Optimal sensor placement for leak localization in water distribution networks based on a novel semi-supervised strategy

Li, Juan; Wang, Cong; Qian, Zhihong; Lu, Changgang

doi:10.1016/j.jprocont.2019.08.001

Cited by 21 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concentration of sensors in the lowest pressure zone of this network can be observed. This zone is also the one identified as the most sensitive by Equation (1). The use of the conditional entropy provides a more widespread distribution of sensors (see Figure 6).…”

Section: Case Studymentioning

confidence: 92%

See 1 more Smart Citation

Optimal Placement of Pressure Sensors Using Fuzzy DEMATEL-Based Sensor Influence

Francés-Chust

Brentan

Carpitella

et al. 2020

Water

View full text Add to dashboard Cite

Nowadays, optimal sensor placement (OSP) for leakage detection in water distribution networks is a lively field of research, and a challenge for water utilities in terms of network control, management, and maintenance. How many sensors to install and where to install them are crucial decisions to make for those utilities to reach a trade-off between efficiency and economy. In this paper, we address the where-to-install-them part of the OSP through the following elements: nodes’ sensitivity to leakage, uncertainty of information, and redundancy through conditional entropy maximisation. We evaluate relationships among candidate sensors in a network to get a picture of the mutual influence among the nodes. This analysis is performed within a multi-criteria decision-making approach: specifically, a herein proposed variant of DEMATEL, which uses fuzzy logic and builds comparison matrices derived from information obtained through leakage simulations of the network. We apply the proposal first to a toy example to show how the approach works, and then to a real-world case study.

show abstract

Section: Case Studymentioning

confidence: 92%

“…Optimal sensor placement (OSP) for leakage detection in water distribution networks (WDNs) currently represents an exciting and lively field of research, aimed at optimising processes of network control, management, and maintenance [1].…”

Section: Introduction and Literature Reviewmentioning

confidence: 99%

Optimal Placement of Pressure Sensors Using Fuzzy DEMATEL-Based Sensor Influence

Francés-Chust

Brentan

Carpitella

et al. 2020

Water

View full text Add to dashboard Cite

show abstract

“…Figure 4a shows the volume of water flow in the five zones of the water supply network. The minimum daily flow volume usually occurred between 1:00 a.m. and 6:00 a.m. Li et al 21 set the lowest hourly coefficients of nodal demands in EPANET from 5:00 a.m. to 6:00 a.m. and 6:00 p.m. to 8:00 p.m. The instantaneous minimum flow in zone 1 was 0.004 m 3 /min at 5:32 a.m., that in zone 2 was 0.085 m 3 /min (including water from zone 1) at 5:22 a.m., that in zone 3 was 0.158 m 3 /min (including water from zones 1 and 2) at 4:42 a.m., that in zone 4 was 0.594 m 3 /min (including water from zones 1, 2, and 3) at 2:16 a.m., and that in zone 5 was 0.785 m 3 /min (including water from zones 1, 2, 3, and 4) at 3:59 a.m. (Figure 4b).…”

Section: Resultsmentioning

confidence: 99%

In‐situ leakage diagnosis of urban water supply network by fire hydrants and EPANET simulation

Chen

2023

Env Prog and Sustain Energy

View full text Add to dashboard Cite

A method of in‐situ leakage diagnosis of a water supply network using fire hydrant water flow measurements and simulation by EPANET software was established. A network with 1032 m of water distribution pipes and 350 user‐side water meters in Taipei was separated into five zones. The lowest volume of daily water flow occurred between 1:00 a.m. and 6:00 a.m., with values ranging from 0.004 to 0.785 m3/min; these data can be regarded as a minimum value of water leakage in the network at midnight. The volume of water leakage was strongly correlated with observed pressure transients, enabling the measurement of the water leakage in the network, which ranged from 5.76 to 628 m3/d. The total water leakage simulated by EPANET was 1.48 m3/d in the network. Although this value deviated by 23% from the District Metered Area (DMA) results, both EPANET and DMA tools confirmed that zones 4 and 5 had severe water leakage problems. Simplifying valves and combining neighboring pipes of the same diameter during the EPANET simulation was efficiently tackle water leakage. EPANET allows for quick diagnosis of the water leakage areas, whereas the DMA tool allows for precise measurements of water volume and pressure. The costs of in‐situ diagnosis and EPANET simulation include instruments, labor, and time, and are estimated to be lower than those of the DMA tool. Furthermore, the methodology of this study can reduce the risks of underground working disasters.

show abstract

“…There are four pressure sensors and they are marked with red dots in the Fig. 9 (Li Et al.,2019). Each pipe in the network was analyzed, for the pipe section with poor positioning accuracy, they are marked with blue in Fig .…”

Section: Case2mentioning

confidence: 99%

An Accurate Leakage Localization Method for Water Supply Network Based on Deep Learning Network

Wang

2022

Water Resour Manage

Self Cite

View full text Add to dashboard Cite

In the water supply network, leakage of pipes will cause water loss and increase the risk of environmental pollution. For water supply systems, identifying the leak point can improve the efficiency of pipeline leak repair. Most existing leak location methods can only locate the leak point approximately to the node or pipe section of the pipe network, but cannot locate the specific location of the pipe section. This paper presents a framework for accurate location of water supply network leakage based on ResNet. The framework is to pinpoint leaks to specific locations along the pipeline. The leakage of two kinds of pipe networks is simulated.For a pipe network containing 40 pipes, the positioning accuracy of the pipe section is 0.94, and the MSE of the specific location of the leakage point is 0.000435. For the pipe network containing 117 pipes, the positioning accuracy of the pipe section is 0.91, and the MSE of the specific location of the leakage point is 0.0009177, and the leak location ability under different sensor arrangements is analyzed. Experiments verify the robustness and applicability of the framework.

show abstract

Optimal sensor placement for leak localization in water distribution networks based on a novel semi-supervised strategy

Cited by 21 publications

References 23 publications

Optimal Placement of Pressure Sensors Using Fuzzy DEMATEL-Based Sensor Influence

Optimal Placement of Pressure Sensors Using Fuzzy DEMATEL-Based Sensor Influence

In‐situ leakage diagnosis of urban water supply network by fire hydrants and EPANET simulation

An Accurate Leakage Localization Method for Water Supply Network Based on Deep Learning Network

Contact Info

Product

Resources

About