基于CMAC网络的飞行器再入制导研究  

The Study of Reentry Guidance Law Based on CMAC Network

作　　者：吴浩[1] 王永骥[1] 郑总准[1] 

机构地区：[1]华中科技大学控制科学与工程系,武汉430074

出　　处：《弹箭与制导学报》2009年第6期17-21,24,共6页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：国家自然科学基金(60674105);2008航天支撑基金资助

摘　　要：针对高速再入飞行器的制导问题,提出了一种改进的标准轨道制导律。该方案在纵向上将LQR控制与小脑模型神经网络(CMAC)相结合,利用在线学习的CMAC对攻角和倾侧角的大小进行修正,提高地心径向距离和剩余航程的跟踪精度。在侧向上,根据定义的侧向边界设置动态调整准则确定倾侧角反向位置。三自由度仿真显示,该制导律在气动偏差下能够得到满足终端精度和约束条件的再入轨道,具有良好的可行性。An improved reentry reference trajectory guidance law for lift-body vehicles was proposed. In longitudinal guidance, online adjusting cerebella model articulation controller （CMAC） was presented to modify the value of angle of attack and bank angle, which was applied to enhance the tracking precision of the nominal trajectory. In lateral guidance, a crossrange boundary was established to determine bank reversals according to dynamic adjusting criterion. The 3DOF simulation results showed satisfactory terminal and procedure conditions in the prescnce of aerodynamic uncertainties, which demonstrated the feasibility of this improved method.

关 键 词：高速再入飞行器 再入制导 LQR方法 小脑模型神经网络 标准轨道跟踪 

分 类 号：V448.235[航空宇航科学与技术—飞行器设计]