Abstract
In this paper, a sensor placement approach to improve the leak location in waterdistribution networks is proposed when the leak signature space (LSS) method is used.The sensor placement problem is formulated as an integer optimization problem where thecriterion to be minimized is the number of overlapping signature domains computed fromthe original LSS representation. First, a semi-exhaustive search approach based on a lazyevaluation mechanism ensures optimal placement in the case of low complexity scenarios.For more complex cases, a stochastic optimization process is proposed, based on eitherthe genetic algorithms (GAs) or particle swarm optimization (PSO). Experiments on twodifferent networks are used to evaluate the performance of the resolution methods, as well asthe efficiency achieved in the leak location when using the sensor placement results.
Highlights
As reported by the International Water Association (IWA), water loss reduction with the sustainability of the source and supply and the cost effectiveness of system operations has emerged as a world-wide issue [1]
Major advances have been made during the last few years, most of them regarding methods based on transient states; [5,6] offer a review of transient-based leak detection methods that summarizes current and past contributions, serving as a basis for the development of new techniques
The second case study is based on the water distribution networks (WDNs) of Limassol in Cyprus proposed as a test case in the EFFINET European project [37]
Summary
As reported by the International Water Association (IWA), water loss reduction with the sustainability of the source and supply and the cost effectiveness of system operations has emerged as a world-wide issue [1]. This method has recently been applied to a real fault scenario [9], and an improvement of this approach has been developed [10,11], where an extended time horizon analysis of pressure measurements is considered and a comparison between different performance metrics is achieved Despite these first results, the performance obtained until now is still far from allowing the detection of WDN leaks with only a few sensors in a robust and fast way. The development of a sensor placement strategy has been an extensive subject of research in the general context of model-based fault detection and isolation (FDI) [12], where the approach may depend on the type of isolability criteria [13,14] These methods do not apply directly to the case of water distribution networks because of the non-explicit non-linear nature of their model.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
