基于动态逆的神经网络超机动飞行控制

为战斗机的过失速超机动飞行设计了一种神经网络控制器。基于时标分离的原则，神经控制器被设计为内环控制器和外环控制器两个部分。网络的训练利用改进的BP算法，将因子模糊化快速进行。样本点数据则由利用动态逆控制所得到的结果来提供。网络的使用利用联想记忆法则。仿真结果说明所设计的系统具有良好的控制性能及鲁棒性。

SUPERMANEUVERABLE FLIGHT CONTROL USING DYNAMICA INVERSION BASED NEURAL NETWORKS

A neural networks controller(NNC) is designed for the post stall supermaneuverable flight. The NNC is composed of an inside loop controller and an outside loop one in accordance with the two time scale. The networks are trained by the fast BP algorithm via fuzzy variables decision, and training samples are provided by the dynamic inversion control results. This NNC is utilized by way of associative memory. Simulation results demonstrate that the designed system has good performance.