This paper shows modeling of highly nonlinear polymerization process using the artificial neural network
approach for the model predictive purposes. Polymerization occurs in a fluidized bed polypropylene
reactor using Ziegler - Natta catalyst and the main objective was modeling of the reactor production rate.
The data set used for an identification of the model is a real process data received from an existing
polypropylene plant and the identified model is a nonlinear autoregressive neural network with the
exogenous input. Performance of a trained network has been verified using the real process data and the
ability of the production rate prediction is shown in the conclusion.
%0 Journal Article
%1 noauthororeditor
%A Karas, Peter
%A Kozak, Stefan
%D 2017
%J International Journal of Advances in Chemistry (IJAC)
%K Identification bed control fluidized model networks neural polypropylene predictive reactor
%N 3/4
%P 01-14
%R 10.5121/ijac.2017.3401
%T ARTIFICIAL NEURAL NETWORK APPROACH TO MODELING OF POLYPROPYLENE REACTOR
%U http://airccse.com/ijac/papers/3417ijac01.pdf
%V 3
%X This paper shows modeling of highly nonlinear polymerization process using the artificial neural network
approach for the model predictive purposes. Polymerization occurs in a fluidized bed polypropylene
reactor using Ziegler - Natta catalyst and the main objective was modeling of the reactor production rate.
The data set used for an identification of the model is a real process data received from an existing
polypropylene plant and the identified model is a nonlinear autoregressive neural network with the
exogenous input. Performance of a trained network has been verified using the real process data and the
ability of the production rate prediction is shown in the conclusion.
@article{noauthororeditor,
abstract = {This paper shows modeling of highly nonlinear polymerization process using the artificial neural network
approach for the model predictive purposes. Polymerization occurs in a fluidized bed polypropylene
reactor using Ziegler - Natta catalyst and the main objective was modeling of the reactor production rate.
The data set used for an identification of the model is a real process data received from an existing
polypropylene plant and the identified model is a nonlinear autoregressive neural network with the
exogenous input. Performance of a trained network has been verified using the real process data and the
ability of the production rate prediction is shown in the conclusion. },
added-at = {2018-05-22T07:04:30.000+0200},
author = {Karas, Peter and Kozak, Stefan},
biburl = {https://www.bibsonomy.org/bibtex/2155fda1dbfb4983c1ba934329f7e9b59/ijac},
doi = {10.5121/ijac.2017.3401},
interhash = {78fa2eefbe92dc4824b0494933212377},
intrahash = {155fda1dbfb4983c1ba934329f7e9b59},
issn = {2455-7862},
journal = {International Journal of Advances in Chemistry (IJAC) },
keywords = {Identification bed control fluidized model networks neural polypropylene predictive reactor},
language = {English},
month = nov,
number = {3/4},
pages = {01-14},
timestamp = {2018-05-22T07:04:30.000+0200},
title = {ARTIFICIAL NEURAL NETWORK APPROACH TO MODELING OF POLYPROPYLENE REACTOR},
url = {http://airccse.com/ijac/papers/3417ijac01.pdf},
volume = 3,
year = 2017
}