Modeling of fixed-bed adsorption of fluoride on bone char using a hybrid neural network approach

This study introduces a hybrid model based on the Thomas equation and artificial neural networks (ANNs) for the modeling of unsymmetrical breakthrough curves obtained from the fluoride adsorption on bone char. Experimental results of kinetics, isotherms and breakthrough curves of fluoride adsorption on two commercial bone chars have been used for analyzing the capabilities and limitations of this hybrid ANN model. Performance of this hybrid model has been studied and compared with respect to the results of traditional linear regression of the Thomas breakthrough equation at different operating conditions of packed-bed adsorption columns. Results showed that an improvement in the modeling capabilities of Thomas model can be obtained using ANNs. Specifically, the hybrid ANNs-Thomas model showed determination coefficients higher than 0.9 and its average mean square errors are lower, up to 86%, than those obtained with the linear modeling approach. In fact, the present study illustrates that the improper handling of the Thomas model using traditional regression approach may lead to imprecise values of design parameters and erroneous conclusions of adsorption performance. On the other hand, the hybrid ANNs-Thomas model is useful for determining reasonable and accurate design parameters of packed-bed adsorption columns. This modeling approach can be useful for the process system engineering of dynamic adsorption systems involved in the field of water treatment and purification. (C) 2013 Elsevier B.V. All rights reserved.