• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.171-182
• /
• 2022

The safe use of a structure requires it to be maintained in an undamaged state. Thus, a typical factor that determines the safety of a structure is a crack in it. In addition, cracks are caused by various reasons, damage the structure in various ways, and exist in different shapes. Making matters worse, if these cracks are unattended, the risk of structural failure increases and proceeds to a catastrophe. Hence, recently, methods of checking structural damage using deep learning and computer vision technology have been introduced. These methods usually have the premise that there should be a large amount of training image data. However, the amount of training image data is always insufficient. Particularly, this insufficiency negatively affects the performance of deep learning crack detection algorithms. Hence, in this study, a method of augmenting crack image data based on the image translation technique was developed. In particular, this method obtained the crack image data for training a deep learning neural network model by transforming a specific case of a asphalt crack image into a concrete crack image or vice versa . Eventually, this method expected that a robust crack detection algorithm could be developed by increasing the diversity of its training data.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.4
• /
• pp.501-507
• /
• 2007

In the first part of this study, the moving least squares finite difference method for solving solid mechanics problems was formulated. This second part verified the accuracy, robustness and effectiveness of the developed method through several numerical examples. It was shown that the method gives excellent convergence rate for elasticity problem. The solution process of elastic crack problems showed the easiness in discontinuity modeling and demonstrates the accuracy and efficiency in finding singular stress solution based on adaptive node distribution. The applicability to the engineering problem with abrupt change in displacement and stresses gradient fields is verified through a localization band problem. The developed method is expected to be extended to the various special engineering problems.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.4
• /
• pp.306-313
• /
• 2011

The damage tolerance analysis is required to guarantee the structural safety and the reliability for aircraft components. The damage tolerance method, which evaluate the life considering the initial crack, considers a fatigue design model of the aircraft main structure. The fatigue crack growth life should be calculated in damage tolerance analysis and the inspection time to define the replacement cycle. In this paper, the damage tolerance analysis is performed for a turbine wheel which has complex geometry. The equation of the stress intensity factor for complex geometry is hard to know, so that they are usually processed by finite element analysis which takes long time. To solve this problem, the stress intensity factors at specified crack are obtained by the FEA and the crack growth life is evaluated using the surrogate model which is generated by the regression analysis of the FEA data. From the results, the efficiency of the crack growth life calculation and the damage tolerance analysis could be increased by taking the surrogate model.

• Magazine of the Korea Concrete Institute
• /
• v.7 no.4
• /
• pp.56-61
• /
• 1995

• Journal of the Korea Concrete Institute
• /
• v.14 no.1
• /
• pp.24-32
• /
• 2002

The modified compression field theory is already applied in shear problem at some code(AASHTO-1998) partly. Nominal shear strength of concrete beam is sum of the concrete shcar strength and the steel shear strength in the current design code. But Torsional moment strength of concrete is neglected in the calculation of the nominal torsional moment strength of concrete beam In the current revised code. Tensile stress of concrete strut between cracks is still in effect due to tension stiffening effect. But The tensile stresses of concrete after cracking are neglected in bending and torsion In design. The torsional behavior is similar to the shear behavior in mechanics. Therefore the torsional moment strength of concrete should be concluded in the nominal torsional moment strength of reinforced concrete beam. This paper shows that the torsional moment strength of concrete is caused by the average principal tensile stress of concrete. To verify the validity of the proposed model, the nominal torsional moment strengths according to two ACI codes (89, 99) and proposed model are compared to experimental torsional moment strengths of 55 test specimens found in literature. The nominal torsional moment strengths by the proposed model show the best results.

• Magazine of the Korea Concrete Institute
• /
• v.14 no.1
• /
• pp.49-52
• /
• 2002

종전의 경우 건축물의 기초 구조는 직접 기초 및 말뚝 기초 등이 많이 활용되었으나 최근에는 말뚝 기초의 경우 소음, 진동 등의 환경 문제가 중요시됨에 따라 대부분 매트 기초로 시공하는 경우가 많아졌다. 따라서, 기초 부분의 매트 콘크리트 시공은 환경 문제를 해결하고 건물의 하부구조를 안전하게 지탱하게 하는 역할은 만족되었지만. 두께가 80cm를 넘어 매스 콘크리트로 되는 경우가 많아 수화열에 의한 균열 문제 등은 콘크리트의 품질 확보에 있어 새롭게 해결해야만 하는 중요한 과제로 등장하고 있다.(중략)

• Journal of the Korea Concrete Institute
• /
• v.24 no.2
• /
• pp.205-214
• /
• 2012

Crack widths play an important role in the serviceability limit state. When crack widths are controlled sufficiently, the reinforcement corrosion can be reduced using only existing concrete cover thickness due to low permeability in the region of finely distributed hair-cracks. Thus, the knowledge about the tensile crack opening is essential in designing more durable concrete structures. Therefore, numerous researches related to the topic have been performed. Nevertheless accurate measurement of a crack width is not a simple task due to several reasons such as unknown potential crack formation location and crack opening damaging strain gages. In order to overcome these difficulties and measure precise crack widths, a displacement measurement system was developed using digital image correlation. Accuracy calibration tests gave an average measurement error of 0.069 pixels and a standard deviation of 0.050 pixels. Direct tensile test was performed using ultra high performance concrete specimens. Crack widths at both notched and unnotched locations were measured and compared with clip-in gages at various loading steps to obtain crack opening profile. Tensile deformation characteristics of concrete were well visualized using displacement vectors and full-field displacement contour maps. The proposed technique made it possible to measure crack widths at arbitrary locations, which is difficult with conventional gages such as clip-in gages or displacement transducers.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.7 no.2
• /
• pp.109-115
• /
• 2019

In case of the cracks in concrete, the penetration of deterioration ions such as chloride ions in to cracks is accelerated. According to the penetration of chloride ions, structural and durability problems to RC(Reinforced Concrete) structures are caused. In this study, the accelerated chloride diffusion coefficient which is in steady state is evaluated for 2 year aged normal and high strength FA(Fly Ash) concrete, after a range of crack depths are induced up to 1.0 mm in 56 aged day. Considering crack effect by linear regression analysis, high strength concrete has slightly less increasing ratio of diffusion coefficient by crack than normal strength concrete, and diffusion coefficient increases non-linearly as crack width is increased. Also, In two types of concrete, crack effect decrease as the curing period increase. In the case of quantifying crack and curing effect by using exponential function form, the coefficients of determination are higher than those of linear regression analysis. Under steady state, it is thought that there is not a high correlation between the crack effect and the curing effect, and considering the two independent effects, it is believed that reasonable prediction equation for diffusion of concrete with crack can be proposed.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.11 no.6
• /
• pp.945-952
• /
• 1987

In this paper, Crack molding method called "Teflon crack Molding Method" is developed. With help of this method, we can mold a crack which is very similar to the natural crack, which has the tip radius of about 20.mu. the vertical and horizontal quality of crack excellent. In addition to these, by using this method in photoelastic experiment we can obtain the clear crack tip location and Isochromatic fringe pattern boundary, therefore the precise in the experimental data can be improved. improved.