Identification of Drilling Fluid Absorption Zones in Well Design by Artificial Intelligence
Abstract
When drilling wells, the presence of geological complications can lead to an increase in non-productive time. Based on the known methods of solving problems using artificial intelligence models to automate data analysis, the authors consider approaches to finding drilling fluid absorption intervals at the design stage of well construction. The results of comparative calculations using the nearest neighbor method, logistic regression, decision tree, neural network based on drilling data on the Western Dome of the Yuzhno-Orlovskoye field, which has a reef structure, are presented. The choice of the object is due to the availability of a sufficient amount of statistical data on previously drilled wells. The uniqueness of the geological structure of reef-type fields lies in the fact that when the trajectory of wells passes through the core of the carbonate massif, fewer losses occur than when drilling in plume zones. The results of testing the developed approach are presented, the advantages and disadvantages of each method are noted. It is concluded that the use of software based on machine learning algorithms can reduce the labor costs of engineers and increase the efficiency of design work.
Full Text:
PDF (Russian)References
Nikitin V.I., Dvoinikov M.V., Kupavnykh K.S., Panteleeva T.A. Application of machine learning in modeling the parameters of drilling fluid using the Herschel–Bulkley rheological model to optimize well flushing // Zapiski Gornogo Instituta. 2025. Vol. 275. Pp. 70-80. EDN OLPTNY
Nikitin, V. I., Agrelkina, M. M. Justification for the Selection of a Relative Permeability Model in the Task of Predicting Drilling Fluid Filtrate Invasion into the Formation. International Journal of Engineering, 2025; 38(10): 2312-2320. doi: 10.5829/ije.2025.38.10a.08.
Lind Yu.B., Mulyukov R.A., Kabirova A.R., Murzagalin A.R. Operational forecasting of drilling complications // “Neftyanoe Khozyaystvo”. – No. 2, 2013. – Pp. 55-57.
Lind Yu.B., Kabirova A.R., Yelkibaeva G.G., Murzagalin A.R., Mulyukov R.A. Modern Information Technologies in Well Construction Design // Exposition Oil Gas. – No. 5(30), 2013. – Pp. 34–36.
Yadrin V.V., Lind Yu.B., Galiev A.F. Application of modern information technologies for predicting losses in order to prevent them when designing well construction and to ensure effective elimination during the drilling process // Problems of Collection, Preparation and Transportation of Oil and Petroleum Products. – 2023, No. 1 (1). – Pp. 79–87.
Zhilov R. A. Intelligent Data Clustering Methods // Izvestiya of the Kabardino Balkarian Scientific Center of the Russian Academy of Sciences. – 2023. – Vol. 116, No. 6. – Pp. 152–159.
Liu D, Deng Y. Determine the Number of Unknown Targets in Open World Based on Elbow Method. – IEEE Transactions on Fuzzy Systems. – 2020. – Vol. 26, no. 5. – P. 986-995.
Cunningham P., Delany S.J. k-Nearest Neighbour Classifiers 2nd Edition (with Python examples). – arXiv:2004.04523. – 2020.
Improving the efficiency of forecasting and preventing zones of complete and catastrophic absorption of drilling mud in reef structures of the Kamsko-Kinelskaya trough system / K. A. Shipovsky, V. S. Cirkova, M. E. Koval [et al.] // Oil Industry. – 2021. – No. 12. – pp. 97-101. – DOI 10.24887/0028-2448-2021-12-97-101
Guo G., Wang H., Bell D., Bi Y., Greer K. KNN Model-Based Approach in Classification. – On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE. – 2003. – V. 2888. – P. 986-996.
Zhang S., Li X., Zong M., Zhu X., Cheng D Learning k for kNN Classification. – ACM Transactions on Intelligent Systems and Technology (TIST). – 2017. – Vol. 8, no. 3. – P. 1-19.
Nick T.G., Campbell K.M. Logistic Regression. – In: Ambrosius, W.T. (eds) Topics in Biostatistics. Methods in Molecular Biology. – 2007. – Vol. 404. – P. 273-301.
Domínguez-Almendros S., Benítez-Parejo N., Gonzalez-Ramirez A.R. Logistic regression models. – Allergologia et Immunopathologia. – 2011. – Vol. 39, no. 5. – P. 295-305.
Shapiro, L. "Komp'juternoe zrenie" / L. Shapiro, Dzh. Stokman. – Moskva: “BINOM”, 2006. – 752 s. – ISBN 5-94774-384-1.
Mathuria M. Decision Tree Analysis on J48 Algorithm for Data Mining. – International Journal of Advanced Research in Computer Science and Software Engineering. – 2013. – Vol. 3, no. 6. – P. 1114-1119.
Rashid, T. “Creating a Neural Network.” – Moscow: Computer Publishing House “Dialectics,” 2017. – 274 p.
Chen Y., Dai X., Liu M., Chen D., Yuan L., Liu Z. Dynamic ReLU. – Computer Vision – ECCV 2020. – 2020. – P. 351-367.
Naidu G., Zuva T., Sibanda E.M. A Review of Evaluation Metrics in Machine Learning Algorithms. – Lecture Notes in Networks and Systems. – 2023. – Vol. 724. – P. 15-25.
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИТ-КОНГРЕСС ВМК МГУ 2026 СНЭ
ISSN: 2307-8162