New Informative Features for Fault Diagnosis of Industrial Systems by Supervised Classification

Abstract : The purpose of this article is to present a method for industrial process diagnosis. We are interested in fault diagnosis considered as a supervised classication task. The interest of the proposed method is to take into account new features (and so new informations) in the classifier. These new features are probabilities extracted from a Bayesian network comparing the faulty observations to the normal operating conditions. The performances of this method are evaluated on the data of a benchmark example: the Tennessee Eastman Process. Three kinds of fault are taken into account on this complex process. We show on this example that the addition of these new features allows to decrease the misclassification rate.
Type de document :
Communication dans un congrès
Workshop on Advanced Control and Diagnosis (ACD'09), 2009, Zielona Gora, Poland. 2009
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00517027
Contributeur : Sylvain Verron <>
Soumis le : lundi 13 septembre 2010 - 13:59:42
Dernière modification le : lundi 13 septembre 2010 - 20:56:07
Document(s) archivé(s) le : mardi 14 décembre 2010 - 02:48:22

Fichier

verron09a.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00517027, version 1

Collections

Citation

Sylvain Verron, Teodor Tiplica, Abdessamad Kobi. New Informative Features for Fault Diagnosis of Industrial Systems by Supervised Classification. Workshop on Advanced Control and Diagnosis (ACD'09), 2009, Zielona Gora, Poland. 2009. 〈inria-00517027〉

Partager

Métriques

Consultations de la notice

90

Téléchargements de fichiers

43