Air-Breathing Hypersonic Vehicles Funnel Control Using Neural Approximation of Non-affine Dynamics
Air-Breathing Hypersonic Vehicles Funnel Control Using Neural Approximation of Non-affine Dynamics
复制标题
使用非仿射动力学神经逼近的吸气式高超声速飞行器漏斗控制
DOI：
10.1109/tmech.2018.2869002
复制
发表时间：
2018-10-01
影响因子：
6.4
通讯作者：
Bu, Xiangwei
中科院分区：
文献类型：
--
作者：
Bu, Xiangwei
针对吸气式高超声速飞行器（AHV）的预定跟踪问题，提出了一种基于神经元逼近的漏斗非仿射控制器。我们提出了一种新的漏斗控制，以迫使速度和高度跟踪误差落在有界漏斗，而所需的瞬态性能和稳态性能都确保跟踪误差。为了处理非仿射动力学问题，基于隐函数定理对速度子系统设计了一种简化的神经网络控制器，通过模型变换结合低通滤波器方法，对高度子系统设计了一种新的不含虚拟控制律的反推控制器。神经逼近和调节律，以保证逼近性能，以拒绝系统的未知动态。通过李雅普诺夫综合保证了所有闭环系统信号的半全局一致最终有界性。最后，仿真结果验证了所提出的控制方法的跟踪性能。
This paper presents a funnel non-affine controller applying neural approximation for prescribed tracking of air-breathing hypersonic vehicles (AHVs). We propose a new funnel control to force velocity and altitude tracking errors to fall within bounded funnels, while the desired transient performance and steady-state performance are ensured for both tracking errors. To handle the nonaffine dynamics, a simplified neural controller is addressed for a velocity subsystem based on implicit function theorem, and a new back-stepping control without virtual control laws is exploited for the altitude subsystem via a model transformation combined with low-pass-filter approach. Neural approximations and regulation laws for guaranteeing approximation performance are employed to reject system unknown dynamics. The semiglobally uniformly ultimate boundedness of all the closed-loop system signals is guaranteed via Lyapunov synthesis. Finally, the tracking performance of the proposed control approach is verified by simulation results.