Research paper: Speed-power models – a Bayesian approach

By comparing the expected speed of a vessel through water (as a function of applied power and wind) with the actual speed of the vessel, the degradation of the hull performance of the ship can be monitored. In the research paper provided below, we developed a data-driven probabilistic model to predict a ship's speed through water as a function of power and draft. The model is based on Gaussian process regression, and we used machine learning strategies to identify the model parameters based on data recorded during the vessel's voyage. The proposed approach improves the prediction of the performance loss due to degradation of the coating and, thus, helps to compile a tailored maintenance strategy for each vessel.

Manolis Levantis, Sergiu Paereli, Wolfgang Betz: Speed-Power Models – A Bayesian Approach, 5th Hull Performance & Insight Conference (HullPIC) 2020, Hamburg