Leak Localization Method for Water-Distribution Networks Using a Data-Driven Model and Dempster–Shafer Reasoning

This article presents a new data-driven method for leak localization in water-distribution networks (WDNs). The uses the information provided by set of pressure sensors installed some internal network nodes addition to flow and measurements from inlet nodes. Pressure are recorded under leak-free operation, WDN model at each sensed node is adjusted. estimation this complemented Kriging spatial interpolation technique estimate that not sensed, leading reference map. Leak based on comparison map with current obtained applying directly sensors. key element use Dempster-Shafer theory reasoning uncertainty. successful application proposed methodology two real-data case studies presented.