Exploiting machine learning for ship systems anomaly detection and healthiness forecasting

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)

Abstract

This paper describes a novel methodology concerning the application of machine learning for the intelligent monitoring of ship systems. Monitoring of machinery condition is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. Operator-approved performance data are used to train a data-driven Expected Behaviour Model (EBM). Once trained, this model accepts newly-acquired data points as input and returns the probability of them belonging to the same performance profile with training data. Through this, emerging anomalies can be detected. This tool is coupled with a short-term healthiness forecasting tool, able to estimate future healthiness index. This combination allows the derivation of a healthiness score of both current and future condition of ship machinery. Additionally, in cases of performance degradation, the Remaining Useful Life (RUL) of given system can be projected. This provides a robust framework for the early detection of incipient machinery faults.
LanguageEnglish
Title of host publicationProceedings of the 2018 Smart Ship Technology Conference
Place of PublicationLondon
PublisherRoyal Institution of Naval Architects
Number of pages6
Publication statusPublished - 23 Jan 2018
EventSmart Ship Technology 2018 - London, United Kingdom
Duration: 23 Jan 201824 Jan 2018

Conference

ConferenceSmart Ship Technology 2018
CountryUnited Kingdom
CityLondon
Period23/01/1824/01/18

Fingerprint

Machinery
Learning systems
Ships
Monitoring
Degradation

Keywords

  • machine learning
  • remaining useful life
  • expected behaviour model

Cite this

Gkerekos, C., Lazakis, I., & Theotokatos, G. (2018). Exploiting machine learning for ship systems anomaly detection and healthiness forecasting. In Proceedings of the 2018 Smart Ship Technology Conference London: Royal Institution of Naval Architects.
Gkerekos, Christos ; Lazakis, Iraklis ; Theotokatos, Gerasimos. / Exploiting machine learning for ship systems anomaly detection and healthiness forecasting. Proceedings of the 2018 Smart Ship Technology Conference. London : Royal Institution of Naval Architects, 2018.
@inproceedings{7e798a15104340e4b011c74994fd5a10,
title = "Exploiting machine learning for ship systems anomaly detection and healthiness forecasting",
abstract = "This paper describes a novel methodology concerning the application of machine learning for the intelligent monitoring of ship systems. Monitoring of machinery condition is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. Operator-approved performance data are used to train a data-driven Expected Behaviour Model (EBM). Once trained, this model accepts newly-acquired data points as input and returns the probability of them belonging to the same performance profile with training data. Through this, emerging anomalies can be detected. This tool is coupled with a short-term healthiness forecasting tool, able to estimate future healthiness index. This combination allows the derivation of a healthiness score of both current and future condition of ship machinery. Additionally, in cases of performance degradation, the Remaining Useful Life (RUL) of given system can be projected. This provides a robust framework for the early detection of incipient machinery faults.",
keywords = "machine learning, remaining useful life, expected behaviour model",
author = "Christos Gkerekos and Iraklis Lazakis and Gerasimos Theotokatos",
year = "2018",
month = "1",
day = "23",
language = "English",
booktitle = "Proceedings of the 2018 Smart Ship Technology Conference",
publisher = "Royal Institution of Naval Architects",
address = "United Kingdom",

}

Gkerekos, C, Lazakis, I & Theotokatos, G 2018, Exploiting machine learning for ship systems anomaly detection and healthiness forecasting. in Proceedings of the 2018 Smart Ship Technology Conference. Royal Institution of Naval Architects, London, Smart Ship Technology 2018, London, United Kingdom, 23/01/18.

Exploiting machine learning for ship systems anomaly detection and healthiness forecasting. / Gkerekos, Christos; Lazakis, Iraklis; Theotokatos, Gerasimos.

Proceedings of the 2018 Smart Ship Technology Conference. London : Royal Institution of Naval Architects, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Exploiting machine learning for ship systems anomaly detection and healthiness forecasting

AU - Gkerekos, Christos

AU - Lazakis, Iraklis

AU - Theotokatos, Gerasimos

PY - 2018/1/23

Y1 - 2018/1/23

N2 - This paper describes a novel methodology concerning the application of machine learning for the intelligent monitoring of ship systems. Monitoring of machinery condition is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. Operator-approved performance data are used to train a data-driven Expected Behaviour Model (EBM). Once trained, this model accepts newly-acquired data points as input and returns the probability of them belonging to the same performance profile with training data. Through this, emerging anomalies can be detected. This tool is coupled with a short-term healthiness forecasting tool, able to estimate future healthiness index. This combination allows the derivation of a healthiness score of both current and future condition of ship machinery. Additionally, in cases of performance degradation, the Remaining Useful Life (RUL) of given system can be projected. This provides a robust framework for the early detection of incipient machinery faults.

AB - This paper describes a novel methodology concerning the application of machine learning for the intelligent monitoring of ship systems. Monitoring of machinery condition is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. Operator-approved performance data are used to train a data-driven Expected Behaviour Model (EBM). Once trained, this model accepts newly-acquired data points as input and returns the probability of them belonging to the same performance profile with training data. Through this, emerging anomalies can be detected. This tool is coupled with a short-term healthiness forecasting tool, able to estimate future healthiness index. This combination allows the derivation of a healthiness score of both current and future condition of ship machinery. Additionally, in cases of performance degradation, the Remaining Useful Life (RUL) of given system can be projected. This provides a robust framework for the early detection of incipient machinery faults.

KW - machine learning

KW - remaining useful life

KW - expected behaviour model

UR - https://www.rina.org.uk/Smart_Ships2018.html

M3 - Conference contribution book

BT - Proceedings of the 2018 Smart Ship Technology Conference

PB - Royal Institution of Naval Architects

CY - London

ER -

Gkerekos C, Lazakis I, Theotokatos G. Exploiting machine learning for ship systems anomaly detection and healthiness forecasting. In Proceedings of the 2018 Smart Ship Technology Conference. London: Royal Institution of Naval Architects. 2018