Robust pattern recognition of three dimensional weld pool surface in gas tungsten arc welding

Measuring weld pool surfaces in real-time is the foundation for intelligent welding that emulates welders' sensory capability. To image and measure the mirror-like weld pool surface under the strong arc radiation, a structured light laser pattern, i.e., a dot matrix, is projected onto the weld pool surface and its specular reflection is intercepted and imaged by an imaging plane placed with a distance from the arc. In this paper, a robust recognition scheme is proposed to identify the reflection pattern of the dot matrix in real-time. In particular, an adaptive segmentation algorithm is developed to identify the reflection pattern. Then a pattern recognition is proposed to determine the row and column number of each laser dot in the pattern such that the reflection pattern can be matched with the projection pattern. The identified reflection pattern can be used to reconstruct the 3D weld pool surface. Experiments with different welding conditions have been conducted, and the real-time performance of the proposed procedure, including the effectiveness, robustness and time cost, has bee verified.

[1]  Bao Mi,et al.  Real-Time Weld Penetration Depth Monitoring With Laser Ultrasonic Sensing System , 2006 .

[2]  William J. Stewart,et al.  Probability, Markov Chains, Queues, and Simulation: The Mathematical Basis of Performance Modeling , 2009 .

[3]  Jeremy S. Smith,et al.  A novel edge feature correlation algorithm for real-time computer vision-based molten weld pool measurements , 2006 .

[4]  Rafael C. González,et al.  Digital image processing, 3rd Edition , 2008 .

[5]  Bryan A. Chin,et al.  A sensing system for weld process control , 1999 .

[6]  Shanben Chen,et al.  Visual sensing and penetration control in aluminum alloy pulsed GTA welding , 2009 .

[7]  Wu Lin,et al.  Reconstructing a three-dimensional P-GMAW weld pool shape from a two-dimensional visual image , 2006 .

[8]  Tao Lin,et al.  Binocular vision system for both weld pool and root gap in robot welding process , 2010 .

[9]  Carl D. Sorensen,et al.  Measurement of Oscillations in Partially Penetrated Weld Pools Through Spectral Analysis , 1990 .

[10]  Tao,et al.  RECONSTRUCTION OF WELD POOL SURFACE BASED ON SHAPE FROM SHADING , 2006 .

[11]  YuMing Zhang,et al.  Sensing Free Surface of Arc Weld Pool Using Specular Reflection: Principle and Analysis , 1996 .

[12]  Yuming Zhang,et al.  Three-dimensional reconstruction of specular surface for a gas tungsten arc weld pool , 2007 .

[13]  Nansheng Liu,et al.  Phase-correction algorithm of deformed grating images in the depth measurement of weld pool surface in gas tungsten arc welding , 2011 .

[14]  Pavel Pudil,et al.  Introduction to Statistical Pattern Recognition , 2006 .

[15]  Fengyan Zhang,et al.  Research on Surface Recover of Aluminum Alloy PGTAW Pool Based on SFS , 2011 .

[16]  YuMing Zhang,et al.  INSTITUTE OF PHYSICS PUBLISHING , 2003 .

[17]  A. J. R. Aendenroomer,et al.  Weld Pool Oscillation as a Tool for Penetration Sensing during Pulsed GTA Welding Measurement of the oscillation frequency of the weld pool during welding yields information about the penetration of the weld , 1998 .

[18]  Makoto Sato,et al.  Acoustic Emission Waveform Analysis From Weld Defects in Steel Ring Samples , 1999 .

[19]  I. C. Ume,et al.  Automated system for laser ultrasonic sensing of weld penetration , 1997, Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics.