Pipeline-safety evaluation is an important problem for industry. On the basis of the magnetic-flux-leakage (MFL) method, this paper presents an automated inspection device for inspection of pipeline defects, analyzes the MFL-inspection theory and some defect-feature parameters, and gives a recognizing algorithm based on a dynamic wavelet-basis-function (WBF) neural network. This dynamic network utilizes a multiscale and multiresolution orthogonal wavelet and backward-propagating through signals and has more significant advantages than BP or other neural networks used in MFL inspection. It also can control the accuracy of the predicted defect profiles, possessing high-speed convergence and good approaching features. The performance that applies the algorithm based on the network for predicting a defect profile from experimental MFL signals is also presented.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on a recognition algorithm for offshore-pipeline defects during magnetic-flux inspection


    Additional title:

    Untersuchung eines Erkennungsalgorithmus von Fehlern an Offshorepipelines bei der magnetischen Streuflussprüfung


    Contributors:
    Tao, J. (author) / Peiwen, Q. (author) / Liang, C. (author) / Liang, L. (author)

    Published in:

    Publication date :

    2005


    Size :

    8 Seiten, 9 Bilder, 2 Tabellen, 7 Quellen




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English