Ship performance and navigation data compression and communication under autoencoder system architecture
作者机构:UiT The Arctic University of NorwayTromsoNorway SINTEF OceanTrondheimNorway
出 版 物:《Journal of Ocean Engineering and Science》 (海洋工程与科学(英文))
年 卷 期:2018年第3卷第2期
页 面:133-143页
核心收录:
学科分类:0710[理学-生物学] 0830[工学-环境科学与工程(可授工学、理学、农学学位)] 0908[农学-水产] 0809[工学-电子科学与技术(可授工学、理学学位)] 0707[理学-海洋科学] 08[工学] 0815[工学-水利工程] 0824[工学-船舶与海洋工程]
基 金:This work has been conducted under the project of“SFI Smart Maritime(237917/O30)-Norwegian Centre for im-proved energy-efficiency and reduced emissions from the mar-itime sector”that is partly funded by the Research Council of Norway An initial version of this paper is presented at the 35th International Conference on Ocean,Offshore and Arc-tic Engineering(OMAE 2016),Busan,Korea,June,2016,(OMAE2016-54093)
主 题:Autoencoder Ship performance and navigation information Ship energy efficiency Data compression Data communication Principal component analysis
摘 要:Modern vessels are designed to collect,store and communicate large quantities of ship performance and navigation information through complex onboard data handling *** data should be transferred to shore based data centers for further analysis and ***,the associated transfer cost in large-scale data sets is a major challenge for the shipping industry,*** same cost relates to the amount of data that are transferring through various communication networks(*** and wireless networks),*** vessels and shore based data ***,this study proposes to use an autoencoder system architecture(i.e.a deep learning approach)to compress ship performance and navigation parameters(*** the number of parameters)and transfer through the respective communication networks as reduced data *** data compression is done under the linear version of an autoencoder that consists of principal component analysis(PCA),where the respective principal components(PCs)represent the structure of the data *** compressed data set is expanded by the same data structure(*** autoencoder system architecture)at the respective data center requiring further analyses and storage.A data set of ship performance and navigation parameters in a selected vessel is analyzed(*** compression and expansion)through an autoencoder system architecture and the results are presented in this ***,the respective input and output values of the autoencoder are also compared as statistical distributions and sample number series to evaluate its performance.