Abstract
In the present paper, a Random Forest classifier is used to detect leak locations on two different sized water distribution networks with sparse sensor placement. A great number of leak scenarios were simulated with Monte Carlo determined leak parameters (leak location and emitter coefficient). In order to account for demand variations that occur on a daily basis and to obtain a larger dataset, scenarios were simulated with random base demand increments or reductions for each network node. Classifier accuracy was assessed for different sensor layouts and numbers of sensors. Multiple prediction models were constructed for differently sized leakage and demand range variations in order to investigate model accuracy under various conditions. Results indicate that the prediction model provides the greatest accuracy for the largest leaks, with the smallest variation in base demand (62% accuracy for greater- and 82% for smaller-sized networks, for the largest considered leak size and a base demand variation of ±2.5%). However, even for small leaks and the greatest base demand variations, the prediction model provided considerable accuracy, especially when localizing the sources of leaks when the true leak node and neighbor nodes were considered (for a smaller-sized network and a base demand of variation ±20% the model accuracy increased from 44% to 89% when top five nodes with greatest probability were considered, and for a greater-sized network with a base demand variation of ±10% the accuracy increased from 36% to 77%).
Highlights
Leakages in water distribution networks can cause great cumulative losses as small leakages can remain undetected for long periods of time
It can be observed that for the same base demand variation and same emitter coefficient range, the model accuracy for the Net3 network decreased by roughly 20% when compared to the Hanoi network
It is evident that the approach that considers the top three and five network nodes significantly increased model accuracy, which would make it possible to successfully localize leak location even in large networks
Summary
Leakages in water distribution networks can cause great cumulative losses as small leakages can remain undetected for long periods of time. Direct losses are typically followed by the overall reduction of the functionality of the water distribution network, which usually manifests as a pressure drop on the user end. Leakages can potentially cause health hazards since microbiological contamination can enter the water distribution network and reach end users. In a recent study by Nkemeni et al [2], a wireless sensor network application was investigated, where processing for leak detection is performed at the sensor nodes. In the work of Rajeswaran et al [4], a multi-stage graph partitioning algorithm was presented, which uses flow measurements to indicate a minimum number of additional measuring locations needed to narrow down leak location in large-size networks. In a work by Bohorquez et al [6], an artificial neural network was applied to detect leak size and location in a single water pipeline
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.
