Please use this identifier to cite or link to this item:
Title: Modeling of desilication of green liquor using artificial neural networks
Authors: Mandavgane, S A
Pandharipande, S L
Subramanian, D
Keywords: Green liquor;Carbonation;Pulp and paper mills;Artificial neural networks (ANN)
Issue Date: Mar-2006
Publisher: CSIR
IPC Code: B01D3/26
Abstract: In the recovery section of pulp and paper mill the smelt from the furnace is dissolved in water, the green coloured solution is called as green liquor. The green liquor obtained from paper mills using agricultural residues as raw material contains silica. This silica interferes in every stage of recovery section. Desilication of green liquor is essential as it restricts silica entry into the downstream units and silica re-entry through recovered and recycled digester chemicals. In present work, multi layer perceptron (MLP) ANN with GDR based learning have been developed for estimation of silica concentration and degree of desilication as a function of pH and time. The numbers of neurons and hidden layers were varied to get the most accurate ANN model. The ANN models thus developed with three hidden layers were found to be of good accuracy level, both for training and test data set.
Page(s): 168-172
ISSN: 0975-0991 (Online); 0971-457X (Print)
Appears in Collections:IJCT Vol.13(2) [March 2006]

Files in This Item:
File Description SizeFormat 
IJCT 13(2) 168-172.pdf122.75 kBAdobe PDFView/Open

Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.