中国空间科学技术

中国空间科学技术 ›› 2023, Vol. 43 ›› Issue (2): 93-102.doi: 10.16708/j.cnki.1000-758X.2023.0024

• 论文 • 上一篇    下一篇

基于时序建模的卫星故障检测方法

杨凯飞，韩笑冬，吕原草，徐楠，宫江雷，李翔   

  1. 1 中国空间技术研究院 通信与导航卫星总体部，北京100094
    2 西安电子科技大学，西安710126
  • 出版日期:2023-04-25 发布日期:2023-03-13

Satellite fault detection method based on time-series modeling

YANG Kaifei，HAN Xiaodong，LYU Yuancao，XU Nan，GONG Jianglei，LI Xiang   

  1. 1 Institute of Telecommunication and Navigation Satellites,CAST,Beijing 100094,China
    2 Xidian University,Xi′an 710126,China
  • Published:2023-04-25 Online:2023-03-13

PDF (PC)

306

摘要： 为解决当前卫星故障检测面临的依赖规则库、多元特征融合不足以及数据正负样本分布不均衡等问题，从卫星数据的时序特性出发，提出基于时序建模的卫星故障检测方法与半监督模型，实现卫星数据规律的有效挖掘与数据驱动的故障检测。考虑卫星数据间的时序关联，提出基于长短期记忆神经网络的卫星故障检测方法，并引入滑动窗口机制实现卫星数据的有效预测与故障检测。考虑卫星数据多元特征参数间的关联关系，引入时间卷积和自编码器神经网络，同时建模不同时刻、多元特征参数间的依赖关系，实现融合多元特征参数进行卫星故障的有效检测。以某型号卫星电源分系统为实验对象，仿真结果表明，所提算法和模型在关键指标方面优于BP神经网络等传统故障检测方法和模型。

关键词: 故障检测, 时间卷积神经网络, 自编码器, 长短期记忆神经网络, 时序建模, 半监督学习

Abstract: A kind of satellite fault detection method was introduced to handle the problems of relying on rule database,insufficient multi parameter fusion and unbalanced distribution of data samples in satellite fault detection.The semi-supervised model was constructed based on time-series characteristics of satellite data and was proposed to achieve effective excavation of satellite data rules and data driven fault detection.Considering the temporal correlation between satellite data,this kind of fault detection method was proposed based on long short-term memory network.Also,a sliding window mechanism was involved for better predicting and detecting efficiency.Considering the correlation between multiple parameters as another dimension,temporal convolutional network(TCN) and auto-encoder network were used to excavate the correlation between historical data and different parameters at the same time.Experimental results show that the proposed model is superior to traditional fault detection models such as BP neural network in key indicators.

Key words: fault detection, temporal convolutional network, autoencoder, long short-term memory network, time-series modeling, semi-supervised learning