Hybrid AI-driven condition monitoring and RUL forecasting for multi-fault diagnosis in two-stroke marine diesel engines

• Hybrid AI framework integrated anomaly detection, fault clustering, fault classification, and RUL prediction. • Load-aware diagnostics and stress modeling improved degradation interpretation. • Consensus-based anomaly voting reduced false positives to below 1 %. • Z-score mapping to fault clusters led to interpretable fault signatures. • RUL predicted without run-to-failure data using PCA and autoencoder health indices. This study proposes a unified, load-aware condition-based monitoring (CBM) framework for two-stroke marine diesel engines that integrates data-driven intelligence with physical interpretability. The methodology establishes a modular architecture comprising four interactive layers: ensemble-based anomaly detection, unsupervised fault clustering and fault labeling, context-aware supervised fault classification, and calibrated remaining useful life (RUL) prognostic predictions. Each pipeline is designed to maintain thermodynamic and mechanical consistency while adjusting to the nonlinear and load-dependent behavior of marine propulsion systems. Anomaly detection combines density-, partition-, and subspace-based models through weighted consensus to ensure robust fault localization with minimal false alarms. The clustering module transforms anomaly patterns into physically meaningful fault signatures, providing training targets for the supervised classifier, which employs load segmentation and direction coupled with probabilistic calibration to achieve interpretable fault classes. The prognostic layer integrates per-cylinder contextual embeddings, SHAP-based feature attribution, and Monte Carlo dropout for uncertainty quantification, producing stable and physically consistent RUL trajectories across the varying load conditions. Validation on data collected from a low-speed two-stroke testbed confirmed the framework’s robustness and interpretability, with representative RUL predictions achieving a mean RMSE and R² of 0.215 and 0.413, respectively. The results demonstrate that the framework offers a reproducible pathway toward intelligent, load-aware CBM systems for maritime applications.