Abstract:

Predicting biogas production is important for energy management in wastewater treatment plants (WWTPs). Biogas production quantity depends on its production system variables, such as, influent flow rate, process temperature, alkalinity, volatile fatty acid, sludge retention time, total suspended solid, etc. WWTPs keep the records of wastewater treatment process values with supervisory control and data acquisition (SCADA) system on a regular basis. The relationship between the biogas production and its production system variables, which are measured continuously with SCADA system, can be identified with classification and regression tree (CART) algorithm by using the existing data. In this paper, CART approach is presented for the prediction of biogas production at WWTPs. Standard CART algorithm is used to select split predictor. Curvature and interaction tests are also applied in the model to search for reducing split predictor selection bias and improving the detection of important interactions among each predictor and response and among each pair of predictors and response in turn.   

Keywords: