Strong noise image processing for vision-based seam tracking in robotic gas metal arc welding

  • Rongqiang Du
  • Yanling XuEmail author
  • Zhen Hou
  • Jun Shu
  • Shanben Chen


The robustness of the image processing algorithm is very important based on vision sensor in robotic seam tracking, which will directly affect the accuracy of weld seam shaping quality. Especially in GMAW (Gas Metal Arc Welding), there is a lot of strong noise image. This paper studies an algorithm for the several weld seam images with strong noise in robotic GMAW, such as the atypical weld seam, the strong arc light and the large spatter. Based on a purpose-built visual sensing system, the fast image segmentation, the feature area recognition of the convolutional neural network (CNN), and the feature search technique are used to identify the weld seam features accurately in the algorithm. The selection range of the threshold is increased from 0.5 × 107 to 0.9 × 107 by using the proposed algorithm, which reduces the difficulty of parameter adjustment and increases the stability of seam tracking system. And, the accuracy of the CNN model was 98.0% for the atypical weld seam identification. To evaluate the robustness of the proposed algorithm, the accuracy is verified using experiments on two typical strong noise images. The experiments show that the average error of feature extraction accuracy is 0.26 mm and 0.29 mm. The results show that the proposed algorithm can extract the feature of weld seam image with strong noise accurately and effectively.


Feature extraction Strong noise image Robotic GMAW Seam tracking Convolutional neural network Image segmentation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


Funding information

This work is partly supported by the Shanghai Natural Science Foundation (18ZR1421500), the National Natural Science Foundation of China under the Grant Nos. 51405298 and 51575349, and the project of Qingpu District, and the State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System (GZ2016KF002).


  1. 1.
    Xu Y, Lv N, Fang G, S D, Zhao W, Ye Z, Chen S (2017) Welding seam tracking in robotic gas metal arc welding. J Mater Process Tech 248:18–30Google Scholar
  2. 2.
    Ding Y, Huang W, Kovacevic R (2016) An on-line shape-matching weld seam tracking system. Robot Cim-Int Manuf 42:103–112CrossRefGoogle Scholar
  3. 3.
    Zou Y, Wang Y, Zhou W, Chen X (2018) Real-time seam tracking control system based on line laser visions. Opt Laser Eng 103:182–192CrossRefGoogle Scholar
  4. 4.
    Ding D (2017) Design of integrated neural network model for weld seam tracking and penetration monitoring. Clust Comput 20(4):3345–3355Google Scholar
  5. 5.
    Muhammad J, Altun H, Abo-Serie E (2017) Welding seam profiling techniques based on active vision sensing for intelligent robotic welding. Int J Adv Manuf Technol 88(1–4):127–145Google Scholar
  6. 6.
    Wu QQ, Lee JP, Park MH, Jin JB, Kim DH, Park CK, Kim IS (2015) A study on the modified Hough algorithm for image processing in weld seam tracking. J Mech Sci Technol 29(11):4859–4865CrossRefGoogle Scholar
  7. 7.
    Gao X, Mo L, Xiao Z, Chen X, Katayama S (2015) Seam tracking based on Kalman filtering of micro-gap weld using magneto-optical image. Int J Adv Manuf Technol 83(1–4):21–32Google Scholar
  8. 8.
    Yue L, Guo X, Yu J (2016) An improved method of contour extraction of complex stripe in 3D laser scanning. DEStech Trans Eng Technol Res (ICMITE2016)Google Scholar
  9. 9.
    Zhang L, Ye Q, Yang W, Jiao J (2014) Weld line detection and tracking via spatial-temporal cascaded hidden Markov models and cross structured light. IEEE T Instrum Meas 63(4):742–753CrossRefGoogle Scholar
  10. 10.
    Fan F, Jing F, Fang Z, Tan M (2017) Automatic recognition system of welding seam type based on SVM method. Int J Adv Manuf Technol 92(1–4):989–999CrossRefGoogle Scholar
  11. 11.
    Karadeniz E, Ozsarac U, Yildiz C (2017) The effect of process parameters on penetration in gas metal arc welding processes. Mater Design 28(2):649–656CrossRefGoogle Scholar
  12. 12.
    Li X, Li X, Khyam MO, Ge SS (2017) Robust welding seam tracking and recognition. IEEE Sensors J 17(17):5609–5617CrossRefGoogle Scholar
  13. 13.
    Zou Y, Chen T (2018) Laser vision seam tracking system based on image processing and continuous convolution operator tracker. Opt Laser Eng 105:141–149CrossRefGoogle Scholar
  14. 14.
    Li X, Li X, Ge SS, Khyam MO, Luo C (2017) Automatic welding seam tracking and identification. IEEE T Ind Electron 64(9):7261–7271CrossRefGoogle Scholar
  15. 15.
    Liu J, Hu Y, Wu B, Frakes DH, Wang Y (2017) A specific structuring element-based opening method for rapid geometry measurement of weld pool. Int J Adv Manuf Technol 90(5–8):1465–1477CrossRefGoogle Scholar
  16. 16.
    Abdel-Hamid O, Mohamed A, Jiang H, Deng L, Penn YGD (2014) Convolutional neural networks for speech recognition. IEEE-ACM T Audio Spe 22(10):1533–1545Google Scholar
  17. 17.
    Kim Y (2014) Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  • Rongqiang Du
    • 1
  • Yanling Xu
    • 1
    Email author
  • Zhen Hou
    • 1
  • Jun Shu
    • 2
  • Shanben Chen
    • 1
  1. 1.School of Materials Science and EngineeringShanghai Jiao Tong UniversityShanghaiChina
  2. 2.Shanghai Hugong Electric Group Co., LtdShanghaiChina

Personalised recommendations