Abstract
Abstract The glass transition temperature (Tg) is a fundamental characteristic of an amorphous polymer. A quantitative structure-property relationship (QSPR) based on error back-propagation artificial neural network (ANN) was constructed to predict Tgs of 107 polystyrenes. Stepwise multiple linear regression (MLR) analysis was adopted to select an optimal subset of molecular descriptors. The chain segments (or motion units) of polymer backbones with 20 carbons in length (10 repeating units) were used to calculate these molecular descriptors reflecting polymer structures. The relative optimal conditions of ANN were obtained by adjusting various network paramters by trial-and-error. Compared to the model already published in the literature, the optimal ANN model with [4-7-1] network structure in this paper is accurate and acceptable, although our model has more samples in the test set. The results demonstrate the feasibility and powerful ability of the chain segment structures as representative of polymers for developing Tg models of polystyrenes.
Highlights
The glass transition temperature (Tg) is known as the 320 polymers
The results demonstrate the feasibility and powerful ability of the chain segment structures as representative of polymers for developing Tg models of polystyrenes
By analyzing the correlation between the 551 descriptors and Tgs of 70 polystyrenes in the training set with stepwise multiple linear regression (MLR) analysis in IBM SPSS Statistics 19, Equation 1 and the corresponding statistical results were obtained
Summary
The glass transition temperature (Tg) is known as the 320 polymers. The Tg model was based on the solubility glass temperature or the transition temperature between parameter and the weighted sum of 13 topological bond glass and rubber states of amorphous materials. Tg is a connectivity parameters of the monomer structures. The fundamental characteristic and is taken as the most crucial model is not validated with the test set. Joyce et al.[5] built property of amorphous polymeric materials[1]. The nature models for Tg prediction based on the monomer structures of the theory in the glass and glass transition is unsolved, of 360 polymers. The model predicted the Tg values for a
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
