Machine learning model and strategy for fast and accurate detection of leaks in water supply network
Abstract 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 p...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2021-04-01
|
Series: | Journal of Infrastructure Preservation and Resilience |
Subjects: | |
Online Access: | https://doi.org/10.1186/s43065-021-00021-6 |
id |
doaj-b7c56b68772e4e069b0f2a85c54d8043 |
---|---|
record_format |
Article |
spelling |
doaj-b7c56b68772e4e069b0f2a85c54d80432021-04-18T11:51:14ZengSpringerOpenJournal of Infrastructure Preservation and Resilience2662-25212021-04-012112110.1186/s43065-021-00021-6Machine learning model and strategy for fast and accurate detection of leaks in water supply networkXudong Fan0Xijin Zhang1Xiong ( Bill) Yu2Department of Civil and Environmental Engineering, Case Western Reserve UniversityDepartment of Civil and Environmental Engineering, Case Western Reserve UniversityDepartment of Civil and Environmental Engineering, Case Western Reserve UniversityAbstract 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.https://doi.org/10.1186/s43065-021-00021-6Water supply networkArtificial intelligenceMachine learningArtificial neural networkAutoencoder neural networkLeak detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xudong Fan Xijin Zhang Xiong ( Bill) Yu |
spellingShingle |
Xudong Fan Xijin Zhang Xiong ( Bill) Yu Machine learning model and strategy for fast and accurate detection of leaks in water supply network Journal of Infrastructure Preservation and Resilience Water supply network Artificial intelligence Machine learning Artificial neural network Autoencoder neural network Leak detection |
author_facet |
Xudong Fan Xijin Zhang Xiong ( Bill) Yu |
author_sort |
Xudong Fan |
title |
Machine learning model and strategy for fast and accurate detection of leaks in water supply network |
title_short |
Machine learning model and strategy for fast and accurate detection of leaks in water supply network |
title_full |
Machine learning model and strategy for fast and accurate detection of leaks in water supply network |
title_fullStr |
Machine learning model and strategy for fast and accurate detection of leaks in water supply network |
title_full_unstemmed |
Machine learning model and strategy for fast and accurate detection of leaks in water supply network |
title_sort |
machine learning model and strategy for fast and accurate detection of leaks in water supply network |
publisher |
SpringerOpen |
series |
Journal of Infrastructure Preservation and Resilience |
issn |
2662-2521 |
publishDate |
2021-04-01 |
description |
Abstract 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. |
topic |
Water supply network Artificial intelligence Machine learning Artificial neural network Autoencoder neural network Leak detection |
url |
https://doi.org/10.1186/s43065-021-00021-6 |
work_keys_str_mv |
AT xudongfan machinelearningmodelandstrategyforfastandaccuratedetectionofleaksinwatersupplynetwork AT xijinzhang machinelearningmodelandstrategyforfastandaccuratedetectionofleaksinwatersupplynetwork AT xiongbillyu machinelearningmodelandstrategyforfastandaccuratedetectionofleaksinwatersupplynetwork |
_version_ |
1721521860670128128 |