An artificial neural network approach for predicting the performance of ship machinery equipment

Tools

Raptodimos, Yiannis and Lazakis, Iraklis; (2016) An artificial neural network approach for predicting the performance of ship machinery equipment. In: Maritime Safety and Operations 2016 Conference Proceedings. University of Strathclyde Publishing, GBR, pp. 95-101.

[thumbnail of Raptodimos-MSO2016-Artificial-neural-network-approach-for-predicting]
Preview
 Text. Filename: Raptodimos_MSO2016_Artificial_neural_network_approach_for_predicting.pdf
Accepted Author Manuscript
Download (466kB)| Preview

Abstract

Inadequate ship machinery maintenance can increase equipment failure posing a threat to the environment, affecting ship 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, endangering lives onboard. Efforts have being made to transform corrective/preventive maintenance techniques into predictive ones. Condition monitoring is considered as a major part of predictive maintenance. It assesses the operational health of equipment, in order to provide early warning of potential failure such that preventive maintenance action may be taken. Condition monitoring is defined as the collection and interpretation of the relevant equipment parameters for the purpose of the identification of the state of equipment changes from normal conditions and trends of the health of the equipment. The equipment condition and the fault developing trend are often highly nonlinear and time-series based. Artificial Neural Networks (ANNs) can be used due to their potential ability in nonlinear time-series trend prediction. Therefore this paper proposes the use of an autoregressive dynamic time series ANN in order to monitor and predict selected physical parameters of ship machinery equipment that contribute to the overall performance and availability, in order to predict their future values that will illustrate their performance state that will eventually lead to the correct maintenance actions and decisions.

ORCID iDs

Raptodimos, Yiannis ORCID logoORCID: https://orcid.org/0000-0002-7508-5956 and Lazakis, Iraklis ORCID logoORCID: https://orcid.org/0000-0002-6130-9410;
CORE (COnnecting REpositories)