基于径向基函数神经网络与扩张状态观测器的无人直升机控制

Unmanned helicopter control based on radial basis function neural network and extended state observer

针对具有系统不确定和外部干扰的无人直升机飞行控制问题,提出了一种基于神经网络和扩张状态观测器的控制方法.利用神经网络逼近系统的不确定性,引入扩张状态观测器对神经网络的逼近误差和系统外部干扰进行估计.基于神经网络和扩张状态观测器的输出,对无人直升机的主旋翼挥舞角、姿态角速率、姿态角、速度与位置系统分别进行了控制器设计,以增强系统鲁棒性和抗干扰能力.同时,引入动态面控制方法以避免对虚拟信号进行直接求导,并通过李雅普诺夫方法分析了闭环控制系统的稳定性.最后使用无人直升机数据进行仿真验证,结果表明设计的控制律能使无人直升机有效跟踪控制指令,具有良好的稳定性与鲁棒性.

In this paper,a flight control combining neural network and extended state observer is proposed for the unmanned helicopter with system uncertainty and external disturbance.Neural network(NN)is used to approximate the uncertainty of all sub-systems.The extended state observer(ESO)is introduced to estimate the approximation error of the NN and the external disturbance of the system.Based on the output of NN and ESO,the controller of main blade flapping motion,attitude rate,attitude angle,velocity and position systems of unmanned helicopter are designed respectively to enhance the robustness and anti-disturbance ability of the system.Meanwhile,the dynamic surface control method is introduced to avoid the direct derivation of virtual signals.The stability of the control law is analyzed via Lyapunov’s stability theorems.Finally,using the data of an unmanned helicopter to simulate the whole system,the results show that the designed control law can make the unmanned helicopter effectively track the control com-mands,and show good stability and robustness.