Dornier Manuel, Decloux Martine, Trystram Gilles, Lebert André. 1995. Interest of neural networks for the optimizatof the crossflow filtration process. Lebensmittel-Wissenschaft und Technologie - Food Science and Technology, 28 (3) : 300-309.
Autre titre : Intérêt des réseaux neuraux pour l'optimisation des processus de filtration des flux croisés
Résumé : In order to build up a model representing the effect of transmembrane pressure and crossflow velocity on crossflow filtration results at quasi-steady state, an approach based on neural networks is proposed. For filtrations of various products (raw cane sugar remelts, natural gum solution) on different membranes (micro- and ultrafiltration) with or without co-current permeate flow, the modelling of both permeate flux and retention rate could be obtained after only five experimental trials. Compared to more classical modelling techniques, the neural networks showed to be sometimes better suited and are useful when the effects of hydrodynammical conditions on filtration results are strongly nonlinear. Thanks to established models, it was possible to determine, with a good safety margin, an optimum region in every case studied.
Mots-clés Agrovoc : écoulement de fluide, hydrodynamique, filtration, membrane, modèle de simulation, modélisation
Classification Agris : Q02 - Traitement et conservation des produits alimentaires
U10 - Informatique, mathématiques et statistiques
Auteurs et affiliations
- Dornier Manuel
- Decloux Martine
- Trystram Gilles
- Lebert André
Autres liens de la publication
- Document en bibliothèque
- Localisation du document : CD_BR6380 [(Bibliothèque de Lavalette)] ; CD_PE343 [(Bibliothèque de Lavalette)]
Source : Cirad - Agritrop (https://agritrop.cirad.fr/389877/)
[ Page générée et mise en cache le 2024-12-18 ]
