1 June 2024 in Glass Structures & Engineering
Fracture morphology characterization in broken glass panes is crucial for designing laminated safety glass (LSG) in civil engineering. Verifying completely broken LSG systems requires destructive sampling, increasing costs and hindering development. Therefore, to determine the residual load-bearing capacity, the link between the pre-fracture characteristics and the fracture morphology must be known. However, when the crack propagation needs to be directly captured with high-speed imaging, conventional methods are no longer sufficient for detecting cracks. To enable such investigations, we propose a novel machine learning framework for crack segmentation in high-speed imaging that addresses the complexity of glass fracture and minimises the required labour costs. In this study, the crack propagation of a sample was recorded and analysed at 2,000,000 images per second. The results showcase accuracies surpassing 97% while requiring only two labeled images for training, thus streamlining practical implementation. Furthermore, we show the method's robustness to the extent that hyperparameter tuning becomes unnecessary. Instead, we offer guidelines for selecting the most crucial hyperparameters depending on the problem. Our method offers a promising approach for non-linear temporal interpolation of noisy images, with implications for various applications extending beyond glass fracture analysis.
1 June 2026 in Engineering Fracture Mechanics
30 May 2026 in Engineering Fracture Mechanics
6 April 2026 in SSRN Electronic Journal
This paper presents an experimental investigation of fracture patterns in fully toughened glass plates of 4 mm and 8 mm thickness across surface compressive pre-stress levels of 88 MPa to 158 MPa under three different support conditions and, thereby, extends the current state of knowledge into the high pre-stress domain. Complete fracture patterns are digitized using a computer vision framework and analyzed with respect to fragment density, base area, perimeter and spatial intensity distribution. Alongside conventional, two-dimensional fracture analysis, three-dimensional fracture surface morphology is characterized using the fractal dimension obtained from CT scans via box-counting. The experimental results are compared to erosion-based type of numerical simulations of the fragmentation process. Our findings show that at higher energy levels, the fragment base area and perimeter exhibit diminishing rates of decrease. Moreover, at high energies, the fractal dimension of fracture surfaces increases, indicating that an increasing amount of strain energy is dissipated into fracture surface roughness rather than macroscopic crack length.