Predicting ship machinery system condition through analytical reliability tools and artificial neural networks

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Inadequate ship machinery maintenance can increase equipment failure posing a threat to the environment, affecting performance, having a great impact in terms of business losses by reducing ship availability and increasing downtime and moreover increasing the potential of major accidents occurring and endangering lives on-board. However, machinery condition and fault developing trends are often highly nonlinear and time-series dependent. This paper addresses the above by developing a neural network methodology alongside reliability analysis tools. Critical ship main engine systems/components are used as input in a dynamic time series neural network, in order to monitor and predict future values of physical parameters related to ship critical systems. The critical main engine systems/components and their relevant parameters to be monitored are identified though the combination of Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA). A case study of a Panamax size container ship is presented in which Artificial Neural Networks (ANN) are used to predict the upcoming future values of all main engine cylinders exhaust gas temperatures, identified as critical parameters through the FTA and FMEA tools. The suggested methodology alongside the case study results for the main engine system demonstrate that ANN predictions were accurate and can provide the platform for predictive maintenance strategies that can assist decision makers in selecting the correct maintenance actions for critical ship machinery. The case study results for the main engine system demonstrated that the ANN predictions were accurate based on past observations. The proposed methodology successfully presented a systematic approach for identifying critical systems/components through FTA/FMEA and monitoring their physical parameters through the ANN model.
LanguageEnglish
Pages404-415
Number of pages12
JournalOcean Engineering
Volume152
Early online date16 Nov 2017
DOIs
Publication statusPublished - 15 Mar 2018

Fingerprint

Machinery
Ships
Neural networks
Fault tree analysis
Failure modes
Engines
Time series
Engine cylinders
Reliability analysis
Exhaust gases
Containers
Accidents
Availability
Monitoring
Industry
Temperature

Keywords

  • predictive maintenance
  • FMEA
  • fault tree analysis
  • artificial neural networks
  • time series

Cite this

@article{c4bed528e7fb4247be1491af753c1dfc,
title = "Predicting ship machinery system condition through analytical reliability tools and artificial neural networks",
abstract = "Inadequate ship machinery maintenance can increase equipment failure posing a threat to the environment, affecting performance, having a great impact in terms of business losses by reducing ship availability and increasing downtime and moreover increasing the potential of major accidents occurring and endangering lives on-board. However, machinery condition and fault developing trends are often highly nonlinear and time-series dependent. This paper addresses the above by developing a neural network methodology alongside reliability analysis tools. Critical ship main engine systems/components are used as input in a dynamic time series neural network, in order to monitor and predict future values of physical parameters related to ship critical systems. The critical main engine systems/components and their relevant parameters to be monitored are identified though the combination of Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA). A case study of a Panamax size container ship is presented in which Artificial Neural Networks (ANN) are used to predict the upcoming future values of all main engine cylinders exhaust gas temperatures, identified as critical parameters through the FTA and FMEA tools. The suggested methodology alongside the case study results for the main engine system demonstrate that ANN predictions were accurate and can provide the platform for predictive maintenance strategies that can assist decision makers in selecting the correct maintenance actions for critical ship machinery. The case study results for the main engine system demonstrated that the ANN predictions were accurate based on past observations. The proposed methodology successfully presented a systematic approach for identifying critical systems/components through FTA/FMEA and monitoring their physical parameters through the ANN model.",
keywords = "predictive maintenance, FMEA, fault tree analysis, artificial neural networks, time series",
author = "I. Lazakis and Y. Raptodimos and T. Varelas",
year = "2018",
month = "3",
day = "15",
doi = "10.1016/j.oceaneng.2017.11.017",
language = "English",
volume = "152",
pages = "404--415",
journal = "Ocean Engineering",
issn = "0029-8018",
publisher = "Elsevier",

}

Predicting ship machinery system condition through analytical reliability tools and artificial neural networks. / Lazakis, I.; Raptodimos, Y.; Varelas, T.

In: Ocean Engineering, Vol. 152, 15.03.2018, p. 404-415.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting ship machinery system condition through analytical reliability tools and artificial neural networks

AU - Lazakis, I.

AU - Raptodimos, Y.

AU - Varelas, T.

PY - 2018/3/15

Y1 - 2018/3/15

N2 - Inadequate ship machinery maintenance can increase equipment failure posing a threat to the environment, affecting performance, having a great impact in terms of business losses by reducing ship availability and increasing downtime and moreover increasing the potential of major accidents occurring and endangering lives on-board. However, machinery condition and fault developing trends are often highly nonlinear and time-series dependent. This paper addresses the above by developing a neural network methodology alongside reliability analysis tools. Critical ship main engine systems/components are used as input in a dynamic time series neural network, in order to monitor and predict future values of physical parameters related to ship critical systems. The critical main engine systems/components and their relevant parameters to be monitored are identified though the combination of Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA). A case study of a Panamax size container ship is presented in which Artificial Neural Networks (ANN) are used to predict the upcoming future values of all main engine cylinders exhaust gas temperatures, identified as critical parameters through the FTA and FMEA tools. The suggested methodology alongside the case study results for the main engine system demonstrate that ANN predictions were accurate and can provide the platform for predictive maintenance strategies that can assist decision makers in selecting the correct maintenance actions for critical ship machinery. The case study results for the main engine system demonstrated that the ANN predictions were accurate based on past observations. The proposed methodology successfully presented a systematic approach for identifying critical systems/components through FTA/FMEA and monitoring their physical parameters through the ANN model.

AB - Inadequate ship machinery maintenance can increase equipment failure posing a threat to the environment, affecting performance, having a great impact in terms of business losses by reducing ship availability and increasing downtime and moreover increasing the potential of major accidents occurring and endangering lives on-board. However, machinery condition and fault developing trends are often highly nonlinear and time-series dependent. This paper addresses the above by developing a neural network methodology alongside reliability analysis tools. Critical ship main engine systems/components are used as input in a dynamic time series neural network, in order to monitor and predict future values of physical parameters related to ship critical systems. The critical main engine systems/components and their relevant parameters to be monitored are identified though the combination of Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA). A case study of a Panamax size container ship is presented in which Artificial Neural Networks (ANN) are used to predict the upcoming future values of all main engine cylinders exhaust gas temperatures, identified as critical parameters through the FTA and FMEA tools. The suggested methodology alongside the case study results for the main engine system demonstrate that ANN predictions were accurate and can provide the platform for predictive maintenance strategies that can assist decision makers in selecting the correct maintenance actions for critical ship machinery. The case study results for the main engine system demonstrated that the ANN predictions were accurate based on past observations. The proposed methodology successfully presented a systematic approach for identifying critical systems/components through FTA/FMEA and monitoring their physical parameters through the ANN model.

KW - predictive maintenance

KW - FMEA

KW - fault tree analysis

KW - artificial neural networks

KW - time series

UR - http://www.sciencedirect.com/science/journal/00298018?sdc=2

U2 - 10.1016/j.oceaneng.2017.11.017

DO - 10.1016/j.oceaneng.2017.11.017

M3 - Article

VL - 152

SP - 404

EP - 415

JO - Ocean Engineering

T2 - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -