Application of artificial neural network technique to the formulation design of dielectric ceramics

摘要

Application of artificial neural network (ANN) technique to the formulation design of BaTiO3 based dielectrics was carried through. Based on the homogenous experimental design the experimental results of 21 samples were analyzed by a three-layer back propagation (BP) network modeling. The results were also expressed and analyzed by intuitive graphics. Influence Of Co2O3 and Li2CO3 on the dielectric constant-temperature characteristic of BaTiO3-Nb2O5-La2O3-SM2O3 system was investigated. Optimized formulations were calculated and the optimized output values were in accordance with experiment results. It follows that the three-layer back propagation network based modeling proved to be a very useful tool in dealing with problems with serious non-linearity encountered in the formulation design of dielectric ceramics. (C) 2002 Elsevier Science B.V. All rights reserved. [References: 11]