基于模糊径向基神经网络的小型无人机控制系统研究  

Study of Small UAV Control System Based on Fuzzy RBF Neural Network

作　　者：罗云林[1] 尹楚雄[1] 

机构地区：[1]中国民航大学航空自动化学院,天津300300

出　　处：《中国民航飞行学院学报》2014年第1期46-49,共4页Journal of Civil Aviation Flight University of China

摘　　要：为保证小型无人机的飞行安全,提出一种由无人机飞行控制器和地面学习单元构成的两层网络学习控制系统架构。无人机飞行控制器采用模糊控制策略,学习单元采用经遗传算法优化的径向基神经网络,充分利用模糊控制和神经网络的各自优势,将模糊控制策略与RBF神经网络相结合提出了一种基于RBF神经网络的自学习模糊控制策略。所设计的飞行控制器用于无人机飞行过程中的姿态控制,仿真及实验结果表明本方法是有效的。To ensure the safety of SUVA a two-layer networked learning control system architecture which consists of flight controller and ground learning unit is proposed. The SUAV flight controller adopts fuzzy control strategy, while learning unit applies the genetic algorithm optimized radial basis function neural network, which makes full use of the respective advantages of fuzzy control and neural networks. Combining fuzzy control strategy and RBF neural network creates a RBF neural network-based self-learning fuzzy control strategy. Flight controller is designed for the UAV flight at- titude control. Simulation and experiment results show that the method is effective.

关 键 词：小型无人机 遗传算法 RBF神经网络 模糊控制 

分 类 号：V249.1[航空宇航科学与技术—飞行器设计] TP183[自动化与计算机技术—控制理论与控制工程]