Single Input Single Output Time Series Artificial Neural Network Models for Free Residual Chlorine Forecasting in Water Distribution Networks

Selcuk Soyupak, Hurevren Kilic, Ibrahim Ethem Karadirek, Habib Muhammetoglu

Abstract

The aim of this study is to investigate the utilization of Single Input Single Output Time Series Artificial Neural Networks models as a forecasting tool for estimating Free Residual Chlorine levels at critical locations of fairly complex Water Distribution Systems. The response surface methodology was adopted in identifying performance and precision trends as a function of number of steps used as inputs and number of steps ahead to predict (Horizons). The utilized response surfaces were for coefficient of determination and mean absolute error. The creation of response surfaces was achieved by developing Artificial Neural Network models for several combinations of number of steps used as inputs and number of steps ahead to predict that enable the calculations of coefficient of determination and mean absolute error for the selected combinations. Then these results have been assembled to obtain contour maps by distance weighted least square technique. The maximum attained coefficient of determination levels were within the range 0.656 to 0.974, while minimum achievable mean absolute error levels were within the range 0.0080 to 0.0284 ppm. The achieved mean absolute error is very low when compared with the followings: a) the applied Free Residual Chlorine levels from the source which is about 0.5 ppm and b) the minimum detection limit of the chlorine analyzers given as 0.01 ppm.

References

  1. Bowden, G. J., Nixon, J. B., Dandy, G. C., Maier, H. R., Holmes, M., 2006. Forecasting chlorine residuals in a water distribution system using a general regression neural network. Mathematical and Computer Modelling, 44, 469-484.
  2. EPANET 2, 2000. Users' Manual. Lewis A. Rossman, Cincinnati, OH, USA.
  3. Gibbs, M. S., Morgan, N., Maier, H. R., Dandy, G. C., Holmes, M., Nixon, J.B., 2003. Use of artificial neural networks for modelling chlorine residuals in water distribution systems. Modsim 2003 - International Congress on Modelling and Simulation, Townsville., Australia, Part 2, 789-794.
  4. May, R. J., Maier, H. R., Dandy, G. C., Nixon, J. B., 2004. Control-oriented water quality modelling using artificial neural networks. Proceedings on CD-ROM, Enviro 7804, Sydney, Australia.
  5. May, R. J., Dandy, G. C., Maier, H. R., Nixon, J. B., 2008. Application of partial mutual information variable selection to ANN forecasting of water quality in water distribution systems, Environmental Modelling and Software 23, 1289-1299.
  6. May, R. J., Maier, H. R., Dandy, G. C., Fernando, T.M.K.G., 2008b. Non-linear variable selection for artificial neural networks using partial mutual information. Environmental Modelling and Software, 23, 1312-1326.
  7. Polycarpou, M. M., Uber, J. G., Wang, Z., Shang, F., Brdys, M. A., 2002. Feed-back control of water quality. In: IEEE Control Systems Magazine, pp. 68- 84.
  8. Rodriguez, M. J., Sérodes, J. B., 1999. Assessing empirical linear and non-linear modelling of residual chlorine in urban drinking water systems. Environmental Modelling and Software, 14, 93-102.
  9. SANN (Statistica Automated Neural Network Software), Stat Com, 2008.
  10. Sharma, A., 2000. Seasonal to inter-annual rainfall probabilistic forecasts for improved water supply management: Part 1 - a strategy for system predictor identification. Journal of Hydrology, 239 (1-4), 232 - 239.
  11. Sérodes, J. B., Rodriguez, M. J., Ponton, A., 2001. Chlorcast(c): a methodology for developing decisionmaking tools for chlorine disinfection control. Environmental Modelling and Software 16, 53-62.
  12. Statsoft, 2012, Statistica Electronic Statistics Text book.
  13. TUBITAK Proje Gelisme Raporu, 2009. Içme suyu dagitim sebekelerinde optimum klorlama uygulamalarinin matematiksel modeller kullanilarak gerçeklestirilmesi ve dezenfeksiyon sistemlerinin Yönetimi, Proje No:107G088, Antalya (Turkey) (In Turkish).
Download


Paper Citation


in Harvard Style

Soyupak S., Kilic H., Karadirek I. and Muhammetoglu H. (2012). Single Input Single Output Time Series Artificial Neural Network Models for Free Residual Chlorine Forecasting in Water Distribution Networks . In Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012) ISBN 978-989-8565-33-4, pages 588-593. DOI: 10.5220/0004171105880593


in Bibtex Style

@conference{ncta12,
author={Selcuk Soyupak and Hurevren Kilic and Ibrahim Ethem Karadirek and Habib Muhammetoglu},
title={Single Input Single Output Time Series Artificial Neural Network Models for Free Residual Chlorine Forecasting in Water Distribution Networks},
booktitle={Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012)},
year={2012},
pages={588-593},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004171105880593},
isbn={978-989-8565-33-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012)
TI - Single Input Single Output Time Series Artificial Neural Network Models for Free Residual Chlorine Forecasting in Water Distribution Networks
SN - 978-989-8565-33-4
AU - Soyupak S.
AU - Kilic H.
AU - Karadirek I.
AU - Muhammetoglu H.
PY - 2012
SP - 588
EP - 593
DO - 10.5220/0004171105880593