Geostatistical techniques for approximate location of pipe burst events in water distribution systems

Abstract

This paper focusses on the customisation and further enhancement of the recently developed data-driven methodology for the automated near real-time detection of pipe bursts and other (e.g. sensor faults) events at the district metered area (DMA) level. Assuming the availability of pressure/flow data from an increased number of sensors deployed in a DMA, the aim is to: (i) overcome the limitations of the probabilistic inference engine when dealing with the increased data availability; and (ii) exploit the event information resulting from the analysis of the larger number of DMA signals for determining the approximate location of the pipe burst events within the DMA. This is achieved by making use of a multivariate Gaussian mixtures-based graphical model and geostatistical techniques. The novel detection and location methodology is demonstrated and tested on a series of simulated pipe burst events that were performed by opening hydrants in a real-life DMA in the UK. The results obtained illustrate that the new methodology can successfully determine the approximate location of pipe bursts within a DMA (in addition to detecting them in a fast and reliable manner). The performance comparison of several geostatistical techniques shows that the Ordinary Cokriging technique outperforms all other techniques tested.

A decision support system for on-line leakage localization

“…An alternative approach based on an inverse approach that formulates the leak detection and localization problem as a parameter estimation approach was presented by Pudar & Ligget (1992) and further inverse approaches were investigated (Ligget & Chen, 1995) (Kapelan et al, 2003) (Wu & Sage, 2006). Additionally, other contributions integrating data-driven and model-driven approaches (Farley et al, 2010;Bicik et al, 2013) or based just on a data-driven approach (Romano et al, 2013) were also presented. Pérez et al (2011) presents a direct modelling methodology developed to help network operators deal with the detection and localization of leaks in district metered areas (DMAs 5 ) of water distribution networks.…”

Leak Detection and Localization through Demand Components Calibration

“…Leakage awareness focuses on leakage detection in the network [(Kapelan et al 2003); ; ; (Palau et al 2012); (Romano et al 2014)], but does not give any information about its precise location. On the other hand, leakage localization (Romano et al 2013) is an activity that identifies and prioritizes the areas of leakage to make pinpointing of leaks easier. Leak localization techniques can be divided into two categories: external and internal (ADEC 2000).…”

Distance and time of water effluence on soil surface after failure of buried water pipe. Laboratory investigations and statistical analysis

“…What can reduce a number of damages is skilful management of a water supply system and proper maintenance. It is, however, impossible to entirely eliminate such incidents as, most often, they occur randomly [5,7,24]. They can result in financial and social losses [7,8,25,28].…”