Vision Based Starting Position Recognition and Positioning Controlfor Thin Steel Sheet Welding Robot
CHEN Haiyong1,2, FANG Zaojun3, XU De3, SUN Hexu1,2
1. School of Control Sciences and Engineering, Hebei University of Technology, Tianjin 300130, China;
2. Hebei Control Engineering Technology Research Center, Tianjin 300130, China;
3. State Key Laboratory of Intelligent Control and Management for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
For the thin steel plate butt welding of containers, a visual control method of welding robot is proposed to recognize starting position and drive the weld torch to accurately track the starting position. Firstly, an iterative circle Hough transformation is presented, which can automatically obtain the region of interest including the torch characteristic point. In the second iteration, the torch characteristic point is recognized and extracted, robustly and quickly. Then the seam is recognized and its characteristic point is extracted by using line Hough transformation. Furthermore, an image space based visual control scheme of starting position is designed, and the accurate starting position control is achieved. The experimental results show that the proposed scheme can extract the torch's and seam's characteristic point coordinates, accurately and robustly. Moreover, the torch can be driven to the starting position quickly and accurately by using the visual control. Finally, test results in the container factory also verify the effectiveness of these methods, and the satisfactory results are obtained.
[1] 谢丁龙.基于计算机视觉的集装箱定位系统的研究[D].天津:天津科技大学,2006.Xie D L. Study on container position system based on computervision[D]. Tianjin: Tianjin University of Science and Technology,2006.[2] 方灶军,鄢治国,徐德.集装箱薄板的对接焊缝视觉跟踪系统[J].上海交通大学学报,2008,42(11):80-83.Fang Z J, Yan Z G, Xu D. Visual tracking system for narrowbutt seams on thin plate of container[J]. Journal of ShanghaiJiaotong University, 2008, 42(11): 80-83.[3] 刘蓉.带头在焊机处的精确定位[J].冶金动力,2006 (1):62-64.Liu R. Precise positioning of strip top at welder[J]. MetallurgicalPower, 2006(1): 62-64.[4] 辛立明,徐志刚,赵明扬,等.激光拼焊生产线定位误差分析及其控制[J].机械科学与技术,2009,28(2):163-166.Xin L M, Xu Z G, ZhaoMY, et al. Analysis and control of positionerror in tailored bland laser welding[J]. Mechanical Scienceand Technology for Aerospace Engineering, 2009, 28(2): 163-166.[5] 鄢治国,徐德,李原,等.基于示教与视觉纠偏的机器人自动焊接方法研究[J].机器人,2007,29(3):256-260.Yan Z G, Xu D, Li Y, et al. Automated robotic welding based onteaching and visual correction[J]. Robot, 2007, 29(3): 256-260.[6] 陈希章,陈善本.弧焊机器人起始焊接位置图像识别与定位[J].焊接学报,2009,30(4):17-22.Chen X Z, Chen S B. Recognition and positioning of start weldingposition for arc welding robot[J]. Transactions of the ChinaWelding Institution, 2009, 30(4): 17-22.[7] 梁潇,李原,梁自泽,等.基于DSP 的视觉传感器在焊接机器人上的应用[J].机器人,2007,29(5):444-450.Liang X, Li Y, Liang Z Z, et. al. DSP-based vision sensor appliedto welding robots[J]. Robot, 2007, 29(5): 444-450.[8] 朱振友.焊接机器人初始焊位视觉识别与导引研究[D].上海:上海交通大学,2004.Zhu Z Y. Research on visual servo scheme for initial position guiding with welding robot[D]. Shanghai: Shanghai JiaotongUniversity, 2004.[9] Zhu Z Y, Lin T, Piao Y J, et al. Recognition of the initial positionof weld based on the image pattern match technology for weldingrobot[J]. International Journal of Advanced ManufacturingTechnology, 2005, 26(7/8): 784-788.[10] Yan Z G, Xu D, Li Y, et al. A visual servoing system for thetorch alignment to initial welding position[M]//Lecture Notesin Computer Science (LNCS), vol.5315. Berlin, Germany:Springer-Verlag, 2008: 697-706.[11] 张俊强,张华.基于图像处理的移动机器人对目标的识别和定位[J].计算机测量与控制,2006,14(5):673-675.Zhang J Q, Zhang H. Recognition and locating of object basedon image-processing for mobile robot[J]. Computer Measurement& Control, 2006, 14(5): 673-675.[12] 方灶军.基于视觉的焊缝跟踪智能控制技术研究[D].北京:中国科学院自动化研究所,2011.Fang Z J. Study on the vision-based intelligent seam trackingcontrol[D]. Beijing: Institute of Automation, CAS, 2011.
