| 引用本文: | 孙志兵,戴金海.基于RBF神经网络的直接自适应飞行控制器.[J].国防科技大学学报,2007,29(1):30-34.[点击复制] |
| SUN Zhibing,DAI Jinhai.Direct Adptive Neuro Flight Controller Based on RBF NN[J].Journal of National University of Defense Technology,2007,29(1):30-34[点击复制] |
|
| |
|
|
| 本文已被：浏览 6879次 下载 5931次 |
| 基于RBF神经网络的直接自适应飞行控制器 |
| 孙志兵, 戴金海 |
|
(国防科技大学 航天与材料工程学院，湖南 长沙 410073)
|
| 摘要: |
| 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。 |
| 关键词: 径向基函数神经网络 直接自适应 飞行控制器 仿真分析 |
| DOI： |
| 投稿日期：2006-08-29 |
| 基金项目:国家部委基金资助项目 |
|
| Direct Adptive Neuro Flight Controller Based on RBF NN |
| SUN Zhibing, DAI Jinhai |
|
(College of Aerospace and Materials Engineering, National Univ. of Defense Technology, Changsha 410073, China)
|
| Abstract: |
| 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 robustness. Fully-tunned law presented in this paper is better than the conventional algorithm which only adjusts weight value of RBF NN. |
| Keywords: radial basis function neural network direct adptive flight controller simulation analyze |
|
|
