On analysing time series of accidents and incidents at hazardous production facilities
https://doi.org/10.21683/1729-2646-2024-24-4-12-19
Abstract
Safe operation of any complex distributed systems is largely defined by the quality of the event analysis and prediction tools. Aside from the external hazards, the so-called hazardous production facilities (HPFs) pose significant threats. Accidents at such facilities are a subject of constant analysis and concern of operating organisations. At the same time, the accident statistics accumulated over the period of operation of such facilities are often heterogeneous. Accidents and incidents at HPFs occur at different times, against different forecast backgrounds, which complicates the construction and verification of digital models of such facilities. This paper proposes an algorithm for preprocessing time series of observations to extract data that can be subsequently used to build and train predictive models with the required accuracy. The proposed approach can be implemented by means of the R language, that in many respects has become a standard for statistical calculations.
About the Authors
A. V. Bochkov
JSC NIIAS
Russian Federation
Russian Federation
Alexander V. Bochkov, Doctor of Engineering, Academic Secretary,
27, bldg 1, Nizhegorodskaya str., Moscow, 109029.
M. A. Kirkin
PJSC Gazprom
Russian Federation
Russian Federation
Maksim A. Kirkin, Chief Expert of Department (V.I. Dontsov),
156A, Moskovsky pr-t, Saint Petersburg, 196105.
References
1. Bochkov A.V. [Problems of hazard estimation and risk management of critical infrastructure facilities of the Gazprom Group: an analytical review]. Vesti gazovoy Nauki 2018;2(34):51-87. (in Russ.)
2. Bochkov A.V. Safonov V.S. Special analysis and assessment of risk indicators for rare events in regard to dangerous industrial facilities. Vesti Gazovoy Nauki 2020;1(42):84-95. (in Russ.)
3. Bochkov A.V. [Using hierarchy analysis for categorising critical facilities in terms of the cumulative damage and the risk of illegal actions]. Issues of Risk Analysis 2008:5(4):6-13. (in Russ.)
4. Pecherkin A.S., Grazhdankin A.I., Razumnyak N.L. Trends in the Dynamics of Background Indicators of Accident Hazards at Hazardous Production Facilities. Occupational safety in industry 2022;11:14-19. DOI: 10.24000/0409-2961-2022-11-14-19. (in Russ.)
5. Guo S., Wang Z., Cui K. et al. Analysis of a hazardous factory explosion accident. SHS web of conferences 2023;166:01053. DOI: 10.1051/shsconf/202316601053.
6. Cadei L., Rossi G., Lancia L. et al. Hazardous Events Prevention and Management Through an Integrated Machine Learning and Big Data Analytics Framework. SPE Conference at Oman Petroleum & Energy Show. Muscat (Oman); March 2022. DOI: 10.2118/200110-ms.
7. Nemchinov D.V., Seliverstova A.N., Nemchinova A.L. Emergency risk management at hazardous production facilities (catalytic reforming unit). Vestnik ASTU. Series: Management, computer science and informatics 2022;3:2229. DOI: 10.24143/2072-9502-2022-3-22-29. (in Russ.)
8. Basu T., Menzer O., Ward J. et al. A Novel Implementation of Siamese Type Neural Networks in Predicting Rare Fluctuations in Financial Time Series. Risks 2022;10(2):39. DOI: 10.3390/risks10020039.
9. Ahmadzadeh A., Aydin B., Kempton D.J. et al. RareEvent Time Series Prediction: A Case Study of Solar Flare Forecasting. 18th IEEE International Conference On Machine Learning And Applications (ICMLA); 2019. DOI: 10.1109/ICMLA.2019.00293.
10. Zhuravlev Yu.I., Senko O.V., Bondarenko N.N. et al. A Method for Predicting Rare Events by Multidimensional Time Series with the Use of Collective Methods. Pattern Recognition and Image Analysis 2019;29:763-768. DOI: 10.1134/S1054661819040217.
11. Leitgöb H. Analysis of rare events. In: SAGE Research Methods Foundations. SAGE Publications Ltd.; 2020. DOI: 10.4135/9781526421036863804.
12. Korablev Yu.A., Golovanova P.S., Kostritsa T.A. Capacity Method of Rare Events Analysis in the Area of Services. Economics of Contemporary Russia 2020;(3):132-142. (in Russ.) DOI: 10.33293/1609-1442-2020-3(90)-132-142.
13. Li Y., Leung C.H., Wu Q. Probabilistic Learning of Multivariate Time Series with Temporal Irregularity (June 16, 2023). (accessed 23.09.2024). Available at: https://arxiv.org/abs/2306.09147. DOI: 10.48550/arxiv.2306.09147.
14. Jhin S.Y., Lee J., Park N. (2023). Precursor-ofAnomaly Detection for Irregular Time Series (October 13, 2023). (accessed 23.09.2024). Available at: https://arxiv.org/abs/2306.15489. DOI: 10.1145/3580305.3599469.
15. Ojeda C., Palma W., Eyheramendy S. et al. A Novel First-Order Autoregressive Moving Average Model to Analyze Discrete-Time Series Irregularly Observed. In: Theory and Applications of Time Series Analysis and Forecasting: Selected contributions from ITISE 2021: Conference proceedings; 2023. Pp. 91-103. DOI: 10.1007/978-3-031-14197-3_7.
16. Liu X., Zhang F., Liu H. et al. iTimes: Investigating Semisupervised Time Series Classification via Irregular Time Sampling. IEEE Transactions on Industrial Informatics 2023;19(5):6930-6938. DOI: 10.1109/tii.2022.3199374.
17. Ayvazyan S.A. Applied statistics. Fundamentals of econometrics. Volume 2. Moscow: Unity-Dana; 2001. (in Russ.)
18. Makridakis S.G., Wheelwright S.C., McGee V.E. Forecasting: Methods and Applications. 2nd ed. New York: John Wiley and Sons Ltd.; 1983.
19. Makridakis S.G., Wheelwright S.C. Forecasting Methods for Management. 5th ed. New York: John Wiley and Sons Ltd.; 1989.
Review
For citations:
Bochkov A.V., Kirkin M.A. On analysing time series of accidents and incidents at hazardous production facilities. Dependability. 2024;24(4):12-19. (In Russ.) https://doi.org/10.21683/1729-2646-2024-24-4-12-19
Views:
289
ISSN 1729-2646 (Print)
ISSN 2500-3909 (Online)
ISSN 2500-3909 (Online)
Email this article 