Predicting the Dielectric Constants of (Zr0.7Sn0.3)TiO4 Ceramics Using Artificial Neural Network

Back-propagation artificial neural network was developed to predict the dielectric constants of (Zr_0.7Sn_0.3)TiO₄ ceramics. Leave-one out method was used to train the ANN model. Test results showed that the prediction performance of the ANN model is satisfactory: the scatter dots distribute along the 0__45°diagonal line in the scatter diagram, the values of statistical criteria are 0.7489(MSE), 2.01%(MSRE), and 1.3061(VOF) respectively. After being trained, the ANN model was used to predict the dielectric constants of several samples, the prediction errors are 1.06(MSE), 2.78%(MSRE), and 1.6971(VOF) respectively, which show that the prediction performance of the ANN model is satisfactory. The work is helpful of the development of high-performance electronic ceramics and has important theoretical meaning and application value.