摘要
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 TiCl4/Hl, 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.
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 TiCl4/H1, 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.
出处
《中国有色金属学会会刊：英文版》
CSCD
2006年第B02期865-868,共4页
Transactions of Nonferrous Metals Society of China
基金
Project (2004E113) Supported by the Natural Science Basic Research Plan of Shaanxi Province of China
