Abstract
Detecting anomalies in satellite telemetry data is pivotal in ensuring its safe operations. Although there exist various data-driven techniques for the task of determining abnormal parts of the signal, they are virtually never validated over real telemetries. Analyzing such data is challenging due to its intrinsic characteristics, as telemetry may be noisy and affected by incorrect acquisition, resulting in missing parts of the signal. In this paper, we tackle this issue and propose a machine learning approach for detecting anomalies in single-channel satellite telemetry. To validate its capabilities in a practical scenario, we build a dataset capturing the nominal and anomalous telemetry data captured on board OPS-SAT—a nanosatellite launched and operated by the European Space Agency. Our extensive experimental study showed that the proposed algorithm offers high-quality anomaly detection in real-life satellite telemetry, reaching 98.4% accuracy over the unseen test set.
This work was partially supported by the: “On-board Anomaly detection from the OPS-SAT telemetry using deep learning” project funded by the European Space Agency under contract No. 4000137339/22/NL/GLC/ov. JN was supported by the Silesian University of Technology Rector’s grant (02/080/RGJ22/0026).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The OXI labeling system has been developed by KP Labs and it is available at https://oxi.kplabs.pl. OXI allows for not only investigating time-series data, together with the ground-truth information but also for generating ground truth.
- 2.
It is of note, however, that our approach can be applied to any time-series data, not only satellite telemetry.
References
Benecki, P., Piechaczek, S., Kostrzewa, D., Nalepa, J.: Detecting anomalies in spacecraft telemetry using evolutionary thresholding and LSTMs. In: Proceedings of the GECCO, GECCO 2021, ACM, New York, NY, USA, pp. 143–144 (2021)
Castellani, A., Schmitt, S., Squartini, S.: Real-world anomaly detection by using digital twin systems and weakly-supervised learning. CoRR abs/2011.06296 (2020). https://arxiv.org/abs/2011.06296
Chicco, D., Jurman, G.: The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21(1), 6 (2020)
ESA: WebMUST - web client for OPS-SAT directory (2021). https://opssat1.esoc.esa.int/webclient-must
Evans, D., et al.: Implementing the New CCSDS Housekeeping Data Compression Standard 124.0-B-1 (Based on POCKET+) on OPS-SAT-1. Small Satellite Conference (2022). https://digitalcommons.usu.edu/smallsat/2022/all2022/133
Evans, D.J., Ortega, M., Zeif, R., Sergert, T.: OPS-SAT: FDIR design on a mission that expects bugs - and lots of them. In: SpaceOps 2016 Conference. American Institute of Aeronautics and Astronautics (2016). https://doi.org/10.2514/6.2016-2481
Fratini, S., Policella, N., Silva, R., Guerreiro, J.: On-board autonomy operations for OPS-SAT experiment. Appl. Intell. 52(6), 6970–6987 (2022)
Gao, Y., et al.: An unsupervised anomaly detection approach for spacecraft based on normal behavior clustering. In: Proceedings of the ICICTA, pp. 478–481 (2012)
Hundman, K., Constantinou, V., Laporte, C., Colwell, I., Söderström, T.: Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In: Proceedings of the SIGKDD, pp. 387–395. ACM (2018)
Kacker, S., Meredith, A., Cahoy, K., Labrèche, G.: Machine learning image processing algorithms onboard OPS-SAT. In: Small Satellite Conference (2022). https://digitalcommons.usu.edu/smallsat/2022/all2022/65
Kopp, M., Pevný, T., Holeňa, M.: Anomaly explanation with random forests. Expert Syst. Appl. 149, 113187 (2020)
Kubicka, M., Zeif, R., Henkel, M., Hörmer, A.J.: Thermal vacuum tests for the ESA’s OPS-SAT mission. Elektrotech. Informationstechnik 139(1), 16–24 (2022)
Labreche, G., et al.: OPS-SAT spacecraft autonomy with TensorFlow lite, unsupervised learning, and online machine learning. In: Proceedings of the IEEE Aerospace Conference. IEEE Computer Society (2022)
Li, K., et al.: A novel method for spacecraft electrical fault detection based on FCM clustering and WPSVM classification with PCA feature extraction. Proc. Inst. Mech. Eng. 231(1), 98–108 (2017)
Marszk, D., Evans, D., Mladenov, T., Labrèche, G., Zelenevskiy, V., Shiradhonkar, V.: MO services and CFDP in action on OPS-SAT. In: Small Satellite Conference (2022). https://digitalcommons.usu.edu/smallsat/2022/all2022/67
Nalepa, J., et al.: Toward On-Board Detection Of Anomalous Events From Ops-Sat Telemetry Using Deep Learning (2022). https://www.researchgate.net/publication/367091759
Nalepa, J., Myller, M., Andrzejewski, J., Benecki, P., Piechaczek, S., Kostrzewa, D.: Evaluating algorithms for anomaly detection in satellite telemetry data. Acta Astronaut. 198, 689–701 (2022)
Nassif, A.B., Talib, M.A., Nasir, Q., Dakalbab, F.M.: Machine learning for anomaly detection: a systematic review. IEEE Access 9, 78658–78700 (2021)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Primartha, R., Tama, B.A.: Anomaly detection using random forest: a performance revisited. In: Proceedings ICoDSE, pp. 1–6 (2017)
Segret, B., et al.: On-board images to characterize a CubeSat’s ADCS. In: Small Satellite Conference (2022). https://digitalcommons.usu.edu/smallsat/2022/all2022/174
Toussaint, F., Thomassin, J., Laurens, S.: ASTERIA in-orbit testing on OPSSAT: an on-board autonomous orbit control solution including collision risks avoidance. In: Small Satellite Conference (2022). https://digitalcommons.usu.edu/smallsat/2022/all2022/103
Wu, R., Keogh, E.J.: Current time series anomaly detection benchmarks are flawed and are creating the illusion of progress (extended abstract). In: 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp. 1479–1480 (2022)
Zeif, R., Henkel, M., Hörmer, A., Kubicka, M., Wenger, M., Koudelka, O.: The redundancy and fail-safe concept of the OPS-SAT payload processing platform. In: 69th International Astronautical Congress, IAC 2018 (2018)
Zeng, Z., Jin, G., Xu, C., Chen, S., Zhang, L.: Spacecraft telemetry anomaly detection based on parametric causality and double-criteria drift streaming peaks over threshold. Appl. Sci. 12(4), 1–24 (2022)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ruszczak, B. et al. (2023). Machine Learning Detects Anomalies in OPS-SAT Telemetry. In: Mikyška, J., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 14073. Springer, Cham. https://doi.org/10.1007/978-3-031-35995-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-35995-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35994-1
Online ISBN: 978-3-031-35995-8
eBook Packages: Computer ScienceComputer Science (R0)