Machine learning model for predicting accidents at gas production facilities
DOI: 10.21293/1818-0442-2025-28-3-53-58
Abstract: Emergency situations lead to disruptions of workflows, regardless of how quickly these emergencies are resolved, therefore the ability to predict such situations would be extremely useful in many fields. The paper implements an approach to preprocessing data from a SCADA database using averaging and correlation analysis. A machine learning (ML) model is then trained on the preprocessed data to classify the current state of the node as an emergency precursor to simulate a real work-flow. The model achieved high accuracy score and other metrics without fine tuning and hyperparameter optimization, thus confirming the possibility of using ML models for the task.
Keywords: machine learning, data preprocessing, SCADA, fault detection, technological process, classifier
For citation:
Garipov E. T., Borovskoy I. G., Kruchinin V. V. Machine learning model for predicting accidents at gas production facilities. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2025, vol. 28, no. 3, pp. 53–58. DOI: 10.21293/1818-0442-2025-28-3-53-58
Authors and copyright holders:
- Garipov E. T. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
- Borovskoy I. G. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
- Kruchinin V. V. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
- 1. Zhakhina R.U., Kostylev K.A. [SCADA systems and their main components]. Actual scientific research in the modern world, 2020, no. 4–1 (60), pp. 62–65 (in Russ.).
- 2. Nychik T.Yu. [Methodology justification of the accident risk assessment for the shipping lock]. Vestnik gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S.O. Makarova, 2013, no. 1, pp. 15–21 (in Russ.).
- 3. Stas G.V., Shainkman L.E., Smirnova E.V. Otsenka riska vozniknoveniya avarii pri dobyche burykh uglei [Evaluating risk of arising accidents by underground mining brown coal]. Izvestiya Tula State University. Earth sciences, 2015, no. 3, pp. 31–41 (in Russ.).
- 4. Morozova T.S. [On implementation of expert statistical method in assessment of accident and failure probability for mixing and charging machines]. Gornaya promyshlennost – Russian Mining industry, 2020, no. 4, pp. 86–91 (in Russ.).
- 5. Edamenko A.S., Yastrebinskaya A.V. [Hazard analysis and accident risk assessment at petroleum product storage facilities]. Technosphere safety technologies, no. 3(101), pp. 60–73 (in Russ.).
- 6. Nemtsov V.S. [Assessment of the risk of an accident of lifting structures during the construction of the bridge]. Natural and man-made risks (physico-mathematical and applied aspects), 2023, no. 1(45), pp. 25–33 (in Russ.).
- 7. Borovskoy I.G., Shelmina E.A., Afanasyeva I.G., Matolygin A.A. [Modeling of artificial intelligence systems for early detection of emergency situations at vital facilities]. Modeling, optimization and IT, 2022, no. 10 (3), pp. 1–16 (in Russ.).
- 8. Sukhanov A.V., Akhmedzyanov D.A. Parametricheskaya diagnostika i otsenka sostoyaniya gazoturbinnyh energeticheskih ustanovok s ispolzovaniem SCADA-tekhnologii i imitatsionnogo modelirovaniya [Parametric diagnostics and assessment of the state of gas turbine power plants using SCADAtechnologies and imitation modelling]. Vestnik USATU, 2021, vol. 25, no. 4(94), pp. 83–90 (in Russ.).
- 9. Antonov O.V., Raykova E.F., Muratov R.E., [Emergency preventing system at production technological objects based on situational mathematical model]. Vestnik of Astrakhan State Technical University. Series: Management, Computer Science and Informatics, 2022, no. 2, pp. 22–32 (in Russ.).
- 10. Zubov D.V., Lebedev D.A. Diagnostika otkazov tekhnologicheskogo oborudovaniya himicheskih proizvodstv s pomoshchyu iskusstvennogo intellekta [Diagnostics of failures of technological equipment of chemical industries using artificial intelligence]. Software Systems and Computational Methods, 2024, no. 2, pp. 30–40 (in Russ.).
- 11. Al-Ammari W.A, Sleiti A.K., Rahman M.A., RezaeiGomari S., Hassan I., Hassan R. Digital twin for leak detection and fault diagnostics in gas pipelines: A systematic review, model development, and case study. Alexandria Engineering Journal, 2025, vol. 123, pp. 91–111.
- 12. Tornyeviadzi H.M., Seidu R. Leakage detection in water distribution networks via 1D CNN deep autoencoder for multivariate SCADA data. Engineering Applications of Artificial Intelligence, 2023, vol. 122, 106062.
- 13. Hussein A.M.H., Sharafiz B.A.R., Faizal B.M., Prajindra S.K., Nawal A.B.A.J. Data-driven multi-fault detection in pipelines utilizing frequency response function and artificial neural networks. Journal of Pipeline Science and Engineering, 2025, vol. 5, no. 1, 100223.
- 14. Bao J., Guangchao Y., Zheng X., Zhang J., Ji X. A Data Driven Model for Predicting Tool Health Condition in High Speed Milling of Titanium Plates Using Real-Time SCADA. Procedia CIRP, 2017, vol. 61, pp. 317–322.
- 15. Phong B.D., Barszcz T., Staszewski W.J. Anomaly detection of wind turbines based on stationarity analysis of SCADA data. Renewable Energy, 2024, vol. 232, 121076.
- 16. RandomForestClassifier – scikit-learn 1.7.1 documentation [Electronic resource]. – Available at: https://scikitlearn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html, free (Accessed: 04.09.2025).
- 17. StandardScaler – scikit-learn 1.7.1 documentation [Electronic resource]. – Available at: https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html, free (Accessed: 04.09.2025).
- 18. accuracy_score – scikit-learn 1.7.1 documentaion [Electronic resource]. – Available at: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html, free (Accessed: 04.09.2025).
Last issue
-2026-1_%D0%BA%D0%BE%D0%BF%D0%B8%D1%8F.jpg)
Editorial office address
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 701-582
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 51-21-21 / 51-43-02
Subscription for updates
