应用神经网络的飞行器动力学自适应控制  

Adaptive Control of Aircraft Dynamics Based on Neural Networks

作　　者：殷业飞[1] 万少松[1] 柳世考[1] 

机构地区：[1]空军工程大学,陕西713800

出　　处：《战术导弹技术》2006年第6期63-67,共5页Tactical Missile Technology

摘　　要：针对具有未知参数的飞行器系统提出了一种基于模型的神经网络预测控制策略.目的是通过一个优化程序以自适应控制律来稳定未知系统.由于能够描述动态函数关系的特性和具有反馈处理结构,回归神经网络以一个期望状态值的自适应估计器得到应用.神经网络的训练是通过动态顺序递归反向传播学习算法来执行的.这表明所提出的神经网络学习算法拥有设计飞行控制系统的潜在能力,所设计的飞行系统能在大范围飞行条件下和其它不确定因素下补偿飞行器动力学不可预测的变化.A model-based neural network predictive control strategy for aircraft systems with unknown parameters is presented to stabilize unknown systems by the adaptive control law. Due to its capability of characterizing dynamic functional relationships and its feedback processing structure, a recurrent neural network is employed as a network training that is performed by the dynamic sequential recursive back propagation learning algorithm. It is shown that the proposed neural network learning algorithm has potential to design flight control system which can compensate for unpredictable changes in aircraft dynamics over a wide rang of flight conditions and other uncertainties.

关 键 词：神经网络 预测控制策略 价值函数 

分 类 号：TJ765[兵器科学与技术—武器系统与运用工程]