Vibrational anomalies can provide valuable insights into the health status of an unmanned aerial vehicle, potentially indicating system degradation including propeller, motor, or sensor damage, as well as environmental anomalies such as strong wind gusts and turbulence. However, many causes for vibrational anomalies are not related to vehicle health, such as sharp shifts in velocity or direction of flight. Thus, depending strictly on vibration signals to detect anomalies can result in false positives for failures. Hence, it is important to include additional telemetries in detecting and diagnosing in-flight anomalies. This paper considers an approach to anomaly detection based on tensor decompositions that incorporates information from vibration signals, as well as additional flight data such as velocity, current draw, voltage drop, and attitude. Using experimental flight data collected by the University of Notre Dame, we construct third-order tensors then apply the CANDECOMP/PARAFAC decomposition to identify trends within each flight and classify flights as nominal or anomalous.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    Tensor Decomposition Analysis for UAV Anomaly Detection


    Beteiligte:
    E. J. Hale (Autor:in) / P. Banerjee (Autor:in) / R. Ghimire (Autor:in)

    Erscheinungsdatum :

    2023


    Format / Umfang :

    11 pages


    Medientyp :

    Report


    Format :

    Keine Angabe


    Sprache :

    Englisch




    Tensor Decomposition Analysis for UAV Anomaly Detection

    Hale, Elizabeth / Banerjee, Portia / Ghimire, Rajeev | AIAA | 2024


    Anomaly Detection in Road Networks Using Sliding-Window Tensor Factorization

    Xu, Ming / Wu, Jianping / Wang, Haohan et al. | IEEE | 2019


    Statistical Analysis of the Knowledge-Guided Tensor Decomposition

    Metzler, Joy J. / Coley, Christopher | AIAA | 2023


    ANOMALY DETECTION SYSTEM, ANOMALY DETECTION APPARATUS, AND ANOMALY DETECTION METHOD

    KOBAYASHI AYUMI | Europäisches Patentamt | 2023

    Freier Zugriff

    Tensor-based Factor Decomposition for Relighting

    Lin, D. / Xu, Y. / Tang, X. et al. | British Library Conference Proceedings | 2005