Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization

Cracks in concrete structures are an integral part of this heterogeneous material. Characteristics of cracks induced by standardized tests yield valuable information about the tested concrete formulation and its mechanical properties. Observing cracks on the surface of the concrete structure leaves...

Full description

Saved in:
Bibliographic Details
Main Authors: Anna Nowacka, Katja Schladitz, Szymon Grzesiak, Matthias Pahn
Format: Article
Language:English
Published: Pouyan Press 2025-04-01
Series:Journal of Soft Computing in Civil Engineering
Subjects:
Online Access:https://www.jsoftcivil.com/article_199726_dae9514bcc90cf041060314fbff65fb4.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849411667202408448
author Anna Nowacka
Katja Schladitz
Szymon Grzesiak
Matthias Pahn
author_facet Anna Nowacka
Katja Schladitz
Szymon Grzesiak
Matthias Pahn
author_sort Anna Nowacka
collection DOAJ
description Cracks in concrete structures are an integral part of this heterogeneous material. Characteristics of cracks induced by standardized tests yield valuable information about the tested concrete formulation and its mechanical properties. Observing cracks on the surface of the concrete structure leaves a wealth of structural information unused, since a crack in concrete is rarely a planar structure but rather spatial. Computed tomography enables looking into the sample without interfering with or destroying the microstructure. The reconstructed tomographic images are 3d images, consisting of voxels whose gray values represent local X-ray absorption. In order to identify voxels belonging to the crack, so to segment the crack structure in the images, appropriate algorithms need to be developed. Convolutional neural networks are known to solve this type of task very well given enough and consistent training data. However, fiber reinforced concrete has not been widely analyzed in the literature, since it is hard to obtain segmented cracks excluding the fibers. We overcome this problem by adapting a 3d version of the well-known U-Net and training it on semi-synthetic 3d images of real concrete samples equipped with simulated cracks. We thus lay the foundations for large experimental quantitative studies of 3d crack initiation and development in various types of concrete.
format Article
id doaj-art-dc7dc2bd492a43ee8b1d3a4077dde477
institution Kabale University
issn 2588-2872
language English
publishDate 2025-04-01
publisher Pouyan Press
record_format Article
series Journal of Soft Computing in Civil Engineering
spelling doaj-art-dc7dc2bd492a43ee8b1d3a4077dde4772025-08-20T03:34:42ZengPouyan PressJournal of Soft Computing in Civil Engineering2588-28722025-04-0192568310.22115/scce.2024.414873.1712199726Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based CharacterizationAnna Nowacka0Katja Schladitz1Szymon Grzesiak2Matthias Pahn3M.Sc., Department of Image Processing, Fraunhofer ITWM, Kaiserslautern, GermanyDr., Department of Image Processing, Fraunhofer ITWM, Kaiserslautern, GermanyM.Sc., Department of Civil Engineering, RPTU, Kaiserslautern, GermanyProf. Dr.-Ing., Department of Civil Engineering, RPTU, Kaiserslautern, Germany, MatthiasCracks in concrete structures are an integral part of this heterogeneous material. Characteristics of cracks induced by standardized tests yield valuable information about the tested concrete formulation and its mechanical properties. Observing cracks on the surface of the concrete structure leaves a wealth of structural information unused, since a crack in concrete is rarely a planar structure but rather spatial. Computed tomography enables looking into the sample without interfering with or destroying the microstructure. The reconstructed tomographic images are 3d images, consisting of voxels whose gray values represent local X-ray absorption. In order to identify voxels belonging to the crack, so to segment the crack structure in the images, appropriate algorithms need to be developed. Convolutional neural networks are known to solve this type of task very well given enough and consistent training data. However, fiber reinforced concrete has not been widely analyzed in the literature, since it is hard to obtain segmented cracks excluding the fibers. We overcome this problem by adapting a 3d version of the well-known U-Net and training it on semi-synthetic 3d images of real concrete samples equipped with simulated cracks. We thus lay the foundations for large experimental quantitative studies of 3d crack initiation and development in various types of concrete.https://www.jsoftcivil.com/article_199726_dae9514bcc90cf041060314fbff65fb4.pdf3d computed tomography3d semantic segmentationdeep learningsupervised learningmulti-scale methodsstructural concrete
spellingShingle Anna Nowacka
Katja Schladitz
Szymon Grzesiak
Matthias Pahn
Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization
Journal of Soft Computing in Civil Engineering
3d computed tomography
3d semantic segmentation
deep learning
supervised learning
multi-scale methods
structural concrete
title Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization
title_full Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization
title_fullStr Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization
title_full_unstemmed Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization
title_short Segmentation of Spatial Crack Structures in Concrete by Deep Learning Enabling Image Based Characterization
title_sort segmentation of spatial crack structures in concrete by deep learning enabling image based characterization
topic 3d computed tomography
3d semantic segmentation
deep learning
supervised learning
multi-scale methods
structural concrete
url https://www.jsoftcivil.com/article_199726_dae9514bcc90cf041060314fbff65fb4.pdf
work_keys_str_mv AT annanowacka segmentationofspatialcrackstructuresinconcretebydeeplearningenablingimagebasedcharacterization
AT katjaschladitz segmentationofspatialcrackstructuresinconcretebydeeplearningenablingimagebasedcharacterization
AT szymongrzesiak segmentationofspatialcrackstructuresinconcretebydeeplearningenablingimagebasedcharacterization
AT matthiaspahn segmentationofspatialcrackstructuresinconcretebydeeplearningenablingimagebasedcharacterization