Detecting pipe bursts using Heuristic and CUSUM methods

M. Bakker; D. Jung; J. Vreeburg; M. Van De Roer; K. Lansey; L. Rietveld

doi:10.1016/j.proeng.2014.02.011

Detecting pipe bursts using Heuristic and CUSUM methods

M. Bakker, D. Jung, J. Vreeburg, M. Van De Roer, K. Lansey, L. Rietveld

Research output: Contribution to journal › Conference article › peer-review

12 Citations (Scopus)

Abstract

Pipe bursts in a drinking water distribution system lead to water losses, interruption of supply, and damage to streets and houses due to the uncontrolled water flow. To minimize the negative consequences of pipe bursts, an early detection is necessary. This paper describes a heuristic burst detection method, which continuously compares forecasted and measured values of the water demand. The forecasts of the water demand were generated by an adaptive water demand forecasting model. To test the method, a dataset of five years of water demand data in a supply area in the Western part of the Netherlands was collected. The method was tested on a subset of the data (only the winter months) in which 9 (larger) burst events were reported. The detection probability for the reported bursts was 44.4%, at an acceptable rate of false alarms of 5.0%. The results were compared with the CUSUM method, which is a general statistical process control (SPC) method to identify anomalies in time series. The heuristic and CUSUM methods generated comparable results, although rate of false alarm for the heuristic method was lower at the same detection probability.

Original language	English
Pages (from-to)	85-92
Number of pages	8
Journal	Procedia Engineering
Volume	70
DOIs	https://doi.org/10.1016/j.proeng.2014.02.011
Publication status	Published - 2014
Externally published	Yes
Event	12th International Conference on Computing and Control for the Water Industry, CCWI 2013 - Perugia, Italy Duration: 2013 Sept 2 → 2013 Sept 4

Bibliographical note

Funding Information:
This study was carried out in the DisConTO project (Distribution Control Training & Operation). The project is a cooperation between 4 water supply companies (Vitens, Dunea, PWN and Brabant Water), Delft University of Technology, The National Institute for Public Health and the Environment (RIVM), Royal HaskoningDHV Consultancy and Engineering and UReason. The project is financially supported by the Dutch government through the “Innowator” program.

Keywords

Demand forecasting
Pipe burst detection
SPC methods

ASJC Scopus subject areas

General Engineering

Access to Document

10.1016/j.proeng.2014.02.011

Cite this

@article{52a81bbfae00468dbb954eefada4faa6,

title = "Detecting pipe bursts using Heuristic and CUSUM methods",

abstract = "Pipe bursts in a drinking water distribution system lead to water losses, interruption of supply, and damage to streets and houses due to the uncontrolled water flow. To minimize the negative consequences of pipe bursts, an early detection is necessary. This paper describes a heuristic burst detection method, which continuously compares forecasted and measured values of the water demand. The forecasts of the water demand were generated by an adaptive water demand forecasting model. To test the method, a dataset of five years of water demand data in a supply area in the Western part of the Netherlands was collected. The method was tested on a subset of the data (only the winter months) in which 9 (larger) burst events were reported. The detection probability for the reported bursts was 44.4%, at an acceptable rate of false alarms of 5.0%. The results were compared with the CUSUM method, which is a general statistical process control (SPC) method to identify anomalies in time series. The heuristic and CUSUM methods generated comparable results, although rate of false alarm for the heuristic method was lower at the same detection probability.",

keywords = "Demand forecasting, Pipe burst detection, SPC methods",

author = "M. Bakker and D. Jung and J. Vreeburg and {Van De Roer}, M. and K. Lansey and L. Rietveld",

note = "Funding Information: This study was carried out in the DisConTO project (Distribution Control Training & Operation). The project is a cooperation between 4 water supply companies (Vitens, Dunea, PWN and Brabant Water), Delft University of Technology, The National Institute for Public Health and the Environment (RIVM), Royal HaskoningDHV Consultancy and Engineering and UReason. The project is financially supported by the Dutch government through the “Innowator” program.; 12th International Conference on Computing and Control for the Water Industry, CCWI 2013 ; Conference date: 02-09-2013 Through 04-09-2013",

year = "2014",

doi = "10.1016/j.proeng.2014.02.011",

language = "English",

volume = "70",

pages = "85--92",

journal = "Procedia Engineering",

issn = "1877-7058",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Detecting pipe bursts using Heuristic and CUSUM methods

AU - Bakker, M.

AU - Jung, D.

AU - Vreeburg, J.

AU - Van De Roer, M.

AU - Lansey, K.

AU - Rietveld, L.

N1 - Funding Information: This study was carried out in the DisConTO project (Distribution Control Training & Operation). The project is a cooperation between 4 water supply companies (Vitens, Dunea, PWN and Brabant Water), Delft University of Technology, The National Institute for Public Health and the Environment (RIVM), Royal HaskoningDHV Consultancy and Engineering and UReason. The project is financially supported by the Dutch government through the “Innowator” program.

PY - 2014

Y1 - 2014

N2 - Pipe bursts in a drinking water distribution system lead to water losses, interruption of supply, and damage to streets and houses due to the uncontrolled water flow. To minimize the negative consequences of pipe bursts, an early detection is necessary. This paper describes a heuristic burst detection method, which continuously compares forecasted and measured values of the water demand. The forecasts of the water demand were generated by an adaptive water demand forecasting model. To test the method, a dataset of five years of water demand data in a supply area in the Western part of the Netherlands was collected. The method was tested on a subset of the data (only the winter months) in which 9 (larger) burst events were reported. The detection probability for the reported bursts was 44.4%, at an acceptable rate of false alarms of 5.0%. The results were compared with the CUSUM method, which is a general statistical process control (SPC) method to identify anomalies in time series. The heuristic and CUSUM methods generated comparable results, although rate of false alarm for the heuristic method was lower at the same detection probability.

AB - Pipe bursts in a drinking water distribution system lead to water losses, interruption of supply, and damage to streets and houses due to the uncontrolled water flow. To minimize the negative consequences of pipe bursts, an early detection is necessary. This paper describes a heuristic burst detection method, which continuously compares forecasted and measured values of the water demand. The forecasts of the water demand were generated by an adaptive water demand forecasting model. To test the method, a dataset of five years of water demand data in a supply area in the Western part of the Netherlands was collected. The method was tested on a subset of the data (only the winter months) in which 9 (larger) burst events were reported. The detection probability for the reported bursts was 44.4%, at an acceptable rate of false alarms of 5.0%. The results were compared with the CUSUM method, which is a general statistical process control (SPC) method to identify anomalies in time series. The heuristic and CUSUM methods generated comparable results, although rate of false alarm for the heuristic method was lower at the same detection probability.

KW - Demand forecasting

KW - Pipe burst detection

KW - SPC methods

UR - http://www.scopus.com/inward/record.url?scp=84899690011&partnerID=8YFLogxK

U2 - 10.1016/j.proeng.2014.02.011

DO - 10.1016/j.proeng.2014.02.011

M3 - Conference article

AN - SCOPUS:84899690011

SN - 1877-7058

VL - 70

SP - 85

EP - 92

JO - Procedia Engineering

JF - Procedia Engineering

T2 - 12th International Conference on Computing and Control for the Water Industry, CCWI 2013

Y2 - 2 September 2013 through 4 September 2013

ER -

Detecting pipe bursts using Heuristic and CUSUM methods

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this