Development of a Residual-Based Anomaly Detection System with Persistence Logic for Marine Diesel Generators
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
https://orcid.org/0009-0001-4660-4892
Edwin Puertas
Edwin Paipa-Sanabria
Juan C Martinez-Santos
Abstract
Diesel generator engines (DGEs) are critical safety and mission assets for naval platforms, supporting continuous electrical power for navigation, communications, habitability, and training operations. In practice, maintenance of auxiliary generation on training ships still relies predominantly on time-based tasks complemented by reactive corrective actions, despite the increasing availability of onboard operational data. This paper presents the development of a residual-based anomaly detection system with persistence logic for the diesel generator engines of a Colombian Navy training ship, focusing on the auxiliary generator sets as a case study. The proposed approach targets early detection of abnormal thermal behavior under scarce fault labels by combining (i) data-quality gates and traceable preprocessing, including plausibility filtering and multivariate inconsistency treatment during cleaning, (ii) target and feature definition for normal-behavior regression, (iii) residual-based monitoring with EWMA smoothing and time-varying control limits, and (iv) persistence rules for sustained event declaration. The methodology is organized as an end-to-end workflow aligned with CRISP-DM and a PHM detection-first strategy. Because historical fault labels are limited and not reliably aligned in time, offline evaluation combines predictive assessment on held-out healthy data with Monte Carlo validation under simulated fault scenarios. Results on historical generator monitoring data from the ship show that the normal-behavior models provide stable residual baselines for key thermal variables, while the detector can identify simulated abnormal scenarios across different severity levels. This paper provides a traceable workflow for anomaly detection in sparse and irregular shipboard monitoring data, discusses the limitations imposed by manual logs and scarce labels, and outlines future work toward health indexing, operational feedback, and more robust diagnostic support
##plugins.themes.bootstrap3.article.details##
Anomaly detection, Marine diesel generators, Residual-based monitoring, EWMA, Shipboard system
Awaisi, K. S., Ye, Q., & Sampalli, S. (2025). Set: A shared-encoder transformer scheme for multi-sensor, multiclass fault classification in industrial iot. IEEE Transactions on Machine Learning in Communications and Networking.
Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1–58. Retrieved from https://doi .org/10.1145/1541880.1541882 doi: 10.1145/1541880.1541882
Costa, F. S., Nassar, S. M., & Dantas, M. A. (2022). Focuser: A fog online context-aware up-to-date sensor ranking method. Journal of Sensor and Actuator Networks.
Diedrich, A., & Niggemann, O. (2022). On residual-based diagnosis of physical systems. Engineering Applications of Artificial Intelligence, 109, 104636. doi: 10.1016/j.engappai.2021.104636
Ferezagia, D. V., Kesa, D. D., Sellyra, E. C., Anggara, D., & Lee, C. W. (2025). Control chart approach to monitor and improve production processes: Maximum exponentially weighted moving average using auxiliary variable (av) and multiple measurement (me). Statistics, Optimization and Information Computing.
Isermann, R. (2005). Model-based fault-detection and diagnosis – status and applications. Annual Reviews in Control, 29(1), 71–85. doi: 10.1016/j.arcontrol.2004.12.002
Jardine, A. K. S., Lin, D., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7), 1483–1510. Retrieved from https://doi.org/10.1016/j.ymssp.2005.09.012 doi: 10.1016/j.ymssp.2005.09.012
Jarosz-Kozyro, A., & Baranowski, J. (2025). Recent advances in data-driven methods for degradation modeling across applications. Processes.
Kim, Y., Gupta, P., & Steen, S. (2025). A comprehensive review of data processing for ship performance analysis. Applied Ocean Research, 162, 104737. Retrieved from https://doi.org/10.1016/j.apor.2025.104737 doi: 10.1016/j.apor.2025.104737
Kumar, A., & Flores-Cerrillo, J. (2024). Machine learning in python for process and equipment condition monitoring, and predictive maintenance. Online: MLforPSE. Retrieved from https://mlforpse.com/
Lee, J., Kao, H.-A., & Yang, S. (2014). Service innovation and smart analytics for industry 4.0 and big data environment. Procedia CIRP, 16, 3–8. Retrieved from https://doi.org/10.1016/j.procir.2014.02.001 doi: 10.1016/j.procir.2014.02.001
Li, S. C.-X., & Marlin, B. M. (2020). Learning from irregularly-sampled time series: A missing data perspective. In Proceedings of the 37th international conference on machine learning (Vol. 119, pp. 5937–5946). PMLR.
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
Michelena, A ., López, V. C., López, F. L., Arce, E., Mendoza García, J., Suárez-García, A., . . . Quintián, H. (2023). A fault-detection system approach for the optimization of warship equipment replacement parts based on operation parameters. Sensors, 23(7), 3389. Retrieved from https://doi.org/10 .3390/s23073389 doi: 10.3390/s23073389
Montgomery, D. C. (2009). Introduction to statistical quality control (6th ed.). Hoboken, NJ: Wiley.
Park, J., & Oh, J. (2023). A machine learning based predictive maintenance algorithm for ship generator engines using engine simulations and collected ship data. Energy, 285, 129269. Retrieved from https://doi.org/10.1016/j.energy.2023.129269 doi: 10.1016/j.energy.2023.129269
Song, J., & Kim, H. S. (2026). Persistence-based absolute relative error for alarm-centric monitoring under low-frequency manufacturing. Mathematics.
Teng, Z., Yi, X., & Wang, B. (2025). Dynamic relative advantage-driven multi-fault synergistic diagnosis method for motors under imbalanced missing data rates. Journal of Dynamics, Monitoring and Diagnostics.
Vachtsevanos, G., Lewis, F., Roemer, M., Hess, A., & Wu, B. (2006). Intelligent fault diagnosis and prognosis for engineering systems. Hoboken, NJ: Wiley.
Velasco-Gallego, C., & Lazakis, I. (2022). RADIS: A realtime anomaly detection intelligent system for fault diagnosis of marine machinery. Expert Systems with Applications, 204, 117634. Retrieved from https://doi.org/10.1016/j.eswa.2022.117634 doi: 10.1016/j.eswa.2022.117634
Xiao, H., Cao, R., Chen, Z., Hong, C., Wang, J., Yao, M., . . . Luo, T. (2025). Handling missing data in large-scale tbm datasets: Methods, strategies, and applications.
Zhang, Y., & Thorburn, P. J. (2022). Handling missing data in near real-time environmental monitoring: A system and a review of selected methods. Future Generation Computer Systems.