Skip to main content
SpringerLink
Log in

Calibrating a profile measurement system for dimensional inspection in rail rolling mills

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Modern, high-speed, railway transportation requires rails to conform strictly to requirements specified in various standards. One key requirement is the conformance of the dimensions of the rail cross section to those of the corresponding rail model, within tight tolerances. This paper deals with a system for dimensional quality inspection during the manufacture of railway rails. Optical triangulation is used to build a profile from laser lines projected on the rails from four different locations. Then, the profile is compared to that of the corresponding rail model. The differences between certain numerical values (the dimensions) for the profile and the model are compared to standard tolerances for each dimension in order to detect dimensional defects. As a prerequisite for this, the cameras used to capture the laser lines must be calibrated. Standard calibration plates are unsuitable for sheet-of-light calibration in a production environment, as determining the location of the laser emitters relative to the plates would be an issue. For this reason, a cylinder-based calibration target is used instead. Different calibration algorithms are discussed and compared to said standard calibration. The results of accuracy and repeatability tests in the production environment are also shown. The accuracy of the system is found to be appropriate for the purpose of quality inspection under the requirements of applicable rail standards.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

References

  1. Ahlström, J., Karlsson, B.: Fatigue behaviour of rail steel—a comparison between strain and stress controlled loading. Wear 258(7), 1187–1193 (2005)

    Article  Google Scholar 

  2. European Committee for Standardization: EN-13674—Railway applications - Track - Rail (2011)

  3. AREMA: AREMA Manual for Railway Engineering—Chapter 4: Rails (2011)

  4. International Union of Railways: UIC Code 860—Technical specification for the supply of rails (2008)

  5. Gosstandart of Russia: GOST R 51685-2000—Railway rails - General Specifications (2001)

  6. Papaelias, M., Roberts, C., Davis, C.L.: A review on non-destructive evaluation of rails: state-of-the-art and future development. Proc. Inst. Mech. Eng. F J. Rail Rapid Transit 222, 367–384 (2008)

    Article  Google Scholar 

  7. Li, G., Wang, C., Liu, J., Jin, W.: Dynamic rail-wear inspecting system based on machine vision. In: IEEE Conference on Industrial Electronics and Applications, pp. 1–4 (2007)

  8. Liu, Z., Sun, J., Wang, H., Zhang, G.: Simple and fast rail wear measurement method based on structured light. Opt. Lasers Eng. 49, 1343–1351 (2011)

    Article  Google Scholar 

  9. Zheng, S., Chai, X., An, X., Li, L.: Railway track gauge inspection method based on computer vision. In: IEEE International Conference on Mechatronics and Automation, pp. 1292–1296 (2012)

  10. Wang, C., Ma, Z., Li, Y., Zeng, J., Jin, T., Liu, H.: Distortion calibrating method of measuring rail profile based on local affine invariant feature descriptor. Measurement 110, 11–21 (2017)

    Article  Google Scholar 

  11. Greenwood Engineering A/S: MiniProf digital profile measuring: your way to valid and reliable data. Commercial Brochure (2010). Retrieved on 26 July 2017

  12. Lohry, W., Chen, V., Zhang, S.: Absolute three-dimensional shape measurement using coded fringe patterns without phase unwrapping or projector calibration. Opt. Express 22, 1287–1301 (2014)

    Article  Google Scholar 

  13. Molleda, J., Usamentiaga, R., Millara, A.F., García, D.F., Manso, P., Suárez, C.M., García, I.: A profile measurement system for rail quality assessment during manufacturing. IEEE Trans. Ind. Appl. 52, 2684–2692 (2016)

    Article  Google Scholar 

  14. Millara, A.F., Molleda, J., Usamentiaga, R., Garcia, D.F.: Profile measurement of rails in rolling mills: integrating autonomic computing capabilities. In: IEEE Industry Applications Society Conference (2018)

  15. Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22, 1330–1334 (2000)

    Article  Google Scholar 

  16. Steger, C.: Extracting lines using differential geometry and gaussian smoothing. Int. Arch. Photogramm. Remote Sens. 31(part B3), 821–826 (1996)

    Google Scholar 

  17. Fitzgibbon, A., Pilu, M., Fisher, R.: Direct least-squares fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 1, 253–257 (1996)

    Google Scholar 

  18. Usamentiaga, R., García, D.F., delaCalle, F.J.: Real-time inspection of long steel products using 3D sensors: calibration and registration. IEEE Transactions on Industry Applications, pp. 1–8 (2016)

  19. Usamentiaga, R., García, D.F., Molleda, J.: Efficient registration of 2D points to CAD models for real-time applications. J. Real-Time Image Proc. 15(2), 329–347 (2018)

    Article  Google Scholar 

  20. MVTec Software GmbH: HALCON 12.0.2 Solution Guide III-C 3D Vision (2016). Retrieved on 13 November 2018

  21. Vo, M., Wang, Z., Luu, L., Ma, J.: Advanced geometric camera calibration for machine vision. Opt. Eng. 50, 110503 (2011)

    Article  Google Scholar 

  22. The MathWorks, Inc.: Computer Vision System Toolbox(TM) Reference, Rev September 2018, for R2018b. Retrieved on 13 November 2018

Download references

Acknowledgements

This work was supported by the Spanish National Plan for Research, Development and Innovation [TIN2014-56047-P], by project FUO-EM-372-14 and by the “Severo Ochoa” program of the Asturian regional government (Administración del Principado de Asturias) [PA-17-PF-BP16009]. None of these funding sources had any involvement in study design, collection, analysis or interpretation of data, the writing of this paper or the decision to submit it for publication. The authors would also like to thank the technicians of ArcelorMittal Asturias for their helpful assistance during tests.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, University of Oviedo, Gijón, Spain

    Álvaro F. Millara, Julio Molleda, Rubén Usamentiaga & Daniel F. García

Authors
  1. Álvaro F. Millara
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Julio Molleda
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rubén Usamentiaga
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Daniel F. García
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Julio Molleda.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Hardware in the laboratory environment

Cameras: Genie Teledyne Dalsa HM1400.

Lenses: Schneider-Kreuznach APO-XENOPLAN 2.0/24-0005.

Laser filters: Coherent 635 CW - 20 BP and Coherent 685 CW - 20 BP.

Laser emitters: Coherent StingRay-640 (640 nm) and Coherent Stingray-685 (685 nm).

Hardware in the production environment

Cameras: Genie Teledyne Dalsa TS-M2560.

Lenses: Goyo 16mm HR 1” F1.4 C.

Laser filters: MidOpt Bi632 and MidOpt BP695.

Laser emitters: Coherent StingRay-640 (640 nm) and Coherent Stingray-685 (685 nm).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Millara, Á.F., Molleda, J., Usamentiaga, R. et al. Calibrating a profile measurement system for dimensional inspection in rail rolling mills. Machine Vision and Applications 32, 17 (2021). https://doi.org/10.1007/s00138-020-01147-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00138-020-01147-5

Keywords

Search

Navigation