Mining of Mineral Deposits

ISSN 2415-3443 (Online)

ISSN 2415-3435 (Print)

Flag Counter

Modeling corrosion crack resistance of oil tanks using neural network analysis

Yurii Vynnykov1, Svitlana Manhura1, Aleksej Aniskin2, Мaryna Rybalko1, Yuliia Nikolaienko1, Andrii Manhura3

1National University “Yuri Kondratyuk Poltava Polytechnic”, Poltava, Ukraine

2University North, Varaždin, Croatia

3Ukrainian Research Institute of Natural Gases (UkrNDIGas), Kharkiv, Ukraine


Min. miner. depos. 2025, 19(4):31-39


https://doi.org/10.33271/mining19.04.031

Full text (PDF)


      ABSTRACT

      Purpose. The research aims to study the influence of aggressive components on corrosion crack resistance of tank steels used in tank farms for long-term storage of oil and petroleum products using neural network analysis.

      Methods. The MATLAB (MATrix LABoratory) system was chosen as the tool environment for interface modeling. It is a high-level programming language for technical calculations. Corrosion crack resistance testing of oil tanks was conducted on samples of 09G2S tank steel from dismantled tanks (with a service life of 5 and 10 years). The tests were performed in model environments at various NaCl concentrations and temperatures in accordance with the NACE standard on cylindrical samples with a diameter of 4 mm. During the research, neural network analysis, which is well suited for working with complex, non-linear dependences, was used to model the corrosion crack resistance of oil tanks. The neural network learns from the collected data, identifying complex correlations between input parameters and the probability of crack formation.

      Findings. Using an artificial neural network, dependences of the corrosion crack resistance of oil tanks, in particular, the rates of local corrosion and the steel destruction process were obtained for any set of known parameters such as sodium chloride concentrations in the experimental medium. Using trained neural networks, generalized corrosion rate dependences of oil tanks on the parameters of environments with different sodium chloride concentrations were obtained, and based on them the corrosion behaviour of tank steel was predicted. Based on the results of neural network analysis, the residual service life of steel tanks for storing oil and petroleum products has been determined, taking into account actual operating conditions.

      Originality. For the first time, neural network analysis has been used to model the corrosion crack resistance of oil tanks, which made it possible to obtain a neural model capable of predicting the corrosion resistance of steels depending on their chemical composition and the corrosion-active environment concentration. For the first time, an artificial neural network has been used to analyze and predict the remaining service life of steel tanks, allowing the remaining service life of oil tank steels to be predicted taking into account actual operating conditions, thereby reducing the risk of accidents.

      Practical implications. The proposed technology for applying neural network analysis can be used to predict the crack resistance of new tanks, assess the remaining service life of oil tanks, and plan preventive maintenance and technical servicing of tanks.

      Keywords: tank, steel, corrosion, crack resistance, ions, neural network, modeling


      REFERENCES

  1. Makarenko, V., & Shatilo, S. (1999). Increasing desulphurisation of the metal of welded joints in oil pipelines. Welding International, 13(12), 991–995. https://doi.org/10.1080/09507119909452086
  2. Radkevych, O., P’yasets’kyi, O., & Vasylenko, I. (2000). Corrosionmechanical resistance of pipe steel in hydrogen-sulfide containing media. Materials Science, 36(3), 425–430. https://doi.org/10.1007/bf02769606
  3. Martinez, F., Briones, F., Villarroel, M., & Vera, R. (2018). Effect of atmospheric corrosion on the mechanical properties of SAE 1020 structural steel. Materials, 11(4), 591. https://doi.org/10.3390/ma11040591
  4. Raffik, M., & Salleh, S. (2017). Effect of heat-treatment on the hardness and mechanical properties of boron alloyed steel. MATEC Web of Conferences, 90, 01014. https://doi.org/10.1051/matecconf/20179001014
  5. Makarenko, V., Vynnykov, Yu., & Manhura, A. (2020). Investigation of the mechanical properties of pipes for long-term cooling systems. International Conference on Building Innovations, 73, 151–160. https://doi.org/10.1007/978-3-030-42939-3_17
  6. Zhou, F., Dai, J., Gao, J., Zhou, Q., & Li, L. (2020). The X80 pipeline steel produced by a novel ultra fast cooling process. Journal of Physics: Conference Series, 1676, 012102. https://doi.org/10.1088/1742-6596/1676/1/012102
  7. Prifiharni, S., Sugandi, M., Pasaribu, R., Sunardi, S., & Mabruri, E. (2019). Investigation of corrosion rate on the modified 410 martensitic stainless steel in tempered condition. IOP Conference Series: Materials Science and Engineering, 541, 012001. https://doi.org/10.1088/1757-899X/541/1/012001
  8. Makarenko, V., Manhura, A., & Makarenko, I. (2020). Calculation method of safe operation resource evaluation of metal constructions for oil and gas purpose. Proceedings of the 2nd International Conference on Building Innovations, 73, 641–649. https://doi.org/10.1007/978-3-030-42939-3_63
  9. Vynnykov, Y., Kharchenko, M., Manhura, S., Aniskin, A., Hajiyev, M., & Manhura, A. (2022). Analysis of corrosion fatigue steel strength of pump rods for oil wells. Mining of Mineral Deposits, 16(3), 31–37. https://doi.org/10.33271/mining16.03.031
  10. Figueredo, R., Oliveira, M., Paula, L., Acciari, H., & Codaro, E. (2018). A comparative study of hydrogen-induced cracking resistances of API 5L B and X52MS carbon steels. International Journal of Corrosion, 2018, 1604507. https://doi.org/10.1155/2018/1604507
  11. Ismail, N., Khatif, N., Kecik, M., & Shaharudin, M. (2016). The effect of heat treatment on the hardness and impact properties of medium carbon steel. IOP Conference Series: Materials Science and Engineering, 114, 012108. https://doi.org/10.1088/1757-899X/114/1/012108
  12. Yuzevych, L., Yankovska, L., Sopilnyk, L., Yuzevych, V., Skrynkovskyy, R., Koman, B., Yasinska-Damri, L., Heorhiadi, N., Dzhala, R., & Yasinskyi, M. (2019). Improvement of the toolset for diagnosing underground pipelines of oil and gas enterprises considering changes in internal working pressure. Eastern-European Journal of Enterprise Technologies, 6(5(102)), 23–29. https://doi.org/10.15587/1729-4061.2019.184247
  13. El May, M., Saintier, N., Palin-Luc, T., Devos, O., & Brucelle, O. (2018). Modelling of corrosion fatigue crack initiation on martensitic stainless steel in high cycle fatigue regime. Corrosion Science, 133, 397–405. https://doi.org/10.1016/j.corsci.2018.01.034
  14. Gopalaswami, N., Liu, Y., Laboureur, D.M., Zhang, B., & Mannan, M. (2019). Experimental study on propane jet fire hazards: Comparison of main geometrical features with empirical models. Journal of Loss Prevention in the Process Industries, 41, 365–375. https://doi.org/10.1016/j.jlp.2016.02.003
  15. Hu, J., Du, L., Xie, H., Gao, X., & Misra, R. (2014). Microstructure and mechanical properties of TMCP heavy plate microalloyed steel. Materials Science and Engineering: A, 607, 122–131. https://doi.org/10.1016/j.msea.2014.03.133
  16. Wang, X., Yuan, G., Zhao, J., & Wang, G. (2020). Microstructure and strengthening/toughening mechanisms of heavy gauge pipeline steel processed by ultrafast cooling. Metals, 10(10), 1323. https://doi.org/10.3390/met10101323
  17. Qin, M., Li, J., Chen, S., & Qu, Y. (2016). Experimental study on stress corrosion crack propagation rate of FV520B in carbon dioxide and hydrogen sulfide solution. Results in Physics, 6, 365–372. https://doi.org/10.1016/j.rinp.2016.06.012
  18. Yuzevych, V., Dzhala, R., & Koman, B. (2018). Analysis of metal corrosion under conditions of mechanical impacts and aggressive environments. Metallofizika i Novitni Tekhnologii, 39(12), 1655–1667. https://doi.org/10.15407/mfint.39.12.1655
  19. Zulkifli, F., Ali, N., Yusof, M., Khairul, W., Rahamathullah, R., Isa, M., & Wan Nik, W. (2017). The effect of concentration of Lawsonia inermis as a corrosion inhibitor for aluminum alloy in seawater. Advances in Physical Chemistry, 2017, 8521623. https://doi.org/10.1155/2017/8521623
  20. Makarenko, V., Manhura, S., Kharchenko, M., Melnikov, O., & Manhura, A. (2021). Study of corrosion and mechanical resistance of structural pipe steels of long-term operation in hydrogen sulfur containing. Materials Science Forum, 1045, 203–211. https://doi.org/10.4028/www.scientific.net/MSF.1045.203
  21. Colorado-Garrido, D., Ortega-Toledo, D., Hernández, J., González-Rodríguez, J., & Uruchurtu, J. (2008). Neural networks for Nyquist plots prediction during corrosion inhibition of a pipeline steel. Journal of Solid State Electrochemistry, 13(11), 1715–1722. https://doi.org/10.1007/s10008-008-0728-7
  22. Liao, K., Yao, Q., Wu, X., & Jia, W. (2012). Numerical corrosion rate prediction method for direct assessment of wet gas gathering pipelines internal corrosion. Energies, 5(10), 3892–3907. https://doi.org/10.3390/en5103892
  23. Zhang, K., Shen, Y., Palulli, R., Ghobadian, A., Nouri, J., & Duwig, C. (2023). Combustion characteristics of steam-diluted decomposed ammonia in multiple-nozzle direct injection burner. International Journal of Hydrogen Energy, 48(42), 16083–16099. https://doi.org/10.1016/j.ijhydene.2023.01.091
  24. Bukhamseen, N.Y., & Ertekin, T. (2017). The use of artificial neural networks to quantify the effect of formation damage on well production response. SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition, SPE-188094-MS. https://doi.org/10.2118/188094-MS
  25. Allegrini, E., Vadenbo, C., Boldrin, A., & Astrup, T. (2015). Life cycle assessment of resource recovery from municipal solid waste incineration bottom ash. Journal of Environmental Management, 151, 132–143. https://doi.org/10.1016/j.jenvman.2014.11.032
  26. Esmaeili, A., Elahifar, B., Fruhwirth, R., & Thonhauser, G. (2012). ROP modeling using neural network and drill string vibration data. SPE Kuwait International Petroleum Conference and Exhibition, 1–13. https://doi.org/10.2118/163330
  27. Lozovan, V., Dzhala, R., Skrynkovskyy, R., & Yuzevych, V. (2019). Detection of specific features in the functioning of a system for the anticorrosion protection of underground pipelines at oil and gas enterprises using neural networks. Eastern-European Journal of Enterprise Technologies, 1(5(97)), 20–27. https://doi.org/10.15587/1729-4061.2019.154999
  28. Vynnykov, Y., Kharchenko, M., Manhura, S., Aniskin, A., & Manhura, A. (2024). Neural network analysis of safe life of the oil and gas industrial structures. Mining of Mineral Deposits, 18(1), 37–44. https://doi.org/10.33271/mining18.01.037
  29. Alloush, R., Elkatatny, S., Mohmoud, M., Moussa, T., Ali, A., & Abdulraheem, A. (2017). Estimation of geomechanical failure parameters from well logs using artificial intelligence techniques. Kuwait Oil & Gas Show and Conference, 9(10), 165–177. https://doi.org/10.2118/187625-MS
  30. Lozovan, V., Skrynkovskyy, R., Yuzevych, V., Yasinskyi, M., & Pawlowski, G. (2019). Forming the toolset for development of a system to control quality of operation of underground pipelines by oil and gas enterprises with the use of neural networks. Eastern-European Journal of Enterprise Technologies, 2(5(98)), 41–48. https://doi.org/10.15587/1729-4061.2019.161484

    31. Лицензия Creative Commons

Copyright © 2025 Dnipro University of Technology

Underground Mining Department

All Rights Reserved.

Journal homepage Authors