Laser-vision-based quality inspection system for small-bead laser welding

A laser-vision-based weld quality inspection system was developed and implemented for non-destructive weld measurement and defect detection. Our laser vision sensor module is designed based on the principle of laser triangulation. This paper summarizes our work on weld joint profile extraction, feature point extraction, weld bead size measurement, and defect detection. The configuration of the laser vision sensor is described and analyzed in detail, as well as the proposed image processing algorithms. A fast and reliable approach for detecting feature points on the laser stripe profile is proposed by using a sliding vector method. Weld joint modeling and dimension measurement methods are discussed in detail. The system allows the three-dimensional (3D) profile of the weld surface to be reconstructed in real time to allow weld monitoring and control, as well as post-weld quality inspection. Some experiments were implemented for size measurement and defect detection, using the laser-vision-based weld quality inspection system for small-sized beads. Experimental results show that the proposed system achieves highly accurate and satisfactory performance for real-time inspection requirements.

[1]  R. White,et al.  A vision system for automated crack detection in welds , 1990 .

[2]  M. Predoi,et al.  Ultrasonic inspection of defects in welded plates and tubes , 1997, 1997 IEEE Ultrasonics Symposium Proceedings. An International Symposium (Cat. No.97CH36118).

[3]  Hartmut Ewald.  3-dimensional magnetic leakage field sensor in nondestructive testing , 2003, Proceedings of the 20th IEEE Instrumentation Technology Conference (Cat. No.03CH37412).

[4]  Li Yu,et al.  The research of defect recognition for radiographic weld image based on fuzzy neural network , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[5]  T. Warren Liao,et al.  Fuzzy reasoning based automatic inspection of radiographic welds: weld recognition , 2004, J. Intell. Manuf..

[6]  Se Hun Rhee,et al.  Measurement of Weld Bead Defect for Shock Absorber Using Laser Vision Sensor , 2004 .

[7]  TANMin,et al.  Hybrid Visual Servoing Control for Robotic Arc Welding Based on Structured Light Vision , 2005 .

[8]  F. Sikstrom,et al.  3D-Scanning for Weld Distortion Measuring , 2006, 2006 IEEE Instrumentation and Measurement Technology Conference Proceedings.

[9]  S. Kumar,et al.  An optical triangulation method for non-contact profile measurement , 2006, 2006 IEEE International Conference on Industrial Technology.

[10]  Dai Guangzhi,et al.  Research on Image Resolution in Ultrasonic Imaging Inspection of Welding Defect , 2007, 2007 8th International Conference on Electronic Measurement and Instruments.

[11]  Chia-Lung Chang,et al.  Weld contour measurement of fillet welds by the reverse engineering technique , 2008 .

[12]  Hwann-Tzong Chen,et al.  Histogram-based interest point detectors , 2009, CVPR.

[13]  Richard Szeliski,et al.  Computer Vision , 2010 .

[14]  J. Yang,et al.  Typical Joint Defects in Laser Welding of Aluminium-Lithium Alloy , 2010 .

[15]  Daniel F. García,et al.  Fast and robust laser stripe extraction for 3D reconstruction in industrial environments , 2010, Machine Vision and Applications.

[16]  De Xu,et al.  Measurement and Defect Detection of the Weld Bead Based on Online Vision Inspection , 2010, IEEE Transactions on Instrumentation and Measurement.

[17]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[19]  Bum-Sik So,et al.  Flexible vision inspection for seat frame of automobile using slit beam , 2011 .

[20]  Eung Suk Lee,et al.  A glass thickness measuring system using the machine vision method , 2011 .

[21]  B. Lee,et al.  Radius measuring algorithm based on machine vision using iterative fuzzy searching method , 2012 .