Development of a Remaining Useful Life Prediction Model for Marine Diesel Engine Filtration Systems
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Published
Jun 14, 2026
Joan Suarez
Clara Guimarães
Edwin Paipa
Juan Carlos Martinez-Santos
Edwin Puerta
https://orcid.org/0009-0007-7874-8261
Clara Guimarães
Edwin Paipa
Juan Carlos Martinez-Santos
Edwin Puerta
Abstract
Marine diesel propulsion engines are essential to naval platforms, enabling maneuvering, navigation readiness, and training operations. However, maintenance of propulsion consumables—particularly fuel filtration elements—often remains time-based and corrective despite the growing availability of onboard operational records. This paper presents the development and validation of a Remaining Useful Life (RUL) prediction model for the propulsion engine filtration system of the Colombian Navy (ARC) training ship, aiming to estimate time to replacement for cartridge-based filters.
The proposed approach handles imperfect manual operational data and scarce, non-uniform maintenance labels through a Prognostics and Health Management (PHM) workflow guided by the Cross-Industry Standard Process for Data Mining (CRISP-DM). It combines physics-informed data quality control using plausibility bounds, outlier mitigation, and time-series reconstruction; expert validation of representative operating cycles using a Delphi protocol; and event logging to align filter-replacement actions with gap-aware approximations. It was trained supervised regression models using an automated machine learning (AutoML) strategy implemented in PyCaret and refined through hyperparameter optimization in Optuna. A Random Forest model achieved the best performance, reaching a test root mean squared error (RMSE) of 52.92 hours with a coefficient of determination of 0.921.
##plugins.themes.bootstrap3.article.details##
Keywords
Remaining Useful Life (RUL), Prognostics and Health Management, Predictive Maintenance, Marine Diesel Engines, Fuel Filtration Systems, CRISP-DM, Machine Learning
References
Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th acm sigkdd international conference on knowledge discovery and data mining (pp. 2623–2631). doi: 10.1145/3292500.3330701
Ali, M. (2020). Pycaret: An open source, low-code machine learning library in python. https://www.pycaret.org. (Software)
Ansari, F., Glawar, R., & Nemeth, T. (2019). Prima: A prescriptive maintenance model for cyber-physical production systems. International Journal of Computer Integrated Manufacturing, 32(4–5), 482–503. doi: 10.1080/0951192X.2019.1571236
Asimakopoulos, I. (2023). Data-driven condition monitoring of two-stroke marine diesel engines. Ships and Offshore Structures. doi: 10.1080/17445302.2023.2237302
Cao, H., Xiao, W., Sun, J., & Gan, M.-G. (2024). A hybrid data- and model-driven learning framework for remaining useful life prediction. Engineering Applications of Artificial Intelligence. doi: 10.1016/j.engappai.2024.108557
Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C., & Wirth, R. (2000). Crisp-dm 1.0: Step-by-step data mining guide [Computer software manual].
Dalzochio, J., Kunst, R., Pignaton, E., Binotto, A., Sanyal, S., Favilla, J., & Barbosa, J. (2020). Machine learning and reasoning for predictive maintenance in industry 4.0: Current status and challenges. Computers in Industry, 123, 103298. doi: 10.1016/j.compind.2020.103298
Doctrina de material naval. tomo iii. mantenimiento (Segunda edición ed.) [Computer software manual]. (2022). Bogotá, D.C., Colombia. (Doctrina Naval – Nivel Operacional (DOC. MAT. NAV.), ARC OP4-3.3)
Duan, X., Vasudevan, A., et al. (2022). A data scientific approach towards predictive maintenance applications. In Advances in transdisciplinary engineering. doi: 10.3233/ATDE220148
Fan, A., Sun, S., Hu, Z., Vladimir, N., & Mao, W. (2026). Enhancing transfer learning strategies for ship fuel consumption prediction under data scarcity. Ocean Engineering, 351, 124398. doi: 10.1016/j.oceaneng.2026.124398
Florentino, R. B., & Moura, L. G. L. (2025). The estimation of the remaining useful life of ceramic plates used in iron ore filtration through a reliability model and machine learning methods applied to industrial process variables of a pims. Applied Sciences.
Gulati, R. (2013). Maintenance and reliability best practices (3rd ed.). New York, NY: Industrial Press.
Hagmeyer, S., & Zeiler, P. (2023). A comparative study on methods for fusing data-driven and physics-based approaches for rul prediction in filtration processes. IEEE Access. doi: 10.1109/ACCESS.2023.3265722
Han, P., Ellefsen, A. L., Li, G., Holmeset, F. T., & Zhang, H. (2021). Fault detection with lstm-based variational autoencoder for maritime components. IEEE Sensors Journal, 21(19), 21903–21912. doi: 10.1109/JSEN.2021.3105226
Hasson, F., Keeney, S., & McKenna, H. (2000). Research guidelines for the delphi survey technique. Journal of Advanced Nursing, 32(4), 1008–1015. doi: 10.1046/j.1365-2648.2000.t01-1-01567.x
International Maritime Organization. (2010). International Safety Management (ISM) Code and Guidelines on Implementation of the ISM Code. (IMO, London)
Jeon, M., Noh, Y., et al. (2021). Data gap analysis of ship and maritime data using meta learning. Applied Soft Computing. doi: 10.1016/j.asoc.2020.107048
Kalafatelis, A. S., Nomikos, N., Giannopoulos, A., Alexandridis, G., Karditsa, A., & Trakadas, P. (2025). Towards predictive maintenance in the maritime industry: A component-based overview. Journal of Marine Science and Engineering.
Kim, D., Antariksa, G., Handayani, M. P., Lee, S., & Lee, J. (2021). Explainable anomaly detection framework for maritime main engine sensor data. Sensors, 5200.
Kirketerp-Møller, T., Hyldgaard, M. W., Cai, J., Dodis, A.-I., & Rytter, N. G. M. (2025). Data-driven predictive maintenance for two-stroke marine diesel engines using machine learning and mlops. Journal of Ocean Engineering and Science. doi: 10.1016/j.joes.2025.11.011
Kocak, G. (2023). Condition monitoring and fault diagnosis of a marine diesel engine with machine learning techniques. Pomorstvo. doi: 10.31217/p.37.1.4
Kumar, A., & Flores-Cerrillo, J. (2024). Machine learning in Python for process and equipment condition monitoring, and predictive maintenance: From data to process insights (1st ed.). MLforPSE. Retrieved 2026-03-01, from https://leanpub.com/ML-Python-for-PM-PdM (First published January 2024)
Llamas Reinoso, J., Martinez-Santos, J. C., & Puertas, E. (2026, January). Main machinery operational data of the training ship arc gloria (2021–2025). Zenodo. Retrieved from https://doi .org/10.5281/zenodo.18307281 doi: 10.5281/zenodo.18307281
Michalski, M. A. D. C., et al. (2025). A multi-criteria framework for selecting machine learning techniques in predictive maintenance. IEEE Access. doi: 10.1109/ACCESS.2025.3604754
Mwangi, M. G.W., Park, M. H., Chun, K.W., Noh, J. H., Kim, C., & Lee, W. J. (2025). Hybrid ai-driven condition monitoring and rul forecasting for multi-fault diagnosis in two-stroke marine diesel engines. Journal of Ocean Engineering and Science.
Pan, Y., Kang, S., Kong, L.,Wu, J., Yang, Y., & Zuo, H. (2025). Remaining useful life prediction methods of equipment components based on deep learning for sustainable manufacturing: a literature review. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 39, e4. doi: 10.1017/S0890060424000271
Pugalenthi, K., Park, H., Hussain, S., & Raghavan, N. (2021). Hybrid particle filter trained neural network for prognosis of lithium-ion batteries. IEEE Access, 135132–135143.
Quan, R., Cheng, G., Guan, X., Zhang, G., & Quan, J. (2025). A ho-bigru-transformer based pemfc degradation prediction method under different current conditions. Renewable Energy, 124132.
Shi, Z.,Wang, Z., & Ding, H. (2026). Multi-source data fusion for marine four-stroke diesel engine fault diagnosis: An adaptive weight transfer learning framework. Energy Conversion and Management, 353, 121194. doi: 10.1016/j.enconman.2026.121194
Shifat, T. A., Yasmin, R., Hur, J.-W., & Park, H. (2021). A data driven rul estimation framework of electric motor using machine learning. Energies. doi: 10.3390/en14113156
Sielaff, L., Lucke, D., & Wolf, Y. (2024). A reference model for predictive maintenance model development. In Procedia cirp.
Sun, J., Ren, H., et al. (2024). Fusion of multi-layer attention mechanisms and cnn-lstm for time-series prognostics in marine applications. Journal of Marine Science and Engineering. doi: 10.3390/jmse12060990
Upadrashta, D., &Wijaya, T. (2025). Ai/ml based anomaly detection and fault diagnosis of turbocharged marine diesel engines: Experimental study on engine of an operational vessel. Information. doi: 10.3390/info17010016
Velasco-Gallego, C., & Lazakis, I. (2023). Mar-rul: A remaining useful life prediction approach for fault prognostics of marine machinery. Applied Ocean Research, 140, 103734. doi: 10.1016/j.apor.2023.103734
Zeiler, P., & Hagmeyer, S. (2023). A comparative study on methods for fusing data-driven and physics-based models for hybrid remaining useful life prediction of air filters. IEEE Access, 35737–35753.
Zhang, J., Jiang, Y., Wu, S., Li, X., Luo, H., & Yin, S. (2022). Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism. Reliability Engineering & System Safety, 221, 108297. doi: 10.1016/j.ress.2021.108297
Zio, E. (2022). Prognostics and health management (phm): Where are we and where do we (need to) go in theory and practice. Reliability Engineering & System Safety, 218, 108119. doi: 10.1016/j.ress.2021.108119
Ali, M. (2020). Pycaret: An open source, low-code machine learning library in python. https://www.pycaret.org. (Software)
Ansari, F., Glawar, R., & Nemeth, T. (2019). Prima: A prescriptive maintenance model for cyber-physical production systems. International Journal of Computer Integrated Manufacturing, 32(4–5), 482–503. doi: 10.1080/0951192X.2019.1571236
Asimakopoulos, I. (2023). Data-driven condition monitoring of two-stroke marine diesel engines. Ships and Offshore Structures. doi: 10.1080/17445302.2023.2237302
Cao, H., Xiao, W., Sun, J., & Gan, M.-G. (2024). A hybrid data- and model-driven learning framework for remaining useful life prediction. Engineering Applications of Artificial Intelligence. doi: 10.1016/j.engappai.2024.108557
Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C., & Wirth, R. (2000). Crisp-dm 1.0: Step-by-step data mining guide [Computer software manual].
Dalzochio, J., Kunst, R., Pignaton, E., Binotto, A., Sanyal, S., Favilla, J., & Barbosa, J. (2020). Machine learning and reasoning for predictive maintenance in industry 4.0: Current status and challenges. Computers in Industry, 123, 103298. doi: 10.1016/j.compind.2020.103298
Doctrina de material naval. tomo iii. mantenimiento (Segunda edición ed.) [Computer software manual]. (2022). Bogotá, D.C., Colombia. (Doctrina Naval – Nivel Operacional (DOC. MAT. NAV.), ARC OP4-3.3)
Duan, X., Vasudevan, A., et al. (2022). A data scientific approach towards predictive maintenance applications. In Advances in transdisciplinary engineering. doi: 10.3233/ATDE220148
Fan, A., Sun, S., Hu, Z., Vladimir, N., & Mao, W. (2026). Enhancing transfer learning strategies for ship fuel consumption prediction under data scarcity. Ocean Engineering, 351, 124398. doi: 10.1016/j.oceaneng.2026.124398
Florentino, R. B., & Moura, L. G. L. (2025). The estimation of the remaining useful life of ceramic plates used in iron ore filtration through a reliability model and machine learning methods applied to industrial process variables of a pims. Applied Sciences.
Gulati, R. (2013). Maintenance and reliability best practices (3rd ed.). New York, NY: Industrial Press.
Hagmeyer, S., & Zeiler, P. (2023). A comparative study on methods for fusing data-driven and physics-based approaches for rul prediction in filtration processes. IEEE Access. doi: 10.1109/ACCESS.2023.3265722
Han, P., Ellefsen, A. L., Li, G., Holmeset, F. T., & Zhang, H. (2021). Fault detection with lstm-based variational autoencoder for maritime components. IEEE Sensors Journal, 21(19), 21903–21912. doi: 10.1109/JSEN.2021.3105226
Hasson, F., Keeney, S., & McKenna, H. (2000). Research guidelines for the delphi survey technique. Journal of Advanced Nursing, 32(4), 1008–1015. doi: 10.1046/j.1365-2648.2000.t01-1-01567.x
International Maritime Organization. (2010). International Safety Management (ISM) Code and Guidelines on Implementation of the ISM Code. (IMO, London)
Jeon, M., Noh, Y., et al. (2021). Data gap analysis of ship and maritime data using meta learning. Applied Soft Computing. doi: 10.1016/j.asoc.2020.107048
Kalafatelis, A. S., Nomikos, N., Giannopoulos, A., Alexandridis, G., Karditsa, A., & Trakadas, P. (2025). Towards predictive maintenance in the maritime industry: A component-based overview. Journal of Marine Science and Engineering.
Kim, D., Antariksa, G., Handayani, M. P., Lee, S., & Lee, J. (2021). Explainable anomaly detection framework for maritime main engine sensor data. Sensors, 5200.
Kirketerp-Møller, T., Hyldgaard, M. W., Cai, J., Dodis, A.-I., & Rytter, N. G. M. (2025). Data-driven predictive maintenance for two-stroke marine diesel engines using machine learning and mlops. Journal of Ocean Engineering and Science. doi: 10.1016/j.joes.2025.11.011
Kocak, G. (2023). Condition monitoring and fault diagnosis of a marine diesel engine with machine learning techniques. Pomorstvo. doi: 10.31217/p.37.1.4
Kumar, A., & Flores-Cerrillo, J. (2024). Machine learning in Python for process and equipment condition monitoring, and predictive maintenance: From data to process insights (1st ed.). MLforPSE. Retrieved 2026-03-01, from https://leanpub.com/ML-Python-for-PM-PdM (First published January 2024)
Llamas Reinoso, J., Martinez-Santos, J. C., & Puertas, E. (2026, January). Main machinery operational data of the training ship arc gloria (2021–2025). Zenodo. Retrieved from https://doi .org/10.5281/zenodo.18307281 doi: 10.5281/zenodo.18307281
Michalski, M. A. D. C., et al. (2025). A multi-criteria framework for selecting machine learning techniques in predictive maintenance. IEEE Access. doi: 10.1109/ACCESS.2025.3604754
Mwangi, M. G.W., Park, M. H., Chun, K.W., Noh, J. H., Kim, C., & Lee, W. J. (2025). Hybrid ai-driven condition monitoring and rul forecasting for multi-fault diagnosis in two-stroke marine diesel engines. Journal of Ocean Engineering and Science.
Pan, Y., Kang, S., Kong, L.,Wu, J., Yang, Y., & Zuo, H. (2025). Remaining useful life prediction methods of equipment components based on deep learning for sustainable manufacturing: a literature review. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 39, e4. doi: 10.1017/S0890060424000271
Pugalenthi, K., Park, H., Hussain, S., & Raghavan, N. (2021). Hybrid particle filter trained neural network for prognosis of lithium-ion batteries. IEEE Access, 135132–135143.
Quan, R., Cheng, G., Guan, X., Zhang, G., & Quan, J. (2025). A ho-bigru-transformer based pemfc degradation prediction method under different current conditions. Renewable Energy, 124132.
Shi, Z.,Wang, Z., & Ding, H. (2026). Multi-source data fusion for marine four-stroke diesel engine fault diagnosis: An adaptive weight transfer learning framework. Energy Conversion and Management, 353, 121194. doi: 10.1016/j.enconman.2026.121194
Shifat, T. A., Yasmin, R., Hur, J.-W., & Park, H. (2021). A data driven rul estimation framework of electric motor using machine learning. Energies. doi: 10.3390/en14113156
Sielaff, L., Lucke, D., & Wolf, Y. (2024). A reference model for predictive maintenance model development. In Procedia cirp.
Sun, J., Ren, H., et al. (2024). Fusion of multi-layer attention mechanisms and cnn-lstm for time-series prognostics in marine applications. Journal of Marine Science and Engineering. doi: 10.3390/jmse12060990
Upadrashta, D., &Wijaya, T. (2025). Ai/ml based anomaly detection and fault diagnosis of turbocharged marine diesel engines: Experimental study on engine of an operational vessel. Information. doi: 10.3390/info17010016
Velasco-Gallego, C., & Lazakis, I. (2023). Mar-rul: A remaining useful life prediction approach for fault prognostics of marine machinery. Applied Ocean Research, 140, 103734. doi: 10.1016/j.apor.2023.103734
Zeiler, P., & Hagmeyer, S. (2023). A comparative study on methods for fusing data-driven and physics-based models for hybrid remaining useful life prediction of air filters. IEEE Access, 35737–35753.
Zhang, J., Jiang, Y., Wu, S., Li, X., Luo, H., & Yin, S. (2022). Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism. Reliability Engineering & System Safety, 221, 108297. doi: 10.1016/j.ress.2021.108297
Zio, E. (2022). Prognostics and health management (phm): Where are we and where do we (need to) go in theory and practice. Reliability Engineering & System Safety, 218, 108119. doi: 10.1016/j.ress.2021.108119
Section
Technical Papers