Application of artificial neural networks coupled with an orthogonal design and optimization algorithms to multifactor optimization of a new FIA system for the determination of uranium(VI) in ore samples

Citation
S. Gang et al., Application of artificial neural networks coupled with an orthogonal design and optimization algorithms to multifactor optimization of a new FIA system for the determination of uranium(VI) in ore samples, ANALYST, 125(5), 2000, pp. 921-925
Citations number
29
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Chemistry & Analysis","Spectroscopy /Instrumentation/Analytical Sciences
Journal title
ANALYST
ISSN journal
0003-2654 → ACNP
Volume
125
Issue
5
Year of publication
2000
Pages
921 - 925
Database
ISI
SICI code
0003-2654(2000)125:5<921:AOANNC>2.0.ZU;2-R
Abstract
A sensitive and selective spectrophotometric flow injection method has been developed for the determination of uranium(VI) in ore samples, based on th e reaction of uranium(VI) with p-acetylchlorophosphonazo (CPA-pA) in a HNO3 medium. Most of the interfering ions were effectively eliminated by the ma sking reagent, diethyleneaminepentaacetic acid (DTPA). Artificial neural ne tworks coupled with an orthogonal design and penalty algorithm were applied to the modeling of the proposed flow injection system and optimization of the experimental conditions. An orthogonal design was utilized to design th e experimental protocol, in which three variables were varied simultaneousl y. ANNs with a faster back propagation (BP) algorithm were used to model th e system. Optimum experimental conditions were generated automatically by u sing jointly ANNs and optimization algorithms in terms of sensitivity and s ampling rate. In the U(VI)-CPA-pA system, Beer's law was obeyed in the rang e 1.0-23.0 mu g mL(-1), the detection limit for uranium(VI) was 0.3 mu g mL (-1) and the sampling rate was 100 h(-1). The method was applied to the det ermination of uranium(VI) in ore samples with satisfactory results. It was shown that this method had advantages over traditional methods in respect o f improvement in the ability of optimization and reduction in analysis time .