• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.197-207
• /
• 2023

Concrete is a widely used material due to its excellent compressive strength and durability. However, depending on the surrounding environment and the characteristics of the materials used in the construction, various defects may occur, such as cracks on the surface and subsidence of the structure. The detects on the surface of the concrete structure occur after completion or over time. Neglecting these cracks may lead to severe structural damage, necessitating regular safety inspections. Traditional visual inspections of concrete walls are labor-intensive and expensive. This research presents a deep learning-based semantic segmentation model designed to detect cracks in concrete walls. The model addresses surface defects that arise from aging, and an image augmentation technique is employed to enhance feature extraction and generalization performance. A dataset for semantic segmentation was created by combining publicly available and self-generated datasets, and notable semantic segmentation models were evaluated and tested. The model, specifically trained for concrete wall fracture detection, achieved an extraction performance of 81.4%. Moreover, a 3% performance improvement was observed when applying the developed augmentation technique.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.505-510
• /
• 2024

Since rolling contact fatigue cracks can always occur on the rail surface, which is the contact surface between wheels and rails, railway rails require thorough inspection and diagnosis to thoroughly inspect the condition of the cracks and prevent breakage. Recent detailed guidelines on the performance evaluation of track facilities present the requirements for methods and procedures for track performance evaluation. However, diagnosing and grading rail surface damage mainly relies on external inspection (visual inspection), which inevitably relies on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we conducted a deep learning model study for rail surface defect detection using Fast R-CNN. After building a dataset of rail surface defect images, the model was tested. The performance evaluation results of the deep learning model showed that mAP was 94.9%. Because Fast R-CNN has a high crack detection effect, it is believed that using this model can efficiently identify rail surface defects.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.6
• /
• pp.133-141
• /
• 2002

This paper describes a versatile finite element technique which has been used to investigate wide range of structural defects of practical importance. The procedure automatically remeshes the three-dimensional finite element model during the stages of crack growth. Problems include the surface cracks in leak-before-break situations, the shape development of multiple surface defects.

• The Journal of the Petrological Society of Korea
• /
• v.19 no.4
• /
• pp.283-292
• /
• 2010

The Suljeongri east three-story stone pagoda in Changnyeong (National Treasure No. 34) has been damaged mainly by lots of cracks. The stones used for this pagoda are medium-granied equigranular pinkish biotite granite. Measured magnetic susceptibility values are of from 2 to 9 (${\times}10^{-3}$ SI unit). From the ${\gamma}$-ray spectrometer mesurement K, eU, and eTh contents of the stones are 3 to 7%, 8 to 19 ppm, and 11 to 35 ppm, respectively. Comparing the petrographical and chemical characteristics between the stones of the pagoda and the country rocks near Suljeongri, it is suggested that the most similar rock could be equigranular biotite granite in the western slope of the Mt. Hwawangsan. Vertical, horizontal and diagonal cracks are intensely developed at the lower part of the stone pagoda. Biotite granite has intrinsic microcracks defined as rift and grain rock cleavages. Both rock cleavages are assumed to have led to the crack growth and consequent mechanical damage of the pagoda. It seems that vertical cracks have been grown parallel to the principal compressional stress, and that horizontal cracks to the reacting tensional stress. Diagonal cracks seems likely to have been resulted from conjugate rift and grain rock cleavages.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.6
• /
• pp.30-38
• /
• 2023

As the number of old buildings subject to safety inspection increases, the burden on designated institutions and management entities that are responsible for safety management is increasing. Accordingly, when selecting buildings subject to safety inspection, appropriate safety inspection standards and appropriate technology are essential. The current safety inspection standards for old buildings give low scores when it is difficult to confirm damage such as cracks in structural members due to finishing materials. This causes the evaluation results to be underestimated regardless of the actual safety status of the structure, resulting in an increase in the number of aging buildings subject to safety inspection. Accordingly, this study proposed a thermal imaging technique, a non-destructive and non-contact inspection, to detect cracks inside finishing materials. A concrete specimen was produced to observe cracks inside the finishing material using a thermal imaging camera, and thermal image data was measured by exciting a heat source on the concrete surface and cracked area. As a result of the measurement, it was confirmed that it was possible to observe cracks inside the finishing material with a width of 0.3mm, 0.5mm, and 0.7mm, but it was difficult to determine the cracks due to uneven temperature distribution due to surface peeling and peeling of the wallpaper. Accordingly, as a result of performing data analysis by deriving the amplitude and phase difference of the thermal image data, clear crack measurement was possible for 0.5mm and 0.7mm cracks. Based on this study, we hope to increase the efficiency of field application and analysis through the development of technology using big data-based deep learning in the diagnosis of internal crack damage in finishing materials.

• Tunnel and Underground Space
• /
• v.19 no.6
• /
• pp.545-557
• /
• 2009

In order to investigate dynamic damage mechanism of brittle materials, Split Hopkinson Pressure Bar (SHPB) have been adapted to apply different impact levels to rocks in South Korea. High resolution X-ray Computed Tomography (CT) was used to estimate the damage in tested rock samples nondestructively. The cracks which are parallel to the loading axis are visible on the contact surface with the incident bar under lower level of impact. The surface cracks disappeared with increment of impact level due to confined effect between the incident bar and sample, while axial splitting are happened near the outer surface.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.14 no.2
• /
• pp.112-120
• /
• 2015

In this study, the growth rate of surface cracks (da/dN) during the retardation period was analyzed in terms of effective stress intensity factor range(${\Delta}K_{eff}^*$) obtained by using the proposed effective plastic zone concept. Effective stress intensity factors obtained by using the effective plastic zone concept were smaller than those obtained by using Willenborg analysis. On the growth rate of surface cracks analyzed by ${\Delta}K$, the dependence of overload stress levels appears. On the growth rate by ${\Delta}K_{eff}$ obtained by Willenborg analysis, there is a linear relationship with two different slops between da/dN and ${\Delta}K_{eff}$. However, on the growth rate by ${\Delta}K_{eff}^*$ obtained by the proposed effective plastic zone concept, there is a linear relationship between da/dN and ${\Delta}K_{eff}^*$ that coincides with the results of constant amplitude loading.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.11
• /
• pp.2442-2449
• /
• 2002

This paper provides an reference stress based J estimation equation fur cylinders with finite internal axial surface cracks under internal pressure. In part 1, the J estimation equation based on deformation plasticity using Ramberg-Osgood (R-0) materials is proposed. In this paper, the developed CE/EPRI -type solutions ale then re-formulated based on the reference stress concept. Such a re-formulation provides a simpler equation for J. estimation are then further extended to combined internal pressure and bending. The proposed reference stress based J estimation equation is compared with elastic-plastic 3-D FE results using actual stress-strain data for a Type 304 stainless steel. Good agreement between the FE results and the proposed reference stress based J estimations provides confidence in the use of the proposed method to elastic -plastic fracture mechanics of pressurised piping.

• The Plant Pathology Journal
• /
• v.24 no.2
• /
• pp.112-117
• /
• 2008

Pre-infection behavior of Fusarium circinatum on stems of pine species was investigated with scanning electron microscopy. Two-year-old stems of Pinus densiflora and p. rigida were inoculated with the fungal conidial suspension and subjected to $25^{\circ}C$ for up to 16 hr. Most microconidia germinated 12 hr after inoculation on pine stems. Conidia produced germ tubes from either one or both ends of microconidia. Germ tubes grew over the stem surface and appeared to enter host tissues through natural openings on pine stems. Surface cracks in the cork were entrance sites of germ tubes of F. circinatum. In addition, host cell wall cracks were often found at the tip of germ tubes. The cuticle appeared to be eroded either at the tip of germ tubes or around germlings. Germ tubes also produced appressoria-like structures, exhibiting swollen tips of germ tubes on the stem surface. There seems to be no significant differences in the pre-infection behavior of F. circinatum on stems between the two pine species.

• Transactions of the Korean hydrogen and new energy society
• /
• v.14 no.4
• /
• pp.321-326
• /
• 2003

We tried to improve the $H_2$-sorption properties of Mg by mechanical grinding under $H_2$ (reactive grinding) with CoO. The sample Mg+10wt.%CoO as prepared absorbs 1.25wt.% hydrogen and the activated sample absorbs 2.39wt.% hydrogen for 60min at 598K, $11.2barH_2$. The reactive grinding of Mg with CoO increases the $H_2$-sorption rates by facilitating nueleation(by creating defects on the surface of the Mg particles and by the additive), by making cracks on the surface of Mg particles and reducing the particle size of Mg and thus by shortening the diffusion distances of hydrogen atoms. Hydriding-dehydriding cycling increases the $H_2$-sorption rates by making cracks on the surface of Mg particles and reducing the particle size of Mg.