The study addresses the issue of quantitative assessment of the human factor impact on the safety of the operation of bridge cranes. The existing methods of industrial safety assessment are oriented primarily towards the analysis of machinery failures and do not account for the level of professional competencies of operators when forecasting incidents, which is particularly important in conditions of operation of equipment with expired service life and restaffing.
The goal of the study is to develop and verify an integrated neural network model that forecasts the probability of an incident as a nonlinear function of equipment technical parameters and the operator’s competency level. The study has used a two-stream architecture of a fully connected neural network, ensuring separate processing of technical parameters (metal structure wear and tear, vibrational characteristics, thermal modes, loading factor, wear and tear of braking system), and competency indices of operators formed based on five key job functions in accordance with professional standards of bridge crane operators. The training dataset included 120 observations for a three-year period of operation. A quantitative nonlinear relationship between incident probability and the level of operator competencies has been established: reducing the integral competency index from 0.75 to 0.5 increases the incident probability by more than 1.7 times under fixed technical parameters. The classification accuracy of the developed model on a test set was 87%, indicating a high ability to distinguish between safe and accident-hazardous conditions. As a practical example shows, the combined impact on technical parameters and competency level reduces the integral risk by more than 50 %. The developed model enables a transition from reactive analysis of incident consequences to proactive industrial safety management, quantitative substantiation of investments in personnel training alongside technical modernization, and the formation of digital risk profiles for cranes, shifts, and teams.
On approval of the Federal norms and rules for industrial safety “Safety rules for hazardous production facilities operating lifting equipment”: the Order of Rostechnadzor of November 26, 2020 № 461. Available at: https://www.consultant.ru/document/cons_doc_LAW_373321/ (accessed: May 11, 2026). (In Russ.).
2. Влияние компетенций специалистов грузоподъемных кранов на вероятность возникновения аварийных ситуаций / В.В. Егельский, Н.Н. Николаев, Е.В. Егельская, А.А. Короткий // Безопасность техногенных и природных систем. 2023. № 2. С. 70–79. DOI: 10.23947/2541-9129-2023-7-2-70-79
Egelsky V.V., Nikolaev N.N., Egelskaya E.V., Korotkiy A.A. Influence of the Competencies of Lifting Crane Specialists on the Probability of Emergencies. Bezopasnost tekhnogennykh i prirodnykh system = Safety of Technogenic and Natural Systems. 2023. № 2. pp. 70–79. (In Russ.). DOI: 10.23947/2541-9129-2023-7-2-70-79
3. Khvan R.V. The use of artificial neural networks in solving the problem of estimating the residual life of lifting cranes. E3S Web of Conferences. 2024. Vol. 515. DOI: 10.1051/e3sconf/202451504015
4. Хван Р.В. Сравнительный анализ качества работы искусственных нейронных сетей для оценки технического состояния стального каната // Безопасность техногенных и природных систем. 2024. № 2. С. 68–77. DOI: 10.23947/2541-9129-2024-8-2-68-77
Khvan R.V. Comparative Analysis of the Performance of Artificial Neural Networks in Assessing the Technical Condition of Steel Ropes. Bezopasnost tekhnogennykh i prirodnykh system = Safety of Technogenic and Natural Systems. 2024. № 2. рр. 68–77. (In Russ.). DOI: 10.23947/2541-9129-2024-8-2-68-77
5. Аблязов Э.К., Аблязов К.А. Оценка технического состояния портового подъемно-транспортного оборудования (ПТО) с использованием нечеткой логики // Морские интеллектуальные технологии. 2024. № 2. Ч. 1. С. 242–251. (In Russ.). DOI: 10.37220/MIT.2024.64.2.027
Ablyazov E.K., Ablyazov K.A. Assessment of the technical condition of the port lifting and transport equipment (LTE) using fuzzy logic. Morskie intellektualnye tekhnologii = Marine intelligent technologies. 2024. № 2. Pt. 1. рр. 242–251. DOI: 10.37220/MIT.2024.64.2.027
6. Li T., Wu W., Li X., Li Y., Gong X., Zhang S., Ma R., Liu X., Zou M. A Hybrid Approach Combining Scenario Deduction and Type-2 Fuzzy Set-Based Bayesian Network for Failure Risk Assessment in Solar Tower Power Plants. Sustainability. 2025. Vol. 17. № 11. DOI: 10.3390/su17114774
7. Sobhanifard F. Optimization of Bayesian Neural Networks using hybrid PSO and fuzzy logic approach for time series forecasting. Discover Artificial Intelligence. 2025. Vol. 5. DOI: 10.1007/s44163-025-00322-9
8. Yang J., Xing L., Wang Y., He L. Combinatorial Reliability Evaluation of Multi-State System with Epistemic Uncertainty. International Journal of Mathematical Engineering and Management Sciences. 2022. Vol. 7. Iss. 3. pp. 312–324. DOI: 10.33889/IJMEMS.2022.7.3.021
9. Panasiuk J.A., Adamus A. A study on elements of machine vision and machine learning in industrial vision systems. Problems of Mechatronics Armament Aviation Safety Engineering. 2024. Vol. 15. № 3. рр. 87–106. DOI: 10.5604/01.3001.0054.7513
10. Shapira A., Simcha M. AHP-Based Weighting of Factors Affecting Safety on Construction Sites with Tower Cranes. Journal of Construction Engineering and Management. 2019. Vol. 135. № 5. рр. 307–318. DOI: 10.1061/(ASCE)0733-9364(2009)135:4(307)
11. Kraus M., Mämpel S. Kennwerte neuer und abgenutzter Kranschienen für die Bemessung von Kranbahnträgern. Stahlbau. 2017. Vol. 86. № 1. рр. 36–44. DOI: 10.1002/stab.201710445
12. Хван Р.В. Комплексная оценка технического состояния надземных рельсовых крановых путей с использованием искусственных нейронных сетей// Безопасность труда в промышленности. 2025. № 6. С. 7–13. DOI: 10.24000/0409-2961-2025-6-7-13
Khvan R.V. Comprehensive Evaluation of the Technical State of Overhead Railway Crane Tracks Using Artificial Neural Networks. Bezopasnost Truda v Promyshlennosti = Occupational Safety in Industry. 2025. № 6. pp. 7–13. (In Russ.). DOI: 10.24000/0409-2961-2025-6-7-13
13. Kettler M., Derler C., Schörghofer A., Macho C., Unterweger H. Laboratory and numerical tests on real crane runway girder with box section. Journal of Constructional Steel Research. 2019. Vol. 160. рр. 540–558. DOI: 10.1016/j.jcsr.2019.06.002