中国空间科学技术 ›› 2021, Vol. 41 ›› Issue (4): 121-126.doi: 10.16708/j.cnki.1000-758X.2021.0058

• 论文 • 上一篇    下一篇

基于循环神经网络的卫星姿态执行器故障诊断

倪平,闻新   

  1. 1 沈阳航空航天大学 航空宇航学院,沈阳110136
    2 南京航空航天大学 航天学院,南京210016
  • 出版日期:2021-08-25 发布日期:2021-07-30

Fault diagnosis of satellite attitude actuator based on recurrent neural network

NI Ping,WEN Xin   

  1. 1 School of Astronautics,Shenyang Aerospace University, Shenyang 110136, China
    2 Academy of Astronautics, Nanjing University of Aeronautics & Astronautics, Nanjing 210016, China
  • Published:2021-08-25 Online:2021-07-30

摘要: 针对卫星姿态控制系统执行器机构故障问题,提出了一种基于循环神经网络的故障诊断方法。对卫星姿态控制系统建模,进行故障分析并采集星敏感器和角速度陀螺的连续时刻故障数据。设计六种异构的循环神经网络,对故障数据进行故障诊断和分类, 分别从网络深度、反馈单元、激活函数和训练算法对比网络效果。带有门循环单元的 (gate recurrent unit,GRU)深层循环神经网络训练效果更好,其故障诊断准确率达到了95.7%。结果表明对于时序的卫星数据,门循环单元和带有一定深度的循环神经网络故障诊断效果更优。

关键词: 卫星姿态, 控制系统, 循环神经网络, 故障诊断, 门控循环单元, 深度学习

Abstract: To solve the problem of actuator failure in satellite attitude control system, a fault diagnosis method based on recurrent neural network was proposed. The satellite attitude control system was modeled, fault analysis was carried out, continuous time fault data of star sensor and angular velocity gyro were collected. Six kinds of heterogeneous cyclic neural networks were designed to diagnose and classify the fault data, and the network effect was compared in terms of the network depth, feedback unit, activation function and training algorithm. The effect of deep loop neural network with GRU is better, the accuracy of fault diagnosis is 95.7%. The results show that, for time series satellite data, GRU and the recurrent neural network with a certain depth have better fault diagnosis effect.

Key words: satellite attitude, control system, recurrent neural network, fault diagnosis, GRU, deep learning