Abstract Anomaly detection of satellite telemetry data has always been a significant issue in the development of aeronautics and astronautics. Timely and effective anomaly detection method of satellite telemetry data is a research hotspot in academia and aerospace industry. For satellite telemetry data, we propose an anomaly detection model based on Bayesian deep learning without domain knowledge. In this model, we show the feasibility of implementing MC-dropout on the Long Short-Term Memory Network (LSTM), and establish the Bayesian LSTM. First, we perform a preliminary anomaly detection task through our model—Monte Carlo Dropout Bidirectional Long Short-term Memory Network (MCD-BiLSTM). Then, Monte Carlo (MC) Sampling Variance, Prediction Entropy and Mutual Information are taken to measure the uncertainty of output through MCD-BiLSTM. What's more, we further explore and exploit the three types of uncertainties, and utilize the variational auto-encoder (VAE) to reevaluate the high uncertainty samples to improve the anomaly detection capability. To our knowledge, it is the first time that Bayesian neural networks have been introduced into the field of satellite telemetry data anomaly detection. The experimental results on an imbalanced satellite telemetry dataset show that our proposed model can add effective regularization constraints, and obtain great robustness on imbalanced data, which performs better than popular traditional neural networks and other Bayesian neural networks.

    Highlights Show the feasibility of Bayesian LSTM based on dropout technology. Take the lead in using BNNs to complete the task of satellite anomaly detection. Propose three kinds of uncertainties output through our Bayesian LSTM. Use proposed uncertainties to re-evaluate and improve the model. Our model is end-to end, and needs no domain knowledge from experts.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Imbalanced satellite telemetry data anomaly detection model based on Bayesian LSTM


    Beteiligte:
    Chen, Junfu (Autor:in) / Pi, Dechang (Autor:in) / Wu, Zhiyuan (Autor:in) / Zhao, Xiaodong (Autor:in) / Pan, Yue (Autor:in) / Zhang, Qiang (Autor:in)

    Erschienen in:

    Acta Astronautica ; 180 ; 232-242


    Erscheinungsdatum :

    2020-12-07


    Format / Umfang :

    11 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    EVALUATING ANOMALY DETECTION IN SATELLITE TELEMETRY DATA

    Nalepa, Jakub / Benecki, Pawel / Andrzejewski, Jacek et al. | TIBKAT | 2022


    Evaluating algorithms for anomaly detection in satellite telemetry data

    Nalepa, Jakub / Myller, Michal / Andrzejewski, Jacek et al. | Elsevier | 2022


    A hybrid data-driven framework for satellite telemetry data anomaly detection

    Xu, Zhaoping / Cheng, Zhijun / Guo, Bo | Elsevier | 2023


    Supporting Anomaly Detection from Satellite Telemetry Data by Regression Trees

    Nakatsugawa, M. / Yairi, T. / Isihama, N. et al. | British Library Conference Proceedings | 2004