Optimization of the removal Pb (II) and its Gibbs free energy by thiosemicarbazide modified chitosan using RSM and ANN modeling.

In this research, the removal of Pb (II) by thiosemicarbazide modified chitosan (TSFCS) using RSM and ANN modeling was studied. Also, Gibbs free energy changes of adsorption process based on changes in initial concentration and temperature of solution was investigated. Optimization of these two objectives was performed using NSGA-II and RSM. The regression coefficients of the RSM model for the removal percentage and Gibbs free energy changes were 0.9776 and 0.9864, respectively. Also, the F-values of RSM for the removal efficiency and Gibbs free energy were 81.72365 and 93.78053, respectively, show the proper accuracy of model. The best structure of the neural network with 5 hidden layers, which has 3, 3, 6, 4, 2 neurons in each layers, respectively. Also the transfer function was tansig, tansig, logsig, tansig, tansig for each layer. The initial population of the study for the purpose of optimization with NSGA-II algorithm was consist of 50 samples. The results of two methods NSGA-II and RSM show that the maximum removal efficiency (92%) and minimum ΔG (-5 Kj/mol) are achieved at the highest temperature (55 °C) and lowest initial concentration of solution (10 ppm). The desirability degree for the RSM optimization obtained 0.981.