Intelligent systems for assessing the residual resource of field pipelines

UDK: 622.692.4; 004:8
DOI: 10.24887/0028-2448-2024-10-134-138
Key words: field pipelines, oil pipeline, gas pipeline, residual resource, intelligent system, neural networks, data analysis, reliability, safety
Authors: E.L. Chizhevskaya (Industrial University of Tyumen, RF, Tyumen) A.D. Vydrenkov (Industrial University of Tyumen, RF, Tyumen) M.Yu. Zemenkova (Industrial University of Tyumen, RF, Tyumen) Yu.D. Zemenkov (Industrial University of Tyumen, RF, Tyumen)

The work is devoted to the actual task of reliability monitoring in hydrocarbon gathering and transportation systems. For field gathering systems transporting mixtures of different composition, the problem of residual life estimation is especially urgent. The article is devoted to models of residual life estimation with application of intelligent models and algorithms. As an example, the results of implementation of the model in the Python software environment for real production systems are presented. The developed model is realized by two interconnected blocks: a block of preliminary processing of data streams coming into the model and a block of machine learning system with the module of data reliability assessment. The system is based on gradient bousting, which is a combined decision tree. The mathematical foundations of the applied clustering algorithm and the basics of validity assessment are presented. A comparative analysis of the results of evaluation using the new model with the known standardized methods on real data is carried out. It is shown that with qualitative preparation of the information the intelligent model makes it possible to obtain more exact results, than known methods and to take into account the production number of factors determining the residual resource of the system. Thus, the new model allows predicting the residual resource with the use of databases of available configuration, which is especially important in the conditions of incomplete information or expansion of databases of monitoring of field systems.

References

1. Lisin I.Yu., Korolenok A.M., Kolotilov Yu.V., System approach to the formation of integrated energy systems on the platform of intelligent information technology solutions (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2020, no. 3, pp. 36-40, DOI: https://doi.org/10.24887/0028-2448-2020-3-36-40

2. Anikin I.D., Belostotskiy M.A., Grechishnikov I.M., Korolenok A.M., Intelligent system for managing integral risk and residual resources of linear sections of main pipelines (In Russ.), Tr. RGU nefti i gaza (NITs) imeni I.M. Gubkina = Proceedings of Gubkin University, 2021, no. 3 (304), pp. 59-67,

DOI: https://doi.org/10.33285/2073-9028-2021-3(304)-59-67

3. Aksyutin O.E., Aleksandrov A.A., Aleshin A.V. et al., Bezopasnost’ Rossii. Pravovye, sotsial’no-ekonomicheskie i nauchno-tekhnicheskie aspekty. Bezopasnost’ sredstv khraneniya i transporta energoresursov (Security of Russia. Legal, socio-economic and scientific-technical aspects. Security of energy storage and transportation facilities): edited by Makhutov N.A., Moscow: Znanie Publ., 2019, 928 p.

4. Leonovich I.A., Vasil’ev G.G., Comparative study of wall thickness calculation practices for main gas pipelines built from high grade pipes (In Russ.), Gazovaya promyshlennost’, 2023, no. 6(850), pp. 56-64.

5. Vydrenkov A.D., Zemenkova M.Yu., Sravnenie metodik rascheta ostatochnogo resursa sistem sbora na promyslovykh uchastkakh truboprovoda (Comparison of methods for calculating the residual resource of collection systems in industrial sections of the pipeline), Proceedings of International scientific and technical conference, Tyumen, 1–2 June 2023, Tyumen: Publ. of TIU, 2023, pp. 223–226.

6. Brink H., Richards J., Fetherolf M., Real-world machine learning, Manning Publications, 2016, 264 p.

7. Raschka S., Unlock deeper insights into Machine Leaning with this vital guide to cutting-edge predictive analytics, Packt Publishing Ltd, 2015, 454 p.

8. Haykin S., Neural networks: A comprehensive foundation, Prentice-Hall, 1999, 874 p.

9. Zemenkova M.Yu., Chizhevskaya E.L, Zemenkov Yu.D., Intelligent monitoring of the condition of hydrocarbon pipeline transport facilities using neural network technologies (In Russ.), Zapiski Gornogo instituta = Journal of Mining Institute, 2022, V. 258, pp. 933–944, DOI: https://doi.org/10.31897/PMI.2022.105

10. Chizhevskaya E.L., Obukhova A.M., Zemenkova M.Yu., Zemenkov Yu.D., Clustering in the analysis of complex safety and effectiveness of management decisions at various stages of the life cycle of pipeline transport systems (In Russ.), Problemy sbora, podgotovki i transporta nefti i nefteproduktov, 2023, no. 6(146), pp. 101–111,

DOI: https://doi.org/10.17122/ntj-oil-2023-6-101-111



Attention!
To buy the complete text of article (Russian version a format - PDF) or to read the material which is in open access only the authorized visitors of the website can. .