Cost-effective sensors placement and leak localization – the Neptun pilot of the ICeWater project

This paper extends previous research to analytically identify leaks within a water distribution network (WDN), by combining hydraulic simulation and network science based data analysis techniques. The WDN model is used to run several ‘leakage scenarios’, by varying leak location (pipe) and severity, and to build a dataset with corresponding variations in pressure and flow, induced by the leak. All junctions and pipes are considered for potential pressure and flow sensors deployment; a clustering procedure on these locations identifies the most relevant nodes and pipes, and cost-effectiveness was considered. A graph is then generated from the dataset, having scenarios as nodes and edges weighted by the similarity between each pair of nodes (scenarios), in terms of pressure and flow variation due to the leak. Spectral clustering groups together similar scenarios in the eigen-space spanned by the most relevant eigen-vectors of the Laplacian matrix of the graph. This method uses superior traditional techniques. Finally, support vector machines classification learning is used to learn the relation between variations in pressure and flow at the deployed meters and the most probable set of pipes affected by the leak.

[1]  YounHun Kim.  Algebraic Connectivity of Graphs , with Applications , 2016 .

[2]  F. Archetti,et al.  A Graph based Analysis of Leak Localization in Urban Water Networks , 2014 .

[3]  Joby Boxall,et al.  Development and Field Validation of a Burst Localization Methodology , 2013 .

[4]  Zoran Kapelan,et al.  Geostatistical techniques for approximate location of pipe burst events in water distribution systems , 2013 .

[5]  Francesco Archetti,et al.  Improving leakage management in urban water distribution networks through data analytics and hydraulic simulation , 2013 .

[6]  Stewart Burn,et al.  LEAK DETECTION IN SIMULATED WATER PIPE NETWORKS USING SVM , 2012, Appl. Artif. Intell..

[7]  Wang Li-juan,et al.  A Leak Detection Method Based on EPANET and Genetic Algorithm in Water Distribution Systems , 2012, SOCO 2012.

[8]  Antonio Candelieri,et al.  Sectorization and analytical leaks localization in the H2OLEAK project: Clustering-based services for supporting water distribution networks management , 2012 .

[9]  Zoran Kapelan,et al.  REAL-TIME LEAK DETECTION IN WATER DISTRIBUTION SYSTEMS , 2011 .

[10]  Joby Boxall,et al.  FIELD VALIDATION OF 'OPTIMAL' INSTRUMENTATION METHODOLOGY FOR BURST/LEAK DETECTION AND LOCATION , 2011 .

[11]  Vicenç Puig,et al.  Methodology for leakage isolation using pressure sensitivity analysis in water distribution networks , 2011 .

[12]  Jiaqi Liu,et al.  A novel clustering method on time series data , 2011, Expert Syst. Appl..

[13]  Avi Ostfeld,et al.  Multi-objective optimization for conjunctive placement of hydraulic and water quality sensors in water distribution systems , 2011 .

[14]  Xia Li,et al.  Leak Detection of Municipal Water Supply Network Based on the Cluster-Analysis and Fuzzy Pattern Recognition , 2010, 2010 International Conference on E-Product E-Service and E-Entertainment.

[15]  Boon-Hee Soong,et al.  Framework of WSN based human centric cyber physical in-pipe water monitoring system , 2010, 2010 11th International Conference on Control Automation Robotics & Vision.

[16]  Joby Boxall,et al.  Field testing of an optimal sensor placement methodology for event detection in an urban water distribution network , 2010 .

[17]  Zoran Kapelan,et al.  A review of methods for leakage management in pipe networks , 2010 .

[18]  Zheng Yi Wu,et al.  Pressure-dependent leak detection model and its application to a district water system , 2010 .

[19]  Richard Mounce,et al.  Field testing of optimal sensor placement and data analysis methodologies for burst detection and location in an urban water network , 2010 .

[20]  Idel Montalvo,et al.  Division of Water Supply Systems into District Metered Areas Using a Multi-agent Based Approach , 2009, ICSOFT.

[21]  Kourosh Behzadian,et al.  Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks , 2009, Environ. Model. Softw..

[22]  C. Sivapragasam,et al.  ANN-based Model for Aiding Leak Detection in Water Distribution Networks , 2008 .

[23]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[24]  Satu Elisa Schaeffer,et al.  Graph Clustering , 2017, Encyclopedia of Machine Learning and Data Mining.

[25]  Jean-Michel Marin,et al.  Confidence bands for Brownian motion and applications to Monte Carlo simulation , 2007, Stat. Comput..

[26]  Malcolm Farley,et al.  Developing a Non-Revenue Water Reduction Strategy Part 1: Investigating and Assessing Water Losses , 2004 .

[27]  Costas Papadimitriou,et al.  Leakage detection in water pipe networks using a Bayesian probabilistic framework , 2003 .

[28]  Antonio Casimiro Caputo,et al.  Using neural networks to monitor piping systems , 2003 .

[29]  T. Jaakkola.  6.867 Machine Learning, Fall 2002 , 2002 .

[30]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[31]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[32]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[33]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[34]  Fan Chung,et al.  Spectral Graph Theory , 1996 .

[35]  Andrew B. Kahng,et al.  New spectral methods for ratio cut partitioning and clustering , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..