2017
DOI: 10.1016/j.crci.2016.11.009
|View full text |Cite
|
Sign up to set email alerts
|

Glass transition temperature of ionic liquids using molecular descriptors and artificial neural networks

Abstract: Glass transition temperature data of ionic liquids (ILs) are analyzed to study the capabilities of artificial neural networks to correlate and predict this property. Molecular descriptors from computational chemistry are considered as independent variables to define the characteristics of an IL molecule. Several network architectures were considered, combinations of different descriptors were analyzed, and results were compared with other values reported in the literature. The independent variables (those that… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
5
0
3

Year Published

2017
2017
2024
2024

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 19 publications
(10 citation statements)
references
References 29 publications
2
5
0
3
Order By: Relevance
“…Many ILs that do exist in the liquid state never crystallize and thus do not show any melting point, instead, on cooling they show a glass transition (Tg). Most ILs (Valderrama et al, 2017) show a glass transition temperature in the 150–250 K range.…”
Section: Ils As Glass Forming Materialsmentioning
confidence: 99%
See 1 more Smart Citation
“…Many ILs that do exist in the liquid state never crystallize and thus do not show any melting point, instead, on cooling they show a glass transition (Tg). Most ILs (Valderrama et al, 2017) show a glass transition temperature in the 150–250 K range.…”
Section: Ils As Glass Forming Materialsmentioning
confidence: 99%
“…Some works have tackled the prediction of the Tg of ILs (Mirkhani et al, 2012; Valderrama et al, 2017). Other studies have identified difficulties behind observing IL's crystallization (Serra et al, 2017; Ferreira et al, 2019).…”
Section: Ils As Glass Forming Materialsmentioning
confidence: 99%
“…Realizarlo más veces no es necesario, por cuanto los parámetros estadísticos de las ecuaciones 1 a la 3, no cambian. Debe siempre haber entrenamiento, prueba y predicción y es necesario que los datos sean excluyentes (Valderrama et al, 2017b). En la Tabla 3, se muestran tres casos de las cincuenta ejecuciones, para los tres casos de estudio.…”
Section: Resultados Y Discusiónunclassified
“…Como metodología de trabajo los valores de las variables independientes usadas para prueba y predicción deben estar dentro de los intervalos utilizados para el entrenamiento de la red (Tablas 1 y 2). Esto porque las redes neuronales artificiales son, en general, buenas herramientas para la interpolación pero no para la extrapolación (Valderrama, et al, 2017b).…”
Section: Metodologíaunclassified
See 1 more Smart Citation