Digital ray detection is the mainstream technology for future ray detection, and traditional manual evaluation methods are not suitable for digital image evaluation. With the development of computer technology, the automatic detection and identification of welding defects is a hot issue in the current non-destructive testing of welding defects.
Taking a large-scale digital welding DR (Digital Radiography) image as the research object, the automatic detection and identification of welding defects was carried out, and the software system for automatic detection and identification of welding defect ray DR images was developed.
main research
(1) The DR image preprocessing algorithm is used to improve the contrast of DR images. An automatic detection algorithm for welding defect ray DR images is proposed. First, set the smoothing radius r and construct a smoothing template of (2r+1)×(2r+1). Then use image median filtering to create an ideal ideal weld image, and simulate the ideal weld image with the original image for image subtraction. Finally, find all areas where the subtraction difference exceeds the gray level connectivity (given the threshold) as a suspicious defect. The effects of two detection parameters of gray connectivity and smooth radius on the automatic detection results of welding defects are analyzed.
(2) According to the binary image and the original gray image generated by the automatic detection of welding defects, the characteristic parameters are analyzed and calculated for all the suspected defects. Nine characteristic parameters and calculation algorithms are proposed, and the corresponding results are obtained. According to the defect characteristic parameters, a qualitative analysis algorithm for welding defects is proposed to realize welding defect detection.
-
Sales@hata-ndt.com -
+86 371 63217179
