Skip to main content
SpringerLink
Log in

Automation of expert analysis of diagnostic data in the MFL nondestructive testing of gas pipelines

  • Magnetic Methods
  • Published:
Russian Journal of Nondestructive Testing Aims and scope Submit manuscript

Abstract

A new flaw-detection technique for testing pipelines based on the data of magnetic in-tube inspection is considered. The technique uses the apparatus of contour analysis of discrete signals. An algorithm for minimization of the magnetic-image description length is proposed. Classification features for the main classes of recognized objects are developed. The solution of the problem of automated expertise of the in-tube testing is studied. The results of practical application of the developed technique are considered.

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

Similar content being viewed by others

References

  1. Shlezinger, M.I., Theory of 2D Grammars Applied to Image Recognition, Doctoral (Phys.-Math.) Dissertation, Kiev: Glushkov Cybernetics Inst., National Academy of Sciences of Ukraine, 1990.

    Google Scholar 

  2. Furman, Ya.A., Vvedenie v konturnyi analiz. Prilozheniya k obrabotke izobrazhenii i signalov (An Introduction to the Contour Analysis. Applications to the Image and Signal Processing), Moscow: Fizmatlit, 2003.

    Google Scholar 

  3. Slesarev, D.A., Vasin, E.S., Stepanov, N.O., Barat, V.A., and Shipyakov, M.N., Identification and Estimation of Defects’ Parameters during Magnetic In-Tube Diagnostics with an MDSkan Flaw Detector, OOO Intron-Plyus, OAO TsTD Diaskan, Tezisy Dokl. XVII Rossiiskoi Nauch.-Tekh. Konf. “Nerazr. Kontrol’ i Diagnostika” (Proc. of XVII Russ. Sci. Tech. Conf. “Nondestruct. Test. and Diagnostics”), 2005.

  4. Suna, R. and Berns, K., NeuroPipe—a Neural-Network-Based System for Pipeline Inspection, Germany: Research Center for Computer Science at the University of Karlsruhe.

  5. Haueisen, J., Unger, R., Beuker, T., and Bellemann, M., Evaluation of Inverse Algorithms in the Analysis of Magnetic Flux Leakage Data, IEEE Trans. Magn., 2002, vol. 38, no. 3.

  6. Rempel, R., Anomaly Detection Using Magnetic Flux Leakage Technology, Rio Pipeline Conference & Exposition, Rio de Janeiro: BJ Pipeline Inspection Services, Instituto Brasileiro de Petroleo e Gas, 2005.

    Google Scholar 

  7. Polikar, R., Udpa, L., Udpa, S., and Honavar, V., An Incremental Learning Algorithm with Confidence Estimation for Automated Identification of NDE Signals, IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 2004, vol. 51, no. 8.

Download references

Author information

Authors and Affiliations

  1. NPO Spetsneftegaz, Yekaterinburg, Russia

    V. A. Kanaikin, A. F. Matvienko & V. A. Povagin

Authors
  1. V. A. Kanaikin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. F. Matvienko
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. V. A. Povagin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to V. A. Kanaikin.

Additional information

Original Russian Text © V.A. Kanaikin, A.F. Matvienko, V.A. Povagin, 2007, published in Defektoskopiya, 2007, Vol. 43, No. 8, pp. 25–31.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kanaikin, V.A., Matvienko, A.F. & Povagin, V.A. Automation of expert analysis of diagnostic data in the MFL nondestructive testing of gas pipelines. Russ J Nondestruct Test 43, 510–514 (2007). https://doi.org/10.1134/S1061830907080025

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1061830907080025

Keywords

Search

Navigation