AN ADVANCED AI-BASED SYSTEM FOR INTELLIGENT BRIDGE ALARM MONITORING ON MARITIME VESSELS
DOI:
https://doi.org/10.59277/RRST-EE.2025.2.12Keywords:
Maritime alarm monitoring, Artificial intelligence (AI), Machine learning, Anomaly detection, Predictive analytics, Python simulations, Smart ships, Maritime safety, Real-time alarm processing, Sensor data analysis, Intelligent maritime systemsAbstract
Effective alarm monitoring systems are crucial within the maritime sector to ensure safety and operational continuity. Artificial intelligence is one of the most popular fields nowadays and is often used for machine learning applications. Utilizing AI-based anomaly detection and predictive analytics to analyze real-time alarm data from the ship’s sensor level, the proposed system enhances situational awareness and reduces false alarms. Therefore, machine learning models are trained on hundreds of thousands of historical alarm patterns to detect potential faults and improve response times. The automated clustering tool provides a classification of maritime alarm scenarios, and a simulated framework that mimics these alerts showcases the system's ability to focus on essential alerts rather than nonsensical ones. Training them on data until October 2024 allows the ground-truth knowledge to be explicitly built, accounting for recent advancements and findings in the field of maritime processes. Experimental results demonstrate significant improvements in alarm classification accuracy and early detection, enabling data-driven decision-making in the marine domain.
References
(1) S. Samya, S. Alagar Sumithra, et al., Software cost effort and time estimation using dragonfly whale lion optimized deep neural network, Rev. Roum. Sci. Techn. – Électrotechn. Et Énerg., 69, 4, pp. 431–436 (2024).
(2) K. Guerraiche, et al., Intelligent fault detection and location in electrical high-voltage transmission lines, Rev. Roum. Sci. Techn. – Électrotechn. Et Énerg., 69, 3, pp. 269–276 (2024).
(3) N. Forti, E. d’Afflisio, P. Braca, L.M. Millefiori, S. Carniel, P. Willett, Next-Gen intelligent situational awareness systems for maritime surveillance and autonomous navigation [Point of View], Proceedings of the IEEE, 110, 10, pp. 1532-1537 (2022).
(4) S.-I. Mihali, Ș.-L. Niță, Credit card fraud detection based on random forest model, 2024 International Conference on Development and Application Systems (DAS), pp. 111-114 (2024).
(5) S.-I. Mihali, Ș.-L. Niță, Cybersecurity of online financial systems using machine learning techniques, 2024 16th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), pp. 1-6 (2024).
(6) R.A. Crăciun, et al., Internet of things platform benchmark: An artificial intelligence assessment, Rev. Roum. Sci. Techn. – Électrotechn. Et Énerg., 69, 1, pp. 97–102 (2024).
(7) ***Alarm Overload Threatens Maritime Safety, LR - Lloyd’s Register (2024).
(8) D. Perišić, Generalization of the time infinite impulse response digital filters, Rev. Roum. Sci. Techn. – Électrotechn. Et Énerg., 69, 3, pp. 323–328 (2024).
(9) ***Ship Alarm Monitoring System Market Key Challenges, Growth and Insightful Market Pros, (2025).
(10) ***New digital systems bring more ‘alarm fatigue’ for mariners, the Maritime Executive (2024).
(11) ***New digital systems bring more ‘alarm fatigue’ for mariners, the Maritime Executive (2024).
(12) ***Rise of BNWAS Adds to Concerns over Alarm Fatigue (2020).
(13) ***Alarm Root Cause Analysis Using AI/ML in MSO Networks.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 REVUE ROUMAINE DES SCIENCES TECHNIQUES — SÉRIE ÉLECTROTECHNIQUE ET ÉNERGÉTIQUE
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
