基于时程卷积自编码的机翼绕流特征识别方法

战庆亮; 白春锦; 张宁; 葛耀君

doi:10.7527/S1000-6893.2021.26531

航空学报 >

2022 , Vol. 43 >Issue 11: 526531 - 526531

DOI: https://doi.org/10.7527/S1000-6893.2021.26531

论文

基于时程卷积自编码的机翼绕流特征识别方法

战庆亮 ,
白春锦 ,
张宁 ,
葛耀君

展开

1. 大连海事大学交通运输工程学院, 大连 116026;
2. 同济大学土木工程防灾国家重点实验室, 上海 200092

收稿日期: 2021-10-18

修回日期: 2021-11-08

网络出版日期: 2021-12-09

基金资助

国家自然科学基金（51778495，51978527）；桥梁结构抗风技术交通行业重点实验室（上海）开放课题（KLWRTBMC21-02）；辽宁省教育厅研究计划（LJKZ0052）

收起

Feature extraction method of flow around airfoil based on time-history convolutional autoencoder

ZHAN Qingliang ,
BAI Chunjin ,
ZHANG Ning ,
GE Yaojun

Expand

1. College of Transportation and Engineering, Dalian Maritime University, Dalian 116026, China;
2. State Key Laboratory for Disaster Reduction in Civil Engineering, Tongji University, Shanghai 200092, China

Received date: 2021-10-18

Revised date: 2021-11-08

Online published: 2021-12-09

Supported by

National Natural Science Foundation of China (51778495, 51978527); Industry Key Laboratory of Bridge Structure Wind Resistance Technology (Shanghai) Open Project (KLWRTBMC21-02); Research Project of Liaoning Education Department (LJKZ0052)

Fold

摘要

机翼周围的流动状态直接影响其受力特性，流动特征的识别与分析对保证机翼的气动力研究尤为关键。基于空间流场参数的流动特征识别结果受主观阈值影响大；基于流场快照数据的流动特征分析难以完整表征流场的时变特征，且大范围的流场快照获取难度大，因而其实用性受限。本文基于流场时程数据的低维表征模型提出了无监督自动编码的流场时程特征识别方法。采用深度学习技术充分挖掘时程信号中的隐含的流动特征，建立流场时程数据的低维表征模型；进一步对低维的表征编码进行分析，将包含不同时序特征的测点样本进行特征聚类，实现了基于空间点时程数据的流场特征提取与识别。通过对NACA0012翼型的流场进行特征提取与分析验证了所得流动特征低维表征的准确性，实现了基于流场时程数据的流动分离区自动识别。本文可为相关流场特征提取、特征分析和特征表征等问题的研究提供新的方法与参考。

关键词： 流场时程; 卷积自编码; 深度学习; 特征提取; 机翼绕流

本文引用格式

战庆亮 , 白春锦 , 张宁 , 葛耀君 . 基于时程卷积自编码的机翼绕流特征识别方法[J]. 航空学报, 2022 , 43(11) : 526531 -526531 . DOI: 10.7527/S1000-6893.2021.26531

Abstract

The flow around an airfoil directly affects its aerodynamics, and flow feature analysis is critical to ensure its aerodynamic characteristics. The feature recognition based on spatial parameters is greatly affected by subjective threshold. And flow analysis based on the snapshot data, which is difficult to obtain a large-scale snapshot in experiment, is difficult to fully represent the time-varying features of the flow evolution. Based on the low-dimensional representation model of flow time-history data, an unsupervised autoencoder method is proposed to identify flow features automatically. Deep learning is used to mine the implicit flow features in the time-history signal, and a low-dimensional representation model of the time-history data is established. The low-dimensional representation code is further analyzed, and the measurement point samples containing different features are clustered to extract and identify flow features. Analysis of the flow field around the NACA0012 airfoil with a low Reynolds number is carried out. The flow separation zone was successfully identified using the proposed feature classification method. Results proved that the proposed method can be used to solve the problems such as flow feature extraction, feature analysis, and feature characterization.

Key words： flow time-history; convolutional autoencoder; deep learning; feature extraction; flow around airfoil

参考文献

[1] 王庶, 米建春. 大湍流度对超低雷诺数下翼型受力及绕流的影响[J]. 航空学报, 2011, 32(1):41-48. WANG S, MI J C. Effect of large turbulence intensity on airfoil load and flow[J]. Acta Aeronautica et Astronautica Sinica, 2011, 32(1):41-48(in Chinese).
[2] HUANG R, LIN C. Vortex shedding and shear-layer instability of a cantilever wing at low Reynolds numbers[C]//33rd Aerospace Sciences Meeting and Exhibit. Reston:AIAA, 1995:589.
[3] ALAM M M, ZHOU Y, YANG H X, et al. The ultra-low Reynolds number airfoil wake[J]. Experiments in Fluids, 2010, 48(1):81-103.
[4] AKBARI M H, PRICE S J. Simulation of dynamic stall for a NACA 0012 airfoil using a vortex method[J]. Journal of Fluids and Structures, 2003, 17(6):855-874.
[5] HOFFMANN J A. Effects of freestream turbulence on the performance characteristics of an airfoil[J]. AIAA Journal, 1991, 29(9):1353-1354.
[6] 叶舒然, 张珍, 王一伟, 等. 基于卷积神经网络的深度学习流场特征识别及应用进展[J]. 航空学报, 2021, 42(4):524736. YE S R, ZHANG Z, WANG Y W, et al. Progress in deep convolutional neural network based flow field recognition and its applications[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524736(in Chinese).
[7] 寇家庆, 张伟伟, 高传强. 基于POD和DMD方法的跨声速抖振模态分析[J]. 航空学报, 2016, 37(9):2679-2689. KOU J Q, ZHANG W W, GAO C Q. Modal analysis of transonic buffet based on POD and DMD method[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(9):2679-2689(in Chinese).
[8] 张洪军, 吕进. 多普勒全场测速技术的进展[J]. 力学进展, 2007, 37(3):428-442. ZHANG H J, LV J. The progress of the Doppler global velocimetry[J]. Advances in Mechanics, 2007, 37(3):428-442(in Chinese).
[9] HUNT J M. A three-dimensional particle tracking velocimetry system for the evaluation of large eddy simulation turbulence models[D]. Seattle:University of Washington, 2016:21-52.
[10] 王怡星, 韩仁坤, 刘子扬, 等. 流体力学深度学习建模技术研究进展[J]. 航空学报, 2021, 42(4):524779. WANG Y X, HAN R K, LIU Z Y, et al. Progress of deep learning modeling technology for fluid mechanics[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524779(in Chinese).
[11] 任峰, 高传强, 唐辉. 机器学习在流动控制领域的应用及发展趋势[J]. 航空学报, 2021, 42(4):524686. REN F, GAO C Q, TANG H. Machine learning for flow control:Applications and development trends[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524686(in Chinese).
[12] LING J L, KURZAWSKI A, TEMPLETON J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance[J]. Journal of Fluid Mechanics, 2016, 807:155-166.
[13] MAULIK R, SAN O, JACOB J D, et al. Sub-grid scale model classification and blending through deep learning[J]. Journal of Fluid Mechanics, 2019, 870:784-812.
[14] REN F, WANG C L, TANG H. Active control of vortex-induced vibration of a circular cylinder using machine learning[J]. Physics of Fluids, 2019, 31(9):093601.
[15] HUANG J Q, LIU H C, CAI W W. Online in situ prediction of 3-D flame evolution from its history 2-D projections via deep learning[J]. Journal of Fluid Mechanics, 2019, 875:R2.
[16] MURATA T, FUKAMI K, FUKAGATA K. Nonlinear mode decomposition with convolutional neural networks for fluid dynamics[J]. Journal of Fluid Mechanics, 2020, 882:A13.
[17] OMATA N, SHIRAYAMA S. A novel method of low-dimensional representation for temporal behavior of flow fields using deep autoencoder[J]. AIP Advances, 2019, 9(1):015006.
[18] FUKAMI K, NAKAMURA T, FUKAGATA K. Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data[DB/OL]. arXiv preprint:2006.06977, 2020.
[19] 战庆亮, 葛耀君, 白春锦. 基于尾流时程目标识别的流场参数选择研究[J]. 力学学报, 2021, 53(10):2692-2702. ZHAN Q L, GE Y J, BAI C J. Study on flow field parameters of wake time history target recognition[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(10):2692-2702(in Chinese).
[20] 战庆亮, 葛耀君, 白春锦. 流场特征识别的无量纲时程深度学习方法[J]. 工程力学, (2021-11-18)[2021-12-02]. http://engineeringmechanics.cn/cn/article/doi/10.6052/j.issn.1000-4750.2021.08.0638. ZHANQ L, GE Y J, BAI C J. Deep learning for flow feature recognition based on dimensionless time history[J]. Engineering Mechanics, (2021-11-18)[2021-1202]. http://engineeringmechanics.cn/cn/article/doi/10.6052/j.issn.1000-4750.2021.08.0638(in Chinese).
[21] MUELLER T J, DELAURIER J D. Aerodynamics of small vehicles[J]. Annual Review of Fluid Mechanics, 2003, 35:89-111.
[22] 战庆亮, 周志勇, 葛耀君. Re=3900圆柱绕流的三维大涡模拟[J]. 哈尔滨工业大学学报, 2015, 47(12):75-79. ZHAN Q L, ZHOU Z Y, GE Y J. 3-Dimensional large eddy simulation of circular cylinder at Re=3900[J]. Journal of Harbin Institute of Technology, 2015, 47(12):75-79(in Chinese).
[23] 王庶. 低雷诺数下NACA 0012翼型空气动力学特性[D]. 北京:北京大学, 2010. WANG S. Aerodynamic characteristics of NACA 0012 airfoil at low Reynolds number[D]. Peking:Peking University, 2010(in Chinese).
[24] 吴鋆, 王晋军, 李天. NACA0012翼型低雷诺数绕流的实验研究[J]. 实验流体力学, 2013, 27(6):32-38. WU J, WANG J J, LI T. Experimental investigation on low Reynolds number behavior of NACA0012 airfoil[J]. Journal of Experiments in Fluid Mechanics, 2013, 27(6):32-38(in Chinese).

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献