Journal
REACTIVE & FUNCTIONAL POLYMERS
Volume 68, Issue 11, Pages 1557-1562Publisher
ELSEVIER
DOI: 10.1016/j.reactfunctpolym.2008.08.009
Keywords
Artificial neural network; Density functional theory; Dielectric dissipation factor; Polymer; Quantitative structure-property relationship (QSPR)
Funding
- Hunan Provincial Education Department [07C205]
- Scientific Research Fund of Hunan Institute of Engineering [0761]
- Natural Science Foundation of Hunan Province [06JJ50017]
Ask authors/readers for more resources
A quantitative structure-property relationship (QSPR) model was constructed to predict the dielectric dissipation factor (or power factor or electrical loss tangent) tan delta of polymers by means of artificial neural network (ANN). The frequency of measurement (v) and five quantum chemical descriptors (q(R)(+), q((R/M))(-), E-MLUMO, E-M/RLUMO, and S-R) Calculated at the DFT/B3LYP/6-31G(d) level were used as vectors to develop the model. The typical back-propagation (BP) neural network was employed for fitting the possible non-linear relationship existed between the six descriptors and tan delta. The optimal condition of the neural network was obtained by adjusting various parameters by trial-and-error. Simulated with the final optimum BP neural network [6-2-1], the results show that the predicted tan delta values are in good agreement with the experimental ones, with the root mean square error (rms) being 0.01067 (R = 0.939) for the training set and 0.01463 (R = 0.902) for the test set. Comparing with existing models, the model proposed is independent of the refractive index n and the dielectric constant epsilon Thus the present model is more useful in predicting the tan delta values for polymers. (c) 2008 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available