Pattern matching and associative artificial neural networks for water distribution system time series data analysis

S. R. Mounce*, R. B. Mounce, T. Jackson, J. Austin, J. B. Boxall

*Corresponding author for this work

Research output: Contribution to journalArticle

18 Citations (Scopus)
4 Downloads (Pure)

Abstract

Water distribution systems, and other infrastructures, are increasingly being pervaded by sensing technologies, collecting a growing volume of data aimed at supporting operational and investment decisions. These sensors monitor system characteristics, i.e. flows, pressures and water quality, such as in pipes. This paper presents the application of pattern matching techniques and binary associative neural networks for novelty detection in such data. A protocol for applying pattern matching to automatically recognise specific waveforms in time series based on their shapes is described together with a system called Advanced Uncertain Reasoning Architecture (AURA) Alert for autonomous determination of novelty. AURA is a class of binary neural network that has a number of advantages over standard artificial neural network techniques for condition monitoring including a sound theoretical basis to determine the bounds of the system operation. Results from application to several case studies are provided including both hydraulic and water quality data. In the case of pattern matching, the results demonstrated some transferability of burst patterns across District Metered Areas; however limitations in performance and difficulties with assembling pattern libraries were found. Results for the AURA system demonstrate the potential for robust event detection across multiple parameters providing valuable information for diagnosis; one example also demonstrates the potential for detection of precursor information, vital for proactive management.

Original languageEnglish
Pages (from-to)617-632
Number of pages16
JournalJournal of Hydroinformatics
Volume16
Issue number3
Early online date8 Oct 2013
DOIs
Publication statusPublished - 1 Jan 2014

Fingerprint

Water distribution systems
Pattern matching
artificial neural network
Time series
time series
Neural networks
Water quality
water quality
Condition monitoring
pipe
Pipe
Hydraulics
infrastructure
Acoustic waves
sensor
hydraulics
Sensors
monitoring
data analysis
detection

Keywords

  • Asset monitoring
  • Auto-associative neural network
  • Event detection system
  • Pattern matching
  • Water distribution systems

ASJC Scopus subject areas

  • Atmospheric Science
  • Geotechnical Engineering and Engineering Geology

Cite this

Pattern matching and associative artificial neural networks for water distribution system time series data analysis. / Mounce, S. R.; Mounce, R. B.; Jackson, T.; Austin, J.; Boxall, J. B.

In: Journal of Hydroinformatics, Vol. 16, No. 3, 01.01.2014, p. 617-632.

Research output: Contribution to journalArticle

Mounce, S. R. ; Mounce, R. B. ; Jackson, T. ; Austin, J. ; Boxall, J. B. / Pattern matching and associative artificial neural networks for water distribution system time series data analysis. In: Journal of Hydroinformatics. 2014 ; Vol. 16, No. 3. pp. 617-632.
@article{975de59842e24134804d29952cf20ab1,
title = "Pattern matching and associative artificial neural networks for water distribution system time series data analysis",
abstract = "Water distribution systems, and other infrastructures, are increasingly being pervaded by sensing technologies, collecting a growing volume of data aimed at supporting operational and investment decisions. These sensors monitor system characteristics, i.e. flows, pressures and water quality, such as in pipes. This paper presents the application of pattern matching techniques and binary associative neural networks for novelty detection in such data. A protocol for applying pattern matching to automatically recognise specific waveforms in time series based on their shapes is described together with a system called Advanced Uncertain Reasoning Architecture (AURA) Alert for autonomous determination of novelty. AURA is a class of binary neural network that has a number of advantages over standard artificial neural network techniques for condition monitoring including a sound theoretical basis to determine the bounds of the system operation. Results from application to several case studies are provided including both hydraulic and water quality data. In the case of pattern matching, the results demonstrated some transferability of burst patterns across District Metered Areas; however limitations in performance and difficulties with assembling pattern libraries were found. Results for the AURA system demonstrate the potential for robust event detection across multiple parameters providing valuable information for diagnosis; one example also demonstrates the potential for detection of precursor information, vital for proactive management.",
keywords = "Asset monitoring, Auto-associative neural network, Event detection system, Pattern matching, Water distribution systems",
author = "Mounce, {S. R.} and Mounce, {R. B.} and T. Jackson and J. Austin and Boxall, {J. B.}",
year = "2014",
month = "1",
day = "1",
doi = "10.2166/hydro.2013.057",
language = "English",
volume = "16",
pages = "617--632",
journal = "Journal of Hydroinformatics",
issn = "1464-7141",
publisher = "IWA Publishing",
number = "3",

}

TY - JOUR

T1 - Pattern matching and associative artificial neural networks for water distribution system time series data analysis

AU - Mounce, S. R.

AU - Mounce, R. B.

AU - Jackson, T.

AU - Austin, J.

AU - Boxall, J. B.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Water distribution systems, and other infrastructures, are increasingly being pervaded by sensing technologies, collecting a growing volume of data aimed at supporting operational and investment decisions. These sensors monitor system characteristics, i.e. flows, pressures and water quality, such as in pipes. This paper presents the application of pattern matching techniques and binary associative neural networks for novelty detection in such data. A protocol for applying pattern matching to automatically recognise specific waveforms in time series based on their shapes is described together with a system called Advanced Uncertain Reasoning Architecture (AURA) Alert for autonomous determination of novelty. AURA is a class of binary neural network that has a number of advantages over standard artificial neural network techniques for condition monitoring including a sound theoretical basis to determine the bounds of the system operation. Results from application to several case studies are provided including both hydraulic and water quality data. In the case of pattern matching, the results demonstrated some transferability of burst patterns across District Metered Areas; however limitations in performance and difficulties with assembling pattern libraries were found. Results for the AURA system demonstrate the potential for robust event detection across multiple parameters providing valuable information for diagnosis; one example also demonstrates the potential for detection of precursor information, vital for proactive management.

AB - Water distribution systems, and other infrastructures, are increasingly being pervaded by sensing technologies, collecting a growing volume of data aimed at supporting operational and investment decisions. These sensors monitor system characteristics, i.e. flows, pressures and water quality, such as in pipes. This paper presents the application of pattern matching techniques and binary associative neural networks for novelty detection in such data. A protocol for applying pattern matching to automatically recognise specific waveforms in time series based on their shapes is described together with a system called Advanced Uncertain Reasoning Architecture (AURA) Alert for autonomous determination of novelty. AURA is a class of binary neural network that has a number of advantages over standard artificial neural network techniques for condition monitoring including a sound theoretical basis to determine the bounds of the system operation. Results from application to several case studies are provided including both hydraulic and water quality data. In the case of pattern matching, the results demonstrated some transferability of burst patterns across District Metered Areas; however limitations in performance and difficulties with assembling pattern libraries were found. Results for the AURA system demonstrate the potential for robust event detection across multiple parameters providing valuable information for diagnosis; one example also demonstrates the potential for detection of precursor information, vital for proactive management.

KW - Asset monitoring

KW - Auto-associative neural network

KW - Event detection system

KW - Pattern matching

KW - Water distribution systems

UR - http://www.scopus.com/inward/record.url?scp=84901028729&partnerID=8YFLogxK

U2 - 10.2166/hydro.2013.057

DO - 10.2166/hydro.2013.057

M3 - Article

VL - 16

SP - 617

EP - 632

JO - Journal of Hydroinformatics

JF - Journal of Hydroinformatics

SN - 1464-7141

IS - 3

ER -