基于RBF神经网络的直接自适应飞行控制器

Direct Adptive Neuro Flight Controller Based on RBF NN

设计了一种径向基神经网络(RBF NN)飞行控制器结构,并给出了相应的控制律和参数调节律。由于调节了RBF NN的全部参数(连接权、高斯函数的中心和宽度),得到了很好的控制性能。以F8战斗机为控制对象进行了仿真分析,仿真表明,在存在70%的模型误差的情况下,该控制器仍然能实现较好的跟踪控制,表现出很好的鲁棒性,远远优于传统的只调节连接权值的算法。

A flight controller structure based on RBF NN was designed,and its control law and tunned law for RBF NN parameters. （center and width of gauss function, weight） were presented. F8 Fight aircraft was taken as the control object and a simulation was thus performed. The results from simulation show that, even under 70% model error, this controller manifests excellent control performance and good mbusmess. Fully-tunned law presented in this paper is better than the conventional algorithm which only adjusts weight value of RBF NN.