Machine learning approaches for improving condition-based maintenance of naval propulsion plants

Andrea Coraddu, Luca Oneto, Aessandro Ghio, Stefano Savio, Davide Anguita, Massimo Figari

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive maintenance up to more effective condition-based maintenance approaches. The central idea in condition-based maintenance is to monitor the propulsion equipment by exploiting heterogeneous sensors, enabling diagnosis and, most of all, prognosis of the propulsion system's components and of their potential future failures. The success of condition-based maintenance clearly hinges on the capability of developing effective predictive models; for this purpose, effective use of machine learning methods is proposed in this article. In particular, authors take into consideration an application of condition-based maintenance to gas turbines used for vessel propulsion, where the performance and advantages of exploiting machine learning methods in modeling the degradation of the propulsion plant over time are tested. Experiments, conducted on data generated from a sophisticated simulator of a gas turbine, mounted on a Frigate characterized by a COmbined Diesel eLectric And Gas propulsion plant type, will allow to show the effectiveness of the proposed machine learning approaches and to benchmark them in a realistic maritime application.

LanguageEnglish
Pages136-153
Number of pages18
JournalProceedings of the Institution of Mechanical Engineers Part M: Journal of Engineering for the Maritime Environment
Volume230
Issue number1
Early online date25 Jul 2014
DOIs
Publication statusPublished - 1 Feb 2016

Fingerprint

Propulsion
Learning systems
Gas turbines
Ship propulsion
Preventive maintenance
Hinges
Costs
Sustainable development
Simulators
Availability
Degradation
Economics
Sensors
Gases
Experiments

Keywords

  • asset decay forecast
  • COmbined Diesel eLectric And Gas propulsion plant
  • condition-based maintenance
  • gas turbine
  • machine learning

Cite this

@article{8de88702f6d74c8ab814cfbc49c731c9,
title = "Machine learning approaches for improving condition-based maintenance of naval propulsion plants",
abstract = "Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive maintenance up to more effective condition-based maintenance approaches. The central idea in condition-based maintenance is to monitor the propulsion equipment by exploiting heterogeneous sensors, enabling diagnosis and, most of all, prognosis of the propulsion system's components and of their potential future failures. The success of condition-based maintenance clearly hinges on the capability of developing effective predictive models; for this purpose, effective use of machine learning methods is proposed in this article. In particular, authors take into consideration an application of condition-based maintenance to gas turbines used for vessel propulsion, where the performance and advantages of exploiting machine learning methods in modeling the degradation of the propulsion plant over time are tested. Experiments, conducted on data generated from a sophisticated simulator of a gas turbine, mounted on a Frigate characterized by a COmbined Diesel eLectric And Gas propulsion plant type, will allow to show the effectiveness of the proposed machine learning approaches and to benchmark them in a realistic maritime application.",
keywords = "asset decay forecast, COmbined Diesel eLectric And Gas propulsion plant, condition-based maintenance, gas turbine, machine learning",
author = "Andrea Coraddu and Luca Oneto and Aessandro Ghio and Stefano Savio and Davide Anguita and Massimo Figari",
year = "2016",
month = "2",
day = "1",
doi = "10.1177/1475090214540874",
language = "English",
volume = "230",
pages = "136--153",
journal = "Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment",
issn = "1475-0902",
number = "1",

}

Machine learning approaches for improving condition-based maintenance of naval propulsion plants. / Coraddu, Andrea; Oneto, Luca; Ghio, Aessandro; Savio, Stefano; Anguita, Davide; Figari, Massimo.

In: Proceedings of the Institution of Mechanical Engineers Part M: Journal of Engineering for the Maritime Environment, Vol. 230, No. 1, 01.02.2016, p. 136-153.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning approaches for improving condition-based maintenance of naval propulsion plants

AU - Coraddu, Andrea

AU - Oneto, Luca

AU - Ghio, Aessandro

AU - Savio, Stefano

AU - Anguita, Davide

AU - Figari, Massimo

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive maintenance up to more effective condition-based maintenance approaches. The central idea in condition-based maintenance is to monitor the propulsion equipment by exploiting heterogeneous sensors, enabling diagnosis and, most of all, prognosis of the propulsion system's components and of their potential future failures. The success of condition-based maintenance clearly hinges on the capability of developing effective predictive models; for this purpose, effective use of machine learning methods is proposed in this article. In particular, authors take into consideration an application of condition-based maintenance to gas turbines used for vessel propulsion, where the performance and advantages of exploiting machine learning methods in modeling the degradation of the propulsion plant over time are tested. Experiments, conducted on data generated from a sophisticated simulator of a gas turbine, mounted on a Frigate characterized by a COmbined Diesel eLectric And Gas propulsion plant type, will allow to show the effectiveness of the proposed machine learning approaches and to benchmark them in a realistic maritime application.

AB - Availability, reliability and economic sustainability of naval propulsion plants are key elements to cope with because maintenance costs represent a large slice of total operational expenses. Depending on the adopted strategy, impact of maintenance on overall expenses can remarkably vary; for example, letting an asset running up until breakdown can lead to unaffordable costs. As a matter of fact, a desideratum is to progress maintenance technology of ship propulsion systems from breakdown or preventive maintenance up to more effective condition-based maintenance approaches. The central idea in condition-based maintenance is to monitor the propulsion equipment by exploiting heterogeneous sensors, enabling diagnosis and, most of all, prognosis of the propulsion system's components and of their potential future failures. The success of condition-based maintenance clearly hinges on the capability of developing effective predictive models; for this purpose, effective use of machine learning methods is proposed in this article. In particular, authors take into consideration an application of condition-based maintenance to gas turbines used for vessel propulsion, where the performance and advantages of exploiting machine learning methods in modeling the degradation of the propulsion plant over time are tested. Experiments, conducted on data generated from a sophisticated simulator of a gas turbine, mounted on a Frigate characterized by a COmbined Diesel eLectric And Gas propulsion plant type, will allow to show the effectiveness of the proposed machine learning approaches and to benchmark them in a realistic maritime application.

KW - asset decay forecast

KW - COmbined Diesel eLectric And Gas propulsion plant

KW - condition-based maintenance

KW - gas turbine

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=84953876479&partnerID=8YFLogxK

U2 - 10.1177/1475090214540874

DO - 10.1177/1475090214540874

M3 - Article

VL - 230

SP - 136

EP - 153

JO - Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment

T2 - Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment

JF - Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment

SN - 1475-0902

IS - 1

ER -