Advertisement

Data Analysis, Visualization, and Leak Size Modeling for Water Distribution Network

  • Shikha Pranesh GuptaEmail author
  • Umesh Kumar Pandey
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 898)

Abstract

Data analysis and visualization are greatly used in ubiquitous computing environments. Contemporary water distribution networks (WDN) have become extremely adaptive, dynamic, heterogeneous, and large scaled. Management of such system is not trivial to fulfill these features, leading to more and more complex management. Along with encompassing state of art and novel techniques for such diversely dynamic system, in this paper two hydraulic parameters namely pressure and flow is measured. Epanet is used for such system’s setup. This technique has their own pros and cons which makes them suitable according to the requirements and contextual situations. Detail analysis of hydraulic parameter of WDN is done in this paper, and it can be a benchmark to lead toward most appropriate solution to model leak size. This paper incorporates a practical approach to collect the information from the network setup and after the visualization, analysis and computation of that data, leak size is modeled.

Keywords

Water distribution network Analysis Visualization Modeling Leakage 

References

  1. 1.
  2. 2.
  3. 3.
  4. 4.
    Hunaidi, O., Chu, W.T.: Acoustical characteristics of leak signals in plastic water distribution pipes. Appl. Acoust. 58, 235–254 (1999)CrossRefGoogle Scholar
  5. 5.
    Martin, L., Angus, S., John, V., Xiao-Jian, W., Pedro, L.: A Review of Leading-edge Leak Detection Techniques for Water Distribution Systems (2003)Google Scholar
  6. 6.
    Casillas, M.V., Puig, V., Garza-Castanon, L.E., Rosich, A.: Optimal sensor placement for leak location in water distribution networks using genetic algorithms. In: Sensors 2013, pp. 14984–15005 (2013)CrossRefGoogle Scholar
  7. 7.
    Caputo, A.C., Pelagagge P.M.: Using neural networks to monitor piping systems. Process Saf. Progr. 22(2), 119–127(2003)CrossRefGoogle Scholar
  8. 8.
    Feng, J., Zhang, H.: Algorithm of pipeline leak detection based on discrete incremental clustering method. In: Huang, D.S., Li, K., Irwin, G.W. (eds.) Computational Intelligence. ICIC 2006. Lecture Notes in Computer Science, vol. 4114. Springer, Berlin, Heidelberg (2006)Google Scholar
  9. 9.
    Mashford, J., De Silva, D., Marney, D., Burn, S.: An Approach Leak Detection in Pipe Networks Using Analysis of Monitored Pressure Values by Support Vector Machine, pp. 534–539. IEEE (2009)Google Scholar
  10. 10.
    Kwok, T.J.: Support vector mixture for classification and regression problems. In: Proceedings of the International Conference on Pattern Recognition (ICPR), Brisbane, Australia, pp. 255–258 (1998)Google Scholar
  11. 11.
    Kumar, A., Kumar, K., Bharanidharan, B., Matial, N., Dey, E., Singh, M., Thakur, V., Sharma, S., Malhotra, N.: Design of water distribution system using EPANET. Int. J. Adv. Res. 3(9), 789–812 (2015)Google Scholar
  12. 12.
    Wu, Z.Y., Sage, P.: Water loss detection via genetic algorithm optimization-based model calibration. In: ASCE 8th International Symposium on Water Distribution System Analysis, Cincinnati (2006)Google Scholar
  13. 13.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, NY (1995)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.MATS UniversityRaipurIndia

Personalised recommendations