Pattern Recognition and Clustering of Transient Pressure Signals for Burst Location

Abstract

A large volume of the water produced for public supply is lost in the systems between sources and consumers. An important—in many cases the greatest—fraction of these losses are physical losses, mainly related to leaks and bursts in pipes and in consumer connections. Fast detection and location of bursts plays an important role in the design of operation strategies for water loss control, since this helps reduce the volume lost from the instant the event occurs until its effective repair (run time). The transient pressure signals caused by bursts contain important information about their location and magnitude, and stamp on any of these events a specific "hydraulic signature". The present work proposes and evaluates three methods to disaggregate transient signals, which are used afterwards to train artificial neural networks (ANNs) to identify burst locations and calculate the leaked flow. In addition, a clustering process is also used to group similar signals, and then train specific ANNs for each group, thus improving both the computational efficiency and the location accuracy. The proposed methods are applied to two real distribution networks, and the results show good accuracy in burst location and characterization.

Advances in Modeling and Management of Urban Water Networks

“…In the field of WDSs, all works are numerical analyses, though most of them, i.e., [38][39][40]43,44], present models calibrated on the basis of experimental data. The methodologies adopted are multi-faceted, ranging from physically based modelling, [40,41,44,45], to GIS algorithms, [42], data-driven techniques, [38,39,43], graph-theory, [43], and optimization algorithms, [38,41,45].…”

“…In this context, Mirshafiei et al [42] present a Geospatial Information System (GIS)-based methodology for partially isolating a leaking pipeline from the remainder of a WDS and its application to an Iranian WDS. Manzi et al [43] present a methodology based on disaggregation, ANN, and clustering techniques for the identification and location of bursts in real WDSs. Thanks to the well-calibrated model of a WDS in Southern Italy, Bosco et al [44] show the extent to which WDS rehabilitation and active pressure control can help in reducing leakage.…”

“…Manzi et al [43] present a methodology aimed at processing transient signals for the detection and location of bursts in WDSs. Disaggregation, ANN, and clustering techniques are the methodological elements.…”

A Digital Twin of a Water Distribution System by Using Graph Convolutional Networks for Pump Speed-Based State Estimation

“…The models proposed from data mining and machine learning have become popular in the last decade [21]. Some of the developed applications using machine learning are applied to optimal pressure management and district metered area design [22], leak detection in WDSs [23][24][25][26][27], water demand estimation [28][29][30], and detection of cyberattacks, physical attacks, and contamination in WDSs [31,32].…”

Near–Real Time Burst Location and Sizing in Water Distribution Systems Using Artificial Neural Networks

“…Data acquired by SCADA are stored and, if well handled, can be used to improve the O&M of the systems. In this line, algorithms based on machine learning and data mining are useful and widely used for leakage and burst detection in water systems, such as Artificial Neural Networks both using steady-state [24,25] and transient-state data [26,27]. The design of a wireless sensor network joint to a machine learning algorithm to detect and to quantify leaks in water systems has been proposed [28].…”