USING ARTIFICIAL NEURAL NETWORK (ANN) MODEL FOR CHROMIUM (VI) REMOVAL FROM AQUEOUS SOLUTIONS BY IRON OXIDE NANOPARTICLES

摘要

Heavy metal industrial wastewater is one of the most important environmental issues. Among the various types of heavy metals; chromium is one of hazardous and toxic environmental pollutant. In order to prevent damage caused by chromium, it is essential to prevent it entering it into environment. The purpose of thisstudy is removing chromium byiron oxide nanoparticlesand thenartificial neural network has been used for estimating the best removal Cr (VI) model. The impact of some important factors such as pH, initial concentration, amount of adsorbent, contact time and temperature on chromium removal process, were investigated. The optimum conditions have been achieved in pH=3, initial concentration of Cr, 10 mg/L; concentration of Fe203, 1gr/L; contact time, 60 minutes and temperature of 25〇C. Actually, almost 90% chromium has been removed under the mentioned conditions.After backpropagation (BP) training, the ANN model was able to predict adsorption efficiency with a tangent sigmoid transfer function (Tansig) at hidden layer with 11 neurons and a linear transfer function (Purelin) at out layer. The Levenberg-Marquardt algorithm (LMA) was applied, giving a minimum mean squared error (MSE) for training and cross validation at the ninth place of decimal. The high correlation coefficient (Rann - 0-996) between the model and experimental data showed that the model is able to predict the removal of Cr (VI) from aqueous solutions by iron oxide nanoparticles.