基于卷积神经网络的超声速后掠翼横流驻波转捩预测方法

doi:10.7527/S1000-6893.2025.32012

Abstract

Abstract:

The typical large sweep angle wing laminar flow design of supersonic aircraft faces the problem of boundary layer transition induced by crossflow instability. The standard e ^N method based on linear stability theory involves solving eigenvalue problems and requires frequent interactive operations， which cannot meet the needs of fast transition prediction and iterative design. To address the above difficulties， a linear stability analysis is conducted on the similarity solution of the three-dimensional compressible boundary layer to generate a large number of eigenvalue samples. The powerful spatial feature extraction ability of convolutional layers is utilized to achieve automatic recognition of the input baseflow profile features， and together with the flow parameters and disturbance parameters at the outer edge of the boundary layer， they are mapped to eigenvalue or local growth rates through fully-connected layers， thus constructing an e ^N convolutional neural network model suitable for predicting the instability and transition of supersonic stationary crossflow waves. By conducting stability analysis on a series of variable operating conditions and geometries of infinite swept wings， the neural network model’s prediction results of disturbance amplification factors are in good agreement with the standard e ^N method. Finally， based on the stability analysis and flight test data of a supersonic swept wing crossflow transition model developed by NASA， the neural network model’s ability to predict transition in real three-dimensional configurations was verified. The results showed that this model has strong generalization ability and ensures high accuracy， making it a relatively simple and reliable modeling method.

Key words: supersonic swept-wing, boundary layer transition, crossflow instability, linear stability theory, e ^N method, convolutional neural networks

CLC Number:

V211

Jiakun FAN, Junqiang AI, Ningjuan DONG, Jiakuan XU, Lei QIAO, Junqiang BAI. Stationary crossflow induced transition prediction method for supersonic swept-wing based on convolutional neural networks[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 532012.

Figures/Tables 24

Fig.1

Fig.2

Table 1

Dimensionless method

无量纲化前	无量纲化后
$u$	$u ˜ = u / w m a x$
$w$	$w ˜ = w / w m a x$
$T$	$T ˜ = T / T e$
$β r$	$β ˜ r = β r δ C F$
$α$	$α ˜ = α ˜ δ C F$

Table 1

Fig.3

Table 2

Prediction results of test set

测试集类型	$M a e$	$β H$	$χ e / (°)$	Error/%
内插测试1	1.5	0.25	30	4.70
内插测试2	2.5	0.40	60	3.65
外插测试1	2.0	1.00	45	11.5
外插测试2	3.5	0.10	45	6.52

Table 2

Fig.4

Fig.5

Fig.6

Fig.7

Table 3

Test examples

算例类型	马赫数	雷诺数/ $(107 ⋅ m - 1)$	后掠角/（°）	翼型/相对厚度/%
基准	2.0	$1.0$	65	15
变马赫数	1.2， 2.8	$1.0$	65	15
变雷诺数	2.0	0.5， 1.5	65	15
变后掠角	2.0	1.0	45，55	15
变翼型	2.0	1.0	65	10，20

Table 3

Fig.8

Fig.9

Fig.10

Fig.11

Table 4

Fig.12

Table 5

Test cases

序号	马赫数	海拔高度/km	温度/K	雷诺数/ $(106 m - 1)$
1	2.0	16.8	216.65	6.2
2	2.0	12.7	216.65	11.5
3	1.98	13.7	216.65	10.9

Table 5

Fig.13

Fig.14

Fig.15

Fig.16

Fig.17

Fig.18

Fig.19

References 43

[1]	DARREN H. Commercial market outlook： 2024-2043［R］. Chicago： Boeing Commercial Airplanes， 2024.
[2]	丁玉临，韩忠华，乔建领，等. 超声速民机总体气动布局设计关键技术研究进展［J］. 航空学报， 2023， 44（2）： 626310.
	DING Y L， HAN Z H， QIAO J L， et al. Research progress in key technologies for conceptual-aerodynamic configuration design of supersonic transport aircraft［J］. Acta Aeronautica et Astronautica Sinica， 2023， 44（2）： 626310 （in Chinese）.
[3]	MORGENSTERN J， NORSTRUD N， STELMACK M， et al. Advanced concept studies for supersonic commercial transports entering service in 2030-35 （N+3）［C］∥28th AIAA Applied Aerodynamics Conference. Reston： AIAA， 2010.
[4]	LIEBHARDT B， LÜTJENS K， UENO A， et al. JAXA’s S4 supersonic low-boom airliner-A collaborative study on aircraft design， sonic boom simulation， and market prospects［C］∥AIAA Aviation 2020 Forum. Reston： AIAA， 2020.
[5]	韩忠华，乔建领，丁玉临，等. 新一代环保型超声速客机气动相关关键技术与研究进展［J］. 空气动力学学报， 2019， 37（4）： 620-635.
	HAN Z H， QIAO J L， DING Y L， et al. Key technologies for next-generation environmentally-friendly supersonic transport aircraft： A review of recent progress［J］. Acta Aerodynamica Sinica， 2019， 37（4）： 620-635 （in Chinese）.
[6]	聂晗，宋文萍，韩忠华，等. 面向超声速民机层流机翼设计的转捩预测方法［J］. 航空学报， 2022， 43（11）： 526342.
	NIE H， SONG W P， HAN Z H， et al. Automatic transition prediction for natural-laminar-flow wing design of supersonic transports［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（11）： 526342 （in Chinese）.
[7]	袁吉森，孙爵，李玲玉，等. 超声速飞机层流布局设计与评估技术进展［J］. 航空学报， 2022， 43（11）： 526316.
	YUAN J S， SUN J， LI L Y， et al. Progress of supersonic aircraft laminar flow layout design and evaluation technologies［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（11）： 526316 （in Chinese）.
[8]	ARNAL D， JUILLEN J C， RENEAUX J， et al. Effect of wall suction on leading edge contamination［J］. Aerospace Science and Technology， 1997， 1（8）： 505-517.
[9]	TANI I， AIHARA Y. Görtler vortices and boundary-layer transition［J］. Zeitschrift Für Angewandte Mathematik und Physik ZAMP， 1969， 20（5）： 609-618.
[10]	RESHOTKO E. Boundary-layer stability and transition［J］. Annual Review of Fluid Mechanics， 1976， 8： 311-349.
[11]	SARIC W， REED H. Crossflow instabilities-theory & technology［C］∥41st Aerospace Sciences Meeting and Exhibit. Reston： AIAA， 2003.
[12]	于晟浩，袁吉森，高亮杰，等. 三维超声速后掠翼转捩的e^N-神经网络模型预测［J］. 力学学报， 2023， 55（6）： 1236-1246.
	YU S H， YUAN J S， GAO L J， et al. e^N-neural network model for predicting transition of 3-d supersonic swept wing［J］. Chinese Journal of Theoretical and Applied Mechanics， 2023， 55（6）： 1236-1246 （in Chinese）.
[13]	周恒，赵耕夫. 流动稳定性［M］. 北京：国防工业出版社， 2004： 77-78.
	ZHOU H， ZHAO G F. Hydrodynamic stability［M］. Beijing： National Defense Industry Press， 2004： 77-78 （in Chinese）.
[14]	SARIC W S， REED H L， KERSCHEN E J. Boundary-layer receptivity to freestream disturbances［J］. Annual Review of Fluid Mechanics， 2002， 34（34）： 291-319.
[15]	SARIC W， REED H， WHITE E. Stability and transition of three-dimensional boundary layers［J］. Annual Review of Fluid Mechanics， 2003， 35（1）： 413-440.
[16]	李学良，李创创，苏伟，等. 分布式粗糙元对高超声速边界层不稳定性的影响试验［J］. 航空学报， 2024， 45（2）： 128627.
	LI X L， LI C C， SU W， et al. Experiment of influence of distributed roughness elements on hypersonic boundary layer instability［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（2）： 128627 （in Chinese）.
[17]	张定金，雷娟棉，赵瑞. 壁温对高超声速裙锥边界层感受性的影响规律［J］. 航空学报， 2024， 45（24）： 156-172.
	ZHANG D J， LEI J M， ZHAO R. Influence of wall temperature on receptivity of hypersonic flare cone boundary layer［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（24）： 156-172 （in Chinese）.
[18]	BIPPES H， NITSCHKE-KOWSKY P. Experimental study of instability modes in a three-dimensional boundary layer［C］∥19th AIAA， Fluid Dynamics， Plasma Dynamics， and Lasers Conference. Reston： AIAA， 1987.
[19]	MOIN P， MAHESH K. DIRECT numerical simulation： A tool in turbulence research［J］. Annual Review of Fluid Mechanics， 1998， 30： 539-578.
[20]	HUAI X， JOSLIN R D， PIOMELLI U. Large-eddy simulation of transition to turbulence in boundary layers［J］. Theoretical and Computational Fluid Dynamics， 1997， 9（2）： 149-163.
[21]	DI PASQUALE D， RONA A， GARRETT S. A selective review of transition modelling for CFD［C］∥39th AIAA Fluid Dynamics Conference. Reston： AIAA， 2009.
[22]	VAN I J L. A suggested semi-empirical method for the calculation of the boundary layer transition region： UTH-74 ［R］. Delft： Delft University of Technology， 1956.
[23]	KRUMBEIN A， KRIMMELBEIN N， GRABE C. Streamline-based transition prediction techniques in an unstructured computational fluid dynamics code［J］. AIAA Journal， 2017， 55（5）： 1548-1564.
[24]	STURDZA P. An aerodynamic design method for supersonic natural laminar flow aircraft［M］. Palo Alto： Stanford University， 2004：47.
[25]	ARNAL D. Transition prediction in transonic flow［M］∥ Symposium Transsonicum Ⅲ. Berlin： Springer Berlin Heidelberg， 1989： 253-262.
[26]	DRELA M， GILES M B. Viscous-inviscid analysis of transonic and low Reynolds number airfoils［J］. AIAA Journal， 1987， 25（10）： 1347-1355.
[27]	CODER J G， MAUGHMER M D. Computational fluid dynamics compatible transition modeling using an amplification factor transport equation［J］. AIAA Journal， 2014， 52（11）： 2506-2512.
[28]	XU J K， HAN X， QIAO L， et al. Fully local amplification factor transport equation for stationary crossflow instabilities［J］. AIAA Journal， 2019， 57（7）： 2682-2693.
[29]	XU J K， QIAO L， BAI J Q. Improved local amplification factor transport equation for stationary crossflow instability in subsonic and transonic flows［J］. Chinese Journal of Aeronautics， 2020， 33（12）： 3073-3081.
[30]	WANG Y X， XU J K， QIAO L， et al. Improved amplification factor transport transition model for transonic boundary layers［J］. AIAA Journal， 2023， 61（9）： 3866-3882.
[31]	唐志共，朱林阳，向星皓，等. 智能空气动力学若干研究进展及展望［J］. 空气动力学学报， 2023， 41（7）： 1-35.
	TANG Z G， ZHU L Y， XIANG X H， et al. Some research progress and prospect of intelligent aerodynamics［J］. Acta Aerodynamica Sinica， 2023， 41（7）： 1-35 （in Chinese）.
[32]	安凯，黄伟，王振国，等. AI驱动高速飞行器多学科发展知识图谱分析［J］. 航空学报， 2024， 45（）： 48-66.
	AN K， HUANG W， WANG Z G， et al. Knowledge map analysis of multidisciplinary development of AI-driven high-speed aircraft［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（Sup 1）： 48-66 （in Chinese）.
[33]	ZAFAR M I， XIAO H， CHOUDHARI M M， et al. Convolutional neural network for transition modeling based on linear stability theory［J］. Physical Review Fluids， 2020， 5（11）： 113903.
[34]	PAREDES P， VENKATACHARI B， CHOUDHARI M M， et al. Toward a practical method for hypersonic transition prediction based on stability correlations［J］. AIAA Journal， 2020， 58（10）： 4475-4484.
[35]	CHANG C L. Development of physics-based transition models for unstructured-mesh CFD codes using deep learning models［C］∥AIAA Aviation 2021 Forum. Reston： AIAA， 2021.
[36]	SROKOWSKI A， ORSZAG S. Mass flow requirements for LFC wing design［C］∥Aircraft Systems and Technology Meeting. Reston： AIAA， 1977.
[37]	CEBECI T， STEWARTSON K. On stability and transition in three-dimensional flows［J］. AIAA Journal， 1980， 18（4）： 398-405.
[38]	MACK L M. Stability of three-dimensional boundary layers on swept wings at transonic speeds［C］∥Symposium Transsonicum III. Berlin： Springer Berlin Heidelberg， 1989： 209-223.
[39]	MACK L. On the stability of the boundary layer on a transonic swept wing［C］∥17th Aerospace Sciences Meeting. Reston： AIAA， 1979.
[40]	ARNAL D， CASALIS G， HOUDEVILLE R. Laminar-turbulent transition prediction in three-dimensional flows［J］. Progress in Aerospace Sciences， 2000， 36（2）： 173-191.
[41]	QIAO L， XU J K， BAI J Q， et al. Fully local transition closure model for hypersonic boundary layers considering crossflow effects［J］. AIAA Journal， 2021， 59（5）： 1692-1706.
[42]	OKEWU E， MISRA S， LIUS F S. Parameter tuning using adaptive moment estimation in deep learning neural networks［C］∥Computational Science and Its Applications-ICCSA 2020. Cham： Springer International Publishing， 2020： 261-272.
[43]	OWENS L R， BEELER G， KING R， et al. Supersonic traveling crossflow wave characteristics in ground and flight tests［C］∥AIAA Scitech 2020 Forum. Reston： AIAA， 2020.

Stationary crossflow induced transition prediction method for supersonic swept-wing based on convolutional neural networks

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 24

References 43

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Xueliang LI, Chuangchuang LI, Yahan ZHANG, Wei SU, Jie WU. Effect of distributed ablation pattern on hypersonic boundary-layer instability with a flat plate [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(2): 130464-130464.
[2]	Xueliang LI, Chuangchuang LI, Wei SU, Jie WU. Experiment of influence of distributed roughness elements on hypersonic boundary layer instability [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(2): 128627-128627.
[3]	Qingdong MENG, Juanmian LEI, Ling ZHOU. Influence of transition characteristics and angle of attack of HyTRV based on transition model [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(18): 129855-129855.
[4]	Yuanhao HU, Yibo SONG, Jiahui LIU, Xiaoli ZHAO, Wenxiang DENG, Jian HU, Jianyong YAO. Fault diagnosis of electro-hydraulic proportional servo valves based on attention convolutional capsule networks [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(15): 630407-630407.
[5]	Hongkang LIU, Jianqiang CHEN, Xinghao XIANG, Yatian ZHAO. Transition prediction for HIAD with different Reynolds numbers by improved k-ω-γtransition model [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(6): 126868-126868.
[6]	Lei HE, Weiqi QIAN, Kangsheng DONG, Xian YI, Congcong CHAI. Aerodynamic characteristics modeling of iced airfoil based on convolution neural networks [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126434-126434.
[7]	LIU Qiang, TU Guohua, LUO Zhenbing, CHEN Jianqiang, ZHAO Rui, YUAN Xianxu. Progress in hypersonic boundary layer transition delay control [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(7): 25357-025357.
[8]	LI Qiang, WAN Bingbing, YANG Kai, ZHU Tao. Experimental research on characteristics of pressure and heat flux fluctuation in hypersonic cone boundary layer [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(2): 124956-124956.
[9]	NIE Han, SONG Wenping, HAN Zhonghua, CHEN Jianqiang, DUAN Maochang, WAN Bingbing. Automatic transition prediction for natural-laminar-flow wing design of supersonic transports [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(11): 526342-526342.
[10]	XU Jiakuan, WANG Yuxuan, ZHANG Yang, QIAO Lei, LIU Jianxin, BAI Junqiang. Progress in amplification factor transport models in subsonic and transonic boundary layers [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(11): 526734-526734.
[11]	WANG Hui, JIA Zikai, JIN Ren, LIN Defu, FAN Junfang, XU Chao. Cooperative object detection in UAV-based vision-guided docking [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(1): 324854-324854.
[12]	YANG Peng, TANG Zhigong, CHEN Jianqiang, YUAN Xianxu, CHEN Xi, DONG Siwei. Temporal evolution of wavepackets on the windward side of an inclined hypersonic cone under a flight condition [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(S1): 726367-726367.
[13]	LI Hongguang, YU Ruonan, DING Wenrui. Research development of small object traching based on deep learning [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(7): 24691-024691.
[14]	WANG Zelin, JI Ritian, HUI Xinyu, DING Chen, WANG Hui, BAI Junqiang. L-shaped directional heat transfer based on deep learning [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(6): 124242-124242.
[15]	CHEN Jianqiang, TU Guohua, WAN Bingbing, YUAN Xianxu, YANG Qiang, ZHUANG Yu, XIANG Xinghao. Characteristics of flow field and boundary-layer stability of HyTRV [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(6): 124317-124317.