Welding Groove Mapping - Implementation and Evaluation of Image Processing Algorithms on Shiny Surfaces

Electric arc welding is a key process in the heavy steel industries. It is a very complex task that demands a high degree of control in order to meet the international standards for fusion welding. We propose a Vision-Based Measurement (VBM) system and evaluate how different algorithms impact the results. The proposed system joins hardware and software to image the welding plates using a single CMOS camera, run computer vision algorithms and control the welding equipment. A complete prototype, using a commercial linear welding robot is presented. The evaluation of the system as a groove mapping equipment, considering different processing algorithms combined with noise removal and line segment detection techniques, allows us to define the appropriated approach for shop floor operation, combining low asymptotic cost and measurement quality.

[1]  Xiwen Liu.  Image Processing in Weld Seam Tracking with Laser Vision Based on Radon Transform and FCM Clustering Segmentation , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[2]  Paul Drews,et al.  Optical sensor systems for automated arc welding , 1986, Robotics.

[3]  Yakup Genc,et al.  Edge Drawing: A Heuristic Approach to Robust Real-Time Edge Detection , 2010, 2010 20th International Conference on Pattern Recognition.

[4]  Jiri Matas,et al.  Progressive probabilistic Hough transform for line detection , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[5]  Patrick Hébert,et al.  Median Filtering in Constant Time , 2007, IEEE Transactions on Image Processing.

[6]  Narciso García,et al.  Line segment detection using weighted mean shift procedures on a 2D slice sampling strategy , 2011, Pattern Analysis and Applications.

[7]  XuYi,et al.  Image smoothing via L0 gradient minimization , 2011 .

[8]  김철희,et al.  중공축 모터를 이용한 회전아크에 관한 연구 ( A Study on Rotating Arc Using Hollow Shaft Motor ) , 2000 .

[9]  Tao Lin,et al.  Robot welding seam tracking method based on passive vision for thin plate closed-gap butt welding , 2010 .

[10]  E. Halmoy.  Simulation of rotational arc sensing in gas metal arc welding , 1999 .

[11]  De Xu,et al.  Seam tracking and visual control for robotic arc welding based on structured light stereovision , 2004, Int. J. Autom. Comput..

[12]  Marcelo H. Ang,et al.  A walk‐through programmed robot for welding in shipyards , 1999 .

[13]  Rafael Grompone von Gioi,et al.  LSD: a Line Segment Detector , 2012, Image Process. Line.

[14]  Honghai Liu,et al.  Welding Image Edge Detection and Identification Research Based on Canny Operator , 2012, 2012 International Conference on Computer Science and Service System.

[15]  P. U. Dilthey,et al.  Through the arc sensing in GMA-welding with high speed rotating torch , 1998, IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200).

[16]  Alessandro Ferrero,et al.  Camera as the instrument: the rising trend of vision based measurement , 2014, IEEE Instrumentation & Measurement Magazine.

[17]  C. Hollitt.  Reduction of computational complexity of Hough transforms using a convolution approach , 2009, 2009 24th International Conference Image and Vision Computing New Zealand.

[18]  Jitendra Malik,et al.  Recovering high dynamic range radiance maps from photographs , 1997, SIGGRAPH.

[19]  E. Iso,et al.  Measurement Uncertainty and Probability: Guide to the Expression of Uncertainty in Measurement , 1995 .

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

[21]  Liguo Zhang,et al.  A novel laser vision sensor for weld line detection on wall-climbing robot , 2014 .

[22]  Cuneyt Akinlar,et al.  EDLines: A real-time line segment detector with a false detection control , 2011, Pattern Recognit. Lett..

[23]  Mamoru Kawahara,et al.  Tracking control system using image sensor for arc welding , 1983, Autom..

[24]  Thomas Risse,et al.  Hough transform for line recognition: Complexity of evidence accumulation and cluster detection , 1989, Comput. Vis. Graph. Image Process..