APPLICATION OF A NEURAL NETWORK FOR DETERMINING THE LEAK LOCATION IN MAIN PIPELINES

Pipelines are widely used for the transportation of water, oil, gas, and other liquid and gaseous media. The occurrence of leaks in pipeline systems leads to significant losses of natural resources and may pose a threat to the environment and public safety. In this regard, the problem of timely leak detection and localization remains one of the most important challenges in the oil and gas industry. This paper addresses the problem of determining the leak location in a pipeline based on pressure measurement data using artificial intelligence methods. An approach to leak localization is proposed based on approximating the relationship between pressure drop, leak flow rate, and the distance to the leak location using a radial basis function neural network implemented in the MATLAB environment. Experimental data were obtained during testing of a leak detection system under simulated leak conditions with different operating modes. The simulation results demonstrate that the developed model provides an effective approximation of the studied relationship and allows the leak location to be determined with a root-mean-square error of approximately 1.9 km for medium and large leaks, confirming the potential of neural network-based methods for pipeline monitoring applications.

1. Adegboye M.A. Recent advances in pipeline monitoring and oil leakage detection technologies: Principles and approaches / M.A. Adegboye, W.K. Fung, A. Karnik // Sensors. – 2019. – Vol. 19. – 2548. https://doi.org/10.3390/s19112548. (In English).

2. Arifin B. M. S., Li Z., Shah S. L., Meyer G. A., Colin A. A novel data-driven leak detection and localization algorithm using the Kantorovich distance // Computers & Chemical Engineering. – 2018. – Vol. 108. – P. 300-313. https://doi.org/10.1016/j.compchemeng.2017.09.022. (In English).

3. Li S.Z. Leak detection of water distribution pipeline subject to failure of socket joint based on acoustic emission and pattern recognition / S.Z. Li, Y.J. Song, G.Q. Zhou // Measurement. – 2018. – Vol. 115. – P. 39-44. https://doi.org/10.1016/j.measurement.2017.10.021. (In English).

4. Zhang S. Pipeline deformation monitoring using distributed fiber optical sensor / S. Zhang, B. Liu, J. He // Measurement. – 2019. – Vol. 133. – P. 208-213. https://doi.org/10.1016/j.measurement.2018.10.021. (In English).

5. Pipeline rupture detection using real-time transient modelling and convolutional neural networks / J. Smith et al // Proceedings of the 12th International Pipeline Conference (IPC 2018), Calgary, Canada. – New York, NY: ASME, 2018. https://doi.org/10.1115/IPC2018-78426. (In English).

6. A novel location algorithm for pipeline leakage based on the attenuation of negative pressure wave / J. Li et al // Process Safety and Environmental Protection. – 2019. – Vol. 123. – P. 309-316. https://doi.org/10.1016/j.psep.2019.01.010. (In English).

7. Deeppipe: A deep-learning method for anomaly detection of multi-product pipelines / J. Zheng et al // Energy. – 2022. – Vol. 259. – 125025. https://doi.org/10.1016/j.energy.2022.125025. (In English).

8. A small leakage detection approach for gas pipelines based on CNN / J. Li et al // Proceedings of the CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), Xiamen, China. – 2019. – P. 390-394. https://doi.org/10.1109/SAFEPROCESS45799.2019.9213371. (In English).

9. A two-stage deep-learning based detection method for pipeline leakage and transient conditions / I. Amini et al // Proceedings of the IEEE Electric Power and Energy Conference (EPEC), Edmonton, Canada. – 2020. – P. 1-5. https://doi.org/10.1109/EPEC48502.2020.9320021. (In English).

10. Deep learning identifies leak in water pipeline system using transient frequency response / Z. Liao et al // Process Safety and Environmental Protection. – 2021. – Vol. 155. – P. 355-365. https://doi.org/10.1016/j.psep.2021.09.033. (In English).

11. Cody R. Detecting leaks in water distribution pipes using a deep autoencoder and hydroacoustic spectrograms / R. Cody, B. Tolson, J. Orchard // Journal of Computing in Civil Engineering. – 2020. – Vol. 34. – 4020001. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000881. (In English).

12. Lur'e M.V. Proektirovanie i ehkspluatatsiya nefteprovodov: uchebnik dlya studentov tekhnicheskikh vuzov / M.V. Lur'e, B.N. Mastobaev, A.E. Soshchenko. – M.: Infra-Inzheneriya, 2023. – 384 s. (In Russian).

13. Bekker A.A. Truboprovodnyi transport nefti i gaza: uchebnoe posobie / A.A. Bekker, V.A. Ivanov. – SPb.: Lan', 2020. – 256 s. (In Russian).

14. Peabody R. (Ed.) Handbook of pipeline engineering. – Cham: Springer, 2023. (In English).

15. Bulatov A.F. Povyshenie ehffektivnosti avtomatizirovannoi sistemy obnaruzheniya utechek iz nefteproduktoprovodov na osnove intellektual'nykh tekhnologii / A.F. Bulatov. – Ufa: UGATU, 2015. – 235 s. (In Russian).

16. Osiadacz A. Flow modelling and control in pipeline systems: A formal systematic approach / A. Osiadacz. – Cham: Springer, 2021. https://doi.org/10.1007/978-3-030-59246-2. (In English).

17. Pipeline inspection and health monitoring technology: The key to integrity management / H. Lu et al. – Singapore: Springer, 2023. https://doi.org/10.1007/978-981-19-6798-6. (In English).