关于无人机导引律优化控制与仿真研究  

Optimization for Variable Structure Guidance Law of UCAV

作　　者：吴俊辰[1] 王洁[1] 徐啟云 杨景[1] 

机构地区：[1]空军工程大学防空反导学院,陕西西安710051

出　　处：《计算机仿真》2016年第2期78-82,共5页Computer Simulation

摘　　要：由于无人机导引律控制受到参数摄动和外界扰动的影响,传统的小扰动线性化导引控制方法已经无法满足需要,为了提高导引律控制的稳定性和导引精度,提出一种递归小波神经网络自适应滑模变结构导引律优化控制方法。首先,将变结构控制理论运用于无人机的导引律控制设计,推导出自适应滑模变结构导引律。然后,应用递归小波神经网络的非线性特点,通过离线训练一个神经网络模块,嵌入到控制回路中,实现对无人机变结构导引律控制的优化。最后,根据优化后的导引律得到无人机状态的期望值,并将期望值与无人机状态的实际值之间的误差进行自主攻击轨迹的飞行控制。仿真结果表明,无人机导引律优化控制能够提高无人机的稳定性,而且具备良好的抗扰动能力,无人机在导引律控制过程中控制量变化平稳,具有良好的动态品质。可行性分析证明了改进方法的有效性和合理性。For the disturbance of UCAV,in order to improve the stability of UCAV,the guidance law was optimized based on recurrent wavelet neural networks in the paper. Using the variable structure control theory to the UCAV＇s guide,the adaptive sliding variable structure guidance law was derived. A module of RWNN was trained off-line. Then,the module was inserted into the control system of UCAV. In the autonomous trajectory control algorithm,the expectation value of state was given by adaptive sliding variable structure guidance law. There exists an error between the expectation value and the value according to the motion model,which was used to drive control. The simulation results show that the design can improve the performance of guidance law,and the states vary smoothly in the control process.

关 键 词：无人机 递归小波神经网络 自适应滑模变结构 自主攻击轨迹 

分 类 号：V249[航空宇航科学与技术—飞行器设计]