Aerodynamic modeling of “Neural”-Fly for fixed-wing aircraft considering strong wind interference

ZHOU Xiaoyu; HUANG Jiangtao; ZHANG Sheng; LIU Gang

doi:10.7638/kqdlxxb-2023.0087

ACTA AERODYNAMICA SINICA > 2024 > 42(3): 92-101. > DOI: 10.7638/kqdlxxb-2023.0087

ZHOU X Y, HUANG J T, ZHANG S, et al. Aerodynamic modeling of “Neural”-Fly for fixed-wing aircraft considering strong wind interference[J]. Acta Aerodynamica Sinica, 2024, 42(3): 92−101. DOI: 10.7638/kqdlxxb-2023.0087

Citation:

PDF (4854 KB)

Aerodynamic modeling of “Neural”-Fly for fixed-wing aircraft considering strong wind interference

1.
Aerospace Technology Research Institute, China Aerodynamics Research and Development Center, Mianyang　621000, China
2.
China Aerodynamics Research and Development Center, Mianyang　621000, China

More Information

Received Date: May 31, 2023
Revised Date: July 16, 2023
Accepted Date: July 26, 2023
Available Online: August 14, 2023
Published Date: August 15, 2023

Graphical Abstract

Abstract

Abstract

The strong and unsteady wind imposes severe challenges to the safe flight and aerodynamic prediction of the fixed-wing aircraft. Traditional aerodynamic models established in the wind-oriented coordinate system have a clear physical meaning but cannot be readily applied to unsteady windy environments. This paper proposes an innovative "neural"-fly aerodynamic modeling method based on deep meta-learning to accurately predict the aerodynamic forces and moments online for fixed-wing aircraft subjected to strong and unsteady wind. Based on variables in a coordinate system relative to the ground, this method decomposes the aerodynamic forces and moments into the sum of polynomial multiplication and constructs the common aerodynamic base functions by a three-step deep meta-learning algorithm using the Generative Adversarial Network. The application of the method for the fixed-wing aircraft F-18 demonstrates that the method can accurately predict the aerodynamic forces and moments under unknown wind conditions, laying a good foundation for real-time aerodynamic modeling.
- fixed-wing aircraft,
- aerodynamic modeling,
- neural-fly,
- generative adversarial network,
- generic base

FullText(HTML)

References (22)

References

[1]	QU Y H, ZHANG Y T, ZHANG Y M. Optimal flight path planning for UAVs in 3-D threat environment[C]//2014 International Conference on Unmanned Aircraft Systems (ICUAS), Orlando, FL, USA. IEEE, 2014: 149-155. doi: 10.1109/ICUAS.2014.6842250
[2]	屈耀红, 于丽丽, 周迎, 等. 小型固定翼无人机多步长在线风场估计[J]. 西北工业大学学报, 2015, 33(5)750-756 doi: 10.3969/j.issn.1000-2758.2015.05.008 QU Y H, YU L L, ZHOU Y, et al. Multi? Step wind field estimation online of small Fixed? Wing UAVs[J]. Journal of Northwestern Polytechnical University, 2015, 33(5)750-756. DOI: 10.3969/j.issn.1000-2758.2015.05.008(in Chinese)
[3]	O’CONNELL M, SHI G Y, SHI X C, et al. Neural-Fly enables rapid learning for agile flight in strong winds[J]. Science Robotics, 2022, 7(66): eabm6597. DOI: 10.1126/scirobotics.abm6597
[4]	ANDERSON J R, 著. 计算流体力学入门[M]. 姚朝晖, 周强, 编译. 北京: 清华大学出版社, 2010.
[5]	VENTURA DIAZ P, YOON S. High-fidelity computational aerodynamics of multi-rotor unmanned aerial vehicles[C]//2018 AIAA Aerospace Sciences Meeting, Kissimmee, Florida. Reston, Virginia: AIAA, 2018. doi: 10.2514/6.2018-1266
[6]	陈文卓. 基于深度神经网络的气动数据建模方法研究[D]. 成都: 电子科技大学, 2021.
[7]	龚正, 沈宏良. 非定常气动力的结构自适应神经网络建模方法[J]. 飞行力学, 2007, 25(4): 13-16. DOI: 10.3969/j.issn.1002-0853.2007.04.004(in Chinese) GONG Z, SHEN H L. Structure self-adapting ANN method in modeling of unsteady aerodynamics[J]. Flight Dynamics, 2007, 25(4): 13-16. doi: 10.3969/j.issn.1002-0853.2007.04.004
[8]	FARRELL W, KINZEL M. Modeling UAVs using CFD and machine learning methods[C]//AIAA SCITECH 2022 Forum, San Diego, CA & Virtual. Reston, Virginia: AIAA, 2022. doi: 10.2514/6.2022-2534
[9]	LI K, KOU J Q, ZHANG W W. Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple Mach numbers[J]. Nonlinear Dynamics, 2019, 96(3): 2157-2177. DOI: 10.1007/s11071-019-04915-9
[10]	陈海, 钱炜祺, 何磊. 基于深度学习的翼型气动系数预测[J]. 空气动力学学报, 2018, 36(2)294-299. DOI: 10.7638/kqdlxxb-2017.0098(in Chinese) CHEN H, QIAN W Q, HE L. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2)294-299. doi: 10.7638/kqdlxxb-2017.0098
[11]	付军泉, 史志伟, 陈坤, 等. 基于EKF的实时循环神经网络在非定常气动力建模中的应用[J]. 空气动力学学报, 2018, 36(4): 658-663. DOI: 10.7638/kqdlxxb-2016.0131(in Chinese) FU J Q, SHI Z W, CHEN K, et al. Applications of real-time recurrent neural network based on extended Kalman filter in unsteady aerodynamics modeling[J]. Acta Aerodynamica Sinica, 2018, 36(4): 658-663. doi: 10.7638/kqdlxxb-2016.0131
[12]	王超, 王方剑, 王贵东, 等. 飞行器大攻角非定常气动特性神经网络建模[J]. 气体物理, 2020, 5(4)11-20DOI: 10.19527/j.cnki.2096-1642.0792(in Chinese) WANG C, WANG F J, WANG G D, et al. Artificial neural network modeling of unsteady aerodynamic characteristics of aircraft at high attack angle[J]. Physics of Gases, 2020, 5(4)11-20. doi: 10.19527/j.cnki.2096-1642.0792
[13]	MORELLI E A. Real-time global nonlinear aerodynamic modeling for learn-to-fly[C]//AIAA Atmospheric Flight Mechanics Conference, San Diego, California, USA. Reston, Virginia: AIAA, 2016. doi: 10.2514/6.2016-2010
[14]	HEIM E H, VIKEN E, BRANDON J M, et al. NASA's learn-to-fly project overview[C]//2018 Atmospheric Flight Mechanics Conference, Atlanta, Georgia. Reston, Virginia: AIAA, 2018. doi: 10.2514/6.2018-3307
[15]	RIDDICK S E. An overview of NASA's learn-to-fly technology development[C]// AIAA Scitech 2020 Forum, Orlando, FL, 6, 2020. https://ntrs.nasa.gov/api/citations/20200002805/downloads/20200002805.pdf doi: 10.2514/6.2020-0760
[16]	周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
[17]	马柳. 基于生成式对抗网络的空气动力学数据建模研究[D]. 成都: 电子科技大学, 2020.
[18]	田青, 朱雅喃, 马闯. 基于深度学习的域适应方法综述[J]. 数据采集与处理, 2022, 37(3): 512-541. DOI: 10.16337/j.1004-9037.2022.03.004(in Chinese) TIAN Q, ZHU Y N, MA C. Review on domain adaptation methods based on deep learning[J]. Journal of Data Acquisition & Processing, 2022, 37(3): 512-541. doi: 10.16337/j.1004-9037.2022.03.004
[19]	GANIN Y, LEMPITSKY V. Unsupervised domain adaptation by backpropagation[C]//32nd International Conference on International Conference on Machine Learning - Volume 37, New York: ACM, 2015: 1180-1189. doi: 10.5555/3045118.3045244
[20]	GANIN Y, USTINOVA E, AJAKAN H, et al. Domain-adversarial training of neural networks[J]. Journal of Machine Learning Research, 2016, 17(1): 2096–2030.https://dl.acm.org/doi/pdf/10.5555/2946645.2946704 doi: 10.5555/2946645.2946704
[21]	SHI G Y, HÖNIG W, SHI X C, et al. Neural-Swarm2: planning and control of heterogeneous multirotor swarms using learned interactions[J]. IEEE Transactions on Robotics, 2022, 38(2): 1063-1079. DOI: 10.1109/TRO.2021.3098436
[22]	BOWERS A H, PAHLE J W, WILSON R J, ET al. An overview of the nasa f-18 high alpha research vehicle[R]. NASA-TM-4772, 1996. https://ntrs.nasa.gov/api/citations/19970003009/downloads/19970003009.pdf

Cited By

Get Citation

PDF

XML

Article views (119) PDF downloads (37)

Turn off MathJax

Article Contents

Abstract

References

Aerodynamic modeling of “Neural”-Fly for fixed-wing aircraft considering strong wind interference

Abstract

References

Catalog

Export File

Citation

Format

Content