Using Of Artificial Neural Network For Modeling Of Oily Wastewater In Reverse Osmosis Process

Primary reason for flux decline during the initial period of a membrane separation process is concentration polarization of solute at the membrane surface. This can occur in conjunction with irreversible fouling of the membrane as well as reversible gelcake layer formation. Oily water emulsions are one of the main pollutants emitted into water by industries and domestic sewage. Also oily water in inland waterways and coastal zone is one of the most serious issues of water pollution which needs to be resolved urgently. The results of an experimental study on separation of oil from oily waters are presented. A Film Tec FT30 membrane as a reverse osmosis membrane and a synthetic emulsion using an Iranian crude oil has been employed. The flux-time curves have been analyzed using a modified form of Hermias model to investigate the mechanism of flux decline. The results show that the experimental data is inconsistent with the Intermediate Blocking Filtration Model. Also the limiting flux at all conditions has been determined.In this research the results were evaluated using neural network modeling.