Modeling and analysis of the electrical properties of PZT through neural networks

Application of ANN (Artificial neural network) to the electrical properties analysis of PZT is discussed in this paper. The same set of results of PZT samples were analyzed by a back-propagation (BP) network in comparison with a multiple nonlinear regression analysis (MNLR) model. The results revealed that the ANN model is much more accurate than MNLR model. The ANN approach also gave quite encouraging predictions for formulations not included in the train set samples, indicating that the BP network is a very useful and accurate tool for the properties analysis and prediction of multi-component solid solution piezoelectric ceramics.