Explainable Predictive Maintenance of Marine Engines Using a Hybrid BiLSTM-Attention-Kolmogorov Arnold Network

Abstract

Predictive maintenance for marine engines requires forecasts that are both accurate and technically interpretable. This work introduces BEACON, a hybrid architecture that combines a bidirectional long short-term memory encoder with attention pooling, a Kolmogorov Arnold network and a lightweight multilayer perceptron for cylinder-level exhaust gas temperature forecasting, evaluated in both centralized and federated learning settings. On operational data from a bulk carrier, BEACON outperformed strong state-of-the-art baselines, achieving an RMSE of (Formula presented.), MAE of (Formula presented.) and (Formula presented.) of approximately 0.95, while producing interpretable response curves and stable SHAP rankings across engine load regimes. A second contribution is the explicit evaluation of explanation stability in a federated learning setting, where BEACON maintained competitive accuracy and attained mean Spearman correlations above (Formula presented.) between client-specific SHAP rankings, whereas baseline models exhibited substantially lower agreement. These results indicate that the proposed hybrid design provides an accurate and explanation-stable foundation for privacy-aware predictive maintenance of marine engines.