Shahid Beheshti University Advanced Environmental Sciences 3115-7173 14 1 2016 03 20 Intelligent optimization of common water treatment plant for the removal of organic carbon Intelligent optimization of common water treatment plant for the removal of organic carbon 1 8 97653 FA Taher Ahmadzadeh Department of Environmental Engineering, Faculty of Environment, University of Tehran Naser Mehrdadi Department of Environmental Engineering, Faculty of Environment, University of Tehran Mojtaba Ardestani Department of Environmental Engineering, Faculty of Environment, University of Tehran Akbar Baghvand Department of Environmental Engineering, Faculty of Environment, University of Tehran Journal Article 2016 02 22 Intelligent model optimization is a key factor in water treatment improvement. In current study, we applied the artificial neural networks modelling for the optimization of coagulation and flocculation processes to get sufficient water quality control over the total organic carbon parameter. ANN network consisted of a multilayer feed forward structure with backpropagation learning algorithm with the output layer of ferric chloride and cationic polymer dosages. The results were simultaneously compared with the nonlinear multiple regression model. Model validation phase performed using 94 unknown samples for which the prediction result was in good agreement with the observed values. Analysis of the results showed a determination coefficient of 0.85 for cationic polymer and 0.97 for ferric chloride models. Mean absolute percentage error and root mean square errors were calculated consequently as 5.8% and 0.96 for polymer and 3.1% and 1.97 for ferric chloride models. According to the results, artificial neural networks showed to be very promising for the optimization of water treatment processes. Intelligent model optimization is a key factor in water treatment improvement. In current study, we applied the artificial neural networks modelling for the optimization of coagulation and flocculation processes to get sufficient water quality control over the total organic carbon parameter. ANN network consisted of a multilayer feed forward structure with backpropagation learning algorithm with the output layer of ferric chloride and cationic polymer dosages. The results were simultaneously compared with the nonlinear multiple regression model. Model validation phase performed using 94 unknown samples for which the prediction result was in good agreement with the observed values. Analysis of the results showed a determination coefficient of 0.85 for cationic polymer and 0.97 for ferric chloride models. Mean absolute percentage error and root mean square errors were calculated consequently as 5.8% and 0.96 for polymer and 3.1% and 1.97 for ferric chloride models. According to the results, artificial neural networks showed to be very promising for the optimization of water treatment processes. https://envs.sbu.ac.ir/article_97653_8f88d51c3b2f2aee72b78e3da782158e.pdf