Digital modernization of oil and gas production is a powerful tool for increasing the efficiency of field development and an innovative driver for the development of the oil and gas industry. Leading oil and gas companies in Russia are transitioning to digital technologies for drilling and production based on the use of machine learning methods and neural network models. An oil and gas well is the main technological object and structure that determines the efficiency of hydrocarbon production at all stages of the field life cycle. The objects of research were complications and emergencies during the construction of oil and gas wells. The purpose of the work is to increase the efficiency of the construction process of oil and gas wells based on the creation of a high-performance automated system for preventing complications and emergencies. This article briefly describes the created automated system for preventing emergency situations during well construction using artificial intelligence technologies. The structure of the automated system and the composition of the main software components are given. The efficiency of the automated system is based on providing the calculation model with a mechanism for a continuous system of transmission, collection, distribution, storage and validation of large volumes of geological and geophysical data (Big GeoData) with elements of blockchain technology. The main advantage of using neural network modeling to solve problems of identifying and predicting complications during the construction of oil and gas wells is to reveal hidden patterns between geological and geophysical, technical and technological parameters. The system has the ability to scale and integrate into any existing oil and gas control and monitoring systems.
Referencies
1. Dmitrievskiy A.N., Eremin N.A., Safarova E.A. et al., Qualitative analysis of time series geodata to prevent complications and emergencies during drilling of oil and gas wells (In Russ.), Nauchnye trudy NIPI Neftegaz GNKAR = SOCAR Proceedings, 2020, no. 3, pp. 31–37, doi: 10.5510/ogp20200300442
2. Kaznacheev P.F., Samoylova R.V., Kurchiski N.V., Application of artificial intelligence methods to improve efficiency in the oil and gas and other raw materials industries (In Russ.), Ekonomicheskaya politika = Economic policy, 2016, V. 11, no. 5, pp. 188–197.
3. Dmitrievskiy A.N., Sboev A.G., Eremin N.A. et al., On increasing the productive time of drilling oil and gas wells using machine learning methods (In Russ.), Georesursy = Georesources, 2020, V. 22, no. 4, pp. 79–85, DOI: https://doi.org/10.18599/grs.2020.4.79-85.
4. Chernikov A.D., Eremin N.A., Stolyarov V.E. et al., Application of artificial intelligence methods for identifying and predicting complications in the construction of oil and gas wells: Problems and solutions (In Russ.), Georesursy = Georesources, 2020, V. 22, no. 3, pp. 87–96, DOI: https://doi.org/10.18599/grs.2020.3.87-96
5. D'yakonov A.G., Golovina A.M., Vyyavlenie anomaliy v rabote mekhanizmov metodami mashinnogo obucheniya (Anomaly detection in mechanisms using machine learning), Proceedings of XIX International conference “Analitika i upravlenie dannymi v oblastyakh s intensivnym ispol'zovaniem dannykh” (Data Analytics and Management in Data Intensive Domains (DAMDID)), Moscow, 10–13th of October 2017, pp. 469–476.
6. Liu F.T., Tony T.K.M., Zhou Z.H., Isolation forest, Proceedings of the 2008 Eighth IEEE Int. Conf. on Data Mining, 2008, pp. 413–422.
7. Gurina E. et al., Application of machine learning to accidents detection at directional drilling, Journal of Petroleum Science and Engineering, 2020, V. 184, DOI:10.1016/j.petrol.2019.106519.
8. Chen T., Guestrin C., Xgboost: A scalable tree boosting system, Proceedings of the 22nd ASM SIGKDD international conference on knowledge discovery and data mining, ACM, 2016, pp. 785–794.
9. Kodirov Sh.Sh., Shestakov A.L., Development of artificial neural network for predicting drill pipe sticking (In Russ.), Vestnik Yuzhno-Ural'skogo gosudarstvennogo universiteta. Seriya. Komp'yuternye tekhnologii, upravlenie, radioelektronika, 2019, V. 19, no. 3, pp. 20-32.
10. Utility model patent application no. 2020129673/03 (053361), Avtomatizirovannaya sistema vyyavleniya i prognozirovaniya oslozhneniy v protsesse stroitel'stva neftyanykh i gazovykh skvazhin (Automated system for identifying and predicting complications during the construction of oil and gas wells), Inventors: Dmitrievskiy A.N., Eremin N.A., Chashchina-Semenova O.K., Fitsner L.K., Chernikov A.D.
11. Utility model patent application no. 2020129671/03 (053358), Avtomatizirovannaya sistema vyyavleniya i prognozirovaniya oslozhneniy v protsesse stroitel'stva neftyanykh i gazovykh skvazhin (Automated system for identifying and predicting complications during the construction of oil and gas wells), Inventors: Dmitrievskiy A.N., Eremin N.A., Chashchina-Semenova O.K., Fitsner L.K., Chernikov A.D.
12. Borozdin S.O., Dmitrievskiy A.N., Eremin N.A. et al., Drilling problems forecast system based on neural network (In Russ.), SPE-202546-RU, 2020, doi:10.2118/202546-RU
13. Arkhipov A.I., Dmitrievskiy A.N., Eremin N.A. et al., 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 (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2020, no. 8, pp. 63–67, DOI: 10.24887/0028-2448-2020-8-63-67
14. Noshi C.I., Schubert J.J., The role of machine learning in drilling operations. A review, SPE-191823-18ERM-MS, 2018, DOI:10.2118/191823-18ERM-MS.
15. Kanfar R. et al., Real-time well log prediction from drilling data using deep learning, arXiv preprint arXiv:2001.10156, 2020.
16. Yuanjun Li et al., Deep learning for well data history analysis, SPE-196011-MS, 2019, https://doi.org/10.2118/196011-MS
