Advertisement

Prediction of bead geometry in cold metal transfer welding using back propagation neural network

  • N Pavan Kumar
  • Praveen K Devarajan
  • S Arungalai Vendan
  • N. Shanmugam
ORIGINAL ARTICLE

Abstract

This paper presents the development of a back propagation neural network model for the forecasting the weld bead geometry (bead height and width) and penetration (depth and area) in cold metal transfer (CMT) welding process. Several welding parameters seem to influence the bead geometry and penetration. Typically, it is observed that high welding speeds or low heat inputs normally produced poor fusion. For this study, the model is based on experimental data. The input parameters considered are peak welding current, welding speed and heat input. The bead height and width, penetration depth and dilution area are taken as output parameters to design the framework of the model. These networks have achieved good agreement with the training data and have yielded satisfactory module. Neural network may effectively be implemented for estimating the weld bead and penetration geometric parameters. The results from the experiments indicate a small error percentage between the predicted and experimental values.

Keywords

Artificial neural networks CMT Welding parameters Bead geometry Penetration depth Regression model 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cam G, Dos Santos, J.F, and Kocak M (1997) Laser and electron beam weldability of Al-alloys: literature review. GKSS Report 97/E/25, IIW Document IX-1896-98, GKSS Research Centre, GeesthachtGoogle Scholar
  2. 2.
    Pickin CG, Williams SW, Lunt M (2011) Characterisation of the cold metal transfer (CMT) process and its application for low dilution cladding. J Materials Processing Techno 211:496–502CrossRefGoogle Scholar
  3. 3.
    Senthil Kumar R, Parmer, R.S (1986) Weld bead geometry prediction for pulse MIG welding. In: Proceedings of an International Conference on Trends in Welding Technology, USA, May 18–22: 647–652Google Scholar
  4. 4.
    Srinivasa Rao P (2004) Development of arc rotation mechanism and experimental studies on pulsed GMA welding with and without arc rotation. I.I.T, KharagpurGoogle Scholar
  5. 5.
    Srinivasa Rao P, Gupta O.P, Murty, S.S.N (2005) Influence of process parameters on bead geometry in pulsed gas metal arc welding. In: IIW International Congress on Frontiers of Welding Science and Technology, MumbaiGoogle Scholar
  6. 6.
    Rajasekaran S (1999) Weld bead characteristics in pulsed GMA welding of Al–Mg alloys. Weld J 78(12):397–407Google Scholar
  7. 7.
    Kim IS, Park CE, Jeong YJ, Son JS (2001) Development of an intelligent system for selection of the process variables in gas metal arc welding processes. Int J Adv Manuf Technol 18:98–102CrossRefGoogle Scholar
  8. 8.
    Kim IS, Son JS, Park CE, Lee CW, Prasad YKDV (2002) A study on prediction of bead height in robotic arc welding using a neural network. J Mater Process Technol 130:229–234CrossRefGoogle Scholar
  9. 9.
    Kim IS, Son JS, Park CE, Kim IJ, Kim HH (2005) An investigation into an intelligent system for predicting bead geometry in GMA welding process. J Mater Process Technol 159:113–118CrossRefGoogle Scholar
  10. 10.
    Krose B, Van der Smagt P (1996) An introduction to neural networks. Eighth Ed, NovemberGoogle Scholar
  11. 11.
    Lee JI, Um KW (2000) A prediction of welding process parameters by prediction of back bead geometry. J Mater Process Technol 108:106–113CrossRefGoogle Scholar
  12. 12.
    Chan B, Pacey J, Bibby M (1999) Modeling gas metal arc weld geometry using artificial neural network technology. Can Metall Q 38(1):43–51Google Scholar
  13. 13.
    Hammerstrom D (1993) Working with neural networks. IEEE Spectrum, 46–53, JulyGoogle Scholar
  14. 14.
    Hagan MT, Demuth HB, Beale M (1996) Neural network design. Vikas Publishing House, Thomson LearningGoogle Scholar
  15. 15.
    Rukmini Srikant R (2003) Tool wear monitoring using artificial intelligence, GITAM College of EngineeringGoogle Scholar
  16. 16.
    Yagnanarayana B (1999) Artificial neural networks. Prentice-Hall, MumbaiGoogle Scholar
  17. 17.
    TERESA MELFI (2010) New Code Requirements for Calculating Heat Input. Lincoln Electric Company. http://www.lincolnelectric.com/en-us/equipment/Documents/ASME-code-requirements. Accessed 20 December 2015
  18. 18.
    Kumar NP, Arungalai vendan S, Sivashanmugam N (2016) Investigations on the parametric effects of cold metal transfer process on the microstructural aspects in AA6061. J Alloys and Compounds 658:255–264CrossRefGoogle Scholar
  19. 19.
    Cong B, Ding J, Williams S (2015) Effect of arc mode in cold metal transfer process on porosity of additively manufactured Al-6.3% Cu alloy. Int J Adv Manuf Technol 76:1593–1606CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  • N Pavan Kumar
    • 1
  • Praveen K Devarajan
    • 1
  • S Arungalai Vendan
    • 1
  • N. Shanmugam
    • 2
  1. 1.School of Electrical EngineeringVIT UniversityVelloreIndia
  2. 2.Department of Mechanical EngineeringNIT TrichyTiruchirappalliIndia

Personalised recommendations