In the oil and gas sector, a lot of attention is paid to the issue of improving the quality of data because poor quality can distort the presentation of the situation and eventually cause making the wrong decision. Oil production monitoring and preventive maintenance involve the collection of data from a variety of sensors that need to be correctly processed and “packaged”. Therefore, particular emphasis is given to improving the quality of the generated data in oil and gas well model fixations. Fixing oil and gas well models is the process of collecting, analyzing, and storing information about well operation parameters such as fluid, gas and oil flow rates, pressure, temperature, fluid composition, and other parameters used to optimize production processes and improve well performance. The presence of gaps in the formation of well models can significantly reduce the quality of these models, which can lead to an incomplete representation of the overall picture of well operation and decrease the accuracy of predicting its productivity. The article proposes an intelligent method of completing missing values for generating data in fixations of oil and gas well models to solve this problem. The method has been successfully tested at the oil and gas company Gazprom Neft PJSC using the data on the fluid flow rate of the wells in the Vyngapurovskoye field.
1. Nurgalieva Z.D., Latypova V.A. Oil and gas well repair analysis technique based on data mining in management. Modeling, Optimization and Information Technology. 2022;10(2). Available from: https://moitvivt.ru/ru/journal/pdf?id=1186 DOI: 10.26102/2310-6018/2022.37.2.017 (In Russ.).
2. Khafizova A.U., Latypova V.A. Evaluation of the efficiency of oil and gas field development using expert methods. Modeling, Optimization and Information Technology. 2022;10(2). Available from: https://moitvivt.ru/ru/journal/pdf?id=1183 DOI: 10.26102/2310-6018/2022.37.2.018 (In Russ.).
3. Malyshev A.S., Pashali A.A., Zdol'nik S.E., Volkov M.G. Remote monitoring of mechanized well stock at OJSC Rosneft Oil Company. Nauchno-tehnicheskij vestnik OJSC “NK Rosneft'”. 2009;1:23–28.
4. Zhil'cov V.V., Dudarev A.V., Shitov G. V., Chuvikova V. V., Solutions and development of intelligent technology for monitoring and managing mechanized well stock. Neftjanoe hozjajstvo = Oil Industry Journal. 2006;10:128–130.
5. Zhil'cov V.V., Fedotov A.V Information technologies in the design of "smart" wells. Prikladnaja informatika. Energetika i racional'noe prirodopol'zovanie = Journal of Applied Informatics. 2013;48(6):15–23.
6. Bahitova R.H., Sultanov B. R. An approach to spatial-panel analysis of oil field data. Innovacii i investicii. 2020;6:287–290.
7. Zhurbich N.I. Preparation of initial data for in-depth analysis of the oil and gas field. Informacionnye tehnologii v nauke, upravlenii, social'noj sfere i medicine. 2019;13–19.
8. Qin J., Chen L., Liu Y., Liu C., Feng C. and Chen B. A machine learning methodology for diagnosing chronic kidney disease. IEEE. 2020;8:4–7.
9. Pocykajlo A.A. Using the method of k-nearest neighbors in the recognition of grayscale images. Izvestiya YuFU. Tekhnicheskie nauki = Izvestija JuFU. Engineering Sciences. 2011;118(5):258–260.
10. Galeev J.E. Cluster analysis of integrated corporate structures. Innovacii i investicii. 2023;2:139–142.
11. Zliobaite I., Hollmen J. Optimizing regression models for data streams with missing values. Machine Learning. 2014;99(1):47–73, DOI: 10.1007/s10994-014-5450-3.
12. Sharifyanov N., Latypova V. A method of filling missing values in data using data mining. 2023 IX International Conference on Information Technology and Nanotechnology (ITNT). 2023;1–5. DOI: 10.1109/ITNT57377.2023.10139280.
Shariyanov Niyaz Vakilevich
Ufa University of Science and Technology
Ufa, The Russian Federation
Latypova Viktoriya Aleksandrovna
Candidate of Technical Sciences
ORCID |
Ufa University of Science and Technology
Ufa, The Russian Federation
