Cargando…

A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning

This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The acoustic emission signal of a pipeline contains leak-related information. However, the noise in the signal often obscures the leak-related information, making traditional acoustic emission featu...

Descripción completa

Detalles Bibliográficos
Autores principales: Ahmad, Sajjad, Ahmad, Zahoor, Kim, Cheol-Hong, Kim, Jong-Myon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8875737/
https://www.ncbi.nlm.nih.gov/pubmed/35214465
http://dx.doi.org/10.3390/s22041562
_version_ 1784658004342210560
author Ahmad, Sajjad
Ahmad, Zahoor
Kim, Cheol-Hong
Kim, Jong-Myon
author_facet Ahmad, Sajjad
Ahmad, Zahoor
Kim, Cheol-Hong
Kim, Jong-Myon
author_sort Ahmad, Sajjad
collection PubMed
description This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The acoustic emission signal of a pipeline contains leak-related information. However, the noise in the signal often obscures the leak-related information, making traditional acoustic emission features, such as count and peaks, less effective. To obtain leak-related features, first, acoustic images were obtained from the time series acoustic emission signals using continuous wavelet transform. The acoustic images (AE images) were the wavelet scalograms that represent the time–frequency scales of the acoustic emission signal in the form of an image. The acoustic images carried enough information about the leak, as the leak-related information had a high-energy representation in the scalogram compared to the noise. To extract leak-related discriminant features from the acoustic images, they were provided as input into the convolutional autoencoder and convolutional neural network. The convolutional autoencoder extracts global features, while the convolutional neural network extracts local features. The local features represent changes in the energy at a finer level, whereas the global features are the overall characteristics of the acoustic signal in the acoustic image. The global and local features were merged into a single feature vector. To identify the pipeline leak state, the feature vector was fed into a shallow artificial neural network. The proposed method was validated by utilizing a data set obtained from the industrial pipeline testbed. The proposed algorithm yielded a high classification accuracy in detecting leaks under different leak sizes and fluid pressures.
format Online
Article
Text
id pubmed-8875737
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88757372022-02-26 A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning Ahmad, Sajjad Ahmad, Zahoor Kim, Cheol-Hong Kim, Jong-Myon Sensors (Basel) Article This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The acoustic emission signal of a pipeline contains leak-related information. However, the noise in the signal often obscures the leak-related information, making traditional acoustic emission features, such as count and peaks, less effective. To obtain leak-related features, first, acoustic images were obtained from the time series acoustic emission signals using continuous wavelet transform. The acoustic images (AE images) were the wavelet scalograms that represent the time–frequency scales of the acoustic emission signal in the form of an image. The acoustic images carried enough information about the leak, as the leak-related information had a high-energy representation in the scalogram compared to the noise. To extract leak-related discriminant features from the acoustic images, they were provided as input into the convolutional autoencoder and convolutional neural network. The convolutional autoencoder extracts global features, while the convolutional neural network extracts local features. The local features represent changes in the energy at a finer level, whereas the global features are the overall characteristics of the acoustic signal in the acoustic image. The global and local features were merged into a single feature vector. To identify the pipeline leak state, the feature vector was fed into a shallow artificial neural network. The proposed method was validated by utilizing a data set obtained from the industrial pipeline testbed. The proposed algorithm yielded a high classification accuracy in detecting leaks under different leak sizes and fluid pressures. MDPI 2022-02-17 /pmc/articles/PMC8875737/ /pubmed/35214465 http://dx.doi.org/10.3390/s22041562 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ahmad, Sajjad
Ahmad, Zahoor
Kim, Cheol-Hong
Kim, Jong-Myon
A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning
title A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning
title_full A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning
title_fullStr A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning
title_full_unstemmed A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning
title_short A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning
title_sort method for pipeline leak detection based on acoustic imaging and deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8875737/
https://www.ncbi.nlm.nih.gov/pubmed/35214465
http://dx.doi.org/10.3390/s22041562
work_keys_str_mv AT ahmadsajjad amethodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT ahmadzahoor amethodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT kimcheolhong amethodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT kimjongmyon amethodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT ahmadsajjad methodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT ahmadzahoor methodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT kimcheolhong methodforpipelineleakdetectionbasedonacousticimaginganddeeplearning
AT kimjongmyon methodforpipelineleakdetectionbasedonacousticimaginganddeeplearning