GaussianCopula-Based Synthetic Data Generation for Turbocharger Fault Scenario Simulation and SFOC Degradation Modelling in Two-Stroke Marine Diesel Engines

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.