Neural Extended State Observer Based Intelligent Integrated Guidance and Control for Hypersonic Flight

作者：Wang, Liang^*; Peng, Ke^*; Zhang, Weihua; Wang, Donghui

来源：Energies, 2018, 11(10): 2605.

DOI：10.3390/en11102605

• integrated guidance and control
• neural network
• extended state observer
• command filter
• back-stepping control

Near-pace hypersonic flight has great potential in civil and military use due to its high speed and low cost. To optimize the design and improve the robustness, this paper focuses on the integrated guidance and control (IGC) design with nonlinear actuator dynamics in the terminal phase of hypersonic flight. Firstly, a nonlinear integrated guidance and control model is developed with saturated control surface deflection, and third-order actuator dynamics is considered. Secondly, a neural network is introduced using an extended state observer (ESO) design to estimate the complex model uncertainty, nonlinearity and disturbance. Thirdly, a command-filtered back-stepping controller is designed with flexible designed sliding surfaces to improve the terminal performance. In this process, hybrid command filters are implemented to avoid the influences of disturbances and repetitive derivation, meanwhile solving the problem of unknown control direction caused by nonlinear saturation. The stability of the closed-loop system is proved by the Lyapunov theory, and the controller parameters can be set according to the relevant remarks. Finally, a series of numerical simulations are presented to show the feasibility and validity of the proposed IGC scheme.

• 出版日期2018-10
• 单位中国人民解放军国防科学技术大学