Аннотация:Borozdin, S. O., Dmitrievsky, A. N., Eremin, N. A., Arkhipov, A. I., Sboev, A. G., Chashchina-Semenova, O. K., & Fitzner, L. K. (2021). Drilling Problems Forecast Based on Neural Network. Day 2 Tue, August 17, 2021. doi:10.4043/30984-msDrilling Problems Forecast Based on Neural NetworkProceedings Offshore Technology Conference 2021. Article published 9 Aug 2021 in Day 2 Tue, August 17, 2021Authors: Sergey Olegovich Borozdin, Anatoly Nikolaevich Dmitrievsky, Nikolai Alexandrovich Eremin, Alexey Igorevich Arkhipov, Alexander Georgievich Sboev, Olga Kimovna Chashchina-Semenova, Leonid Konstantinovich FitznerAbstractThis paper poses and solves the problem of using artificial intelligence methods for processing Big 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 help 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 Big data volumes from various sources and types of sensors used to measure parameters while well drilling has been carried out. Artificial intelligence classification models have been developed to predict the operational results of the well drilling. High performance computing cluster is described which is used for implementing of the model. Drilling problems forecast accuracy which has been reached with developed system may significantly reduce non-productive time spent on eliminating of stuck pipe, mud loss and oil and gas influx events.Keywords: artificial intelligence, machine learning methods, geological and technological research,neural network model, construction of oil and gas wells, identification and prediction of complications, prevention of emergency situationsConclusionBased on the data from the Volve field, research tests of the developed software were carried out on standard equipment and on a computing cluster.On standard equipment, the work was demonstrated in real time to predict the complications "Stuck" and "Mud loss". For the well 9-F-15S shows that the use of developed software allows one to obtain a prognosis of the “Mud loss” complication 7–10 minutes ahead.On the computational cluster it is shown that with a probability of more than 90% in the marked data of drilling parameters, the complications "Stuck" and "Mud loss" are found. This confirms the possibility of using developed software for predicting complications during the drilling of oil and gas wells.References1.Eva K. Halland Wenche Tjelta Johansen Fridtjof Riis CO2 storage atlas Norwegian North sea, Norwegian Petroleum Directorate, www.npd.no.2.Stolyarov V.E., Eremin N.A., Pakhomov A.L., Laptev Ya. A. Digital automated system for quality control of manufactured products // Sensors and systems. - 2020. - No. 3 (245). S. 52-60.3.Kaznacheev P.F., Samoilova R.V., Kurchiski N.V. Application artificial intelligence methods to improve the efficiency in the oil and gas and other resource industries // Economic policy. - 2016., T. 11. - No. 5.4.Arkhipov A.I., Dmitrievsky A.N., Eremin N.A., Chernikov A.D., Borozdin S.O., Safarova E.A., Seinaroev M.R. Analysis of the data quality of the geological and technological station research in the recognition of losses and gas-oil-water showings to improve the accuracy of forecasting neural network algorithms // Oil Industry. - 2020. - No. 8. - P. 63–67.Прогноз проблем при бурении на основе нейронной сети Материалы Конференции по оффшорным технологиям. Статья опубликована 9 августа 2021 года в День 2 Вт, 17 августа 2021 года Авторы: Сергей Олегович Бороздин, Анатолий Николаевич Дмитриевский, Николай Александрович Еремин, Алексей Игоревич Архипов, Александр Георгиевич Сбоев, Ольга Кимовна Чащина-Семенова, Леонид Константинович Фитцнер