Artificial neural networks combined with experimental design: a
“soft” approach for chemical kinetics

J 2012

Artificial neural networks combined with experimental design: a “soft” approach for chemical kinetics

AMATO, Filippo; González-Hernández JOSÉ LUIS a Josef HAVEL

Základní údaje

Originální název

Artificial neural networks combined with experimental design: a “soft” approach for chemical kinetics

Autoři

AMATO, Filippo; González-Hernández JOSÉ LUIS a Josef HAVEL

Vydání

Talanta, Elsevier, 2012, 0039-9140

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10406 Analytical chemistry

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 3.498

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14310/12:00059296

Organizační jednotka

Přírodovědecká fakulta

DOI

https://doi.org/10.1016/j.talanta.2012.01.044

UT WoS

000303305700010

Klíčová slova anglicky

Chemical kinetics; Soft-modelling; Artificial Neural Networks; Experimental design; Rate constants; Multicomponent analysis; Optimization.

Štítky

AKR, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 22. 4. 2013 14:09, Ing. Andrea Mikešková

Anotace

V originále

The possibilities of artificial neural networks (ANNs) “soft” computing to evaluate chemical kinetic data have been studied. In the first stage, , a set of “standard” kinetic curves with known parameters (rate constants and/or concentrations of the reactants), which is some kind of “normalized maps”, is prepared. The data base should be built according to a suitable experimental design (ED). In the second stage, such data set is then used for ANNs “learning”. Afterwards, in the second stage, experimental data are evaluated and parameters of “other” kinetic curves are computed without solving anymore the system of differential equations. The combined ED-ANNs approach has been applied to solve several kinetic systems. It was also demonstrated that using ANNs, the optimization of complex chemical systems can be achieved even not knowing or determining the values of the rate constants. Moreover, the solution of differential equations is here not necessary, as well. Using ED the number of experiments can be reduced substantially. Methodology of ED-ANNs applied to multicomponent analysis shows advantages over classical methods while the knowledge of kinetic reactions is not needed. ANNs computation in kinetics is robust as shown evaluating the effect of experimental errors and it is of general applicability.

Návaznosti

MSM0021622411, záměr

Název: Studium a aplikace plazmochemických reakcí v neizotermickém nízkoteplotním plazmatu a jeho interakcí s povrchem pevných látek

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Studium a aplikace plazmochemických reakcí v neizotermickém nízkoteplotním plazmatu a jeho interakcí s povrchem pevných látek

Citovat

AMATO, Filippo; González-Hernández JOSÉ LUIS a Josef HAVEL. Artificial neural networks combined with experimental design: a “soft” approach for chemical kinetics. Talanta. Elsevier, 2012, roč. 93, MAY, s. 72-78. ISSN 0039-9140. Dostupné z: https://doi.org/10.1016/j.talanta.2012.01.044.

@article{970280,
   author = {Amato, Filippo and José Luis, GonzálezandHernández and Havel, Josef},
   article_number = {MAY},
   doi = {https://doi.org/10.1016/j.talanta.2012.01.044},
   keywords = {Chemical kinetics; Soft-modelling; Artificial Neural Networks; Experimental design; Rate constants; Multicomponent analysis; Optimization.},
   language = {eng},
   issn = {0039-9140},
   journal = {Talanta},
   title = {Artificial neural networks combined with experimental design: a “soft” approach for chemical kinetics},
   volume = {93},
   year = {2012}
}

TY  - JOUR
ID  - 970280
AU  - Amato, Filippo - José Luis, González-Hernández - Havel, Josef
PY  - 2012
TI  - Artificial neural networks combined with experimental design: a “soft” approach for chemical kinetics
JF  - Talanta
VL  - 93
IS  - MAY
SP  - 72-78
EP  - 72-78
PB  - Elsevier
SN  - 00399140
KW  - Chemical kinetics
KW  - Soft-modelling
KW  - Artificial Neural Networks
KW  - Experimental design
KW  - Rate constants
KW  - Multicomponent analysis
KW  - Optimization.
N2  - The possibilities of artificial neural networks (ANNs) “soft” computing to evaluate chemical kinetic data have been studied. In the first stage, , a set of “standard” kinetic curves with known parameters (rate constants and/or concentrations of the reactants), which is some kind of “normalized maps”, is prepared. The data base should be built according to a suitable experimental design (ED). In the second stage, such data set is then used for ANNs “learning”. Afterwards, in the second stage, experimental data are evaluated and parameters of “other” kinetic curves are computed without solving anymore the system of differential equations. The combined ED-ANNs approach has been applied to solve several kinetic systems. It was also demonstrated that using ANNs, the optimization of complex chemical systems can be achieved even not knowing or determining the values of the rate constants. Moreover, the solution of differential equations is here not necessary, as well. Using ED the number of experiments can be reduced substantially. Methodology of ED-ANNs applied to multicomponent analysis shows advantages over classical methods while the knowledge of kinetic reactions is not needed. ANNs computation in kinetics is robust as shown evaluating the effect of experimental errors and it is of general applicability.
ER  -

AMATO, Filippo; González-Hernández JOSÉ LUIS a Josef HAVEL. Artificial neural networks combined with experimental design: a “soft” approach for chemical kinetics. \textit{Talanta}. Elsevier, 2012, roč.~93, MAY, s.~72-78. ISSN~0039-9140. Dostupné z: https://doi.org/10.1016/j.talanta.2012.01.044.

Přehled o publikaci