Segmentation of cracks in 3d images of fiber reinforced concrete using deep learning

TL;DR

This paper presents a 3D deep learning approach using a modified U-Net to accurately segment cracks in computed tomography images of fiber reinforced concrete, enabling better structural analysis without destructive testing.

Contribution

The study adapts a 3D U-Net for crack segmentation in CT images and demonstrates its effectiveness on both synthetic and real concrete samples.

Findings

Successful training on semi-synthetic data improves real crack detection.

The method accurately segments cracks in diverse concrete types.

Deep learning enhances non-destructive structural analysis.

Abstract

Cracks in concrete structures are very common and 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. Computed tomography enables looking into the sample without interfering 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. We adapted a 3d version of the well-known U-Net and trained it on semi-synthetic 3d images of real concrete samples equipped with simulated crack structures. Here, we explain the general approach. Moreover, we show how to teach the network to detect also real crack systems in 3d images of varying types of real concrete, in particular of fiber reinforced concrete.