Image-based feature extraction technique for inclined crack quantification using pulsed eddy current

Existing eddy current non-destructive testing (NDT) techniques generally do not consider the inclination angle of inclined cracks, which potentially harms a larger region of a tested structure. This work proposes the use of 2D scan images generated by using pulsed eddy current (PEC) non-destructive...

Full description

Bibliographic Details
Main Authors:	Nafiah, Faris, Sophian, Ali, Khan, Md. Raisuddin, Abdul Hamid, Syamsul Bahrin, Zainal Abidin, Ilham Mukriz
Format:	Article
Language:	English English English
Published:	Chinese Mechanical Engineering Society 2019
Subjects:	TJ170 Mechanics applied to machinery. Dynamics
Online Access:	http://irep.iium.edu.my/79655/ http://irep.iium.edu.my/79655/ http://irep.iium.edu.my/79655/ http://irep.iium.edu.my/79655/1/79655_Image-Based%20Feature%20Extraction.pdf http://irep.iium.edu.my/79655/2/79655_Image-Based%20Feature%20Extraction_SCOPUS.pdf http://irep.iium.edu.my/79655/3/79655_Image-Based%20Feature%20Extraction_WOS.pdf

id	iium-79655
recordtype	eprints
spelling	iium-796552020-03-19T08:02:07Z http://irep.iium.edu.my/79655/ Image-based feature extraction technique for inclined crack quantification using pulsed eddy current Nafiah, Faris Sophian, Ali Khan, Md. Raisuddin Abdul Hamid, Syamsul Bahrin Zainal Abidin, Ilham Mukriz TJ170 Mechanics applied to machinery. Dynamics Existing eddy current non-destructive testing (NDT) techniques generally do not consider the inclination angle of inclined cracks, which potentially harms a larger region of a tested structure. This work proposes the use of 2D scan images generated by using pulsed eddy current (PEC) non-destructive testing (NDT) technique in the quantification of the inclination and depth of inclined cracks. The image-based feature extraction technique effectively identifies the crack axis, which consequently enables extraction of features from the extracted linear scans. The technique extracts linear scans from the images to allow the extraction of three novel image-based features, namely the length of extracted linear scans (LLS), the linear scan skewness (LSS), and the highest value on linear scan (LSmax). The correlation of the three features to surface crack inclination angles and depths were analysed and found to be highly dependent on the crack depths, while only LLS and LSS are correlated to the crack inclination angles. © 2019, The Author(s). Chinese Mechanical Engineering Society 2019 Article PeerReviewed application/pdf en http://irep.iium.edu.my/79655/1/79655_Image-Based%20Feature%20Extraction.pdf application/pdf en http://irep.iium.edu.my/79655/2/79655_Image-Based%20Feature%20Extraction_SCOPUS.pdf application/pdf en http://irep.iium.edu.my/79655/3/79655_Image-Based%20Feature%20Extraction_WOS.pdf Nafiah, Faris and Sophian, Ali and Khan, Md. Raisuddin and Abdul Hamid, Syamsul Bahrin and Zainal Abidin, Ilham Mukriz (2019) Image-based feature extraction technique for inclined crack quantification using pulsed eddy current. Chinese Journal of Mechanical Engineering (English Edition), 32 (1). pp. 1-9. ISSN 1000-9345 E-ISSN 2192-8258 https://link.springer.com/content/pdf/10.1186/s10033-019-0341-y.pdf 10.1186/s10033-019-0341-y
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English English
topic	TJ170 Mechanics applied to machinery. Dynamics
spellingShingle	TJ170 Mechanics applied to machinery. Dynamics Nafiah, Faris Sophian, Ali Khan, Md. Raisuddin Abdul Hamid, Syamsul Bahrin Zainal Abidin, Ilham Mukriz Image-based feature extraction technique for inclined crack quantification using pulsed eddy current
description	Existing eddy current non-destructive testing (NDT) techniques generally do not consider the inclination angle of inclined cracks, which potentially harms a larger region of a tested structure. This work proposes the use of 2D scan images generated by using pulsed eddy current (PEC) non-destructive testing (NDT) technique in the quantification of the inclination and depth of inclined cracks. The image-based feature extraction technique effectively identifies the crack axis, which consequently enables extraction of features from the extracted linear scans. The technique extracts linear scans from the images to allow the extraction of three novel image-based features, namely the length of extracted linear scans (LLS), the linear scan skewness (LSS), and the highest value on linear scan (LSmax). The correlation of the three features to surface crack inclination angles and depths were analysed and found to be highly dependent on the crack depths, while only LLS and LSS are correlated to the crack inclination angles. © 2019, The Author(s).
format	Article
author	Nafiah, Faris Sophian, Ali Khan, Md. Raisuddin Abdul Hamid, Syamsul Bahrin Zainal Abidin, Ilham Mukriz
author_facet	Nafiah, Faris Sophian, Ali Khan, Md. Raisuddin Abdul Hamid, Syamsul Bahrin Zainal Abidin, Ilham Mukriz
author_sort	Nafiah, Faris
title	Image-based feature extraction technique for inclined crack quantification using pulsed eddy current
title_short	Image-based feature extraction technique for inclined crack quantification using pulsed eddy current
title_full	Image-based feature extraction technique for inclined crack quantification using pulsed eddy current
title_fullStr	Image-based feature extraction technique for inclined crack quantification using pulsed eddy current
title_full_unstemmed	Image-based feature extraction technique for inclined crack quantification using pulsed eddy current
title_sort	image-based feature extraction technique for inclined crack quantification using pulsed eddy current
publisher	Chinese Mechanical Engineering Society
publishDate	2019
url	http://irep.iium.edu.my/79655/ http://irep.iium.edu.my/79655/ http://irep.iium.edu.my/79655/ http://irep.iium.edu.my/79655/1/79655_Image-Based%20Feature%20Extraction.pdf http://irep.iium.edu.my/79655/2/79655_Image-Based%20Feature%20Extraction_SCOPUS.pdf http://irep.iium.edu.my/79655/3/79655_Image-Based%20Feature%20Extraction_WOS.pdf
first_indexed	2023-09-18T21:51:39Z
last_indexed	2023-09-18T21:51:39Z
_version_	1777413809311318016

Image-based feature extraction technique for inclined crack quantification using pulsed eddy current

Similar Items