Detecting pipe bursts using Heuristic and CUSUM methods

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 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 languageEnglish (US)
Title of host publicationProcedia Engineering
PublisherElsevier Ltd
Pages85-92
Number of pages8
Volume70
DOIs
StatePublished - 2014
Event12th International Conference on Computing and Control for the Water Industry, CCWI 2013 - Perugia, Italy
Duration: Sep 2 2013Sep 4 2013

Other

Other12th International Conference on Computing and Control for the Water Industry, CCWI 2013
CountryItaly
CityPerugia
Period9/2/139/4/13

Fingerprint

Pipe
Water
Water distribution systems
Statistical process control
Heuristic methods
Potable water
Time series

Keywords

  • Demand forecasting
  • Pipe burst detection
  • SPC methods

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Bakker, M., Jung, D., Vreeburg, J., Van De Roer, M., Lansey, K. E., & Rietveld, L. (2014). Detecting pipe bursts using Heuristic and CUSUM methods. In Procedia Engineering (Vol. 70, pp. 85-92). Elsevier Ltd. https://doi.org/10.1016/j.proeng.2014.02.011

Detecting pipe bursts using Heuristic and CUSUM methods. / Bakker, M.; Jung, D.; Vreeburg, J.; Van De Roer, M.; Lansey, Kevin E; Rietveld, L.

Procedia Engineering. Vol. 70 Elsevier Ltd, 2014. p. 85-92.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bakker, M, Jung, D, Vreeburg, J, Van De Roer, M, Lansey, KE & Rietveld, L 2014, Detecting pipe bursts using Heuristic and CUSUM methods. in Procedia Engineering. vol. 70, Elsevier Ltd, pp. 85-92, 12th International Conference on Computing and Control for the Water Industry, CCWI 2013, Perugia, Italy, 9/2/13. https://doi.org/10.1016/j.proeng.2014.02.011
Bakker M, Jung D, Vreeburg J, Van De Roer M, Lansey KE, Rietveld L. Detecting pipe bursts using Heuristic and CUSUM methods. In Procedia Engineering. Vol. 70. Elsevier Ltd. 2014. p. 85-92 https://doi.org/10.1016/j.proeng.2014.02.011
Bakker, M. ; Jung, D. ; Vreeburg, J. ; Van De Roer, M. ; Lansey, Kevin E ; Rietveld, L. / Detecting pipe bursts using Heuristic and CUSUM methods. Procedia Engineering. Vol. 70 Elsevier Ltd, 2014. pp. 85-92
@inproceedings{0b58a9f6abbf4610b0c3fc89aaf36e34,
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 Lansey, {Kevin E} and L. Rietveld",
year = "2014",
doi = "10.1016/j.proeng.2014.02.011",
language = "English (US)",
volume = "70",
pages = "85--92",
booktitle = "Procedia Engineering",
publisher = "Elsevier Ltd",

}

TY - GEN

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, Kevin E

AU - Rietveld, L.

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

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

U2 - 10.1016/j.proeng.2014.02.011

DO - 10.1016/j.proeng.2014.02.011

M3 - Conference contribution

VL - 70

SP - 85

EP - 92

BT - Procedia Engineering

PB - Elsevier Ltd

ER -