The Application of Artificial Neural Network for Modeling Adsorption of Crab Chitosan Polymer

Adsorption is the process of interaction between a liquid and a solid surface. Adsorption causes the movement of substance molecules dissolved in a liquid to the surface of a solid. This can occur due to physical forces or chemical bonds. So, it is responsible for reducing the concentration of the substance in the solution. In this study, an artificial neural network (ANN) was used to model the adsorption of crab chitosan polymer on sand grains with sizes of 40 mesh and 60 mesh. ANN could model adsorption more accurately compared to adsorption isotherm models such as Langmuir, Freundlich, Henry, and HarkinsJura. In this study the ANN, Langmuir, Freundlich, Henry, and Harkins-Jura models gave mean absolute relative errors (MAREs) of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.6% ,17.1% ,13.4% ,26.2%</tex> , and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">21.5%</tex> , respectively.