Vision-based initial weld point positioning using the geometric relationship between two seams

This paper presents a novel vision-based initial weld point positioning method for the welding systems of container manufacture. The new method is based on the geometric relationship between the two seams at the two different stages of the whole welding task such as the initialization stage and the welding stage. The torch is aligned with the initial weld point manually at the first stage, and the image feature and the parameters of the seam line are computed. At the second stage, the target image feature of the seam line is firstly computed using the geometric relationship, then the alignment of the torch is automated based on the difference between the target and the current image features. The geometric relationship between the two seams is analyzed, and then the realization of the new method including the image processing, the computation of the parameters of the seam line, and the control system design is given in detail. Finally, experiments are well conducted to prove the effectiveness of the proposed initial weld point positioning method.

[1]  Hsing-Chia Kuo,et al.  An image tracking system for welded seams using fuzzy logic , 2002 .

[2]  Tao Lin,et al.  Recognition of the initial position of weld based on the image pattern match technology for welding robot , 2005 .

[3]  G. Pritschow,et al.  Fast and robust image processing for laser stripe-sensors in arc welding automation , 2002, Industrial Electronics, 2002. ISIE 2002. Proceedings of the 2002 IEEE International Symposium on.

[4]  Lin Li,et al.  Adaptive control of full penetration gas tungsten arc welding , 1996, IEEE Trans. Control. Syst. Technol..

[5]  De Xu,et al.  Visual seam tracking system for butt weld of thin plate , 2010 .

[6]  Kang-Yul Bae,et al.  An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe , 2002 .

[7]  Tao Lin,et al.  Practical method to locate the initial weld position using visual technology , 2006 .

[8]  Yanling Xu,et al.  Real-time seam tracking control technology during welding robot GTAW process based on passive vision sensor , 2012 .

[9]  Shan-Ben Chen,et al.  The autonomous detection and guiding of start welding position for arc welding robot , 2010, Ind. Robot.

[10]  De Xu,et al.  A Vision-Based Self-Tuning Fuzzy Controller for Fillet Weld Seam Tracking , 2011, IEEE/ASME Transactions on Mechatronics.

[11]  Suck-Joo Na,et al.  A study on automatic seam tracking in pulsed laser edge welding by using a vision sensor without an auxiliary light source , 2002 .

[12]  Xu Lin,et al.  A method to locate initial welding position of container reinforcing plates using structured-light , 2008, 2008 27th Chinese Control Conference.

[13]  Mikael Fridenfalk Development of intelligent robot systems based on sensor control , 2003 .

[14]  Xinhua Tang,et al.  A visual seam tracking system for robotic arc welding , 2008 .

[15]  Yong Qiang Wu,et al.  A Fuzzy Controller Design of Seam Tracking for Welding Robot , 2012 .

[16]  Y. M. Zhang,et al.  Control of dynamic keyhole welding process , 2007, Autom..