Slika naslovnice

Modelling of adsorption of methane, nitrogen, carbon dioxide, their binary mixtures, and their ternary mixture on activated carbons using artificial neural network

This work examines the use of neural networks in modelling the adsorption process of gas mixtures (CO2, CH4, and N2) on different activated carbons. Seven feed-forward neural network models, characterized by different structures, were constructed with the aim of predicting the adsorption of gas mixt...

Full description

Permalink: http://skupnikatalog.nsk.hr/Record/nsk.NSK01001068836/Details
Matična publikacija: Kemija u industriji (Online)
68 (2019), 7/8 ; str. 289-302
Glavni autori: Barki, Hadjer (Author), Khaouane, Latifa, Hanini, Salah
Vrsta građe: e-članak
Jezik: eng
Predmet:
Modeliranje > Adsorpcija > Aktivni ugljen > Smjesa plinova > Neuronske mreže
Online pristup: https://doi.org/10.15255/KUI.2019.002
Kemija u industriji (Online)
Hrčak
LEADER 03823naa a22003854i 4500
001 NSK01001068836
003 HR-ZaNSK
005 20200825125037.0
006 m d
007 cr||||||||||||
008 200709s2019 ci d |o |0|| ||eng
024 7 |2 doi  |a 10.15255/KUI.2019.002 
035 |a (HR-ZaNSK)001068836 
040 |a HR-ZaNSK  |b hrv  |c HR-ZaNSK  |e ppiak 
041 0 |a eng  |b eng  |b hrv 
042 |a croatica 
044 |a ci  |c hr 
080 1 |a 66  |2 2011 
100 1 |a Barki, Hadjer  |4 aut  |9 HR-ZaNSK 
245 1 0 |a Modelling of adsorption of methane, nitrogen, carbon dioxide, their binary mixtures, and their ternary mixture on activated carbons using artificial neural network  |h [Elektronička građa] /  |c Hadjer Barki, Latifa Khaouane, Salah Hanini. 
300 |b Graf. prikazi. 
504 |a Bibliografija: 67 jed. 
504 |a Summary ; Sažetak. 
520 |a This work examines the use of neural networks in modelling the adsorption process of gas mixtures (CO2, CH4, and N2) on different activated carbons. Seven feed-forward neural network models, characterized by different structures, were constructed with the aim of predicting the adsorption of gas mixtures. A set of 417, 625, 143, 87, 64, 64, and 40 data points for NN1 to NN7, respectively, were used to test the neural networks. Of the total data, 60 %, 20 %, and 20 % were used, respectively, for training, validation, and testing of the seven models. Results show a good fit between the predicted and experimental values for each model; good correlations were found (R = 0.99656 for NN1, R = 0.99284 for NN2, R = 0.99388 for NN3, R = 0.99639 for Q1 for NN4, R = 0.99472 for Q2 for NN4, R = 0.99716 for Q1 for NN5, R = 0.99752 for Q3 for NN5, R = 0.99746 for Q2 for NN6, R = 0.99783 for Q3 for NN6, R = 0.9946 for Q1 for NN7, R = 0.99089 for Q2 for NN7, and R = 0.9947 for Q3 for NN7). Moreover, the comparison between the predicted results and the classical models (Gibbs model, Generalized dual-site Langmuir model, and Ideal Adsorption Solution Theory) shows that the neural network models gave far better results. 
520 |a U ovom radu ispitana je primjena neuronskih mreža u modeliranju procesa adsorpcije smjese plinova (CO2, CH4 i N2) na različitim aktivnim ugljicima. Izrađeno je sedam modela neuronskih mreža, karakteriziranih različitim strukturama s ciljem predviđanja adsorpcije smjesa plinova. Za testiranje neuronskih mreža primijenjen je skup od 417, 625, 143, 87, 64, 64 i 40 podatkovnih točaka za NN1 do NN7. Od ukupnih podataka 60 %, 20 % i 20 % rabljeno je za obuku, validaciju i testiranje sedam modela. Rezultati pokazuju dobar odnos predviđenih i eksperimentalnih vrijednosti za svaki model; pronađene su dobre korelacije (R = 0,99656 za NN1, R = 0,99284 za NN2, R = 0,99388 za NN3, R = 0,99639 za Q1 za NN4, R = 0,99472 za Q2 za NN4, R = 0,99716 za Q1 za NN5, R = 0,99972 za Q3 za NN5, R = 0,99746 za Q2 za NN6, R = 0,99783 za Q3 za NN6, R = 0,9946 za Q1 za NN7, R = 0,99089 za Q2 za NN7 i R = 0,9947 za Q3 za NN7). Dodatno, usporedba predviđenih rezultata i klasičnih modela (Gibbsov model, generalizirani Langmuirov model i teorija idealne adsorpcije otopine) pokazuje da su modeli neuronskih mreža dali daleko bolje rezultate. 
653 0 |a Modeliranje  |a Adsorpcija  |a Aktivni ugljen  |a Smjesa plinova  |a Neuronske mreže 
700 1 |a Khaouane, Latifa  |4 aut  |9 HR-ZaNSK 
700 1 |a Hanini, Salah  |4 aut  |9 HR-ZaNSK 
773 0 |t Kemija u industriji (Online)  |x 1334-9090  |g 68 (2019), 7/8 ; str. 289-302  |w nsk.(HR-ZaNSK)000530475 
981 |b Be2019  |b B04/19 
998 |b tino2008 
856 4 0 |u https://doi.org/10.15255/KUI.2019.002 
856 4 0 |u http://silverstripe.fkit.hr/kui/issue-archive/article/671  |y Kemija u industriji (Online) 
856 4 0 |u https://hrcak.srce.hr/222487  |y Hrčak 
856 4 1 |y Digitalna.nsk.hr 

Slični primjerci