<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper presents a model to predict Electrical Power Generator (EPG) faults. The fault tree (FT) model is developed and used to help maintenance engineers in fault analysis procedure of this rotating machine. By identifying the main, intermediate and basic events it’s possible to construct the FT with logical reasoning. The top dreaded event is defined. By using a Bayesian network (BN) as a complementary tool, fault prediction of the EPG becomes possible and easy. By using the developed BN, the probability of occurrence of the top event (EPG failure) is calculated. Also, by this approach, we can process complex information that causes system faults in an easy and simple way. The essential elements to do this analysis are the reliable and good exploitation of the information previously stored in the system. The use of the BN in combination with the FT gives the possibility of qualitative and quantitative analysis, diagnosis, and prediction of faults from the same Bayesian model. The flexibility of the proposed BN model in this paper allows better and precise decision making. Also, priorities regarding maintenance job are defined and resources are a priori prepared.</p>
</abstract>

This paper presents a model to predict Electrical Power Generator (EPG) faults. The fault tree (FT) model is developed and used to help maintenance engineers in fault analysis procedure of this rotating machine. By identifying the main, intermediate and basic events it’s possible to construct the FT with logical reasoning. The top dreaded event is defined. By using a Bayesian network (BN) as a complementary tool, fault prediction of the EPG becomes possible and easy. By using the developed BN, the probability of occurrence of the top event (EPG failure) is calculated. Also, by this approach, we can process complex information that causes system faults in an easy and simple way. The essential elements to do this analysis are the reliable and good exploitation of the information previously stored in the system. The use of the BN in combination with the FT gives the possibility of qualitative and quantitative analysis, diagnosis, and prediction of faults from the same Bayesian model. The flexibility of the proposed BN model in this paper allows better and precise decision making. Also, priorities regarding maintenance job are defined and resources are a priori prepared.

Electrical Power Generator Faults Analysis Using Fault Tree and Bayesian Network

Laboratory of Research on Electromechanical and Dependability

Acta Universitatis Sapientiae, Electrical and Mechanical Engineering

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Electrical Power Generator Faults Analysis Using Fault Tree and Bayesian Network"}

This paper presents a model to predict Electrical Power Generator (EPG) faults. The fault tree (FT) model is developed and used to help maintenance engineers...

Electrical Power Generator Faults Analysis Using Fault Tree and Bayesian Network

Published Online: Dec 25, 2023

Page range: 45 - 59

Received: Mar 16, 2023

DOI: https://doi.org/10.2478/auseme-2023-0004

Keywords
Bayesian network, fault tree, electrical generator, fault prediction, information, maintenance priorities

© 2023 Toufik Touil et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Electrical Power Generator Faults Analysis Using Fault Tree and Bayesian Network

Published Online: Dec 25, 2023

Page range: 45 - 59

Received: Mar 16, 2023

DOI: https://doi.org/10.2478/auseme-2023-0004

KeywordsBayesian network, fault tree, electrical generator, fault prediction, information, maintenance priorities

© 2023 Toufik Touil et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Keywords
Bayesian network, fault tree, electrical generator, fault prediction, information, maintenance priorities