Artificial neural network optimization for removal of hazardous dye Eosin Y from aqueous solution using Co2O3-NP-AC: Isotherm and kinetics study

Abstract

The present research is focused on the synthesis and characterization of cobalt (III) oxide (Co2O3) nanoparticle loaded on activated carbon to prepare an outstanding sorbent for the removal of eosin Y (EY) as hazardous dye from aqueous solution. The sorbent was identified by SEM and XRD analysis. The effect of solution pH, adsorbent dosage (0.005–0.02g), contact time (0.5–30min) and initial eosin Y concentration (30–80mgL−1) on the adsorption process was investigated and modeled by artificial neural network. Following optimization of variables, the experimental equilibrium data was analysis by Langmuir, Freundlich, Tempkin and D–R isothermal models and explored that the data well presented by Langmuir model with a maximum adsorption capacity of 555.56mgg−1 at 25°C. Kinetic studies at various adsorbent dosage and initial EY concentrations show that high removal percentage (>90%) was achieved within 15min of the start of every experiment at most conditions. The adsorption of EY follows the pseudo-second-order rate equation in addition to intraparticle diffusion model. The experimental data were applied to train the multilayer feed forward neural network with three inputs and one output with different algorithms and different numbers of neurons in the hidden layer. The minimum mean squared error (MSE) of 1.49e−04 and determination coefficient of (R2) 0.9991.