Lookup NU author(s): Serena Lim,
Dr Kayvan Pazouki,
Dr Alan J Murphy
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
© 2018 ASME. Holistic energy management in the shipping industry involves reliable data collection, systematic processing and smart analysis. The era of digitisation allows sensor technology to be used on-board vessels, converting different forms of signal into a digital format that can be exported conveniently for further processing. Appropriate sensor selection is important to ensure continuous data collection when vessels sail through harsh conditions. However, without proper processing, this leads to the collection of big data sets but without resulting useful intelligence that benefits the industry. The adoption of digital and computer technology, allows the next phase of fast data processing. This contributes to the growing area of big data analysis, which is now a problem for many technological sectors, including the maritime industry. Enormous databases are often stored without clear goals or suitable uses. Processing of data requires engineering knowledge to ensure suitable filters are applied to raw data. This systematic processing of data leads to transparency in real time data display and contributes to predictive analysis. In addition, the generation of series of raw data when coupled with other external data such as weather information provides a rich database that reflects the true scenario of the vessel. Subsequent processing will then provide improved decision making tools for optimal operations. These advances open the door for different market analyses and the generation of new knowledge. This paper highlights the crucial steps needed and the challenges of sensor installation to obtain accurate data, followed by pre and post processing of data to generate knowledge. With this, big data can now provide information and reveal hidden patterns and trends regarding vessel operations, machinery diagnostics and energy efficient fleet management. A case study was carried out on a tug boat that operates in the North Sea, firstly to demonstrate confidence in the raw data collected and secondly to demonstrate the systematic filtration, aggregation and display of useful information.
Author(s): Lim S, Pazouki K, Murphy AJ, Zhang B
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 37th International Conference on Ocean, Offshore and Arctic Engineering - OMAE
Year of Conference: 2018
Online publication date: 22/06/2018
Acceptance date: 17/06/2018
Publisher: American Society of Mechanical Engineers (ASME)
Library holdings: Search Newcastle University Library for this item