Data‐aware monitoring method for fuel economy in ship‐based CPS. Issue 3 (20th August 2020)

• Record Type: Journal Article
• Authors: Shi, Yiran; Xue, Shengjun; Zhang, Xing; Huang, Tao
• Is Part Of: IET cyber-physical systems. Volume 5:Issue 3(2020)
• Page Start: 245
• Page End: 252
• Publication Date: 2020-08-20
• Subjects: computerised monitoring -- globalisation -- fuel economy -- energy consumption -- energy conservation -- ships -- neural nets -- cyber‐physical systems; fuel consumption data -- data‐aware monitoring method -- ship‐based CPS -- fuel consumption index -- navigation data -- fuel economy -- network communication technology -- ship fuel consumption -- traditional fuel consumption monitoring methods -- shipping industry -- conduct energy management -- equipment condition monitoring -- shipping data -- remote monitoring centres -- sailing conditions
• DOI: 10.1049/iet-cps.2019.0080
• Languages: English
• ISSNs: 2398-3396

Abstract

Abstract : With the acceleration of economic globalisation and the rapid development of network communication technology, remote monitoring and the management of ship fuel consumption have received extensive attention. Traditional fuel consumption monitoring methods are difficult to meet the growing management needs of the shipping industry due to problems such as large statistical errors and delayed information feedback. In order to better conduct energy management, equipment condition monitoring, and navigation analysis, the cyber‐physical system (CPS) is deployed on ships to collect shipping data and communicate with remote monitoring centres. However, complex actual sailing conditions, sailing weather and other external factors tend to reduce the accuracy of fuel consumption data. In view of this challenge, a data‐aware monitoring method for fuel consumption in ship‐based CPS, named DMM, is proposed in this study. Technically, the fuel consumption index of ships is introduced firstly. Then, a fuel consumption model based on CPS is proposed, which improves the current fuel consumption model of the ship. Furthermore, the artificial neural network is employed to analyse a large amount of navigation data to get more accurate monitoring results of fuel consumption. Finally, experiments are conducted to verify the effectiveness of the authors' proposed method.