Volume 15 • Issue 1 • PP: 50–61 • 2027
Robust Estimation of Component Cost-Risk Indices in a CODLAG Naval Propulsion Digital Shadow
Open Access & Copyright
© 2027 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
View PDF Abstract
Maintenance-economic studies often convert condition indicators into apparent costs without verifying whether the resulting targets are independent of the model inputs. This can produce exceptionally high but operationally misleading accuracy. We formulate component-level estimation for a COmbined Diesel-eLectric And Gas (CODLAG) propulsion plant as a leakage-resistant digital-shadow problem. The primary dataset is the public UCI naval propulsion dataset: 11,934 steady-state observations generated by a calibrated numerical frigate simulator across nine speed settings, 51 compressor-health states, and 26 turbine-health states. Because it contains neither monetary maintenance records nor live vessel telemetry, the outputs are explicitly defined as dimensionless compressor and turbine cost-risk indices rather than currency costs. Health coefficients and every target-derived quantity are excluded from predictors. Models are tuned by three-fold grouped inner validation and assessed by five-fold outer validation in which all observations sharing a degradation pair remain in the same fold. Extra Trees achieved an aggregate cost-risk RMSE of 0.0222 (95% CI half-width 0.0049) and R2 of 0.9886 (95% CI half-width 0.0049) under nominal interpolation. However, combined noise, missingness, calibration bias, and channel loss reduced R2 to 0.6335 even after corruption-augmented training, while leave-one-speed-regime-out testing produced mean R2 = −0.379. Scenario-matched 90% split-conformal intervals retained 89.5–90.4% empirical coverage by widening from 0.032 nominally to 0.406 under severe corruption. An external NASA C-MAPSS FD001 benchmark yielded RMSE 16.97 cycles and R2 = 0.821 for remaining-useful-life prediction on 100 unseen engines. The study therefore supports robust condition-risk ranking within the simulated envelope, not direct monetary forecasting or autonomous maintenance scheduling. The principal contribution is a transparent validation protocol that exposes target leakage, simulator determinism, sensor-quality sensitivity, and the boundary between a digital shadow and a deployable digital twin.
Keywords
References
[1] R. Ahmad and S. Kamaruddin, “An overview of time-based and condition-based maintenance in industrial applications,” Computers & Industrial Engineering, vol. 63, no. 1, pp. 135–149, 2012.
[2] V. J. Jimenez, N. Bouhmala, and A. H. Gausdal, “De-veloping a predictive maintenance model for vessel ma-chinery,” Journal of Ocean Engineering and Science, vol. 5, no. 4, pp. 358–386, 2020.
[3] D. Kimera and F. N. Nangolo, “Maintenance optimiza-tion for marine mechanical systems,” Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, vol. 234, no. 2, pp. 446–462, 2020.
[4] H. Ye, W. Zhu, H. Li, W. Ji, C. G. Soares, and J. Wang, “Failure warning for offshore wind turbines based on Autoregressive models,” Ocean Engineering, vol. 332, p. 121448, 2025.
[5] J. Luo, X. Luo, X. Ma, Y. Zan, and X. Bai, “An integrated condition-based opportunistic maintenance framework for offshore wind farms,” Reliability Engi-neering & System Safety, vol. 256, p. 110701, 2025.
[6] F. Ying, L. Huang, M. Song, and Y. Fu, “Optimization of an opportunistic maintenance strategy for wind turbines based on subsystem fault chains,” Ocean Engineering, vol. 339, p. 122106, 2025.
[7] I. Errandonea, S. Beltrán, and S. Arrizabalaga, “Digital twin for maintenance: A literature review,” Computers in Industry, vol. 123, p. 103316, 2020.
[8] F. Tao, B. Xiao, Q. Qi, J. Cheng, and P. Ji, “Digital twin modeling,” Journal of Manufacturing Systems, vol. 64, pp. 372–389, 2022.
[9] B. Schleich, N. Anwer, L. Mathieu, and S. Wartzack, “Shaping the digital twin for design and production en-gineering,” CIRP Annals, vol. 66, no. 1, pp. 141–144, 2017.
[10] B. R. Barricelli, E. Casiraghi, and D. Fogli, “A survey on digital twin: Definitions, characteristics, applica-tions, and design implications,” IEEE Access, vol. 7, pp. 167 653–167 671, 2019.
[11] A. Coraddu, L. Oneto, A. Ghio, S. Savio, D. Anguita, and M. Figari, “Machine learning approaches for im-proving condition-based maintenance of naval propul-sion plants,” Proceedings of the Institution of Mechan-ical Engineers, Part M, vol. 230, no. 1, pp. 136–153, 2016.
[12] F. Cipollini, L. Oneto, A. Coraddu, A. J. Murphy, and D. Anguita, “Condition-based maintenance of naval propulsion systems: Data analysis with minimal feed-back,” Reliability Engineering & System Safety, vol. 177, pp. 12–23, 2018.
[13] A. S. Kalafatelis, N. Nomikos, A. Karditsa, and P. Trakadas, “Towards predictive maintenance in the maritime industry: A component-based overview,” Jour-nal of Marine Science and Engineering, vol. 13, p. 425, 2025.
[14] F. Maione, P. Lino, G. Maione, and G. Giannino, “A machine learning framework for condition-based main-tenance of marine diesel engines: A case study,” Algo-rithms, vol. 17, no. 9, p. 411, 2024.
[15] M. Acanfora, L. Mocerino, G. Giannino, and U. Cam-pora, “A comparison between digital-twin-based methodologies for predictive maintenance of marine diesel engine,” Proceedings of SPEEDAM, pp. 1254–1259, 2024.
[16] H. Zhang, G. Li, L. I. Hatledal, Y. Chu, A. Ellefsen, and P. Han, “A digital twin of the research vessel gun-nerus for lifecycle services: Outlining key technologies,” IEEE Robotics & Automation Magazine, vol. 30, no. 3, pp. 6–19, 2023.
[17] A. Hasan, T. Asfihani, O. Osen, and R. T. Bye, “Lever-aging digital twins for fault diagnosis in autonomous ships,” Ocean Engineering, vol. 292, p. 116546, 2024.
[18] International Organization for Standardization, “ISO 23247-1:2021, Automation systems and integration—Digital twin framework for manufacturing—Part 1: Overview and general principles,” International Organi-zation for Standardization, Tech. Rep., 2021.
[19] International Organization for Standardization, “ISO 13374-1:2003, Condition monitoring and diagnostics of machines—Data processing, communication and presentation—Part 1: General guidelines,” International Organization for Standardization, Tech. Rep., 2003.
[20] International Organization for Standardization, “ISO 55000:2014, Asset management—Overview, principles and terminology,” International Organization for Stan-dardization, Tech. Rep., 2014.
[21] Y. Cai, R. H. Teunter, and B. de Jonge, “A data-driven approach for condition-based maintenance optimiza-tion,” European Journal of Operational Research, vol. 311, no. 3, pp. 1036–1049, 2023.
[22] A. Coraddu, L. Oneto, A. Ghio, S. Savio, D. Anguita, and M. Figari, “Condition Based Maintenance of Naval Propulsion Plants,” UCI Machine Learning Repository, 2014.
[23] A. Saxena and K. Goebel, “Turbofan Engine Degrada-tion Simulation Data Set,” NASA Ames Prognostics Data Repository, Moffett Field, CA, 2008.
[24] A. Saxena, K. Goebel, D. Simon, and N. Eklund, “Dam-age propagation modeling for aircraft engine run-to-failure simulation,” in Proceedings of the 1st Interna-tional Conference on Prognostics and Health Manage-ment, 2008.
[25] A. E. Hoerl and R. W. Kennard, “Ridge regression: Biased estimation for nonorthogonal problems,” Tech-nometrics, vol. 12, no. 1, pp. 55–67, 1970.
[26] L. Breiman, “Random forests,” Machine Learning, vol. 45, pp. 5–32, 2001.
[27] P. Geurts, D. Ernst, and L. Wehenkel, “Extremely ran-domized trees,” Machine Learning, vol. 63, pp. 3–42, 2006.
[28] J. Lei, M. G’Sell, A. Rinaldo, R. J. Tibshirani, and L. Wasserman, “Distribution-free predictive inference for regression,” Journal of the American Statistical As-sociation, vol. 113, no. 523, pp. 1094–1111, 2018.
[29] Y. Lei, N. Li, L. Guo, N. Li, T. Yan, and J. Lin, “Ma-chinery health prognostics: A systematic review from data acquisition to rul prediction,” Mechanical Systems and Signal Processing, vol. 104, pp. 799–834, 2018.
[30] A. A. Murtaza, A. Saher, M. H. Zafar, S. K. R. Moosavi, M. F. Aftab, and F. Sanfilippo, “Paradigm shift for predictive maintenance and condition monitoring from industry 4.0 to industry 5.0,” Results in Engineering, vol. 22, p. 102935, 2024.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.