A water supply network leakage detection method based on space-time multi-element fusion perception

By dividing the water supply network into independent metering areas and utilizing IoT flow meters and similarity analysis, the problem of low accuracy in water supply network leakage detection in existing technologies has been solved, achieving high-precision leakage detection and efficient water resource management.

CN114662035BActive Publication Date: 2026-07-17HANGZHOU LAISON TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HANGZHOU LAISON TECH CO LTD
Filing Date
2022-02-25
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing water supply network leakage detection methods based on a single time point and a single detection area have low accuracy and are easily affected by complex fluctuations, making it difficult to achieve high-precision leakage identification.

Method used

By dividing the water supply network into multiple independent metering areas, using IoT flow meters to acquire flow data in real time, calculating flow change vectors and vector projections, and combining similarity analysis to achieve spatiotemporal fusion perception across multiple time periods and regions, a similarity threshold is set to determine leakage areas.

Benefits of technology

It enables high-precision and rapid detection of water supply network leakage, reduces the overall leakage rate of the network, and improves the efficiency of water resource transportation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114662035B_ABST
    Figure CN114662035B_ABST
Patent Text Reader

Abstract

A method for detecting leakage in water supply networks based on spatiotemporal multi-dimensional fusion sensing is proposed. For the water supply network to be detected, it is divided into N independent metering areas. An IoT flow meter is used to acquire and record the flow rate of each area in real time within a set time period. T is set as the number of reference detection periods, and the flow rate information clusters of all independent metering areas at the current time t are recorded. The flow rate change vector of independent metering area n in the current time period is calculated. Similarly, the flow rate change vectors of the K independent metering areas adjacent to area n are calculated as D. n The reference vector is used to calculate D. n Vector projection onto the reference vector; calculation of the flow change vector D for the current time period in the independent metering area n. n The invention compares the overall similarity of reference vectors; for independent metering areas n in time period t, the overall similarity of regional flow indicates that the water use in the area is normal, while a negative similarity indicates that leakage has occurred. This invention enables leakage detection in water supply networks.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • A Time Series Analysis-Based Method for Monitoring and Early Warning of Leakage in Water Supply Networks

    CN110043808B

  • Automatic identification and locating method for leakage of water supply network

    CN111237646A

  • Leakage detection method for pipeline network in independent metering area based on double-layer recurrent neural network

    CN112836758B

  • Independent metering area pipe network leakage detection method based on mode detection

    CN112780953A

  • Water supply pipe network leakage monitoring method based on multi-region joint evaluation

    CN113739082A