A Survey on Anomaly Detection and Diagnosis Problem in the Space System Operation

Year 2019, Volume: 2 Issue: 1, 13 - 17, 01.01.2019

Seçil Taburoğlu

https://doi.org/10.38016/jista.509532

Cited By: 3

Abstract

Spacecraft telemetry
data is transferred from satellite to ground control station. The data contains
not only  information about health status
of the satellite but also contains response messages to telecommand
(telecommand data is send to spacecraft from ground control station) data.
Telemetry data can indicate data error, communication link failure, sensor
error, equipment and electronic devices failure. Safety and reliability are
provided by telemetry and telecommand data. 
The most important subjects are safety and reliability for space
mission. Therefore, telemetry data should be analyzed and take measures against
to attack or unexpected situation. Various intelligent anomaly detection
methods are proposed in the literature. Supervised/unsupervised (machine
learning) anomaly detection approaches and data mining technology are the most used
methods.  This survey paper presents an
overview on anomaly detection approaches in space system operation.

Keywords

Anomaly detection, Machine Learning, Data Moning, spacraft health

References

• [1] Liu, Datong, et al. "Satellite Telemetry Data Anomaly Detection with Hybrid Similarity Measures." Sensing, Diagnostics, Prognostics, and Control (SDPC), 2017 International Conference on. IEEE, 2017,[2] Biswas, Gautam, et al. "An application of data driven anomaly identification to spacecraft telemetry data." Prognostics and Health Management Conference. 2016.
• [3] Gao, Yu, et al. "An unsupervised anomaly detection approach for spacecraft based on normal behavior clustering." Intelligent Computation Technology and Automation (ICICTA), 2012 Fifth International Conference on. IEEE, 2012.
• [4] Machida, K., et al. "Telemetry-mining: A machine Learning Approach to Anomaly detection and fault Diagnosis for space Systems." 2nd IEEE International Conference on Space Mission Challenges for Information Technology, IEEE. 2006.
• [5] Gao, Yu, et al. "Fault detection and diagnosis for spacecraft using principal component analysis and support vector machines." Industrial Electronics and Applications (ICIEA), 2012 7th IEEE Conference on. IEEE, 2012.
• [6] Gilmore, Colin, and Jason Haydaman. "Anomaly Detection and Machine Learning Methods for Network Intrusion Detection: an Industrially Focused Literature Review." Proceedings of the International Conference on Security and Management (SAM). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp), 2016.
• [7] Yairi, Takehisa, et al. "A Data-Driven Health Monitoring Method for Satellite Housekeeping Data Based on Probabilistic Clustering and Dimensionality Reduction." IEEE Transactions on Aerospace and Electronic Systems 53.3 (2017): 1384-1401.
• [8] Shi, Xintian, et al. "Satellite telemetry time series clustering with improved key points series segmentation." Prognostics and System Health Management Conference (PHM-Harbin), 2017. IEEE, 2017.
• [9] Azevedo, Denise Rotondi, Ana Maria Ambrósio, and Marco Vieira. "Applying data mining for detecting anomalies in satellites." Dependable Computing Conference (EDCC), 2012 Ninth European. IEEE, 2012.
• [10] Chandola, Varun, Arindam Banerjee, and Vipin Kumar. "Anomaly detection: A survey." ACM computing surveys (CSUR) 41.3 (2009): 15.