Prediction of wastewater treatment plant performance using artificial neural networks

Artificial neural networks (ANN) models were developed to predict the performance of a wastewater treatment plant (WWTP) based on past information. The data used in this work were obtained from a major conventional treatment plant in the Greater Cairo district, Egypt, with an average flow rate of 1 million m3/day. Daily records of biochemical oxygen demand (BOD) and suspended solids (SS) concentrations through various stages of the treatment process over 10 months were obtained from the plant laboratory. Exploratory data analysis was used to detect relationships in the data and evaluate data dependence. Two ANN-based models for prediction of BOD and SS concentrations in plant effluent are presented. The appropriate architecture of the neural network models was determined through several steps of training and testing of the models. The ANN-based models were found to provide an efficient and a robust tool in predicting WWTPperformance.