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

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 (Zr0.7Sn0.3)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.

[1] D. Signorini,et al. Neural networks , 1995, The Lancet.

[2] D. J. C. Mackay,et al. Estimation of Hot Torsion Stress Strain Curves in Iron Alloys Using a Neural Network Analysis , 1999 .

[3] Sybrand van der Zwaag,et al. Effects of Carbon Concentration and Cooling Rate on Continuous Cooling Transformations Predicted by Artificial Neural Network , 1999 .

[4] Matthieu Hamel,et al. Journal of Medicinal Chemistry , 2010 .

[5] Ah Chung Tsoi,et al. Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[6] J. Billingsley. Mathematics for Control , 2005 .

[7] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[8] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[9] Hong Chen,et al. Approximation capability in C(R¯n) by multilayer feedforward networks and related problems , 1995, IEEE Trans. Neural Networks.

[10] M Karplus,et al. Evolutionary optimization in quantitative structure-activity relationship: an application of genetic neural networks. , 1996, Journal of medicinal chemistry.