Paper Title:
Modeling Methodology Based on Stacked Neural Networks for Inferential Prediction of Polypropylene Melt Index
  Abstract

A modeling methodology based on stacked neural networks by combining several individual networks in parallel is proposed. Stacked neural network as an effective method for modeling of inherently complex and nonlinear systems especially a system with a limited number of experimental data points is chosen for yield prediction. Proper determination of the stacking weights is essential for good stacked neural networks model performance, so determination of appropriate weights for combining individual networks using robust least squares estimation is proposed. Inferential prediction of melt index as the most important characteristic process of polypropylene polymerization has been carried out. The application of the proposed modeling method based on stacked neural networks to the development of melt index soft sensor in an industrial propylene polymerization plant demonstrates its effectiveness.

  Info
Periodical
Edited by
Qi Luo
Pages
670-674
DOI
10.4028/www.scientific.net/AMM.55-57.670
Citation
L. Y. Xia, H. T. Pan, M. F. Zhou, Y. J. Cai, X. F. Sun, "Modeling Methodology Based on Stacked Neural Networks for Inferential Prediction of Polypropylene Melt Index", Applied Mechanics and Materials, Vols. 55-57, pp. 670-674, 2011
Online since
May 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Jong Won Lee, Jin Hak Yi, Jae Dong Kim, Chung Bang Yun
1983
Authors: Xiang Hu Liu
Abstract:Fitting of forecast function is very difficult and important in non-linear regression forecast problems. The accuracy is directly affected by...
595
Authors: Dong Xiang Nan, Yun Sheng Zhang, Xue Qiang Sun
Abstract:There has been a growing interest in artificial neural networks (ANNs) based on quantum theoretical concepts and techniques due to cognitive...
757
Authors: Meng Shan Li, Bing Xiang Liu, Yan Wu
Chapter 1: Material Science and Technology
Abstract:Temperature of the polymer melt is one of the most important parameters for the polymer continuous extrusion molding process. There are many...
425
Authors: Shuo Ding, Xiao Heng Chang
Chapter 15: Information Technologies and Networks: Its Applications
Abstract:BP neural network is a kind of widely used feed-forward network. However its innate shortcomings are gradually giving rise to the study of...
1746