Application of artificial neural network in deoxygenation of water by glucoseoxidase immobilized in calcium alginate/MnO2 composite

Abstract

A three-layer artificial neural network (ANN) model was developed to predict the remained DO (deoxygenation) in water after DO removal with an enzymatic granular biocatalyst (GB), based on the experimental data obtained in a laboratory stirring batch study. The effects of operational parameters such as initial pH, initial glucose concentration and temperature on DO removal were investigated. On the basis of batch reactor test results, the optimum value of operating temperature, glucose concentration and pH were found to be 30oC, 80 mM and 7, respectively. After back-propagation training, the ANN model was able to predict the remained DO with a tangent sigmoid function (tansig) at hidden layer with 7 neurons and a linear transfer function (purelin) at the output layer. The linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of 0.995 for three model variables used in this study.