CREATION OF AN INTEGRATED MODEL FOR ENSURING OPERATIONAL SHIP SAFETY
https://doi.org/10.33815/2313-4763.2025.1.30.209-221
Abstract
The article proposes a novel integrated mathematical model meticulously designed to enhance the operational safety of ships. This comprehensive model seamlessly combines several critical components: probabilistic risk assessment, providing quantitative measures of potential hazards; an in-depth analysis of the degradation of safety barriers, tracking the erosion of protective layers over time or under stress; an aggregate evaluation of the real-time state of various ship subsystems, unifying heterogeneous data for a holistic view; and robust risk prediction capabilities grounded in advanced neural network technologies, enabling the forecasting of future risk trajectories based on learned patterns from complex operational data.
Building upon a robust modeling methodology, a series of five distinct operational scenarios were rigorously simulated. These scenarios were carefully crafted to encompass a wide spectrum of ship functioning conditions, critically considering dynamic environmental changes, various technical failures (e.g., machinery malfunctions, system breakdowns), and the potential loss of efficiency in existing security and safety systems. Such comprehensive scenario testing allows for a thorough validation of the model's performance across diverse and challenging operational contexts.
The simulation results unequivocally demonstrate the proposed model's exceptional ability to detect dangerous conditions at remarkably early stages of their development, far before they escalate into critical incidents. Furthermore, the model is capable of generating precise quantitative risk assessments, offering clear numerical insights into potential threats. Crucially, it also produces actionable recommendations for preventive response, empowering decision-makers with timely and relevant guidance to avert adverse events. The embedded indicators for integrated risk, safety margin, and continuous safety barrier degradation monitoring collectively confirm the system's high information content, providing a rich, multi-faceted understanding of the ship's safety status. This also highlights its remarkable adaptability within a highly dynamic maritime environment, where conditions can change rapidly and unpredictably. The innovative approach presented in this work can therefore serve as a foundational basis for the creation of sophisticated functional platforms dedicated to comprehensively managing the safety of marine vessels. Moreover, it offers significant potential for seamless integration into modern navigation and broader information management systems, thereby paving the way for more resilient, predictive, and proactively managed maritime operations in the future.
References
2. Melnyk, O., Onishchenko, O., Drozhzhyn, O., Pasternak, O., Vilshanyuk, M., Zayats, S., & Shcheniavskyi, G. (2024). The ship safety evaluation and analysis on the multilayer model case study. E3S Web of Conferences, 501, 01018. https://doi.org/10.1051/e3sconf/202450101018.
3. Melnyk, O., Onyshchenko, S., Koskina, Y., Aleksandrovska, N., Drozhzhyn, O., Maluha, E., Pulyaev, I., & Bondaryuk, M. (2024). Full overlap ship security model: An integrative approach to shipboard equipment information security. E3S Web of Conferences, 501, 02002. https://doi.org/10.1051/e3sconf/202450102002.
4. Karimi, N., Javanmardi, E., Nadaffard, A., & Facchini, F. (2025). Systematic analysis and optimization of operational delay factors in port supply chains using a hybrid DEMATEL-OPA-DGRA approach. Ocean & Coastal Management, 263, 107620. https://doi.org/10.1016/j.ocecoaman.2025.107620.
5. Fan, C., Montewka, J., Bolbot, V., Zhang, Y., Qiu, Y., & Hu, S. (2024). Towards an analysis framework for operational risk coupling mode: A case from MASS navigating in restricted waters. Reliability Engineering & System Safety, 248, 110176. https://doi.org/10.1016/j.ress.2024.110176.
6. Wang, Y., Kadakia, Y., Wu, Z., & Christofides, P. D. (2023). An overview of control methods for process operational safety and cybersecurity. Methods in Chemical Process Safety, 8, 1–50. https://doi.org/10.1016/bs.mcps.2024.07.006.
7. Naserbegi, A., Aghaie, M., Sadeghi, K., Ghazaie, S., & Sokolova, E. (2024). Improving operational flexibility of the integrated pressurized water reactor with the MED-TVC desalination system by control logic systems in the off-design mode. Nuclear Engineering and Design, 430, 113702. https://doi.org/10.1016/j.nucengdes.2024.113702.
8. Kang, G., Im, J., & Lee, C. (2024). Operational strategy to minimize operating cost in LNG terminal using a comprehensive numerical boil-off gas model. Energy, 296, 130878. https://doi.org/10.1016/j.energy.2024.130878.
9. Guo, W., Zhang, X., Ge, Y., & Du, Y. (2025). Deep Q-network and knowledge jointly-driven ship operational efficiency optimization in a seaport. Transportation Research Part E: Logistics and Transportation Review, 197, 104046. https://doi.org/10.1016/j.tre.2025.104046.
10. Mochizuki, H. (2025). Summary of researches on operational characteristics and safety of molten salt fast reactors based on neutronics and thermal-hydraulics coupling analysis. Nuclear Engineering and Design, 435, 113941. https://doi.org/10.1016/j.nucengdes.2025.113941.
11. Deng, W., Ma, X., & Qiao, W. (2024). A novel methodology to quantify the impact of safety barriers on maritime operational risk based on a probabilistic network. Reliability Engineering & System Safety, 243, 109884. https://doi.org/10.1016/j.ress.2023.109884.
12. Hellas, M. S., Chaib, R., Nettour, D., & Zerrouki, H. (2024). A new approach proposal for ensuring security engineering through barrier and operational quantitative risk analysis (BOQRA). Journal of Loss Prevention in the Process Industries, 91, 105390. https://doi.org/10.1016/j.jlp.2024.105390.
13. Zhang, M., Wang, H., Conti, F., Manderbacka, T., Remes, H., & Hirdaris, S. (2025). A hybrid deep learning method for the real-time prediction of collision damage consequences in operational conditions. Engineering Applications of Artificial Intelligence, 145, 110158. https://doi.org/10.1016/j.engappai.2025.110158.
14. Obeng, F., Domeh, D., Khan, F., Bose, N., & Sanli, E. (2024). An operational risk management approach for small fishing vessel. Reliability Engineering & System Safety, 247, 110104. https://doi.org/10.1016/j.ress.2024.110104.
15. Onishchenko, O. A., Melnyk, O. M., Kurdiuk, S. V., Drozdenko, O. I., Havryliuk, T. K., & Burlachenko, D. A. (2024). Zastosuvannia metodiv mashynnoho navchannia dlia optymizatsii marshrutiv i zavdan avtonomnykh nadvodnykh aparativ [Application of machine learning methods for optimizing routes and tasks of autonomous surface vehicles]. Nauka i tekhnika, 12(40), 1372–1386. https://doi.org/10.52058/2786-6025-2024-12(40)-1372-1386.
