Novel leakage detection by ensemble CNN-SVM and graph-based localization in water distribution systems

Jiheon Kang, Youn Jong Park, Jaeho Lee, Soo Hyun Wang, Doo Seop Eom

Research output: Contribution to journalArticlepeer-review

157 Citations (Scopus)


In many water distribution systems, a significant amount of water is lost because of leakage during transit from the water treatment plant to consumers. As a result, water leakage detection and localization have been a consistent focus of research. Typically, diagnosis or detection systems based on sensor signals incur significant computational and time costs, whereas the system performance depends on the features selected as input to the classifier. In this paper, to solve this problem, we propose a novel, fast, and accurate water leakage detection system with an adaptive design that fuses a one-dimensional convolutional neural network and a support vector machine.We also propose a graph-based localization algorithm to determine the leakage location. An actual water pipeline network is represented by a graph network and it is assumed that leakage events occur at virtual points on the graph. The leakage location at which costs are minimized is estimated by comparing the actual measured signals with the virtually generated signals. The performance was validated on a wireless sensor network based test bed, deployed on an actual WDS. Our proposed methods achieved 99.3% leakage detection accuracy and a localization error of less than 3 m.

Original languageEnglish
Article number2764861
Pages (from-to)4279-4289
Number of pages11
JournalIEEE Transactions on Industrial Electronics
Issue number5
Publication statusPublished - 2018 May


  • Ensemble convolutional neural network (CNN) and support vector machine (SVM)
  • Leakage detection
  • One-dimensional (1-D) CNNS
  • Pipeline network localization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'Novel leakage detection by ensemble CNN-SVM and graph-based localization in water distribution systems'. Together they form a unique fingerprint.

Cite this