Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.15255/KUI.2020.073

Dragonfly Support Vector Machine Modelling of the Adsorption Phenomenon of Certain Phenols by Activated Carbon Fibres

Mohamed Hentabli orcid id orcid.org/0000-0002-6693-0708 ; Laboratory of Biomaterials and Transport Phenomena (LBMPT), Faculty of Technology, University Yahia Fares of Médéa, Alžir
Abd-Elmouneïm Belhadj ; Laboratory of Biomaterials and Transport Phenomena (LBMPT), Faculty of Technology, University Yahia Fares of Médéa, Alžir
Farid Dahmoune ; Département de Biologie, Facultés des Sciences de la Nature et de la Vie et des Science de la Terre, Université de Bouira, 10 000 Bouira, Alžir


Puni tekst: engleski pdf 828 Kb

str. 501-508

preuzimanja: 320

citiraj


Sažetak

The objective of this research was to build a mathematical model based on a Support Vector Machine (SVM) capable of predicting the amount adsorbed at equilibrium (qe). Activated carbon fibres (ACF) were used for the adsorption of certain phenols (phenol, 2-chlorophenol, 4-chlorophenol, 2,4,6-trichlorophenol, 4-nitrophenol, and 2,4-dinitrophenol). An experimental dataset of 129 points was collected from previously published papers. The inputs considered for modelling were temperature (T), concentration at equilibrium (ce), and two descriptors (boiling point (BP) and density (d)) to differentiate between the pollutants studied. The data used were pre-processed by the statistical analysis to ensure that they were adequate for modelling. The results showed a superiority of the Gaussian kernel function DA-SVM model demonstrated by its determination coefficient (R2 = 0.997) and root mean squared error (RMSE = 0.027 mmol l–1).




This work is licensed under a Creative Commons Attribution 4.0 International License.

Ključne riječi

adsorption; phenols; support vector machine; dragonfly algorithm; activated carbon fibre; amount adsorbed at equilibrium

Hrčak ID:

261462

URI

https://hrcak.srce.hr/261462

Datum izdavanja:

23.8.2021.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.166 *