Performance Assessment of Advanced Biological Wastewater Treatment Plants Using Artificial Neural Networks

Abstract

In this study, the application of Artificial Neural Network (ANN) techniques was used to predict the performance of wastewater treatment plant. The ANN-based model for prediction of effluent biological oxygen demand (BOD) concentrations was formed using a three-layered feed forward ANN, which used a back propagation learning algorithm. Based on the mean absolute percentage error (MAPE), the sum of the squares error (SSE), the absolute fraction of variance (R 2 ), the root-mean-square (RMS), the coefficient of variation in percent (cov) values, and ANN models predicted effluent BOD concentration. The R 2 values were found to be 94.13% and 93.18% for the training and test sets of treatment plant process, respectively. It was found that the ANN model could be employed successfully in estimating the daily BOD in the effluent of wastewater biological treatment plants.