Enter your email address
Submit
Write your message
1- Mechanical Engineering Department, Babol Noshirvani University of Technology
Abstract: (50 Views)
| In marine engineering, ship vibration analysis is crucial for ensuring structural integrity, operational safety, and environmental sustainability. Traditional analysis, following classical paradigms established by early contributors such as Todd, Kumai, and Schlick, relies primarily on costly simulations and empirical tests. This study seeks to overcome these limitations by integrating machine learning (ML) methodologies with semi-empirical models to develop a predictive hybrid model, thereby advancing vibration analysis toward a data-driven paradigm. The research is significant for improving ship design, mitigating vibration-related risks, and reducing reliance on resource-intensive approaches, aligning with global efforts to promote energy-efficient and sustainable maritime operations. The proposed hybrid model combines Random Forest (RF) and Logistic Regression (LR), leveraging RF’s capacity for modeling nonlinear relationships and LR’s interpretability for linear adjustments. Trained on Kumai’s seminal dataset and validated on 373 cases spanning 34 ship types, the model accurately predicts critical parameters (α, τ₂, N₂, N₃, and c̄) with exceptional precision. Performance metrics demonstrate strong results, including near-perfect R² values (0.9938 for α) and minimal MSE (0.0000 for α, 0.0701 for N₃). Natural frequency predictions exhibit less than 3% error, as validated against empirical data for crude oil tankers. Feature importance analysis identifies structural parameters (length, displacement, block coefficient) as key predictors, enhancing interpretability for engineering applications. This work bridges the gap between classical vibration theory and modern ML, offering a cost-effective, scalable alternative to conventional simulations. By enabling precise vibration predictions across diverse vessels, the model facilitates predictive maintenance, design optimization, and operational safety. The findings highlight the transformative potential of hybrid ML in maritime engineering, paving the way for digital twins and sustainability-driven ship design. |
Keywords: Hybrid Machine Learning, Random Forest, Logistic Regression, Ship Vibrations, Predictive Maintenance
Full-Text [PDF 517 kb]
(15 Downloads)
Highlights
- Hybrid ML model (RF + LR) predicts ship vibrations with high accuracy.
- Achieves R²=0.9938 & near-zero MSE for key parameter α on 373 ships.
- Validated on 34 ship types; <3% error in natural frequency prediction.
- Length, displacement, block coefficient are top predictors (>60% importance).
- Enables cost-effective design optimization & predictive maintenance for safety.
Audio file of the article abstract [MP3 3928 KB] (1 Download)
References
1. Ahmadi, F., Rahbar-Ranji, A., & Nowruzi, H. (2023). Estimation of ultimate shear strength of one-side corroded plates with cracks by FEM and ANNs. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 45(6), 1-13.
https://doi.org/10.1007/s40430-023-04300-z [DOI:10.1007/s40430-023-04123-5]
2. Barrios, J., Méndez, G., & Cavazos, A. (2020). Hybrid-learning type-2 takagi-sugeno-kang fuzzy systems for temperature estimation in hot-rolling. Metals, 10(6), 758. [DOI:10.3390/met10060758]
3. Braunbehrens, R., Strecker, K., Anand, A., Felder, M., Petzschmann, J., & Bottasso, C. (2024). Site-specific production forecast through data-driven and engineering models. Journal of Physics Conference Series, 2767(9), 092054. [DOI:10.1088/1742-6596/2767/9/092054]
4. Charlou, M., Babarit, A., & Gentaz, L. (2023). A new validated open-source numerical tool for the evaluation of the performance of wind-assisted ship propulsion systems. Mechanics & Industry, 24, 26. [DOI:10.1051/meca/2023026]
5. Connolly, D., Costa, P., Kouroussis, G., Galvín, P., Woodward, P., & Laghrouche, O. (2015). Large scale international testing of railway ground vibrations across Europe. Soil Dynamics and Earthquake Engineering, 71, 1-12. [DOI:10.1016/j.soildyn.2015.01.001]
6. Daniel, J., Schuster, M., Andresen-Paulsen, G., Holz, F., Wittekind, K., & Ehlers, S. (2022). An advanced prediction model for underwater noise emissions of ships. Journal of Ship Production and Design, 38(04), 220-238.
https://doi.org/10.5957/JSPD.06210017 [DOI:10.5957/jspd.06210017]
7. Ding, J., Chen, Z., & Du, Y. (2021). Probability box theory-based uncertain power flow calculation for power system with wind power. International Journal of Emerging Electric Power Systems, 22(2), 243-253. [DOI:10.1515/ijeeps-2020-0227]
8. Dong, L., Zhang, H., Yu, J., & Hu, G. (2023). Energy harvesting potential assessment and systematic design for energy-regenerative shock absorbers on railway freight wagons. Journal of Intelligent Material Systems and Structures, 35(3), 270-290.
https://doi.org/10.1177/1045389X231200146 [DOI:10.1177/1045389x231200146]
9. Fu, C., Xu, Y., Yang, Y., Lu, K., Gu, F., & Ball, A. (2020). Response analysis of an accelerating unbalanced rotating system with both random and interval variables. Journal of Sound and Vibration, 466, 115047. [DOI:10.1016/j.jsv.2019.115047]
10. Gao, M. and Liu, W. (2022). Study on a base-galloping hybrid excitation piezoelectric vibration energy harvester. Journal of Physics Conference Series, 2383(1), 012003. [DOI:10.1088/1742-6596/2383/1/012003]
11. García-Miguel, P., Zarilli, D., Alonso-Martínez, J., Plaza, M., & Arnaltes, S. (2024). Optimal operation and market integration of a hybrid farm with green hydrogen and energy storage: a stochastic approach considering wind and electricity price uncertainties. Sustainability, 16(7), 2856. [DOI:10.3390/su16072856]
12. Hammad, K., Al-Turki, A., Sudirman, S., & Sawlan, Z. (2024). Enhancing reservoir model history matching with ai surrogate and ensemble iterative algorithms..
https://doi.org/10.2118/221028-MS [DOI:10.2118/221028-ms]
13. Hu, Y., Qiao, Y., Chu, J., Yuan, L., & Pan, L. (2019). Joint point-interval prediction and optimization of wind power considering the sequential uncertainties of stepwise procedure. Energies, 12(11), 2205. [DOI:10.3390/en12112205]
14. Lan, T., Hwang, H., Chen, J., & Long, Y. (2023). Improvement in vibration of hybrid powertrain with combined control methods. Sensors and Materials, 35(6), 1871.
https://doi.org/10.18494/SAM4318 [DOI:10.18494/sam4318]
15. Li, Z., Wang, S., Li, F., Li, L., Liu, L., & Zou, H. (2022). Influence of 3d modification on dynamic characteristics of herringbone gearbox system and vibration reduction design. Proceedings of the Institution of Mechanical Engineers Part K Journal of Multi-Body Dynamics, 236(4), 602-622. [DOI:10.1177/14644193221107483]
16. Lin, Y., Zhang, H., Liu, J., Ju, W., Wang, J., & Chen, X. (2021). Research on short-term wind power prediction of gru based on similar days. Journal of Physics Conference Series, 2087(1), 012089. [DOI:10.1088/1742-6596/2087/1/012089]
17. Liu, L., Zhou, W., Guan, K., Peng, B., Xu, S., Tang, J., … & Jin, Z. (2024). Knowledge-guided machine learning can improve carbon cycle quantification in agroecosystems. Nature Communications, 15(1). [DOI:10.1038/s41467-023-43860-5] [PMID] []
18. Ma, X., Huang, S., Song, Y., & Zhang, Z. (2023). Uncertainty quantification and probabilistic reliability analysis for the self-excited vibration of a spline-shafting system. Inter-Noise and Noise-Con Congress and Conference Proceedings, 268(3), 5294-5301.
https://doi.org/10.3397/IN_2023_0746 [DOI:10.3397/in_2023_0746]
19. Marino, L. and Cicirello, A. (2023). A switching gaussian process latent force model for the identification of mechanical systems with a discontinuous nonlinearity. Data-Centric Engineering, 4. [DOI:10.1017/dce.2023.12]
20. Mezouary, L., Hadri, A., Kharrou, M., Fakır, Y., Elfarchouni, A., Bouchaou, L., … & Chehbouni, A. (2024). Contribution to advancing aquifer geometric mapping using machine learning and deep learning techniques: a case study of the al haouz-mejjate aquifer, marrakech, morocco. Applied Water Science, 14(5). [DOI:10.1007/s13201-024-02162-x]
21. Miao, K., Yong, H., Zhang, L., Guo, L., & Hermans, T. (2025). Quantifying groundwater contaminant source uncertainty in fracture networks combining falsification and bayesian evidential learning.. [DOI:10.5194/egusphere-egu25-11456]
22. Mukangango, J., Muyskens, A., & Priest, B. (2024). A robust approach to gaussian process implementation. Advances in Statistical Climatology Meteorology and Oceanography, 10(2), 143-158. [DOI:10.5194/ascmo-10-143-2024]
23. Mylonas, C., Abdallah, I., & Chatzi, E. (2019). Deep unsupervised learning for condition monitoring and prediction of high dimensional data with application on windfarm scada data., 189-196. [DOI:10.1007/978-3-030-12075-7_21]
24. Nowruzi, H., Shora, M. M., & Ghassemi, H. (2017). Using computational fluid dynamic and artificial neural networks to predict the performance and cavitation volume of a propeller under different geometrical and physical conditions. Ocean Engineering, 136, 76-86. [DOI:10.1016/j.oceaneng.2017.03.002]
25. Sankararaman, S., & Mahadevan, S. (2014). Uncertainty Quantification in Structural Health Monitoring. In Encyclopedia of Earthquake Engineering. Springer, Berlin, Heidelberg. [DOI:10.1007/978-3-642-36197-5_281-1]
26. Sengupta, M., Zhang, H., Zhao, Y., Jervis, M., & Graña, D. (2021). Direct depth-domain bayesian amplitude-variation-with-offset inversion. Geophysics, 86(5), M167-M176. [DOI:10.1190/geo2020-0219.1]
27. Taghva, H. R., Ghassemi, H., & Nowruzi, H. (2018). Seakeeping performance estimation of the container ship under irregular wave condition using artificial neural network. American Journal of Civil Engineering and Architecture, 6(4), 123-129. [DOI:10.12691/ajcea-6-4-3]
28. Venturini, M., Alvisi, S., Simani, S., & Manservigi, L. (2018). Comparison of different approaches to predict the performance of pumps as turbines (pats). Energies, 11(4), 1016. [DOI:10.3390/en11041016]
29. Wang, Z., Sumbal, S., & Toumazou, C. (2025). A hybrid ode-neural network framework for modeling and guiding glp-1-mediated glucose dynamics.. [DOI:10.21203/rs.3.rs-5912837/v1]
30. Zhang, X., Li, X., Zhang, J., Song, L., & Li, Y. (2015). A hybrid model for the prediction of low-frequency noise emanating from a concrete box-girder railway bridge. Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit, 230(4), 1242-1256. [DOI:10.1177/0954409715605127]
31. Zhang, Y., Sun, H., & Guo, Y. (2019). Wind power prediction based on pso-svr and grey combination model. Ieee Access, 7, 136254-136267.
https://doi.org/10.1109/ACCESS.2019.2942012 [DOI:10.1109/access.2019.2942012]
32. Zhou, W., Liu, L., Guan, K., Jin, Z., Peng, B., & Wang, S. (2025). Scalable quantification of agroecosystem carbon budget and crop yield based on knowledge-guided machine learning.. [DOI:10.5194/egusphere-egu25-7574]
33. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. [DOI:10.1023/A:1010933404324]
34. Wang, J., & Liu, Y. (2019). A hybrid ensemble approach for structural health monitoring using machine learning. Structural Control and Health Monitoring, 26(4), e2345. [DOI:10.1002/stc.2345]
35. Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied Logistic Regression. Wiley. [DOI:10.1002/9781118548387]
36. Kim, D., Park, S., & Lee, J. (2018). Integrating tree-based ensembles with linear models for prediction: A case study in mechanical vibrations. Mechanical Systems and Signal Processing, 102, 120-137. [DOI:10.1016/j.ymssp.2017.07.021]
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.