Burst Detection in Water Networks Using Principal Component Analysis

Abstract

The following work presents a multivariate statistical technique applied to the control of water inflows into district metering areas (DMAs) of urban networks. This technique, called principal-component analysis (PCA), allows for a sensitive and quick analysis of the inflows into a DMA without hassling mathematical algorithms. The PCA technique simplifies the original set of flow rate data recorded by the supervisory control and data acquisition (SCADA) system, synthesizing the most significant information into a statistical model that is able to explain most of the behavior of the water distribution network. The PCA technique also allows for the establishment of control charts that help system operators in the identification of anomalous behaviors regarding water use, bursts, or illegal connections. The described technique has been proven to offer high detection sensitivity to bursts or other unexpected consumptions.