A machine learning-based multi-scale morphological approach for crack segmentation

Xiangkun Tian

doi:10.1111/jace.70363

A machine learning-based multi-scale morphological approach for crack segmentation

2025-11-07

0

PRE

AI

DOI：10.1111/jace.70363

Original

Original request for help

Save

Abstract

En 中文

To achieve quantitative analysis of cracks in different regions for Cf/SiC composites, this study proposes an automated, multi-scale crack segmentation and quantitative analysis framework for composites with complex backgrounds. This framework is based on the ResNet50-Unet model, which achieves accurate segmentation of fibers and matrix. In addition, adaptive grayscale thresholding combined with multi-scale morphological pore elimination effectively suppresses the influence of pseudo-cracks (defects or pores) while extracting cracks. Moreover, a KD-Tree-based crack connection algorithm module repairs micro-crack fractures, significantly improving crack connectivity. The results demonstrate that the machine learning model achieves a segmentation accuracy of 97%. Following the pore elimination process, the crack line density, area density, and average width were significantly reduced from 18.8 mm/mm2, 7.2 mm2/cm2, and 6.8 µm to 1.1 mm/mm2, 0.2 mm2/cm2, and 2.2 µm, respectively. Subsequent to the crack connection procedure, the crack line density, area density, and total crack length increased from 1.1 mm/mm2, 0.23 mm2/cm2, and 1.8 cm to 1.6 mm/mm2, 0.31 mm2/cm2, and 2.1 cm, respectively. These findings validate the effectiveness of the proposed crack extraction framework in enabling precise crack quantification and offer a novel methodology for crack analysis in ceramic matrix composites.

Keywords:

Cf/SiC composites

crack connection algorithm

crack segmentation

ResNet50-Unet

A machine learning-based multi-scale morphological approach for crack segmentation

Abstract

Journal

Organization