This work presents a method for detecting and identificating possible damages to propeller blades in multirotor vehicles, for a particular case study of a quadrotor. The detection method is based on a neural network, which takes as input the energy of several spectral bands of the inertial measurements and control variables, and outputs a measure of how damaged a propeller is. The ability of the network to correctly generalize from a limited dataset will be shown by training it using data gathered from an indoor, controlled environment, and testing it using data from outdoor flights.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Neural network-based propeller damage detection for multirotors


    Beteiligte:
    Pose, Claudio (Autor:in) / Giribet, Juan (Autor:in) / Torre, Gabriel (Autor:in) / Marzik, Guillermo (Autor:in)


    Erscheinungsdatum :

    06.06.2023


    Format / Umfang :

    4613757 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Scaling Effects on Controllers for Multirotors

    Thai, Lam Ngoc / Nahon, Meyer / Charland-Arcand, Guillaume | IEEE | 2020


    Active Battery Charge Drift Stabilization for Redundant Multirotors

    Stephan, Johannes / Fichter, Walter | AIAA | 2020


    Aerodynamic Interference Model for Multirotors in Forward Flight

    Han, Dong / Barakos, George N. | AIAA | 2020


    L1 Adaptive Controller for Attitude Control of Multirotors

    Mallikarjunan, Srinath / Nesbitt, Bill / Kharisov, Evgeny et al. | AIAA | 2012