A hybrid knowledge-based approach for leak monitoring in pipes and pipelines used for the transport of fluids (liquids, LPG (Liquefied Petroleum Gas), gases). The hybrid leak detection and realization scheme combines real time transient model based methods with artificial neural networks. This enables to combine analytical knowledge available prior to system operation with knowledge by example, presented in form of measured process signals. Knowledge by example can be presented before and during system operation, enabling a flexible information processing scheme. A real application for a pipeline transporting petrochemical liquids demonstrates the performance of the approach.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Knowledge-based leak monitoring for pipelines


    Additional title:

    Wissensbasierte Lecküberwachung für Pipelines


    Contributors:
    Geiger, G. (author) / Werner, T. (author) / Matko, D. (author)


    Publication date :

    2001


    Size :

    6 Seiten, 7 Bilder, 10 Quellen



    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Leak detection on petroleum pipelines

    Allen, Randall | Tema Archive | 2012


    Leak detection methods for pipelines

    Billmann, L. / Isermann, R. | Tema Archive | 1987


    Leak detection methods for gas pipelines

    Benkherouf, A. / Allidina, A.Y. | Tema Archive | 1987


    Leak detection methods in transmission pipelines

    El-Shiekh, T.M. | Tema Archive | 2010


    Leak location of pipelines based on characteristic entropy

    Ni, Lei / Jiang, Juncheng / Pan, Yong et al. | Tema Archive | 2014