Loading...

A stacked neural network approach for yield prediction of propylene polymerization

Monemian, S. A ; Sharif University of Technology | 2010

1116 Viewed
  1. Type of Document: Article
  2. DOI: 10.1002/app.31251
  3. Publisher: 2010
  4. Abstract:
  5. Prediction of reaction yield as the most important characteristic process of a slurry polymerization industrial process of propylene has been carried out. Stacked neural network as an effective method for modeling of inherently complex and nonlinear systems-espe-cially a system with a limited number of experimental data points-was chosen for yield prediction. Also, effect of operational parameters on propylene polymerization yield was modeled by the use of this method. The catalyst system was Mg(OEt)2/DIBP/TiCl 4/PTES/AlEt3, where Mg(OEt)2, DIBP (diisobutyl phthalate), TiCl4, PTES (phenyl triethoxy silane), and triethyl aluminum (AlEt3) (TEAl) were employed as support, internal electron donor (ID), catalyst precursor, external electron donor (ED), and co-catalyst, respectively. The experimental results confirmed the validity of the proposed model
  6. Keywords:
  7. Modeling ; Polyolefins ; Ziegler-Natta polymerization ; Catalyst precursors ; Catalyst system ; Cocatalyst ; Electron donors ; Experimental data ; Industrial processs ; Internal electron donor ; Operational parameters ; Phthalates ; Propylene polymerization ; Reaction yields ; Slurry polymerization ; Stacked neural network ; Stacked neural networks ; Yield prediction ; Ziegler natta polymerization ; Catalysis ; Catalysts ; Esters ; Nonlinear systems ; Polymerization ; Polyolefins ; Propylene ; Neural networks ; Catalyst ; Neural network ; Polymerization ; Polyolefin ; Precursor ; Predictive model
  8. Source: Journal of Applied Polymer Science ; Volume 116, Issue 3 , May , 2010 , Pages 1237-1246 ; 00218995 (ISSN)
  9. URL: http://onlinelibrary.wiley.com/doi/10.1002/app.v116:3/issuetoc