Neural networks applied in kinetic analysis of complex nucleation-growth processes: Outstanding solution for fully overlapping reaction mechanisms

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25310%2F22%3A39919961" target="_blank" >RIV/00216275:25310/22:39919961 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0022309322002411" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0022309322002411</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.jnoncrysol.2022.121640" target="_blank" >10.1016/j.jnoncrysol.2022.121640</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neural networks applied in kinetic analysis of complex nucleation-growth processes: Outstanding solution for fully overlapping reaction mechanisms

Popis výsledku v původním jazyce

Performance of several neural network architectures (convolutional neural network CNN, multilayer perceptron MLP, CNN/MLP hybrid CDD) was evaluated for kinetic analysis of complex processes with overlapping independent reaction mechanisms based on the nucleation-growth Johnson-Mehl-Avrami (JMA) model. Theoretically simulated data used for the testing covered absolute majority of real-life JMA-JMA solid-state kinetics scenarios. The performance of the tested architectures decreased in the following order: MLP &gt; CDD &gt;&gt; CNN. For partially overlapping processes the CDD and MLP architectures provided accurate estimates of the JMA model kinetic parameters, performing on par with traditional methods of kinetic analysis. For the fully overlapping kinetic processes, the accuracy of the estimates provided by the neural networks significantly worsened, however still largely outperforming the traditional approaches of kinetic analysis based on the standard non-linear optimization, such as mathematic or kinetic deconvolution. The corresponding kinetic predictions were of suitable precision for majority of real-life applications preparation (glass-ceramics).

Název v anglickém jazyce

Neural networks applied in kinetic analysis of complex nucleation-growth processes: Outstanding solution for fully overlapping reaction mechanisms

Popis výsledku anglicky

Performance of several neural network architectures (convolutional neural network CNN, multilayer perceptron MLP, CNN/MLP hybrid CDD) was evaluated for kinetic analysis of complex processes with overlapping independent reaction mechanisms based on the nucleation-growth Johnson-Mehl-Avrami (JMA) model. Theoretically simulated data used for the testing covered absolute majority of real-life JMA-JMA solid-state kinetics scenarios. The performance of the tested architectures decreased in the following order: MLP &gt; CDD &gt;&gt; CNN. For partially overlapping processes the CDD and MLP architectures provided accurate estimates of the JMA model kinetic parameters, performing on par with traditional methods of kinetic analysis. For the fully overlapping kinetic processes, the accuracy of the estimates provided by the neural networks significantly worsened, however still largely outperforming the traditional approaches of kinetic analysis based on the standard non-linear optimization, such as mathematic or kinetic deconvolution. The corresponding kinetic predictions were of suitable precision for majority of real-life applications preparation (glass-ceramics).

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20504 - Ceramics

Projekt

<a href="/cs/project/LM2018103" target="_blank" >LM2018103: Výzkumná infrastruktura CEMNAT</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Non-Crystalline Solids

ISSN

0022-3093

e-ISSN

1873-4812

Svazek periodika

588

Číslo periodika v rámci svazku

July

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

11

Strana od-do

"121640-1"-"121640-11"

Kód UT WoS článku

000913318200001

EID výsledku v databázi Scopus

2-s2.0-85127934638