• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.2
• /
• pp.173-182
• /
• 2007

Cracks in concrete structures should be measured to periodically assess potential problems in durability and serviceability. Conventional crack measurement systems depend on visual inspections and manual measurements of the crack features such as width, length, and direction using microscope and crack gage. However, conventional methods take long time as well as manpower, and lack quantitative objectivity resulted by inspectors. In this study, an evaluation technique for concrete surface cracks is developed using image processing and artificial neural network. Developed technique consists of three major parts: (1) crack detection (2) crack analysis and (3) pattern recognition. To examine validity of the technique developed in this study, crack analyzing tests were performed on the images obtained from various types of concrete surface cracks. The test results revealed that the system is highly effective in automatically analyzing concrete surface cracks in terms of features and patterns of cracks.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.1
• /
• pp.80-90
• /
• 2001

The aim of this study is to develop the methodology which enables to identify the mechanical properties of element such as stress intensity factor by using the AE parameters. Considering the multivariate and nonlinear properties of AE parameters such as ringdown count, rise time, energy, event duration and peak amplitude from fatigue cracks of machine element the principal component regression(PCR) and artificial neural network(ANN) models for the estimation of stress intensity factor were developed and validated. The AE parameters were found to be very significant to estimate the stress intensity factor. Since the statistical values including correlation coefficients, standard mr of calibration, standard error of prediction and bias were stable, the PCR and ANN models for stress intensity factor were very robust. The performance of ANN model for unknown data of stress intensity factor was better than that of PCR model.

• 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.

• Tunnel and Underground Space
• /
• v.13 no.6
• /
• pp.465-475
• /
• 2003

Groundwater inflow into the caverns constructed in fractured rock mass was simulated by numerical modeling, NAPSAC (DFN, discrete fracture network model) and NAMMU (CPM, continuous porous media model), a finite-element software package for groundwater flow in 3D fractured media developed by AEA Technology, UK. The input parameters for modeling were determined on surface fracture survey, core logging and single hole hydraulic test data. In order to predict the groundwater inflow more accurately, the anisotropic hydraulic conductivity was considered. The anisotropic hydraulic conductivities were calculated from the fracture network properties. With a minor adjustment during model calibration, the numerical modeling is able to reproduce reasonably groundwater inflows into cavern and the travel length and times to the ground surface along the flow paths in the normal, dry and rainy seasons.

• Tunnel and Underground Space
• /
• v.11 no.1
• /
• pp.42-58
• /
• 2001

In order to protect the environment from waste disposal activities, the prediction of the flux and flow paths of the contaminants from underground facilities should be assessed as accurately as possible. Especially, the prediction of the pathways and travel times of the nuclides from high level radioactive wastes in a deep repository to biosphere is one of the primary tasks for assessing the ultimate safety and performance of the repository. Since the contaminants are mainly transported with groundwater along the discontinuities developed within rock mass, the characteristics of groundwater flow through discontinuities is important for the prediction of contaminant fates as well as safety assessment of a repository. In this study, the actual fracture network could be effectively generated based on in situ data by separating geometric parameter and hydraulic parameter. The calculated anisotropic hydraulic conductivity was applied to a 3D porous medium model to calculate the path flow and travel time of the large studied area with the consideration of the complex topology in the area. Using the model, the pathways and travel times for groundwater were analyzed. From this study, it was concluded that the suggested techniques and procedures for predicting the pathways and travel times of groundwater from underground facilities to biosphere is acceptable and those can be applied to the safety assessment of a repository for radioactive wastes.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 1998.11a
• /
• pp.127-130
• /
• 1998

이 연구에서는 부정류의 판상체 이중공극 프랙탈 모델과 입방체 이중공극 프랙탈 모델의 지하수위 거동을 비교 연구하였다. 균열내 지하수위 거동 해석은 판상 이중공극 프랙탈 모델은 Hmm과 Bidaux(1996)을 이용하였고 입방체 이중공극 프랙탈 모델의 경우에는 입방체블록과 같은 크기의 구상체 블록으로 간주하여 지하수위 거동을 해석하였다. 그리고 0.5, 1, 1.5, 2, 2.5, 3차원에 대해서 판상체 이중공극 프랙탈 모델과 입방체 이중공극 프랙탈 모델의 이론적인 수위강하 곡선을 작성하여 비교, 분석하였다. 부정류의 판상체 이중공극 프랙탈 모델과 입방체 이중공극 프랙탈 모델은 기반암내 균열의 분포가 프랙탈망을 형성하고, 균열과 매트릭스 블록이 거의 수평의 층상으로 발달하는 경우와 균열이 수평방향과 수직방향으로 발달하면서 매트릭스 블록이 입방체를 이루는 경우에 적용될 수 있다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.29 no.2
• /
• pp.201-208
• /
• 2016

Recently, extensive research on crack analysis using extended finite element method(XFEM) which has main advantages in element re-meshing and visualization of cracks has been conducted. However, its application was restricted to the members of a single material. In this study, the applicability and feasibility of the XFEM to the multiple crack analysis of reinforced concrete beams were demonstrated. ABAQUS which has implemented XFEM was used for the crack analysis and its results were compared with test results. Enriched degree-of-freedom locking phenomenon was discovered and its causes and the ways to prevent it were suggested. The locking occurs when cracks in the adjacent elements simultaneously develop. A modelling technique for multiple cracking similar to test results was also proposed. The analysis with XFEM showed similar results to the tests in terms of crack patterns, spacing of cracks, and load-deflection relationship.

• 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.

• Tunnel and Underground Space
• /
• v.26 no.4
• /
• pp.327-337
• /
• 2016

In this study, laboratory hydraulic fracturing tests are carried out to evaluate the effects of the cleavage anisotropy of Pocheon granite. Breakdown pressure is smaller when cracks are generated to the direction of rift plane in constant pressurization rate condition because of higher microcracks density. Besides not only injection rate changes but also the amount of injection pressure for fracture initiation and crack expansion is detected while testing due to internal deformation. Pressurization rate is higher while hydraulic fracture testing with constant injection rate condition in case of the specimen which has rift plane perpendicular to borehole because there are much flow paths to penetrate compared to the specimen which has hardway plane perpendicular to borehole. Observation by X-ray CT scanning shows that almost all of cracks due to hydraulic fracturing are generated to the direction of plane which has higher microcrack density that is rift plane or grain plane.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.