A Hybrid Leakage Detection and Isolation Approach Based on Ensemble Multivariate Changepoint Detection Methods

Tuoyua Cheng, Yuanzhe Li, Fouzi Harrou, Ying Sun, Jinliang Gao, TorOve Leiknes

    Research output: Contribution to journalArticlepeer-review

    Abstract

    Early leakage detection and isolation are of paramount importance to the maintenance and resilience of the water distribution system (WDS). Efficient and accurate leakage detection and isolation algorithms could support practitioners to optimize WDS design and operation. Modern WDS, as equipped with supervisory control and data acquisition (SCADA), could record nodal measurements to facilitate training, validation, and selection of both mechanism-based and data-driven models. In this study for the battle of the leakage detection and isolation methods, a hybrid approach based on benchmark simulation and the ensemble multivariate changepoint detection (EMCPD) is proposed to detect leakage occurrences. Bilinear bivariate spatial interpolation for irregular spaced data and two-sample one-sided Student’s t-test is further invocated to isolate leakage sites.
    Original languageEnglish (US)
    Journalhttps://zenodo.org/communities/battledim2020/
    StatePublished - Jun 2 2020

    Fingerprint Dive into the research topics of 'A Hybrid Leakage Detection and Isolation Approach Based on Ensemble Multivariate Changepoint Detection Methods'. Together they form a unique fingerprint.

    Cite this