论文部分内容阅读
针对飞行器在大机动飞行过程中气动参数不确定、外部未知干扰因素较多及系统建模可能存在误差等问题,设计了一种基于RBF神经网络的非线性自适应反演控制器。飞行器大机动飞行过程中的广义不确定性由RBF神经网络在线逼近,神经网络权值矩阵通过自适应律在线更新。反演设计过程中对虚拟控制律的反复求导带来的“项数膨胀”问题,通过引入一阶滤波器来解决。通过构造Lyapunov函数,证明了闭环系统所有信号均有界,并且跟踪误差指数收敛到零的一个小邻域内。对某飞行器进行了大机动飞行仿真,结果表明该控制器具有良好的跟踪效果和鲁棒性。
Aiming at the problems of uncertainty of aerodynamic parameters, unknown external disturbances and possible system modeling errors during the flight, a nonlinear adaptive inversion controller based on RBF neural network is designed. The generalized uncertainties in the large maneuvering flight of aircraft are approximated online by RBF neural network and the neural network weight matrix is updated online by adaptive law. The problem of “number expansion” caused by repeated derivation of the virtual control law in the inversion design process is solved by introducing the first-order filter. By constructing Lyapunov function, it is proved that all the signals in the closed-loop system are bounded, and the tracking error index converges to a small neighborhood of zero. A large maneuvering flight simulation of an aircraft was carried out. The results show that the controller has good tracking performance and robustness.