Condition-based maintenance of naval propulsion systems: data analysis with minimal feedback

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

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The maintenance of the several components of a Ship Propulsion Systems is an onerous activity, which need to be efficiently programmed by a shipbuilding company in order to save time and money. The replacement policies of these components can be planned in a Condition-Based fashion, by predicting their decay state and thus proceed to substitution only when really needed. In this paper, authors propose several Data Analysis supervised and unsupervised techniques for the Condition-Based Maintenance of a vessel, characterised by a combined diesel-electric and gas propulsion plant. In particular, this analysis considers a scenario where the collection of vast amounts of labelled data containing the decay state of the components is unfeasible. In fact, the collection of labelled data requires a drydocking of the ship and the intervention of expert operators, which is usually an infrequent event. As a result, authors focus on methods which could allow only a minimal feedback from naval specialists, thus simplifying the dataset collection phase. Confidentiality constraints with the Navy require authors to use a real-data validated simulator and the dataset has been published for free use through the OpenML repository.

LanguageEnglish
Pages12-23
Number of pages12
JournalReliability Engineering and System Safety
Volume177
Early online date19 Apr 2018
DOIs
Publication statusPublished - 30 Sep 2018

Fingerprint

Propulsion
Ship propulsion
Feedback
Shipbuilding
Ships
Substitution reactions
Simulators
Gases
Industry

Keywords

  • condition-based maintenance
  • data analysis
  • minimal feedback.
  • naval propulsion systems
  • novelty detection
  • supervised learning
  • unsupervised learning

Cite this

Cipollini, Francesca ; Oneto, Luca ; Coraddu, Andrea ; Murphy, Alan John ; Anguita, Davide. / Condition-based maintenance of naval propulsion systems : data analysis with minimal feedback. In: Reliability Engineering and System Safety. 2018 ; Vol. 177. pp. 12-23.
@article{307d607930a04ce885dd8b3b0c25f546,
title = "Condition-based maintenance of naval propulsion systems: data analysis with minimal feedback",
abstract = "The maintenance of the several components of a Ship Propulsion Systems is an onerous activity, which need to be efficiently programmed by a shipbuilding company in order to save time and money. The replacement policies of these components can be planned in a Condition-Based fashion, by predicting their decay state and thus proceed to substitution only when really needed. In this paper, authors propose several Data Analysis supervised and unsupervised techniques for the Condition-Based Maintenance of a vessel, characterised by a combined diesel-electric and gas propulsion plant. In particular, this analysis considers a scenario where the collection of vast amounts of labelled data containing the decay state of the components is unfeasible. In fact, the collection of labelled data requires a drydocking of the ship and the intervention of expert operators, which is usually an infrequent event. As a result, authors focus on methods which could allow only a minimal feedback from naval specialists, thus simplifying the dataset collection phase. Confidentiality constraints with the Navy require authors to use a real-data validated simulator and the dataset has been published for free use through the OpenML repository.",
keywords = "condition-based maintenance, data analysis, minimal feedback., naval propulsion systems, novelty detection, supervised learning, unsupervised learning",
author = "Francesca Cipollini and Luca Oneto and Andrea Coraddu and Murphy, {Alan John} and Davide Anguita",
year = "2018",
month = "9",
day = "30",
doi = "10.1016/j.ress.2018.04.015",
language = "English",
volume = "177",
pages = "12--23",
journal = "Reliability Engineering and System Safety",
issn = "0951-8320",

}

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

In: Reliability Engineering and System Safety, Vol. 177, 30.09.2018, p. 12-23.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Condition-based maintenance of naval propulsion systems

T2 - Reliability Engineering and System Safety

AU - Cipollini, Francesca

AU - Oneto, Luca

AU - Coraddu, Andrea

AU - Murphy, Alan John

AU - Anguita, Davide

PY - 2018/9/30

Y1 - 2018/9/30

N2 - The maintenance of the several components of a Ship Propulsion Systems is an onerous activity, which need to be efficiently programmed by a shipbuilding company in order to save time and money. The replacement policies of these components can be planned in a Condition-Based fashion, by predicting their decay state and thus proceed to substitution only when really needed. In this paper, authors propose several Data Analysis supervised and unsupervised techniques for the Condition-Based Maintenance of a vessel, characterised by a combined diesel-electric and gas propulsion plant. In particular, this analysis considers a scenario where the collection of vast amounts of labelled data containing the decay state of the components is unfeasible. In fact, the collection of labelled data requires a drydocking of the ship and the intervention of expert operators, which is usually an infrequent event. As a result, authors focus on methods which could allow only a minimal feedback from naval specialists, thus simplifying the dataset collection phase. Confidentiality constraints with the Navy require authors to use a real-data validated simulator and the dataset has been published for free use through the OpenML repository.

AB - The maintenance of the several components of a Ship Propulsion Systems is an onerous activity, which need to be efficiently programmed by a shipbuilding company in order to save time and money. The replacement policies of these components can be planned in a Condition-Based fashion, by predicting their decay state and thus proceed to substitution only when really needed. In this paper, authors propose several Data Analysis supervised and unsupervised techniques for the Condition-Based Maintenance of a vessel, characterised by a combined diesel-electric and gas propulsion plant. In particular, this analysis considers a scenario where the collection of vast amounts of labelled data containing the decay state of the components is unfeasible. In fact, the collection of labelled data requires a drydocking of the ship and the intervention of expert operators, which is usually an infrequent event. As a result, authors focus on methods which could allow only a minimal feedback from naval specialists, thus simplifying the dataset collection phase. Confidentiality constraints with the Navy require authors to use a real-data validated simulator and the dataset has been published for free use through the OpenML repository.

KW - condition-based maintenance

KW - data analysis

KW - minimal feedback.

KW - naval propulsion systems

KW - novelty detection

KW - supervised learning

KW - unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=85046406818&partnerID=8YFLogxK

UR - https://www.sciencedirect.com/journal/reliability-engineering-and-system-safety

U2 - 10.1016/j.ress.2018.04.015

DO - 10.1016/j.ress.2018.04.015

M3 - Article

VL - 177

SP - 12

EP - 23

JO - Reliability Engineering and System Safety

JF - Reliability Engineering and System Safety

SN - 0951-8320

ER -