Adsorción de metales pesados (Hg2+, Cu2+ y Ni2+) en NTC utilizando redes neuronales Feed forward backprop y Elman backprop
In the present work, mono and multicomponent adsorption systems of heavy metals (Hg2+, Cu2+y Ni2+)as adsorbates and carbon nanotubes (CNT) as adsorbents were studied. First, the thermodynamic and QSAR properties at 298.15 and 30815K were determined using computational simulation. Subsequently, Feedf...
Gespeichert in:
Veröffentlicht in: | Investigación y ciencia (Aguascalientes, Mexico) Mexico), 2023 (89) |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | spa |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In the present work, mono and multicomponent adsorption systems of heavy metals (Hg2+, Cu2+y Ni2+)as adsorbates and carbon nanotubes (CNT) as adsorbents were studied. First, the thermodynamic and QSAR properties at 298.15 and 30815K were determined using computational simulation. Subsequently, Feedforward backprop and Elman backprop artificial neural networks were developed, where the network with the highest precision of the thermodynamic and QSAR properties was the Elman Backprop with the Logsig function using 5 and 3 neurons in the hidden layer at 298.15 and 308.15 K, finally, the networks had an r2 of 0.999, and a mean square error of 0.021, 0.024 and 0.214 respectively
En el presente trabajo se estudiaron sistemas de adsorción mono y multicomponente de metales pesados (Hg2+, Cu2+y Ni2+)como adsorbatos y nanotubos de carbono (NTC) como adsorbentes. Primero, se determinaron las propiedades termodinámicas y QSARa 298.15 y 30815K utilizando simulación computacional. Posteriormente, se desarrollaron redes neuronales artificiales Feed forward backprop y Elman backprop, en donde la red con mayor precisión de las propiedades termodinámicas y QSAR fue, la Elman Backprop con la función Logsig utilizando 5 y 3 neuronas en la capa oculta a 298.15 y 308.15 K, por otro lado, las redes tuvieron una r2 de 0.999, y un error cuadrático medio de 0.021, 0.024 y 0.214 respectivamente. |
---|---|
ISSN: | 1665-4412 |