航空学报 > 2025, Vol. 46 Issue (13): 531317-531317   doi: 10.7527/S1000-6893.2024.31317

基于离线网络/在线辨识的舰载机自抗扰控制

闫明1, 王家兴2, 李贺琦2, 刘凯1()   

  1. 1.大连理工大学 力学与航空航天学院,大连 116024
    2.中国航空工业集团 沈阳飞机设计研究所 飞行控制部,沈阳 110035
  • 收稿日期:2024-09-30 修回日期:2025-01-02 接受日期:2025-02-21 出版日期:2025-02-26 发布日期:2025-02-25
  • 通讯作者: 刘凯 E-mail:carsonliu@dlut.edu.cn
  • 基金资助:
    装备预研教育部联合基金(8091B032223);国防基础科研项目(JCKY2022110C019)

Active disturbance rejection control of carrier-based aircraft based on offline network/online identification

Ming YAN1, Jiaxing WANG2, Heqi LI2, Kai LIU1()   

  1. 1.School of Mechanics and Aerospace Engineering,Dalian University of Technology,Dalian 116024,China
    2.Flight Control Department,Shenyang Aircraft Design Research Institute,AVIC,Shenyang 110035,China
  • Received:2024-09-30 Revised:2025-01-02 Accepted:2025-02-21 Online:2025-02-26 Published:2025-02-25
  • Contact: Kai LIU E-mail:carsonliu@dlut.edu.cn
  • Supported by:
    Ministry of Education Joint Fund for Equipment Pre-research(8091B032223);Defense Industrial Technology Development Program(JCKY2022110C019)

摘要:

针对舰载机复杂环境强不确定性条件下的高精度着舰控制问题,提出了一种基于离线神经网络/在线辨识的直接升力模式舰载机自抗扰控制方法。首先,参考美国“魔毯”控制系统并分析其关键技术机理,设计舰载机直接升力着舰自抗扰控制方法,通过扩展状态观测器对阵风扰动和系统不确定项带来的总扰动进行估计补偿。其次,依据构建的着舰控制工程性能指标评价准则,筛选最优控制参数,建立以飞行模型不确定性为输入,最优着舰控制参数为输出的神经网络映射关系。最后通过在线辨识高效优化自抗扰控制参数。仿真结果表明,文中所提的方法相比基线控制器具有更高的鲁棒性,能够有效提升舰载机在干扰条件下的高精度着舰性能。

关键词: 直接升力控制, 自抗扰控制, 神经网络, 魔毯, 在线辨识

Abstract:

To address the high-precision landing control problem of carrier-based aircraft under complex environment and strong uncertainty, this paper proposes a direct lift mode active disturbance rejection control method based on offline neural network/online identification. Firstly, referring to the American ‘Magic Carpet’ control system and analyzing its key technical mechanism, the direct lift landing active disturbance rejection control method of carrier-based aircraft is designed. The extended state observer is used to estimate and compensate the total disturbance caused by gust disturbance and system uncertainty. Secondly, according to the evaluation criteria of landing control engineering performance index, the optimal control parameters are selected, and the neural network mapping relationship with flight model uncertainty as input and optimal landing control parameters as output is established. Finally, the active disturbance rejection control parameters are efficiently optimized by online identification. The simulation results show that the proposed method has higher robustness than the baseline controller, and can effectively improve the high-precision landing performance of carrier-based aircraft under interference conditions.

Key words: direct lift control, active disturbance rejection control, neural networks, Magic Carpet, online identification

中图分类号: