Evaluating the performance of a sequencing batch reactor for sanitary wastewater treatment using artificial neural network

In this work, the performance of a sequencing batch reactor (SBR) was studied for treating sanitary wastewater of Yazd power plant, Iran. For this purpose, at the first, a pilot system was designed, installed, and started up. Then the effects of retention time, pH, temperature, influent chemical oxygen demand (COD) concentration, and air flow rate were investigated on the effluent concentration of COD. In SBR reactor used in the Yazd power plant, the microalga was not used for the wastewater treatment. In this case, the COD effluent output was, at the best conditions, approximately 92 mg/L. In the studied SBR system, we used the Chlorella vulgaris microalgae and microorganisms, simultaneously. In this case, the COD level reached 34 mg/L. An artificial neural network (ANN) was developed by applying Levenberg-Marquardt training algorithm to predict the effluent concentration of COD. The optimum conditions were obtained at pH = 8, temperature of 30 degrees C, influent COD concentration of 600 mg/L, and air flow rate of 50 L/min. ANN predicted results were in good agreement with the experimental data with a validation coefficient of determination (R-2) and validation mean square error of 0.962 and 0.0015, respectively.