Simulated fault data from a mathematical model of a damaged rotor system are used to develop a neural network based approach for rotor system damage detection. The mathematical model of the damaged rotor is a comprehensive rotorcraft aeroelastic analysis based on a finite element approach in space and time. Selected helicopter rotor faults are simulated through changes in inertial, damping, stiffness and aerodynamic properties of the damaged blade. Noise is added to the numerical simulation to account for sensor noise and inherent uncertainty in the real system. A feedforward neural network with backpropagation learning is trained using both 'ideal' and 'noisy' simulated data. Testing of the trained neural network shows that it can detect and identify damage in the rotor system from simulated and noise contaminated blade response and vibratory hub loads data. For accurate estimation of the type and extent of damages, it is important to train the neural network with noise contaminated response data.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Detection of helicopter rotor system simulated faults using neural networks


    Weitere Titelangaben:

    Detektion simulierter Hubschrauberrotorschäden unter Anwendung neuronaler Netzwerke


    Beteiligte:
    Ganguli, R. (Autor:in) / Chopra, I. (Autor:in) / Haas, D.J. (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    1997


    Format / Umfang :

    11 Seiten, 14 Bilder, 6 Tabellen, 20 Quellen




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Print


    Sprache :

    Englisch





    Detection of helicopter rotor system simulated faults using neural networks

    Ganguli, Ranjan / Chopra, Inderjit / Haas, David | AIAA | 1996


    Detection of helicopter rotor system simulated faults using neural networks

    Ganguli, R. / Chopra, I. / Haas, D.J. | Tema Archiv | 1996


    Detection of Helicopter Rotor System Simulated Faults Using Neural Networks

    Ganguli, R. / Chopra, I. / Haas, D. et al. | British Library Conference Proceedings | 1996