Adsorption behavior of dyes from aqueous solution using agricultural waste: modeling approach

Abstract

The development of efficient and ecofriendly biosorbent for the removal of dyes is a priority in regions where human health is directly affected by elevated dye concentrations. Biosorption of dyes on shelled Moringa oleifera seed powder (SMOS) was investigated for the removal of methylene blue and Congo red from aqueous solution. Sorption studies led to the standardization of the optimum conditions: dye concentration (25 mg/l), contact time (40 min), particle size (105 μM), and volume (200 ml) at pH 6.5 and 2.5 for the removal of methylene blue (90.27 %) and Congo red (98.52 %). A single layer artificial neural network (ANN) model was developed to simulate the process and predict the removal efficiency of SMOS for the removal of dyes. Different ANN architectures were tested by varying network topology, resulting into an excellent agreement between the experimental data and the predicted values. The Levenberg–Marquardt algorithm was found best of BP algorithms with a minimum mean squared error for training and cross validation as 1.89951E−09 and 0.145001313, respectively.