Journal of Intelligent Manufacturing

, Volume 25, Issue 6, pp 1301–1313 | Cite as

Intelligent modelling of back-side weld bead geometry using weld pool surface characteristic parameters

  • XueWu Wang
  • RuiRui Li


In manual welding process, skilled welders can ensure the weld quality through compensating for deviation observed from the weld pool surface. In this paper a three dimensional vision sensing system was used to mimic the human vision system to observe the three-dimensional weld pool surface in pipe GTAW process. Novel characteristic parameters containing information about the penetration state specified by its back-side weld pool width and height were proposed based on the reconstructed three dimensional weld pool surfaces. Then, variation in characteristic parameters and their relationships with the back-side parameters were studied through experiments under different welding conditions. Direct measurement of penetration is not preferred in a manufacturing site, soft-sensing method was thus proposed as an alternative to obtain it in real time due to established soft-sensing model and auxiliary variables which can be sensed in real time. In order to obtain the penetration status in real time conveniently, back-propagation neural network, principle component analysis based back-propagation neural network and global best adaptive mutation particle swarm optimization based back-propagation neural network models were established to estimate the penetration based on the proposed characteristic parameters. It was found that the top-side characteristic parameters proposed can reflect the back-side weld pool parameters accurately and the models are capable of predicting the penetration status in real time by observing the three-dimensional weld pool surface.


GTAW Characterization Intelligent model PCA-BPNN GBAMPSO 



This work is partially funded by the National Science Foundation under grant CMMI-0927707 and China Oevrsea Scholarship. The assistance from PhD students Mr. WeiJie Zhang and Mr. YuKang Liu in experiments and guidance from Professor YuMing Zhang at the University of Kentucky Welding Research Laboratory are greatly appreciated.


  1. Abdi, H., & Williams, L. J. (2010). Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2, 433–459.CrossRefGoogle Scholar
  2. Beardsley, H. E., Zhang, Y. M., & Kovacevic, R. (1994). Infrared sensing of full penetration state in gas tungsten arc welding. International Journal of Machine Tools and Manufacture, 34(8), 1079–1090.CrossRefGoogle Scholar
  3. Chau, K. W. (2007). Application of a PSO-based neural network in analysis of outcomes of construction claims. Automation in Construction, 16(5), 642–646.CrossRefGoogle Scholar
  4. Chen, S. B., Zhao, D. B., Lou, Y. J., & Wu, L. (2004). Computer vision sensing and intelligent control of welding pool dynamics. Robotic Welding, Intelligence and Automation, LNCIS, 299, 25–55.CrossRefGoogle Scholar
  5. Chen, B., Wang, J. F., & Chen, S. B. (2010). Prediction of pulsed GTAW penetration status based on BP neural network and D-S evidence theory information fusion. The International Journal of Advanced Manufacturing Technology, 48(1–4), 83–94.CrossRefGoogle Scholar
  6. Chien, C. F., Hsu, C. Y., & Hsiao, C. W. (2012). Manufacturing intelligence to forecast and reduce semiconductor cycle time. Journal of Intelligent Manufacturing, 23(6), 2281–2294.CrossRefGoogle Scholar
  7. Chokkalingham, S., Chandrasekhar, N., & Vasudevan, M. (2012). Predicting the depth of penetration and weld bead width from the infra red thermal image of the weld pool using artificial neural network modeling. Journal of Intelligent Manufacturing, 23(5), 1995–2001.Google Scholar
  8. Fan, C. J., Lv, F. L., & Chen, S. B. (2009). Visual sensing and penetration control in aluminum alloy pulsed GTA welding. The International Journal of Advanced Manufacturing Technology, 42(1–2), 126–137.Google Scholar
  9. Gaitonde, V. N., & Karnik, S. R. (2012). Minimizing burr size in drilling using artificial neural network (ANN)-particle swarm optimization (PSO) approach. Journal of Intelligent Manufacturing, 23(5), 1783–1793.CrossRefGoogle Scholar
  10. Graham, G. M., & Ume, I. C. (1997). Automated system for laser ultrasonic sensing of weld penetration. Mechatronics, 7(8), 711–721.CrossRefGoogle Scholar
  11. Hartman, D. A., DeLapp, D. R., Cook, G. E., & Barnett, R. J. (1999). Intelligent fusion control throughout varying thermal regions. In Proceedings of the IEEE industry applications conference, Vol. 1 (pp. 635–644). Phoenix, AZ, 3–7 October.Google Scholar
  12. Ju, J. B., Suga, Y., & Ogawa, K. (2002). Penetration control by monitoring Molten pool oscillation in TIG arc welding. In Proceedings of The twelfth international offshore and polar engineering conference (pp. 241–246). Kitakyushu, Japan, May 26–31.Google Scholar
  13. Kennedy, J., & Eberhart, R. (1995). Particle swarm optimization. In Proceedings of the IEEE international conference on neural networks: IV (pp. 1942–1948). New Jersey, Piscataway: IEEE Press.Google Scholar
  14. Kovacevic, R., Zhang, Y. M., & Li, L. (1996). Monitoring of weld penetration based on weld pool geometrical appearance. Welding Journal, 75(10), 317s–329s.Google Scholar
  15. Kovacevic, R., & Zhang, Y. M. (1997). Neurofuzzy model-based weld fusion state estimation. IEEE Control Systems Magazine, 17(2), 30–42.CrossRefGoogle Scholar
  16. Li, T. S., & Chen, S. H. (2011). Modeling and optimization of thermal-flow lithography process using a neural-genetic approach. Journal of Intelligent Manufacturing, 22(2), 191–200.CrossRefGoogle Scholar
  17. Lin, H. L. (2012). The use of the Taguchi method with grey relational analysis and a neural network to optimize a novel GMA welding process. Journal of Intelligent Manufacturing, 23(5), 1671–1680.CrossRefGoogle Scholar
  18. Lu, W., & Zhang, Y. M. (2006). Robust sensing and control of the weld pool surface. Measurement Science and Technology, 17, 2437–2446.CrossRefGoogle Scholar
  19. Luo, H., Devanathan, R., Wang, J., Chen, X., & Sun, Z. (2002). Vision based neurofuzzy logic control of weld pool geometry. Science and Technology of Welding and Joining, 7(5), 321–325.CrossRefGoogle Scholar
  20. McLain, R. B., & Henson, M. A. (2000). Principal component analysis for nonlinear model reference adaptive control. Computers and Chemical Engineering, 24(1), 99–110.CrossRefGoogle Scholar
  21. Rokhlin, S. I., & Guu, A. C. (1993). A study of arc force, pool depression, and weld penetration during gas tungsten arc welding. Welding Journal, 72(8), 381s–390s.Google Scholar
  22. Saeed, G., & Zhang, Y. M. (2007). Weld pool surface depth measurement using calibrated camera and structured-light. Measurement Science & Technology, 18, 2570–2578.CrossRefGoogle Scholar
  23. Song, H. S., & Zhang, Y. M. (2008). Measurement and analysis of three dimensional specular gas tungsten arc weld pool surface. Welding Journal, 87(4), 85s–95s.Google Scholar
  24. Tarng, Y. S., Wu, J. L., Yeh, S. S., & Juang, S. C. (1999). Intelligent modelling and optimization of the gas tungsten arc welding process. Journal of Intelligent Manufacturing, 10(1), 73–79.CrossRefGoogle Scholar
  25. Vorman, A. R., & Brandt, H. (1976). Feedback control of GTA welding using puddle width measurement. Welding Journal, 55(9), 742–749.Google Scholar
  26. Wang, J. J., Lin, T., & Chen, S. B. (2005). Obtaining weld pool vision information during aluminum alloy TIG welding. The International Journal of Advanced Manufacturing Technology, 26(3), 219–227.CrossRefGoogle Scholar
  27. Wang, X. W., Gu, X. S., Liu, Z. Q., & Shang, Y. Q. (2009). Soft Sensing Model of C3 Concentration of FCCU Based on PSO-BP Neural Network. Journal of System Simulation, 21(4), 973–976.Google Scholar
  28. Wu, C. S., & Gao, J. Q. (2006). Vision-based neuro-fuzzy control of weld penetration in gas tungsten arc welding of thin sheets. International Journal of Modelling, Identification and Control, 1(2), 126–132.Google Scholar
  29. Zhang, Y. M., Wu, L., Walcott, B. L., & Chen, D. H. (1993). Determining joint penetration in GTAW with vision sensing of weld-face geometry. Welding Journal, 72(10), 463s–469s.Google Scholar
  30. Zhang, Y. M., Kovacevic, R., & Wu, L. (1996). Dynamic analysis and identification of gas tungsten arc welding process for full penetration control. Journal of Engineering for Industry -Transactions of the ASME, 118(1), 123–136.Google Scholar
  31. Zhang, Y. M., Kovacevic, R., & Li, L. (1996). Adaptive control of full penetration GTA welding. IEEE Transactions on Control Systems Technology, 4(4), 394–403.CrossRefGoogle Scholar
  32. Zhang, Y. M., Kovacevic, R., & Li, L. (1996). Characterization and real-time measurement of geometrical appearance of weld pool. International Journal of Machine Tool and Manufacturing, 36(7), 799–816.CrossRefGoogle Scholar
  33. Zhang, Y. M., Li, L., & Kovacevic, R. (1997). Dynamic estimation of full penetration using geometry of adjacent weld pools. Journal of Manufacturing Science and Engineering-Transactions of the ASME, 119(4), 631–643.CrossRefGoogle Scholar
  34. Zhang, Y. M., & Kovacevic, R. (1998). Neurofuzzy model based control of weld fusion zone geometry. IEEE Transactions on Fuzzy Systems, 6(3), 389–401.CrossRefGoogle Scholar
  35. Zhang, W. J., Liu, Y. K., Wang, X. W., & Zhang, Y. M. (2012). Characterization of three dimensional weld pool surface in GTAW. Welding Journal, 91(7), 195s–203s.Google Scholar
  36. Zhao, D. B., Chen, S. B., Wu, L., Dai, M., & Chen, Q. (2001). Intelligent Control for the Shape of the Weld Pool in Pulsed GTAW with Filler Metal. Welding Research Supplement, 80(11), 253s–260s.Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Key Laboratory of Advanced Control and Optimization for Chemical ProcessesMinistry of Education, East China University of Science and TechnologyShanghaiPeople’s Republic of China

Personalised recommendations