| A NEURAL NETWORK STUDY ON GLASS TRANSITION TEMPERATURE OF POLYMERS |
| |
| 作者姓名： | 章林溪 |
| |
| 作者单位： | Department of |
| |
| 基金项目： | This research was financially supported by NSFC (No. 29874012) and the Special Funds for Major State Basic Research Projects (95-12 and G1999064800). |
| |
| 摘 要： | In this paper, an atificial neural network model is adopted to study the glass transition temperature of polymers. Inour artificial neural networks, the input nodes are the characteristic ratio C_∞, the average molecular weigh M_e betweenentanglement points and the molecular weigh M_(mon) of repeating unit. The output node is the glass transition temperature T_g,and the number of the hidden layer is 6. We found that the artificial neural network simulations are accurate in predicting theoutcome for polymers for which it is not trained. The maximum relative error for predicting of the glass transitiontemperature is 3.47%, and the overall average error is only 2.27%. Artificial neural networks may provide some new ideas toinvestigate other properties of the polymers.
|
| 收稿时间： | 2001-03-01 |
| 修稿时间： | 2001-04-01 |
A NEURAL NETWORK STUDY ON GLASS TRANSITION TEMPERATURE OF POLYMERS* |
| |
| Lin-xi Zhang,De-lu Zhao,You-xing Huang.A NEURAL NETWORK STUDY ON GLASS TRANSITION TEMPERATURE OF POLYMERS[J].Chinese Journal of Polymer Science,2002,0(1):25-30. |
| |
| Authors: | Lin-xi Zhang De-lu Zhao You-xing Huang |
| |
| Institution: | a.Department of Physics; Zhejiang University Hangzhou 310028 China b.Polymer Physics Laboratory Center of Molecular Science; Institute of Chemistry Chinese Academy of Sciences; Beijing 100080; China |
| |
| Abstract: | In this paper, an atificial neural network model is adopted to study the glass transition temperature of polymers. Inour artificial neural networks, the input nodes are the characteristic ratio C∞, the average molecular weigh Me betweenentanglement points and the molecular weigh Mmon of repeating unit. The output node is the glass transition temperature Tg,and the number of the hidden layer is 6. We found that the artificial neural network simulations are accurate in predicting the outcome for polymers for which it is not trained.The maximum relative error for predicting of the glass transition temperature is 3.47%,and the overall average error is only 2.27%.Artificial neural networks may provide some new ideas to investigate other properties of the polymers. |
| |
| Keywords: | Neural network Glass transition temperature |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《高分子科学》浏览原始摘要信息 |
| 点击此处可从《高分子科学》下载免费的PDF全文 |
