A novelty detection approach to diagnosing hull and propeller fouling

Andrea Coraddu, Serena Lim, Luca Oneto, Kayvan Pazouki, Rose Norman, Alan John Murphy

Research output: Contribution to journalArticle

Abstract

Hull and propeller performance have a primary role in overall vessel efficiency. Vessel fouling is a common phenomenon where undesirable substances attach or grow on the ship hull. A clear understanding of the extent of the degradation of the hull will allow better management of assets and prediction of the best time for dry docking and hull maintenance work. In this paper, the authors investigate the problems of predicting the hull condition in real operations based on data measured by the on-board systems. The proposed solution uses an unsupervised Machine Learning (ML) modelling technique to eliminate the need for collecting labeled data related to the hull and propeller fouling condition. Two anomaly detection methods based on Support Vector Machines and k-nearest neighbour have been applied to predict the hull condition using the available parameters measured on-board. Data from the Research Vessel The Princess Royal has been exploited to show the effectiveness of the proposed methods and to benchmark them in a realistic maritime application.

LanguageEnglish
Pages65-73
Number of pages9
JournalOcean Engineering
Volume176
Early online date22 Feb 2019
DOIs
Publication statusPublished - 15 Mar 2019

Fingerprint

Propellers
Fouling
Support vector machines
Learning systems
Ships
Degradation

Keywords

  • Data analytics
  • Hull and propeller performance
  • Hull fouling detection
  • Sensor data collection
  • Ship efficiency
  • Supervised learning

Cite this

Coraddu, Andrea ; Lim, Serena ; Oneto, Luca ; Pazouki, Kayvan ; Norman, Rose ; Murphy, Alan John. / A novelty detection approach to diagnosing hull and propeller fouling. In: Ocean Engineering. 2019 ; Vol. 176. pp. 65-73.
@article{fb68188119a743399f794fa5ca1711fb,
title = "A novelty detection approach to diagnosing hull and propeller fouling",
abstract = "Hull and propeller performance have a primary role in overall vessel efficiency. Vessel fouling is a common phenomenon where undesirable substances attach or grow on the ship hull. A clear understanding of the extent of the degradation of the hull will allow better management of assets and prediction of the best time for dry docking and hull maintenance work. In this paper, the authors investigate the problems of predicting the hull condition in real operations based on data measured by the on-board systems. The proposed solution uses an unsupervised Machine Learning (ML) modelling technique to eliminate the need for collecting labeled data related to the hull and propeller fouling condition. Two anomaly detection methods based on Support Vector Machines and k-nearest neighbour have been applied to predict the hull condition using the available parameters measured on-board. Data from the Research Vessel The Princess Royal has been exploited to show the effectiveness of the proposed methods and to benchmark them in a realistic maritime application.",
keywords = "Data analytics, Hull and propeller performance, Hull fouling detection, Sensor data collection, Ship efficiency, Supervised learning",
author = "Andrea Coraddu and Serena Lim and Luca Oneto and Kayvan Pazouki and Rose Norman and Murphy, {Alan John}",
year = "2019",
month = "3",
day = "15",
doi = "10.1016/j.oceaneng.2019.01.054",
language = "English",
volume = "176",
pages = "65--73",
journal = "Ocean Engineering",
issn = "0029-8018",
publisher = "Elsevier",

}

A novelty detection approach to diagnosing hull and propeller fouling. / Coraddu, Andrea; Lim, Serena; Oneto, Luca; Pazouki, Kayvan; Norman, Rose; Murphy, Alan John.

In: Ocean Engineering, Vol. 176, 15.03.2019, p. 65-73.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A novelty detection approach to diagnosing hull and propeller fouling

AU - Coraddu, Andrea

AU - Lim, Serena

AU - Oneto, Luca

AU - Pazouki, Kayvan

AU - Norman, Rose

AU - Murphy, Alan John

PY - 2019/3/15

Y1 - 2019/3/15

N2 - Hull and propeller performance have a primary role in overall vessel efficiency. Vessel fouling is a common phenomenon where undesirable substances attach or grow on the ship hull. A clear understanding of the extent of the degradation of the hull will allow better management of assets and prediction of the best time for dry docking and hull maintenance work. In this paper, the authors investigate the problems of predicting the hull condition in real operations based on data measured by the on-board systems. The proposed solution uses an unsupervised Machine Learning (ML) modelling technique to eliminate the need for collecting labeled data related to the hull and propeller fouling condition. Two anomaly detection methods based on Support Vector Machines and k-nearest neighbour have been applied to predict the hull condition using the available parameters measured on-board. Data from the Research Vessel The Princess Royal has been exploited to show the effectiveness of the proposed methods and to benchmark them in a realistic maritime application.

AB - Hull and propeller performance have a primary role in overall vessel efficiency. Vessel fouling is a common phenomenon where undesirable substances attach or grow on the ship hull. A clear understanding of the extent of the degradation of the hull will allow better management of assets and prediction of the best time for dry docking and hull maintenance work. In this paper, the authors investigate the problems of predicting the hull condition in real operations based on data measured by the on-board systems. The proposed solution uses an unsupervised Machine Learning (ML) modelling technique to eliminate the need for collecting labeled data related to the hull and propeller fouling condition. Two anomaly detection methods based on Support Vector Machines and k-nearest neighbour have been applied to predict the hull condition using the available parameters measured on-board. Data from the Research Vessel The Princess Royal has been exploited to show the effectiveness of the proposed methods and to benchmark them in a realistic maritime application.

KW - Data analytics

KW - Hull and propeller performance

KW - Hull fouling detection

KW - Sensor data collection

KW - Ship efficiency

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85061732869&partnerID=8YFLogxK

U2 - 10.1016/j.oceaneng.2019.01.054

DO - 10.1016/j.oceaneng.2019.01.054

M3 - Article

VL - 176

SP - 65

EP - 73

JO - Ocean Engineering

T2 - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -