Total dissolved solids (TDS) modeling by artificial neural networks in the distribution system of drinking water of Hyderabad city

  • Authors:

  • Niaz A. Memon;M. A. Unar;Nikos. E. Mastorakis;G. B. Khaskheli

  • Affiliations:

  • Department of Civil Engineering, Quaid-e-Awam University of Engineering Science & Technology, Nawabshah, Pakistan;Department of Computer Systems and Software Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan;Technical University of Sofia, Bulgaria;Department of Civil Engineering, Mehran University of Engineering & Technology, Jamshoro

  • Venue:
  • ICCOMP'09 Proceedings of the WSEAES 13th international conference on Computers
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Demanding public opinion for providing safe drinking water is now an increasing constant pressure on the authorities concerned to prevent the human health from contaminated drinking water. Hence latest techniques are employed to predict the critical parameters like, pH, chlorine, turbidity, TDS, and Electrical conductivity, in the distribution systems. In this study Radial Basis Function RBF model is presented to predict the TDS, one of the important parameters of distribution system of drinking water of Hyderabad city. The mean value of TDS observed at 10 locations is 586.418 mg/l with standard deviation of 5.734. ANN model is trained, tested and validated for the data available from a 3 years study completed on weekly basis. Input and output weights are generated and the Sum of Square Error (SSE) is 0.139088 with faster training time of 0.95300 seconds. 09 Neurons in the hidden layer of the model reveal that the ANNs modeling for predicting the parameters of the drinking water is highly successful; which is the prime object of this study.