In this study, in order to facilitate application of the NNs as well as to provide user-friendly conditions, a performance diagnostic computer code using MATLAB® was newly proposed. As a result, not only more precise and prompt analysis results can be obtained due to use of the toolbox in MATLAB® on diagnosis and numerical analysis, but also the graphical user interface platform can be realized. The proposed engine diagnostics system is able to train the BPN with each fault pattern and then construct the total training network by assembling the trained BPNs. The database for network learning and test was constructed using a gas turbine performance simulation program. In order to investigate reliability on construction of the database for diagnostic results, an analysis is performed with five combination cases of 40 fault patterns. Finally, a diagnostic application example for the PT6A-62 turboprop engine is performed using the trained network with the database, which represents the best diagnostic results among test sets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Intelligent performance diagnostics of a gas turbine engine using user-friendly interface neural networks


    Beteiligte:
    Kong, Chang-duk (Autor:in) / Ki, Ja-young (Autor:in) / Kang, Myoung-cheol (Autor:in) / Kho, Seong-hee (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2004-08-01


    Format / Umfang :

    7 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Rocket engine diagnostics using neural networks

    WHITEHEAD, BRUCE / KIECH, EARL / ALI, MOONIS | AIAA | 1990


    Turbine Engine Diagnostics (TED) system

    DE HOFF, RONALD / MALTBAEK, CHRISTINA | AIAA | 1993


    Performing Diagnostics & Prognostics On Simulated Engine Failures Using Neural Networks

    Macmann, Owen B. / Seitz, Timothy M. / Behbahani, Alireza R. et al. | AIAA | 2016