Modeling and Optimization of Adjustment of Human Welder on Weld Pool Dynamics for Intelligent Robot Welding

  • Gang ZhangEmail author
  • Yukang Liu
  • Yu Shi
  • Ding Fan
  • Yuming Zhang
Conference paper
Part of the Transactions on Intelligent Welding Manufacturing book series (TRINWM)


An improved machine–human cooperative control system was developed to obtain sufficient data pairs for modeling welder’s adjustment on weld pool dynamics by data-driven approaches. Spectral analysis shows that weld widths are apparently changed due to low-frequency variations of the welder’s hand movement, which can be filtered by a low-pass filter to remove the high-frequency components. The effect of welding torch orientation on weld pool dynamics was numerically studied to understand the mechanism of human welder’s adjustment and to provide the useful data for control system optimization. A gay multiple linear regression model (GMLRM) was employed to analyze the contribution and interactive compensation of each adjusted parameter on the weld widths as the welding current randomly changes in a given range. A nonlinear adaptive kernel radial basis function neural network (AK-RBFNN) was also proposed to improve the model accuracy. Results indicate that the redundant, coupled, and integrated hand adjustments are adopted to maintain the desired weld pool status, and the human welder’s adjustment reflect nonlinear, complex characteristics. Results also show that the proposed AK-RBFNN model can appraise the weld widths with a good accuracy.


GTAW Weld pool dynamics Numerical simulation Multiple linear regression 



This work is funded by the Scientific research project of university of GanSu Province (2018A-018) and Hongliu Outstanding Young Talents Support Project of Lanzhou University of Technology. The authors would like to thank the assistance from Xinxin WANG and Lei XIAO on the numerical model establishment.


  1. 1.
    Byrd AP, Stone RT, Anderson et al (2015) The use of virtual welding simulators to evaluate experienced welders. Weld J 12:389s–395sGoogle Scholar
  2. 2.
    Hashimoto N (2015) Measurement of welder’s movement for welding skill analysis. Bull Hiroshiima Inst Tech Res 49:83–87Google Scholar
  3. 3.
    Seto N, Mori K, Hirose S (2012) Extracting of the skill from expert welders for aluminium alloy and investigation of their viewpoints using analytic hierarchy process. Light Metal Weld 8:14–22Google Scholar
  4. 4.
    Asai S, Ogawa T, Takebayashi H (2012) Visualization and digitization of welder skill for education and training. Weld World 56:26–34CrossRefGoogle Scholar
  5. 5.
    Hashimoto N (2015) Difference of improving welder’s skill through training progression. Bull Hiroshima Inst Tech Res 49:75–81Google Scholar
  6. 6.
    Zhang WJ, Liu YK, Zhang YM (2012) Characterization of three-dimensional weld pool surface in gas tungsten arc welding. Weld J 91:195s–203sGoogle Scholar
  7. 7.
    Zhang WJ, Zhang YM (2012) Modeling of human welder response to 3D weld pool surface: Part1-Principles. Weld J 91:310s–318sGoogle Scholar
  8. 8.
    Zhang WJ, Zhang YM (2012) Modeling of human welder response to 3D weld pool surface: part 2-results and analysis. Weld J 91:329s–337sGoogle Scholar
  9. 9.
    Liu YK, Zhang WJ, Zhang YM (2015) Dynamic neuro-fuzzy based human intelligence modeling and control in GTAW. IEEE T Autom Sci Eng 12:324–335CrossRefGoogle Scholar
  10. 10.
    Liu YK, Zhang WJ, Zhang YM (2013) Control of human arm movement in machine-human cooperative welding process. Control Eng Pract 21:1469–1480CrossRefGoogle Scholar
  11. 11.
    Liu YK, Zhang YM (2014) Model-based predictive control of weld penetration in gas tungsten arc welding. IEEE T Control Syst T 22:955–966CrossRefGoogle Scholar
  12. 12.
    Liu YK, Zhang WJ, Zhang YM (2013) Adaptive neuro-fuzzy inference system (ANFIS) modeling of human welder’s responses to 3D weld pool surface in GTAW. J Manuf Sci Eng T ASME 135:0210101–02101011Google Scholar
  13. 13.
    Liu YK, Zhang YM (2015) Iterative local ANFIS-based human welder intelligence modeling and control in pipe GTAW process: a data-driven approach. IEEE T Mech 20:1079–1088CrossRefGoogle Scholar
  14. 14.
    Liu YK, Zhang YM (2015) Controlling 3D weld pool surface by adjusting welding speed. Weld J 94:125s–134sGoogle Scholar
  15. 15.
    Zhang WJ, Zhang YM (2013) Analytical real-time measurement of three-dimensional specular weld pool surface. Meas Sci Technol 24:115011–115029CrossRefGoogle Scholar
  16. 16.
    Liu YK, Shao Z, Zhang YM (2014) Learning human welder movement in pipe GTAW: a virtualized welding approach. Weld J 93:388s–398sGoogle Scholar
  17. 17.
    Zhang G, Shi Y, Li CK et al (2014) Research on the correlation between the status of three-dimensional weld pool surface and weld penetration in TIG welding. Acta Metall Sin 8:995–1002Google Scholar
  18. 18.
    Du HY, Wei YH, Wang WX et al (2009) Numerical simulation of temperature and fluid in GTAW-arc under changing process conditions. J Mater Process Tech 209:3725–3765Google Scholar
  19. 19.
    Wang XX, Fan D, Huang JK et al (2014) A unified model of coupled arc plasma and weld pool for double electrodes TIG welding. J Phys D Appl Phys 47:275202–275211CrossRefGoogle Scholar
  20. 20.
    Rokhlin SI, Guu AC (1993) A study of arc force, pool depression, and weld penetration during gas tungsten arc welding. Weld J 8:382s–390sGoogle Scholar
  21. 21.
    Voller VR, Prakash C (1987) A fixed grid numerical modeling methodology for convection diffusion mushy region phase-change problems. Int J Heat Mass Trans 30:1709–1718CrossRefGoogle Scholar
  22. 22.
    Goldak J (1984) A new finite element model for welding heat sources. Metall Trans B 15:299–305CrossRefGoogle Scholar
  23. 23.
    Tsai MS, Eagar TW (1985) Distribution of the heat and current fluxes in gas tungsten arcs. Metall Trans B 16:841–846CrossRefGoogle Scholar
  24. 24.
    Wu CS (2008) Welding thermal process and molten pool dynamic. Mechanical Industry Publication, BeijingGoogle Scholar
  25. 25.
    Boulos IM, Fauchais P, Pfender E (1994) Thermal plasma-fundamentals and applications. Plenum 1:388Google Scholar
  26. 26.
    Mougenot J, Gonzalez JJ, Freton P et al (2013) Plasma–weld pool interaction in tungsten inert-gas configuration. J Phys D Appl Phys 46:135206–135220CrossRefGoogle Scholar
  27. 27.
    Parvez S, Abid M, Nash DH et al (2013) Effect of torch angel on arc properties and weld pool shape in stationary GTAW. J Eng Mech 139:1268–1277CrossRefGoogle Scholar
  28. 28.
    Ancona A, Lugarà PM, Ottonelli F et al (2004) A sensing torch for on-line monitoring of the gas tungsten arc welding process of steel pipes. Meas Sci Technol 15:2412–2422CrossRefGoogle Scholar
  29. 29.
    Wu LF (2016) Using fractional GM (1,1) model to predict the life of complex equipment, Grey Syst. Theory Appl 6:32–40Google Scholar
  30. 30.
    Prieto M, Tanner P, Andrade C (2016) Multiple linear regression model for the assessment of bond strength in corroded and non-corroded steel bars in structural concrete. Mater Struct 49:4749–4763CrossRefGoogle Scholar
  31. 31.
    Wettschereck D, Dietterich T (1992) Improving the performance of radial basis function networks by learning center locations. In: Advances in neural information processing systems vol 4, pp 1133–1140Google Scholar
  32. 32.
    Aftab W, Moinuddin M, Shaikh MS (2014) A novel kernel for RBF based neural networks. Abstr Appl Anal 2014:1–10CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Gang Zhang
    • 1
    • 2
    Email author
  • Yukang Liu
    • 2
  • Yu Shi
    • 1
  • Ding Fan
    • 1
  • Yuming Zhang
    • 2
  1. 1.State Key Laboratory of Advanced Processing and Recycling Non-Ferrous MetalsLanzhou University of TechnologyLanzhouChina
  2. 2.Electrical and Computer Engineering DepartmentInstitute of Sustainable Manufacturing, University of KentuckyLexingtonUSA

Personalised recommendations