Premium
Semiempirical Modeling with Application of Artificial Neural Networks for the Photocatalytic Reaction of Ethylenediaminetetraacetic Acid (EDTA) over Titanium Oxide (TiO 2 )
Author(s) -
Emilio Carina A.,
Litter Marta I.,
Magallanes Jorge F.
Publication year - 2002
Publication title -
helvetica chimica acta
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.74
H-Index - 82
eISSN - 1522-2675
pISSN - 0018-019X
DOI - 10.1002/1522-2675(200203)85:3<799::aid-hlca799>3.0.co;2-j
Subject(s) - ethylenediaminetetraacetic acid , multivariate analysis of variance , artificial neural network , chemistry , photocatalysis , biological system , factorial experiment , titanium oxide , multivariate statistics , artificial intelligence , inorganic chemistry , chelation , computer science , machine learning , catalysis , organic chemistry , biology
The use of chemometric techniques, full factorial and Doehlert experimental designs, multivariate analysis by MANOVA (=multiple‐way analysis of the variance), and artificial neural networks (ANNs) for the photocatalytic reaction of ethylenediaminetetraacetic acid (EDTA) over TiO 2 in aqueous solution is described. Based on the previous knowledge of the photocatalytic system, variables such as EDTA concentration, photocatalyst concentration, pH, and irradiation time were chosen to build a set of experiments for the analysis. By means of MANOVA, the statistical significance of the individual variables and the inspection of interactions between them were analyzed. By the use of ANNs, correlation plots among variables may help to build a semiempirical modeling for understanding and prediction the behavior of the system, optimizing parameters valuable for further technological applications.