论文部分内容阅读
基于大系统递阶控制思想,提出了一种运用再励学习算法设计歼击机自动着陆横侧向协调控制系统的方法.将再励学习算法引入歼击机着陆阶段的横侧向子系统的协调控制中,对滚转通道和航向通道的控制器参数进行在线寻优,提高了在线补偿神经网络消除非线性系统逆误差的能力,有效地改善了歼击机着陆阶段横侧向控制子系统的鲁棒性能.通过将这种方法应用于某型歼击机自动着陆控制的实时仿真研究,仿真结果表明了本文方法的有效性和可行性.
Based on the idea of hierarchical control of large-scale systems, a method of re-learning learning is proposed to design a lateral automatic landing control system for fighter aircraft. The re-learning algorithm is introduced into the coordinated control of the lateral subsystem of the landing phase of the fighter plane, The online optimization of the controller parameters of the roll path and the course path improves the capability of on-line compensation neural network to eliminate the inverse error of the nonlinear system and effectively improves the robust performance of the transverse control subsystem during the landing phase of the fighter plane. This method is applied to the real-time simulation of automatic landing control of a certain type of fighter. The simulation results show the effectiveness and feasibility of the proposed method.