Fault tree analysis and artificial neural network modelling for establishing a predictive ship machinery maintenance methodology

Raptodimos, Y and Lazakis, I; (2017) Fault tree analysis and artificial neural network modelling for establishing a predictive ship machinery maintenance methodology. In: International Conference on Smart Ship Technology 2017. Royal Institution of Naval Architects, GBR.

[thumbnail of Raptodimos-Lazakis-ICSST-2017-neural-network-modelling-for-establishing-a-predictive-ship-machinery-maintenance-methodology]
Preview
 Text. Filename: Raptodimos_Lazakis_ICSST_2017_neural_network_modelling_for_establishing_a_predictive_ship_machinery_maintenance_methodology.pdf
Accepted Author Manuscript
Download (645kB)| Preview

Abstract

A dynamic fault tree model for a ship main engine is developed in order to analyse and identify critical systems/components of the main engine. The identified most critical systems are then used as input in an artificial neural network. An autoregressive dynamic time series neural network modelling approach is examined in a container ship case study, in order to monitor and predict future values of selected physical parameters of the most critical ship machinery equipment obtained from the fault tree analysis. The case study results of the combination of the fault tree analysis and artificial neural network model demonstrated promising prospects for establishing a dense methodology for ship machinery predictive maintenance by successfully identifying critical ship machinery systems and accurately forecasting the performance of machinery parameters.

ORCID iDs

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