Leak Localization In Water Distribution Networks Using Pressure Models And Classifiers

This chapter proposes an architecture and an associate methodology for leak localization in Water Distribution Networks (WDN) that are based on pressure models and classifiers. In a first stage of the proposed architecture, residuals are obtained by comparing available pressure measurements with the estimations provided by a WDN model. In a second stage, a classifier is applied to the residuals with the aim of determining the leak location. The classifier is trained with data generated by simulation of the WDN under different leak scenarios and uncertainty conditions. Several classification approaches are considered and compared. The proposed methodology is tested both using synthetic and experimental data with real WDNs of different sizes. The comparison with the current approaches shows a performance improvement.