Leakage localization in water distribution using data-driven models and sensitivity analysis

Tom Nørgaard Jensen, Vicenc Puig, Juli Romera, Carsten Skovmose Kallesøe, Rafal Wisniewski, Jan Dimon Bendtsen

Research output: Contribution to journalConference article in JournalResearchpeer-review

3 Citations (Scopus)

Abstract

Water scarcity is becoming an increasing problem worldwide, and an issue compounding the problem is water leakage in the piping networks delivering potable/consumable water to end-users (Sensus, 2012). In this paper, we consider the problem of isolating leakages in water supply networks using reduced network models. Using a reduced order model of the network, the expected behaviour of the network can be estimated and then compared with actual measurements obtained from the network. The result of this comparison is a set of residuals which are used to isolate a leakage to a network node. The localization is based on a sensitivity matrix which captures the residuals’ sensitivities to leakages. As the reduced order model is adaptive based on measurements from the network, the reduced order model is plug-and-play commissionable. The calculation of the sensitivity matrix is based on an EPANET model of the network and is performed off-line.

Original languageEnglish
Book seriesIFAC-PapersOnLine
Volume51
Issue number24
Pages (from-to)736-741
Number of pages6
ISSN2405-8963
DOIs
Publication statusPublished - 2018
Event10th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes - Warsaw, Poland
Duration: 29 Aug 201831 Aug 2018

Conference

Conference10th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes
CountryPoland
CityWarsaw
Period29/08/201831/08/2018

Fingerprint

Sensitivity analysis
Water
Water supply
Potable water

Keywords

  • Large-Scale Hydraulic Networks
  • Leakage Localization
  • Water Supply Systems

Cite this

@inproceedings{d3f24e25ed884491b677a67794306ccc,
title = "Leakage localization in water distribution using data-driven models and sensitivity analysis",
abstract = "Water scarcity is becoming an increasing problem worldwide, and an issue compounding the problem is water leakage in the piping networks delivering potable/consumable water to end-users (Sensus, 2012). In this paper, we consider the problem of isolating leakages in water supply networks using reduced network models. Using a reduced order model of the network, the expected behaviour of the network can be estimated and then compared with actual measurements obtained from the network. The result of this comparison is a set of residuals which are used to isolate a leakage to a network node. The localization is based on a sensitivity matrix which captures the residuals’ sensitivities to leakages. As the reduced order model is adaptive based on measurements from the network, the reduced order model is plug-and-play commissionable. The calculation of the sensitivity matrix is based on an EPANET model of the network and is performed off-line.",
keywords = "Large-Scale Hydraulic Networks, Leakage Localization, Water Supply Systems",
author = "Jensen, {Tom N{\o}rgaard} and Vicenc Puig and Juli Romera and Kalles{\o}e, {Carsten Skovmose} and Rafal Wisniewski and Bendtsen, {Jan Dimon}",
year = "2018",
doi = "10.1016/j.ifacol.2018.09.657",
language = "English",
volume = "51",
pages = "736--741",
journal = "I F A C Workshop Series",
issn = "1474-6670",
publisher = "Elsevier",
number = "24",

}

Leakage localization in water distribution using data-driven models and sensitivity analysis. / Jensen, Tom Nørgaard; Puig, Vicenc; Romera, Juli; Kallesøe, Carsten Skovmose; Wisniewski, Rafal; Bendtsen, Jan Dimon.

In: IFAC-PapersOnLine, Vol. 51, No. 24, 2018, p. 736-741.

Research output: Contribution to journalConference article in JournalResearchpeer-review

TY - GEN

T1 - Leakage localization in water distribution using data-driven models and sensitivity analysis

AU - Jensen, Tom Nørgaard

AU - Puig, Vicenc

AU - Romera, Juli

AU - Kallesøe, Carsten Skovmose

AU - Wisniewski, Rafal

AU - Bendtsen, Jan Dimon

PY - 2018

Y1 - 2018

N2 - Water scarcity is becoming an increasing problem worldwide, and an issue compounding the problem is water leakage in the piping networks delivering potable/consumable water to end-users (Sensus, 2012). In this paper, we consider the problem of isolating leakages in water supply networks using reduced network models. Using a reduced order model of the network, the expected behaviour of the network can be estimated and then compared with actual measurements obtained from the network. The result of this comparison is a set of residuals which are used to isolate a leakage to a network node. The localization is based on a sensitivity matrix which captures the residuals’ sensitivities to leakages. As the reduced order model is adaptive based on measurements from the network, the reduced order model is plug-and-play commissionable. The calculation of the sensitivity matrix is based on an EPANET model of the network and is performed off-line.

AB - Water scarcity is becoming an increasing problem worldwide, and an issue compounding the problem is water leakage in the piping networks delivering potable/consumable water to end-users (Sensus, 2012). In this paper, we consider the problem of isolating leakages in water supply networks using reduced network models. Using a reduced order model of the network, the expected behaviour of the network can be estimated and then compared with actual measurements obtained from the network. The result of this comparison is a set of residuals which are used to isolate a leakage to a network node. The localization is based on a sensitivity matrix which captures the residuals’ sensitivities to leakages. As the reduced order model is adaptive based on measurements from the network, the reduced order model is plug-and-play commissionable. The calculation of the sensitivity matrix is based on an EPANET model of the network and is performed off-line.

KW - Large-Scale Hydraulic Networks

KW - Leakage Localization

KW - Water Supply Systems

UR - http://www.scopus.com/inward/record.url?scp=85054583142&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2018.09.657

DO - 10.1016/j.ifacol.2018.09.657

M3 - Conference article in Journal

VL - 51

SP - 736

EP - 741

JO - I F A C Workshop Series

JF - I F A C Workshop Series

SN - 1474-6670

IS - 24

ER -