Data Compression of Ship Performance and Navigation Information Under Deep Learning
Various emission control regulations enforce vessels to collect performance and navigation data and evaluate ship energy efficiency by implementing onboard sensors and data acquisition (DAQ) systems. These DAQ systems are designed to collect, store and communicate large amounts of performance and navigation information through complex data handling processes. It is suggested that this information should eventually be transferred to shore based data analysis centers for further processing and storage. However, the associated data transfer costs introduce additional challenges in this process and enforce to investigate cost effective data handling approaches in shipping. That mainly relates to the amount of data that are transferring through various communication networks (i.e. satellites & wireless networks) between vessels and shore based data centers. Hence, this study proposes to use a deep learning approach (i.e. autoencoder system architecture) to compress ship performance and navigation information, which can be transferred through the respective communication networks as a reduced data set. The compressed data set can be expanded in the respective data center requiring further analysis. Therefore, a data set of ship performance and navigation information is analyzed (i.e. compression and expansion) through an autoencoder system architecture in this study. The compressed data set represents a subset of ship performance and navigation information can also be used to evaluate energy efficiency type applications in shipping. Furthermore, the respective input and output data sets of the autoencoder are also compared as statistical distributions to evaluate the network performance.