基于小波神经网络的自适应飞/推控制系统设计

基于小波神经网络提出了一种H∞自适应控制方法。控制器由等效控制器和H∞控制器两部分组成。用小波神经网络逼近非线性函数,并把逼近误差引入到权值的自适应律中用以改善系统的动态性能。H∞控制器用于减弱外部及神经网络的逼近误差对跟踪的影响。所设计的控制器不仅保证了闭环系统的稳定性,而且使外部干扰及神经网络的逼近误差对跟踪的影响减小到给定的性能指标。最后基于所设计的控制方法对新一代歼击机设计了飞/推控制系统,并对飞机作大迎角机动仿真。仿真结果表明所设计的飞/推控制系统是有效的,同时验证了所设计的非线性控制方法是有效性的。 

Design for Adaptive Flight/Propulsion Control System Based on Wavelet Neural Networks

In this paper, an adaptive H∞ control method based on wavelet neural network is proposed for the nonlinear uncertain systems. The controller is made up of equivalent controller and H∞ controller. The wavelet neural networks are used to approximate the nonlinear functions and the approximation errors of the neural networks are introduced to the adaptive law in order to improve the quality of the system. H∞ controller is designed for attenuating the external disturbance and approximation errors of the neural networks. The controller can not only guarantee the stability of the overall system,but also attenuate the effect of the external disturbance and approximation errors of the neural networks to a prescribed level. At last, based on forgoing designed control method a flight/propulsion control system has been designed and high angle attack flight simulation has been made. The simulation results suggest that the flight/propulsion control system is valid. They validate the availability of this control method for the uncertain nonlinear system too.