Prediction of weld bead geometry of MAG welding based on XGBoost algorithm

  • Kai Chen
  • Huabin ChenEmail author
  • Liang Liu
  • Shanben Chen


Evaluating the welding joint quality in real time is difficult for chassis parts robotic gas-shielded welding. Series of metal active gas (MAG) joints were conducted in this paper to investigate the relationship between welding current, welding speed, energy input, and weld bead geometry. Bead width and bead reinforcement are obtained using a line-structured light measurement method, and the penetration depth of the bead is measured with the macroscopic metallurgical microscope. The ratio of penetration depth to the plate thickness and reinforcement is chosen as the evaluation criterion of the joint quality. Based on XGBoost algorithm, two data-driven models are proposed to recognize penetration status and predict the bead reinforcement. In the prediction results, the absolute error of the penetration coefficient is 0.079 at the maximum, and the average relative error is 11.06%. For the test result of reinforcement prediction model, the relative error is 20.5% on average. The test results show that the XGBoost-based models can be used for real-time prediction of welding quality.


MAG welding XGBoost algorithm line-structured light measurement penetration coefficient 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



The authors wish to thank Dr. Meng Kong and Dr. Jie Zhang for useful advice on this paper.

Funding information

The authors are grateful for the financial support from the National Natural Science Foundation of China (Grant No. 51575348).


  1. 1.
    Benyounis KY, Olabi AG (2008) Optimization of different welding processes using statistical and numerical approaches – a reference guide. Adv Eng Softw 39(6):483–496CrossRefGoogle Scholar
  2. 2.
    Hsu YF, Rubinsky B, Mahin K (1986) An inverse finite element method for the analysis of stationary arc welding processes. J Heat Transf 108(4):734–741CrossRefGoogle Scholar
  3. 3.
    Choudhury S, Sharma A, Mohanty UK, Kasai R, Komura M, Tanaka M (2017) Mathematical model of complex weld penetration profile: a case of square ac waveform arc welding. J Manuf Process 30:483–491CrossRefGoogle Scholar
  4. 4.
    Tarng YS, Yang WH (1998) Optimisation of the weld bead geometry in gas tungsten arc welding by the Taguchi method. Int J Adv Manuf Technol 14(8):549–554CrossRefGoogle Scholar
  5. 5.
    Palani PK, Murugan N (2006) Development of mathematical models for prediction of weld bead geometry in cladding by flux cored arc welding. Int J Adv Manuf Technol 30(7–8):669–676CrossRefGoogle Scholar
  6. 6.
    Khanna P, Maheshwari S (2018) Development of mathematical models for prediction and control of weld bead dimensions in MIG welding of stainless steel 409M. Mater Today Proc 5(2):4475–4488CrossRefGoogle Scholar
  7. 7.
    Prasad KS, Chalamalasetti SR, Damera NR (2015) Application of grey relational analysis for optimizing weld bead geometry parameters of pulsed current micro plasma arc welded inconel 625 sheets. Int J Adv Manuf Technol 78(1–4):625–632CrossRefGoogle Scholar
  8. 8.
    Sharma A, Verma DK, Arora N (2016) A scheme of comprehensive assessment of weld bead geometry. Int J Adv Manuf Technol 82(9–12):1507–1515CrossRefGoogle Scholar
  9. 9.
    Yan C (2004) CO2 welding spatter model based on partial least-squares regression. Trans China Weld Inst 25(5):125–128Google Scholar
  10. 10.
    Xu WH, Lin SB, Fan CL, Yang CL (2015) Prediction and optimization of weld bead geometry in oscillating arc narrow gap all-position GMA welding. Int J Adv Manuf Technol 79(1–4):183–196CrossRefGoogle Scholar
  11. 11.
    Kim IS, Son JS, Yarlagadda PKDV (2003) A study on the quality improvement of robotic GMA welding process. Robot Comput Integr Manuf 19(6):567–572CrossRefGoogle Scholar
  12. 12.
    Mirapeix J, García-Allende PB, Cobo A (2007) Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks. NDT E Int 40(4):315–323CrossRefGoogle Scholar
  13. 13.
    Datta S, Bandyopadhyay A, Pal PK (2008) Grey-based Taguchi method for optimization of bead geometry in submerged arc bead-on-plate welding. Int J Adv Manuf Technol 39(11–12):1136–1143CrossRefGoogle Scholar
  14. 14.
    Datta S, Nandi G, Bandyopadhay A, Pal PK (2009) Application of PCA-based hybid Taguchi method for correlated multicriteria optimization of submerged arc weld. Int J Adv Manuf Technol 45(3–4):276–286CrossRefGoogle Scholar
  15. 15.
    Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM: 785–794Google Scholar
  17. 17.
    Ke G, Meng Q, Finely T, Wang T, Chen W (2017) LightGBM: a highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing SystemsGoogle Scholar
  18. 18.
    Chen S, Chen X, Li J, Lin T (2005) The research on acquisition of welding seam space position information for arc welding robot based on vision. J Intell Robot Syst 43:77–97CrossRefGoogle Scholar
  19. 19.
    Muhammad J, Altun H, Abo-Serie E (2016) Welding seam profiling techniques based on active vision sensing for intelligent robotic welding. Int J Adv Manuf Technol 88(1–4)Google Scholar

Copyright information

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

Authors and Affiliations

  • Kai Chen
    • 1
  • Huabin Chen
    • 1
    Email author
  • Liang Liu
    • 1
  • Shanben Chen
    • 1
  1. 1.Shanghai Key Laboratory of Materials Laser Processing and Modification, School of Materials Science and EngineeringShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations