Comparison between artificial neural networks and Hermia’s models to assess ultrafiltration performance

•Feed-forward artificial neural network was employed to model crossflow UF.•The pretreatment and internal architecture of the ANNs were studied.•The ANNs achieved very accurate fitting results to experimental data.•ANNs achieve fittings that were comparable to Hermia’s models. In this work, flux dec...

Full description

Saved in:
Bibliographic Details
Published inSeparation and purification technology Vol. 170; pp. 434 - 444
Main Authors Corbatón-Báguena, María-José, Vincent-Vela, María-Cinta, Gozálvez-Zafrilla, José-Marcial, Álvarez-Blanco, Silvia, Lora-García, Jaime, Catalán-Martínez, David
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.10.2016
Subjects
Accuracy
Artificial neural networks
Computer simulation
Crossflow ultrafiltration
Dynamics
Fittings
Flux
Fouling
Mathematical models
Modeling
Ultrafiltration
Fouling
Modeling
Crossflow ultrafiltration
Artificial neural networks
Online AccessGet full text

Cover

More Information
Summary:•Feed-forward artificial neural network was employed to model crossflow UF.•The pretreatment and internal architecture of the ANNs were studied.•The ANNs achieved very accurate fitting results to experimental data.•ANNs achieve fittings that were comparable to Hermia’s models. In this work, flux decline during crossflow ultrafiltration of macromolecules with ceramic membranes has been modeled using artificial neural networks. The artificial neural network tested was the multilayer perceptron. Operating parameters (transmembrane pressure, crossflow velocity and time) and dynamic fouling were used as inputs to predict the permeate flux. Several pretreatments of the experimental data and the optimal selection of the parameters of the neural networks were studied to improve the fitting accuracy. The fitting accuracy obtained with artificial neural networks was compared with Hermia pore blocking models adapted to crossflow ultrafiltration. The artificial neural networks generate simulations whose performance was comparable to that of Hermia’s models adapted to crossflow ultrafiltration. Considering the computational speed, high accuracy and the ease of the artificial neural networks methodology, they are a competitive, powerful and fast alternative for dynamic crossflow ultrafiltration modeling.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1383-5866
1873-3794
DOI:10.1016/j.seppur.2016.07.007