Electronics and Electrical Engineering and Control

A real⁃time in⁃flight wind estimation and prediction method based on deep learning

  • Rongsheng ZHANG ,
  • Yansheng WU ,
  • Xudong QIN ,
  • Puzhuo ZHANG
Expand
  • 1.Beijing Institute of Astronautical Systems Engineering,Beijing 100076,China
    2.China Aerospace Science and Technology Corporation,Beijing 100048,China
E-mail: WuYSh_CASC@163.com

Received date: 2022-07-28

  Revised date: 2022-09-28

  Accepted date: 2022-10-25

  Online published: 2022-11-04

Abstract

The in-flight wind of launch vehicles is difficult to measure during flight, and the prediction error is great occasionally. In this paper, a real-time in-flight wind estimation and prediction method is proposed based on deep learning. By computing the spatial and temporal distribution of actual measurement data of in-flight wind in past 15 years, we acquire the rule that the wind velocity is higher and the wind direction is concentrated at 270° in winter, which is taken as the basis of sample set generation and wind prediction. Response of flight state to in-flight wind is obtained. Based on the obtained result, a deep neural network is designed to estimate the in-flight wind via the launch vehicle’s flight state. Next, a wind prediction method is proposed based on spatial and temporal distribution of in-flight wind. The rationality of wind prediction via deep learning is also given. We carry out a flight experiment on launch vehicle to verify the accuracy and real-timeliness of the proposed method. The proposed method is feasible for engineering implementation.

Cite this article

Rongsheng ZHANG , Yansheng WU , Xudong QIN , Puzhuo ZHANG . A real⁃time in⁃flight wind estimation and prediction method based on deep learning[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023 , 44(13) : 327860 -327860 . DOI: 10.7527/S1000-6893.2022.27860

References

1 JOHNSON D L, VAUGHAN W W. The wind environment interactions relative to launch vehicle design[J]. Journal of Aerospace Technology and Management2020(12): 1-13.
2 LESTER H C, TOLEFSON H B. A study of launch-vehicle responses to detailed characteristics of the wind profile[J]. Journal of Applied Meteorology19643(5): 491-498.
3 王建明, 林娜, 张博戎. 某大型低温火箭高空风载荷分析[J]. 导弹与航天运载技术2021(5): 137-141.
  WANG J M, LIN N, ZHANG B R. Analysis on flight wind-load for large cryogenic rocket[J]. Missiles and Space Vehicles2021(5): 137-141 (in Chinese).
4 余梦伦. CZ-2E火箭高空风弹道修正[J]. 导弹与航天运载技术2001(1): 9-15.
  YU M L. CZ-2E ballistic correction for high altitude wind[J]. Missiles and Space Vehicles2001(1): 9-15 (in Chinese).
5 程胡华, 李娟, 肖云清, 等. 风偏差对火箭最大气动载荷精度的影响[J]. 北京航空航天大学学报202147(10): 2034-2042.
  CHENG H H, LI J, XIAO Y Q, et al. Influence of wind deviation on rocket maximum aerodynamic load accuracy[J]. Journal of Beijing University of Aeronautics and Astronautics202147(10): 2034-2042 (in Chinese).
6 马林, 昝兴海, 张琦. 考虑随机误差传递的高空风计算方法[J]. 兵器装备工程学报201637(8): 173-176.
  MA L, ZAN X H, ZHANG Q. Calculation method of the upper-air wind considering random error transfer[J]. Journal of Ordnance Equipment Engineering201637(8): 173-176 (in Chinese).
7 唐学海, 刘伯阳. 一种基于椭球分层模型的电波折射修正算法[J]. 电子与信息学报201537(6): 1507-1512.
  TANG X H, LIU B Y. Radio wave refraction correction algorithm based on ellipsoid stratification atmospheric structure model[J]. Journal of Electronics & Information Technology201537(6): 1507-1512 (in Chinese).
8 FU B S, QI H, XU J T, et al. Attitude control in ascent phase of missile considering actuator non-linearity and wind disturbance[J]. Applied Sciences20199(23): 5113.
9 GAO Z X, FU J. Robust LPV modeling and control of aircraft flying through wind disturbance[J]. Chinese Journal of Aeronautics201932(7): 1588-1602.
10 王景国, 卞韩城, 陈学林, 等. CZ-2F火箭整流罩残骸落点预报方法研究[J]. 载人航天201420(5): 457-460.
  WANG J G, BIAN H C, CHEN X L, et al. Research on impact point prediction methods of CZ-2F rocket fairing debris[J]. Manned Spaceflight201420(5): 457-460 (in Chinese).
11 LEGRAND K, PUECHMOREL S, DELAHAYE D, et al. Robust aircraft optimal trajectory in the presence of wind[J]. IEEE Aerospace and Electronic Systems Magazine201833(11): 30-38.
12 HUI Y L, NAN Y, CHEN S D, et al. Dynamic attack zone of air-to-air missile after being launched in random wind field[J]. Chinese Journal of Aeronautics201528(5): 1519-1528.
13 李争学, 贺元军, 张广春, 等. 风干扰引起的飞行器附加攻角和附加侧滑角计算方法[J]. 导弹与航天运载技术2016(5): 66-73.
  LI Z X, HE Y J, ZHANG G C, et al. Calculation of the additional attack angle and the additional sideslip angle of craft caused by wind disturbance[J]. Missiles and Space Vehicles2016(5): 66-73 (in Chinese).
14 杨小龙. 飞行器纵向风扰动的辨识方法研究[J]. 系统工程理论与实践199616(9): 81-84.
  YANG X L. Longitudinal wind disturbance identification for a flight vehicle[J]. Systems Engineering-Theory & Practice199616(9): 81-84 (in Chinese).
15 孙友, 杨广慧. 大气层内飞行器风速在线辨识方法[J]. 航天控制201230(6): 3-6.
  SUN Y, YANG G H. A method of on-line wind identification in the field of guided aerocraft[J]. Aerospace Control201230(6): 3-6 (in Chinese).
16 李洪. 智慧火箭发展路线思考[J]. 宇航总体技术20171(1): 1-7.
  LI H. The developing roadmap of intelligent launch vehicle[J]. Astronautical Systems Engineering Technology20171(1): 1-7 (in Chinese).
17 CHAI R Q, TSOURDOS A, SAVVARIS A, et al. Six-DOF spacecraft optimal trajectory planning and real-time attitude control: A deep neural network-based approach[J]. IEEE Transactions on Neural Networks and Learning Systems202031(11): 5005-5013.
18 张荣升, 吴燕生, 秦旭东, 等. 运载火箭推力下降故障下的在线弹道重构方法[J]. 南京航空航天大学学报202153(S1): 25-31.
  ZHANG R S, WU Y S, QIN X D, et al. Online trajectory reconstruction of launch vehicle with thrust drop faults[J]. Journal of Nanjing University of Aeronautics & Astronautics202153(S1): 25-31 (in Chinese).
19 ZHANG R S, ZHANG P Z, QIN X D, et al. Real-time guidance for launch vehicles under thrust drop fault via deep learning[C]∥ 2021 China Automation Congress (CAC). Piscataway: IEEE Press, 2022: 5520-5525.
20 高晓光, 李新宇, 岳勐琪, 等. 基于深度学习的地空导弹发射区拟合算法[J]. 航空学报201940(9): 322858.
  GAO X G, LI X Y, YUE M Q, et al. Fitting algorithm of ground-to-air missile launching area based on deep learning[J]. Acta Aeronautica et Astronautica Sinica201940(9): 322858 (in Chinese).
21 ZHANG C Y, JI R P, LIANG Y, et al. LSTM-based boost-phase ballistic missile tracking[C]∥ 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). Piscataway: IEEE Press, 2021: 931-936.
22 KIM J, LIM M C, PARK S S, et al. Ballistic object trajectory and launch point estimation from radar measurements using long-short term memory networks[C]∥ 2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA). Piscataway: IEEE Press, 2019: 26-31.
23 HUANG L M, CHEN W C. Deep learning midcourse guidance for interceptor missile[C]∥2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Piscataway: IEEE Press, 2019: 1129-1134.
24 汪韧, 惠俊鹏, 俞启东, 等. 基于LSTM模型的飞行器智能制导技术研究[J]. 力学学报202153(7): 2047-2057.
  WANG R, HUI J P, YU Q D, et al. Research of LSTM model-based intelligent guidance of flight aircraft[J]. Chinese Journal of Theoretical and Applied Mechanics202153(7): 2047-2057 (in Chinese).
25 王因翰, 范世鹏, 吴广, 等. 基于GRU的敌方拦截弹制导律快速辨识方法[J]. 航空学报202243(2): 325024.
  WANG Y H, FAN S P, WU G, et al. Fast guidance law identification approach for incoming missile based on GRU network[J]. Acta Aeronautica et Astronautica Sinica202243(2): 325024 (in Chinese).
26 JIAO R H, PENG K X, DONG J. Remaining useful life prediction for a roller in a hot strip mill based on deep recurrent neural networks[J]. IEEE/CAA Journal of Automatica Sinica20218(7): 1345-1354.
27 康守强, 周月, 王玉静, 等. 基于改进SAE和双向LSTM的滚动轴承RUL预测方法[J]. 自动化学报202248(9): 2327-2336.
  KANG S Q, ZHOU Y, WANG Y J, et al. RUL prediction method of a rolling bearing based on improved SAE and Bi-LSTM[J]. Acta Automatica Sinica202248(9): 2327-2336 (in Chinese).
28 任俊超, 刘丁, 万银. 基于混合集成建模的硅单晶直径自适应非线性预测控制[J]. 自动化学报202046(5): 1004-1016.
  REN J C, LIU D, WAN Y. Hybrid integrated modeling based adaptive nonlinear predictive control of silicon single crystal diameter[J]. Acta Automatica Sinica202046(5): 1004-1016 (in Chinese).
29 HOU X R, WANG K, ZHONG C, et al. ST-trader: A spatial-temporal deep neural network for modeling stock market movement[J]. IEEE/CAA Journal of Automatica Sinica20218(5): 1015-1024.
30 SUN L H, YANG B Q, MA J. A trajectory prediction algorithm for HFVs based on LSTM[C]∥ 2021 40th Chinese Control Conference (CCC). Piscataway: IEEE Press, 2021: 7927-7931.
31 SATIR A S, DEMIR U, SEVER G G, et al. Nonlinear model based guidance with deep learning based target trajectory prediction against aerial agile attack patterns[C]∥ 2021 American Control Conference (ACC). Piscataway: IEEE Press, 2021: 2607-2612.
32 赵世军, 高太长, 刘涛, 等. 基于北斗一号的高空风探测方法研究[J]. 气象科技201240(2): 170-174.
  ZHAO S J, GAO T C, LIU T, et al. Upper wind sounding method based on Beidou-Ⅰ navigation system[J]. Meteorological Science and Technology201240(2): 170-174 (in Chinese).
33 徐延万. 液体弹道导弹与运载火箭系列控制系统(上)[M]. 北京: 中国宇航出版社, 1989: 147-149.
  XU Y W. Control system design of liquid propellant ballistic missile and launch vehicle(I) [M]. Beijing: China Astronautic Publishing House, 1989: 147-149 (in Chinese).
Outlines

/