A quantitative structure-property relationship (QSPR) study based on partial least squares (PLS) and artificial neural network (ANN) was developed for the prediction of ferric iron precipitation in bioleaching process. The leaching temperature, initial pH, oxidation/reduction potential (ORP), ferrous concentration and particle size of ore were used as inputs to the network. The output of the model was ferric iron precipitation. The optimal condition of the neural network was obtained by adjusting various parameters by trial-and-error. After optimization and training of the network according to back-propagation algorithm, a 5-5-1 neural network was generated for prediction of ferric iron precipitation. The root mean square error for the neural network calculated ferric iron precipitation for training, prediction and validation set were 32.860, 40.739 and 35.890, respectively, which were smaller than those obtained by the PLS model (180.972, 165.047 and 149.950, respectively). The obtained results reveal the reliability and good predictivity of the neural network model for the prediction of ferric iron precipitation in bioleaching process.
