Modeling of desilication of agro based black liquor using artificial neural networks

Abstract

Black liquor, obtained from agricultural residues and used as raw material for paper production, contains additional silica, which causes serious processing problems. In present work, multi layer perceptron (MLP) ANN with GDR based learning have been developed for estimation of silica concentration, lignin concentration, degree of desilication and delignification as a function of pH and time. ANNs model thus developed with one hidden layer was found to be of good accuracy level, both for training and test data set.