Ship Performance Monitoring using Machine-learning

Gupta, Prateek K.; Rasheed, Adil; Steen, Sverre

doi:10.48550/arxiv.2110.03594

Cited by 1 publication

(1 citation statement)

References 22 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ISO 19030 ISO (2016) along with several researchers (Koboević et al (2019); Coraddu et al (2019)) recommends observing the horizontal shift (along the speed axis) of the calm-water speed-power curve, termed as the speed-loss, over time to monitor the performance of a sea-going ship using the in-service data. Alternatively, it is suggested to observe the vertical shift of the calm-water speed-power curve, often termed as the change in power demand (adopted by Gupta et al (2021a) and Carchen and Atlar (2020)). Some researchers also formulated and used some indirect performance indicators like fuel consumption (Koboević et al (2019)), resistance (or fouling) coefficient (Munk (2016); Foteinos et al (2017); Carchen and Atlar (2020)), (generalized) admiralty coefficient (Ejdfors (2019); Gupta et al (2021b)), wake fraction (Carchen and Atlar (2020)), fuel efficiency (Kim et al (2021)), etc.…”

Section: Introductionmentioning

confidence: 99%

Data Processing Framework for Ship Performance Analysis

Gupta,

Kim,

Steen

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The hydrodynamic performance of a sea-going ship can be analysed using the data obtained from the ship. Such data can be gathered from different sources, like onboard recorded in-service data, AIS data, and noon reports. Each of these sources is known to have their inherent problems. The current work gives a brief introduction to these data sources as well as the common problems associated with them, along with some examples. In order to resolve most of these problems, a streamlined semi-automatic data processing framework for fast data processing is developed and presented here. The data processing framework can be used to process the data obtained from any of the above three mentioned sources. The framework incorporates processing steps like interpolating weather hindcast (metocean) data to ship's location in time, deriving additional features, validating data, estimating resistance components, data cleaning, and outlier detection. A brief description of each of the processing steps is provided with examples from existing datasets. The processed data can be further used to analyse the hydrodynamic performance of a ship.

show abstract