Streamlined semi-automatic data processing framework for ship performance analysis
Prateek Gupta, Young-Rong Kim, Sverre Steen, Adil Rasheed
Abstract
The hydrodynamic performance of a sea-going ship can be analyzed using data from different sources, like onboard recorded in-service data, AIS data, and noon reports. Each of these sources is known to have its inherent problems. The current work highlights the most prominent issues, explained with examples from actual datasets. A streamlined semi-automatic approach to processing the data is finally outlined, which can be used to prepare a dataset for ship performance analysis. Typical data processing steps like interpolating metocean data, deriving additional features, estimating resistance components, data cleaning, and outlier detection are arranged in the best possible manner not only to streamline the data processing but also to obtain reliable results. A semi-automatic implementation of the data processing framework, with limited user intervention, is used to process the datasets here and present the example plots for various data processing steps, proving the effectiveness of the proposed approach.