Application of artificial intelligence methods for identifying and predicting complications in the construction of oil and gas wells: problems and solutions

This paper poses and solves the problem of using artificial intelligence methods for processing large volumes of geodata from geological and technological measurement stations in order to identify and predict complications during well drilling. Digital modernization of the life cycle of wells using artificial intelligence methods, in particular, helps to improve the efficiency of drilling oil and gas wells. In the course of creating and training artificial neural networks, regularities were modeled with a given accuracy, hidden relationships between geological and geophysical, technical and technological parameters were revealed. The clustering of multidimensional data volumes from various types of sensors used to measure parameters during well drilling has been carried out. Artificial intelligence classification models have been developed to predict the operational results of the well construction process. The analysis of these issues is carried out, and the main directions for their solution are determined.
Keywords: artificial intelligence, machine learning methods, geological and technological research, neural network model, regression model, construction of oil and gas wells, identification and prediction of complications, prevention of emergency situations

The article was prepared as part of the work of the Federal Target Program «Research and Development in Priority Areas of Development of the Scientific and Technological Complex of Russia for 2014–2020» on the topic: «Development of a high performance automated system for preventing complications and emergencies during the construction of oil and gas wells based on permanent geological and technological models of fields using artificial intelligence technologies and industrial blockchain to reduce the risks of geological exploration, incl. on offshore projects «under the Agreement with the Ministry of Science and Higher Education of the Russian Federation on the allocation of a subsidy in the form of a grant dated November 22, 2019 No. 075-15-2019-1688.

References

• Abu-Abed F, Khabarov A. (2017). Classification of pre-emergency situations in the process of industrial drilling of oilfield well systems. J. Fundam. Appl. Sci., 9(2S), pp. 1171–1181.
• Abukova L.A., Dmitrievsky A.N., Eremin N.A. (2017). Digital modernization of Russian oil and gas complex. Neftyanoe Khozyaystvo = Oil Industry, 11, pp. 54–58. (In Russ.). DOI: 10.24887/0028-2448-2017-10-54-58
• Alotaibi B., Aman B., & Nefai M. (2019, March 15). Real-Time Drilling Models Monitoring Using Artificial Intelligence. Society of Petroleum Engineers. https://doi.org/10.2118/194807-MS
• Arkhipov A.I., Dmitrievsky A.N., Eremin N.A., Chernikov A.D., Borozdin S.O., Safarova E.A., Seinaroev M.R. (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(1162), pp. 63–67. (In Russ.)
• Bakanov A.B., Drozhdin V.V., Zinchenko R.E., Kuznetsov R.N. (2009). Methods of adaptation and generation of software development. Izvestiya PGPU im. V.G. Belinskogo, 13(17), pp. 66–69. (In Russ.)
• Bobb I.F. (2018). International experience of E&P software solutions development. Georesursy = Georesources, 20(3), pp. 193-196. DOI: https://doi.org/10.18599/grs.2018.3.103-196
• Chen T., Guestrin C. (2016). Xgboost: A scalable tree boosting system. Proc. 22nd ASM SIGKDD Int. Conf on Knowledge Discovery and Data Mining, pp. 785–794.
• Development of a high-performance automated system for preventing troubles and emergencies during the construction of oil and gas wells based on constantly operating geological and technological models of fields using artificial intelligence technologies and industrial block chain to reduce the risks of geological exploration, including on offshore projects. (2019). Report. Oil and Gas Research Institute of the Russian Academy of Sciences. (In Russ.)
• Diakonov A.G., Golovina A.M. (2017). Detection of anomalies in the work of mechanisms by machine learning methods. Analytics and data management in areas with intensive data use: Proc. XIX Int. Conf. DAMDID/ RCDL, pp. 469–476.
• Djamaluddin B., Prabhakar P., James, B., Muzakir A., & AlMayad H. (2019). Real-Time Drilling Operation Activity Analysis Data Modelling with Multidimensional Approach and Column-Oriented Storage. Society of Petroleum Engineers. https://doi.org/10.2118/194701-MS
• Dmitrievsky A.N., Eremin N.A., Stolyarov V.E. (2020). The role of information in the application of artificial intelligence technologies in the construction of wells for oil and gas fields. Nauchnyi zhurnal Rossiiskogo gazovogo obshchestva, 3(26), pp. 22–37. (In Russ.)
• Dmitrievsky 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. (In Russ.). DOI: https://doi.org/10.18599/grs.2020.SI.32-35
• Dmitrievsky A.N., Eremin N.A., Stolyarov V.E. (2019). Digital transformation of gas production. IOP Conference Series: Materials Science and Engineering. https://doi.org/10.1088/1757-899X/700/1/012052
• Eremin N.A. (1994). Hydrocarbon field simulation by fuzzy logic methods. Moscow: Nauka, 462 p. (In Russ.)
• Eremin N.A., Chernikov A.D., Sardanashvili O.N., Stolyarov V.E., Arkhipov A.I. (2020). Digital well-building technologies. Creation of a highperformance automated system to prevent complications and emergencies in the process of construction of oil and gas wells. Business magazine «Neftegaz. RU», 4(100), pp. 38–50. (In Russ.)
• Gurina E., Klyuchnikov N., Zaytsev A., Romanenkova E., Antipova K., Simon I., Makarov V., Koroteev D. (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.2019.106519
• Ivlev A., Eremin N. (2018). Petrobotics: robotic drilling systems. Burenie i neft, 2, pp. 8–13. (In Russ.)
• Kabanikhin S.I., Shishlenin M.A. (2018). Digital field. Georesursy = Georesources, 20(3), pp. 139–141. https://doi.org/10.18599/grs.2018.3.139-141
• Kanfar R., Shaikh O., Yousefzadeh M., Mukerji T. (2020). Real-Time Well Log Prediction from Drilling Data Using Deep Learning. arXiv: 2001.10156. DOI: 10.2523/IPTC-19693-MS
• Kaznacheev P.F., Samoilova R.V., Kjurchisky 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), pp. 188–197. DOI: 10.18288/1994-5124-2016-5-09
• Kohonen T. (1990). The self-organizing map. Proceedings of the IEEE, 78(9), pp. 1464–1480.
• Li Y., Sun R., Horne R. (2019). Deep learning for well data history analysis. SPE Annual Technical Conference and Exhibition. Society of Petroleum Engineers. https://doi.org/10.2118/196011-MS
• Lind Yu.B., Mulyukov R.A., Kabirova A.R., Murzagalin A.R. Online prediction оf troubles in drilling process. Neftyanoe Khozyaystvo = Oil Industry, 2, pp. 55–57. (In Russ.)
• Liu F.T., Tony T.K.M., Zhou Z.H. (2008). Isolation forest. Proc. Eighth IEEE Int. Conf. on Data Mining, pp. 413–422.
• Loermans T. (2017). AML (Advanced Mud Logging): First Among Equals. Georesursy = Georesources, 19(3), pp. 216–221. https://doi.org/10.18599/grs.19.3.11
• Mayani M.G., Baybolov T., Rommetveit R., Ødegaard S. I., Koryabkin V. & Lakhtionov S. (2020). Optimizing Drilling Wells and Increasing the Operation Efficiency Using Digital Twin Technology. Society of Petroleum Engineers. https://doi.org/10.2118/199566-MS
• Muslimov R.Kh. (2017). Solving the Fundamental Problems of the Russian Oil Industry is the Basis for a Large-Scale Transition to Innovative Development. Georesursy = Georesources, 19(3), pp. 151–158. https://doi.org/10.18599/grs.19.3.1
• Noshi 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-MS
• Pichugin 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.)
• Rakichinsky V.N., Sledkov V.V. (2014). Risk Management for Well Construction Technology Implementation at Lukoil. Rogtec. 10.09, pp.62–72. (In Russ.)
• Singh K., Yalamarty S.S., Kamyab M., & Cheatham C. (2019). Cloud-Based ROP Prediction and Optimization in Real Time Using Supervised Machine Learning. Unconventional Resources Technology Conference.https://doi.org/10.15530/urtec-2019-343.
• Yurchenko I.G., Kryukov A.O. (2018). Advantages and disadvantages of introducing self-learning neural networks at oil and gas industry. Problems of geology and development of mineral resources: Proc. XXII Int. Symp. Tomsk, vol. 2, pp. 835–836. (In Russ.)