Implementing unsupervised learning algorithm for marine engine data clustering applications

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

Abstract

Data preparation and processing is of great importance in a ship condition monitoring tool, as inaccurate and misinterpretation of data can significantly affect the condition monitoring accuracy and performance. Data for performance parameters related to the case study of a Panamax container ship main engine are clustered using an artificial neural network, the Self-Organizing Map (SOM). Neighbouring clusters are compared through a distance metric to examine the existence of data similarities. Additionally, the SOM has a supplementary functionality of identifying data clusters exceeding thresholds, consequently providing diagnostics connected to a Failure Mode and Effects Analysis (FMEA) for the main engine, providing valuable insight and information regarding potential faults. The SOM model is validated through actual data extracted from the case study. Moreover, simulated data representing data exceeding alarm levels for the engine fuel oil system demonstrate the capabilities of the SOM clustering process in combination with the associated FMEA results.
LanguageEnglish
Title of host publicationProceedings of the 2018 Smart Ship Technology Conference
Place of PublicationLondon
PublisherRoyal Institution of Naval Architects
Number of pages8
Publication statusPublished - 24 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

Marine engines
Unsupervised learning
Self organizing maps
Learning algorithms
Condition monitoring
Engines
Failure modes
Ships
Fuel oils
Containers
Neural networks
Processing

Keywords

  • data clustering
  • marine engine
  • FMEA
  • condition monitoring
  • self organising maps

Cite this

Raptodimos, Y., & Lazakis, I. (2018). Implementing unsupervised learning algorithm for marine engine data clustering applications. In Proceedings of the 2018 Smart Ship Technology Conference London: Royal Institution of Naval Architects.
Raptodimos, Yiannis ; Lazakis, Iraklis. / Implementing unsupervised learning algorithm for marine engine data clustering applications. Proceedings of the 2018 Smart Ship Technology Conference. London : Royal Institution of Naval Architects, 2018.
@inproceedings{9d1e071c0aa04b6db8e907e26875637a,
title = "Implementing unsupervised learning algorithm for marine engine data clustering applications",
abstract = "Data preparation and processing is of great importance in a ship condition monitoring tool, as inaccurate and misinterpretation of data can significantly affect the condition monitoring accuracy and performance. Data for performance parameters related to the case study of a Panamax container ship main engine are clustered using an artificial neural network, the Self-Organizing Map (SOM). Neighbouring clusters are compared through a distance metric to examine the existence of data similarities. Additionally, the SOM has a supplementary functionality of identifying data clusters exceeding thresholds, consequently providing diagnostics connected to a Failure Mode and Effects Analysis (FMEA) for the main engine, providing valuable insight and information regarding potential faults. The SOM model is validated through actual data extracted from the case study. Moreover, simulated data representing data exceeding alarm levels for the engine fuel oil system demonstrate the capabilities of the SOM clustering process in combination with the associated FMEA results.",
keywords = "data clustering, marine engine, FMEA, condition monitoring, self organising maps",
author = "Yiannis Raptodimos and Iraklis Lazakis",
year = "2018",
month = "1",
day = "24",
language = "English",
booktitle = "Proceedings of the 2018 Smart Ship Technology Conference",
publisher = "Royal Institution of Naval Architects",
address = "United Kingdom",

}

Raptodimos, Y & Lazakis, I 2018, Implementing unsupervised learning algorithm for marine engine data clustering applications. 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.

Implementing unsupervised learning algorithm for marine engine data clustering applications. / Raptodimos, Yiannis; Lazakis, Iraklis.

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 - Implementing unsupervised learning algorithm for marine engine data clustering applications

AU - Raptodimos, Yiannis

AU - Lazakis, Iraklis

PY - 2018/1/24

Y1 - 2018/1/24

N2 - Data preparation and processing is of great importance in a ship condition monitoring tool, as inaccurate and misinterpretation of data can significantly affect the condition monitoring accuracy and performance. Data for performance parameters related to the case study of a Panamax container ship main engine are clustered using an artificial neural network, the Self-Organizing Map (SOM). Neighbouring clusters are compared through a distance metric to examine the existence of data similarities. Additionally, the SOM has a supplementary functionality of identifying data clusters exceeding thresholds, consequently providing diagnostics connected to a Failure Mode and Effects Analysis (FMEA) for the main engine, providing valuable insight and information regarding potential faults. The SOM model is validated through actual data extracted from the case study. Moreover, simulated data representing data exceeding alarm levels for the engine fuel oil system demonstrate the capabilities of the SOM clustering process in combination with the associated FMEA results.

AB - Data preparation and processing is of great importance in a ship condition monitoring tool, as inaccurate and misinterpretation of data can significantly affect the condition monitoring accuracy and performance. Data for performance parameters related to the case study of a Panamax container ship main engine are clustered using an artificial neural network, the Self-Organizing Map (SOM). Neighbouring clusters are compared through a distance metric to examine the existence of data similarities. Additionally, the SOM has a supplementary functionality of identifying data clusters exceeding thresholds, consequently providing diagnostics connected to a Failure Mode and Effects Analysis (FMEA) for the main engine, providing valuable insight and information regarding potential faults. The SOM model is validated through actual data extracted from the case study. Moreover, simulated data representing data exceeding alarm levels for the engine fuel oil system demonstrate the capabilities of the SOM clustering process in combination with the associated FMEA results.

KW - data clustering

KW - marine engine

KW - FMEA

KW - condition monitoring

KW - self organising maps

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 -

Raptodimos Y, Lazakis I. Implementing unsupervised learning algorithm for marine engine data clustering applications. In Proceedings of the 2018 Smart Ship Technology Conference. London: Royal Institution of Naval Architects. 2018