Original paper

UDC 662.86:338.24 © N.V. Kondrashova¹, Yu.V. Zabajkin², 2025
ISSN 0041-5790 (Print) • ISSN 2412-8333 (Online) • Ugol’ – Russian Coal Journal, 2025, № 5, pp. 97-106
DOI: http://dx.doi.org/10.18796/0041-5790-2025-5-97-106

SMART DISTRIBUTED TRAINING SYSTEMS TO OPTIMIZE SAFETY PROCESSES IN THE COAL MINING INDUSTRY

Authors

N.V. Kondrashova¹, Yu.V. Zabajkin^2
1ITMO National Research University, Saint-Petersburg, 197101, Russian Federation
²Gubkin Russian State University of Oil and Gas, Moscow, 119991, Russian Federation
e-mail: nvkondrashova@mail.ru

Authors Information

Kondrashova N.V. – PhD (Pedagogical), Associate Professor, ITMO National Research University, Saint-Petersburg, 197101, Russian Federation, e-mail: nvkondrashova@mail.ru
Zabajkin Yu.V. – PhD (Economic), Associate Professor of the Department of Automation of Technological Processes, Gubkin Russian State University of Oil and Gas, Moscow, 119991, Russian Federation

Abstract

The present-day coal mining industry is undergoing a period of fundamental transformation due to introduction of digital technologies and smart systems to control the production processes. Distributed training systems represent an innovative approach to improving the safety of technological cycles, but their successful implementation in the coal mining industry involves a number of specific challenges of organizational, technical and cognitive nature. This research aims to develop and validate an integrated multi-parameter model of distributed training systems to enhance industrial safety at the high-risk coal mining operations. The work applies integrated analysis methods including multilevel parametric modeling of production processes, hierarchical cluster analysis of incidents, multifactor regression modeling and predictive modeling based on multilayer recurrent neural networks with long shortterm memory (LSTM). The empirical base included longitudinal data from 37 coal mining companies for the period of 2018-2023, including 5783 recorded incidents of various severity with detailed parameters for 142 characteristics. The results of the study demonstrate that implementation of the developed model of the distributed training systems helps to reduce the incident rate by 27.4 ±1.8%, shorten the response time to potentially hazardous situations by 43.6 ±2.3% and increase the integral safety factor of the production processes by 0.38±0.02 points. The variance analysis showed a statistically significant reduction (p < 0.001) in the severity of the incident consequences in all the categories with the greatest effect for accidents involving electrical equipment (a decrease by 42.3±1.7%). The costeffectiveness analysis demonstrated a 32.7±1.4% reduction in financial losses associated with industrial incidents during the first year upon the implementation, with an average investment payback period of 6.4±0.3 months. The results obtained significantly expand the theoretical understanding of the possibilities to integrate the smart distributed training systems into high-risk production environments and they offer verified practical solutions for coal mining companies seeking to improve industrial safety.

Keywords

Distributed training systems, coal mining industry, industrial safety, predictive modeling, digital transformation, multifactor risk management, smart training systems.

References

1. Boneh D., Shoup V. A graduate course in applied cryptography. 2020. 709 p.
2. Goodfellow I., Bengio Y., Courville A. Deep learning. Cambridge, MIT Press, 2016. 800 p.
3. Jurafsky D., Martin J.H. Speech and language processing. 3rd ed. draft. Stanford University, 2025. 608 p.
4. Kurzweil R. The singularity is near: when humans transcend biology. New York, Viking, 2005. 672 p.
5. Murphy K.P. Probabilistic machine learning: an introduction. Cambridge, MIT Press, 2022. 826 p.
6. Pham H.T., Pham H., Blazek L.W. Approaches to measuring software safety. Software Quality Professional. 2013;15(4):4-16.
7. Russell S., Norvig P. Artificial intelligence: a modern approach. 4th ed. Hoboken, Pearson, 2021. 1136 p.
8. Sutton R.S., Barto A.G. Reinforcement learning: an introduction. 2nd ed. Cambridge, MIT Press, 2018. 552 p.
9. Жданеев О.В., Власова И.М. Вызовы и приоритеты цифровой трансформации угольной отрасли // Уголь. 2023. № 1. С. 62-69. DOI: 10.18796/0041-5790-2023-1-62-69. Zhdaneev O.V., Vlasova I.M. Digital transformation of the coal industry. Ugol’. 2023;(1):62-69. (In Russ.). DOI: 10.18796/0041-5790-2023-1-62-69.
10. Построение информационной модели горно-обогатительных предприятий / И.Е. Кириллов, И.Н. Морозов, П.М. Мурашев и др. // Вестник Московского университета МВД России. 2021. № 2. С. 288-291. DOI: 10.24412/2073-0454-2021-2-288-291. Kirillov I.E., Morozov I.N., Murashev P.M. et al. Building an information model for mining and processing enterprises. Vestnik Moskovskogo universiteta MVD Rossii. 2021;(2):288-291. (In Russ.). DOI: 10.24412/2073-0454-2021-2-288-291.
11. Рубин А.Я. Вопросы промышленной безопасности и актуальные способы ее обеспечения на опасных производственных объектах // Безопасность труда в промышленности. 2023. № 4. С. 91-96. Rubin A.Ya. Issues of industrial safety and actual ways of its ensuring at hazardous production facilities. Bezopasnost' truda v promyshlennosti. 2023;(4):91-96. (In Russ.).
12. Рыльников А.Г., Пыталев И.А. Цифровая трансформация горнодобывающей отрасли: технические решения и технологические вызовы // Известия Тульского государственного университета. Науки о Земле. 2020. № 1. С. 470-481. https://doi.org/10.46689/2218-5194-2020-1-1-470-481. Rylnikov A.G., Pytalev I.A. Digital transformation of the mining industry: technical solutions and technological challenges. Izvestiya Tul'skogo gosudarstvennogo universiteta. Nauki o Zemle. 2020;(1):470-481. (In Russ.). https://doi.org/10.46689/2218-5194-2020-1-1-470-481.
13. Салтымаков Е.А., Уткаев Е.А., Снетова Е.С. Разработка цифровой платформы для количественного учета выбросов шахтного метана в атмосферу // Вестник Научного центра ВостНИИ по промышленной и экологической безопасности. 2023. № 3. С. 51-58. Saltymakov E.A., Utkaev E.A., Snetova E.S. Development of a digital platform for quantitative assessment of mine methane emissions into the atmosphere. Vestnik Nauchnogo centra VostNII po promyshlennoj i ekologicheskoj bezopasnosti. 2023;(3):51-58. (In Russ.).
14. Роль распределенных серверных систем в модернизации угольного сектора / С.А. Тронин, А.А. Ксенофонтов, О.А. Юссуф и др. // Уголь. 2025;(2):110-118. DOI: 10.18796/0041-5790-2025-2-110-118. Tronin S.A., Ksenofontov A.A., Yussuf О.A., Burova O.A., Frolova V.B. The role of distributed server systems in upgrading the coal sector. Ugol’. 2025;(2): 110-118. (In Russ.). DOI: 10.18796/0041-5790-2025-2-110-118.

For citation

Kondrashova N.V., Zabajkin Yu.V. Smart distributed training systems to optimize safety processes in the coal mining industry. Ugol’. 2025;(5):97-106. (In Russ.). DOI: 10.18796/0041-5790-2025-5-97-106.

Paper Info

• Received April 9, 2025
• Reviewed April 16, 2025
• Accepted April 26, 2025