Volume 38, Number 3, June 2020
|Page(s)||668 - 676|
|Published online||06 August 2020|
A Neural Network Adaptive Fault-Tolerant Control Method for Launch Vehicles with the Limited Faults
Beijing Institute of Astronautical Systems Engineering, Beijing 100076, China
2 China Aerospace Science and Technology Corporation, Beijing 100048, China
To tolerate the limited faults such as thrust decline or actuator jamming of launch vehicles, an adaptive fault-tolerant control method based on radial basis function neural network (RBFNN) is proposed in this paper. The method is based on a limited faults dynamics model, and the baseline controller is designed based on the pole placement, using RBFNN to online identify and compensate the fault parameters and uncertain disturbances in the model. Then an adaptive fault-tolerant control law is designed based on Lyapunov theory. The simulation results show that the proposed adaptive control method can effectively ensure the attitude stability as well as control accuracy under the limited faults of launch vehicles, compared with the traditional PD control method.
针对运载火箭推力下降或伺服机构卡死等有限故障，提出了一种基于径向基神经网络（radial basis function neural network，RBFNN）的自适应容错姿态控制方法。该方法在有限故障动力学模型基础上，采用极点配置设计基线控制器，使用RBFNN在线辨识模型的故障参数和不确定干扰，最后基于Lyapunov理论设计自适应容错控制律对故障模型和干扰进行补偿。仿真结果表明，在有限故障工况下，该方法与传统PD方法相比，对故障具有较好的自适应能力，并能满足姿态稳定和控制精度要求。
Key words: radial basis function neural network / active fault-tolerant control / limited faults / adaptive control
关键字 : 径向基神经网络 / 主动容错控制 / 有限故障 / 自适应控制
© 2019 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.