• Journal of the Korean Geotechnical Society
• /
• v.34 no.12
• /
• pp.145-154
• /
• 2018

The damage investigation and inspection methods performed in concrete facilities such as bridges, tunnels, retaining walls and so on, are usually visually examined by the inspector using the surveying tool in the field. These methods highly depend on the subjectivity of the inspector, which may reduce the objectivity and reliability of the record. Therefore, the new image processing techniques are necessary in order to automatically detect the cracks and objectively analyze the characteristics of cracks. In this study, deep learning and image processing technique were developed to detect cracks and analyze characteristics in images for concrete facilities. Two-stage image processing pipeline was proposed to obtain crack segmentation and its characteristics. The performance of the method was tested using various crack images with a label and the results showed over 90% of accuracy on crack classification and segmentation. Finally, the crack characteristics (length and thickness) of the crack image pictured from the field were analyzed, and the performance of the developed technique was verified by comparing the actual measured values and errors.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.2
• /
• pp.36-44
• /
• 2024

This paper presents the application of Convolutional Neural Networks (CNNs) and Region of Interest (ROI) techniques for concrete crack analysis. Surfaces of concrete structures, such as beams, etc., are exposed to fatigue stress and cyclic loads, typically resulting in the initiation of cracks at a microscopic level on the structure's surface. Early detection enables preventative measures to mitigate potential damage and failures. Conventional manual inspections often yield subpar results, especially for large-scale infrastructure where access is challenging and detecting cracks can be difficult. This paper presents data collection, edge segmentation and ROI techniques application, and analysis of concrete cracks using Convolutional Neural Networks. This paper aims to achieve the following objectives: Firstly, achieving improved accuracy in crack detection using image-based technology compared to traditional manual inspection methods. Secondly, developing an algorithm that utilizes enhanced Sobel edge segmentation and ROI techniques. The algorithm provides automated crack detection capabilities for non-destructive testing.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.263-266
• /
• 2004

본 논문에서는 터널 구조물에서 발생하는 균열의 인식과 이에 대한 정보를 획득하기 위한 방법에 대한 연구를 수행하였다. 터널 구조물에서 발생하는 균열의 경우, 건설 분야의 특수성 때문에 기존의 경계점 인식(edge detection) 알고리즘을 적용하는 경우 정밀도 저하의 문제가 발생한다. 이러한 문제점을 해결하고 더불어 정밀도를 향상시킬 수 있는 방법으로 영상에서 균열을 인식하는 균열 인식 단계와 인식된 균열의 길이, 두께 등을 측정하는 균열 정보 획득 단계로 구분하였다. 균열 인식 단계에서는 균열의 시작점과 끝점을 기준으로 휴리스틱(Heuristic) 알고리즘을 사용하여 픽셀 값의 분포에 따라 균열의 중심선을 계산하여 균열을 인식한다. 균열 정보 획득 단계에서는 균열 인식 단계에서 얻은 정보를 통해 균열의 길이, 진행 방향 정보, 그리고 균열의 두께를 계산한다. 균열의 길이 및 진행 방향 정보는 균열 인식 단계에서 얻어진 정보를 통하여 계산하며, 균열 두께 측정은 각 픽셀의 누적 값을 이용하여 계산하는 원형 검출기(Daugman 알고리즘)를 변형하여 사용하였다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.5
• /
• pp.345-355
• /
• 2023

An analysis of covariance and Pearson correlation coefficient were performed to identify the relationship between both variables: traffic volume and crack. For this, it was carried out to analyse 216 tunnel inspection/diagnosis results with respect to the traffic. As a result, it has been proven that traffic volume and cracks in concrete linings are highly correlated. Therefore, it is recommended to consider traffic volume in planning of preemptive maintenance such as crack repair, etc.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.3
• /
• pp.617-623
• /
• 1990

Cracks present in pressure vessels have been reported to be mostly semi-elliptic surface cracks. The fatigue crack growth rates(FCGR) of surface cracks in the pressure vessel materials, API5A-K55 and SPV 500, used in this study were showed to be different depending on the direction of propagation of the surface crack. An equation for the prediction of the shape change of the surface crack was obtained by combining the Paris' relations for each direction of surface crack extension and agreed well with the experimental data. And also FGGR in both materials were evaluated and prediction of the shape change of surface crack were made using averaged stress intensity factor.

• The Journal of Engineering Geology
• /
• v.8 no.3
• /
• pp.275-284
• /
• 1998

Deformation behavior and microcrack development due to uniaxial compressive cyclic loading in the Pocheon granite were investigated using the ultrasonic velocity measurements and the differential strain analysis(DSA). Most microcracks were developed along the direction parallel to the loading axis. Microcracks developed at the early stage of cyclic loading were formed by propagation of pre-existing cracks. Ultrasonic velocity measurement, DSA and measurement of permanent deformation are good tools to represent microcrack development in rock. Since results from each method are slightly different, microcrack development should be interpreted from all three methods. The magnitude of microcracks developed at the early stage of cyclic loading under 80% loading level is twice compared with those under 70% loading level. The highest volumetric crack strain is about 3000, indicating that the Pocheon granite will fail with 0.3% occupation of microcrack in volume.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.8
• /
• pp.17-28
• /
• 2023

Laboratory-scale hydraulic fracturing experiments were conducted on granite specimens at various viscosities and injection rates of the fracturing fluid. A series of cross-sectional computed tomography (CT) images of fractured specimens was obtained via a three-dimensional X-ray CT imaging method. Pixel-level fracture segmentation of the CT images was conducted using a convolutional neural network (CNN)-based Nested U-Net model structure. Compared with traditional image processing methods, the CNN-based model showed a better performance in the extraction of thin and complex fractures. These extracted fractures extracted were reconstructed in three dimensions and morphologically analyzed based on their fracture volume, aperture, tortuosity, and surface roughness. The fracture volume and aperture increased with the increase in viscosity of the fracturing fluid, while the tortuosity and roughness of the fracture surface decreased. The findings also confirmed the anisotropic tortuosity and roughness of the fracture surface. In this study, a CNN-based model was used to perform accurate fracture segmentation, and quantitative analysis of hydraulic stimulated fractures was conducted successfully.

• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.1068-1077
• /
• 2007

This paper proposes a method that extracts characteristics of cracks such as length, thickness and direction from a concrete slab surface image with image processing techniques. These techniques extract the cracks from the concrete surface image in variable conditions including bad image conditions) using the ART2-based RBF network to recognize the dominant directions -45 degree, 45 degree, horizontal and vertical) of the extracted cracks from the automatically calculated specifications like the lengths, directions and widths of the cracks. Our proposed extraction algorithms and analysis of the concrete cracks used a Robert operation to emphasize the cracks, and a Multiple operation to increase the difference in brightness between the cracks and background. After these treatments, the cracks can be extracted from the image by using an iterated binarization technique. Noise reduction techniques are used three separate times on this binarized image, and the specifications of the cracks are extracted form this noiseless image. The dominant directions can be recognized by using the ART2-based RBF network. In this method, the ART2 is used between the input layer and the middle layer to learn, and the Delta learning method is used between the middle layer and the output layer. The experiments using real concrete images showed that the cracks were effectively extracted, and the Proposed ART2-based RBF network effectively recognized the directions of the extracted cracks.

• Journal of Ocean Engineering and Technology
• /
• v.3 no.2
• /
• pp.87-100
• /
• 1989

해양구조물의 원통형 조인트에 대한 파괴역학적 피로수명 산출방법이 개발되었다. 개발된 방법을 이용해서 2평면 K형 조인트에 대한 피로수명을 구체적인 파괴역학적 방법으로 산출 하였다. 이 분석을 위해 용접부위 표면균열의 응력확대 계수를 3차원 유한요소법에 의해 계산하였다. 계산된 결과에 의하면 용접부위 표면균열 첨단은 단순한 Mode I형태를 보이지 않고 Mode I, II, III이 복합된 형태임이 입증되었다. 계산된 응력확대 계수를 사용해서 16개의 용접부위균열 성장형태를 일반적인 피로균열 성장법칙을 적용해서 계산하였고, 균열성장의 안정분석을 통해 각 균열의 최종 파괴상태를 파괴해석도면(failure assessment diagram)법을 이용해서 계산하였다.

• International Journal of Highway Engineering
• /
• v.9 no.2 s.32
• /
• pp.39-49
• /
• 2007

The objective of this study was to investigate features of transverse crack occurrence and propagation in continuously reinforced concrete pavement(CRCP) when subjected to environmental loading. The finite element model of CRCP was developed and the element removal method was implemented to predict the crack propagation process. To investigate the effect of the type of environmental loading on the CRCP behavior and cracking aspects, the following three different cases were considered: (1) the temperature gradient between top and bottom of the slab does not vary and the constant temperature drop throughout the depth occurs; (2) the temperature at the slab bottom does not vary and the temperature gradient increases; and (3) the temperature between the mid-depth and the bottom of the slab is the same and does not vary and the temperature at the top decreases. The analysis results showed that the crack occurrence and propagation through the depth of the slab in CRCP were significantly affected by the type of environmental loading. The changes in stress distribution and displacements during the crack occurrence and propagation process could also be investigated.