Abstract
The welding deviation detection is the basis of robotic tracking welding, but the on-line real-time measurement of welding deviation is still not well solved by the existing methods. There is plenty of information in the gas metal arc welding(GMAW) molten pool images that is very important for the control of welding seam tracking. The physical meaning for the curvature extremum of molten pool contour is revealed by researching the molten pool images, that is, the deviation information points of welding wire center and the molten tip center are the maxima and the local maxima of the contour curvature, and the horizontal welding deviation is the position difference of these two extremum points. A new method of weld deviation detection is presented, including the process of preprocessing molten pool images, extracting and segmenting the contours, obtaining the contour extremum points, and calculating the welding deviation, etc. Extracting the contours is the premise, segmenting the contour lines is the foundation, and obtaining the contour extremum points is the key. The contour images can be extracted with the method of discrete dyadic wavelet transform, which is divided into two sub contours including welding wire and molten tip separately. The curvature value of each point of the two sub contour lines is calculated based on the approximate curvature formula of multi-points for plane curve, and the two points of the curvature extremum are the characteristics needed for the welding deviation calculation. The results of the tests and analyses show that the maximum error of the obtained on-line welding deviation is 2 pixels(0.16 mm), and the algorithm is stable enough to meet the requirements of the pipeline in real-time control at a speed of less than 500 mm/min. The method can be applied to the on-line automatic welding deviation detection.
Similar content being viewed by others
References
PRESERN S, GYERGYEK L. An intelligent tactile sensor-an on-line hierarchical object and seam analyzer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1983, PAMI-5(2): 217–219.
SHI Y H, YOO W S, NA S J. Mathematical modeling of rotational arc sensor in GMAW and its applications to seam tracking and endpoint detection[J]. Science and Technology of Welding and Joining, 2006, 11(6): 723–730.
HONG Bo, YAN Junguang, YANG Jiawang, et al. A capacitive sensor for automatic weld seam tracking[J]. Transactions of the China Welding Institution, 2014, 35(2): 55–58. (in Chinese)
YOU B H, KIM J W. A study on an automatic seam tracking system by using an electromagnetic sensor for sheet metal arc welding of butt joints[J]. Proceedings of Institution of Mechanical Engineers, 2002: 911–920.
HU Shengsun, MENG Yingqian, LIU Yong. Development of seam tracking system with ultrasonic sensor using self-tuning fuzzy control[J]. China Welding, 2001, 10(1): 39–42.
WU Minsheng, CHEN Wuzhu, HE Fangdian, et al. A seam tracking sensor with modulated infrared beam for arc welding[J]. Journal of Tsinghua University(Science and Technology), 1990, 30(2): 31–36. (in Chinese)
LIU Suyi, WANG Guorong, ZHANG Hua, et al. Design of robot welding seam tracking system with structured light vision[J]. Chinese Journal of Mechanical Engineering, 2010, 23(4): 436–442.
JIANG Lipei, XUE Long, ZOU Yong. Practical technology of welding automation[M]. Beijing: China Machine Press, 2010. (in Chinese)
ZHANG Y M, KOVACEVIC R, LI L. Characterization and real-time measurement of geometrical appearance of the weld pool[J]. International Journal of Machine Tools & Manufacture, 1996, 36(7): 799–816.
XU Yanling, FANG Gu, Lü Na, et al. Computer vision technology for seam tracking in robotic GTAW and GMAW[J]. Robotics and Computer-Integrated Manufacturing, 2015, 32: 25–36.
YANG Jiajia, WANG Kehong, WU Tongli, et al. Two-directional synchronous visual sensing and image processing of weld pool in aluminum alloy twin arc pulsed MIG welding[J]. Journal of Mechanical Engineering, 2014, 50(12): 44–50. (in Chinese)
ZHANG Guokai, WU Chuansong, LIU Xinfeng. Single vision system for simultaneous observation of keyhole and weld pool in plasma arc welding[J]. Journal of Materials Processing Technology, 2015, 215: 71–78.
GAO Jinqiang, QIN Guoliang, YANG Jialin, et al. Image processing of weld pool and keyhole in Nd:YAG laser welding of stainless steel based on visual sensing[J]. Transactions of Nonferrous Metals Society of China, 2011, 21(2): 423–428.
BRZAKOVIC D, KHANI D T. Weld pool edge detection for automated control of welding[J]. IEEE Transactions on Robotics and Automation, 1991, 7(3): 397–403.
LUO M, SHIN Y C. Vision-based weld pool boundary extraction and width measurement during keyhole fiber laser welding[J]. Optics and Lasers in Engineering, 2015, 64: 59–70.
LEONARDO N, RONALD T, FELIX A, et al. Novel algorithm for the real time multi-feature detection in laser beam welding[C]//IEEE International Symposium on Circuits and Systems(ISCAS), COEX, Seoul, Korea, May 20–23, 2012: 181–184.
ZHANG Weijie, LIU Yukang, ZHANG Yuming. Real-time measurement of the weld pool surface in GTAW process[C].//IEEE International Instrumentation & Measurement Technology Conference, Minneapolis, USA, May 6–9, 2013: 1640–1645.
XIONG Zhenyu, GU Wangping, WANG Jian, et al. Molten pool image processing and feature extraction based on multiple visions[J]. Electric Welding Machine, 2013, 43(5): 93–96. (in Chinese)
ZHANG Gang, SHI Yu, LI Chunkai, et al. Research on the correlation between the status of three-dimensional weld pool surface and weld penetration in TIG welding[J]. Acta Metallurgica Sinica, 2014, 50(8): 995–1002. (in Chinese)
JIAO Xiangdong, YANG Yongyong, ZHOU Canfeng. Seam tracking technology for hyperbaric underwater welding[J]. Chinese Journal of Mechanical Engineering, 2009, 22(2): 265–269.
HIRAI A, KANEKO Y, HOSODA T, et al. Sensing and control of weld pool by fuzzy-neural network in robotic welding system[C].//The 27th Annual Conference of the IEEE Industrial Electronics Society, Denver, USA, November 29–December 02, 2001: 238–242.
GAO Xiangdong, DING Dukun, BAI Tianxiang, et al. Weld pool image centroid algorithm for seam tracking in arc welding process[J]. IET Image Processing, 2011, 5(5): 410–419.
FENG Shengqiang, TERASAKI H, KOMIZO Y, et al. Development of evaluation technique of GMAW welding quality based on statistical analysis[J]. Chinese Journal of Mechanical Engineering, 2014, 27(6): 1257–1263.
BASKORO A S, ERWANTO, WINARTO. Monitoring of molten pool image during pipe welding in gas metal arc welding(GMAW) using machine vision[C]//2011 International Conference on Advanced Computer Science and Information System (ICACSIS), Jakarta, Indonesia, December 17–18, 2011: 381–384.
LIU J, FAN Z, OLSEN S I, et al, Weld pool visual sensing without external Illumination[C]//IEEE International Conference on Automation Science and Engineering, Trieste, Italy, August 24–27, 2011: 145–150.
FAN Fanglei, LI Liangyu, YUE Jianfeng, et al. An image processing arithmetic of the molten pool during GMAW welding[J]. Mechanical Science and Technology for Aerospace Engineering, 2008, 27(10): 1199–1201. (in Chinese)
YUE Jianfeng, LI Liangyu, FAN Fanglei, et al. Welding pool adaptive vision detection for arc welding robot gas metal arc welding[J]. Chinese Journal of Mechanical Engineering, 2008, 44(4): 206–210. (in Chinese)
LI Jing, QIN Xiaolin, LI Fang, et al. New method based on region coarse localization and Chan-Vese model for weld pool edge extraction in MAG welding[J]. Journal of Mechanical Engineering, 2011, 47(12): 74–78. (in Chinese)
WU Mingliang, ZHANG Gang, HUANG Jiankang, et al. Edge detection for aluminum alloy MIG welding pool based on pulse coupled neural network[C]//Seventh International Conference on Natural Computation, Shanghai, China, July 26–28, 2011: 691–694.
XUE Jiaxiang, JIA Lin, LI Haibao, et al. Edge detection of molten pool and weld line for CO2 welding based on B-spline wavelet[J]. China Welding, 2004, 13(2): 137–141.
LI Yuan, WANG Qinglin, XU De, et al. Processing and features extraction of molten pool for pipe welding[J]. Transactions of the China Welding Institution, 2008, 29(8): 57–60. (in Chinese)
LIU Pengfei, SUN Zhenguo, HUANG Cao, et al. Weld pool image sensor for pulsed MIG welding[J]. China Welding, 2008, 17(1): 1–5.
LI Jing, LI Fang, ZHU Wei, et al. A new seam location extraction method for pipe-line backing welding of MAG based on passive optical vision sensor[J]. Transactions of the China Welding Institution, 2011, 32(10): 69–72. (in Chinese)
BAE K Y, LEE T H, AHN K C. An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe[J]. Journal of Materials Processing Technology, 2002, 120: 458–465.
ZOU Yong, LI Yunhua, JIANG Lipei, et al. Weld pool image processing algorithm for seam tracking of welding robot[C]//2011 Sixth IEEE Conference on Industrial Electronics and Applications, Beijing, China, June 21–23, 2011: 155–159.
ZOU Yong, JIANG Lipei, XUE Long, et al. Man-machine interaction system of all-position welding robot of pipeline[J]. Electric Welding Machine, 2009, 39(4): 56–58.
TIAN Yanyan, QI Guoqing. Edge detection based on wavelet transform module maxima[J]. Journal of Dalian Maritime University, 2007, 33(1): 102–106.
ZOU Yong, LI Yunhua, JIANG Lipei, et al. Method of detecting weld deviation based on molten pool image edge features[J]. Transactions of the China Welding Institution, 2015, 36(8): 18–22. (in Chinese)
WANG Yinghui, WU Weiyong, ZHAO Rujia. Segmentation and recognition techniques for planar contour[J]. Journal of Computer Aided Design & Computer Graphics, 2002, 14(12): 1142–1145.
Author information
Authors and Affiliations
Corresponding author
Additional information
ZOU Yong, born in 1976, is currently a PhD candidate at Beihang University, China. He is also a teacher at Beijing Institute of Petrochemical Technology, China. He received his master degree from China University of Petroleum(Beijing), China, in 2004. His research interests include welding automation and robots.
JIANG Lipei, born in 1942, is currently a professor and a PhD candidate supervisor at Beijing Institute of Petrochemical Technology, China. His research interests include welding power and technology, welding automation and underwater welding.
LI Yunhua, born in 1963, is currently a professor and a PhD candidate supervisor at Beihang University, China. His main research interests include mechachonics, hydraulic control, and robotics.
XUE Long, born in 1966, is currently a professor at Beijing Institute of Petrochemical Technology, China. His research interests include automation and robotics, underwater welding.
HUANG Junfen, born in 1975, is currently a lecturer at Beijing Institute of Petrochemical Technology, China. Her research interests include underwater welding, robotics.
HUANG Jiqiang, born in 1971, is currently an associate professor at Beijing Institute of Petrochemical Technology, China. His research interests include underwater welding, automation.
Rights and permissions
About this article
Cite this article
Zou, Y., Jiang, L., Li, Y. et al. Welding deviation detection algorithm based on extremum of molten pool image contour. Chin. J. Mech. Eng. 29, 74–83 (2016). https://doi.org/10.3901/CJME.2015.0908.110
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3901/CJME.2015.0908.110