Artificial neural network (ANN) approach for modeling and formulation of phenol adsorption onto activated carbon

Abstract

In this study, a three-layer feed-forward back propagation network with Levenberg-Marquardt (LM) learning algorithm was applied to predict adsorption of phenol onto activated carbon (AC). Batch experiments were carried out to obtain experimental data. The neural network was trained considering the amount of adsorbent, initial concentration of phenol, temperature, contact time and pH as input parameters and the final concentration of phenol as a desired parameter. Different transfer functions for hidden and output layers and different number of neurons in a hidden layer were tested to optimize the network structure. An empirical equation for final concentration of phenol was developed by using the weights of optimized network. Accuracy of the developed ANN model was also measured using statistical parameters, such as mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE) and correlation coefficient (R2). Results showed that MAE, MSE, RMSE, and R2 values of the ANN model were 0.1540, 0.0565, 0.2378, and 0.9998, respectively, which indicate high accuracy of the ANN model. In the equilibrium study, predicted results of the ANN model were also compared with experimental data and the results of other conventional isotherm models.