Article (Scientific journals)
A fault detector/classifier for closed-ring power generators using machine learning
Quintanilha, Igor M.; Elias, Vitor R. M.; Silva, Felipe B. et al.
2021In Reliability Engineering and System Safety
Peer Reviewed verified by ORBi
 

Files


Full Text
Elsevier2021-AuthorPostPrint.pdf
Author postprint (608.82 kB)
Request a copy

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Condition-based monitoring; Detection; Classification; Machine learning; Principal components; Random forests
Abstract :
[en] Condition-based monitoring of power-generation systems is naturally becoming a standard approach in industry due to its inherent capability of fast fault detection, thus improving system efficiency and reducing operational costs. Most such systems employ expertise-reliant rule-based methods. This work proposes a different framework, in which machine-learning algorithms are used for detecting and classifying several fault types in a power-generation system of dynamically positioned vessels. First, principal component analysis is used to extract relevant information from labeled data. A random-forest algorithm then learns hidden patterns from faulty behavior in order to infer fault detection from unlabeled data. Results on fault detection and classification for the proposed approach show significant improvement on accuracy and speed when compared to results from rule-based methods over a comprehensive database.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Quintanilha, Igor M.
Elias, Vitor R. M.
Silva, Felipe B.
Fonini, Pedro A. M.
Silva, Eduardo A. B.
Netto, Sergio L.
Apolinário Jr., José A.
Campos, Marcello L. R.
Alves Martins, Wallace ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Wold, Lars E.
Andersen, Rune B.
External co-authors :
yes
Language :
English
Title :
A fault detector/classifier for closed-ring power generators using machine learning
Publication date :
2021
Journal title :
Reliability Engineering and System Safety
ISSN :
1879-0836
Publisher :
Elsevier, Oxford, Netherlands
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Security, Reliability and Trust
Available on ORBilu :
since 12 April 2021

Statistics


Number of views
67 (0 by Unilu)
Number of downloads
0 (0 by Unilu)

Scopus citations®
 
10
Scopus citations®
without self-citations
10
OpenCitations
 
4
WoS citations
 
8

Bibliography


Similar publications



Contact ORBilu