具有未知干扰的无人机鲁棒滑模飞行控制

研究无人机飞行稳定性控制问题,由于无人机飞行控制系统存在时变外部干扰,飞行过程中升阴比变化激烈,控制稳定性难度较大。利用滑模控制良好的鲁棒能力提出一种神经网络的鲁棒飞行控制方法。因神经网络有良好非线性逼近能力,可对无人机飞行系统中的不确定进行在线逼近,并将神经网络权值误差引入到权值的自适应律中用以改善系统的动态性能。利用神经网络的组合,设计无人机鲁棒滑模飞行控制器。控制器分为两部分,一部分是等效控制器,另一部分是滑模控制器,能有效减小系统的跟踪误差。最后将所设计的鲁棒滑模控制对无人机飞行姿态控制进行仿真。仿真结果表明,新方法能提高无人机的鲁棒飞行控制能力且能实现无人机姿态的精确跟踪和稳定性控制。

Robust Sliding Mode Flight Control for Unmanned Aerial Vehicles with Unknown Disturbance

Aiming at the difficult modeling of system uncertainty and the time-varying disturbance,the robust sliding mode flight control scheme was proposed for the unmanned aerial vehicle using the good robust ability of the sliding mode control in this paper.The neural networks were used to approximate the nonlinear functions,and the approximation errors of the neural networks were used to the adaptive law in order to improve the performance of the closed-loop system.Based on the output of the neural network,the robust sliding mode flight control scheme was designed.This designed controller consisted of an equivalent controller and an adaptive sliding mode controller.The sliding mode controller was a robust controller and it was used to minish the track error of the control system.Finally,the developed sliding mode control scheme was used to control the attitude of unmanned aerial vehicle to demonstrate the robust control ability of the proposed control method.