This paper presents the results from a pilot study of a 'smart system ', used for defect detection in railroad rails. The experimental data used to train the pattern recognition 'smart system', were extracted from experiments conducted during a previous long range ultrasonic guided wave study. Reflection coefficient plots corresponding to a variety of transverse and oblique defects were shown to provide features that were successfully used to train a 'smart System'to identify those defects automatically. This paper presents a brief introduction to support vector machines, followed by a description of the procedure used to determine the best training data to be used to train the 'smart System',, and concluding with lessons learned during this study.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Smart system for long range ultrasonic defect detection of railroad rails


    Additional title:

    Intelligentes System zum weit reichenden Fehlernachweis von Eisenbahnschienen mit Ultraschall


    Contributors:

    Published in:

    Publication date :

    2004


    Size :

    7 Seiten, 5 Bilder, 2 Tabellen, 5 Quellen



    Type of media :

    Conference paper


    Type of material :

    Storage medium


    Language :

    English





    Air coupled ultrasonic testing of railroad rails

    McNamara, J. / Lanza di Scalea, F. | Tema Archive | 2002


    Welded railroad rails

    Clason, C.B. | Engineering Index Backfile | 1944


    Welded railroad rails

    Clason, C.B. | Engineering Index Backfile | 1945


    Fissures in railroad rails

    Moore, H.F. | Engineering Index Backfile | 1940