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

R. F. Yu, S. F. Kang, S. L. Liaw, M. C. Chen

Research output: Contribution to journalConference articlepeer-review

40 Scopus citations


Coagulant dosing is one of the major operation costs in water treatment plant, and conventional control of this process for most plants is generally determined by the jar test. However, this method can only provide periodic information and is difficult to apply to automatic control. This paper presents the feasibility of applying artificial neural network (ANN) to automatically control the coagulant dosing in water treatment plant. Five on-line monitoring variables including turbidity (NTU(in)), pH (pH(in)) and conductivity (Con(in)) in raw water, effluent turbidity (NTU(out)) of settling tank, and alum dosage (Dos) were used to build the coagulant dosing prediction model. Three methods including regression model, time series model and ANN models 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 R2 of 0.97 (RMS=0.016), very low average predicted error 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 water treatment.

Original languageEnglish
Pages (from-to)403-408
Number of pages6
JournalWater Science and Technology
Issue number3-4
StatePublished - 2000
EventWater Quality Management in Asia (Asian Waterqual'99) - Taipei, Taiwan
Duration: 18 Oct 199920 Oct 1999


  • Artificial neural network
  • Coagulant dosing
  • On-line monitoring
  • Real-time control
  • Water treatment plant


Dive into the research topics of 'Application of artificial neural network to control the coagulant dosing in water treatment plant'. Together they form a unique fingerprint.

Cite this