焊缝缺陷X射线实时自动检测系统的图像处理

基金项目:

国家自然科学基金资助项目(50628506)

详细信息

Image Processing of Real-Time Automatic X-Ray Inspection System for Weld Defects

摘要: 针对焊缝缺陷X射线实时自动检测技术普遍存在误检率与漏检率高的问题, 研制了钢管焊缝缺陷X射线实时自动检测系统。研究了采用波形分析法与背景消除法信息融合进行焊缝缺陷检测的方法, 从而有效降低了误检率与漏检率。该系统已用于西气东输钢管焊缝缺陷X射线实时自动检测。
- 射线检测 /
- 焊缝缺陷 /
- 实时图像处理
Abstract: Real-time automatic X-ray inspection technique has the advantage of good consistency and high automation, so it is fit for on-line inspection of long weld. However this technique is hard to be applied in practice due to high false alarm and missed detection rates. Aiming at this problem, the real-time X-ray automatic inspection system for weld defects in pipe was established. The information fusion was proposed in two defect segmentation methods of weld X-ray image et al, background subtraction and grey level wave analysis, thus the false alarm and missed detection rates were decreased greatly. This system was being used for steel pipe manufacture in the West-East natural gas transmission project.
- Radiographic testing /
- Weld defects /
- Real-time image progressing

[1]	Du Dong, Cai Guo-rui, Tian Yuan, et al. Automatic Inspection of Weld Defects with X-ray Real-Time Imaging[J]. Lecture Notes in Control and Information Sciences,2007,362:359-366.
[2]	耿荣生.更快、更可靠和更直观——第16届世界无损检测会议综述[J].无损检测,2004,26(11):565-569.
[3]	Tian Yuan, Du dong, Hou runshi, et al. A model of automatic detection system for weld defects based on machine vision[J]. Lecture Notes in Control and Information Sciences,2007,362:341-348.
[4]	韩崇昭, 朱洪艳, 段战胜,等.多源信息融合[M].北京: 清华大学出版社, 2006.