一种新的基于误差矢量化的选择性神经网络集成方法及其在高密度聚乙烯串级反应过程中的应用(英文)

• 作 者: 朱群雄 赵乃伟 徐圆
• 机 构: College of Information Science & Technology,Beijing University of Chemical Technology,
• 出 处: Chinese Journal of Chemical Engineering
• 发表日期: 2012年06期
• 关键词: 神经网络集成 ensemble 高密度聚乙烯 矢量化 polyethylene 串级 satisfactory selecting generalization

Chemical processes are complex, for which traditional neural network models usually can not lead to satisfactory accuracy. Selective neural network ensemble is an effective way to enhance the generalization accuracy of networks, but there are some problems, e.g., lacking of unified definition of diversity among component neural networks and difficult to improve the accuracy by selecting if the diversities of available networks are small. In this study, the output errors of networks are vectorized, the diversity of networks is defined based on the error vectors, and the size of ensemble is analyzed. Then an error vectorization based selective neural network ensemble (EVSNE) is proposed, in which the error vector of each network can offset that of the other networks by training the component networks orderly. Thus the component networks have large diversity. Experiments and comparisons over standard data sets and actual chemical process data set for production of high-density polyethylene demonstrate that EVSNE performs better in generalization ability.

Chemical processes are complex, for which traditional neural network models usually can not lead to satisfactory accuracy. Selective neural network ensemble is an effective way to enhance the generalization accuracy of networks, but there are some problems, eg, lacking of unified definition of diverse among component neural networks and difficult to improve the accuracy by selecting if the diversities of available networks are small. In this study, the output errors of networks are vectorized, the diversity of networks is defined based on the error vectors, and the size of ensemble is Then an error vectorization based selective neural network ensemble (EVSNE) is proposed, in which the error vector of each network can offset that of the other networks by training the component networks orderly. Thus the component networks have large diversity. Experiments and comparisons over standard data sets and actual chemical process data set for production of high-density polyethylen e demonstrate that EVSNE perform better in generalization ability.