Comparison of RSM and ANN for the investigation of linear alkylbenzene synthesis over H14[NaP5W30O110]/SiO2 catalyst

Design of experiments (DOE) and artificial neural networks (ANNs) were successfully applied for studying the operating parameters of benzene alkylation with 1-decene over H14[NaP5W30O110]/SiO2 catalyst. In this reaction catalyst loading, catalyst weight percent and benzene to 1-decene molar ratio (B...

Full description

Saved in:
Bibliographic Details
Published in:Journal of industrial and engineering chemistry (Seoul, Korea) 2013, 19(6), , pp.1981-1989
Main Authors: Hafizi, A., Ahmadpour, A., Koolivand-Salooki, M., Heravi, M.M., Bamoharram, F.F.
Format: Article
Language:English
Subjects:
ANN
Benzene
Catalysts
Conversion
Learning theory
Linear alkylbenzene
Mathematical models
Neural networks
Preyssler heteropoly acid
RSM
Selectivity
Silica-supported catalyst
Silicon dioxide
화학공학
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Design of experiments (DOE) and artificial neural networks (ANNs) were successfully applied for studying the operating parameters of benzene alkylation with 1-decene over H14[NaP5W30O110]/SiO2 catalyst. In this reaction catalyst loading, catalyst weight percent and benzene to 1-decene molar ratio (Bz/C10) were chosen as independent variables in experimental design. Prediction of 1-decene conversion and 2-phenyldecane selectivity was performed applying response surface method (RSM) and ANN models. Final selected multi-layer (3-6-2-2) ANN model resulted a coefficient of determination (R2) of 0.95 for 1-decene conversion and 0.99 for 2-phenyldecane selectivity, while the R2 of RSM was 0.93 and 0.92 for these two parameters.
ISSN:1226-086X
1876-794X
DOI:10.1016/j.jiec.2013.03.007