A neuro-fuzzy-structure is applied to the classification of faults, based on symptoms generated by identifying a mathematical model. The hybrid neuro-fuzzy scheme SARAH used consists of three layers corresponding to the three fuzzy inference steps. All parameters are automatically determined based on experimental data by clustering and learning. Finally the performance of the diagnosis scheme is illustrated on the example of an automobile actuator with several different faults.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Fault diagnosis of electromechanical actuators using a neuro-fuzzy network


    Additional title:

    Fehlerdiagnose von elektromechanischen Stellgeräten mit Neuro-Fuzzy-Netzen


    Contributors:
    Pfeufer, T. (author) / Ayoubi, M. (author)


    Publication date :

    1995


    Size :

    9 Seiten, 7 Bilder, 2 Tabellen, 25 Quellen


    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Automated fault diagnosis using neuro-fuzzy systems

    Benkhedda, Hassen / Patton, Ron | AIAA | 1996


    Fault diagnosis using Neuro-Fuzzy Transductive Inference algorithm

    Bo Zhang, / Jianjun Luo, / Zhiqiu Chen, et al. | IEEE | 2008


    Electromechanical actuators

    Bigham, J. | NTRS | 1982


    Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems

    Chen, J. / Roberts, C. / Weston, P. | Tema Archive | 2008


    Adaptive Neuro-Fuzzy Inference Controllers for Smart Material Actuators

    Grigorie, T. / Botez, R. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 2010