Condition-based maintenance of naval propulsion systems with supervised data analysis

Francesca Cipollini, Luca Oneto, Andrea Coraddu, Alan John Murphy, Davide Anguita

Research output: Contribution to journalReview article

10 Citations (Scopus)

Abstract

The behavior and interaction of the main components of Ship Propulsion Systems cannot be easily modeled with a priori physical knowledge, considering the large amount of variables influencing them. Data-Driven Models (DDMs), instead, exploit advanced statistical techniques to build models directly on the large amount of historical data collected by on-board automation systems, without requiring any a priori knowledge. DDMs are extremely useful when it comes to continuously monitoring the propulsion equipment and take decisions based on the actual condition of the propulsion plant. In this paper, the authors investigate the problem of performing Condition-Based Maintenance through the use of DDMs. In order to conceive this purpose, several state-of-the-art supervised learning techniques are adopted, which require labeled sensor data in order to be deployed. A naval vessel, characterized by a combined diesel-electric and gas propulsion plant, has been exploited to collect such data and show the effectiveness of the proposed approaches. Because of confidentiality constraints with the Navy the authors used a real-data validated simulator and the dataset has been published for free use through the UCI repository.

LanguageEnglish
Pages268-278
Number of pages11
JournalOcean Engineering
Volume149
Early online date27 Dec 2017
DOIs
Publication statusPublished - 1 Feb 2018

Fingerprint

Propulsion
Naval vessels
Ship propulsion
Supervised learning
Automation
Simulators
Monitoring
Sensors
Gases

Keywords

  • condition-based maintenance
  • data analysis
  • naval propulsion systems

Cite this

Cipollini, Francesca ; Oneto, Luca ; Coraddu, Andrea ; Murphy, Alan John ; Anguita, Davide. / Condition-based maintenance of naval propulsion systems with supervised data analysis. In: Ocean Engineering. 2018 ; Vol. 149. pp. 268-278.
@article{4492f1f09c0d41d9a4538c6475041b60,
title = "Condition-based maintenance of naval propulsion systems with supervised data analysis",
abstract = "The behavior and interaction of the main components of Ship Propulsion Systems cannot be easily modeled with a priori physical knowledge, considering the large amount of variables influencing them. Data-Driven Models (DDMs), instead, exploit advanced statistical techniques to build models directly on the large amount of historical data collected by on-board automation systems, without requiring any a priori knowledge. DDMs are extremely useful when it comes to continuously monitoring the propulsion equipment and take decisions based on the actual condition of the propulsion plant. In this paper, the authors investigate the problem of performing Condition-Based Maintenance through the use of DDMs. In order to conceive this purpose, several state-of-the-art supervised learning techniques are adopted, which require labeled sensor data in order to be deployed. A naval vessel, characterized by a combined diesel-electric and gas propulsion plant, has been exploited to collect such data and show the effectiveness of the proposed approaches. Because of confidentiality constraints with the Navy the authors used a real-data validated simulator and the dataset has been published for free use through the UCI repository.",
keywords = "condition-based maintenance, data analysis, naval propulsion systems",
author = "Francesca Cipollini and Luca Oneto and Andrea Coraddu and Murphy, {Alan John} and Davide Anguita",
year = "2018",
month = "2",
day = "1",
doi = "10.1016/j.oceaneng.2017.12.002",
language = "English",
volume = "149",
pages = "268--278",
journal = "Ocean Engineering",
issn = "0029-8018",
publisher = "Elsevier",

}

Condition-based maintenance of naval propulsion systems with supervised data analysis. / Cipollini, Francesca; Oneto, Luca; Coraddu, Andrea; Murphy, Alan John; Anguita, Davide.

In: Ocean Engineering, Vol. 149, 01.02.2018, p. 268-278.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Condition-based maintenance of naval propulsion systems with supervised data analysis

AU - Cipollini, Francesca

AU - Oneto, Luca

AU - Coraddu, Andrea

AU - Murphy, Alan John

AU - Anguita, Davide

PY - 2018/2/1

Y1 - 2018/2/1

N2 - The behavior and interaction of the main components of Ship Propulsion Systems cannot be easily modeled with a priori physical knowledge, considering the large amount of variables influencing them. Data-Driven Models (DDMs), instead, exploit advanced statistical techniques to build models directly on the large amount of historical data collected by on-board automation systems, without requiring any a priori knowledge. DDMs are extremely useful when it comes to continuously monitoring the propulsion equipment and take decisions based on the actual condition of the propulsion plant. In this paper, the authors investigate the problem of performing Condition-Based Maintenance through the use of DDMs. In order to conceive this purpose, several state-of-the-art supervised learning techniques are adopted, which require labeled sensor data in order to be deployed. A naval vessel, characterized by a combined diesel-electric and gas propulsion plant, has been exploited to collect such data and show the effectiveness of the proposed approaches. Because of confidentiality constraints with the Navy the authors used a real-data validated simulator and the dataset has been published for free use through the UCI repository.

AB - The behavior and interaction of the main components of Ship Propulsion Systems cannot be easily modeled with a priori physical knowledge, considering the large amount of variables influencing them. Data-Driven Models (DDMs), instead, exploit advanced statistical techniques to build models directly on the large amount of historical data collected by on-board automation systems, without requiring any a priori knowledge. DDMs are extremely useful when it comes to continuously monitoring the propulsion equipment and take decisions based on the actual condition of the propulsion plant. In this paper, the authors investigate the problem of performing Condition-Based Maintenance through the use of DDMs. In order to conceive this purpose, several state-of-the-art supervised learning techniques are adopted, which require labeled sensor data in order to be deployed. A naval vessel, characterized by a combined diesel-electric and gas propulsion plant, has been exploited to collect such data and show the effectiveness of the proposed approaches. Because of confidentiality constraints with the Navy the authors used a real-data validated simulator and the dataset has been published for free use through the UCI repository.

KW - condition-based maintenance

KW - data analysis

KW - naval propulsion systems

UR - https://www.sciencedirect.com/journal/ocean-engineering

UR - http://www.scopus.com/inward/record.url?scp=85038258680&partnerID=8YFLogxK

U2 - 10.1016/j.oceaneng.2017.12.002

DO - 10.1016/j.oceaneng.2017.12.002

M3 - Review article

VL - 149

SP - 268

EP - 278

JO - Ocean Engineering

T2 - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -