Review of status and prospect of weld defect detection

HU Dan, GAO Xiang-dong, ZHANG Nan-feng, ZHANG Yan-xi,
YOU De-yong, XIAO Xiao-ting, SUN You-song
(Guangdong Provincial Welding Engineering Technology Research Center,
Guangdong University of Technology, Guangzhou 510006, China)

Abstract: Aiming at the technical problems of weld surface shape defect detection, the weld surface defect detection methods were studied. The principle, basic structure, application scope and the research status of magnetic particle testing, ultrasonic testing, eddy current testing, penetrant testing, magnetooptical imaging testing, infrared detection and structuredlight vision testing were discussed. The theory and algorithm of image acquisition, image processing, feature extraction and weld defect classification and recognition based on structuredlight vision testing were summarized and analyzed systematically. The results indicate that in order to meet the requirements of comprehensive inspection of weld defects, multiinspection technology can be integrated and the advantages are complementary. With the development of artificial intelligence technology and the improvement of welded parts quality requirements, the realization of weld defects detection technology visualization, automation is the future development trend. Artificial intelligence technology is the key technology of weld defect detection. There is still a long way in that the real intelligent detection is achieved.
Key words: weld defects; nondestructive testing; physical detection; structuredlight vision testing