Cargando…

Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals

The damage caused by corrosion in chemical process installations can lead to unexpected plant shutdowns and the leakage of potentially toxic chemicals into the environment. When subjected to corrosion, structural changes in the material occur, leading to energy releases as acoustic waves. This acous...

Descripción completa

Detalles Bibliográficos
Autores principales: Van Dijck, Gert, Van Hulle, Marc M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Molecular Diversity Preservation International (MDPI) 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3231411/
https://www.ncbi.nlm.nih.gov/pubmed/22163921
http://dx.doi.org/10.3390/s110605695
_version_ 1782218215829536768
author Van Dijck, Gert
Van Hulle, Marc M.
author_facet Van Dijck, Gert
Van Hulle, Marc M.
author_sort Van Dijck, Gert
collection PubMed
description The damage caused by corrosion in chemical process installations can lead to unexpected plant shutdowns and the leakage of potentially toxic chemicals into the environment. When subjected to corrosion, structural changes in the material occur, leading to energy releases as acoustic waves. This acoustic activity can in turn be used for corrosion monitoring, and even for predicting the type of corrosion. Here we apply wavelet packet decomposition to extract features from acoustic emission signals. We then use the extracted wavelet packet coefficients for distinguishing between the most important types of corrosion processes in the chemical process industry: uniform corrosion, pitting and stress corrosion cracking. The local discriminant basis selection algorithm can be considered as a standard for the selection of the most discriminative wavelet coefficients. However, it does not take the statistical dependencies between wavelet coefficients into account. We show that, when these dependencies are ignored, a lower accuracy is obtained in predicting the corrosion type. We compare several mutual information filters to take these dependencies into account in order to arrive at a more accurate prediction.
format Online
Article
Text
id pubmed-3231411
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher Molecular Diversity Preservation International (MDPI)
record_format MEDLINE/PubMed
spelling pubmed-32314112011-12-07 Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals Van Dijck, Gert Van Hulle, Marc M. Sensors (Basel) Article The damage caused by corrosion in chemical process installations can lead to unexpected plant shutdowns and the leakage of potentially toxic chemicals into the environment. When subjected to corrosion, structural changes in the material occur, leading to energy releases as acoustic waves. This acoustic activity can in turn be used for corrosion monitoring, and even for predicting the type of corrosion. Here we apply wavelet packet decomposition to extract features from acoustic emission signals. We then use the extracted wavelet packet coefficients for distinguishing between the most important types of corrosion processes in the chemical process industry: uniform corrosion, pitting and stress corrosion cracking. The local discriminant basis selection algorithm can be considered as a standard for the selection of the most discriminative wavelet coefficients. However, it does not take the statistical dependencies between wavelet coefficients into account. We show that, when these dependencies are ignored, a lower accuracy is obtained in predicting the corrosion type. We compare several mutual information filters to take these dependencies into account in order to arrive at a more accurate prediction. Molecular Diversity Preservation International (MDPI) 2011-05-27 /pmc/articles/PMC3231411/ /pubmed/22163921 http://dx.doi.org/10.3390/s110605695 Text en © 2011 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/3.0/).
spellingShingle Article
Van Dijck, Gert
Van Hulle, Marc M.
Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals
title Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals
title_full Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals
title_fullStr Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals
title_full_unstemmed Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals
title_short Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals
title_sort information theory filters for wavelet packet coefficient selection with application to corrosion type identification from acoustic emission signals
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3231411/
https://www.ncbi.nlm.nih.gov/pubmed/22163921
http://dx.doi.org/10.3390/s110605695
work_keys_str_mv AT vandijckgert informationtheoryfiltersforwaveletpacketcoefficientselectionwithapplicationtocorrosiontypeidentificationfromacousticemissionsignals
AT vanhullemarcm informationtheoryfiltersforwaveletpacketcoefficientselectionwithapplicationtocorrosiontypeidentificationfromacousticemissionsignals