An official website of the United States government
Localizing pipe leaks is a significant challenge for water utilities worldwide. Pipe leaks in water distribution systems (WDSs) can cause the loss of a large amount of treated water, leading to pressure loss, increased energy costs, and contamination risks. What makes localizing pipe leaks challenging is the underground location of the water pipes and the similarity in impact on hydraulic properties (e.g., pressure, flow) due to leaks as compared to the effects of WDS operational changes. Physical methods to locate leaks are expensive, intrusive, and heavily localized. Computational approaches such as data-driven machine learning models provide an economical alternative to physical methods. Machine learning models are readily available and easily customizable to most problems; therefore, there is an increasing trend in their application for leak localization in WDSs. While several studies have applied machine learning models to localize leaks in single pipes and small test networks, these studies have yet to thoroughly test these models against the different complexities of leak localization problems, and hence their applicability to real-world WDSs is still unclear. The simplicity of the WDSs, the oversimplification of leak characteristics, and the lack of consideration of modeling and measuring device uncertainties adopted in most of these studies make the scalability of their proposed approaches questionable to real-world WDSs. Our study addresses this issue by devising four study cases of different complexity that account for realistic leak characteristics and model- and measuring device-related uncertainties. Two established machine learning models—multilayer perceptron (MLP) and convolutional neural network (CNN)—are trained and tested for their ability to localize the leaks and predict their sizes for each of the four study cases using different simulated hydraulic inputs. In addition, the potential benefit of combining different types of hydraulic data as inputs to the machine learning models in localizing leaks is also explored. Pressure and flow, two common hydraulic measurements, are used as inputs to the machine learning models. Further, the impact of single and multiple time point input in leak localization is also investigated. The results for the L-Town network indicate good accuracies for both the models for all study cases, with CNN consistently outperforming MLP.
more »
« less
SUPERVISED MACHINE LEARNING MODELS FOR LEAK DETECTION IN WATER DISTRIBUTION SYSTEMS
Water distribution systems (WDSs) face a significant challenge in the form of pipe leaks. Pipe leaks can cause loss of a large amount of treated water, leading to pressure loss, increased energy costs, and contamination risks. Locating pipe leaks has been a constant challenge for water utilities and stakeholders due to the underground location of the pipes. Physical methods to detect leaks are expensive, intrusive, and heavily localized. Computational approaches provide an economical alternative to physical methods. Data-driven machine learning-based computational approaches have garnered growing interest in recent years to address the challenge of detecting pipe leaks in WDSs. While several studies have applied machine learning models for leak detection on single pipes and small test networks, their applicability to the real-world WDSs is unclear. Most of these studies simplify the leak characteristics and ignore modeling and measuring device uncertainties, which makes the scalability of their approaches questionable to real-world WDSs. Our study addresses this issue by devising four study cases that account for the realistic leak characteristics (multiple, multi-size, and randomly located leaks) and incorporating noise in the input data to account for the model- and measuring device- related uncertainties. A machine learning-based approach that uses simulated pressure as input to predict both location and size of leaks is proposed. Two different machine learning models: Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN), are trained and tested for the four study cases, and their performances are compared. The precision and recall results for the L-Town network indicate good accuracies for both the models for all study cases, with CNN generally outperforming MLP.
more »
« less
- Award ID(s):
- 1919228
- PAR ID:
- 10344227
- Date Published:
- Journal Name:
- 2nd International Joint Conference on Water Distribution Systems Analysis & Computing and Control in the Water Industry
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Machine learning model and strategy for fast and accurate detection of leaks in water supply networkAbstract The water supply network (WSN) is subjected to leaks that compromise its service to the communities, which, however, is challenging to identify with conventional approaches before the consequences surface. This study developed Machine Learning (ML) models to detect leaks in the WDN. Water pressure data under leaking versus non-leaking conditions were generated with holistic WSN simulation code EPANET considering factors such as the fluctuating user demands, data noise, and the extent of leaks, etc. The results indicate that Artificial Neural Network (ANN), a supervised ML model, can accurately classify leaking versus non-leaking conditions; it, however, requires balanced dataset under both leaking and non-leaking conditions, which is difficult for a real WSN that mostly operate under normal service condition. Autoencoder neural network (AE), an unsupervised ML model, is further developed to detect leak with unbalanced data. The results show AE ML model achieved high accuracy when leaks occur in pipes inside the sensor monitoring area, while the accuracy is compromised otherwise. This observation will provide guidelines to deploy monitoring sensors to cover the desired monitoring area. A novel strategy is proposed based on multiple independent detection attempts to further increase the reliability of leak detection by the AE and is found to significantly reduce the probability of false alarm. The trained AE model and leak detection strategy is further tested on a testbed WSN and achieved promising results. The ML model and leak detection strategy can be readily deployed for in-service WSNs using data obtained with internet-of-things (IoTs) technologies such as smart meters.more » « less
-
The effectiveness of model-based leak localization methods in water distribution systems (WDSs), including optimization-based and machine learning approaches, significantly depends on the quality and quantity of input data. Pressure data, easily accessible due to nonintrusive sensor installation and maintenance, are commonly used. However, economic constraints limit the number of sensors in WDSs, highlighting the need for strategic sensor placement to enhance data quality. This study introduces a novel, method-independent sensor placement strategy that integrates cluster definitions (leak resolution) with intuitive surrogates for localization performance, addressing the limitations of existing methods reliant on complex, nonintuitive metrics. We propose the Euclidean cluster-based optimal placement of sensors (ECOPS) approach, which employs sensitivity and uniqueness as fundamental signal properties to guide sensor placement. Validation tests within a comprehensive real-world WDS demonstrate that ECOPS outperforms existing surrogate-based approaches and improves the performance of current sensors installed for leak characterization. These findings provide compelling evidence of ECOPS’s potential for enhancing pressure sensor placement, thereby improving leak localization in WDS applications.more » « less
-
null (Ed.)The primary goal of the project is to leverage recent developments in smart water technologies to detect and reduce water leakages in large water distribution networks with the aid of neural networks. A cost effective non-invasive solution to detect leakages in transmission pipelines is needed by many water utilities as it will lead to significant water savings and reduced pipe breakage frequencies, especially in older infrastructure systems. The eventual goal of the project is to test the ANN model on a real network using field measured pressure and pipe breakage data after tuning and developing the model with simulated data. In this project we propose building a regression model, based on Multi-Layer Perceptron (MLP) algorithm, which is a class of feedforward Artificial Neural Networks (ANNs) to detect the leak locations within a proposed network. The model should be able to learn the structure, i.e. mapping of various leak nodes and sensor nodes in an area, such that it can detect the leak nodes based on the pressure values with significant accuracy.more » « less
-
Soil piping (concentrated leak erosion) is a major contributor to soil erosion in many parts of the world, and collapse of eroded pipes can result in the formation of gullies and sinkholes or trigger slope instability. Despite these significant impacts, there is little understanding of factors controlling pipe collapse, and how water within the pipe influences moisture levels within a slope. In this study, physical models were employed on unsaturated model slopes with pre-formed macropores to investigate how soil properties, pipe characteristics, and hydraulic conditions govern internal erosion processes and slope stability. Experiments simulated shallow field conditions (0.45 m overburden) using 4 mm and 12 mm pipes to establish preferential flow paths, while varying model parameters including initial compaction moisture content and density, pipe condition (absent, closed, or open), slope angle, and model width. Volumetric water content sensors monitored moisture evolution, while cameras captured slope responses to subsurface flow. Results demonstrate that initial compaction conditions (water content and density), pipe size, hydraulic connectivity, and pipe condition control internal erosion processes and slope stability.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/https://doi.org/10.4995/WDSA-CCWI2022.2022.14831
