Pattern recognition of barely visible impact damage in carbon composites using pulsed thermography

Simple item page
dc.contributor.authorZhou, Jia
dc.contributor.authorDu, Weixiang
dc.contributor.authorYang, Lichao
dc.contributor.authorDeng, Kailun
dc.contributor.authorAddepalli, Sri
dc.contributor.authorZhao, Yifan
dc.date.accessioned2021-12-22T09:28:24Z
dc.date.available2021-12-22T09:28:24Z
dc.date.issued2021-12-13
dc.description.abstractThis paper proposes a novel framework to characterise the morphological pattern of Barely Visible Impact Damage using machine learning. Initially, a sequence of image processing methods are introduced to extract the damage contour, which is then described by a Fourier descriptor-based filter. The uncertainty associated with the damage contour under the same impact energy level is then investigated. A variety of geometric features of the contour are extracted to develop an AI model, which effectively groups the tested 100 samples impacted by 5 different impact energy levels with an accuracy of 96%. Predictive polynomial models are finally established to link the impact energy to the three selected features. It is found that the major axis length of the damage has the best prediction performance, with an R2 value up to 0.97. Additionally, impact damage caused by low energy exhibits higher uncertainty than that of high energy, indicating lower predictability.en_UK
dc.description.sponsorshipEngineering and Physical Sciences Research Council (Grant Number: EP/P027121/1)en_UK
dc.identifier.citationZhou J, Du W, Yang L, et al., (2022) Pattern recognition of barely visible impact damage in carbon composites using pulsed thermography, IEEE Transactions on Industrial Informatics, Volume 18, Number 10, October 2022, pp. 7252-7261en_UK
dc.identifier.eissn1941-0050
dc.identifier.issn1551-3203
dc.identifier.urihttps://doi.org/10.1109/TII.2021.3134184
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/17349
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectNDTen_UK
dc.subjectImage processingen_UK
dc.subjectFeature extractionen_UK
dc.subjectArtificial intelligenceen_UK
dc.subjectCFRPen_UK
dc.titlePattern recognition of barely visible impact damage in carbon composites using pulsed thermographyen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Impact_Damage_in_Carbon_Composites-2021.pdf
Size:
4.11 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)