Neural networks approaches for predicting COD concentration during effluent treatment process

Present study reveals that the efficiency of an effluent treatment plant closely relates to the operation of the plant. To forecast and improve the operating performance, an Artificial Neural Network (ANN) paradigm has been applied to an effluent treatment plant. An ANN which is able to learn the non-linear performance relationships of historical data of a plant has been proved to be capable of providing operational guidance for plant operators. Here, the application of Artificial Neural Network (ANN) techniques is used to predict the Chemical Oxygen Demand for effluent treatment plant. Sets of historical plant data of COD were collected from common effluent treatment plant at Govindpura, Bhopal (India). Data were collected over a period of 3 years from the influent and effluent streams of the station. Two ANN-based models for forecasting of COD concentrations at influent and effluent points were formed using a three-layered feed forward ANN, which uses a back propagation learning algorithm. Using Forecaster XL software the correlation factor (R) for Model-1 is found to be 0.9078 and for Model-2 is 0.9216. Thus, ANN proved as a good tool for prediction and forecasting the effluent treatment plant parameters.