基于自适应逆的无人直升机指令控制器设计

Design of unmanned helicopter command controller based on adaptive inversion

使用动态逆和在线神经网络相结合的方法设计了无人直升机的指令控制器。该方法用无人机近似线性模型的动态逆使系统反馈线性化 ,然后用一神经网络在线消除逆误差的影响。由于在线神经网络的自适应作用 ,消除了无人机未建模动态和不确定性的影响。仿真结果表明所设计的控制器具有较好的性能。

Design of a unmanned helicopter command controller using combination of dynamic inversion and a on line neural network is presented. The method uses dynamic inversion of a linear model of UAV to approximately linearize the system feedbacks. The controller is then augmented with an on line neural network that seeks to improve the response by adaptively eliminating the effect of inversion errors in flight, and the effects of uncertainty of UAV is also eliminated due to the adaptability of the network. Simulation results demonstrate that the performance of proposed controller is quite good.