A hybrid model for evaluating the accuracy  of failure forecasts in ship power plants

Vladimir Vychuzhanin; Alexey Vychuzhanin

Journal: Volume 31, No. 1, 2026

Pages: 44 – 59

DOI: https://doi.org/10.62660/bcstu/1.2026.44

494 Views

A hybrid model for evaluating the accuracy of failure forecasts in ship power plants

Vladimir Vychuzhanin, Alexey Vychuzhanin

Received 01.10.2025

Revised 03.02.2026

Accepted 16.03.2026

Published 08.04.2026

Abstract

The growing complexity of ship power plants (SPP) and the heterogeneity of diagnostic data have made it increasingly difficult to ensure reliable failure forecasting and maintain operational safety. The purpose of this study was to analyse the correspondence between predicted and actual failures in SPP diagnostics using a comprehensive approach that combines knowledge-based methods, probabilistic modelling, and simulation experiments, and to test the proposed methodology by applying the developed model. The research integrated Case-Based Reasoning (CBR), probabilistic modelling, and simulation-based degradation analysis within a unified framework. Using diagnostic data from 150 operational cases of typical SPPs (main engine, generator, pump, cooling, and power systems), the model’s forecasting accuracy was quantitatively compared with baseline approaches, including classical CBR, adaptive CBR, ARIMA, and Decision Tree models. The integrated approach achieved the best performance (Root Mean Square Error = 0.32, R² = 0.93), reducing average error by 30-50% relative to classical methods. Each component of the hybrid framework contributed distinctly: the CBR layer ensured contextual consistency, probabilistic modelling reduced uncertainty by ≈ 20%, and simulation-based analysis increased stability under incomplete or noisy data by ≈ 15%. At the subsystem level, the greatest improvements were observed for the main engine (root mean square error reduction by 46%) and the pump system (by 39%), confirming the model’s adaptability to variable operating conditions. Robustness tests with 10-20% missing or perturbed input data demonstrated sustained accuracy (R² > 0.90), validating the model’s resilience and practical applicability. The proposed methodology has practical value for improving the efficiency of maintenance and reliability of ship power systems, as it provides accurate, interpretable, and noise-resistant equipment failure prediction

Keywords

intelligent diagnostics; reliability assessment; case-based reasoning; simulation modelling; technical condition forecasting; Bayesian networks; adaptive model

References

Arias Chao, M., Kulkarni, C., Goebel, K., & Fink, O. (2020). Fusing physics-based and deep learning models for prognostics. ArXiv. doi: 10.48550/arXiv.2003.00732 .
Farid, M. (2022). Data-driven method for real-time prediction and uncertainty quantification of fatigue failure under stochastic loading using artificial neural networks and Gaussian process regression. International Journal of Fatigue, 155, article number 106415. doi: 10.1016/j.ijfatigue.2021.106415.
Karatuğ, Ç., & Arslanoğlu, Y. (2022). Development of condition-based maintenance strategy for fault diagnosis for ship engine systems. Ocean Engineering, 256, article number 111515. doi: 10.1016/j.oceaneng.2022.111515.
Karatuğ, Ç., Arslanoğlu, Y., & Soares, C.G. (2023). Review of maintenance strategies for ship machinery systems. Journal of Marine Engineering & Technology, 22(5), 233-247. doi: 10.1080/20464177.2023.2180831.
Liu, Y., Liu, Z., Zuo, H., Jiang, H., Li, P., & Li, X. (2022). A DLSTM-network-based approach for mechanical remaining useful life prediction. Sensors, 22(15), article number 5680. doi: 10.3390/s22155680.
Maione, F., Lino, P., Maione, G., & Giannino, G. (2024). A machine learning framework for condition-based maintenance of marine diesel engines: A case study. Algorithms, 17(9), article number 411. doi: 10.3390/ a17090411 .
Marandi, S., Hu, Y.-S., & Modarres, M. (2025). Complex system diagnostics using a knowledge graph-informed and large language model-enhanced framework. ArXiv. doi: 10.48550/arXiv.2505.21291 .
Moon, H., & Choi, J. (2021). Hierarchical spline for time series forecasting: An application to naval ship engine failure rate. Authorea. doi: 10.22541/au.159969715.57074848.
Neykov, N., & Stefanova, S. (2023). Using case-based reasoning in system diagnostics and maintenance. In X.S. Yang, S. Sherratt, N. Dey & A. Joshi (Eds.), Proceedings of seventh international congress on information and communication technology (pp. 305-312). Singapore: Springer. doi: 10.1007/978-981-19-2394-4_28 .
Orhan, M.F., & Celik, M. (2023). A literature review and future research agenda on fault detection and diagnosis studies in marine machinery systems. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 238(1), 3-21. doi: 10.1177/14750902221149291 .
Pajak, M., Kluczyk, M., Muślewski, Ł., Lisjak, D., & Kolar, D. (2023). Ship diesel engine fault diagnosis using data science and machine learning. Electronics, 12(18), article number 3860. doi: 10.3390/electronics12183860.
Rigas, S., Tzouveli, P., & Kollias, S. (2024). An end-to-end deep learning framework for fault detection in marine machinery. Sensors, 24(16), article number 5310. doi: 10.3390/s24165310.
Shi, Z., & Chehade, A. (2021). A dual-LSTM framework combining change point detection and remaining useful life prediction. Reliability Engineering & System Safety, 205, article number 107257. doi: 10.1016/j.ress.2020.107257 .
Tveten, M., & Stakkeland, M. (2024). Fault detection in propulsion motors in the presence of concept drift. ArXiv. doi: 10.48550/arXiv.2406.08030 .
Vizentin, G., Vukelic, G., Murawski, L., Recho, N., & Orovic, J. (2020). Marine propulsion system failures – a review. Journal of Marine Science and Engineering, 8(9), article number 662. doi: 10.3390/jmse8090662 .
Vychuzhanin, V.V., & Rudnichenko, N.D. (2014). Assessment of risks structurally and functionally complex technical systems. Eastern-European Journal of Enterprise Technologies, 1(2(67)), 18-22. doi: 10.15587/1729 4061.2014.19846 .
Vychuzhanin, V.V., & Vychuzhanin, A. (2025). Stochastic models and methods for diagnostics, assessment, and prediction of the technical condition of complex critical systems. Lviv-Torun: Liha-Pres. doi: 10.36059/978-966-397-457-6 .
Wang, J., Cao, H., Cui, Z., Ai, Z., & Jiang, K. (2023). Intelligent fault diagnosis of marine diesel engines based on efficient channel attention-improved convolutional neural networks. Processes, 11(12), article number 3360. doi: 10.3390/pr11123360.
Zhao, Y., Wang, S., & Chen, N. (2022). Thermal fault diagnosis of marine diesel engine based on LSTM neural network algorithm. Vibroengineering Procedia, 41, 198-203. doi: 10.21595/vp.2022.22515 .
Zhu, G., Huang, L., Yin, J., Gai, W., & Wei, L. (2023). Multiple faults diagnosis for ocean-going marine diesel engines based on different neural network algorithms. Science Progress, 106(4). doi: 10.1177/00368504231212765 .

Suggested citation

Vychuzhanin, V., & Vychuzhanin, A. (2026). A hybrid model for evaluating the accuracy of failure forecasts in ship power plants. Bulletin of Cherkasy State Technological University, 31(1), 44-59. https://doi.org/10.62660/bcstu/1.2026.44

[1] Arias Chao, M., Kulkarni, C., Goebel, K., & Fink, O. (2020). Fusing physics-based and deep learning models for prognostics. ArXiv. doi: 10.48550/arXiv.2003.00732 .

[2] Farid, M. (2022). Data-driven method for real-time prediction and uncertainty quantification of fatigue failure under stochastic loading using artificial neural networks and Gaussian process regression. International Journal of Fatigue, 155, article number 106415. doi: 10.1016/j.ijfatigue.2021.106415.

[3] Karatuğ, Ç., & Arslanoğlu, Y. (2022). Development of condition-based maintenance strategy for fault diagnosis for ship engine systems. Ocean Engineering, 256, article number 111515. doi: 10.1016/j.oceaneng.2022.111515.

[4] Karatuğ, Ç., Arslanoğlu, Y., & Soares, C.G. (2023). Review of maintenance strategies for ship machinery systems. Journal of Marine Engineering & Technology, 22(5), 233-247. doi: 10.1080/20464177.2023.2180831.

[5] Liu, Y., Liu, Z., Zuo, H., Jiang, H., Li, P., & Li, X. (2022). A DLSTM-network-based approach for mechanical remaining useful life prediction. Sensors, 22(15), article number 5680. doi: 10.3390/s22155680.

[6] Maione, F., Lino, P., Maione, G., & Giannino, G. (2024). A machine learning framework for condition-based maintenance of marine diesel engines: A case study. Algorithms, 17(9), article number 411. doi: 10.3390/ a17090411 .

[7] Marandi, S., Hu, Y.-S., & Modarres, M. (2025). Complex system diagnostics using a knowledge graph-informed and large language model-enhanced framework. ArXiv. doi: 10.48550/arXiv.2505.21291 .

[8] Moon, H., & Choi, J. (2021). Hierarchical spline for time series forecasting: An application to naval ship engine failure rate. Authorea. doi: 10.22541/au.159969715.57074848.

[9] Neykov, N., & Stefanova, S. (2023). Using case-based reasoning in system diagnostics and maintenance. In X.S. Yang, S. Sherratt, N. Dey & A. Joshi (Eds.), Proceedings of seventh international congress on information and communication technology (pp. 305-312). Singapore: Springer. doi: 10.1007/978-981-19-2394-4_28 .

[10] Orhan, M.F., & Celik, M. (2023). A literature review and future research agenda on fault detection and diagnosis studies in marine machinery systems. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 238(1), 3-21. doi: 10.1177/14750902221149291 .

[11] Pajak, M., Kluczyk, M., Muślewski, Ł., Lisjak, D., & Kolar, D. (2023). Ship diesel engine fault diagnosis using data science and machine learning. Electronics, 12(18), article number 3860. doi: 10.3390/electronics12183860.

[12] Rigas, S., Tzouveli, P., & Kollias, S. (2024). An end-to-end deep learning framework for fault detection in marine machinery. Sensors, 24(16), article number 5310. doi: 10.3390/s24165310.

[13] Shi, Z., & Chehade, A. (2021). A dual-LSTM framework combining change point detection and remaining useful life prediction. Reliability Engineering & System Safety, 205, article number 107257. doi: 10.1016/j.ress.2020.107257 .

[14] Tveten, M., & Stakkeland, M. (2024). Fault detection in propulsion motors in the presence of concept drift. ArXiv. doi: 10.48550/arXiv.2406.08030 .

[15] Vizentin, G., Vukelic, G., Murawski, L., Recho, N., & Orovic, J. (2020). Marine propulsion system failures – a review. Journal of Marine Science and Engineering, 8(9), article number 662. doi: 10.3390/jmse8090662 .

[16] Vychuzhanin, V.V., & Rudnichenko, N.D. (2014). Assessment of risks structurally and functionally complex technical systems. Eastern-European Journal of Enterprise Technologies, 1(2(67)), 18-22. doi: 10.15587/1729 4061.2014.19846 .

[17] Vychuzhanin, V.V., & Vychuzhanin, A. (2025). Stochastic models and methods for diagnostics, assessment, and prediction of the technical condition of complex critical systems. Lviv-Torun: Liha-Pres. doi: 10.36059/978-966-397-457-6 .

[18] Wang, J., Cao, H., Cui, Z., Ai, Z., & Jiang, K. (2023). Intelligent fault diagnosis of marine diesel engines based on efficient channel attention-improved convolutional neural networks. Processes, 11(12), article number 3360. doi: 10.3390/pr11123360.

[19] Zhao, Y., Wang, S., & Chen, N. (2022). Thermal fault diagnosis of marine diesel engine based on LSTM neural network algorithm. Vibroengineering Procedia, 41, 198-203. doi: 10.21595/vp.2022.22515 .

[20] Zhu, G., Huang, L., Yin, J., Gai, W., & Wei, L. (2023). Multiple faults diagnosis for ocean-going marine diesel engines based on different neural network algorithms. Science Progress, 106(4). doi: 10.1177/00368504231212765 .