Deck motion prediction and compensation technology based on BP neural network

被引：0
作者：
Zhao, Suo [1 ,2 ]
Lin, Li [2 ]
Li, Zhen [2 ]
Hou, Zhongxi [1 ]
机构：
[1] College of Aerospace Sciences, National University of Defense Technology, Changsha
[2] Shenyang Aircraft Design & Research Institute, Shenyang
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2024年 / 50卷 / 09期
关键词：
advance network; automatic carrier landing; BP neural network; deck motion compensation; deck motion prediction;
D O I：
10.13700/j.bh.1001-5965.2022.0743
中图分类号：
学科分类号：
摘要：
The impact of deck motion on the complete automatic landing success rate is taken into account during the landing procedure. Aiming at the asynchrony of the deck and the longitudinal height of the carrier-based aircraft caused by the delay in the response of the carrier-based aircraft, the deck motion prediction technology is used to forecast the motion parameters of the ship in the effective time in the future. A six-degree-of-freedom deck motion model based on sine wave combination is established, and a deck motion prediction model is established based on a back-propagation (BP) artificial neural network. A deck motion compensation model is developed in accordance with the advance network, and the landing guidance system is integrated to guarantee that the vector of the deck and the carrier aircraft are in synchronization. The aircraft motion model is established, and the feasibility of the deck motion prediction and compensation technology is verified through the simulation experiments. © 2024 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.
引用
收藏
页码：2772 / 2780
页数：8
相关论文
共 15 条
  • [1] WU H Z, LUO F P, SHI X C, Et al., Analysis on the status quo and development trend of automatic carrier landing technology, Aircraft Design, 40, 6, pp. 1-5, (2020)
  • [2] YANG Y D., Helicopter flight control, pp. 37-70, (2007)
  • [3] XU D S, LIU X Y, WANG L X., Influence of carrier motion on landing safety for carrier-based airplanes, Journal of Beijing University of Aeronautics and Astronautics, 37, 3, pp. 289-294, (2011)
  • [4] WANG K, XU M L, LI Y F, Et al., A robust learning model for deck motion prediction of aircraft carrier, Acta Automatica Sinica, 48, pp. 1-9, (2021)
  • [5] YANG L, XU D H., Aircraft carrier landing process simulation based on extremely short-term prediction of ship motion, Chinese Journal of Ship Research, 13, 4, pp. 99-103, (2018)
  • [6] LI X L, LV X H, YU J D, Et al., Neural network application on ship motion prediction, Proceedings of the International Conference on Intelligent Human-Machine Systems and Cybernetics, pp. 414-417, (2017)
  • [7] WANG Y C, ZHANG S Z, SUN N., Analysis on tracking algorithm of 6-DOF ship motion trajectory, Ship Science and Technology, 44, 8, pp. 56-59, (2022)
  • [8] RUMELHART D E, HINTON G E, WILLIAMS R J., Learning representations by back-propagating errors, Nature, 323, 6088, pp. 533-536, (1986)
  • [9] SHI G J, ZHANG Y, WANG Q L., Prediction technology for ship deck motion, Helicopter Technique, 4, pp. 20-24, (2020)
  • [10] WU P F, SHI Z S, WU Z H, Et al., An estimation and compensation method of deck motion for unmanned helicopter landing on ship, Electronics Optics & Control, 26, 12, pp. 22-27, (2019)
12