Application of artificial neural network to control the coagulant dosing in water treatment plant

Goagulant dosing is one of the major operation costs in water treatment pla nt, and conventional control of this process for most plants is generally d etermined by the jar test. However, this method can only provide periodic i nformation and is difficult to apply to automatic control. This paper prese nts the Feasibility of applying artificial neural network (ANN) to automati cally control the coagulant dosing in water treatment plant. Five on-line m onitoring variables including turbidity (NTUin), pH (pH(in)) and conductivi ty (Con(in)) in raw water, effluent turbidity (NTUout) of settling tank, an d alum dosage (Dos) were used to build the coagulant dosing prediction mode l. Three methods including regression model, time series model and ANN mode ls were used to predict alum dosage. According to the result of this study, the regression model performed a poor prediction on coagulant dosage. Both time-series and ANN models performed precise prediction results of dosage. The ANN model with ahead coagulant dosage performed the best prediction of alum dosage with a R-2 of 0.97 (RMS=0.016), very low average predicted err or of 0.75 mg/L of alum were also found in the ANN model. Consequently, the application of ANN model to control the coagulant dosing is feasible in wa ter treatment.