Journal of Inorganic Materials

• Research Paper • Previous Articles     Next Articles

Application of Artificial Neural Network (ANN) Technique to the Formulation Design of BaTiO3 Dielectric Ceramics

GUO Dong1; WANG Yong-Li1; XIA Jun-Tao2; LI Long-Tu1; GUI Zhi-Lun1   

  1. 1. Dept. Materials Science & Engineering; Tsinghua University; Beijing 100084; China; 2. School of Chemical Engineering and Materials Science; Beijing Institute of Technology; Beijing 100081, China
  • Received:2001-06-29 Revised:2001-07-25 Published:2002-07-20 Online:2002-07-20

Abstract: Application of the artificial neural network (ANN) to the formulation design of BaTiO3 based dielectrics was carried through for the first time. Based on the
homogenous experimental design, the experimental results of 21 samples were analyzed by a three-layered BP network model. The results were also expressed by intuitionistic
graphics. In addition, optimized formulations were calculated and the optimized ε25 output values were in accordance with experiments. The three-layer
BP network proved to be a very useful tool in dealing with problems with serious non-linearity encountered in the formulation design of dielectric ceramics.

Key words: BaTiO3, dielectric constant, artificial neural network, BP algorithm

CLC Number: