Leak localization in water distribution networks using GIS-Enhanced autoencoders

被引:1
作者
Weyns, Michael [1 ]
Mazaev, Ganjour [1 ]
Vaes, Guido [2 ]
Vancoillie, Filip [3 ]
De Turck, Filip [1 ]
Van Hoecke, Sofie [1 ]
Ongenae, Femke [1 ]
机构
[1] Ghent Univ imec, IDLab, Ghent, Belgium
[2] Hydroscan, Modelling & Res, Leuven, Belgium
[3] De Watergroep, Brussels, Belgium
关键词
Leak localization; water distribution networks; machine learning; autoencoders; geographical information systems; SYSTEMS;
D O I
10.1080/1573062X.2023.2216191
中图分类号
TV21 [水资源调查与水利规划];
学科分类号
081501 ;
摘要
Water loss due to persistent leakages in water distribution networks remains a substantive problem around the world, all the more so given noticeable trends of increasing global water scarcities. In this paper, we present a data-driven leak localization approach leveraging a connected Geographical Information System together with an autoencoder to perform anomaly detection on time-variable sensor data. Data-driven approaches are able to circumvent many of the uncertainty issues associated with model-based approaches, but they usually require significant amounts of high-quality data, reflecting many different leak scenarios, to perform well. Our approach obviates this requirement by relying only on leakless data during model training. We examine the efficacy of this approach on 19 realistic leak experiments conducted in the field. Based on these evaluations, we were able to achieve average search costs as low as 2.2 kilometers, for a total network length of 215 kilometers.
引用
收藏
页码:859 / 881
页数:23
相关论文
共 50 条
[41]   Application of fiber optics in water distribution networks for leak detection and localization: a mixed methodology-based review [J].
Ibrahim, Kabir ;
Tariq, Salman ;
Bakhtawar, Beenish ;
Zayed, Tarek .
H2OPEN JOURNAL, 2021, 4 (01) :244-261
[42]   Wasserstein-Enabled Leaks Localization in Water Distribution Networks [J].
Ponti, Andrea ;
Giordani, Ilaria ;
Candelieri, Antonio ;
Archetti, Francesco .
WATER, 2024, 16 (03)
[43]   Use of Machine Learning for Leak Detection and Localization in Water Distribution Systems [J].
Mashhadi, Neda ;
Shahrour, Isam ;
Attoue, Nivine ;
El Khattabi, Jamal ;
Aljer, Ammar .
SMART CITIES, 2021, 4 (04) :1293-1315
[44]   Water distribution network calibration for unreported leak localization with consideration of uncertainties [J].
Moasheri, R. ;
Ghazizadeh, M. Jalili ;
Kohanali, R. Ahmadi .
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY, 2025, 22 (01) :399-418
[45]   A graph partitioning algorithm for leak detection in water distribution networks [J].
Rajeswaran, Aravind ;
Narasimhan, Sridharakumar ;
Narasimhan, Shankar .
COMPUTERS & CHEMICAL ENGINEERING, 2018, 108 :11-23
[46]   Performance optimization of a leak detection scheme for water distribution networks [J].
Przystalka, Piotr .
IFAC PAPERSONLINE, 2018, 51 (24) :914-921
[47]   AN UNSUPERVISED APPROACH TO LEAK DETECTION AND LOCATION IN WATER DISTRIBUTION NETWORKS [J].
Quinones-Grueiro, Marcos ;
Verde, Cristina ;
Prieto-Moreno, Alberto ;
Llanes-Santiago, Orestes .
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2018, 28 (02) :283-295
[48]   The performance of encoder–decoder neural networks for leak detection in water distribution networks [J].
Doss, Prasanna Mohan ;
Rokstad, Marius Møller ;
Tscheikner-Gratl, Franz .
Water Supply, 2024, 24 (08) :2750-2764
[49]   Leak detection in real water distribution networks based on acoustic emission and machine learning [J].
Fares, Ali ;
Tijani, I. A. ;
Rui, Zhang ;
Zayed, Tarek .
ENVIRONMENTAL TECHNOLOGY, 2023, 44 (25) :3850-3866
[50]   Leak detection and localization in water distribution systems using advanced feature analysis and an Artificial Neural Network [J].
Mahdi, Nibras M. ;
Jassim, Ahmed Hikmet ;
Abulqasim, Shahlla Abbas ;
Basem, Ali ;
Ogaili, Ahmed Ali Farhan ;
Al-Haddad, Luttfi A. .
DESALINATION AND WATER TREATMENT, 2024, 320