We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
A simple threeâdescriptor model for the prediction of the glassâtransition temperatures of vinyl polymers.
- Authors
Xinliang Yu; Wenhao Yu; Xueye Wang
- Abstract
An artificial neural network (ANN) implementing a backâpropagation algorithm was applied for the prediction of the glassâtransition temperature (Tg) values of 84 polyacrylates and 21 polyvinyls. The experimental Tgdata of the polymers were divided into a training set (50 polyacrylates) and a testing set (34 polyacrylates and 21 polyvinyls). Three molecule descriptors (mean atomic van der Waals volume, bond information content, and threeâdimensional molecule representation of structures based on electron diffraction descriptor for signal 13/weighted by atomic masses, Mor13m) were used as input parameters of the neural network. Simulated with the optimum backâpropagation ANN 3â[3â2]â1, the root mean square (rms) error for the testing set was 17.7 K, and the correlation coefficient was 0.942, which were accurate in comparison with existing models. The ANN model could be used not only to reveal the quantitative relation between Tgand the molecular structure but also to predict the Tgvalues of the polyacrylates and polyvinyls. © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2010
- Subjects
ARTIFICIAL neural networks; ALGORITHMS; GLASS transition temperature; MOLECULES; ELECTRON diffraction; MOLECULAR structure
- Publication
Journal of Applied Polymer Science, 2010, Vol 115, Issue 6, p3721
- ISSN
0021-8995
- Publication type
Article
- DOI
10.1002/app.31423