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

朱群雄; 赵乃伟; 徐圆

Your Location：

Home >

Browse articles >

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

Updated：2026-01-06

- A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process^*
- A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process^*
- 中国化学工程学报（英文版） 2012年20卷第6期页码：1142-1147
- Affiliations：
  
  College of Information Science & Technology, Beijing University of Chemical Technology,Beijing,China,100029
- Author bio：
- Funds：
  
  Supported by the National Natural Science Foundation of China (61074153;61104131);the Fundamental Research Fundsfor Central Universities of China (ZY1111;JD1104)
- DOI：
  中图分类号：
- 纸质出版：2012
- Accepted：
Scan QR Code
朱群雄, 赵乃伟, 徐圆. A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process^*[J]. 中国化学工程学报（英文版）, 2012,20(6):1142-1147.

[J]. Chinese Journal of Chemical Engineering, 2012, 20(6): 1142-1147.
朱群雄, 赵乃伟, 徐圆. A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process^*[J]. 中国化学工程学报（英文版）, 2012,20(6):1142-1147. DOI：

[J]. Chinese Journal of Chemical Engineering, 2012, 20(6): 1142-1147. DOI：

摘要

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.

关键词

Keywords

references

浏览量

1128

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Recovery rubidium chloride and cyclic utilization of hexacyanoferrate(II) ion from hexacyanoferrate-internediate solutions via solvent extraction

Synthesis of chemiluminescent carbonized polymer dots under atmospheric conditions for multimode luminescence anti-counterfeiting

Dynamic behavior of a single bubble in cavity flow driven by a turbulent channel

COS generation behavior during desulfurization for H2S over zeolite in simulated blast furnace gas

Controllable synthesis of Ni3S2/V3S4@NF-xF(x=0, 4, 8) catalysts for efficient hydrogen production in seawater and urea electrolyte