(47-1) 19 * << * >> * Russian * English * Content * All Issues

Classification of surface defects in the base metal of pipelines based on complex diagnostics results
N.P. Aleshin 1, S.V. Skrynnikov 2, N.V. Krysko 1, N.A. Shchipakov 1, A.G. Kusyy 1

Federal State Budgetary Educational Institution of Higher Education «Bauman Moscow State Technical University»,
105005, Moscow, Baumanskaya 2nd street, building 5 building 1;
Public Joint Stock Company Gazprom, 117997, Moscow, Russian Federation, GSP-7, Nametkina St., 16

 PDF, 2575 kB

DOI: 10.18287/2412-6179-CO-1185

Pages: 170-178.

Full text of article: Russian language.

We discuss issues of classification of operational volumetric and planar surface defects based on the results of complex diagnostics by non-destructive ultrasonic sounding using Rayleigh surface waves generated by an electromagnetic-acoustic transducer and the eddy current method. The paper presents results of feature selection using a variance analysis (ANOVA) and an Extra Trees Classifier algorithm, making it possible to select an optimal eddy current transducer for surface defect classification. The classification of surface defects by the amplitude of ultrasonic and eddy current signals, as well as the phase of the eddy current signal separately is shown to be unambiguous. Models for classifying surface defects as being volumetric or planar are constructed based on statistical methods such as Bayesian inference and the Dempster-Schafer theory. The workability of the constructed classification models is evaluated using metrics such as the Jaccard coefficient and the F1-measure.

surface defects, ultrasonic testing, eddy current testing, complex diagnostics, joint data evaluation, machine learning, Bayesian inference, Dempster-Schafer theory.

Aleshin NP, Skrynnikov SV, Krysko NV, Shchipakov NA, Kusyy AG. Classification of surface defects in the base metal of pipelines based on complex diagnostics results. Computer Optics 2023; 47(1): 170-178. DOI: 10.18287/2412-6179-CO-1185.


  1. Davydova DG. Defects in process pipelines: typology, assessment of the impact on operation [In Russian]. Prombezopasnost-Priuralye 2012; 8: 24-28.
  2. Yerekhinsky BA, Maslakov SV, Shustov NI, Mitrofanov AV, Baryshov SN, Zaryaev MYu, Kravtsov AV, Yegorov SV. Cracking of metal housings of Christmas-tree gate valves of northern fields gas producers [In Russian]. Territory "Neftegaz" 2014; 2: 31-36.
  3. Safina IS, Kauzova PA, Gushchin DA. Assessment of the technical condition of vertical steel tanks [In Russian]. TekhNadzor 2016; 3(112): 39-42.
  4. Butusov DS, Egorov SI, Zavyalov AP, Lyapichev DM. Stress corrosion cracking of gas pipelines: Textbook [In Russian]. Moscow: Publishing Center of the Russian State University of Oil and Gas named after I.M. Gubkin; 2015.
  5. Kalinichenko NP, Vasiliev MA. Atlas of defects in welded joints and base metal: teaching aid [In Russian]. Tomsk: Publishing House of Tomsk Polytechnic University; 2006. ISBN: 978-5-98298-908-6.
  6. Aleshin NP. Physical methods of non-destructive testing of welded joints: textbook [In Russian]. 2nd ed., revised. Moscow: “Innovative Engineering” Publisher; 2019. ISBN: 978-5-94275-695-6.
  7. Kuncheva LI. Fuzzy classifier design. Heidelberg: Springer-Verlag; 2000. DOI: 10.1007/978-3-7908-1850-5.
  8. Fung G, Mangasarian O. Proximal Support vector machine classifiers. Mach Learn 2005; 59(1-2): 77-97.
  9. Quinlan JR. Induction of decision trees. Mach Learn 1986; 1: 81-106. DOI:10.1007/BF00116251.
  10. Minsky M, Papert SA. Perceptrons: An introduction to computational geometry. The MIT Press; 2017. DOI: 10.7551/mitpress/11301.001.0001.
  11. Challa, S, Koks D. Bayesian and Dempster-Shafer fusion. Sadhana 2004; 29: 145-176. DOI: 10.1007/BF02703729.
  12. Meyer SL. Data analysis for scientists and engineers. Peer Management Consultants Ltd; 1992. ISBN: 978-0-9635027-0-4.
  13. Hall DL. Mathematical techniques in multisensor data fusion. Artech Print on Demand; 2004. ISBN: 978-1-58053-335-5.
  14. Gros XE. NDT data fusion. London: U.K.: Arnold; 1997. ISBN: 978-0340676486.
  15. Gros XE. Applications of NDT data fusion. New York: Springer; 2001. ISBN: 978-0-7923-7412-1.
  16. Dromigny A, Zhu YM. Improving the dynamic range of real-time X-ray imaging systems via Bayesian fusion. J Nondestr Eval 1997; 16: 147-160. DOI: 10.1023/A:1022606310811
  17. Aleshin NP, Skrynnikov SV, Krysko NV, Shchipakov NA, Kusy AG. Approaches to weld quality assurance in gas pipelines based on an integrated analysis of data obtained by various non-destructive test methods [In Russian]. GAS Industry of Russia 2021; S3(823): 28-32.
  18. Aleshin NP, Krysko NV, Kusyy AG, Skrynnikov SV, Mogilner LY. Investigating the detectability of surface volumetric defects in ultrasonic testing with the use of rayleigh waves generated by an electromagnetic-acoustic transducer [In Russian]. Russian Journal of Nondestructive Testing 2021; 57 (5): 361-368. DOI: 10.31857/S0130308221050031.
  19. Aleshin NP, Krysko NV, Skrynnikov SV, Kusyy AG. Studying detectability of plane surface defects by ultrasonic method using rayleigh waves [In Russian]. Russian Journal of Nondestructive Testing 2021; 57 (6): 446-454. DOI: 10.31857/S0130308221060038.
  20. SONAFLEX multipurpose test electronics unit. Source: <https://nordinkraft.de/sonaflex/>.
  21. Shubochkin AE. Development and current state of the eddy current method of non-destructive testing: monograph [In Russian]. Moscow: "Spectrum" Publishing house; 2014. ISBN: 978-5-4442-0075-9.
  22. Wright M. Eddy current testing technology. Waterloo: Eclipce Scientific; 2015. ISBN: 978-0-9917095-6-4.
  23. Barker TB, Milivojevich A. Quality by experimental design. CRC Press; 2016. ISBN: 9781032098050.
  24. Aleshin NP, Krysko NV, Kirikov AV. Development of a flaw detector robot combining inspection methods with the use of digital technologies [In Russian]. Proc XIII All-Russian Conf on Testing and Research of the Properties of Materials "TestMat" 2021: 144-156.
  25. Murphy KP. Machine learning: A probabilistic perspective. MIT Press Publisher; 2012. ISBN: 978-0262018029.
  26. Chen Q, Whitbrook A, Aickelin U, Roadknight C. Data classification using the Dempster-Shafer method. J Exp Theor Artif Intell 2014; 26(4): 493-517. DOI: 10.1080/0952813X.2014.886301.
  27. Powers DMW. Evaluation: From precision, recall and f-measure to ROC, informedness, markedness & correlation. J Mach Learn Res 2011; 2(1): 37-63.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20