Z.F. Ismagilova, M.A. Priestov, R.I. Shaikhetdinov
DOI: https://doi.org/10.25689/NP.2023.4.282-298
Abstract
The paper discusses a technique for replacing part of an integrated oil and gas field model with a machine learning model. This will reduce the calculation time of this model and increase its response. Four most suitable algorithms were identified, test training and prediction of calculation parameters of one of the components of the integrated model were performed. As an example, we consider an integrated model of an oil and gas field, built on the basis of Petroleum Experts software. Synthetic models and models of real deposits were created and prepared. The degree of influence of operational parameters on the calculation of the integrated model is assessed. Methods have been developed to take into account the influence of these parameters without building an integrated model. The possibility of using machine learning to replace components of an integrated model is assessed. The machine learning algorithm is written in the Python programming language using the scikit-learn library. The integration of the machine learning model with the integrated model was carried out in the Petroleum Experts Resolve software product.
References
DOI 10.33285/0132-2222-2019-6(551)-31-39. EDN CRBNXZ. (in Russian)
2. Solovyev I.G., Govorkov D.A., Kushmanov P.V., Fomin V.V. Intelligent oil and gas producing systems. Avtomatizaciya, Telemekhanizaciya i Svyaz v Neftyanoj Promyshlennosti [Automation, Telemetry and Communication in Oi Industry]. 2016, No. 4, pp. 18-23. EDN TORMZQ. (in Russian)
3. Chernikov A.D., Eremin N.A., Stolyarov V.E. Application of artificial intelligence methods for identifying and predicting complications in the construction of oil and gas wells: problems and solutions. Georesursy [Georesources]. 2020, Vol.22, No. 3, pp. 87-96. DOI 10.18599/grs.2020.3.87-96. EDN ORNYBD. (in Russian)
4. Dmitrievsky A.N., Eremin N.A., Stolyarov V.E. Role of information in application of artificial intelligence technologies in construction of wells for oil and gas fields. Nauchnyj Zhurnal Rossijskogo Gazovogo Obshchestva [Scientific Journal of Russian Gas Society]. 2020, No. 3(26), pp. 6-21. EDN HJUUIG. (in Russian)
5. Anufriev A.A., Shatalov A.N., Mingazova A.Z. Opyt ekspluatacii i vybor optimalnogo varianta raboty ustanovki pererabotki gaza Irgizskogo mestorozhdeniya [Operating experience and optimization of gas processing facility in Irgizsky field]. TatNIPIneft’s collection of research papers, Vol.84. Moscow, Neftyanoye Khozyaistvo Publ., 2016, pp. 208-214. EDN XSIUZF. (in Russian)
6. Anufriev A.A., Shatalov A.N., Morunova D.N., Mingazova A.Z. Varianty uvelicheniya stepeni otbora uglevodorodnyh komponentov ot potenciala na UPG "Irgizskaya" [Options for increasing hydrocarbon components recovery at Irgizskaya gas processing facility]. TatNIPIneft’s collection of research papers, Vol.85. Naberezhnye Chelny, Ekspoziciya Neft Gaz, 2017, pp. 356-362. EDN XQLMHB. (in Russian)
7. Zhao Xianzheng, Wang Hongyu, Liu Jichao, Lai Jishun Research and Contemplation on How to Build Old Oilfields into Digital Intelligent Ones – Take Dagang Oilfield for Example[J]. Oil Forum, 2021, 40 (5): 1–8. DOI: 10.3969/j.issn.1002-302x.2021.05.001.
8. Sorokin V.S., Gudoshnikov A.S., Nyunyaykin D.V., Kochenkov A.A., Sethuraman P., Barysheva S., Lipanin D.S., Mokrev A.A., Vukolov S.A., Ardalin A.A. Production Optimizer Pilot for the Large Artificially-Lifted and Mature Samotlor Oil Field. Paper presented at the SPE Russian Petroleum Technology Conference, Virtual, October 2021. doi: https://doi.org/10.2118/206517-MS. (in Russian)
9. Menad Nait Amar, Mohammed Abdelfetah Ghriga, Hocine Ouaer, Mohamed El Amine Ben Seghier, Binh Thai Pham, Pål Østebø Andersen, Modeling viscosity of CO2 at high temperature and pressure conditions, Journal of Natural Gas Science and Engineering, Volume 77, 2020,
ISSN 1875-5100, https://doi.org/10.1016/j.jngse.2020.103271.
10. El-Banbi, Ahmed & Elshreef, Khaled & Sayyouh, Mohamed. (2006). New Modified Black-Oil PVT Correlations for Gas Condensate and Volatile Oil Fluids. 10.2118/102240-MS.
11. Elgibaly, Ahmed & Ghareeb, Mohamed & Kamel, Said & El-Bassiouny, Mohamed. (2021). Prediction of gas-lift performance using neural network analysis. AIMS Energy. 9. 355-378. 10.3934/energy.2021019.
12. Jianwei Gu, Wei Liu, Kai Zhang, Liang Zhai, Yigen Zhang, Fuzhen Chen, Reservoir production optimization based on surrograte model and differential evolution algorithm, Journal of Petroleum Science and Engineering, Volume 205, 2021, ISSN 0920-4105, https://doi.org/10.1016/j.petrol.2021.108879.
13. Mai-Cao, L. and Truong-Khac, H. 2022. A Comparative Study on Different Machine Learning Algorithms for Petroleum Production Forecasting: DOI: 10.14800/IOGR.1205. Improved Oil and Gas Recovery. 6, (Jul. 2022).
14. Ojedapo, Babawale, Ikiensikimama, Sunday Sunday, and Virtue Urunwo Wachikwu-Elechi. "Petroleum Production Forecasting Using Machine Learning Algorithms." Paper presented at the SPE Nigeria Annual International Conference and Exhibition, Lagos, Nigeria, August 2022. doi: https://doi.org/10.2118/212018-MS.
15. Cifrovye instrumenty povysheniya ekonomicheskoi effektivnosti razrabotki mestorozhdenij. [Digital tools to improve economic efficiency of field development]. Available at: https://magazine.neftegaz.ru/articles/tsifrovizatsiya/784611-povyshenie-ekonomicheskoi-effektivnosti-razrabotki-neftegazovykh-mestorozhdenii-na-osnove-vnedreniya/ (in Russian)
Authors
Z.F. Ismagilova, Candidate of Technical Sciences, Associate Professor of the Department of Transport and Storage of Oil and Gas, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: iiii.iskandar@inbox.ru
M.A. Pristov, Master's student of the Department of Transport and Storage of Oil and Gas, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: pristov.maxim@mail.ru
R.I. Shaikhetdinov, Master's student of the Department of Transport and Storage of Oil and Gas, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: radikshaihetdinov@yandex.ru
For citation:
Z.F. Ismagilova, M.A. Priestov, R.I. Shaikhetdinov Primeneniye algoritmov mashinnogo obucheniya dlya zameny komponentov integrirovannoy modeli neftegazovogo mestorozhdeniya [Application of machine learning algorithms to replace components of the integrated oil and gas field model]. Neftyanaya Provintsiya, No. 4(36), 2023. pp. 282-298. DOI https://doi.org/10.25689/NP.2023.4.282-298. EDN VKLNRN (in Russian)