Hybrid AI-driven condition monitoring and RUL forecasting for multi-fault diagnosis in two-stroke marine diesel engines
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".