New Informative Features for Fault Diagnosis of Industrial Systems by Supervised Classification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

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

Résumé

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.
Fichier principal
Vignette du fichier
verron09a.pdf (688.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00517027 , version 1 (13-09-2010)

Identifiants

  • HAL Id : inria-00517027 , version 1

Citer

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. ⟨inria-00517027⟩

Collections

UNIV-ANGERS
58 Consultations
156 Téléchargements

Partager

Gmail Facebook X LinkedIn More