A crack detection model fusing local details and global context for nuclear cladding coating surfaces

Abstract Crack detection on the surface of nuclear cladding coatings is critical for ensuring the safe operation of nuclear power plants. However, due to the imbalance between crack and background pixels, complex crack morphology, numerous interfering factors, and the subtle features of fine cracks...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Quan, Xiwen Li, Jie Yang, Zhaoyu Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-16846-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226427186020352
author Wei Quan
Xiwen Li
Jie Yang
Zhaoyu Chen
author_facet Wei Quan
Xiwen Li
Jie Yang
Zhaoyu Chen
author_sort Wei Quan
collection DOAJ
description Abstract Crack detection on the surface of nuclear cladding coatings is critical for ensuring the safe operation of nuclear power plants. However, due to the imbalance between crack and background pixels, complex crack morphology, numerous interfering factors, and the subtle features of fine cracks in nuclear cladding coating surface images, the detection performance of existing methods remains unsatisfactory. To address these issues, this paper proposes a novel crack detection model for nuclear cladding coatings surfaces, named CrackCTFuse. This model effectively captures both local detailed features and global context in crack images. Additionally, a crack local feature enhancement module is designed to supplement and enhance the edge details information of cracks, and a crack feature fusion module is proposed to facilitate the effective integration of local and global features. Moreover, a multi-scale convolutional attention module based on channel segmentation is developed to aggregate multi-scale contextual information, enhance skip connections, and improve the model’s ability to perceive and represent crack features at various scales. Experiments conducted on the constructed nuclear cladding coating surfaces crack dataset demonstrate the effectiveness and accuracy of the CrackCTFuse model, achieving a MIoU of 92.70% and an F1-score of 92.54%.
format Article
id doaj-art-6c2b66c33e1f44febb7ea6dc8f63e851
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6c2b66c33e1f44febb7ea6dc8f63e8512025-08-24T11:20:23ZengNature PortfolioScientific Reports2045-23222025-08-0115111610.1038/s41598-025-16846-0A crack detection model fusing local details and global context for nuclear cladding coating surfacesWei Quan0Xiwen Li1Jie Yang2Zhaoyu Chen3School of Electrical Engineering, Southwest Jiaotong UniversitySchool of Electrical Engineering, Southwest Jiaotong UniversitySchool of Electrical Engineering, Southwest Jiaotong UniversitySchool of Electrical Engineering, Southwest Jiaotong UniversityAbstract Crack detection on the surface of nuclear cladding coatings is critical for ensuring the safe operation of nuclear power plants. However, due to the imbalance between crack and background pixels, complex crack morphology, numerous interfering factors, and the subtle features of fine cracks in nuclear cladding coating surface images, the detection performance of existing methods remains unsatisfactory. To address these issues, this paper proposes a novel crack detection model for nuclear cladding coatings surfaces, named CrackCTFuse. This model effectively captures both local detailed features and global context in crack images. Additionally, a crack local feature enhancement module is designed to supplement and enhance the edge details information of cracks, and a crack feature fusion module is proposed to facilitate the effective integration of local and global features. Moreover, a multi-scale convolutional attention module based on channel segmentation is developed to aggregate multi-scale contextual information, enhance skip connections, and improve the model’s ability to perceive and represent crack features at various scales. Experiments conducted on the constructed nuclear cladding coating surfaces crack dataset demonstrate the effectiveness and accuracy of the CrackCTFuse model, achieving a MIoU of 92.70% and an F1-score of 92.54%.https://doi.org/10.1038/s41598-025-16846-0
spellingShingle Wei Quan
Xiwen Li
Jie Yang
Zhaoyu Chen
A crack detection model fusing local details and global context for nuclear cladding coating surfaces
Scientific Reports
title A crack detection model fusing local details and global context for nuclear cladding coating surfaces
title_full A crack detection model fusing local details and global context for nuclear cladding coating surfaces
title_fullStr A crack detection model fusing local details and global context for nuclear cladding coating surfaces
title_full_unstemmed A crack detection model fusing local details and global context for nuclear cladding coating surfaces
title_short A crack detection model fusing local details and global context for nuclear cladding coating surfaces
title_sort crack detection model fusing local details and global context for nuclear cladding coating surfaces
url https://doi.org/10.1038/s41598-025-16846-0
work_keys_str_mv AT weiquan acrackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT xiwenli acrackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT jieyang acrackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT zhaoyuchen acrackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT weiquan crackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT xiwenli crackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT jieyang crackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces
AT zhaoyuchen crackdetectionmodelfusinglocaldetailsandglobalcontextfornuclearcladdingcoatingsurfaces