Predictive model based on artificial neural net for purity of perovskite-type SrTiO3 nanocrystalline

A three-layer structure back-propagation network model based on the non-linear relationship between the purity of the perovskite-type SrTiO3 nano-crystal samples and the technology factors, such as reaction time, reaction temperature, raw material adding amount of NaOH and SrCl2, and the rate of TiCl4Hl, was established. The input variables were pretreated by using the main component analysis firstly. Moreover, the momentum terms were introduced so as to accelerate the converging rate and avoid the non-converging situation. At the same time, the variable learning speed was adopted. The results show that the improved back propagation neural network model is very efficient for the prediction of the perovskite-type SrTiO3 nano-crystal sample purity.