BTPC-Based DES-Functionalized CNTs for A s 3 + Removal from Water

NARX Neural Network Approach

Seef Saadi Fiyadh, Mohammed Abdulhakim Alsaadi, Mohamed Khalid Alomar, Sabah Saadi Fayaed, Farouk Mjalli, Ahmed El-Shafie

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this study, a novel adsorbent process was developed using a deep eutectic solvent (DES) system based on benzyltriphenylphosphonium chloride (BTPC) as a functionalization agent of carbon nanotubes (CNTs) for arsenic ion removal from water. The nonlinear autoregressive network with exogenous inputs (NARX) neural network strategy was used for the modeling and predicting the adsorption capacity of functionalized carbon nanotubes. The developed adsorbent was characterized using zeta potential, Fourier transform infrared (FTIR), and Raman spectroscopy. The effects of operational parameters such as initial concentration, adsorbent dosage, pH, and contact time are studied to investigate the optimum conditions for maximum arsenic removal. Three kinetic models were used to identify the adsorption rate and mechanism, and the pseudo-second order best described the adsorption kinetics. Four statistical indicators were used to determine the efficiency and accuracy of the NARX model, with a minimum value of mean square error, 6.37×10-4. In addition, a sensitivity study of the parameters involved in the experimental work was performed. The NARX model prediction was consolidated with the experimental result and proved its efficiency at predicting arsenic removal from water with a correlation coefficient R2 of 0.9818.

Original languageEnglish
Article number04018070
JournalJournal of Environmental Engineering (United States)
Volume144
Issue number8
DOIs
Publication statusPublished - Aug 1 2018

Fingerprint

Carbon Nanotubes
Arsenic
Adsorbents
Eutectics
Chlorides
arsenic
Carbon nanotubes
chloride
Neural networks
adsorption
Adsorption
Water
Nonlinear networks
kinetics
Kinetics
Raman spectroscopy
Zeta potential
FTIR spectroscopy
Mean square error
water

Keywords

  • Arsenic ions
  • Carbon nanotubes
  • Deep eutectic solvents
  • NARX neural network
  • Water treatment

ASJC Scopus subject areas

  • Environmental Engineering
  • Environmental Chemistry
  • Civil and Structural Engineering
  • Environmental Science(all)

Cite this

BTPC-Based DES-Functionalized CNTs for A s 3 + Removal from Water : NARX Neural Network Approach. / Fiyadh, Seef Saadi; Alsaadi, Mohammed Abdulhakim; Alomar, Mohamed Khalid; Fayaed, Sabah Saadi; Mjalli, Farouk; El-Shafie, Ahmed.

In: Journal of Environmental Engineering (United States), Vol. 144, No. 8, 04018070, 01.08.2018.

Research output: Contribution to journalArticle

Fiyadh, Seef Saadi ; Alsaadi, Mohammed Abdulhakim ; Alomar, Mohamed Khalid ; Fayaed, Sabah Saadi ; Mjalli, Farouk ; El-Shafie, Ahmed. / BTPC-Based DES-Functionalized CNTs for A s 3 + Removal from Water : NARX Neural Network Approach. In: Journal of Environmental Engineering (United States). 2018 ; Vol. 144, No. 8.
@article{fabafa27a9a747f187176bfdf349be59,
title = "BTPC-Based DES-Functionalized CNTs for A s 3 + Removal from Water: NARX Neural Network Approach",
abstract = "In this study, a novel adsorbent process was developed using a deep eutectic solvent (DES) system based on benzyltriphenylphosphonium chloride (BTPC) as a functionalization agent of carbon nanotubes (CNTs) for arsenic ion removal from water. The nonlinear autoregressive network with exogenous inputs (NARX) neural network strategy was used for the modeling and predicting the adsorption capacity of functionalized carbon nanotubes. The developed adsorbent was characterized using zeta potential, Fourier transform infrared (FTIR), and Raman spectroscopy. The effects of operational parameters such as initial concentration, adsorbent dosage, pH, and contact time are studied to investigate the optimum conditions for maximum arsenic removal. Three kinetic models were used to identify the adsorption rate and mechanism, and the pseudo-second order best described the adsorption kinetics. Four statistical indicators were used to determine the efficiency and accuracy of the NARX model, with a minimum value of mean square error, 6.37×10-4. In addition, a sensitivity study of the parameters involved in the experimental work was performed. The NARX model prediction was consolidated with the experimental result and proved its efficiency at predicting arsenic removal from water with a correlation coefficient R2 of 0.9818.",
keywords = "Arsenic ions, Carbon nanotubes, Deep eutectic solvents, NARX neural network, Water treatment",
author = "Fiyadh, {Seef Saadi} and Alsaadi, {Mohammed Abdulhakim} and Alomar, {Mohamed Khalid} and Fayaed, {Sabah Saadi} and Farouk Mjalli and Ahmed El-Shafie",
year = "2018",
month = "8",
day = "1",
doi = "10.1061/(ASCE)EE.1943-7870.0001412",
language = "English",
volume = "144",
journal = "Journal of Environmental Engineering, ASCE",
issn = "0733-9372",
publisher = "American Society of Civil Engineers (ASCE)",
number = "8",

}

TY - JOUR

T1 - BTPC-Based DES-Functionalized CNTs for A s 3 + Removal from Water

T2 - NARX Neural Network Approach

AU - Fiyadh, Seef Saadi

AU - Alsaadi, Mohammed Abdulhakim

AU - Alomar, Mohamed Khalid

AU - Fayaed, Sabah Saadi

AU - Mjalli, Farouk

AU - El-Shafie, Ahmed

PY - 2018/8/1

Y1 - 2018/8/1

N2 - In this study, a novel adsorbent process was developed using a deep eutectic solvent (DES) system based on benzyltriphenylphosphonium chloride (BTPC) as a functionalization agent of carbon nanotubes (CNTs) for arsenic ion removal from water. The nonlinear autoregressive network with exogenous inputs (NARX) neural network strategy was used for the modeling and predicting the adsorption capacity of functionalized carbon nanotubes. The developed adsorbent was characterized using zeta potential, Fourier transform infrared (FTIR), and Raman spectroscopy. The effects of operational parameters such as initial concentration, adsorbent dosage, pH, and contact time are studied to investigate the optimum conditions for maximum arsenic removal. Three kinetic models were used to identify the adsorption rate and mechanism, and the pseudo-second order best described the adsorption kinetics. Four statistical indicators were used to determine the efficiency and accuracy of the NARX model, with a minimum value of mean square error, 6.37×10-4. In addition, a sensitivity study of the parameters involved in the experimental work was performed. The NARX model prediction was consolidated with the experimental result and proved its efficiency at predicting arsenic removal from water with a correlation coefficient R2 of 0.9818.

AB - In this study, a novel adsorbent process was developed using a deep eutectic solvent (DES) system based on benzyltriphenylphosphonium chloride (BTPC) as a functionalization agent of carbon nanotubes (CNTs) for arsenic ion removal from water. The nonlinear autoregressive network with exogenous inputs (NARX) neural network strategy was used for the modeling and predicting the adsorption capacity of functionalized carbon nanotubes. The developed adsorbent was characterized using zeta potential, Fourier transform infrared (FTIR), and Raman spectroscopy. The effects of operational parameters such as initial concentration, adsorbent dosage, pH, and contact time are studied to investigate the optimum conditions for maximum arsenic removal. Three kinetic models were used to identify the adsorption rate and mechanism, and the pseudo-second order best described the adsorption kinetics. Four statistical indicators were used to determine the efficiency and accuracy of the NARX model, with a minimum value of mean square error, 6.37×10-4. In addition, a sensitivity study of the parameters involved in the experimental work was performed. The NARX model prediction was consolidated with the experimental result and proved its efficiency at predicting arsenic removal from water with a correlation coefficient R2 of 0.9818.

KW - Arsenic ions

KW - Carbon nanotubes

KW - Deep eutectic solvents

KW - NARX neural network

KW - Water treatment

UR - http://www.scopus.com/inward/record.url?scp=85048642540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048642540&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)EE.1943-7870.0001412

DO - 10.1061/(ASCE)EE.1943-7870.0001412

M3 - Article

VL - 144

JO - Journal of Environmental Engineering, ASCE

JF - Journal of Environmental Engineering, ASCE

SN - 0733-9372

IS - 8

M1 - 04018070

ER -