application of artificial neural network for the prediction of phenol removal from aqueous solution

In this study, the prediction of adsorption capacity of phenol from aqueous solution using lead ferrite-activated carbon composite was investigated using artificial neural network. the network input parameters are ph, contact time, initial phenol concentration and temperature. modeling was done based on 80 measurements of data sets under different operating conditions.multi-layer perceptron (mlp) neural network trained by levenberg-marquardt (lm) and scaled conjugate gradient (scg) algorithms were applied. the optimal number of hidden layers and neurons in each layer was determined using the trial and error method. the values of rmse, aare%, and r2 of the total dataset in the case of mlp-lm model were 0.85389, 1.0007, and 0.99899, respectively. results showed that the proposed neural network model could be successfully used to estimate the adsorption capacity of adsorbent for the phenol removal from aqueous solution.