Artificial neural network for modeling adsorption of ciprofloxacin onto Fe3O4/ maifan stone composite

Novel Fe3O4/maifan stone composite were prepared by a simple solvothermal method. Physicochemical properties of the novel Fe3O4/maifan stone composite were analyzed using energy-dispersive X-ray spectroscopy, X-ray diffraction, scanning electron microscopy, transmission electron microscopy, N2 adsorption, Fourier-transform infrared spectroscopy and X-ray photoelectron spectroscopy. The Fe3O4/maifan stone composite were used for the adsorption of ciprofloxacin (CIP) antibiotic removal. This paper represents an artificial neural network (ANN) based approach for modeling the adsorp-tion process of the adsorption of CIP onto Fe3O4/maifan stone composite in batch adsorption experi-ments. The ANN model was trained and validated with the adsorption experiments data where pH, adsorbent dosage, and initial CIP concentration were selected as the variables for the batch study, whereas the removal efficiency was considered as the output. The ANN model was first developed using a three-layer back-propagation network with the optimum structure of 3-3-1. The model employed tangent sigmoid transfer function as input in the hidden layer whereas a linear transfer function was used in the output layer. The comparison between modeled data and experimental data provided high degree of correlation (R2 = 0.99942) which indicated the applicability of ANN model for describing the adsorption process with reasonable accuracy. The kinetics of the adsorp-tion of CIP onto Fe3O4/maifan stone composite was better fitted with the pseudo-second-order kinetics model, and thermodynamic parameters of the adsorption of CIP onto Fe3O4/maifan stone composite were calculated. This Fe3O4/maifan stone composite adsorbent can be easily separated.