Reliability Assessment of Ship Lubricating Oil Systems Through Improved Dynamic Bayesian Networks and Multi-Source Data Fusion
Source abstract
Abstract
The operational efficiency and reliability of the ship’s lubrication oil system directly impact the vessel’s safety. Traditional reliability analysis methods struggle to effectively handle the system’s dynamic characteristics and multi-source data analysis. To address these issues, this study proposes an innovative method that integrates feature dimensionality reduction, a dynamic Bayesian network of gravity model to improve the accuracy of system reliability analysis. First, the proportional hazards model is used to evaluate the operational reliability of each component, providing a quantitative basis for assessing the system’s health status through failure rate estimation. Then, a dynamic Bayesian network model is employed for overall system reliability analysis, fully considering the impact of multi-state devices and different maintenance strategies. The proposed DBN-based reliability assessment method achieves significant improvements over the traditional Fault Tree Analysis (FTA). The reliability of the main lubrication oil system (GUB) increases from 0.169 to 0.261, representing a 9.2% improvement; under scheduled maintenance conditions, the system reliability stabilizes at approximately 0.9873 after 0.4×105 h, compared to only 0.24 without maintenance. The proposed method effectively evaluates the reliability of the lubrication oil system, and the maintenance strategy using this method can greatly improve the reliability, providing strong support for scientifically guiding maintenance decisions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Engineering Diagnostics and Reliability · Fault Detection and Control Systems · Risk and Safety Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Jiangsu Shipbuilding and Ocean Engineering Design and Research Institute, Zhenjiang 212100, China
School of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, China
Funding
Research on the Mechanism of Hydrogen-Oxygen Flame Line Heating and Forming of Outer Hull Plate and Intelligent Operation Decision Support System (National Natural Science Foundation of China) · V-DT-driven an-dAI-enabled Comprehensive Protection Technology for Complex Equipment of Large Ships at Sea Research
References (35)
Show source-provided references
1. Cybersecurity risk assessment of a marine dual-fuel engine on inland waterways ship
2. Maritime safety and the ISM code: A study of investigated casualties and incidents10.1007/s13437-013-0051-8 ↗
3. Reliability analysis and operator modelling10.1016/0951-8320(95)00143-3 ↗
4. Reliability block diagram (RBD) and fault tree analysis (FTA) approaches for estimation of system reliability and availability–a case study10.1108/IJQRM-05-2019-0176 ↗
5. Zhao, J., Gao, C., Tang, T., Xiao, X., Luo, M., and Yuan, B. (2022). Overview of equipment health state estimation and remaining life prediction methods. Machines, 10.10.3390/machines10060422 ↗
6. Stein, J., Lopes, S., and Medino, A. (2021). A Generalization of the Ornstein-Uhlenbeck Process: Theoretical Results, Simulations and Parameter Estimation. arXiv.
7. Walz, T.P., Mopuru, S.K.R., Vogelbacher, G., Richter, A., Höflinger, F., Häring, I., Finger, J., and Stolz, A. (2023, January 24–28). Markov Modelling for Autonomous Vehicle Safety Assessment: Numerical Modularization to Avoid System State-Explosion. Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain.10.1109/ITSC57777.2023.10421943 ↗
8. Data-driven lightning-related failure risk prediction of overhead contact lines based on Bayesian network with spatiotemporal fragility model10.1016/j.ress.2022.109016 ↗
9. A probabilistic assessment of ship blackout incident with Fault Tree Analysis into (FTA) Bayesian Network (BN)10.1080/20464177.2024.2423425 ↗
10. A comparison of DBN model performance in SIPPRA health monitoring based on different data stream discretization methods10.1016/j.ress.2023.109206 ↗
11. Deep learning-based methods in structural reliability analysis: A review10.1088/1361-6501/acc602 ↗
12. Blockchain as a service environment: A dependability evaluation10.1007/s11227-023-05342-9 ↗
13. Multiscale shape-memory effects in a dynamic polymer network for synchronous changes in color and shape10.1016/j.apmt.2021.101276 ↗
14. Jiang, H., Li, S., Shao, Y., Xu, A., Yuan, J., and Zhao, Q. (2022, January 8–10). A multi-channel fusion method based on tensor for rolling bearing fault diagnosis. Proceedings of the International Conference on Neural Computing for Advanced Applications, Jinan, China.10.1007/978-981-19-6135-9_10 ↗
15. Xu, Y., Xie, T., Zhou, Z., Lu, Y., Jun, J., Chen, S., Li, J., Ma, Y., and Chao, J. (2016, January 25–28). Research of practical expert system for transformer fault diagnosis based on multidimensional data fusion. Proceedings of the 2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Xi’an, China.10.1109/APPEEC.2016.7779516 ↗
16. OROSNJAK, M., Beker, I., Brkljač, N., and Vrhovac, V. (2024). Predictors of Successful Maintenance Practices in Companies Using Fluid Power Systems: A Model-Agnostic Interpretation. Appl. Sci., 14.10.3390/app14135921 ↗
17. Data-driven operating monitoring for coal-fired power generation equipment: The state of the art and challenge
18. Meidani, K. (2024). Machine Learning for Symbolic Mathematics and Physics Discovery. [Ph.D. Thesis, Carnegie Mellon University].
19. Neupane, D., Bouadjenek, M.R., Dazeley, R., and Aryal, S. (2024). Data-driven machinery fault detection: A comprehensive review. arXiv.10.2139/ssrn.4856168 ↗
20. Wang, Z., He, J., Zhou, W., Zhou, K., Zhao, X., Lyu, S., Shen, J., and Lu, Y. (2024, January 15–16). Large-scale chip layout pattern clustering method based on graph matching. Proceedings of the Eighth International Workshop on Advanced Patterning Solutions (IWAPS 2024), Jiaxing, China.10.1117/12.3052980 ↗
21. A hybrid knowledge-based and data-driven method for aging-dependent reliability evaluation of high-voltage circuit breaker10.1109/TPWRD.2023.3314083 ↗
22. Efficient and unbiased safety test for autonomous driving systems10.1109/TIV.2022.3213310 ↗
23. Fault diagnosis of rolling bearings based on the improved symmetrized dot pattern enhanced convolutional neural networks10.1007/s42417-023-00949-x ↗
24. Edge computing on IoT for machine signal processing and fault diagnosis: A review10.1109/JIOT.2023.3239944 ↗
25. Unreliability tracing of power systems for identifying the most critical risk factors considering mixed uncertainties in wind power output
26. Kalanpour, N. (2024). Shrinkage Estimators for Semi-Parametric Proportional Hazards Mixture Cure Models. [Ph.D. Thesis, Memorial University of Newfoundland].
27. On the suitable superstructure thermoeconomic optimization of a waste heat recovery system for a Brazilian diesel engine power plant10.1016/j.enconman.2021.113947 ↗
28. 6210 dual-fuel engine performance test and analysis
29. Wang, Y., and Xu, W. (2024). Complete Ensemble Empirical Mode Decomposition with Adaptive Noise to Extract Deep Information of Bearing Fault in Steam Turbines via Deep Belief Network. Int. J. High Speed Electron. Syst., 2440079.10.1142/S0129156424400792 ↗
30. Sheidaei, A., Foroushani, A.R., Gohari, K., and Zeraati, H. (2022). A novel dynamic Bayesian network approach for data mining and survival data analysis. BMC Med Informatics Decis. Mak., 22.10.1186/s12911-022-02000-7 ↗
31. Bearing fault diagnosis based on clustering and sparse representation in frequency domain10.1109/TIM.2021.3118092 ↗
32. Systematic review on tool breakage monitoring techniques in machining operations10.1016/j.ijmachtools.2022.103882 ↗
33. Reliability analysis of the multi-state system with nonlinear degradation model under Markov environment10.1016/j.ress.2023.109411 ↗
34. Fokeev, A., Subgatullin, B., and Ushakov, D. (2021, January 16–18). An approach to the calculation of general industrial nonlinear electrical loads. Proceedings of the 2021 International Conference on Electrotechnical Complexes and Systems (ICOECS), Ufa, Russia.10.1109/ICOECS52783.2021.9657455 ↗
35. Prediction maintenance based on vibration analysis and deep learning —A case study of a drying press supported on a Hidden Markov Model10.1016/j.asoc.2024.111885 ↗