Auto Identification of Weld Seam’s Initial Position for Visual Servoing Weld Robot

Abstract:

During the practical researches and applications based on passive visual servo, weld torch was often moved to the weld seam initial position manually by human or by the means of accurate mounting devices, which will often cause low efficiency, as well as a increase in manufacturing cost. To solve this problem an algorithm was presented in this paper to identify the initial position of the Aluminum plate weld seam. It’s totally based on passive visual servo system without utilizing any auxiliary optical equipment. This algorithm combined a variety of DIP techniques and approaches, accurate initial position could be extracted successfully. More images were processed by this method to confirm the validity. With the realization of auto-identification precision of the weld jig can be reduced dramatically and the degree of the automation and flexibility can be improved greatly.

• Periodical: Applied Mechanics and Materials (Volumes 130-134)
• Pages: 2447-2450
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.130-134.2447
• Online since: October 2011
• Authors: Yi Bo Deng, Hua Zhang, Guo Hong Ma
• Keywords: Image Processing, Seam Tracking, Visual Servo, Weld Automation

References

[1] YiJiong Tan, FangMing Zhou, JiangChao Wang. Trends and Achievements in welding robot technology [J]. Welding Machine, 2006(3): P6~10.

[2] Qiang Chen, ZhenGuo Sun. Computer Vision Sensing Technology and Its Application in Welding[J]. Transactions Of The China Welding Institution, 2001(1): p.83~90.

[3] S B Chen, et al. Intelligent methodology for sensing modeling and control of pulsed GTAW [J]. Welding Journal, 2000, 79(6).

[4] Zhongxi Sheng, Hongbo Ma, Shan chun Wei, Tao Lin. Automatatic Seam Tracking System Based on Vision Sensor [J]. Journal Of ShangHai Jiaotong University, Vol. 44 Sup. 2010(10). P. 130~133.

[5] Jingshan He, Chunli Yang, Sanbao Lin, et al. Image method seam tracking sensing system without auxiliary Light in TIG welding [J]. Transactions of the China welding institution, 2000, 21: P37~41.

[6] Boqi Zhang，Jun Zheng，Jiluan PAN, Tracing method based on visual inspection for butt-joint weld [J]. Electric Welding Machine Vol. 40, 2010 (12), P15~18.

[7] Otsu,N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics, 9(1) (1979), P62~66.

DOI: 10.1109/tsmc.1979.4310076

[8] Haralick,R., Shapiro,L. Computer and robot vision. AddisonWesley. Vol. 1, (1992), P28~48.