Abstract Accurate fault prognosis of track circuit is important to maintain railway signaling system. A method widely used is fuzzy neural network (FNN). However, a typical problem with such method is the lack of flexibility of the fuzzy operators. A practical solution is introducing the generalized weighted average (GWA) operator to replace the transfer functions of neurons in rule and output layers. The strength of logic operation would be adjusted by compensation parameters so as to simulate the flexibility of human thinking. In this paper, we propose a fault prognosis model based on GWA-FNN and deduce the iterative algorithm of training parameters. The simulation results show that the fault prognosis of track circuit based on GWA-FNN has better accuracy and generalization ability compared to Sum–Prod model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fault Prognosis of Track Circuit Based on GWA Fuzzy Neural Network


    Beteiligte:
    Wang, Meng (Autor:in) / Zheng, Hongyun (Autor:in) / Huang, Zanwu (Autor:in)


    Ausgabe :

    1st ed. 2016


    Erscheinungsdatum :

    2016-01-01


    Format / Umfang :

    9 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Track circuit fault diagnosis method and system

    XIAO CAIXIA / ZHOU MINGXI / HE LIANG et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    Fault isolation, prognosis, and mitigation for vehicle component electrical power circuit

    LIN WEN-CHIAO / DU XINYU / ALLAN ALEXANDER M et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Fault isolation, prognosis, and mitigation for vehicle component electrical power circuit

    LIN WEN-CHIAO / DU XIANGLONG / ALLAN ALEXANDER M et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Track Predition Based on CNN-GRU Neural Network

    Ju, Cong / Fu, Yuhui / Li, Chenghao | IEEE | 2023