基于单隐层神经网络的空天飞行器直接自适应轨迹线性化控制

Direct Adaptive Trajectory Linearization Control of Aerospace Vehicle Using SHLNN

基于轨迹线性化方法(TLC)及神经网络技术研究了一种新的直接自适应TLC控制方案。利用单隐层神经网络(SHLNN)对于光滑非线性函数的逼近能力,对消系统中不确定因素的影响,神经网络自适应律采用Lyapunov方法设计,保证了整个系统所有信号有界。最后利用该方案设计了空天飞行器飞行控制系统,并在高超声速飞行条件下进行了仿真验证,仿真结果表明整个控制系统具有很好的性能和鲁棒性。

This paper presents a novel nonlinear adaptive control method based on trajectory linearization control method （TLC） and neural networks. TLC method is a novel nonlinear tracking and decoupling control way. However, inherent uncertainties may render it useless. In this paper, a neural network is used to cancels uncertainties through on-line learning. The adaptive law is designed based on Lyapunov approach, so all signal boundedness of the whole system is guaranteed. Finally, the flight control system of the aerospace vehicle is designed based on the proposed method and the simulation results demonstrate the excellent performance and robustness of the controllers.