hybrid model is established for leak detection of longdistance gas transport pipelines. Firstly, a mechanism model is built on the basic transportflow equations, where the mass balance condition, momentum balance condition and state equation are considered. Next, a neural network model is used to compensate for the error of the mechanism model and improve the modelling precision. Here, the radial basis function (RBF) neural network is adopted. Therefore, the merits of the mechanism model and the neural network model are integrated to construct a hybrid model of long-distance gas pipelines. The experimental system of a long-distance pipeline is established and the pressure data of multiple nodes is collected. Finally, based on the experimental pressure data, the output of the mechanism model and the output of the hybrid model are compared. The comparison shows that the detection precision of the hybrid model is better.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Hybrid modelling for leak detection of long-distance gas transport pipeline


    Beteiligte:
    Wang, Junru (Autor:in) / Wang Tao (Autor:in) / Wang, Junzheng (Autor:in)

    Erschienen in:

    Insight ; 55 , 7 ; 372-381


    Erscheinungsdatum :

    2013


    Format / Umfang :

    10 Seiten, 30 Bilder, 4 Tabellen, 36 Quellen




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Print


    Sprache :

    Englisch





    Study outlines pipeline leak-detection selection

    Kristiansen, Morten | Tema Archiv | 2012


    Canadian pipeline installs leak-detection system

    Yoon, M.S. / Mensik, M. / Luk, W.Y. | Tema Archiv | 1988


    Post-earthquake pipeline leak detection technologies

    Du, Winncy Y. / Yelich, Scott W. | Tema Archiv | 2008