Skip to main content
Log in

Online visual quality inspection for weld seams

  • ORIGINAL ARTICLE
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

Arc welding is a widely used technology in almost all sectors of industrial production. Many task are automatically performed by robots. This paper presents a flexible vision-based quality management system to detect defects online during the weld process. The proposed method uses a single camera on the weld arms to observe the newly welded seam behind the weld head. Two phases, training and verification, are included in the system. The quality parameters are learned from a set of welded seams (training seams), selected by a weld engineer, which show sufficient quality, and by which the measurement reference and tolerance are formed. The verification process is conducted by frame-to-frame comparison of current work with the reference. The observed features are the position and the width of the seam as well as the light distribution in the vicinity of the arc.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Du Q, Chen S, Lin T (2006) Inspection of weld shape based on shape from shading. Int J Adv Manuf Technol 27:667–671

    Article  Google Scholar 

  2. Fischler MA, Bolles RC (1981) The random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395

    Article  MathSciNet  Google Scholar 

  3. Harris C, Stephens RC (1988) A combined corner and edge detector. In: Matthews MM (ed) Proc. of 4th alvey vision conf. University of Manchester, Manchester, pp 147–151

    Google Scholar 

  4. Kim JS, Son YT, Cho HS, Kho KI (1996) A robust visual seam tracking system for robotic arc welding. Mechatronics 6:141–163

    Article  Google Scholar 

  5. Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distribution. Pattern Recogn 29:51–59

    Article  Google Scholar 

  6. Tung PC, Wu MC, Hwang YR (2004) An image-guided mobile robotic welding system for SMAW repair processes. Int J Mach Tools Manuf 44:1223–1233

    Article  Google Scholar 

  7. Xu D, Wang L, Tan M (2004) Image processing and visual control method for arc welding robot. In: Proc. of int. conf. on robotics and biomimetics, Shenyang, 22–26 August 2004

  8. Xu P, Xu G, Tang X, Yao S (2007) A visual seam tracking system for robotic arc welding. Int J Adv Manuf Technol. doi:10.1007/s00170-007-0939-6

  9. Zhang XG, Xu JJ, Ge GY (2004) Defect recognition on x ray images for weld inspection using svm. In: Proc. of 3rd int. conf. on machine learing and cybernetics. Shanghai, pp 3721–3725

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to D. Schreiber.

Additional information

The work has been carried out within the KPlus Programme.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Schreiber, D., Cambrini, L., Biber, J. et al. Online visual quality inspection for weld seams. Int J Adv Manuf Technol 42, 497–504 (2009). https://doi.org/10.1007/s00170-008-1605-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-008-1605-3

Keywords

Navigation