Automatic detection and classification of weld flaws in TOFD data using wavelet transform and support vector machines

作者：Al Ataby A^*; Al Nuaimy W; Brett C R; Zahran O

来源：Insight: Non-Destructive Testing and Condition Monitoring , 2010, 52(11): 597-602.

DOI：10.1784/insi.2010.52.11.597

Ultrasonic tine-of-flight diffraction (TOED) is known as a reliable non-destructive testing technique for the inspection of welds in steel structures, providing accurate positioning and sizing off-laws. The automation of data processing in TOED is required towards building a comprehensive computer-aided TOED inspection and interpretation tool. A number of signal and image processing tools have been specifically developed for use with TOED data. These tools have been adapted to unction autonomously, without the need for continuous intervention through automatic configuration of the critical parameters according to the nature of the data and the acquisition settings. This paper presents several multi-resolution approaches employing the wavelet transform and texture analysis for de-noising and enhancing the quality of data to help in the automatic detection and classification of defects. The automatic classification is implemented using a support vector machines classifier, which is considered faster and more accurate than artificial neural networks. The results achieved so far have been promising in terms of accuracy, consistency and reliability.

• 出版日期2010-11