Neural-network-based adaptive dynamic models are commonly used to estimate allowable control travel and the proximity to a limiting flight condition in the design of advanced envelope protection algorithms for fly-by-wire aircraft. In this paper, linear models are compensated with adaptive neural networks, which use instantaneous sensor data as well as past flight history information for concurrent learning. A law for collecting appropriate training data into the history stack is established. It is observed that using the proposed time history data for online neural network training provides more accurate dynamic trim and control limit predictions compared to using instantaneous sensor data only. Simulation results for a fixed-wing aircraft during maneuvers show comparisons between the different adaptation schemes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Concurrent Learning Enabled Adaptive Limit Detection for Active Pilot Cueing


    Beteiligte:
    Gursoy, Gonenc (Autor:in) / Yavrucuk, Ilkay (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2014-07-04


    Format / Umfang :

    9 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Concurrent Learning Enabled Adaptive Limit Detection for Active Pilot Cueing

    Gursoy, G. / Yavrucuk, I. | British Library Conference Proceedings | 2010



    DEVELOPMENT OF A LIMIT AVOIDANCE FRAMEWORK FOR ACTIVE PILOT CUEING

    Gursoy, Gonenc / Unal, Zeynep / Akmenek, Bulut Efe et al. | British Library Conference Proceedings | 2019


    Active-inceptor tactile-cueing hands-off rate-limit

    IRWIN III JOSEPH G / EINTHOVEN PIETER G / MILLER DAVID G et al. | Europäisches Patentamt | 2015

    Freier Zugriff

    PILOT CUEING FOR ROTORCRAFT SHIPBOARD LANDINGS

    Walters, Robert / McCandless, Joseph / Feigh, Karen M. | TIBKAT | 2020