Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications

Yiannis Raptodimos, Iraklis Lazakis

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Condition monitoring is the process of monitoring parameters expressing machinery condition, interpreting them for the identification of change which could indicate developing faults. Data processing is important in a ship condition monitoring software tool, as misinterpretation of data can significantly affect the accuracy and performance of the predictions made. Data for key performance parameters for a PANAMAX container ship main engine cylinder are clustered using a two-stage approach. Initially, the data is clustered using the artificial neural network (ANN)-self-organising map (SOM) and then the clusters are interclustered using the Euclidean distance metric into groups. The case study results demonstrate the capability of the SOM to monitor the main engine condition by identifying clusters containing data which are diverse compared to data representing normal engine operating conditions. The results obtained can be further expanded for application in diagnostic purposes, identifying faults, their causes and effects to the ship main engine.
LanguageEnglish
Pages649-656
Number of pages8
JournalShips and Offshore Structures
Volume13
Issue number6
Early online date14 Mar 2018
DOIs
Publication statusE-pub ahead of print - 14 Mar 2018

Fingerprint

Marine engines
Self organizing maps
Condition monitoring
Engines
Neural networks
Engine cylinders
Machinery
Containers
Ships
Monitoring

Keywords

  • ship condition monitoring
  • data clustering
  • ANN
  • self-organising maps
  • ship machinery

Cite this

@article{688b467203394873a4e92af1a4e9f786,
title = "Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications",
abstract = "Condition monitoring is the process of monitoring parameters expressing machinery condition, interpreting them for the identification of change which could indicate developing faults. Data processing is important in a ship condition monitoring software tool, as misinterpretation of data can significantly affect the accuracy and performance of the predictions made. Data for key performance parameters for a PANAMAX container ship main engine cylinder are clustered using a two-stage approach. Initially, the data is clustered using the artificial neural network (ANN)-self-organising map (SOM) and then the clusters are interclustered using the Euclidean distance metric into groups. The case study results demonstrate the capability of the SOM to monitor the main engine condition by identifying clusters containing data which are diverse compared to data representing normal engine operating conditions. The results obtained can be further expanded for application in diagnostic purposes, identifying faults, their causes and effects to the ship main engine.",
keywords = "ship condition monitoring, data clustering, ANN, self-organising maps, ship machinery",
author = "Yiannis Raptodimos and Iraklis Lazakis",
year = "2018",
month = "3",
day = "14",
doi = "10.1080/17445302.2018.1443694",
language = "English",
volume = "13",
pages = "649--656",
journal = "Ships and Offshore Structures",
issn = "1744-5302",
number = "6",

}

Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications. / Raptodimos, Yiannis; Lazakis, Iraklis.

In: Ships and Offshore Structures , Vol. 13, No. 6, 14.03.2018, p. 649-656.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications

AU - Raptodimos, Yiannis

AU - Lazakis, Iraklis

PY - 2018/3/14

Y1 - 2018/3/14

N2 - Condition monitoring is the process of monitoring parameters expressing machinery condition, interpreting them for the identification of change which could indicate developing faults. Data processing is important in a ship condition monitoring software tool, as misinterpretation of data can significantly affect the accuracy and performance of the predictions made. Data for key performance parameters for a PANAMAX container ship main engine cylinder are clustered using a two-stage approach. Initially, the data is clustered using the artificial neural network (ANN)-self-organising map (SOM) and then the clusters are interclustered using the Euclidean distance metric into groups. The case study results demonstrate the capability of the SOM to monitor the main engine condition by identifying clusters containing data which are diverse compared to data representing normal engine operating conditions. The results obtained can be further expanded for application in diagnostic purposes, identifying faults, their causes and effects to the ship main engine.

AB - Condition monitoring is the process of monitoring parameters expressing machinery condition, interpreting them for the identification of change which could indicate developing faults. Data processing is important in a ship condition monitoring software tool, as misinterpretation of data can significantly affect the accuracy and performance of the predictions made. Data for key performance parameters for a PANAMAX container ship main engine cylinder are clustered using a two-stage approach. Initially, the data is clustered using the artificial neural network (ANN)-self-organising map (SOM) and then the clusters are interclustered using the Euclidean distance metric into groups. The case study results demonstrate the capability of the SOM to monitor the main engine condition by identifying clusters containing data which are diverse compared to data representing normal engine operating conditions. The results obtained can be further expanded for application in diagnostic purposes, identifying faults, their causes and effects to the ship main engine.

KW - ship condition monitoring

KW - data clustering

KW - ANN

KW - self-organising maps

KW - ship machinery

U2 - 10.1080/17445302.2018.1443694

DO - 10.1080/17445302.2018.1443694

M3 - Article

VL - 13

SP - 649

EP - 656

JO - Ships and Offshore Structures

T2 - Ships and Offshore Structures

JF - Ships and Offshore Structures

SN - 1744-5302

IS - 6

ER -