Development of a clustering-based model for enhancing acoustic leak detection

Samer El-Zahab, Ahmed Asaad, Eslam Mohammed Abdelkader, Tarek Zayed

Research output: Journal article publicationJournal articleAcademic researchpeer-review

1 Citation (Scopus)

Abstract

According to the Canadian Infrastructure Report of 2016, Canada’s water and wastewater infrastructures are in a declining state. One of the problems plaguing water systems is leakage. Leaks are costly as they create losses in precious water resources as well as treatment chemicals and energy required to produce drinking water. Therefore, the city of Montréal has implemented a pilot project to detect the leaks in a portion of its water supply network using noise loggers. The main shortcoming tackled is the inaccuracy of the current system as it can regularly present false rulings on new events. This article presents a novel approach for the analysis of the signals using k-means clustering and provides a set of models for leak detection. The developed model was tested against real-life conditions and detected two possible leaks that were undetected by the current system in addition to its ability to detect all confirmed leak conditions.

Original languageEnglish
Pages (from-to)278-286
Number of pages9
JournalCanadian Journal of Civil Engineering
Volume46
Issue number6
DOIs
Publication statusPublished - Apr 2019

Keywords

  • Automated leak detection
  • Infrastructure systems
  • Leaks
  • Noise loggers
  • Water networks

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Environmental Science(all)

Cite this