Prediction of removal efficiency of Lanaset Red G on walnut husk using artificial neural network model

Abstract

An artificial neural network (ANN) model was used to predict removal efficiency of Lanaset Red (LR) G on walnut husk (WH). This adsorbent was characterized by FTIR-ATR. Effects of particle size, adsorbent dose, initial pH value, dye concentration, and contact time were investigated to optimize sorption process. Operating variables were used as the inputs to the constructed neural network to predict the dye uptake at any time as an output. Commonly used pseudo second-order model was fitted to the experimental data to compare with ANN model. According to error analyses and determination of coefficients, ANN was the more appropriate model to describe this sorption process. Results of ANN indicated that pH was the most efficient parameter (43%), followed by initial dye concentration (40%) for sorption of LR G on WH.