Author： Lim T Y Ratnam M M Khalid M A
Publisher： The British Institute of Non-Destructive Testing
ISSN： 1354-2575
Source： Insight - Non-Destructive Testing and Condition Monitoring, Vol.49, Iss.3, 2007-03, pp. : 154-159
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
An effective weld defect classification algorithm has been developed using a large database of simulated defects. Twenty-five shape descriptors used for the classification were studied and an optimal set of nine descriptors with highest discriminative capability was selected using a statistical approach. A multi-layer perceptron (MLP) neural network was trained using shape parameters extracted from the simulated images of weld defects. By testing on 60 unknownsimulated defects, the optimised set of nine shape descriptors gave the highest classification accuracy of 100%. Defect classification on 49 real defects from digitised radiographs produced maximum overall classification accuracy of 97.96%.
Related content
Access to resources
Recommend
By Shitole C'Shekhar N Zahran O Al-Nuaimy W
Insight - Non-Destructive Testing and Condition Monitoring, Vol. 49, Iss. 2, 2007-02 ,pp. :
By Al-Ataby A Al-Nuaimy W Brett C R Zahran O
Insight - Non-Destructive Testing and Condition Monitoring, Vol. 52, Iss. 11, 2010-11 ,pp. :