An Advanced Sensor Placement Strategy for Small Leaks Quantification Using Lean Graphs

Abstract

Small leaks in water distribution networks have been a major problem both economically and environmentally, as they go undetected for years. We model the signature of small leaks as a unique Directed Acyclic Graph, called the Lean Graph, to find the best places for k sensors for detecting and locating small leaks. We use the sensors to develop dictionaries that map each leak signature to its location. We quantify leaks by matching out-of-normal flows detected by sensors against records in the selected dictionaries. The most similar records of the dictionaries are used to quantify the leaks. Finally, we investigate how much our approach can tolerate corrupted data due to sensor failures by introducing a subspace voting based quantification method. We tested our method on water distribution networks of literature and simulate small leaks ranging from [0.1, 1.0] liter per second. Our experimental results prove that our sensor placement strategy can effectively place k sensors to quantify single and multiple small leaks and can tolerate corrupted data up to some range while maintaining the performance of leak quantification. These outcomes indicate that our approach could be applied in real water distribution networks to minimize the loss caused by small leaks.

GA-Sense: Sensor placement strategy for detecting leaks in water distribution networks based on time series flow and genetic algorithm

“…We evaluated the effectiveness of our proposed GA-Sense method against two other methodologies: leak detection using artificial neural networks (ANNs) [28] , and leak detection utilizing the lean graph approach [ 7 , 26 ]. We considered a specific experimental scenario ( Table 7 ) to provide an in-depth evaluation of the accuracy of GA-Sense in comparison to these widely used techniques.…”

“…Traditional approaches often rely on data from one-time leakage scenarios, and neglect the importance of time series data, which are important in identifying the most effective locations for sensor placement under various conditions. One method of optimizing sensor placement involves the use of a genetic algorithm [2] , [3] , [4] , [5] , [6] , while some researchers [7] have employed the lean graph method for the detection of pipe leaks.…”

State‐of‐the‐art review of leak diagnostic experiments: Toward a smart water network

“…The study views sensor placement position as a stochastic problem and calculates an optimization function through entropy loss for the relative position of two sensors for finding the leak location. Shiddiqi et al (2020) used the lean graphs approach for solving the sensor placement problem for localizing small leaks. They characterized small leaks to have a 0.1–1 L/min flow rate and used the clustering approach to plot the district metering network (DMA).…”