation distributions and the measured data at various flow positions were all below 10−3, and thus the data-driven deep neural network models were validated with the ability of nonlinear modeling of the separated shear flow, characterization of flow features and prediction of experimental results. Furthermore, the DNN model managed to enrich the complex flow field information by nonlinear fitting of the discrete measurement points, which leads to optimization of vortex generator designs.
| [1] |
MONTAZER E, YARMAND H, SALAMI E, et al. A brief review study of flow phenomena over a backward-facing step and its optimization[J]. Renewable and Sustainable Energy Reviews, 2018, 82: 994–1005. doi: 10.1016/j.rser.2017.09.104
|
| [2] |
HUDY L M, NAGUIB A, HUMPHREYS W M. Stochastic estimation of a separated-flow field using wall-pressure-array measurements[J]. Physics of Fluids, 2007, 19(2): 024103. doi: 10.1063/1.2472507
|
| [3] |
MA C H, AWASTHI M, MOREAU D, et al. Aeroacoustics of turbulent flow over a forward–backward facing step[J]. Journal of Sound and Vibration, 2023, 563: 117840. doi: 10.1016/j.jsv.2023.117840
|
| [4] |
YU K K, HAO J A, WEN C Y, et al. Bi-global stability of supersonic backward-facing step flow[J]. Journal of Fluid Mechanics, 2024, 981: A29. doi: 10.1017/jfm.2024.76
|
| [5] |
MA X Y, GEISLER R, SCHRÖDER A. Experimental investigation of three-dimensional vortex structures down-stream of vortex generators over a backward-facing step[J]. Flow, Turbulence and Combustion, 2017, 98(2): 389–415. doi: 10.1007/s10494-016-9768-8
|
| [6] |
李仁康, 王如根, 何成, 等. 涡流发生器对高负荷压气机叶栅角区分离影响的实验研究[J]. 实验流体力学, 2017, 31(6): 22–28,36. DOI: 10.11729/syltlx20160195
LI R K, WANG R G, HE C, et al. Experimental investigation on the effects of vortex generator on corner separation in a high-load compressor cascade[J]. Journal of Experiments in Fluid Mechanics, 2017, 31(6): 22–28,36. doi: 10.11729/syltlx20160195
|
| [7] |
XU B, CHEN X D, LIU T H, et al. On the anti-rolling performance of a train using a vortex generator array[J]. Engineering Applications of Computational Fluid Mechanics, 2023, 17(1): 2275614. doi: 10.1080/19942060.2023.2275614
|
| [8] |
张奕, 潘翀, 窦建宇, 等. 微型涡流发生器影响下的湍流边界层流场与摩阻特性[J]. 实验流体力学, 2023, 37(4): 48–58. DOI: 10.11729/syltlx20230027
ZHANG Y, PAN C, DOU J Y, et al. Flowfield and friction characteristics downstream of mirco vortex generator in turbulent boundary layer[J]. Journal of Experiments in Fluid Mechanics, 2023, 37(4): 48–58. doi: 10.11729/syltlx20230027
|
| [9] |
管新蕾, 孙小姣, 王维, 等. 弧形涡流发生器对湍流相干结构及强化换热的影响[J]. 实验流体力学, 2024, 38(4): 104–112. DOI: 10.11729/syltlx20230142
GUAN X L, SUN X J, WANG W, et al. Effect of arc-shaped vortex generator on coherent structures and heat transfer enhancement in turbulence[J]. Journal of Experiments in Fluid Mechanics, 2024, 38(4): 104–112. doi: 10.11729/syltlx20230142
|
| [10] |
HRISTOZOVA L, SEBASTIAN R, SCHREYER A M. Flow fields around asymmetrical micro vortex generators in supersonic flow[J]. Aerospace Science and Technology, 2024, 145: 108838. doi: 10.1016/j.ast.2023.108838
|
| [11] |
BRUNTON S L, NOACK B R, KOUMOUTSAKOS P. Machine learning for fluid mechanics[J]. Annual Review of Fluid Mechanics, 2020, 52: 477–508. doi: 10.1146/annurev-fluid-010719-060214
|
| [12] |
MA Y L, DU Z, XU Q Y, et al. Flow field reconstruction of compressor blade cascade based on deep learning methods[J]. Aerospace Science and Technology, 2024, 155: 109637. doi: 10.1016/j.ast.2024.109637
|
| [13] |
ZHONG J X, QU F, SUN D, et al. Fast flow field prediction approach of supersonic inlet in wide operating range based on deep learning[J]. Aerospace Science and Technology, 2024, 146: 108955. doi: 10.1016/j.ast.2024.108955
|
| [14] |
ZHANG Y Y, ZHENG X H, GONG Z Q, et al. Towards sparse sensor annotations: Uncertainty-based active transfer learning for airfoil flow field prediction[J]. Chinese Journal of Aeronautics, 2024, 37(12): 87–98. doi: 10.1016/j.cja.2024.08.039
|
| [15] |
柴聪聪, 易贤, 郭磊, 等. 基于BP神经网络的冰形特征参数预测[J]. 实验流体力学, 2021, 35(3): 16–21. DOI: 10.11729/syltlx20200016
CHAI C C, YI X, GUO L, et al. Prediction of ice shape characteristic parameters based on BP nerual network[J]. Journal of Experiments in Fluid Mechanics, 2021, 35(3): 16–21. doi: 10.11729/syltlx20200016
|
| [16] |
余柏杨, 吕宏强, 周岩, 等. 基于机器学习的高速复杂流场流动控制效果预测分析[J]. 实验流体力学, 2022, 36(3): 44–54. DOI: 10.11729/syltlx20210168
YU B Y, LYU H Q, ZHOU Y, et al. Predictive analysis of flow control in high-speed complex flow field based on machine learning[J]. Journal of Experiments in Fluid Mechanics, 2022, 36(3): 44–54. doi: 10.11729/syltlx20210168
|
| [17] |
张兴焕, 张平涛, 彭博, 等. 基于机器学习的结冰风洞温度场预测[J]. 实验流体力学, 2022, 36(5): 8–15. DOI: 10.11729/syltlx20210196
ZHANG X H, ZHANG P T, PENG B, et al. Prediction of icing wind tunnel temperature field with machine learning[J]. Journal of Experiments in Fluid Mechanics, 2022, 36(5): 8–15. doi: 10.11729/syltlx20210196
|
| [18] |
黎杨, 汪奇, 陈骏喆, 等. 基于深度神经网络的小样本船舶流场预测[J]. 船舶力学, 2023, 27(11): 1594–1607. DOI: 10.3969/i.issn.1007-7294.2023.11.002
LI Y, WANG Q, CHEN J Z, et al. Flow field prediction of ships with small sample sizes based on deep neural networks[J]. Journal of Ship Mechanics, 2023, 27(11): 1594–1607. doi: 10.3969/i.issn.1007-7294.2023.11.002
|
| [19] |
XIE H R, HUA Y, LI Y B, et al. Estimation of sequential transient flow around cylinders using recurrent neural network coupled graph convolutional network[J]. Ocean Engineering, 2024, 293: 116684. doi: 10.1016/j.oceaneng.2024.116684
|
| [20] |
ZHANG F, HU H B, ZHANG H, et al. Predicting pressure fields from incomplete velocity fields based on deep convolutional neural network[J]. Ocean Engineering, 2024, 309: 118578. doi: 10.1016/j.oceaneng.2024.118578
|
| [21] |
LIN J C. Review of research on low-profile vortex generators to control boundary-layer separation[J]. Progress in Aerospace Sciences, 2002, 38(4-5): 389–420. doi: 10.1016/S0376-0421(02)00010-6
|
| [22] |
WALEFFE F. On a self-sustaining process in shear flows[J]. Physics of Fluids, 1997, 9(4): 883–900. doi: 10.1063/1.869185
|
| [23] |
MA X Y, TANG Z Q, JIANG N. Investigation of spanwise coherent structures in turbulent backward-facing step flow by time-resolved PIV[J]. Experimental Thermal and Fluid Science, 2022, 132: 110569. doi: 10.1016/j.expthermflusci.2021.110569
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: