SCI和EI收录∣中国化工学会会刊

Chin.J.Chem.Eng. ›› 2012, Vol. 20 ›› Issue (6): 1142-1147.

• PROCESS MODEL • Previous Articles     Next Articles

A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process*

ZHU Qunxiong, ZHAO Naiwei, XU Yuan   

  1. College of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, China
  • Received:2012-05-12 Revised:2012-07-10 Online:2012-12-28 Published:2012-12-28
  • Supported by:
    Supported by the National Natural Science Foundation of China (61074153;61104131);the Fundamental Research Fundsfor Central Universities of China (ZY1111;JD1104)

A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process*

朱群雄, 赵乃伟, 徐圆   

  1. College of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, China
  • 通讯作者: XU Yuan,E-mail:xyfancy@163.com
  • 基金资助:
    Supported by the National Natural Science Foundation of China (61074153;61104131);the Fundamental Research Fundsfor Central Universities of China (ZY1111;JD1104)

Abstract: 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.

Key words: high-density polyethylene modeling, selective neural network ensemble, diversity definition, error vectorization

摘要: 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.

关键词: high-density polyethylene modeling, selective neural network ensemble, diversity definition, error vectorization