航空兵器2025，Vol.32Issue(3)：72-77,6.DOI:10.12132/ISSN.1673-5048.2025.0025
固定翼无人机纵向姿态神经网络自适应滑模控制
Neural Network Adaptive Sliding Mode Control for Longitudinal Attitude of Fixed-Wing UAVs
麻玥瑄 1陆宇 1朱威禹2
作者信息
- 1. 南京理工大学能源与动力工程学院,南京 210094
- 2. 中山大学航空航天学院,广东 深圳 511400
- 折叠
摘要
Abstract
Aiming at the problems such as model uncertainty and external interference existing in the longi-tudinal attitude control of fixed-wing UAVs,this paper proposes an adaptive sliding mode control method based on the radial basis function neural network(RBFNN).The method utilizes RBF to approximate the unmodeled dynamics in the system,and adjusts the weights of the neural network in real time through the designed adaptive law,to achieve effective compensation for model errors and external interference.Meanwhile,based on the Lya-punov stability theory,the sliding mode control law is designed to ensure the global stability and finite-time con-vergence characteristics of the closed-loop system.The simulation experiment results show that,compared with the traditional PID control and conventional sliding mode control methods,the proposed method can significantly improve the tracking accuracy and robustness of the control system in the presence of parameter perturbation and external interference,verifying the effectiveness of this method in the longitudinal attitude control of fixed-wing UAVs.关键词
固定翼/无人机/纵向姿态/神经网络/自适应/滑模控制Key words
fixed-wing/UAV/longitudinal attitude/neural network/adaptive/sliding mode control分类
军事科技引用本文复制引用
麻玥瑄,陆宇,朱威禹..固定翼无人机纵向姿态神经网络自适应滑模控制[J].航空兵器,2025,32(3):72-77,6.
