| 基于EGK'M-RBF网络的顺丁橡胶门尼黏度预测 |
| |
| 引用本文： | 李大字,钱丽,王淑红,靳其兵.基于EGK'M-RBF网络的顺丁橡胶门尼黏度预测[J].化工学报,2011,62(8):2367-2371. |
| |
| 作者姓名： | 李大字 钱丽 王淑红 靳其兵 |
| |
| 作者单位： | 北京化工大学信息科学与技术学院，北京 100029;北京燕山石化公司橡胶厂，北京 102500 |
| |
| 基金项目： | 国家高技术研究发展计划项目，北京市优秀人才资助项目 |
| |
| 摘 要： | 提出一种基于增强的全局K'-means算法(EGK'M)-RBF网络的建模方法,该方法采用作者提出的EGK'M来确定RBF网络隐含层的结构,包括隐含层中心个数、中心位置以及隐含层扩展常数,采用KPCA提取非线性特征信息,实现辅助变量的二次选择.并与基于PCA和EGK'M-RBF网络模型、基于KPCA和K-means算法...
|
| 关 键 词： | 改进的全局K'-means算法 核主元分析法 门尼黏度 RBF网络 |
Estimation of Mooney viscosity of polybutadiene rubber based on EGK'M-RBF network |
| |
| LI Dazi,QIAN Li,WANG Shuhong,JIN Qibing.Estimation of Mooney viscosity of polybutadiene rubber based on EGK'M-RBF network[J].Journal of Chemical Industry and Engineering(China),2011,62(8):2367-2371. |
| |
| Authors: | LI Dazi QIAN Li WANG Shuhong JIN Qibing |
| |
| Abstract: | A modeling method by radial basis function(RBF)network based on enhanced global K’-means algorithm(EGK’M)was presented.An EGK’M algorithm was proposed to determine the hidden layer structure of RBF network,including the number of hidden layer nodes,the position of each center and the width of basis function.KPCA algorithm was used to extract non-linear feature information and to achieve secondary selection of auxiliary variable.The obtained model was compared with the model based on principle components analysis with EGK’M-RBF and the model based on KPCA with RBF network based on K’-means algorithm.Experiment results demonstrate that the model proposed in this paper gives better predictive ability,smaller absolute error and mean square error. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《化工学报》浏览原始摘要信息 |
|
点击此处可从《化工学报》下载全文 |
