高超声速飞行器的神经网络动态逆控制研究  

Neural Network Dynamic Inversion Control For a Hypersonic Flight Vehicle

作　　者：鲁波[1] 陆宇平[1] 方习高[1] 

机构地区：[1]南京航空航天大学自动化学院,江苏南京210016

出　　处：《计算机测量与控制》2008年第7期966-968,共3页Computer Measurement &Control

基　　金：国家高技术研究发展计划("863"计划)项目(2006AA705404)

摘　　要：针对通用的高超声速飞行器的纵向动力学设计一个神经网络动态逆补偿控制方法,并对其进行了分析;这种飞行器模型具有高度非线性、多变量、不稳定的特性,包括6个不确定参数;在4.5903km高度和15马赫的平衡巡航条件下的仿真研究,评价了飞行器对高度和空速的阶跃变化的响应;阶跃变化为速度30 m/s,高度40 m;通过仿真结果表明,采用神经网络补偿逆误差,弥补了非线性动态逆要求精确数学模型的缺点,而且可以简化动态逆控制律的设计,改善整个控制系统的性能。A neural network dynamic inversion method is presented and analyzed for the longitudinal dynamics of a generic hypersonic air vehicle. This vehicle model is nonlinear, multivariable, and unstable and includes uncertain parameters. Simulation studies are conducted for trimmed cruise conditions of 4590. 3 m, and Mach 15 where the responses of the vehicle to a step change in altitude and air speed are evaluated. The commands are 30 m/s step velocity and 40 m step altitude. Simulation results show that through adaptively canceling the inversion error by neural networks the limitation of needing accurate mathematical model in the dynamic inversion method can be released. Besides this the design of dynamic inversion control law can be greatly simplified by utilizing the online neural networks and the control effects are improved.

关 键 词：神经网络 动态逆 飞行控制系统 高超声速 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] V241[自动化与计算机技术—控制科学与工程]