%0 Journal Article %T Artificial Neural Network Optimization of Adsorption Parameters for Cr(VI), Ni(II) and Cu(II) Ions Removal from Aqueous Solutions by Riverbed Sand %J Iranian Journal of Chemistry and Chemical Engineering %I Iranian Institute of Research and Development in Chemical Industries (IRDCI)-ACECR %Z 1021-9986 %A Kavitha, Balasubramani %A Sarala Thambavani, D %D 2020 %\ 10/01/2020 %V 39 %N 5 %P 203-223 %! Artificial Neural Network Optimization of Adsorption Parameters for Cr(VI), Ni(II) and Cu(II) Ions Removal from Aqueous Solutions by Riverbed Sand %K Adsorption %K Isotherm %K Kinetics %K Thermodynamics %K Artificial neural network models %R 10.30492/ijcce.2020.39785 %X Removal of Cr(VI), Ni(II), and Cu(II) from aqueous solution by Riverbed Sand containing Quartz as major clay minerals as a non-toxic and economically viable treatment was investigated. The structure, morphology, surface area, and elemental composition were confirmed using XRD, SEM, EDAX, FT-IR, and BET techniques. The N2 adsorption-desorption isotherm reveals their mesoporous structure and large BET surface area (122.75 m²/g). The effect of the initial metal concentration, pH, adsorption dosage, contact time, and temperature were examined in batch experiments to understand adsorption isotherms, kinetics, and thermodynamics. Results suggest that the equilibrium adsorption was described by the Langmuir model. Adsorption kinetics was described well by the pseudo-second-order model and were followed by an intraparticle diffusion mechanism. The thermodynamics studies reveal that the adsorption was spontaneous and exothermic. An Artificial Neural Network (ANN) model was used to optimize the removal efficiency of Cr(VI), Ni(II), and Cu(II) on QKCI. The model was developed using a three-layer feed-forward backpropagation algorithm with 15, 18, and 20 hidden neurons for Cr(VI), Ni(II), and Cu(II) ions. Comparison between the model results and experimental data gives a high degree of correlation (R2= 0.9863 for Cr(VI), 0.9591 for Cu(II)) and 0.9469 for Ni(II) indicating that the model is able to predict the sorption efficiency with reasonable accuracy. %U https://ijcce.ac.ir/article_39785_f1cccdbf06716ec782a0fb78d77b3a9a.pdf