基于IL-NN的三旋翼无人机预定义时间抗扰容错跟踪控制OA
IL-NN based predefined-time robust and fault-tolerant tracking control for trirotor UAVs
针对三旋翼无人机同时存在外部扰动和执行器故障时的轨迹跟踪问题,设计了基于迭代学习神经网络(IL-NN)的预定义时间容错跟踪控制策略.同时考虑执行器故障和未知外部时变扰动,建立三旋翼无人机故障动力学模型.针对未知外部时变扰动,设计基于迭代学习算法的神经网络结构,相比于自适应神经网络权值估计,降低计算复杂度;采用内外环控制策略,引入自适应算法在线估计执行器故障,设计基于预定义时间的自适应容错跟踪控制器,实现无人机在故障和扰动下的快速稳定跟踪;通过Lyapunov理论证明了内外环系统在预定义时间内收敛.最后,通过无人机飞控半实物实验平台验证了所提方法的有效性.
This paper addresses the trajectory tracking problem of trirotor unmanned aerial vehicles(UAVs)subject to simultaneous external disturbances and actuator faults,and proposes a predefined-time fault-tolerant tracking control strategy based on an iterative learning neural network.A comprehensive fault dynamics model is established for trirotor UAVs,which incorporates actuator faults and unknown time-varying external disturbances.To compensate for the adverse effects of unknown time-varying disturbances,an iterative learning neural network(IL-NN)is developed,which effec-tively reduces computational complexity compared with traditional adaptive neural networks.An inner-outer loop control structure is employed,where an adaptive algorithm is applied to achieve online actuator fault estimation.On this basis,a predefined-time adaptive fault-tolerant controller is constructed to guarantee fast and stable tracking performance under faults and disturbances.The predefined-time stability of the entire closed-loop system is rigorously proven by Lyapunov stability theory.Finally,hardware-in-the-loop experiments on a UAV flight control platform are carried out,and the results demonstrate the effectiveness and superiority of the proposed control scheme.
郝伟;李佳磊;张琦林;马文来;李庆
山东航空学院 飞行学院,山东 滨州 256600||通用航空运行与控制山东省工程研究中心,山东 滨州 256600山东航空学院 飞行学院,山东 滨州 256600山东航空学院 飞行学院,山东 滨州 256600山东航空学院 飞行学院,山东 滨州 256600||通用航空运行与控制山东省工程研究中心,山东 滨州 256600中国航空工业集团公司西安飞行自动控制研究所,陕西 西安 710076
三旋翼无人机预定义时间控制迭代学习神经网络容错控制
trirotor UAVpredefined-time controliterative learning neural networkfault-tolerant control
《控制理论与应用》 2026 (9)
1917-1928,12
国家自然科学基金项目(62103060),山东省自然科学基金项目(ZR2019PF021,ZR2020MF142),山东省高等学校"青创团队计划"团队项目(2023KJ274)资助. Supported by the National Natural Science Foundation of China(62103060),the natural Science Foundation of Shandong Province(ZR2019PF021,ZR2020MF142)and the Young Innovation Teams Project of Colleges and Universities in Shandong Province(2023KJ274).
评论