Premium
A stacked neural network approach for yield prediction of propylene polymerization
Author(s) -
Monemian Seyed Ali,
Shahsavan Hamed,
Bolouri Oberon,
Taranejoo Shahrouz,
Goodarzi Vahabodin,
TorabiAngaji Mahmood
Publication year - 2009
Publication title -
journal of applied polymer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.575
H-Index - 166
eISSN - 1097-4628
pISSN - 0021-8995
DOI - 10.1002/app.31251
Subject(s) - polymerization , yield (engineering) , catalysis , silane , materials science , chemical engineering , polymer chemistry , chemistry , organic chemistry , polymer , composite material , engineering
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–especially 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/AlEt 3 , where Mg(OEt) 2 , DIBP (diisobutyl phthalate), TiCl 4 , PTES (phenyl triethoxy silane), and triethyl aluminum (AlEt 3 ) (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. © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2010