Fault-Tolerant Weld Line Detection Using Image Processing and Fusion of Execution Monitoring Systems

Abstract

Quality control, cost reduction and above all, human and environmental safety are great reasons that stimulate the investments in technologies like automatic inspection. The automatic inspection of weld lines in storage tanks is of special interest, due to the fact that such tanks are currently used to store harmful products. For a reliable inspection it is necessary to accurately detect the weld line relative position and orientation with respect to the inspection robot. In this paper, the development of a system to perform weld line detection and estimation in storage tanks is proposed. The system uses visual information to perform the detection task and a fault-tolerant estimation process, main contribution of this work, to increase the confidence and performance of the detection system. The fault-tolerant estimation is based on the \(\alpha \)\(\beta \) filter and on a knowledge-based execution monitoring system, constructed through the fusion of two subsystems: a data-based and a model-based fault detection systems.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

References

  1. Carvalho, E. A. N. (2007). Sistema para posicionamento de sensores aplicado à inspeção automatizada de cordões de solda em tanques de armazenamento de combustíveis derivados do petróleo. Master’s thesis, PPGEE-UFCG, Campina Grande, PB.

  2. Carvalho, E. A. N., Molina, L., Freire, E. O., Freire, R. C. S., & Luciano, B. (2007). IEEE-IMTC: Fillet weld identification for automatic inspection of spherical tanks.

  3. Carvalho, E. A. N., Molina, L., Freire, E. O., Luciano, B., & Freire, R. C. S. (2008). Sistema para identificação, localização e estimação de cordões de solda presentes em tanques de armazenamento de combustíveis derivados do petróleo. XVII CBA.

  4. Cassandras, C. G. & Lafortune, S. (2006). Introduction to discrete event systems. New York: Springer.

  5. Deutsch, W. A. K. (2000). Automated ultrasonic inspection—examples from the steel mill. World conference for nondestructive testing.

  6. Deutsch, W. A. K., Schulte, P., Joswig, M. & Kattwinkel, R. (2006). Automatic inspection of welded pipes with ultrasound, 9th ECNDT.

  7. Duda, R. O., & Hart, P. E. (1972). Use of the hough transformation to detect lines and curves in pictures. ACM Communication, 15, 11–15.

    Article  Google Scholar 

  8. Gertler, J. J. (1998). Fault detection and diagnosis in engineering systems (Vol. I). CRC.

  9. Gonzalez, R. C., & Woods, R. E. (2002). Digital image processing. Upper Saddle: Prantice Hall.

    Google Scholar 

  10. Greig, A., & Broome, D. (1991). Automatic of complex geometry welds, 5th IEEE international conference on advanced robotics.

  11. Horn, B. K. P. (1986). Robot visiong. New York: McGraw-Hil.

    Google Scholar 

  12. Hough, P. V. C. (1962). Method and means for recognizing complex patterns. Us Patent 3,069,654.

  13. Kalata, P. R., & Murphy, K. M. (1997). Alpha-beta target tracking and track rate variations, 29th southeastern symposium on system theory.

  14. Kapur, J. N., Sahoo, P. K., & Wong, K. C. (1985). A new method for gray-level picture thresholding using the entropy of the histogram. Computer Vision, Graphics, and Image Processing, 29, 273–285.

    Article  Google Scholar 

  15. Kälviäinen, H., Hirvonen, P., Xu, L., & Oja, E. (1995). Probabilistic and non-probabilistic hough transforms: Overview and comparisons. Image and Vision Computing, 13(4), 239–252.

    Google Scholar 

  16. Molina, L., Carvalho, E. A. N., Freire, E. O., Montalvão, J. R., & Chagas, F. A. (2008). IEEE-LARS: A robotic vision system using a modified hough transform to perform weld line detection on storage tanks.

  17. Molina, L., Carvalho, E. A. N., Moura, M. A., Freire, E. O., & Montalvão, J. R. (2008b). Um métodos de visão robótica para identificação de cordães de solda em tanques de armazenamento visando inspeção automatizada. XVII CBA.

  18. Molina, L., Freire, E. O., Carvalho, E. A. N., & Basilio, J. C. S. (2009). Fault-tolerant weld line detection for automatic inspection of storage tanks based on visual information and alpha-beta filter. IX SBAI.

  19. Noriega, G., & Pasupathy, S. (1992). Application of kalman filtering to real-time preprocessing of geophysical data. IEEE Transactions on Geoscience and Remote Sensing, 30(5), 897–910.

    Article  Google Scholar 

  20. Oppenheim, A. V., & Schafer, R. W. (1989). Discrete-time signal processing. Toronto: Prentice-Hall Inc.

    MATH  Google Scholar 

  21. Pettersson, O. (2005). Execution monitoring in robotics: A survey. Robotics and Autonomous Systems, 53, 73–88.

    Article  Google Scholar 

  22. Platte, M., Deutsch, V., Vogt, M., & Deutsch, W. A. K. (2002). Ultrasonic testing—compact and understandable. Wuppertal: Castell.

  23. Schanze, T. (1995). Sinc interpolation of discrete periodic signals. IEEE Transactions on Signal Processing, 43(6), 1502–1503.

    Article  Google Scholar 

  24. Tsuge, H. (1988). Automation of in-service inspection of spherical tanks. Weld. Int., 2(7), 649–652.

    Article  Google Scholar 

Download references

Acknowledgments

The authors wish to thank CNPq and CAPES for the financial support that made possible the realization of this project.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Lucas Molina.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Molina, L., Carvalho, E.Á.N., Freire, E.O. et al. Fault-Tolerant Weld Line Detection Using Image Processing and Fusion of Execution Monitoring Systems. J Control Autom Electr Syst 24, 70–80 (2013). https://doi.org/10.1007/s40313-013-0016-3

Download citation

Keywords

  • Weld line detection
  • Fault-tolerant estimation
  • Image processing
  • \(\alpha \)\(\beta \) filter