Penalized Functional Decomposition for Detecting Bursts in Water Distribution Systems

Abstract

Detecting pipe bursts in water distribution systems (WDSs) is of critical importance for urban infrastructure maintenance. A pipe burst can be detected from measurements that are continuously collected from hydraulic meters installed in WDSs, with widely accepted statistical process control techniques. However, the significant autocorrelation inevitably embedded in the continuously collected hydraulic measurements makes it extremely difficult for existing methods to accurately estimate the breakout time and the magnitude of a burst. To overcome the limitation, this paper proposes a new method to model the autocorrelation patterns with functional basis expansion. Functional regression is adopted to detect the pipe burst by decomposing the hydraulic measurements into three components: the normal components, the burst-induced anomaly component, and noises. A regularized estimation algorithm is developed to identify the three components by incorporating the knowledge of the impacts of bursts on the autocorrelation patterns in hydraulic measurements. A simulated water distribution network is built through EPANET. Analysis results based on the simulated data show that the proposed method not only outperforms existing methods with higher burst detectability and lower false alarm rate, but can also estimate the burst starting time, and magnitude estimation.