Linear Prediction for Leak Detection in Water Distribution Networks

Cody, Roya; Dey, Pampa; Narasimhan, Sriram

doi:10.1061/(asce)ps.1949-1204.0000415

Cited by 28 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Martini et al (2018) used one hydrophone and two accelerometers for comparing the performance of polyvinyl chloride (PVC) and high‐density polyethylene pipe (HDPE) pipes. Additionally, a single sensor arrangement has been demonstrated for lab‐scale leak detection experiments (Cody, Dey, et al, 2020). Moreover, the optimal sensor placing on the pipe is one important issue for leak detection and localization (Zhao et al, 2020).…”

Section: Design Parameters Of Leak Experimentsmentioning

confidence: 99%

“…Cui et al (2016) proposed an empirical mode decomposition (EMD) based method to reduce attenuation and signal dispersion effects. Cody, Dey, et al (2020) developed a linear prediction (LP) method for extracting shorter signal segments along with cross‐correlation for leak detection and localization.…”

Section: Design Parameters Of Leak Experimentsmentioning

confidence: 99%

“…Most experiments in this regard focus on simulating leaks in controlled conditions either on a lab or testbed scale (Capponi et al, 2020). Although helpful in studying the impact of one factor at a time on the performance, the ability to observe the impact of multiple variants at the same time as present in the real environment is not truly possible in the lab and requires further investigation in real water distribution and supply networks (Cody, Dey, et al, 2020). A well‐design experiment for leak detection in water networks presents three main challenges: reliability, validity, and repeatability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

State‐of‐the‐art review of leak diagnostic experiments: Toward a smart water network

Bakhtawar

Zayed

2023

WIREs Water

View full text Add to dashboard Cite

Effective water pipeline leak detection and localization can help water practitioners save water losses and reduce pipe rehabilitation budgets. Different sensing technologies can provide essential data aiding model development for predicting future leaks in the water distribution networks. Solutions for applying different sensing technologies to real water distribution networks are being developed for real‐time data collection, precise leak localization, reducing false alarms, and continuous pipeline monitoring. Experiments of different scales and specifications have been conducted to test the application and effectiveness of sensing technologies for leak diagnosis in water pipelines. Quality data collection is especially crucial for the successful implementation of these experiments. However, practitioners need help designing effective leak detection and localization experiments, wasting time, and resources. There needs to be a greater understanding of the design parameters for more accurate testing, such as sensor selection, sensor placement, ambient noise sources, and system operations. The current study, therefore, delineates design parameters for design leak diagnosis experiments for lab, testbed, and real networks. For application in real water networks, expert opinion is used to help identify the benefits and limitations and the implementation issues of available sensing technologies. An example experiment design using multi‐sensing technologies for smart leak diagnostics in Hong Kong is also presented. The study can guide water practitioners and researchers to design a multi‐sensing leak diagnostic experiments enabling a smart and sustainable utility management.This article is categorized under: Engineering Water > Methods Engineering Water > Sustainable Engineering of Water Science of Water > Water Extremes

show abstract

Section: Design Parameters Of Leak Experimentsmentioning

confidence: 99%

Section: Design Parameters Of Leak Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

State‐of‐the‐art review of leak diagnostic experiments: Toward a smart water network

Bakhtawar

Zayed

2023

WIREs Water

View full text Add to dashboard Cite

show abstract

“…Cross-correlation methods have been successful in location leaks, for example [6,9], Alternative methods using support vector machines and probabilistic models have also been used [10], together with predictive machine learning algorithms to predict leakage flow rate in plastic water pipes [11]. Another data-driven anomaly detection approach has been investigated by Cody et al [12] to extract leaksensitive features for leak detection and location.…”

Section: Introductionmentioning

confidence: 99%

Estimating the spectrum of leak noise in buried plastic water distribution pipes using acoustic or vibration measurements remote from the leak

Scussel

Brennan

Almeida

et al. 2021

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

An appropriate model of leak noise at source is necessary in analytical and numerical approaches to investigate the characteristics of leak noise measured remotely from the leak in buried water pipes. It is extremely difficult to measure leak noise at source in practice, so an inverse method is needed to predict this from measurements made either side of the leak at convenient access points. This paper presents such a method, and illustrates the approach using four data sets from three different test sites. The method requires that the noise propagates in the pipe according to a simple model of wave propagation within the frequency range over which leak noise is detected at the sensors.Using the measured data, the real and imaginary parts of the wavenumber are estimated, and these, together with an estimated position of the leak between the two sensors, the frequency response functions corresponding to the sections of the pipe either side of the leak position are estimated. If pressure measurements are made, then both the level and shape of the leak noise spectrum can be estimated, but if accelerometers are used then only an estimate of the shape of the spectrum is possible. From the measurements presented, it is found that it is not possible to state categorically that the leak noise spectra decays according to a particular frequency power law. There is some evidence that it decays with a frequency power law of 1 ω − , which agrees with previous laboratory based experiments, but this is not definitive in all cases.

show abstract

“…In the work of Rajeswaran et al [4], a multi-stage graph partitioning algorithm was presented, which uses flow measurements to indicate a minimum number of additional measuring locations needed to narrow down leak location in large-size networks. In the work by Cody et al [5], a linear prediction signal processing technique was used to extract features from acoustic data, which can detect and localize pipe leaks. In a work by Bohorquez et al [6], an artificial neural network was applied to detect leak size and location in a single water pipeline.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Leak Localization in Urban Water Distribution Networks Using Big Data for Random Forest Classifier

Lučin

Čarija

et al. 2021

Mathematics

View full text Add to dashboard Cite

In the present paper, a Random Forest classifier is used to detect leak locations on two different sized water distribution networks with sparse sensor placement. A great number of leak scenarios were simulated with Monte Carlo determined leak parameters (leak location and emitter coefficient). In order to account for demand variations that occur on a daily basis and to obtain a larger dataset, scenarios were simulated with random base demand increments or reductions for each network node. Classifier accuracy was assessed for different sensor layouts and numbers of sensors. Multiple prediction models were constructed for differently sized leakage and demand range variations in order to investigate model accuracy under various conditions. Results indicate that the prediction model provides the greatest accuracy for the largest leaks, with the smallest variation in base demand (62% accuracy for greater- and 82% for smaller-sized networks, for the largest considered leak size and a base demand variation of ±2.5%). However, even for small leaks and the greatest base demand variations, the prediction model provided considerable accuracy, especially when localizing the sources of leaks when the true leak node and neighbor nodes were considered (for a smaller-sized network and a base demand of variation ±20% the model accuracy increased from 44% to 89% when top five nodes with greatest probability were considered, and for a greater-sized network with a base demand variation of ±10% the accuracy increased from 36% to 77%).

show abstract

Linear Prediction for Leak Detection in Water Distribution Networks

Cited by 28 publications

References 50 publications

State‐of‐the‐art review of leak diagnostic experiments: Toward a smart water network

State‐of‐the‐art review of leak diagnostic experiments: Toward a smart water network

Estimating the spectrum of leak noise in buried plastic water distribution pipes using acoustic or vibration measurements remote from the leak

Data-Driven Leak Localization in Urban Water Distribution Networks Using Big Data for Random Forest Classifier

Contact Info

Product

Resources

About