2016
DOI: 10.1061/(asce)wr.1943-5452.0000661
|View full text |Cite
|
Sign up to set email alerts
|

Leakage Zone Identification in Large-Scale Water Distribution Systems Using Multiclass Support Vector Machines

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
78
0
1

Year Published

2019
2019
2022
2022

Publication Types

Select...
6
4

Relationship

1
9

Authors

Journals

citations
Cited by 118 publications
(79 citation statements)
references
References 31 publications
0
78
0
1
Order By: Relevance
“…We test the proposed methodology in a medium-size water distribution system located in southern China, H Town [39], which owns one fixed-head reservoir, 898 demand nodes, and 1012 pipes. Under the peak hour demand scenario, a minimum service pressure of 24 m is required-more details can be referred to Table 2.…”
Section: Resultsmentioning
confidence: 99%
“…We test the proposed methodology in a medium-size water distribution system located in southern China, H Town [39], which owns one fixed-head reservoir, 898 demand nodes, and 1012 pipes. Under the peak hour demand scenario, a minimum service pressure of 24 m is required-more details can be referred to Table 2.…”
Section: Resultsmentioning
confidence: 99%
“…Izquierdo et al [14] assessed anomalies utilizing a hybrid model composed of a deterministic part (flow rates and head at the nodes) coupled with a state estimation technique and artificial neural networks (ANN). Zhang et al [15] used the K-means algorithm to classify the water network into several zones and then used support vector machine (SVM) to locate the zones containing the leakages. Another approach suggested by Fang et al [16] is a prediction of leakage events with a convolutional neural network (CNN) dependent on historical data.…”
Section: Introductionmentioning
confidence: 99%
“…These approaches can be further categorized into transient‐based methods, optimization‐based methods, and data‐driven methods. The transient‐based methods often analyze the transients induced by leaks using signal process techniques (e.g., Colombo et al, 2009; Wang et al, 2020); the optimization‐based methods typically define the leak detection as a demand calibration problem (e.g., Sanz et al, 2015; Sophocleous et al, 2019; Zhang et al, 2016); the data‐driven methods analyze the data from monitoring sites (e.g., pressure sensors and flow meters) to identify leaks (e.g., Romano et al, 2014; Zhou et al, 2019). While the model‐based approaches are efficient and cost‐effective in identifying leaks (Duan et al, 2011), they often exhibit equifinality and low‐reliability issues in practical applications, especially for highly looped and complex networks (Sophocleous et al, 2019).…”
Section: Introductionmentioning
confidence: 99%