A methodology to develop and manage data-driven models for marine engine long-term health prognosis.

This study proposes a novel methodology to develop and manage data-driven models for ship machinery Prognostics and Health Management (PHM). A four-stroke marine engine is investigated considering exhaust valve wear degradation. Simulated datasets are generated using a physics-based digital twin integrated with stochastic degradation models. Health indicators (HI) construction and forecast sub-models are developed, based on Multi-Layer Perceptron and Bayesian Neural Networks, respectively. Data-driven model management employs error and uncertainty metrics for deciding re-training of HI forecast sub-models, resulting in R2 increases from 0.24 to 0.89 and from 0.26 to 0.94 in Cases 1 and 2, respectively. This is the first study that integrates thermodynamic models with stochastic degradation models to develop marine engine digital twins, while also introducing data-driven model management, thus contributing to the PHM system adoption by the maritime industry.