Corrosion detection and severity level prediction using acoustic emission and machine learning based approach

Failure caused by corrosion in industries are the major cause of breakdown maintenance. Acoustic emission during the accelerated corrosion testing is a reliable method for corrosion detection, however, classification of these acoustic emission signals by machine learning techniques is still in its i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Muhammad Fahad Sheikh, Khurram Kamal, Faheem Rafique, Salman Sabir, Hassan Zaheer, Kashif Khan
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Acoustic emission Corrosion detection Accelerated corrosion testing Machine learning classifiers Severity level prediction Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/53b2030637ed4f6a8c448869e19ad4e6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:53b2030637ed4f6a8c448869e19ad4e6
record_format	dspace
spelling	oai:doaj.org-article:53b2030637ed4f6a8c448869e19ad4e62021-11-22T04:22:17ZCorrosion detection and severity level prediction using acoustic emission and machine learning based approach2090-447910.1016/j.asej.2021.03.024https://doaj.org/article/53b2030637ed4f6a8c448869e19ad4e62021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2090447921001970https://doaj.org/toc/2090-4479Failure caused by corrosion in industries are the major cause of breakdown maintenance. Acoustic emission during the accelerated corrosion testing is a reliable method for corrosion detection, however, classification of these acoustic emission signals by machine learning techniques is still in its infancy. Proposed approach uses a hybrid technique that combines the detection of corrosion through acoustic emission signals from accelerated corrosion testing with machine learning techniques to accurately predict the corrosion severity levels. Laboratory based experimentation setup was established for accelerated corrosion testing of mild steel samples for different time spans and mass loss of samples were recorded. Acoustic emission signals were acquired at high frequency sampling rate with Sound Well AE sensor, NI Elvis kit and NI Labview software. AE mean, AE RMS, AE energy, and kurtosis were selected as distinct features as they represent a linear relationship with the corrosion process. For multi-class problem, five Corrosion severity levels have been made based on mass loss occurred during accelerated corrosion testing for which Naive Bayes, BP-NN and RBF-NN showed accuracy of 90.4%, 94.57%, and 100% respectively.Muhammad Fahad SheikhKhurram KamalFaheem RafiqueSalman SabirHassan ZaheerKashif KhanElsevierarticleAcoustic emissionCorrosion detectionAccelerated corrosion testingMachine learning classifiersSeverity level predictionEngineering (General). Civil engineering (General)TA1-2040ENAin Shams Engineering Journal, Vol 12, Iss 4, Pp 3891-3903 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Acoustic emission Corrosion detection Accelerated corrosion testing Machine learning classifiers Severity level prediction Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Acoustic emission Corrosion detection Accelerated corrosion testing Machine learning classifiers Severity level prediction Engineering (General). Civil engineering (General) TA1-2040 Muhammad Fahad Sheikh Khurram Kamal Faheem Rafique Salman Sabir Hassan Zaheer Kashif Khan Corrosion detection and severity level prediction using acoustic emission and machine learning based approach
description	Failure caused by corrosion in industries are the major cause of breakdown maintenance. Acoustic emission during the accelerated corrosion testing is a reliable method for corrosion detection, however, classification of these acoustic emission signals by machine learning techniques is still in its infancy. Proposed approach uses a hybrid technique that combines the detection of corrosion through acoustic emission signals from accelerated corrosion testing with machine learning techniques to accurately predict the corrosion severity levels. Laboratory based experimentation setup was established for accelerated corrosion testing of mild steel samples for different time spans and mass loss of samples were recorded. Acoustic emission signals were acquired at high frequency sampling rate with Sound Well AE sensor, NI Elvis kit and NI Labview software. AE mean, AE RMS, AE energy, and kurtosis were selected as distinct features as they represent a linear relationship with the corrosion process. For multi-class problem, five Corrosion severity levels have been made based on mass loss occurred during accelerated corrosion testing for which Naive Bayes, BP-NN and RBF-NN showed accuracy of 90.4%, 94.57%, and 100% respectively.
format	article
author	Muhammad Fahad Sheikh Khurram Kamal Faheem Rafique Salman Sabir Hassan Zaheer Kashif Khan
author_facet	Muhammad Fahad Sheikh Khurram Kamal Faheem Rafique Salman Sabir Hassan Zaheer Kashif Khan
author_sort	Muhammad Fahad Sheikh
title	Corrosion detection and severity level prediction using acoustic emission and machine learning based approach
title_short	Corrosion detection and severity level prediction using acoustic emission and machine learning based approach
title_full	Corrosion detection and severity level prediction using acoustic emission and machine learning based approach
title_fullStr	Corrosion detection and severity level prediction using acoustic emission and machine learning based approach
title_full_unstemmed	Corrosion detection and severity level prediction using acoustic emission and machine learning based approach
title_sort	corrosion detection and severity level prediction using acoustic emission and machine learning based approach
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/53b2030637ed4f6a8c448869e19ad4e6
work_keys_str_mv	AT muhammadfahadsheikh corrosiondetectionandseveritylevelpredictionusingacousticemissionandmachinelearningbasedapproach AT khurramkamal corrosiondetectionandseveritylevelpredictionusingacousticemissionandmachinelearningbasedapproach AT faheemrafique corrosiondetectionandseveritylevelpredictionusingacousticemissionandmachinelearningbasedapproach AT salmansabir corrosiondetectionandseveritylevelpredictionusingacousticemissionandmachinelearningbasedapproach AT hassanzaheer corrosiondetectionandseveritylevelpredictionusingacousticemissionandmachinelearningbasedapproach AT kashifkhan corrosiondetectionandseveritylevelpredictionusingacousticemissionandmachinelearningbasedapproach
_version_	1718418220859260928

Corrosion detection and severity level prediction using acoustic emission and machine learning based approach

Ejemplares similares