| Autor: |
Fiyadh SS; Nanotechnology & Catalysis Research Centre (NANOCAT), IPS Building, University of Malaya, Kuala Lumpur 50603, Malaysia. saadisaif3@gmail., AlOmar MK; Department of Civil Engineering, Al-Maaref University College, Ramadi 31001, Iraq., Binti Jaafar WZ; Department of Civil Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia., AlSaadi MA; Nanotechnology & Catalysis Research Centre (NANOCAT), IPS Building, University of Malaya, Kuala Lumpur 50603, Malaysia.; National Chair of Materials Science and Metallurgy, University of Nizwz, Sultanate of Oman, Nizwa 616, Oman., Fayaed SS; Department of Civil Engineering, Al-Maaref University College, Ramadi 31001, Iraq., Binti Koting S; Department of Civil Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia., Lai SH; Department of Civil Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia., Chow MF; Institute of Energy Infrastructure (IEI), Department of Civil Engineering, Universiti Tenaga Nasional, 43000 Kajang, Selangor, Malaysia. Chowmf@uniten.edu.my., Ahmed AN; Institute of Energy Infrastructure (IEI), Department of Civil Engineering, Universiti Tenaga Nasional, 43000 Kajang, Selangor, Malaysia., El-Shafie A; Department of Civil Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia. |
| Abstrakt: |
Multi-walled carbon nanotubes (CNTs) functionalized with a deep eutectic solvent (DES) were utilized to remove mercury ions from water. An artificial neural network (ANN) technique was used for modelling the functionalized CNTs adsorption capacity. The amount of adsorbent dosage, contact time, mercury ions concentration and pH were varied, and the effect of parameters on the functionalized CNT adsorption capacity is observed. The (NARX) network, (FFNN) network and layer recurrent (LR) neural network were used. The model performance was compared using different indicators, including the root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute percentage error (MAPE), mean square error (MSE), correlation coefficient ( R 2 ) and relative error (RE). Three kinetic models were applied to the experimental and predicted data; the pseudo second-order model was the best at describing the data. The maximum RE, R 2 and MSE were 9.79%, 0.9701 and 1.15 × 10 -3 , respectively, for the NARX model; 15.02%, 0.9304 and 2.2 × 10 -3 for the LR model; and 16.4%, 0.9313 and 2.27 × 10 -3 for the FFNN model. The NARX model accurately predicted the adsorption capacity with better performance than the FFNN and LR models. |
