Research on Welding Line Defect Recognition of the In-Service Pipeline Using X-Ray Detecting

Abstract:

This paper, based on the practical demands of in-service pipeline detection, a set of X-ray digital image welding line defect intelligent recognition system is established. Taking the welding line image detected by X-ray as objects of study, self-adaptive median filter method filters noise, high frequency enhancement filter method conducts the image edge sharpening enhancement; a edge detection method for X-ray digital image based on morphological gradient is proposed; a group of characteristics parameters that accurately reflects the essence characteristic of defects is selected, using a self-organizing, self-adaptive three-layer feed-forward neural network, applying BP algorithm, the BP neural network recognition system is established, thus, to achieve detection and recognition of weld defects.

• Periodical: Applied Mechanics and Materials (Volumes 195-196)
• Pages: 5-12
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.195-196.5
• Online since: August 2012
• Authors: Pei Xin Yuan, Cong Cong Zhang, Yue Yuan
• Keywords: BP Algorithm, Digital Image Processing, Edge Detecting, Feature Extraction, Neural Network (NN), Weld Defects Recognition, X-Ray

References

[1] Wang Huan. Research on Digital Image Processing and Welding Line Defect Recognition of the In-service Pipeline via X-ray Detection. Master theses. Northeastern University . 2007. (In Chinese).

[2] Canny, John. A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698.

DOI: 10.1109/tpami.1986.4767851

[3] Gunn, S. R. Edge Detection Error in the Discrete Laplacian of a Gaussian. I Proceedings of IEEE International Conference on Image Processing, 1998, 515-519.

DOI: 10.1109/icip.1998.723491

[4] Gunn, S, R. On the Discrete Representation of the Laplacian of a Gaussian Pattern Recognition, (1999).

[5] Jin Zhong, Bo Feng, Zhang Lin Hill. A X-ray digital image weld edge inspection method based on morphology. Measurement techniques, 2006, (5). (In Chinese).

[6] Lashkia．V Defect detection in x—ray images using fuzz— Y reasoning．Image and Vision Computing，2001，19(5)：261—269.

[7] Wang Shuwen, Yan Cheng, Zhang Tian-Xu and so on. Mathematical Morphology in Image Processing, Computer Engineering and Applications, 2004, 40 (32) : 89-92. (In Chinese).

[8] Xudong, Huang Ke is, Shang Yong and so on. Intelligent choice of cutting the neural network modeling, Machine Tool & Automatic Manufacturing Technique, 1999, (10) : 13-16, 41. (In Chinese).

[9] Lu lineage THE CHINA. Feedforward neural network hidden nodes dynamically removed, Control Theory and Applications, 1997, 14 (1) : 101-104. (In Chinese).