Development of a Neural Sensor for On-Line Prediction of Coagulant Dosage in a Potable Water Treatment Plant in the Way of Its Diagnosis

  • Hector Hernandez
  • Marie-Véronique Le Lann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4140)


Coagulation is one of the most important stages in surface water treatment, allowing for the removal of colloidal particles. Its control, in the majority of the plants remains still manual and requires long and expensive analyses of laboratory which provide only periodic information. The present work describes an innovative methodology integrating various techniques for the development of a diagnosis system of this plant. A first part, concerned by this paper, consisted in developing a software sensor based on artificial neural networks for predicting on-line the amount of optimal coagulant dosage from raw water characteristics such as turbidity, pH, temperature, etc. In a second part this information will be integrated like an input to a diagnosis system of the plant. The development of the neural sensor has been performed based in real data covering several years of operation and its performance have been compared toward those given by a multi-linear interpolation.


Hide Layer Total Solid Suspend Water Treatment Plant Coagulant Dosage Online Prediction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baba, K., Enbutu, I., Yoda, M.: Explicit representation of knowledge acquired from plant historical data using neural network. In: Int. Joint Conf. on Neural Networks, Washington, DC (1990)Google Scholar
  2. 2.
    Mirsepassi, A., Cathers, B., Dharmappa, H.B.: Predicted of chemical dosage in water treatment plants using ANN and Box-Jenkings models. In: Preprints of 6th IAWQ Asia-Pacific Regional Conference, Korea, 16-561-1568 (1997)Google Scholar
  3. 3.
    Enbutsu, I., Baba, K., Hara, N., Waseda, K., Nogita, A.: Integration of multi AI paradigms for intelligent operation support system – fuzzy rule extraction from a neural network. Wat. Res. 28, 11–12 (1998)Google Scholar
  4. 4.
    Valentin, N.: Construction d’un capteur logiciel pour le contrôle automatique du procédé de coagulation en traitement d’eau potable. Thèse de doctorat, UTC/L.desEaux/CNRS (2000)Google Scholar
  5. 5.
    Lamrini, B., Benhammou, A., Le Lann, M.-V., Karama, A.: A neural software sensor for online prediction of coagulant dosage in a drinking water treatment plant. Transactions of the Institute of Measurements and Control 27(3), 195–213 (2005)CrossRefGoogle Scholar
  6. 6.
    Lind, C.: Coagulation Control and Optimization: Part One, Public Works, pp. 56–57 (October 1994)Google Scholar
  7. 7.
    Lind, C.: Coagulation Control and Optimization: Part Two. Public Works, pp. 32–33 (November 1994)Google Scholar
  8. 8.
    Jackson, J.E.: A user’s guide to principal components. Wiley Series in Probability and Mathematical Statistics. John Wiley &Sons, Chichester (2003)Google Scholar
  9. 9.
    McCulloch, W.S., Pitts, W.: A logical calculs of the ideas immanent in nervous activity. Bulletin of Math. Biophysics 5, 115–133 (1943)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Rumelhart, D.E., McClelland, J.L.: Parallel distribution processing: exploration in the microstructure of cognition, vol. 1. MIT Press, Cambridge (1986)Google Scholar
  11. 11.
    Duch, W.: Survey of neural transfer functions. Neural Computing Surveys 2 (1999)Google Scholar
  12. 12.
    Matlab, Neural Network Toolbox, User’ Guide, Inc. (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hector Hernandez
    • 1
  • Marie-Véronique Le Lann
    • 1
    • 2
  1. 1.Laboratoire d’Analyse et d’Architecture des Systèmes, LAAS-CNRSToulouseFrance
  2. 2.Département de Génie Electrique et InformatiqueUniversité de Toulouse, INSAToulouseFrance

Personalised recommendations