Premium
Influence of Process Parameters on the Gas Phase Polymerization of Ethylene: RSM or ANN Statistical Methods?
Author(s) -
Ishola Niyi B.,
McKenna Timothy F. L.
Publication year - 2021
Publication title -
macromolecular theory and simulations
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.37
H-Index - 56
eISSN - 1521-3919
pISSN - 1022-1344
DOI - 10.1002/mats.202100059
Subject(s) - response surface methodology , pentane , artificial neural network , biological system , materials science , process (computing) , design of experiments , mathematics , computer science , statistics , machine learning , chemistry , organic chemistry , biology , operating system
The direct and interactive effects of process variables, including the use of iso‐pentane as an inert condensing agent, on the rate of polymerization and main physical properties of linear low‐density polyethylene are studied using two different statistical methods. Response surface methodology (RSM) based on a three level five factor Box–Behnken design is used to generate the number of experimental runs. The generated dataset is used to develop the RSM and artificial neural network (ANN) models. The effect of the input on the dependent variables is studied using the 3D response surface of the developed RSM model. The developed models are statistically analyzed and compared to determine their performance capability. The ANN model marginally outperforms the RSM model based on the computed statistical parameters but provides less information on the variable interactions.