«Proceedings of Gubkin University»

Challenges of integrated approach to diagnosis of linear part of pipelines in improving system energy efficiency

UDC: 620.19:621.43
DOI: -

Authors:

¹ Gazprom Diagnostics, St. Petersburg, Russian Federation
² National University of Oil and Gas “Gubkin University”, Moscow, Russian Federation

Keywords: defects, in-line diagnostics, energy efficiency, machine learning

Annotation:

The development of methods of pipelines diagnostic inspections under tightening budget policy of energy corporations in terms of optimizing the costs of diagnostics, maintenance and repair (DMR), a balanced integrated approach combining various methods and methodologies of surveys without compromising the quality of technical condition assessment becomes urgent. It is shown that only such an approach can become the key to further energy efficiency growth of the entire gas transmission system. The paper considers and systematizes retrospective data on in-line and ground-based types of surveys, as well as evaluates the prospects for using information-intensive methods using machine learning. Examples of the quality of accounting for negative factors such as the degree of corrosion and stress-corrosion damage, the defects in geometry and welds detected by the results of surveys, etc. are given. The prospects of using artificial intelligence algorithms to predict the appearance of defects of various nature are considered separately. An assessment of the dynamics of the distribution of various survey methods in the next decade is made based on the analysis of existing trends and trends.

Bibliography:

1. Jarboui S., Hind A. Global Energy Transition and the Efficiency of the Largest Oil and Gas Companies // Energies 17. – 2024. – No. 10. – P. 2271.
2. Lin B., Du K. Measuring energy efficiency under heterogeneous technologies using a latent class stochastic frontier approach: An application to Chinese energy economy // Energy. – 2014. – No. 76. – P. 884–890.
3. Using Hybrid Machine Learning Methods to Predict and Improve the Energy Consumption Efficiency in Oil and Gas Fields / L. Jun, G. Yidong, Zh. Xiangyang, F. Zhanbao // Mobile Information Systems. – 2021. – P. 1–7. – DOI: 10.1155/2021/5729630
4. Ivanova T. Digital technologies in oil and gas production as a tool to ensure optimal energy efficiency and sustainability // E3S Web of Conferences. – 2023. – DOI: 10.1051/e3sconf/202341901007
5. Improving the accuracy of estimates of the pulse sequence period using the methodology of complete sufficient statistics / K.N. Zhuchkov, M. Vasilchenko, A.D. Zagrebneva, A.P. Zavyalov // Scientific Reports. – 2022. – Vol. 12, No. 1. – P. 19932. – DOI: 10.1038/s41598-022-24457-2 – EDN JCVKPJ.
6. Perspektivnye podhody v zadachah ocenki parametrov signalov / N.G. Parhomenko, S.G. Horuzhij, K.N. ZHuchkov [i dr.] // Morskaya radioelektronika. – 2006. – № 2 (16). – S. 46–49. – EDN FPVKCE.
7. O metodah obespecheniya energeticheskoj effektivnosti transportirovki gaza v sovremennyh usloviyah / A.P. Zav’yalov, D.P. Nikulina, M.M. Churikova, I.M. Grechishnikov // Trudy Rossijskogo gosudarstvennogo universiteta nefti i gaza imeni I.M. Gubkina. – 2023. – № 1 (310). – S. 145–152. – DOI: 10.33285/2073-9028-2023-1(310)-145-152 – EDN QUAIIT.
8. Zhuchkov K.N., Zav’yalov A.P. Sovershenstvovanie nauchno-metodicheskih podhodov k informacionno-analiticheskomu obespecheniyu sistemy diagnosticheskogo obsluzhivaniya oborudovaniya i truboprovodov kompressornyh stancij // Oborudovanie i tekhnologii dlya neftegazovogo kompleksa. – 2021. – № 1 (121). – S. 104–108. – DOI: 10.33285/1999-6934-2021-1(121)-104-108 – EDN YUVZKO.
9. Skrynnikov S.V. Sovremennye principy i napravleniya razvitiya sistemy organizacii diagnostiki, tekhnicheskogo obsluzhivaniya i remonta v PAO “Gazprom” // Gazovaya promyshlennost’. – 2017. – № S2 (754). – S. 4–9.
10. Leveraging Machine Learning for Pipeline Condition Assessment / L. Hongfang, X. Zhao-Dong, Z. Xulei [et al.] // Journal of Pipeline Systems Engineering and Practice. – 2023. –Vol. 14, No. 3. – DOI: 10.1061/JPSEA2.PSENG-1464
11. Zav’yalov A.P., Zhuchkov K.N., Vasil’chenko M. Process Pipeline Strength Calculation Methodology Enhancement Using Finite-Element Method // Journal of Pipeline Systems Engineering and Practice. – 2023. – Vol. 14, No. 2. – DOI: 10.1061/JPSEA2.PSENG-1401 – EDN PLAOJD.
12. Moubray J. Reliability-centered Maintenance. Second Edition’. – NY: Industrial Press Inc., 1997.
13. Review of prediction of stress corrosion cracking in gas pipelines using machine learning / M. Hussain, T. Zhang, M. Chaudhry, I. Jamil // Machines. – 2024. – No. 12. – 42 p. – MDPI.
14. Shatrov A.V., Pashchenko D.E. Sravnenie klassicheskih regressionnyh modelej s modelyami, postroennymi s pomoshch’yu prodvinutyh metodov mashinnogo obucheniya // Advanced Science. – 2019. – № 1 (12). – S. 24–28. – DOI: 10.25730/VSU.0536.19.004 – EDN QANBHL.
15. Kislenko N.A., Belinskij A.V., Kazak A.S. Metody, algoritmy i instrumenty modelirovaniya i optimizacii rezhimov raboty edinoj sistemy gazosnabzheniya Rossii na osnove tekhnologij iskusstvennogo intellekta. Chast’ 1 // Gazovaya promyshlennost’. – 2021. – № 9 (821). – S. 88–96. – EDN VZIBLB.
16. Tolstov A.G. Vvedenie v informatiku sistem tekhnicheskoj diagnostiki. – M.: IRC Gazprom, 2007. – 487 s. – EDN QNTYVL.
17. A comparison of random forest-based algorithms: random credal random forest versus oblique random forest / C.J. Mantas, Ja.G. Castellano, S. Moral-García, J. Abellán // Soft Computing – A Fusion of Foundations, Methodologies and Applications. – 2019. – Vol. 23, No. 21. – P. 10739–10754. – DOI: 10.1007/s00500-018-3628-5 – EDN OJRMWU.
18. Issledovanie tochnostnyh harakteristik i skhodimosti metodov prognozirovaniya poyavleniya defektov na truboprovode s ispol’zovaniem iskusstvennogo intellekta / K.N. Zhuchkov, A.P. Zav’yalov, K.V. Ovodkova, D.S. Pochikeev // Trudy Rossijskogo gosudarstvennogo universiteta nefti i gaza imeni I.M. Gubkina. – 2023. – № 4/313. – S. 104–117.