Visual Technique for Detecting Weld Position Based on Neural Network Technology

Abstract:

Seam tracking technology is an important area of research automatic arc welding, precise seam tracking is crucial to achieve high quality welds. In order to achieve precise seam tracking, seam deviation (the weld center arc deviation) detection is a key. Unlike the conventional method by image processing techniques to obtain the seam deviation information directly, but selected image processing area (including the distal end portion of the molten pool welds and the front end of the pool), and analyzed as a pool image centroid characteristic parameters of the weld deviation. Study these parameters to create a new method for visual weld deviation measurement model, establish the weld center neural network model using artificial neural network modeling technology.

• Periodical: Applied Mechanics and Materials (Volumes 530-531)
• Pages: 209-212
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.530-531.209
• Online since: February 2014
• Authors: Zhao Yu Li, Xiang Dong Gao
• Keywords: Neural Network (NN), Pool Image Centroid, Seam Tracking, Visual Model, Weld Deviation

References

[1] Z.H. Yan, G.J. Zhang and M.Z. Qiu: Pulse MIG welding pool image detection and treatment[J]. Transactions of the China Welding Institution 2005, 26 (2): 37～40.

[2] B.C. Li, T.Q. Peng and B. Peng: Intelligent image processing technology [M]. Publishing House of electronics industry, BeiJing (2004).

[3] X.D. Gao and X.Z. Luo: An image centroid method for seam tracking in gas tungsten arc welding [J]. Transactions of the China Welding Institution 2003, 24(6): 15～18.

[4] D.Q. Zhu and Hui Si. Principles and Applications of Artificial Neural Networks[M]. BeiJing: Science Press, (2006).

[5] J. Gao. Artificial neural network theory and simulation[M]. BeiJing：China Machine Press, (2003).

[6] Martin T. Hagan, Howard B. Demuth, Mark Beale. Neural Network Design[M]. BeiJing：China Machine Press，(2002).