摘要
针对四旋翼无人机在自然环境下飞行遭遇外部风扰和模型不确定等问题,设计了一种可靠的目标轨迹跟踪控制器,凭借循环神经网络技术,提出了一种自适应滑模控制方法。从四旋翼无人机动力学模型出发,分别考虑了全驱动、欠驱动子系统。通过将外部风扰和模型不确定部分进行集合成总干扰项,运用循环神经网络对该集总干扰项进行自适应估计,并依据Lyapunov理论,设计了具有反馈补偿的自适应滑模控制器。最后凭借理论和对比仿真充分证明了所提控制方法的有效性。
A reliable target trajectory tracking controller is designed to address the issues of external wind disturbances and model uncertainties encountered during flight of quadrotor unmanned aerial vehicle(UAV)within natural environments.An adaptive sliding mode control method based on recurrent neural network(RNN)is proposed.Regarding starting from the dynamics model of quadrotor UAV,the fully actuated and underactuated subsystems are considered separately.By combining external wind disturbances with model uncertainties and then integrating into total disturbance terms,a recurrent neural network is used to estimate the total disturbance terms adaptively.Based on Lyapunov theory,a feedback compensation adaptive sliding mode controller is designed.Thus,the effectiveness of the proposed control method is fully verified through theoretical and comparative simulations.
作者
王宁涛
陆伟民
应彬
龚政
WANG Ningtao;LU Weimin;YING Bin;GONG Zheng(Zhejiang Dayou Industrial Co.,Ltd.Hangzhou Science and Technology Development Branch,Hangzhou 310051,China)
出处
《航天控制》
CSCD
2024年第6期11-17,共7页
Aerospace Control
基金
浙江大有集团有限公司科技项目(DY2023-09)。
关键词
四旋翼无人机
循环神经网络
自适应滑模控制
跟踪控制
Quadrotor UAV
Recurrent neural network
Adaptive sliding mode control
Tracking control
