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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fault Prognosis of Track Circuit Based on GWA Fuzzy Neural Network


    Contributors:
    Wang, Meng (author) / Zheng, Hongyun (author) / Huang, Zanwu (author)


    Edition :

    1st ed. 2016


    Publication date :

    2016-01-01


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





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

    LIN WEN-CHIAO / DU XINYU / ALLAN ALEXANDER M et al. | European Patent Office | 2021

    Free access

    Track Predition Based on CNN-GRU Neural Network

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


    A fault diagnosis method for the tuning area of jointless track circuits based on a neural network

    Zhao, Lin-Hai / Zhang, Cai-Lin / Qiu, Kuan-Min et al. | SAGE Publications | 2013