Most modern ships have several measurement evices that keep track of the vessel speed, fuel consumption, weather conditions etc. Storing, analysing and acting upon these data could become a valuable asset for the ship owners and operators. In this article a freely available data set is presented collected on a ferry. The data were used to develop the models used in an onboard trim optimisation application. The paper presents a novel and publicly available set of high-quality sensory data collected from a ferry over a period of two months and overviews existing machine-learning methods for the prediction of main propulsion efficiency. Neural networks are applied in both real-time and predictive settings. Performance results for the real-time models are shown. The presented models were successfully deployed in a trim optimisation application onboard a product tanker.
A machine-learning approach to predict main energy consumption under realistic operational conditions
Maschinelles Lernverfahren zur Vorhersage des Hauptenergieverbrauches unter realistischen Betriebsbedingungen
Ship Technology Research / Schiffstechnik ; 59 , 1 ; 64-72
2012
9 Seiten, 9 Bilder, 3 Tabellen, 11 Quellen
Aufsatz (Zeitschrift)
Englisch
Taylor & Francis Verlag | 2012
|MACHINE LEARNING TO PREDICT PART CONSUMPTION USING FLIGHT DEMOGRAPHICS
Europäisches Patentamt | 2023
|SAE Technical Papers | 2021
|