Burst detection in district metering areas using a data driven clustering algorithm

Wu, Yipeng; Liu, Shuming; Wang, Xue; Liu, Youfei; Guan, Yisheng

doi:10.1016/j.watres.2016.05.016

Cited by 105 publications

(45 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to accurately localize the water leaks, correct and oriented monitoring of detail information concerning system behavior is required. Among these monitoring devices, the acoustic equipment (e.g., noise correlators and listening sticks) is efficient to localize the leaks manually through reading abnormal behaviors at potential locations of the WDN system [10,11]. However, the expensive cost, as well as time consuming and labour demanding features prevent the acoustic equipment being widely used in reality.…”

Section: Introductionmentioning

confidence: 99%

“…With the aim of achieving an accurate estimation of consumed water, the WDN has been divided into smaller sub-networks, named district metered areas (DMAs) for management. Almost all of the previous implementations are applied on the DMA level [10]. Practically, the performance of the leak localization methods is highly sensitive to the numbers of the installed sensors, as well as the placement of these sensors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leak Localization in Water Distribution Networks Using Pressure and Data-Driven Classifier Approach

Sun

Parellada

Puig

et al. 2019

Water

View full text Add to dashboard Cite

Leaks in water distribution networks (WDNs) are one of the main reasons for water loss during fluid transportation. Considering the worldwide problem of water scarcity, added to the challenges that a growing population brings, minimizing water losses through leak detection and localization, timely and efficiently using advanced techniques is an urgent humanitarian need. There are numerous methods being used to localize water leaks in WDNs through constructing hydraulic models or analyzing flow/pressure deviations between the observed data and the estimated values. However, from the application perspective, it is very practical to implement an approach which does not rely too much on measurements and complex models with reasonable computation demand. Under this context, this paper presents a novel method for leak localization which uses a data-driven approach based on limit pressure measurements in WDNs with two stages included: (1) Two different machine learning classifiers based on linear discriminant analysis (LDA) and neural networks (NNET) are developed to determine the probabilities of each node having a leak inside a WDN; (2) Bayesian temporal reasoning is applied afterwards to rescale the probabilities of each possible leak location at each time step after a leak is detected, with the aim of improving the localization accuracy. As an initial illustration, the hypothetical benchmark Hanoi district metered area (DMA) is used as the case study to test the performance of the proposed approach. Using the fitting accuracy and average topological distance (ATD) as performance indicators, the preliminary results reaches more than 80% accuracy in the best cases.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Leak Localization in Water Distribution Networks Using Pressure and Data-Driven Classifier Approach

Sun

Parellada

Puig

et al. 2019

Water

View full text Add to dashboard Cite

show abstract

“…Currently, the probability of pipe failure is estimated based on pipe properties, historical (failure) data and external conditions, with emphasis on reactive leakage control in the form of leak detection and localization (Mounce et al 2003;Puust et al 2010;Bakker et al 2014;Gelazanskas and Gamage 2014;Okeya et al 2015;Wu et al 2016). However, to deal with the unknown state and continuous degradation of pipes, a proactive strategy, with a focused on leak prevention, is required.…”

Section: Introductionmentioning

confidence: 99%

Monitoring Support for Water Distribution Systems based on Pressure Sensor Data

Geelen

Yntema²,

Molenaar

et al. 2019

Water Resour Manage

View full text Add to dashboard Cite

The increasing age and deterioration of drinking water mains is causing an increasing frequency of pipe bursts. Not only are pipe repairs costly, bursts might also lead to contamination of the Dutch non-chlorinated drinking water, as well as damage to other above-and underground infrastructure. Detection and localization of pipe bursts have long been priorities for water distribution companies. Here we present a method for proactive leakage control, referred to as Monitoring Support. Contrary to most leak prevention methods, our method is based on real-time pressure sensor measurements and focuses on detection of recurring pressure anomalies, which are assumed to be indicative of misuse or malfunctioning of the water distribution network. The method visualizes and warns for both recurring and one-time anomalous events and offers monitoring experts an unsupervised decision support tool that requires no training data or manual labeling. Additionally, our method supports any time series data source and can be applied to other types of distribution networks, such as those for gas, electricity and oil. The performance of our method, including both instance-based and featurebased clustering, was validated on two pressure sensor data sets. Results indicate that featurebased clustering is the best method for detection of recurring pressure anomalies, with accuracy F 1-scores of 92% and 94% for a 2013 and 2017 data set, respectively.

show abstract

“…Research on water demand time series have been largely focused on pattern analysis for urban planning and management [3][4][5][6], forecasting [2,[7][8][9], or a combination of both to produce a more accurate forecast [10][11][12]. On the other hand, the research on utilizing water demand time series for anomaly detection pale in comparison, especially in the area of unsupervised methodology [13,14]. Such a phenomenon can be explained as follows.…”

Section: Introductionmentioning

confidence: 99%

“…While unsupervised methodology can eliminate the need for data labeling, proposed unsupervised methodology by Candelieri [11] requires at least a year of data for the identification of seasonality. Wu et al [13] also require a large amount of data as insufficient data cannot demonstrate the overall variation of flow measurement [1]. Although extended work by Wu et al [14] reduced the amount of data required, the methodology required a pre-requisite of installing flow sensors at every inlet/outlet of a District Metering Area (DMA) that may not be available.…”

mentioning

confidence: 99%

Unsupervised Bayesian Nonparametric Approach with Incremental Similarity Tracking of Unlabeled Water Demand Time Series for Anomaly Detection

Chan

Chin

2019

Water

View full text Add to dashboard Cite

In this paper, a fusion of unsupervised clustering and incremental similarity tracking of hourly water demand series is proposed. Current research using unsupervised methodologies to detect anomalous water is limited and may possess several limitations such as a large amount of dataset, the need to select an optimal cluster number, or low detection accuracy. Our proposed approach aims to address the need for a large amount of dataset by detecting anomaly through (1) clustering points that are relatively similar at each time step, (2) clustering points at each time step by the similarity in how they vary from each time step, and (3) to compare the incoming points with a reference shape for online anomalous trend detection. Secondly, through the use of Bayesian nonparametric approach such as the Dirichlet Process Mixture Model, the need to choose an optimal cluster number is eliminated and provides a subtle solution for ‘reserving’ an empty cluster for the future anomaly. Among the 165 randomly generated anomalies, the proposed approach detected a total of 159 anomalies and other anomalous trends present in the data. As the data is unlabeled, identified anomalous trends cannot be verified. However, results show great potential in using minimally unlabeled water demand data for a preliminary anomaly detection.

show abstract

Burst detection in district metering areas using a data driven clustering algorithm

Cited by 105 publications

References 26 publications

Leak Localization in Water Distribution Networks Using Pressure and Data-Driven Classifier Approach

Leak Localization in Water Distribution Networks Using Pressure and Data-Driven Classifier Approach

Monitoring Support for Water Distribution Systems based on Pressure Sensor Data

Unsupervised Bayesian Nonparametric Approach with Incremental Similarity Tracking of Unlabeled Water Demand Time Series for Anomaly Detection

Contact Info

Product

Resources

About