Optimizing of Iron bioleaching from a contaminated kaolin clay by the use of artificial neural network

In this research, bioleaching of Iron from highly contaminated kaolin sample with Aspergillus niger was optimized. In order to study the effect of initial pH, sucrose and spore concentration on Iron, oxalic and citric acid concentration, more than twenty experiments were performed. The resulted data were utilized to train, validate and test the two layer artificial neural network (ANN). In order to minimize the over fitting, Bayesian regularization and early stopping methods with back propagation technique were utilized as training algorithm of ANN. Good validation for prediction of Iron removal percentage was resulted due to the inhibition of over-fitting problems with selection of appropriate ANN topology and training algorithm. The results showed that optimized condition of initial pH, sucrose and spore concentration to achieve high Iron removal (about 65%) should be 6, 60 g/l and 3.5×107 spore/l, respectively.