Enter your email address
Submit
Write your message
1- Faculty of Mechanical Engineering, Sharif University of Technology, Tehran, Iran
Abstract: (16 Views)
Stern-tube bearing failures can immobilize vessels and discharge lubricants into the sea, yet traditional threshold-based oil monitoring often overlooks the earliest signs of wear. We have developed an AI-driven predictive-maintenance framework that combines routine oil-analysis data with machine-learning models to detect incipient faults. Using a labelled dataset of 437 samples (54.2 % normal, 40.3 % warning, 5.5 % abnormal), we trained Random Forest and CatBoost classifiers; the Random Forest achieved an overall accuracy of 85 %. Applying the ADASYN over sampler raised recall for the rare abnormal class from 0.42 to 0.73. SHAP analysis identified copper and lead (bearing wear) as well as sodium and boron (seal-water ingress and additive depletion) as the most influential predictors. In a field trial on an AHTS-DP1 vessel, the model flagged rising boron six months before a dry-dock inspection confirmed seal damage caused by fishing-net entanglement, enabling timely repair and averting a potential MARPOL violation. Compared with the operator’s existing rule-based alerts, the proposed system cut false alarms by 40 % while detecting subtle degradation earlier. These findings show that merging tribological expertise with data-driven analytics can markedly enhance stern-tube reliability and promote more sustainable ship operations.
Full-Text [PDF 689 kb]
(4 Downloads)
Highlights
1. Critical Role of Stern Tube Monitoring, ensuring safe and reliable ship operation requires continuous monitoring of the stern tube as a key marine component.
2. AI-Driven Oil Analysis, the study integrates real oil analysis data with advanced AI algorithms, achieving about 85% accuracy.
3. Real-World Validation, the proposed method was successfully validated under actual sea operating conditions.
4. Early Fault Detection, potential failures were identified up to six months before dry docking, enabling timely maintenance and risk reduction.
5. Enhanced Reliability and Sustainability, combining tribology with data-driven analytics improve stern tube reliability and supports sustainable maritime operation.
1. Critical Role of Stern Tube Monitoring, ensuring safe and reliable ship operation requires continuous monitoring of the stern tube as a key marine component.
2. AI-Driven Oil Analysis, the study integrates real oil analysis data with advanced AI algorithms, achieving about 85% accuracy.
3. Real-World Validation, the proposed method was successfully validated under actual sea operating conditions.
4. Early Fault Detection, potential failures were identified up to six months before dry docking, enabling timely maintenance and risk reduction.
5. Enhanced Reliability and Sustainability, combining tribology with data-driven analytics improve stern tube reliability and supports sustainable maritime operation.
Audio file of the article abstract [MP3 3018 KB] (0 Download)
References
1. Li R.; Ouyang W.; Liu Q.; Jin Y.; Yang J. (2024). Dynamic bearing characteristics of the ship stern shaft-bearing system with wave impact. Ocean Engineering 297, pp. 119020. [DOI:10.1016/j.oceaneng.2024.119020]
2. Wodtke M.; Litwin W. (2020). Water-lubricated stern tube bearing - experimental and theoretical investigations of thermal effects. Tribology International 151, pp. 106608. [DOI:10.1016/j.triboint.2020.106608]
3. Lee J.; Jeong B.; An T.-H. (2019). Investigation on effective support point of single stern tube bearing for marine propulsion shaft alignment. Marine Structures 64, pp. 1-17. [DOI:10.1016/j.marstruc.2018.10.010]
4. Lin C.-G.; Zou M.-S.; Sima C.; Liu S.-X.; Jiang L.-W. (2019). Friction-induced vibration and noise of marine stern tube bearings considering perturbations of the stochastic rough surface. Tribology International 132, pp. 661-671. [DOI:10.1016/j.triboint.2018.11.026]
5. Rossopoulos G. N.; Papadopoulos C. I.; Leontopoulos C. (2020). Tribological comparison of an optimum single and double-slope design of the stern tube bearing: case study for a marine vessel. Tribology International 148, pp. 106343. [DOI:10.1016/j.triboint.2020.106343]
6. Frost J.; Frycz M.; Kowalski J.; Wodtke M.; Litwin W. (2023). Environmentally acceptable lubricants (EAL) compared with a reference mineral oil as marine stern tube bearing lubricant - experimental and theoretical investigations. Tribology International 181, pp. 109001. [DOI:10.1016/j.triboint.2023.109001]
7. Rossopoulos G. N.; Pervelis I.; Skaltsas D.; Papadopoulos C. I.; Vlachos O.; Koutsoumpas G.; Leontopoulos C. (2025). Experimental characterization of the tribological and acoustic performance of different stern-tube bearing materials. Tribology International 191, pp. 110590. [DOI:10.1016/j.triboint.2025.110590]
8. Qin H.-L.; Zhou X.-C.; Zhao X.-Z.; Xing J.-T.; Yan Z.-M. (2015). A new rubber/UHMWPE alloy for water-lubricated stern bearings. Wear 332-333, pp. 257-261. [DOI:10.1016/j.wear.2015.02.016]
9. Zhang S.-D.; Long Z.-L.; Yang X.-Y. (2020). Reaction force of ship stern bearing in hull large deformation based on stochastic theory. International Journal of Naval Architecture and Ocean Engineering 12 (2), pp. 723-732. [DOI:10.1016/j.ijnaoe.2020.03.009]
10. Litwin W.; Dymarski C. (2016). Experimental research on water-lubricated marine stern tube bearings in conditions of improper lubrication and cooling causing rapid bush wear. Tribology International 95, pp. 449-455. [DOI:10.1016/j.triboint.2015.12.005]
11. Fang S.; Mu L.; Jia S.; Liu K.; Liu D. (2022). Combining artificial intelligence and laboratory experiments to explore the behaviour of sunken and submerged oil: a typical oil drift and diffusion detection technology. Journal of Cleaner Production 338, pp. 133026. [DOI:10.1016/j.jclepro.2022.133026]
12. American Bureau of Shipping (ABS); Germanischer Lloyd (GL). Rules and guidelines for ship classification. Classification Society Publications, n.d.
13. Dubai Dry Dock. (2024). AHTS-DP1 technical documents. Internal company documentation.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
International Journal of Maritime Technology is licensed under a
Creative Commons Attribution-NonCommercial 4.0 International License.