A neural network approach for the diagnosis of the continuous pulp digester - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2001

A neural network approach for the diagnosis of the continuous pulp digester

Résumé

A strategy for detection of feedstock variations in a continuous pulp digester is presented. A Gaussian Radial Basis Function Neural Network is used to infer these unmeasured variations. The absence of plant data motivates the development of training set data. The efficiency and limitation of the approach is demonstrated with a first principles model.
Fichier principal
Vignette du fichier
duf01-Digester-Workshop-Annapolis-paper.pdf (721.13 Ko) Télécharger le fichier
duf01-Digester-Workshop-Annapolis-talk.pdf (971.86 Ko) Télécharger le fichier
duf01-Digester-Workshop-Annapolis-talk.ppt (3.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Autre
Format : Autre

Dates et versions

hal-00352521 , version 1 (13-01-2009)
hal-00352521 , version 2 (22-01-2009)

Identifiants

  • HAL Id : hal-00352521 , version 2

Citer

Pascal Dufour, Sharad Bhartiya, Prasad S. Dhurjati, Francis J. Doyle Iii. A neural network approach for the diagnosis of the continuous pulp digester. Digester Workshop, Jun 2001, Annapolis, MD, United States. ⟨hal-00352521v2⟩

Collections

TDS-MACS
102 Consultations
160 Téléchargements

Partager

Gmail Facebook X LinkedIn More