On increasing the productive time of drilling oil and gas wells using machine learning methods

Dmitrievsky, A.N.; Sboev, A.G.; Eremin, N.A.; Chernikov, A.D.; Naumov, A.V.; Gryaznov, A.V.; Moloshnikov, I.A.; Borozdin, S.O.; Safarova, E.A.

Авторы: Dmitrievsky A.N., Sboev A.G., Eremin N.A., Chernikov A.D., Naumov A.V., Gryaznov A.V., Moloshnikov I.A., Borozdin S.O., Safarova E.A.
Журнал: Георесурсы
Том: 22
Номер: 4
Год издания: 2020
Первая страница: 79
Последняя страница: 85
DOI: 10.18599/grs.2020.4.79-85
Аннотация: UDC 622.276: 681.518:622.276.7Dmitrievsky A.N., Sboev A.G., Eremin N.A., Chernikov A.D., Naumov A.V., Gryaznov A.V., Moloshnikov I.A., Borozdin S.O., Safarova E.A. (2020). On increasing the productive time of drilling oil and gas wells using machine learning methods. Georesursy = Georesources, 22(4), pp. 79–85. DOI: https://doi.org/10.18599/grs.2020.4.79-85UDC 622.276: 681.518:622.276.7Abstract. The article is devoted to the development of a hybrid method for predicting and preventing the development of troubles in the process of drilling wells based on machine learning methods and modern neural network models. Troubles during the drilling process, such as filtrate leakoff; gas, oil and water shows and sticking, lead to an increase in unproductive time, i.e. time that is not technically necessary for well construction and is caused by various violations of the production process. Several different approaches have been considered, including based on the regression model for predicting the indicator function, which reflects an approach to a developing trouble, as well as anomaly extraction models built both on basic machine learning algorithms and using the neural network model of deep learning. Showing visualized examples of the work of the developed methods on simulation and real data. Intelligent analysis of Big Geodata from geological and technological measurement stations is based on well-proven machine learning algorithms. Based on these data, a neural network model was proposed to prevent troubles and emergencies during the construction of wells. The use of this method will minimize unproductive drilling time.Keywords: machine learning, neural networks, detection of anomalies, prediction of troubles, hybrid simulation, drilling of oil and gas wells, geological and technological information, prevention of accidents and complications, artificial intelligence, automated system, neural network modelingRecommended citation: Dmitrievsky A.N., Sboev A.G., Eremin N.A., Chernikov A.D., Naumov A.V.,Gryaznov A.V., Moloshnikov I.A., Borozdin S.O., Safarova E.A. (2020). On increasing the productive time of drilling oil and gas wells using machine learning methods. Georesursy = Georesources, 22(4), pp. 79–85.DOI: https://doi.org/10.18599/grs.2020.4.79-85ConclusionWithin the framework of the system being created to predict the main types of complications in thedrilling process a number of modern hybrid methods of data mining (Data Driven methods) were developed and tested. Those methods included machine learning technologies and Data Driven neural networks, which have demonstrated their effectiveness on the available small amounts of simulation and real data of well drilling (Eremin et al., 2020a-2020e). Further work will be aimed at expanding data sets from geological and technological measurement stations, accordingly assessing the accuracy of the proposed models and their refinement. AcknowledgmentsThe article was prepared based on the results of work carried out within the framework of the Program of State Academies of Sciences for 2013– 2020. Section 9 «Earth Sciences»; direction of fundamental research: 132 «Integrated development and conservation of the Earth’s interior, innovative processes for the development of mineral deposits and deep processing of mineral raw materials», on the topic of the state assignment «Fundamental basis of innovative technologies in the oil and gas industry», No. АААА-А16-116031750016-3; No. 0139-2019-0009 in Parus and No. АААА-А19-119013190038-2 in ROSRID.ReferencesArkhipov A.I., Dmitrievsky A.N., Eremin N.A. et al. (2020). Data quality analysis of the station of geological and technological researches in recognizing losses and kicks to improve the prediction accuracy of neural network algorithms. Neftyanoe khozyaystvo = Oil industry, 8, pp. 63–67.DOI: 10.24887/0028-2448-2020-8-63-67 Borozdin, S., Dmitrievsky, A., Eremin, N., Arkhipov, A., Sboev, A., Chashchina-Semenova, O., Fitzner L., Safarova, E. (2020). Drilling Problems Forecast System Based on Neural Network. Society of Petroleum Engineers. https://doi.org/10.2118/202546-MSChen T., Guestrin C. (2016). Xgboost: A scalable tree boosting system. Proc. 22nd ASM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining. ACM, pp. 785–94.https://doi.org/10.1145/2939672.2939785Diakonov A.G., Golovina A.M. (2017). Detection of anomalies in the work of mechanisms by machine learning methods. Proc. XIX Int. Conf.: Analytics and data management in areas with intensive data use. Moscow, pp. 469–476. (In Russ.)Dmitrievsky A.N., Eremin N.A., Filippova D.S.et al. (2020). Qualitative Analysis of Time Series GeoData to Prevent Complications and Emergencies During Drilling of Oil and Gas Wells. Socar Proceedings, 3, pp. 31–37. http://dx.doi.org/10.5510/OGP20200300442Dmitrievsky A.N., Eremin N.A. Filippova D.S., Safarova E.A. (2020). Digital oil and gas complex of Russia. Georesursy = Georesources, Special issue, pp. 32–35. DOI:https://doi.org/10.18599/grs.2020.SI.32-35Eremin N.A., Stolyarov V.E. (2020). On the digitalization of gas production processes at the late stages of field development. Socar Proceedings, 1, pp. 59–69. (In Russ.). DOI: 10.5510/ogp20200100424Eremin N.A., Vodopiyan A.O., Duplyakin V.O., Chernikov A.D., Kosmos S.A. (2020a). Software component «Oil and Gas Blockchain». Software Registration Certificate RU 2020614626. Application form 2020613699.Eremin N.A., Dmitrievsky A.N., Chashchina-Semenova O.K., Fitsner L.K., Chernikov A.D. (2020b). Software component «Adaptation of generalized neural network models for predicting complications and emergencies to geophysical parameters when drilling a specific well». Software Registration Certificate RU 2020660890. Application form 2020660179.Eremin N.A., Dmitrievsky A.N., Chashchina-Semenova O.K., Fitsner L.K., Chernikov A.D. (2020c). Software component «Orchestration - integration of modules of the system for predicting complications and emergencies during drilling and well construction». Software Registration Certificate RU 2020660891. Application form 2020660181.Eremin N.A., Dmitrievsky A.N., Chashchina-Semenova O. K., Fitsner L.K., Chernikov A.D. (2020d). Software component «Neural network calculations - construction of models for forecasting complications and emergencies during drilling and well construction». Software Registration Certificate RU 2020660892. Application form 2020660182.Eremin N.A., Dmitrievsky A.N., Chashchina-Semenova O.K., Fitsner L.K., Chernikov A.D. (2020e). Software component «Indication of forecast of complications and emergencies during drilling and well construction» (SC «Indication»). Software Registration Certificate RU 2020661356. Application form 2020660450.Gurina E. et al. (2020). Application of machine learning to accidents detection at directional drilling. Journal of Petroleum Science and Engineering, 184, 106519. https://doi.org/10.1016/j.petrol.2019.106519Kanfar R. et al. (2020). Real-Time Well Log Prediction From Drilling Data Using Deep Learning. arXiv preprint arXiv: 2001.10156. https://doi.org/10.2523/IPTC-19693-MSKaznacheev P.F., Samoilova R.V., Kjurchinski N.V. (2016). Improving Efficiency of the Oil and Gas Sector and Other Extractive Industries by Applying Methods of Artificial Intelligence. Ekonomicheskaya Politika = Economic Policy, 11(5). (In Russ.)Kodirov S.S., Shestakov A.L. (2019). The development of an artificial neural network for predicting stuck pipe columns of drill pipes. Vestnik Yuzhno-Ural’skogo gosudarstvennogo universiteta. Seriya: Komp’yuternye tekhnologii, upravlenie, radioelektronika = Bulletin of the South Ural State University. Series Computer Technology, Aotimatic Control, Radio Electronics, 19(3). (In Russ.)Kohonen T. (1990). The self-organizing map. Proc. IEEE, 78(9), pp. 1464–1480. https://doi.org/10.1109/5.58325Li Y. et al. (2019). Deep learning for well data history analysis. Society of Petroleum Engineers. https://doi.org/10.2118/196011-MSLiu F.T., Tony T.K.M., Zhou Z.H. (2008). Isolation forest. Proc. 8th IEEE Int. Conf. on Data Mining, pp. 413–422. https://doi.org/10.1109/ICDM.2008.17Noshi C.I., Schubert J.J. (2018). The Role of Machine Learning in Drilling Operations. A Review. Society of Petroleum Engineers. https://doi.org/10.2118/191823-18ERM-MSPichugin O.N., Prokofiev Y.Z., Alexandrov D.M. (2013). Decision Trees as an effective method for analysis and forecasting. Neftepromyslovoe delo, 11, pp. 69–75. (In Russ.)
Добавил в систему: Еремин Николай Александрович

	ИСТИНА	Войти в систему Регистрация
	Интеллектуальная Система Тематического Исследования НАукометрических данных
	Главная Поиск Статистика О проекте Помощь

ИСТИНА

Интеллектуальная Система Тематического Исследования НАукометрических данных

On increasing the productive time of drilling oil and gas wells using machine learning methodsстатья

Прикрепленные файлы