Neural network model of the wells' drilling speed and modes predicting in complex reservoirs
https://doi.org/10.31660/0445-0108-2021-1-55-76
Abstract
The article considers the problem connected with the study of well drilling rates in complex reservoirs. Its solution is presented in the form of a neural network model that takes into account the structural, geomechanical and technological features of the «rock mass — well» system.
The possibility of predicting the well drilling method with different strength and structural-lithological characteristics of the massif, based on neural network modeling, is presented.
The purpose of this study is to obtain mathematical models for analysis of the probabilistic and statistical patterns of well drilling processes in conditions of uncertainty.
The scientific novelty of the work performed is the qualitative and quantitative assessment of the mutual influence of geological and technological factors on the well drilling rate; search for optimal well drilling modes in complex reservoirs on the basis of mathematical modeling.
About the Author
Yu. E. Katanov
Industrial University of Tyumen
Russian Federation
Russian Federation
Yury E. Katanov, Candidate of Geology and Mineralogy, Associate Professor at the Department of Applied Geophysics, Leading Researcher at Well Workover Technology and Production Stimulation Laboratory
Tyumen
References
1. Basarygin, Yu. M., Bulatov, A. I., & Proselkov, Yu. M. (2001). Tekhnologiya bureniya neftyanykh i gazovykh skvazhin. Moscow, Nedra Publ., 679 p. (In Russian).
2. Bulatov, A. I., Proselkov, Yu. M., & Shamanov, S. A. (2003). Tekhnika i tekhnologiya bureniya neftyanykh i gazovykh skvazhin. Moscow, Nedra Publ., 1007 p. (In Russian).
3. Bаldenko, D. F., Baldenko, F. D., & Gnoevykh, A. N. (1999). Positive Displacement Downhole Motors. Moscow, Nedra Publ., 375 p. (In Russian).
4. Katanov, Yu. E. (2014). Mechanisms and principals of modeling of rocks deformational-spatial instability. Construction of Oil and Gas Wells on Land and Sea, (11), pp. 19-23. (In Russian).
5. Katanov, Yu. E., & Grigoriev, N. V. (2014). Substantiation of the parameters of rocks (heterogeneity environments) when modeling. International research journal, (8-1(27)), pp. 18-21 (In Russian).
6. Ivashchenko, V. V., & Katanov, Yu. E. (2016). Prognozirovanie produktivnykh kharakteristik porod-kollektorov v usloviyakh neopredelennosti. Novaya nauka: Problemy i perspektivy, (121-3), pp. 31-33.
7. Katanov, Yu. E. (2012). Creation of the linear simulator for prediction of the technological process. Higher Educational Institutions News. Neft' I Gas, (1), pp. 112-116. (In Russian).
8. Petukhov, A. V. (2002). Teoriya i metodologiya izucheniya strukturnoprostranstvennoy zonal'nosti treshchinnykh kollektorov nefti i gaza. Ukhta, Ukhta State Technical University Publ., 276 p. (In Russian).
9. Yаgafarov, A. K., Kleshchenko, I. I., Popov, I. P., Vaganov, Yu. V., Katanov, Yu. E., Popova, Zh. S., & Savina, M. E. (2017). Tekhnologii povysheniya produktivnosti skvazhin i vozdeystviya na zalezhi uglevodorodov na mestorozhdeniyakh Zapadnoy Sibiri. Tyumen, Industrial University of Tyumen Publ., 204 p. (In Russian).
10. Katanov, Yu. E. (2019). Osnovy teorii upravleniya. Tyumen, Industrial University of Tyumen Publ., 170 p. (In Russian).
11. Katanov, Yu. E., Aleksandrov, V. M., & Yagafarov, A. K. (2020). Geological and mathematical analogy of reservoir and polymer structures. TEST Engineering & Management, pp. 6977-6991. ((n English).
12. Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge, MA, USA, 1070 p. (In English).
13. Morin, F., & Bengio, Y. (2005). Hierarchical Probabilistic Neural Network Language Model. Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, pp. 246-252. (In English).
14. Nowlan, S. J., & Hinton, G. E. (1992). Simplifying Neural Networks by Soft Weight-Sharing. Neural Computation, 4(4), pp. 473-493. (In English). DOI: 10.1162/neco.1992.4.4.473
15. Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014). Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1717-1724. (In English).
16. Saxe, A. M., McClelland, J. L., & Ganguli, S. (2013). Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. (In English). Available at: https://arxiv.org/abs/1312.6120.
17. Katanov, Yu. E. (2020). Komp'yuternye tekhnologii. Chast' 1. Geologiya, geofizika, gidrogeologiya. Tyumen, Industrial University of Tyumen Publ., 180 p. (In English).
18. Katanov, Yu. E. (2012). Razrabotka proekta informatsionnogo obespecheniya "INTELLPRO". Novye informatsionnye tekhnologii v neftegazovoy otrasli i obrazovanii: materialy V Vserossiyskoy nauchno-tekhnicheskoy konferentsii s mezhdunarodnym uchastiem, November, 1-2. Tyumen, Industrial University of Tyumen Publ., pp. 20-25. (In Russian).
19. Men'shikov, A. I. (2019). Issledovanie optimal'nykh rezhimov raboty sharoshechnykh dolot v usloviyakh neopredelennosti. Nauka v sovremennom obshchestve: zakonomernosti i tendentsii razvitiya: sbornik trudov Mezhdunarodnoy nauchnoprakticheskoy konferentsii, (Sterlitamak, April, 4). Ufa, Omega Sayns LLC Publ., pp. 48-54. (In Russian).
20. Men'shikov, A. I. (2019). Klasterizatsii parametrov bureniya. Tekhnologicheskoe razvitie nauki: tendentsii, problemy i perspektivy: sbornik statey po itogam Mezhdunarodnoy nauchno-prakticheskoy konferentsii (Sterlitamak, June, 8). Ufa, Aeterna LLC, pp. 30-35. (In Russian).
21. Men'shikov, A. I. (2020). Issledovanie rezhimov raboty sharoshechnykh dolot na osnove derev'ev resheniy. Informatsionnye tekhnologii kak osnova progressivnykh nauchnykh issledovaniy: sbornik trudov Mezhdunarodnoy nauchno-prakticheskoy konferentsii (Perm, May, 25), Ufa, Aeterna LLC, pp. 78-83. (In Russian).
22. Men'shikov, A. I. (2020). Prognozirovanie mekhanicheskoy skorosti bureniya massiva sharoshechnymi dolotami na osnove neyrosetevogo modelirovaniya. Informatsionnye tekhnologii kak osnova progressivnykh nauchnykh issledovaniy: sbornik trudov Mezhdunarodnoy nauchno-prakticheskoy konferentsii (Perm, May, 25), Ufa, Aeterna LLC Publ., pp. 83-87. (In Russian).
Review
For citations:
Katanov Yu.E. Neural network model of the wells' drilling speed and modes predicting in complex reservoirs. Oil and Gas Studies. 2021;(1):55-76. (In Russ.) https://doi.org/10.31660/0445-0108-2021-1-55-76
Views:
485
Email this article 
Post a Comment 