The main purpose of thiswork is to build a data driven model to create realistic operating profiles in order to assess and compare different design solutions. The proposed approach takes advantage on the new generation of automation systems which allow gathering a large amount of data from on-board machinery. Data driven models are built upon statistical inference procedures based on the historical data collection. The advantage of these methods is that there is no need of any a-priory knowledge of the underlying physical system. Furthermore, thanks to the nature of these approaches, it is possible to exploit even data from sensors that could contain some kind of hidden information that cannot be easily extracted with a parametric approach. The use of these tools is nowadays made possible since such information is digitally available from different sources: (i) data stored on board of vessels; (ii) Automatic Identification System (AIS) data available through the internet. A data driven modelling of the operational profiles of the vessel (and in general of the fleet) could provide a tool both to diagnose and predict the vesselâs state (e.g. for condition based maintenance purposes), for improving the performance and the efficiency of the vessel, and for improving design solutions. The diagnosis and prognosis of the shipâs performance can be used as decision support in determining when actions to improve performance should be taken. The developed model will be tested on a real DAMEN vessel where on-board sensors data acquisitions are available from the automation system.
|Titolo:||Operational profiles data analytics for ship design improvement|
|Data di pubblicazione:||2016|
|Appare nelle tipologie:||04.01 - Contributo in atti di convegno|