Time-Series-Based Leakage Detection Using Multiple Pressure Sensors in Water Distribution Systems.

Yu Shao,Xiaowei Liu,Xin Li,Shipeng Chu,Tuqiao Zhang

doi:10.3390/s19143070

Abstract

Leak detection is nowadays an important task for water utilities as leakages in water distribution systems (WDS) increase economic costs significantly and create water resource shortages. Monitoring data such as pressure and flow rate of WDS fluctuate with time. Diagnosis based on time series monitoring data is thought to be more convincing than one-time point data. In this paper, a threshold selection method for the correlation coefficient based on time series data is proposed based on leak scenario falsification, to explore the advantages of data interpretation based on time series for leak detection. The approach utilizes temporal varying correlation between data from multiple pressure sensors, updates the threshold values over time, and scans multiple times for a scanning time window. The effect of scanning time window length on threshold selection is also tested. The performance of the proposed method is tested on a real, full-scale water distribution network using synthetic data, considering the uncertainty of demand and leak flow rates, sensor noise, and so forth. The case study shows that the scanning time window length of 3–6 achieves better performance; the potential of the method for leak detection performance improvement is confirmed, though affected by many factors such as modeling and measurement uncertainties.

Highlights

The urban water supply network system can be seen as a mobile data carrier which transmits the information of pipe flow rate, nodal pressure, and water quality under the condition of satisfying energy balance, pressure balance, and water quality balance
This paper focuses on the detection process and has the following assumptions: there is only one leak that appears at one time and leaks occurs at a node in the water distribution system model; pressure sensors in the water network are placed in the selected nodes and are working well, and the measured pressures are synthetically generated from the simulated pressure value by adding random noise; the error of the prediction model is considered by adding the noise of the nodal demand to the real nodal demand; sudden special events that may produce significant relevant demand variations are not considered
Compared to the single-time scanning time window (STW), we can clearly see that the proposed method using multitime STW can effectively improve the detection probability for a given cumulative rate of false alarm

Summary

Introduction

The urban water supply network system can be seen as a mobile data carrier which transmits the information of pipe flow rate, nodal pressure, and water quality under the condition of satisfying energy balance, pressure balance, and water quality balance. Have a certain degree of leakage, leakage management of pipe networks becomes one of the most concerning problems for water supply companies. Over the past few decades, several researchers have conducted extensive research on leak detection in water distribution systems; a number of methods have been proposed to identify pipe bursts/leaks [1]. Leak detection techniques can be divided into two categories: external and internal [2]. Internal methods are divided into four main categories: (1) transient-based methods,

Objectives

Methods

Results

Conclusion