Research on Satellite Power Subsystem Anomaly Detection Technology Based on Health Baseline

  • Lei ZhangEmail author
  • Zhidong Li
  • Bo Sun
  • Shuai Zhang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 550)


There is a huge amount of data in the satellite power subsystem, and the information and knowledge related to the operating status of the power subsystem in these data is an important for the abnormal state detection of the power subsystem. In order to make data mining of satellite power subsystem and set the reference for its anomaly detection, a satellite power subsystem anomaly detection technology based on the health baseline is proposed. According to the core operating conditions of the satellite power subsystem, health baselines are constructed respectively, and the effectiveness of the proposed method is verified by the telemetry data of the satellite power subsystem. With robustness, the test results show that anomaly detection of the onboard power subsystem can be achieved based on the constructed health baseline.


Satellite Power subsystem Health baseline 


  1. 1.
    Wang, Z., Chen, H.: Research on spatial outlier detection based on quantitative value of attributive correlation. Comput. Eng. 32, 37–39 (2006)Google Scholar
  2. 2.
    Tan, Z., Aruna, J., He, X., et al.: A system for denial-of-service attack detection based on multivariate correlation analysis. IEEE Trans. Parallel Distrib. Syst. 25, 447–456 (2014)CrossRefGoogle Scholar
  3. 3.
    Ding, J., Liu, Y., Zhang, L., et al.: An anomaly detection approach for multiple monitoring data series based on latent correlation probabilistic model. Appl. Intell. 44, 340–361 (2016)CrossRefGoogle Scholar
  4. 4.
    Zhang, T., Lu, C., Tao, L., Li, K.: Rolling bearing fault diagnosis based on health baseline method. In: Vibroengineering Procedia. 28th International Conference on Vibroengineering, vol. 14, pp. 141–145 (2017)Google Scholar
  5. 5.
    Pang, J., Liu, D., Liao, H., et al.: Anomaly detection based on data stream monitoring and prediction with improved Gaussian process regression algorithm. In: International Conference on Prognostics & Health Management (2015)Google Scholar
  6. 6.
    Lee, H., Byington, C., Watson, M.: PHM system enhancement through noise reduction and feature normalization. In: Aerospace Conference (2010)Google Scholar
  7. 7.
    Xiong, L., Ma, H.D., Fang, H.Z., et al.: Anomaly detection of spacecraft based on least squares support vector machine. In: Prognostics & System Health Management Conference (2011)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Institute of Spacecraft System EngineeringBeijingChina

Personalised recommendations