Pressure Sensor Placement for Leak Localization Using Simulated Annealing with Hyperparameter Optimization

Pressure sensor placement is critical to system safety and operation optimization of water supply networks (WSNs). The majority of existing studies focuses on sensitivity or burst identification ability of monitoring systems based on certain specific operating conditions of WSNs, while nodal connectivity or long-term hydraulic fluctuation is not fully considered and analyzed. A new method of pressure sensor placement is proposed in this paper based on Graph Neural Networks. The method mainly consists of two steps: monitoring partition establishment and sensor placement. (1) Structural Deep Clustering Network algorithm is used for clustering analysis with the integration of complicated topological and hydraulic characteristics, and a WSN is divided into several monitoring partitions. (2) Then, sensor placement is carried out based on burst identification analysis, a quantitative metric named “indicator tensor” is developed to calculate hydraulic characteristics in time series, and the node with the maximum average partition perception rate is selected as the sensor in each monitoring partition. The results showed that the proposed method achieved a better monitoring scheme with more balanced distribution of sensors and higher coverage rate for pipe burst detection. This paper offers a new robust framework, which can be easily applied in the decision-making process of monitoring system establishment.

Download Full-text

Compressed sensing based optimal sensor placement for leak localization in water distribution networks

Journal of Hydroinformatics ◽

10.2166/hydro.2017.145 ◽

2017 ◽

Vol 20 (6) ◽

pp. 1286-1295 ◽

Cited By ~ 4

Author(s):

Xiang Xie ◽

Quan Zhou ◽

Dibo Hou ◽

Hongjian Zhang

Keyword(s):

Compressed Sensing ◽

Knapsack Problem ◽

Water Distribution ◽

Sensor Placement ◽

Real Life ◽

Distribution Networks ◽

Water Distribution Networks ◽

Mutual Coherence ◽

Optimal Sensor Placement ◽

Leak Localization

Abstract The performance of model-based leak detection and localization techniques heavily depends on the configuration of a limited number of sensors. This paper presents a sensor placement optimization strategy that guarantees sufficient diagnosability while satisfying the budget constraint. Based on the theory of compressed sensing, the leak localization problem could be transformed into acquiring the sparse leak-induced demands from the available measurements, and the average mutual coherence is devised as a diagnosability criterion for evaluating whether the measurements contain enough information for identifying the potential leaks. The optimal sensor placement problem is then reformulated as a {0, 1} quadratic knapsack problem, seeking an optimal sensor placement scheme by minimizing the average mutual coherence to maximize the degree of diagnosability. To effectively handle the complicated real-life water distribution networks, a validated binary version of artificial bee colony algorithm enhanced by genetic operators, including crossover and swap, is introduced to solve the binary knapsack problem. The proposed strategy is illustrated and validated through a real-life water distribution network with synthetically generated field data.

Download Full-text