Simulation of liquid production and water cut dynamics using fluid flow model and neural networks

Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy


Release:

2023. Vol. 9. № 2 (34)

Title: 
Simulation of liquid production and water cut dynamics using fluid flow model and neural networks


For citation: Legostaev, D. Yu., & Kosyakov, V. P. (2023). Simulation of liquid production and water cut dynamics using fluid flow model and neural networks. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 9(2), 75–92. https://doi.org/10.21684/2411-7978-2023-9-2-75-92

About the authors:

Dmitry Yu. Legostaev, Junior Researcher, Tyumen Branch of the Khristianovich Institute of Theoretical and Applied Mechanics of the Siberian Branch of the Russian Academy of Sciences; Senior Lecturer, Department of Applied and Technical Physics, University of Tyumen; eLibrary AuthorID, legostaevdy@yandex.ru; ORCID: 0000-0001-6371-7031

Vitaly P. Kosyakov, Cand. Sci. (Phys.-Math.), Senior Researcher, Tyumen Branch of the Khristianovich Institute of Theoretical and Applied Mechanics of the Siberian Branch of the Russian Academy of Sciences; Associate Professor, Department of Oil and Gas Flow Metering, University of Tyumen; eLibrary AuthorID, Web of Science ResearcherID; lik.24@yandex.ru; ORCID: 0000-0002-2297-408X

Abstract:

In the oil industry, there is a noticeable tendency to use proxy modeling of various levels of complexity to perform operational predictive calculations, in particular machine learning methods that are actively developing in the context of digitalization and intellectualization of production processes. In this paper, using the example of a synthetic oil reservoir model development element, we present an approach to the joint use of a physically meaningful fluid flow model and machine learning methods for solving adaptation and prediction problems. A feature of the considered synthetic model is the presence of a pronounced zonal inhomogeneity of the permeability field. Within the framework of the proposed approach, a single-phase filtration model, simplified in comparison with the original formulation was used, the history matching of which was carried out by restoring the field of reservoir filtration parameters using a network of radial basis functions. Based on the reconstructed field, the connection coefficients between the wells were calculated, which qualitatively and quantitatively correspond to the true well connections. The next step was to train a recurrent neural network in order to predict the water cut of the produced fluid. The use of a recurrent neural network made it possible to reproduce the characteristic non-monotonic behavior of the water cut of the produced fluid, caused by non-stationary modes of operation of injection and production wells. A combination of the presented models makes it possible to predict the volume of the produced fluid and its phase composition. To assess the predictive properties of the models, the actual data set was divided into training and test intervals.

References:

Aziz, Kh., & Settari, A. (2004). Petroleum reservoir simulation. Izhevsk Institute of Computer Science. [In Russian]

Andreev, V. B. (2013). Numerical methods. MAX Press. [In Russian]

Bekman, A. D., Pospelova, T. A., & Zelenin, D. V. (2020). A new approach to water cut forecasting based on results of capacitance resistance modeling. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 6(1), 192–207. https://doi.org/10.21684/2411-7978-2020-6-1-192-207 [In Russian]

Vlasov, A. I., & Mozhchil, A. F. (2018). Technology overview: From digital to intelligent field. PROneft. Professionally about Oil, (3), 68–74. https://doi.org/10.24887/2587-7399-2018-3-68-74 [In Russian]

Kanevskaya, R. D. (2002). Mathematical simulation of hydrodynamic processes of hydrocarbon deposits development. Izhevsk Institute of Computer Science. [In Russian]

Kosyakov, V. P., & Rodionov, S. P. (2016). Optimal control of wells on the basis of two-phase filtration equations. Proceedings of MIPT, 8(3), 79–90. [In Russian]

Kosyakov, V. P., Legostaev, D. Yu., & Musakaev, E. N. (2021). The problem of the combined use of filtration theory and machine learning elements for solving the inverse problem of restoring the hydraulic conductivity of an oil field. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 7(2), 113–129. https://doi.org/10.21684/2411-7978-2021-7-2-113-129 [In Russian]

Kosyakov, V. P., & Legostaev, D. Yu. (2022). Using elements of machine learning to solve the inverse problem of reconstructing the hydraulic conductivity field for a filtration problem. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 8(2), 129–149. https://doi.org/10.21684/2411-7978-2022-8-2-129-149 [In Russian]

Mazo, A. B., & Potashev, K. A. (2020). The superelements. Modeling of oil fields development. INFRA-M. https://doi.org/10.12737/1043236 [In Russian]

Potashev, K. A., Akhunov, R. R., & Mazo, A. B. (2022). Calculation of the flow rate between wells in the flow model of an oil reservoir using streamlines. Georesources, 24(1), 27–35. https://doi.org/10.18599/grs.2022.1.3 [In Russian]

Umanovskiy, A. W. (2022). Proxy modeling of reservoir hydrodynamics with graph neural networks. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 8(3), 155–177. https://doi.org/10.21684/2411-7978-2022-8-3-155-177 [In Russian]

Alakeely, A., & Horne, R. N. (2020). Simulating the behavior of reservoirs with convolutional and recurrent neural networks. SPE Reservoir Evaluation & Engineering, 23(3), 992–1005. https://doi.org/10.2118/201193-PA

Bai, T., & Tahmasebi, P. (2021). Efficient and data-driven prediction of water breakthrough in subsurface systems using deep long short-term memory machine learning. Computational Geosciences, 25(1), 285–297. https://doi.org/10.1007/s10596-020-10005-2

Farrell, P. E., Ham, D. A., Funke, S. F., & Rognes, M. E. (2013). Automated derivation of the adjoint of high-level transient finite element programs. SIAM Journal on Scientific Computing, 35(4), C369–C393. https://doi.org/10.48550/arXiv.1204.5577

Gopa, K., Yamov, S., Naugolnov, M., Perets, D., & Simonov, M. (2018, October 15–17). Cognitive analytical system based on data-driven approach for mature reservoir management [Conference paper SPE-191592-18RPTC-MS]. SPE Russian Petroleum Technology Conference, Moscow, Russia. https://doi.org/10.2118/191592-18RPTC-MS

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

Illarionov, E., Temirchev, P., Voloskov, D., Kostoev, R., Simonov, M., Pissarenko, D., Orlov, D., & Koroteev, D. (2022). End-to-end neural network approach to 3D reservoir simulation and adaptation. Journal of Petroleum Science and Engineering, 208, Article 109332. https://doi.org/10.1016/j.petrol.2021.109332

Innes, M., Saba, E., Fischer, K., Gandhi, Dh., Rudilosso, M. C., Joy, N. M., Karmali, T., Pal, A., & Shah, V. (2018). Fashionable modelling with Flux. ArXiv, Article 1811.01457. https://doi.org/10.48550/arXiv.1811.01457

Musakaev, E. N., Rodionov, S. P., & Musakaev, N. G. (2021). Hierarchical approach to identifying fluid flow models in a heterogeneous porous medium. Mathematics, 9(24), Article 3289. https://doi.org/10.3390/math9243289

Temirchev, P., Simonov, M., Kostoev, R., Burnaev, E., Oseledets, I., Akhmetov, A., Margarit, A., Sitnikov, A., & Koroteev, D. (2020). Deep neural networks predicting oil movement in a development unit. Journal of Petroleum Science and Engineering, 184, Article 106513. https://doi.org/10.1016/j.petrol.2019.106513