Comparison of supervised classification algorithms combined with feature extraction and selection: Application to a turbo-generator rotor fault detection
Alexandre Bacchus
(1, 2, 3)
,
Mélisande Biet
(2)
,
Ludovic Macaire
(3)
,
Yvonnick Le Menach
(2)
,
Abdelmounaïm Tounzi
(2)
Ludovic Macaire
- Fonction : Auteur
- PersonId : 10991
- IdHAL : ludovic-macaire
- ORCID : 0000-0002-4375-5169
- IdRef : 06065614X
Abdelmounaïm Tounzi
- Fonction : Auteur
- PersonId : 17796
- IdHAL : abdelmounaim-tounzi
- ORCID : 0000-0001-6166-6349
- IdRef : 136806910
Résumé
The goal of this paper consists in applying pattern recognition methods to turbo-generators. Previous works have shown that a monitor, thanks to pattern recognition, is practical on asynchronous machines. This procedure has rarely taken advantage of these methods for turbogenerator. The statistical model has been obtained from harmonics extracted from flux probes and from stator current and voltage. For this purpose, the main way is to build a learning matrix to predict the functional state of a new measurement. Finally, three classifiers have been compared: k Nearest Neighbors, Linear Discriminant Analysis and Support Vector Machines. The best classification result is obtained by Linear Discriminant Analysis combined with Factorial Discriminant Analysis achieving a score of 84.6%.
Format du dépôt | Notice |
---|---|
Type de dépôt | Communication dans un congrès |
Titre |
en
Comparison of supervised classification algorithms combined with feature extraction and selection: Application to a turbo-generator rotor fault detection
|
Résumé |
en
The goal of this paper consists in applying pattern recognition methods to turbo-generators. Previous works have shown that a monitor, thanks to pattern recognition, is practical on asynchronous machines. This procedure has rarely taken advantage of these methods for turbogenerator. The statistical model has been obtained from harmonics extracted from flux probes and from stator current and voltage. For this purpose, the main way is to build a learning matrix to predict the functional state of a new measurement. Finally, three classifiers have been compared: k Nearest Neighbors, Linear Discriminant Analysis and Support Vector Machines. The best classification result is obtained by Linear Discriminant Analysis combined with Factorial Discriminant Analysis achieving a score of 84.6%.
|
Auteur(s) |
Alexandre Bacchus
1, 2, 3
, Mélisande Biet
2
, Ludovic Macaire
3
, Yvonnick Le Menach
2
, Abdelmounaïm Tounzi
2
1
CRIStAL -
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
( 410272 )
- Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq
- France
2
L2EP -
Laboratoire d’Électrotechnique et d’Électronique de Puissance - ULR 2697
( 13338 )
- Université de Lille - Bâtiment ESPRIT, Cité scientifique - 59655 Villeneuve d'Ascq
- France
3
LAGIS-SI
( 390300 )
- France
|
Titre du congrès |
2013 9th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED)
|
Ville |
Valencia
|
Pays |
Espagne
|
Langue du document |
Anglais
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Invité |
Non
|
Audience |
Internationale
|
Actes |
Oui
|
Date de publication |
2013
|
Page/Identifiant |
558--565
|
Date début congrès |
2013
|
Titre de la collection |
2013 9th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED)
|
Domaine(s) |
|
DOI | 10.1109/DEMPED.2013.6645770 |
Loading...