Abstract
This paper proposes a methodology for leak detection and isolation in Water Distribution Systems (WDS). Our work is based on the construction of regression models with optimal parameters which describe the behavior of the network in a normal scenario (no leaks) and comparing these models against predicted output for actual data obtained from pressure measurements along a time horizon. The proposed detection method takes into account possible presence of noise in the demand (assumed known) and/or in the measurements obtained from sensors located in the nodes of the network. A typical water network testbed is employed to validate the proposed methodology. Epanet® software was used to perform the simulations of leak scenarios in order to validate the effectiveness of the proposed approach. Encouraging results are obtained in scenarios with noise and different demand patterns.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Perez, R., Puig, V., Pascual, J.: Leakage detection using pressure sensitivity analysis. In: Computing and Control in the Water Industry Conference, Sheffield, UK (2009)
Puig, V., Schmid, F., Quevedo, J., Pulido, B.: A new fault diagnosis algorithm that improves the integration of fault detection and isolation. In: Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference, Seville, Spain (2005)
Meseguer, J., Puig, V., Escobet, T.: Observer gain effect in linear interval observer-based fault detection. In: Proceedings Sixth IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, Beijing, PR China (2006)
Mashford, J., De Silva, D., Marney, D., Burn, S.: An approach to leak detection in pipe networks using analysis of monitored pressure values by support vector machine. In: Third International Conference on Network and System Security, pp. 534–539 (2009)
Covas, D., Ramos, H.: Hydraulic Transients used for Leak Detection in Water Distribution Systems. In: 4th International Conference on Water Pipeline Systems, BHR Group, pp. 227–241 (2001)
Gertler, J., Romera, J., Puig, V., Quevedo, J.: Leak detection and isolation in water distribution networks using principal components analysis and structured residuals. In: 2010 Conference on Control and Fault Tolerant Systems. Final program and book of abtracts, pp. 191–196. IEEE Press. Institute of Electrical and Electronics Engineers (2010)
Pérez, R., Puig, V., Pascual, J., Quevedo, J., Landeros, E., Peralta, A.: Leakage Isolation using Pressure Sensitivity Analysis in Water Distribution Networks: Application to the Barcelona case study. In: 12th IFAC Symposium on Large-Scale Systems: Theory and Applications, pp. 1–6 (2010)
Bamieh, B., Giarré, L.: Identification of linear parameter varying models. International Journal of Robust and Nonlinear Control, 841–853 (2002)
Vento, J., VicençPuig: Leak Detection and Isolation in Water Pipe Networks using Interval LPV Models.Reporte Técnico UPC (2012)
Blesa, J., Puig, V., Saludes, J., Vento, J.: Leak Detection, Isolation and Estimation in Pressurized Water Pipe Networks Using LPV Models and Zonotopes. In: IFAC Symposium in Nonlinear Control Systems, vol. 1, pp. 36–41 (2010)
Casillas, M., Garza, L., Puig, V.: Extended-Horizon Analysis of Pressure Sensitivities for Leak Detection in Water Distribution Networks. In: 8th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, SafeProcess, pp. 1–6 (accepted for publication, 2012)
Epanet®, http://www.arnalich.com/w/epanet/descargascasosok.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Casillas, M.V., Garza-Castañón, L.E., Puig, V., Vargas-Martínez, A. (2012). Leak Detection in Water Distribution Networks with Optimal Linear Regression Models. In: Su, CY., Rakheja, S., Liu, H. (eds) Intelligent Robotics and Applications. ICIRA 2012. Lecture Notes in Computer Science(), vol 7506. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33509-9_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-33509-9_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33508-2
Online ISBN: 978-3-642-33509-9
eBook Packages: Computer ScienceComputer Science (R0)