References

geores

Георесурсы

Georesources

1608-50431608-5078

Georesursy LLC

10.18599/grs.2024.1.9

geores-234

Research Article

СТАТЬИ

RESEARCH ARTICLES

Прогнозирование гидродинамических параметров состояния призабойной зоны скважин с помощью методов машинного обучения

Prediction of Hydrodynamic Parameters of the State of the Bottomhole Zone of Wells Using Machine Learning Methods

Соромотин

А. В.

Soromotin

A. V.

Андрей Витальевич Соромотин – инженер 2-й категории отдела проектирования и мониторинга разработки Северной группы месторождений, филиал

614015, Пермь, ул. Пермская, д. 3а

Andrey V. Soromotin – Engineer of the Depertment of Design and Monitoring of North group of fields

3a, Permskaya st., Perm, 614015

s@soromotinav.ru

Мартюшев

Д. А.

Martyushev

D. A.

Дмитрий Александрович Мартюшев – доктор тех. наук, доцент, доцент кафедры Нефтегазовые технологии

614990, Пермь, пр-т Комсомольский, д. 29

Dmitriy A. Martyushev – Dr. Sci. (Technical Sciences), Assistant Professor, Department of Oil and Gas Technologies

29, Komsomolskiy av., Perm, 614990

martyushevd@inbox.ru

Мелехин

А. А.

Melekhin

A. A.

Александр Александрович Мелехин – канд. тех. наук, доцент кафедры Нефтегазовые технологии

614990, Пермь, пр-т Комсомольский, д. 29

Alexander A. Melekhin – Cand. Sci. (Technical Sciences), Assistant Professor, Department of Oil and Gas Technologies

29, Komsomolskiy av., Perm, 614990

melehin.sasha@mail.ru

ООО «ЛУКОЙЛ-Инжиниринг» «ПермНИПИнефть» в г. ПермиРоссияLLC «LUKOIL-Engineering” “PermNIPIneft” in PermRussian Federation

Пермский национальный исследовательский политехнический университетРоссияPerm National Research Polytechnic UniversityRussian Federation

2024

06062024

261109117

2024

Соромотин А.В., Мартюшев Д.А., Мелехин А.А.

Soromotin A.V., Martyushev D.A., Melekhin A.A.

Данная работа распространяется под лицензией Creative Commons Attribution 4.0.

This work is licensed under a Creative Commons Attribution 4.0 License.

https://www.geors.ru/jour/article/view/234

Актуальность разработки методики оперативной оценки призабойной зоны пласта (проницаемости призабойной зоны пласта и скин-фактора) обусловлена в первую очередь экономическими причинами, поскольку существующие подходы к ее определению, основанные на проведении гидродинамических исследований, ведут к недоборам нефти и повышению рисков необеспечения вывода скважины на режим. Современные методы работы с большими данными, например глубокое обучение искусственных нейронных сетей, позволяют осуществлять контроль за состоянием призабойной зоны пласта (ПЗП) скважин без их остановки на гидродинамические исследования, что сократит убытки у предприятий, осуществляющих добычу нефти, с одной стороны, и позволит проводить оперативный анализ для эффективного и своевременного применения технологий интенсификации, повышения нефтеотдачи пласта, с другой. В работе проанализированы существующие методы по определению призабойных характеристик пласта и подходов машинного обучения. Предложена методика для оперативной оценки состояния призабойной зоны пласта: проницаемости ПЗП и скин-фактора – с помощью обучения искусственных нейронных сетей на геологических и эксплуатационных данных и результатах интерпретации гидродинамических исследований на примере терригенных объектов нефтяных месторождений. Представлены результаты тестирования различных архитектур нейронных сетей для прогнозирования проницаемости ПЗП: количества слоев и нейронов в них с выбором наилучшей. Использованы технические приемы для предотвращения переобучения моделей. Предложена авторская методика по оценке скин-фактора скважин с помощью комплексного анализа построенных статистических моделей и моделей обучения искусственных нейронных сетей для решения задачи регрессии.

The relevance of the development of a methodology for the operational assessment of the bottomhole formation zone (the permeability of the bottom-hole formation zone and the skin factor) is primarily due to economic considerations, since existing approaches to its definition based on hydrodynamic studies lead to shortages and increased risks of failure to ensure the output of the well. In this regard, the use of modern methods of working with big data, such as deep learning of artificial neural networks, will ensure monitoring of the condition of the bottom-hole zone of the well formation without stopping them for hydrodynamic tests, which will reduce losses for oil production enterprises. It will allow for operational analysis for effective and timely application of intensification technologies, enhanced oil recovery. The authors analyzed the existing methods for determining the bottom-hole characteristics of the formation and machine learning approaches in the direction of solving this problem. The article presents a methodology for the operational assessment of the state of the bottom-hole formation zone: the permeability of the near bottomhole zone (NBHZ) and the skin factor using artificial neural network training approaches based on geological, operational data and the results of interpretation of hydrodynamic studies on the example of sandstones of oil fields in the Perm Region. A fully connected neural network was used to predict the NBHZ permeability. The article presents the results of testing various neural network architectures: the number of layers and neurons in layers with the choice of the best one. Some techniques were used to prevent over-training of models. The author’s methodology for assessing the skin factor of wells is proposed using a comprehensive analysis of the constructed statistical models and training models of artificial neural networks to solve the regression problem. In future studies, it is planned to use recurrent and convolutional neural networks to study the dynamic components of the formation of the bottom-hole formation zone and create an integrated approach to solve the problem.

терригенный коллекторпризабойная зона пластапроницаемостьскин-фактормашинное обучениенейронная сеть

sandstone reservoirbottom-hole formation zonepermeabilityskin factormachine learningneural network

Работа выполнена при поддержке Министерства науки и высшего образования Российской Федерации (проект № FSNM-2024-0005).

References1

Abdulaziz A.M., Ali M.K., Hafad O.F. (2022). Influences of Well Test Techniques and Uncertainty in Petrophysics on Well Test Results. Energies, 15(19), 7414. https://doi.org/10.3390/en15197414

Abobaker E., Elsanoose A., Khan F., Rahman M.A., Aborig A., Noah K. (2021). A New Evaluation of Skin Factor in Inclined Wells with Anisotropic Permeability. Energies, 14(17), 5585. https://doi.org/10.3390/en14175585

Alghazal M., Alshakhs M., Bouaouaja M. (2020). Technology integration to assessend-point oil saturation of the relative permeability curves. International Petroleum Technology Conference. Dhahran, Kingdom of Saudi Arabia. https://doi.org/10.2523/iptc-19614-ms

Alobaidi D.A. (2016). Permeability prediction in one of iraqi carbonate reservoir using hydraulic flow units and neural networks. Iraqi Journal of Chemical and Petroleum Engineering, 17(1), pp. 1–11. https://doi.org/10.31699/IJCPE.2016.1.1

Al-Obaidi S.H. (2016). Improve The Efficiency Of The Study Of Complex Reservoirs And Hydrocarbon Deposits-East Baghdad Field. International Journal of Scientific & Technology Research, 5(8), pp. 129–131.

Al-Obaidi S.H., Khalaf F.H. (2018). The Effects Of Hydro Confining Pressure On The Flow Properties Of Sandstone And Carbonate Rocks. Journal of Geology & Geophysics, 7(2), 327. https://doi.org/10.4172/2381-8719.1000327

Aygun A., Maulik R., Karakus A. (2023). Physics-informed neural networks for mesh deformation with exact boundary enforcement. Engineering Applications of Artificial Intelligence, 125, 106660. https://doi.org/10.1016/j.engappai.2023.106660

Bahaloo S., Mehrizadeh M., Najafi-Marghmaleki A. (2023). Review of application of artificial intelligence techniques in petroleum operations. Petroleum Research, 8(2), pp. 167–182. https://doi.org/10.1016/j.ptlrs.2022.07.002

Bennis M., Torres-Verdín C. (2019). Estimation of Dynamic Petrophysical Properties from Multiple Well Logs Using Machine Learning and Unsupervised Rock Classification. SPWLA 60th Annual Logging Symposium. The Woodlands, Texas, USA, SPWLA-2019-KKKK. https:// doi.org/10.30632/T60ALS-2019_KKKK

Bennis M., Torres-Verdín C. (2023). Automatic Multiwell Assessment of Flow-Related Petrophysical Properties of Tight Gas Sandstones Based on The Physics of Mud-Filtrate Invasion. SPE Reservoir Evaluation and Engineering, 26(3), pp. 543–564. https://doi.org/10.2118/214668-PA

Bist N., Nair A., Yadav K., Sircar A. (2023). Diverting agents in the oil and gas industry: A comprehensive analysis of their origins, types, and applications. Petroleum Research. https://doi.org/10.1016/j.ptlrs.2023.09.004

Dong S.-Q., Zhong Z.-H., Cui X.-H., Zeng L.-B., Yang X., Liu J.- J., Sun Y.-M., Hao J.-R. (2023). A deep kernel method for lithofacies identification using conventional well log. Petroleum Science, 20(3), pp. 1411–1428. https://doi.org/10.1016/j.petsci.2022.11.027

Dong W., Wang X., Wang J. (2018). A new skin factor model for partially penetrated directionally-drilled wells in anisotropic reservoirs. Journal of Petroleum Science and Engineering, 161, pp. 334–348. https:// doi.org/10.1016/j.petrol.2017.11.062

Dvoynikov M.V., Minaev Ya.D., Minibaev V.V., Kambulov E.Yu., Lamosov M.E. (2024). Technology for killing gas wells at managed pressure. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 335(1), pp. 7–18. https://doi.org/10.18799/24131830/2024/1/4315

Eriavbe F.E., Okene U.O. (2019). Machine Learning Application to Permeability Prediction Using Log & Core Measurements: A Realistic Workflow Application for Reservoir Characterization. SPE Nigeria Annual International Conference and Exhibition, Lagos, Nigeria, SPE-198874-MS. https://doi.org/10.2118/198874-MS

Galkin V.I., Martyushev D.A., Ponomareva I.N., Chernykh I.A. (2021). Developing features of the near-bottomhole zones in productive formations at fields with high gas saturation of formation oil. Journal of Mining Institute, 249, pp. 386–392. https://doi.org/10.31897/PMI.2021.3.7

Gomaa S., Emara R., Mahmoud O., El-hoshoudy A.N. (2022). New correlations to calculate vertical sweep efficiency in oil reservoirs using nonlinear multiple regression and artificial neural network. Journal of King Saud University – Engineering Sciences, 34(7), 368–375. https://doi.org/10.1016/j.jksues.2021.07.010

Gouda A., Attia A.M. (2022). Development of a new approach using an artificial neural network for estimating oil formation volume factor at bubble point pressure of Egyptian crude oil. Journal of King Saud University – Engineering Sciences, 36(1), pp. 72–80. https://doi.org/10.1016/j.jksues.2022.08.001

Hameed M.R.A., Hamd-Allah S.M. (2023). Studying the Effect of Permeability Prediction on Reservoir History Matching by Using Artificial Intelligence and Flow Zone Indicator Methods. Iraqi Geological Journal, 56(1E), pp. 9–21. https://doi.org/10.46717/igj.56.1E.2ms-2023-5-12

He Y., Liu Y., Cai H. (2022). Fine characterisation of remaining oil using timevarying numerical simulation: Experimental study. Characterisation in Model, and Application in QHD Oilfield. Offshore Technology Conference Asia. Virtual and Kuala Lumpur, Malaysia, OTC-31410-MS. https://doi.org/10.4043/31410-ms

Kantaatmadja B.P., Jiang L., Ralphie B. (2019). Hydrocarbon identification and evaluation in a bioturbated reservoir with newgeneration pulsed neutron technology. SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition. Bali, Indonesia, SPE-196364-MS. https://doi.org/10.2118/196364-ms

Khairullin M.K., Shamsiev, M.N., Gadilshina, B.R., Morozov, P. E., Abdullin, A. I., Badertdinova, E.R. (2016). Determination of the Parameters of the Hole Bottom Zone of a Vertical Well from the Results of Thermodynamic Investigations. Journal of Engineering Physics and Thermophysics, 89(6), pp. 1449–1453. https://doi.org/10.1007/s10891-016-1512-7

Kubota L., Gioria R.S. (2022). Data-driven technique estimates skin factor and average pressure during oil-flowing periods. Journal of Petroleum Science and Engineering, 219, 111061. https://doi.org/10.1016/j.petrol.2022.111061

Li D., Zhou X., Xu Y., Wan Y., Zha W. (2023). Deep learning-based analysis of the main controlling factors of different gas-fields recovery rate. Energy, 285, 128767. https://doi.org/10.1016/j.energy.2023.128767

Liu S., Fan M., Lu D. (2023). Uncertainty quantification of the convolutional neural networks on permeability estimation from micro-CT scanned sandstone and carbonate rock image. Geoenergy Science and Engineering, 230, 212160. https://doi.org/10.1016/j.geoen.2023.212160

Liu X., Li D., Yang J., Zha W., Zhou Z., Gao L., Han J. (2020). Automatic well test interpretation based on convolutional neural network for infinite reservoir. Journal of Petroleum Science and Engineering, 195, 107618. https://doi.org/10.1016/j.petrol.2020.107618

Mahmoudi M., Fattahpour V., Nouri A., Yao T., Baudet B.A., Leitch M., Fermaniuk B. (2016). New Criteria for Slotted Liner Design for Heavy Oil Thermal Production. SPE Thermal Well Integrity and Design Symposium, Banff, Alberta, Canada, SPE-182511-MS. https://doi.org/10.2118/182511-MS

Matinkia M., Hashami R., Mehrad M., Hajsaeedi M. R., Velayati A. (2023). Prediction of permeability from well logs using a new hybrid machine learning algorithm. Petroleum, 9(1), pp. 108–123. https://doi.org/10.1016/j.petlm.2022.03.003

Negara A., Jin G., Agrawal G. (2016). Enhancing Rock Property Prediction from Conventional Well Logs Using Machine Learning Technique-Case Studies of Conventional and Unconventional Reservoirs. The Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, SPE-183106-MS. https://doi.org/10.2118/183106-MS

Pei X., Liu Y., Lin Z., Fan P., Mi L., Xue L. (2024). Anisotropic dynamic permeability model for porous media. Petroleum Exploration and Development, 51(1), pp. 193-202. https://doi.org/10.1016/S1876-3804(24)60016-9

Ponomareva I.N., Martyushev D.A., Govindarajan S.K. (2022). A new approach to predict the formation pressure using multiple regression analysis: Case study from Sukharev oil field reservoir – Russia. Journal of King University – Engineering Sciences. https://doi.org/10.1016/j.jksues.2022.03.005

Rashid M., Luo M., Ashraf U., Hussain W., Ali N., Rahman N., Hussain S., Martyushev D.A., Vo Thanh H., Anees A. (2023). Reservoir Quality Prediction of Gas-Bearing Carbonate Sediments in the Qadirpur Field: Insights from Advanced Machine Learning Approaches of SOM and Cluster Analysis. Minerals, 13(1), 29. https://doi.org/10.3390/min13010029

Singh M., Makarychev G., Mustapha H., Voleti D., Akkurt R., Daghar Kh.A., Mawlod A.A., Marzouqi Kh.A., Shehab S., Maarouf A., Jundi O.E., Razouki A. (2020). Machine Learning Assisted Petrophysical Logs Quality Control, Editing and Reconstruction. The Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, SPE-202977-MS. https://doi.org/10.2118/202977-MS

Sivagnanam M., Wang J., Gates I.D. (2017). On the fluid mechanics of slotted liners in horizontal wells. Chemical Engineering Science, 164, pp. 23–33. https://doi.org/10.1016/j.ces.2017.01.070

Wang C.-C., Yang Y.-F., Han D.-L., Su M.-M., Hu R.-R. (2023). Influence of matrix physical properties on flow characteristics in dual network model. Petroleum Science, 20(4), pp. 2244–2252. https://doi.org/10.1016/j.petsci.2023.06.006

Wang S., Xiang J., Wang X., Feng Q., Yang Y., Cao X., Hou L. (2024). A deep learning based surrogate model for reservoir dynamic performance prediction. Geoenergy Science and Engineering, 233, 212516. https://doi.org/10.1016/j.geoen.2023.212516

Xie J. (2015). Slotted Liner Design Optimization for Sand Control in SAGD Wells. SPE Thermal Well Integrity and Design Symposium, Alberta, Canada, SPE-178457-MS. https://doi.org/10.2118/178457-MS

Yang Y., Horne R.N., Cai J., Yao J. (2023). Recent advances on fluid flow in porous media using digital core analysis technology. Advances in Geo-Energy Research, 9(2), pp. 71–75. https://doi.org/10.46690/ager.2023.08.01

Zakharov L.А., Martyushev D.А., Ponomareva I.N. (2022). Predicting dynamic formation pressure using artificial intelligence methods. Journal of Mining Institute, 253, pp. 23–32. https://doi.org/10.31897/PMI.2022.11

Zhou X., Wei J., Zhao J., Zhang X., Fu X., Sultanov Sh., Gayubov A., Chen Y., Wang J. (2024). Study on pore structure and permeability sensitivity of tight oil reservoir. Energy, 288, 129632. https://doi.org/10.1016/j.energy.2023.129632

The authors declare that there are no conflicts of interest present.