Ship machinery condition monitoring using vibration data through supervised learning

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

383 Downloads (Pure)

Abstract

This paper aims to present an integrated methodology for the monitoring of marine machinery using vibration data. Monitoring of machinery is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. The proposed methodology will train models using pre-classified (healthy/faulty) data and then classify new data points using the models developed. For this, vibration points are first acquired, appropriately processed and stored in a database. Specific features are then extracted from the data and stored. These data are then used to train supervised models pertinent to specific machinery components. Finally, new data are compared against the models developed in order to evaluate their condition. The above will provide a flexible but robust framework for the early detection of emerging machinery faults. This will lead to minimisation of ship downtime and increase of the ship’s operability and income through operational enhancement.
Original languageEnglish
Title of host publicationProceedings of MSO 2016, International Conference on Maritime Safety and Operations
EditorsIraklis Lazakis, Gerasimos Theotokatos
Pages103-110
Number of pages8
Publication statusPublished - 13 Oct 2016
EventInternational Conference of Maritime Safety and Operations 2016 - University of Strathclyde, Glasgow, United Kingdom
Duration: 13 Oct 201614 Oct 2016
http://www.incass.eu/mso-2016/welcome/

Conference

ConferenceInternational Conference of Maritime Safety and Operations 2016
Abbreviated titleMSO 2016
CountryUnited Kingdom
CityGlasgow
Period13/10/1614/10/16
Internet address

Fingerprint

Supervised learning
Condition monitoring
Machinery
Ships
Machine vibrations
Monitoring

Keywords

  • vibration measurements
  • predictive maintenance
  • machine learning
  • condition monitoring
  • SVM

Cite this

Gkerekos, C., Lazakis, I., & Theotokatos, G. (2016). Ship machinery condition monitoring using vibration data through supervised learning. In I. Lazakis, & G. Theotokatos (Eds.), Proceedings of MSO 2016, International Conference on Maritime Safety and Operations (pp. 103-110)
Gkerekos, Christos ; Lazakis, Iraklis ; Theotokatos, Gerasimos. / Ship machinery condition monitoring using vibration data through supervised learning. Proceedings of MSO 2016, International Conference on Maritime Safety and Operations. editor / Iraklis Lazakis ; Gerasimos Theotokatos. 2016. pp. 103-110
@inproceedings{50daa07ce35744dc9620cb2fccf293f9,
title = "Ship machinery condition monitoring using vibration data through supervised learning",
abstract = "This paper aims to present an integrated methodology for the monitoring of marine machinery using vibration data. Monitoring of machinery is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. The proposed methodology will train models using pre-classified (healthy/faulty) data and then classify new data points using the models developed. For this, vibration points are first acquired, appropriately processed and stored in a database. Specific features are then extracted from the data and stored. These data are then used to train supervised models pertinent to specific machinery components. Finally, new data are compared against the models developed in order to evaluate their condition. The above will provide a flexible but robust framework for the early detection of emerging machinery faults. This will lead to minimisation of ship downtime and increase of the ship’s operability and income through operational enhancement.",
keywords = "vibration measurements, predictive maintenance, machine learning, condition monitoring, SVM",
author = "Christos Gkerekos and Iraklis Lazakis and Gerasimos Theotokatos",
year = "2016",
month = "10",
day = "13",
language = "English",
isbn = "9781909522169",
pages = "103--110",
editor = "Iraklis Lazakis and Gerasimos Theotokatos",
booktitle = "Proceedings of MSO 2016, International Conference on Maritime Safety and Operations",

}

Gkerekos, C, Lazakis, I & Theotokatos, G 2016, Ship machinery condition monitoring using vibration data through supervised learning. in I Lazakis & G Theotokatos (eds), Proceedings of MSO 2016, International Conference on Maritime Safety and Operations. pp. 103-110, International Conference of Maritime Safety and Operations 2016, Glasgow, United Kingdom, 13/10/16.

Ship machinery condition monitoring using vibration data through supervised learning. / Gkerekos, Christos; Lazakis, Iraklis; Theotokatos, Gerasimos.

Proceedings of MSO 2016, International Conference on Maritime Safety and Operations. ed. / Iraklis Lazakis; Gerasimos Theotokatos. 2016. p. 103-110.

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

TY - GEN

T1 - Ship machinery condition monitoring using vibration data through supervised learning

AU - Gkerekos, Christos

AU - Lazakis, Iraklis

AU - Theotokatos, Gerasimos

PY - 2016/10/13

Y1 - 2016/10/13

N2 - This paper aims to present an integrated methodology for the monitoring of marine machinery using vibration data. Monitoring of machinery is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. The proposed methodology will train models using pre-classified (healthy/faulty) data and then classify new data points using the models developed. For this, vibration points are first acquired, appropriately processed and stored in a database. Specific features are then extracted from the data and stored. These data are then used to train supervised models pertinent to specific machinery components. Finally, new data are compared against the models developed in order to evaluate their condition. The above will provide a flexible but robust framework for the early detection of emerging machinery faults. This will lead to minimisation of ship downtime and increase of the ship’s operability and income through operational enhancement.

AB - This paper aims to present an integrated methodology for the monitoring of marine machinery using vibration data. Monitoring of machinery is a crucial aspect of maintenance optimisation that is required for the vessel operation to remain sustainable and profitable. The proposed methodology will train models using pre-classified (healthy/faulty) data and then classify new data points using the models developed. For this, vibration points are first acquired, appropriately processed and stored in a database. Specific features are then extracted from the data and stored. These data are then used to train supervised models pertinent to specific machinery components. Finally, new data are compared against the models developed in order to evaluate their condition. The above will provide a flexible but robust framework for the early detection of emerging machinery faults. This will lead to minimisation of ship downtime and increase of the ship’s operability and income through operational enhancement.

KW - vibration measurements

KW - predictive maintenance

KW - machine learning

KW - condition monitoring

KW - SVM

UR - http://www.incass.eu/mso-2016/welcome/

M3 - Conference contribution book

SN - 9781909522169

SP - 103

EP - 110

BT - Proceedings of MSO 2016, International Conference on Maritime Safety and Operations

A2 - Lazakis, Iraklis

A2 - Theotokatos, Gerasimos

ER -

Gkerekos C, Lazakis I, Theotokatos G. Ship machinery condition monitoring using vibration data through supervised learning. In Lazakis I, Theotokatos G, editors, Proceedings of MSO 2016, International Conference on Maritime Safety and Operations. 2016. p. 103-110