Release:
2024. Vol. 10. № 4 (40)About the authors:
Roman Yu. Ponomarev, Manager, Tyumen Petroleum Research Center, Tyumen, Russia; ryponomarev@tnnc.rosneft.ruAbstract:
When designing the development of oil and gas fields, the use of mathematical modeling methods is required to select the optimal option for field development. One of the key tasks is to simulate the dynamics of flooding producing wells with an operating reservoir pressure maintenance system. The target modeling parameters include the time of water breakthrough into the producing well and the amount of product flooding at the breakthrough time. Practically, such calculations are performed on 3D hydrodynamic simulators based on the numerical solution of differential filtration equations. The accuracy of numerical modeling in this case largely depends on the quality of constructing the grid calculation area, while the quality significantly depends on the shape of the calculation area. The increase in the size of grid blocks, typical for hydrodynamic modeling, has a negative effect on the calculation accuracy. One of the alternative methods of modeling physical processes is neural network modeling. A recent widespread method is physically informed neural networks capable of approximating exact solutions of differential equations with high accuracy. The key feature of this approach is organizing neural network learning process both on precise initial and boundary values, as well as on the execution of predefined systems of differential and algebraic equations. In this case, a trained neural network can calculate desired values at any point in the definition area, and not only at the nodal points when using finite difference solutions. Thus, this works aims to develop neural network methods for calculating phase saturation in large-scale modeling of two-phase filtration; and to evaluate the accuracy of the solutions obtained. The article provides a comparative analysis of solutions to the one-dimensional Buckley–Leverett problem. Three methods of obtaining solutions are considered: an exact analytical solution; a numerical solution obtained by finite difference methods; and a grid-less neural network approximation based on a multilayer perceptron model. The upwind method was used as a finite difference method, which provides the most accurate reproduction of saturation changes. A multilayer perceptron with two types of activation functions was used as a physically informed neural network. An additional condition, which corresponds to the law of conservation of mass at the jump, needed to be included in the error functional in order to determine the position of the saturation jump. The results showed that after training, the neural network solution can reproduce the evolution of rarefaction waves and saturation jumps with high accuracy. The nodes density of the training sample can be reduced without significantly reducing the accuracy of the neural network approximation. The results obtained can be used in the development of hybrid algorithms for modeling oil displacement processes.Keywords:
References:
Barenblatt, G. I., Entov, V. M., & Ryzhik, V. M. (1984). Movement of Liquids and Gases in Natural Formations. Nedra. [In Russian]
Basniev, K. S., Kochina, I. N., & Maksimov, V. M. (1993). Theory of two-phase filtration of immiscible liquids. In Underground Hydromechanics (pp. 227–251). Nedra. [In Russian]
Brilliant, L. S., Gorbunova, D. V., Zavyalov, A. S., Simakov, E. A., Beskursky, V. V., & Ryabets, D. A. (2019). Production management based on neural network optimization of well operating modes at the BS8 facility of the Zapadno-Malobalykskoye field. Business Magazine “Neftegaz.RU”, (6), 92–98. [In Russian]
Brilliant, L. S., Zavyalov, A. S., Danko, M. Yu., Elisheva, A. O., & Tsinkevich, O. V. (2020). Procedure of proxy modelling algorithms testing. Nedropolzovanie XXI vek, (4), 128–137. https://www.elibrary.ru/obkwbf [In Russian]
Brilliant, L. S., Komyagin, A. I., Blyashuk, M. M., Tsinkevich, O. V., & Zhuravleva, A. A. (2017). Method of Real-Time Control of Reservoir Flooding (R.F. Patent No. 2614338). RF Federal Service for Intellectual Property. [In Russian]
Vasiliev, A. N., Tarkhov, D. A., & Shemyakina, T. A. (2015). Neural Network Approach to Problems of Mathematical Physics. Nestor-Istoriya. [In Russian]
Vasiliev, A. N., Tarkhov, D. A., & Shemyakina, T. A. (2016). Approximate analytical solutions of ordinary differential equations. Modern Information Technologies and IT-Education, 12(3-2), 188–195. Retrieved Dec. 4, 2024, from http://sitito.cs.msu.ru/index.php/SITITO/article/view/141 [In Russian]
Vershinin, V. E., & Ponomarev, R. Yu. (2023). Application of neural network modeling methods in solving initial boundary value problems for partial differential equations. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 9(3), 132–147. https://doi.org/10.21684/2411-7978-2023-9-3-132-147 [In Russian]
Zrelova, D. P., & Ulyanov, S. V. (2022). Physics-informed classical Lagrange / Hamilton neural networks in deep learning. Modern Information Technologies and IT-Education, 18(2), 310–325. https://doi.org/10.25559/SITITO.18.202202.310-325 [In Russian]
Ivanenko, B. P. (2014). Neural Network Simulation of Oil Fields and Hydrogeological Objects. Publishing House of National Research Tomsk State University. [In Russian]
Kovalenko, A. N., Chernomorets, A. A., & Petina, M. A. (2017). On the neural networks application for solving of partial differential equations. Belgorod State University Scientific Bulletin. Economics. Information Technologies, (9), 103–110. [In Russian]
Kolmogorov, A. N. (1957). On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Doklady Akademii Nauk SSSR, 114(5), 953–956. [In Russian]
Ovcharov, V. V. (2014). Scaling of relative permeability functions as a method of regularizing numerical solution of the water-oil displacement problem. Oil Industry, (3), 102–105. [In Russian]
Haykin, S. (2019). Neural Networks (2nd ed.). Dialektika. [In Russian] (Original work published 2001, Prentice Hall)
Aziz, K., & Settari, A. (1979). Petroleum Reservoir Simulation. Applied Science Publishers.
Fuks, O., & Tchelepi, H. A. (2020). Limitations of physics informed machine learning for nonlinear two-phase transport in porous media. Journal of Machine Learning for Modeling and Computing, 1(1), 19–37. https://doi.org/10.1615/JMachLearnModelComput.2020033905
Gasmi, C. F., & Tchelepi, H. (2021). Physics informed deep learning for flow and transport in porous media. arXiv. https://doi.org/10.48550/arXiv.2104.02629
Gasmi, C. F., & Tchelepi, H. (2022). Uncertainty quantification for transport in porous media using parameterized physics informed neural networks. arXiv. https://doi.org/10.48550/arXiv.2205.12730
Ponomarev, R. Yu., & Vershinin, V. E. (2021, Oct. 12–15). Long-term forecasting and optimization of non-stationary well operation modes through neural networks simulation [Conference paper SPE-206529-MS]. SPE Russian Petroleum Technology Conference, Virtual. https://doi.org/10.2118/206529-MS
Vershinin, V. E., Ponomarev, R. Yu., & Strekalov, A. V. (2020, Oct. 26–29). Neural network as a tool for predicting and controlling the technological regime of production wells [Conference paper SPE-201937-MS]. SPE Russian Petroleum Technology Conference, Virtual. https://doi.org/10.2118/201937-MS
