中国空间科学技术

中国空间科学技术 ›› 2025, Vol. 45 ›› Issue (1): 46-58.doi: 10.16708/j.cnki.1000-758X.2025.0005

• 智能航天器专栏 • 上一篇    

基于数字孪生和机器学习的卫星未知故障检测方法

沈英龙1，蔡君亮2，林佳伟2，杨帆1,3,*   

  1. 1.厦门大学 航空航天学院，厦门361102
    2.北京控制工程研究所，北京100190
    3.厦门市大数据智能分析与决策重点实验室，厦门361102
  • 收稿日期:2023-11-20 修回日期:2024-02-04 录用日期:2024-02-14 发布日期:2025-01-23 出版日期:2025-02-01

Detecting satellite unknown fault patterns using digital twin and machine learning

SHEN Yinglong1，CAI Junliang2，LIN Jiawei2，YANG Fan 1,3,*   

  1. 1.School of Aerospace Engineering,Xiamen University,Xiamen 361102,China
    2.Beijing Aerospace Control Center,Beijing 100190,China
    3.Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision-Making,Xiamen 361102,China
  • Received:2023-11-20 Revision received:2024-02-04 Accepted:2024-02-14 Online:2025-01-23 Published:2025-02-01

PDF (PC)

45

摘要： 卫星传统故障诊断方法及现有的数据驱动诊断方法都存在无法找出异于已知故障类型的未知故障的问题，可靠性与安全性较低。针对上述问题，提出基于卫星数字孪生体和多种机器学习模型的故障诊断与未知故障检测方法。首先，通过卫星数字孪生产生覆盖各种类型故障的仿真数据，并利用XGBoost分类模型和卫星真实故障样本验证了数字孪生数据的高仿真性，实现了已知故障类型的诊断。在此基础上，考虑到现有诊断方法无法精准识别未知类型故障的发生，提出一种分布外检测模型Con-DAGMM，通过正常数据和已知类型故障数据训练模型，实现了对未知故障的及时预警。利用数字孪生数据与在轨卫星真实故障数据进行实验，实验结果表明，所提方法故障诊断精度高，在测试数据上的平均准确率达到98.8%，且Con-DAGMM实现了高性能的未知故障检测，在精准率、召回率和F1分数上优于Deep-SVDD等对比方法。结果表明，卫星数字孪生可以克服卫星历史数据中故障样本稀缺的问题，且分布外检测的思路能成功应用于卫星未知故障的预警，提高了在轨卫星的安全性与可靠性。

关键词: 卫星控制系统, 未知故障检测, 故障诊断, 数字孪生, 机器学习, 分布外检测

Abstract: Traditional satellite fault diagnosis methods and existing data-driven diagnosis methods both face challenges in identifying unknown faults that differ from known fault types,resulting in lower reliability and safety．To address the problem,a fault diagnosis and unknown fault detection method based on satellite digital twin and machine learning models is proposed．Firstly,various types of fault-simulated data are generated using satellite digital twin,and the fidelity of digital twin data are validated using XGBoost and real satellite fault samples, achieving the diagnosis of known fault types．On this basis,considering that existing methods cannot identify the occurrence of unknown fault types precisely,an out-of-distribution detection model Con-DAGMM is proposed,which is trained on normal data and known fault data to provide warnings for unknown fault．Experiments are conducted using digital twin data and satellite real fault data．The experimental results demonstrate that the proposed method achieves high fault diagnosis accuracy with an average accuracy of 98.8% on the test data．Furthermore,Con-DAGMM achieve high-performance unknown fault detection,outperforming Deep-SVDD and other comparison methods in precision,recall and F1 scores．The results indicate that satellite digital twin can overcome the scarcity of fault samples in satellite historical data,and the out-of-distribution detection approach can be successfully applied to warning of satellite unknown faults,enhancing the satellite's safety and reliability．

Key words: satellite control system, unknown fault detection, fault diagnosis, digital twin, machine learning, out-of-distribution detection