ANALYSIS OF CLASSIFICATION MODELS FOR RECOGNIZING PRECEDENT EVENTS IN OIL AND GAS PRODUCTION PROCESSES

A. V. Zviagintseva, I. Y. Kovalev

About the authors

A. V. Zviagintseva, I. Y. Kovalev

Звягинцева Анна Викторовна – д.т.н. доцент, профессор кафедры компьютерных технологий ФГБОУ ВО «ДонГУ», 283001, Донецк, ул. Университетская, 24. Область научных интересов: системный анализ, событийная и комплексная оценка; безопасность и управление социально - экономическими и техногенными системами; инфор мационно-аналитические системы; обработка и анализ данных. Число научных публикаций – более 150.

Ковалев Илья Юрьевич – аспирант кафедры компьютерных технологий ФГБОУ ВО «ДонГУ», 283001, Донецк, ул. Университетская, 24. Область научных интересов: машинное обучение, рекомендательные системы, нейронные сети, интеллектуальный анализ данных, прогн озирование событий. Число научных публикаций – более 3.

Download PDF

UDC: 004.891.3: 005.332.7
DOI: 10.24412/2413-7383-2025-2-37-66-78
Language: Russian

Abstract: The article provides a comparative testing of event classification models using a dataset of accidents at oil wells with natural oil and gas inflow as an example. The data were analyzed and processed, the hyperparameters of each model were adjusted, the models were trained, tested, and metrics were calculated.

Keywords: events, oil production, binary classification, machine learning.

References

1. 3W Dataset [online]. Available at: https://github.com/ricardovvargas/3w_dataset (accessed May 20, 2025). References
2. Energy Institute Statistical Review of World Energy 2024 – Energy Institute. 2024, 76 p.
3. Jenergeticheskaja strategija Rossijskoj Federacii do 2050 goda. Moscow, Ministerstvo jenergetiki Rossijskoj Federacii, 2025, 107 p.
4. Shmal' G.I. Problemy pri razrabotke trudnoizvlekaemyh zapasov nefti v Rossii i puti ih reshenija. Georesursy, no 18(4), 2016: 256 –260.
5. Kalarash R.A. Korotkova T.G. Statistika avarij na ob"ektah neftehimicheskoj i neftepererabatyvajushhej promyshlennosti. Nauchnye trudy KubGTU, no 7, 2019: 314–324.
6. Uroki, izvlechennye iz avarij. Tekst: jelektronnyj. Rostehnadzor: [sajt]. URL https://www.gosnadzor.ru/ industrial/oil/lessons/ (28.05.2025).
7. Rukovodstvo po bezopasnosti “Metodicheskie rekomendacii po klas sifikacii avarijno opasnyh proisshestvij na opasnyh proizvodstvennyh ob"ektah neftegazovogo kompleksa”. Utv. Prikazom Rostehnadzora ot 20.11.2023, no 410, 17 p.
8. Zviaginceva A.V. Guchmazova T.K. Klemenjuk V.R. Vyjavlenie vzaimosvjazi slozhnyh sobytij na primere analiza statisticheskih dannyh o chrezvychajnyh situacijah. Vestnik DonNU. Serija G: Tehnicheskie nauki, no 3, 2024: 45–54.
9. Alvarez G. Operational Risk Quantification: Mathematical Solutions for Analyzing Loss Data, 2001, 18 p.
10. Upravlenie riskami organizacij. Integrirovannaja model'. Kratkoe izlozhenie. Konceptual'nye osnovy. Proektnyj konsul'tativnyj sovet COSO, 2004, 111 p.
11. Zviaginceva A.V. Verojatnostnye metody kompleksnoj ocenki prirodno -antropogennyh sistem. Moscow, Spektr, 2016, 258 p.
12. Chernovalova M.V. Chernenskij L.L. Makarova M.M. Precedentnyj podhod dlja ocenki vlijanija molnij na sistemy ulichnogo osveshhenija s ispol'zovaniem ontologij. Programmnye produkty i sistemy, no 35(4), 2022: 729–736.
13. Mikrjukov A.A. Kuular A.V. Sovershenstvovan ie processa upravlenija incidentami na osnove precedentnogo podhoda. Otkrytoe obrazovanie. V.25, no 4, 2021: 47–54.
14. Rychka O.V. Analiz jeffektivnosti usovershenstvovannyh metodov poiska i obrabotki anomalij dlja nelinejnyh modelej s vnutrennej linejnost'ju. Problemy iskusstvennogo intellekta, no 3(18), 2020: 101 –110.
15. Krivov M.V. Aslamova E.A. Aslamova V.S. Sistema vyrabotki strategij upravlenija promyshlennoj bezopasnost'ju. Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitel'naja tehnika i informatika, no 59, 2022: 55–65.
16. Safonov V.S. Odisharija G.Je. Shvyrjaev A.A. Teorija i praktika analiza riska v gazovoj promyshlennosti. Moscow, NUMC Minprirody Rossii, 1996, 207 p. Анализ моделей классификации для распознавания прецедентных событий… З
17. David M.W. Evaluation: from precision, recal l and F-measure to ROC, informedness, markedness and correlation // International Journal of Machine Learning Technology. Vol.2, no 1, 2011: 37 –63.
18. NORSOK D-010 Well integrity in drilling and well operations. 2013. Standards Norway, 224 p.
19. GOST R 54483-2021. Neftjanaja i gazovaja promyshlennost'. Sooruzhenija neftegazopromyslovye morskie. Obshhie trebovanija. Moscow, Rossijskij institut standartizacii, 2021, 45 p.
20. GOST R 53554-2009. Poisk, razvedka i razrabotka mestorozhdenij uglevodorodnogo syr'ja. Terminy i opredelenija. Moscow, Standartinform, 2020, 19 p.
21. R.E.V. Vargas, et al. A realistic and public dataset with rare undesirable real events in oil wells // Journal of Petroleum Science and Engineering.. Vol.181, 2019, 9 p.
22. GOST R 59304-2021. Neftjanaja i gazovaja promyshlennost'. Sistemy podvodnoj dobychi. Terminy i

Issue: 2(37)'2025
Section: SYSTEM ANALYSIS, CONTROL AND INFORMATION PROCESSING, STATISTICS
How to cite: A. V. Zviagintseva, I. Y. Kovalev. ANALYSIS OF CLASSIFICATION MODELS FOR RECOGNIZING PRECEDENT EVENTS IN OIL AND GAS PRODUCTION PROCESSES // Problems of Artificial Intelligence. - 2025. - № 2 (37). - P. 66-78. - https://paijournal.guiaidn.ru/en/2025/2(37)-7.html

Back to issue 2(37)'2025