Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains

This contribution proposes a hybrid approach integrating transient test-based techniques with machine learning for automatic leak detection in water transmission mains. Transient numerical simulations calibrated using experimental tests are used to develop a data-driven method based on neural networ...

Full description

Saved in:
Bibliographic Details
Main Authors: Caterina Capponi, Andrea Menapace, Silvia Meniconi, Daniele Dalla Torre, Maurizio Tavelli, Maurizio Righetti, Bruno Brunone
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/69/1/142
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204799782354944
author Caterina Capponi
Andrea Menapace
Silvia Meniconi
Daniele Dalla Torre
Maurizio Tavelli
Maurizio Righetti
Bruno Brunone
author_facet Caterina Capponi
Andrea Menapace
Silvia Meniconi
Daniele Dalla Torre
Maurizio Tavelli
Maurizio Righetti
Bruno Brunone
author_sort Caterina Capponi
collection DOAJ
description This contribution proposes a hybrid approach integrating transient test-based techniques with machine learning for automatic leak detection in water transmission mains. Transient numerical simulations calibrated using experimental tests are used to develop a data-driven method based on neural networks to identify leak locations and characteristics. The accuracy of leak localization is demonstrated using three different degrees of noise in terms of mean absolute error, ranging between 0.54 m and 2.1 m. This proposed hybrid approach shows prospects for in-field applications.
format Article
id doaj-art-6e8b52d9dfb14da0955a4d071c572abe
institution OA Journals
issn 2673-4591
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-6e8b52d9dfb14da0955a4d071c572abe2025-08-20T02:11:13ZengMDPI AGEngineering Proceedings2673-45912024-09-0169114210.3390/engproc2024069142Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission MainsCaterina Capponi0Andrea Menapace1Silvia Meniconi2Daniele Dalla Torre3Maurizio Tavelli4Maurizio Righetti5Bruno Brunone6Department of Civil and Environmental Engineering, University of Perugia, 06125 Perugia, ItalyFaculty of Agricultural, Environmental and Food Science, Free University of Bolzano/Bozen, 39100 Bolzano, ItalyDepartment of Civil and Environmental Engineering, University of Perugia, 06125 Perugia, ItalyFaculty of Agricultural, Environmental and Food Science, Free University of Bolzano/Bozen, 39100 Bolzano, ItalyFaculty of Engineering, Free University of Bolzano/Bozen, 39100 Bolzano, ItalyFaculty of Agricultural, Environmental and Food Science, Free University of Bolzano/Bozen, 39100 Bolzano, ItalyDepartment of Civil and Environmental Engineering, University of Perugia, 06125 Perugia, ItalyThis contribution proposes a hybrid approach integrating transient test-based techniques with machine learning for automatic leak detection in water transmission mains. Transient numerical simulations calibrated using experimental tests are used to develop a data-driven method based on neural networks to identify leak locations and characteristics. The accuracy of leak localization is demonstrated using three different degrees of noise in terms of mean absolute error, ranging between 0.54 m and 2.1 m. This proposed hybrid approach shows prospects for in-field applications.https://www.mdpi.com/2673-4591/69/1/142transmission mainspressure transientanomaly detectionexperimental testsmachine learning
spellingShingle Caterina Capponi
Andrea Menapace
Silvia Meniconi
Daniele Dalla Torre
Maurizio Tavelli
Maurizio Righetti
Bruno Brunone
Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains
Engineering Proceedings
transmission mains
pressure transient
anomaly detection
experimental tests
machine learning
title Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains
title_full Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains
title_fullStr Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains
title_full_unstemmed Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains
title_short Hybrid Transient-Machine Learning Methodology for Leak Detection in Water Transmission Mains
title_sort hybrid transient machine learning methodology for leak detection in water transmission mains
topic transmission mains
pressure transient
anomaly detection
experimental tests
machine learning
url https://www.mdpi.com/2673-4591/69/1/142
work_keys_str_mv AT caterinacapponi hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains
AT andreamenapace hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains
AT silviameniconi hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains
AT danieledallatorre hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains
AT mauriziotavelli hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains
AT mauriziorighetti hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains
AT brunobrunone hybridtransientmachinelearningmethodologyforleakdetectioninwatertransmissionmains