Pipe bursting is a serious problem for water supply systems. We propose a two-step burst detection and localization method for a long-distance water transportation pipeline. First, we use the Dempster–Shafer theory, an effective inference method for processing uncertain information, and combine two risk functions to identify a pipe burst. Then we identify the location of the burst point using a hydraulic model. The method is prototyped on a transportation pipeline in Guangzhou, China and tested with one-year historical records. The detection system correctly identified all the bursts and the alarm rate is acceptable for the system inspectors (average: two alarms/month). The burst location is identified within the acceptable limits of accuracy.

This paper describes an infrastructure to detect burst events in a water distribution network, which we illustrate using the Guangzhou water distribution system (WDS). We consider three issues: The feasibility and capability of accurate detection, the layout and design of the monitoring infrastructure, and the burst event detection algorithm. Background noise is identified by analyzing the monitored data. A burst event can be accurately detected only when the impact of the burst can be differentiated from the background noise. We hypothesize that there is a minimum pipe diameter below which accurate burst detection is impossible. We found that data from at least two sensors close to the burst event are required to reduce detection errors.