GaussianCopula-Based Synthetic Data Generation for Turbocharger Fault Scenario Simulation and SFOC Degradation Modelling in Two-Stroke Marine Diesel Engines
Source abstract
Abstract
This paper proposes a data-driven framework for simulating turbocharger (TC) failure scenarios and modelling specific fuel oil consumption (SFOC) degradation in two-stroke low-speed marine diesel engines. A GaussianCopula model was fitted to the joint distribution of fifteen variables, using approximately eleven months of operational sensor data (n = 480 clean records, 4 h interval, January–December 2014) taken from a container ship. Three physically motivated failure scenarios were produced: turbine blade fouling, bearing wear and compressor surge. Predictive models trained on the real dataset achieved R2 = 0.9998 for TC RPM and R2 = 0.984 for fuel flow when using Gradient Boosting with 5-fold cross-validation. Feature importance analysis showed that the dominant determinants of TC speed were scavenging air intake pressure (35.3%) and engine power (MCR, 31.3%). Shaft power (45.5%) and TC RPM (19.3%) together explained most of the fuel consumption variance. Simulated failure scenarios produced SFOC increases of +6.6% (fouling), +9.6% (surge), and +13.3% (bearing wear) when compared to a normal operating baseline of 202 g/kWh, which is in line with published empirical data from MAN B&W engine performance curves. An IsolationForest anomaly detector trained only on normal operating samples flagged failure scenario records at a rate of 17.5–23.7%, which demonstrates that moderate-sensitivity early warning detection is feasible from routine sensor streams. The results show that TC condition monitoring could serve as a leading indicator of fuel-efficiency degradation. This has significant implications for condition-based maintenance planning and CII (Carbon Intensity Indicator) compliance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Combustion Engine Technologies · Machine Fault Diagnosis Techniques · Technical Engine Diagnostics and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Maritime Vocational School, Bandirma Onyedi Eylul University, Bandırma 10200, Balıkesir, Türkiye
References (35)
Show source-provided references
1. MAN Energy Solutions (2024). Marine Engine Programme 2024, MAN Energy Solutions.
2. Pestana-Viana, D., Gutiérrez, R.H., de Lima, A.A., e Silva, F.L., Vaz, L., de M. Prego, T., and Monteiro, U.A. (2018). Application of machine learning in diesel engines fault identification. Proceedings of the International Conference on Rotor Dynamics, Springer International Publishing.10.1007/978-3-319-99268-6_6 ↗
3. Viana, D.P., de Sá Só Martins, D.H., de Lima, A.A., Silva, F., Pinto, M.F., Gutiérrez, R.H., Vaz, L.A., de M. Prego, T., Monteiro, U.A., and Haddad, D.B. (2023). Diesel engine fault prediction using artificial intelligence regression methods. Machines, 11.10.3390/machines11050530 ↗
4. Predicting faults in diesel engines with kernel machines regression techniques10.1007/s10489-025-06643-7 ↗
5. Data-driven model for marine engine fault diagnosis using in-cylinder pressure signals10.1080/20464177.2024.2432777 ↗
6. Wang, J., Cao, H., Cui, Z., Ai, Z., and Jiang, K. (2023). Intelligent fault diagnosis of marine diesel engines based on efficient channel attention-improved convolutional neural networks. Processes, 11.10.3390/pr11123360 ↗
7. Data-driven open-set fault classification of residual data using Bayesian filtering10.1109/TCST.2020.2997648 ↗
8. Guan, H., Hu, G., Du, H., Yin, Y., and He, W. (2025). A reliability fault diagnosis method for diesel engines based on the belief rule base with data-driven initialization. Sensors, 25.10.3390/s25165091 ↗
9. A literature review and future research agenda on fault detection and diagnosis studies in marine machinery systems
10. A novel methodology for marine dual fuel engines sensors diagnostics and health management10.1177/1468087421998635 ↗
11. Chen, J., Wang, Z., Wang, B., Yao, C., Song, E., and Sun, K. (2025). Fault simulation and analysis of marine methanol-diesel dual-fuel engines. Proceedings of the 2025 IEEE 20th Conference on Industrial Electronics and Applications (ICIEA), IEEE.10.1109/ICIEA65512.2025.11149235 ↗
12. Marine diesel-generator model for voltage and frequency variation analysis during fault scenarios
13. Impact of late and early fuel injection on main engine efficiency and exhaust gas emissions
14. Fault effect analysis of the exhaust manifold leakage for a turbocharged spark ignition engine10.1177/0954407014521175 ↗
15. Reliability assessment of main engine subsystems considering turbocharger failure as a case study
16. Impact of defective turbocharging system on the safety and reliability of large marine diesel engine
17. Knežević, V., Orović, J., Stazić, L., and Čulin, J. (2020). Fault tree analysis and failure diagnosis of marine diesel engine turbocharger system. J. Mar. Sci. Eng., 8.10.3390/jmse8121004 ↗
18. Integrated simulation framework for assessing turbocharger fault effects on diesel-engine performance and operability10.1061/(ASCE)EY.1943-7897.0000673 ↗
19. Wang, J., Wen, H., Qian, H., Guo, J., Zhu, J., Dong, J., and Shen, H. (2023). Typical fault modeling and vibration characteristics of the turbocharger rotor system. Machines, 11.10.3390/machines11020311 ↗
20. Rahat, M., Pashami, S., Nowaczyk, S., and Kharazian, Z. (2020). Modeling turbocharger failures using Markov process for predictive maintenance. Proceedings of the 30th European Safety and Reliability Conference (ESREL2020) & 15th Probabilistic Safety Assessment and Management Conference (PSAM15), European Safety and Reliability Association.10.3850/978-981-14-8593-0_4295-cd ↗
21. Chan, T.K., and Chin, C.S. (2016). Data analysis to predictive modeling of marine engine performance using machine learning. Proceedings of the IEEE TENCON—Technologies for Smart Nation, IEEE.10.1109/TENCON.2016.7848391 ↗
22. Patki, N., Wedge, R., and Veeramachaneni, K. (2016). The synthetic data vault. Proceedings of the IEEE International Conference on Data Science and Advanced Analytics (DSAA), IEEE.10.1109/DSAA.2016.49 ↗
23. Fonctions de répartition à n dimensions et leurs marges
24. MAN Energy Solutions (2021). Service Letter SL2021-714/PXN: Low-Load Operation—5% to 40% Engine Load, MAN Energy Solutions.
25. MAN Diesel & Turbo (2011). Service Letter SL2011-544/MTS: Low-Load Operation, MAN Diesel & Turbo.
26. MAN Diesel & Turbo (2010). Turbocharger Cut-Out: Slow Steaming and SFOC Reductions, MAN Diesel & Turbo.
27. Analysis of Two-Stroke Marine Diesel Engine Operation Including Turbocharger Cut-Out by Using a Zero-Dimensional Model10.3390/en8065738 ↗
28. Hountalas, D.T., Sakellaridis, N.F., Pariotis, E., and Dalmyras, F. (2014, January 25–27). Effect of Turbocharger Cut-Out on Two-Stroke Marine Diesel Engine Performance and NOx Emissions at Part-Load Operation. Proceedings of the ASME 12th Biennial Conference on Engineering Systems Design and Analysis, Copenhagen, Denmark.10.1115/ESDA2014-20514 ↗
29. Scikit-learn: Machine learning in Python
30. Random forests10.1023/A:1010933404324 ↗
31. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗
32. (2002). Internal Combustion Engines—Determination and Method for the Measurement of Engine Power—General Requirements (Standard No. ISO 15550:2002).
33. Liu, F.T., Ting, K.M., and Zhou, Z.-H. (2008). Isolation forest. Proceedings of the 8th IEEE International Conference on Data Mining (ICDM), IEEE.10.1109/ICDM.2008.17 ↗
34. Clausen, N.B. (2012). How efficient can a two-stroke engine be?. Proceedings of the STG Ship Efficiency Conference, STG.
35. International Maritime Organization (IMO) (2023). Carbon Intensity Indicator (CII)—Guidelines for the Operational Carbon Intensity Rating of Ships, IMO. Resolution MEPC.338(76).