%0 Journal Article %T APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR PREDICTING COD REMOVAL EFFICIENCIES OF ROTATING DISKS AND PACKED-CAGE RBCS IN TREATING HYDROQUINONE %J Iranian Journal of Science and Technology Transactions of Civil Engineering %I Shiraz University %Z 2228-6160 %D 2013 %\ 08/01/2013 %V 37 %N 2 %P 325-326 %! APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR PREDICTING COD REMOVAL EFFICIENCIES OF ROTATING DISKS AND PACKED-CAGE RBCS IN TREATING HYDROQUINONE %K Hydroquinone %K COD %K rotating biological contactor %K Neural Networks %R 10.22099/ijstc.2013.1621 %X In this study, an artificial neural network (ANN) was applied to predict the performanceof two rotating biological contactor (RBC) systems in removal of hydroquinone (a toxic aromaticcompound). The first system was a two-staged conventional RBC and the second one was a onestagedpacked-cage RBC with bee-cell 2000 biofilm carriers. Both systems had a total area ofabout 2 m2 for biofilm attachment. The main aim is to predict COD removal efficiencies in bothsystems using ANN. Efficiency evaluation of the reactors was obtained at different influent CODfrom 200 to 5000 mg/L. Exploratory data analysis was used to detect relationships between thedata and the evaluated dependents. The appropriate architecture of the neural network models wasdetermined using several steps of training and testing the models. The modeling results showedthat there is a good agreement between the experimental data and the predicted values with acorrelation coefficient (R2) of 0.998 and 0.997 for RBC with rotating disks and packed-cage RBC,respectively. %U https://ijstc.shirazu.ac.ir/article_1621_196d9dcebba8c9e043965608b7a70f66.pdf