A new model to distinguish welds performed by short-circuit GMAW based on FRESH algorithm and MLP ANN

  • Rafaela A. CamposEmail author
  • Renan P. F. Amaral
  • Nielson Soares
  • Leonardo G. da Fonseca
  • Moisés L. Lagares Júnior
  • Eduardo P. de Aguiar
Technical Paper


The short-circuit gas metal arc welding has been continuously studied over the years, due to its important role in manufacturing processes. Concerning the process, many kinds of research are carried out aiming to understand the influence of the shielding gas in welds quality. In this context, this work treats the voltage and current welding signals as time series and applies a feature extraction based on scalable hypothesis tests, which is called FRESH algorithm, in order to obtain the signal features. After that, these features are applied in a multilayer perceptron artificial neural network, trained by the scaled conjugate gradient method, which classifies the welds according to the flow rate and type of shielding gas used in the process. The model presented excellent performance, which shows that the proposal is suitable to be used in welding quality monitoring.


Gas metal arc welding (GMAW) Shielding gas FRESH algorithm Artificial neural network 



The authors would like to acknowledge FAPEMIG, CAPES, CNPq and Federal University of Juiz de Fora for financial support.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. 1.
    Norrish J, Cuiuri D (2014) The controlled short circuit GMAW process: a tutorial. J Manuf Process 16(1):86CrossRefGoogle Scholar
  2. 2.
    Koushki AR, Goodarzi M, Paidar M (2016) Influence of shielding gas on the mechanical and metallurgical properties of DP-GMA-welded 5083–H321 aluminum alloy. Int J Miner Metall Mater 23(12):1416CrossRefGoogle Scholar
  3. 3.
    Ley F, Campbell S, Galloway A, McPherson N (2015) Effect of shielding gas parameters on weld metal thermal properties in gas metal arc welding. Int J Adv Manuf Technol 80(5–8):1213CrossRefGoogle Scholar
  4. 4.
    Uttrachi GD (2007) GMAW shielding gas flow control systems. Weld J 86(4):22Google Scholar
  5. 5.
    Mvola B, Kah P (2017) Effects of shielding gas control: welded joint properties in GMAW process optimization. Int J Adv Manuf Technol 88(9–12):2369CrossRefGoogle Scholar
  6. 6.
    Cai X, Fan C, Lin S, Ji X, Yang C, Guo W (2017) Effects of shielding gas composition on arc properties and wire melting characteristics in narrow gap MAG welding. J Mater Process Technol 244:225CrossRefGoogle Scholar
  7. 7.
    Cai X, Fan C, Lin S, Yang C, Hu L, Ji X (2017) Effects of shielding gas composition on arc behaviors and weld formation in narrow gap tandem GMAW. Int J Adv Manuf Technol 91(9–12):3449CrossRefGoogle Scholar
  8. 8.
    Campbell S, Galloway A, McPherson N (2012) Techno-economic evaluation of reducing shielding gas consumption in GMAW whilst maintaining weld quality. Int J Adv Manuf Technol 63(9):975CrossRefGoogle Scholar
  9. 9.
    Cruz JG, Torres EM, Alfaro SCA (2015) A methodology for modeling and control of weld bead width in the GMAW process. J Braz Soc Mech Sci Eng 37(5):1529CrossRefGoogle Scholar
  10. 10.
    Cruz JG, Torres EM, Alfaro SCA (2018) Modelling and control of weld height reinforcement in the GMAW process. J Braz Soc Mech Sci Eng 40(3):164CrossRefGoogle Scholar
  11. 11.
    Panda BN, Babhubalendruni MR, Biswal B, Rajput DS (2015) Application of artificial intelligence methods to spot welding of commercial aluminum sheets (BS 1050). In: Proceedings of fourth international conference on soft computing for problem solving. Springer, Berlin, pp 21–32Google Scholar
  12. 12.
    Campbell S, Galloway A, McPherson N (2012) Artificial neural network prediction of weld geometry performed using GMAW with alternating shielding gases. Weld J 91(6):174SGoogle Scholar
  13. 13.
    Casalino G, Facchini F, Mortello M, Mummolo G (2016) ANN modelling to optimize manufacturing processes: the case of laser welding. IFAC-Pap OnLine 49(12):378CrossRefGoogle Scholar
  14. 14.
    Møller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6(4):525CrossRefGoogle Scholar
  15. 15.
    Christ M, Kempa-Liehr AW, Feindt M (2016) Distributed and parallel time series feature extraction for industrial big data applications. arXiv preprint arXiv:1610.07717
  16. 16.
    Elmasri R, Lee JY (1998) Implementation options for time-series data. In: Etzion O, Jajodia S, Sripada S (eds) Temporal databases: research and practice. Springer, Berlin, pp 115–128CrossRefGoogle Scholar
  17. 17.
    Bagnall A, Lines J, Bostrom A, Large J, Keogh E (2017) The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov 31(3):606MathSciNetCrossRefGoogle Scholar
  18. 18.
    Nanopoulos A, Alcock R, Manolopoulos Y (2001) Feature-based classification of time-series data. Int J Comput Res 10(3):49Google Scholar
  19. 19.
    Geurts P (2001) in Pattern extraction for time series classification. In: European conference on principles of data mining and knowledge discovery. Springer, Berlin, pp 115–127Google Scholar
  20. 20.
    Benjamini Y, Yekutieli D (2001) The control of the false discovery rate in multiple testing under dependency. Ann Stat 29:1165–1188MathSciNetCrossRefGoogle Scholar
  21. 21.
    Radivojac P, Obradovic Z, Dunker AK, Vucetic S (2004) Feature selection filters based on the permutation test. In: European conference on machine learning. Springer, Berlin, pp 334–346Google Scholar
  22. 22.
    Massey FJ Jr (1951) The Kolmogorov–Smirnov test for goodness of fit. J Am Stat Assoc 46(253):68CrossRefGoogle Scholar
  23. 23.
    Curran-Everett D (2000) Multiple comparisons: philosophies and illustrations. Am J Physiol Regul Integr Comp Physiol 279(1):R1CrossRefGoogle Scholar
  24. 24.
    Stehman S (1996) Estimating the kappa coefficient and its variance under stratified random sampling. Photogram Eng Remote Sens 62(4):401Google Scholar
  25. 25.
    Sokolova M, Japkowicz N, Szpakowicz S (2006) Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Springer, BerlinGoogle Scholar
  26. 26.
    Friedrich R, Siegert S, Peinke J, Siefert M, Lindemann M, Raethjen J, Deuschl G, Pfister G et al (2000) Extracting model equations from experimental data. Phys Lett A 271(3):217CrossRefGoogle Scholar
  27. 27.
    Welch P (1967) The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans Audio Electroacoust 15(2):70CrossRefGoogle Scholar
  28. 28.
    Fulcher BD, Jones NS (2014) Highly comparative feature-based time-series classification. IEEE Trans Knowl Data Eng 26(12):3026CrossRefGoogle Scholar

Copyright information

© The Brazilian Society of Mechanical Sciences and Engineering 2019

Authors and Affiliations

  1. 1.Industrial and Mechanical Engineering DepartmentFederal University of Juiz de ForaJuiz de ForaBrazil
  2. 2.Mechanical Engineering DepartmentPontifical Catholic University of Rio de JaneiroRio de JaneiroBrazil
  3. 3.Graduate Program in Computational ModelingFederal University of Juiz de ForaJuiz de ForaBrazil
  4. 4.Department of Computational and Applied MechanicsFederal University of Juiz de ForaJuiz de ForaBrazil

Personalised recommendations