Ship Performance and Navigation Information under High Dimensional Digital Models

Abstract

Future vessels will be facilitated by modern internet of things to collect various ship performance and navigation information. Such information is collected as large-scale data sets, the so-called Big Data, that should be utilized towards digitalization of the shipping industry. However, various data handling challenges are encountered by the shipping industry during the phase of digitalization, onboard as well as onshore. Data-driven models, the so-called digital models, to support data handling frameworks of the shipping industry are proposed by this study. Such models can overcome the respective data handling challenges in shipping, where conventional mathematical models may fail to facilitate. These models can be derived from ship performance and navigation data sets by considering the high-dimensional parameter space. Such high-dimensional models consist of several data clusters and each data cluster may consist of a possible unique data structure. These data clusters often relate to sub-operational conditions of vessels and ship systems. The identification of the distribution of data clusters and the structure of each data cluster in relation to ship performance and navigation conditions have been done under this study for a selected vessel as the main contribution. Furthermore, the domain knowledge in shipping (i.e., vessel operational and navigation conditions) is also considered during this analysis to interpret the meaning in such digital models.