BTT导弹神经网络自适应控制器设计

Design of Nonlinear Adaptive Control System for BTT Missile Based on RBF Neural Networks

在导弹系统存在非匹配不确定性的情况下 ,提出了一种基于RBF神经网络和反演控制技术的神经网络自适应导弹控制系统的设计方法。首先应用RBF神经网络在线辨识系统中存在的不确定性 ,然后利用反演控制技术设计了导弹非线性自适应控制器 ,成功的处理了非匹配不确定性 ,并应用Lyapunov稳定性理论推导出RBF神经网络权重矩阵及中心点值的调节律 ,保证了系统的稳定性。证明了系统的所有信号均有界且全局指数收敛至原点的一个邻域。最后给出的BTT导弹非线性六自由度数字仿真结果显示了该设计方法的有效性。

In this paper, a nonlinear adaptive control scheme for missile control system with mismatched uncertainties is proposed on the basis of RBF neural networks and inverse control technology. In this scheme the Radical-Basis-Function ( RBF ) neural networks are used to identify the uncertainties of the system, then the nonlinear adaptive controller is designed by using inverse control techniques which deals with the mismatched uncertainties of the system successfully. Also the regulating law of RBF neural network weight matrix and center values are firstly derived through Lyapunov stability theory so as to guarantee the stability of the whole system. All signals of the system are bounded and exponentially converge to the neighborhood of the origin. Finally nonlinear six-degree-of-freedom (6- DOF ) simulation results for a bank-to-turn ( BTT ) missile model demonstrates the effectiveness of this method.