• 한국방재학회:학술대회논문집
• /
• 2008.02a
• /
• pp.573-576
• /
• 2008

절토사면 및 천심도 터널의 경우 불연속면을 따른 블록의 미끄러짐 및 회전 등이 안정성에 큰 영향을 미친다. 국도나 지방도 등을 확장 공사함에 따라 산악이 많은 우리나라 지형의 특성상 절토사면이 많이 발생하게 되고, 경우에 따라서는 이러한 절토사면에 터널이 위치하게 된다. 이런 상황의 터널갱구부 및 인접한 절토사면부에서 붕괴 및 균열이 빈번하게 발생되고 있다. 본 연구에서는 대절토사면과 인접한 터널갱구부에 대하여 편토압이 균열의 주원인인지를 결정하기 위하여 변위 및 응력 패턴을 분석한 사례연구를 제시하였다. 조사대상지역은 울진군에 위치한 터널굴진 현장이고, 붕괴는 터널갱구부와 인접한 절토사면부에서 발생하였으며 터널갱구부 상단의 숏크리트 타설지역에서 다수의 균열이 관찰되었다. 언급한 터널갱구부의 변위 및 응력패턴을 모사하기 위하여 유한차분법에 근거한 플랙을 사용하였으며, 세밀한 수치해석을 위해 편재절리모델을 도입하였다. 마지막으로, 터널갱구부의 균열에 영향을 미친 주원인에 대한 고찰을 다루었다.

• 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.

• Journal of The Geomorphological Association of Korea
• /
• v.19 no.2
• /
• pp.145-159
• /
• 2012

Fracture patterns observed in the phyllosilicate-bearing layers of the Mawrth Vallis region are analyzed using High Resolution Imaging Science Experiment image data in order to understand the causes of polygonal fracturing. HiRISE data show that the different mineralogies have distinct surface textures and morphologies. The majority of the nontronite-bearing rocks typically appear to have been heavily eroded and are fractured into irregular shaped blocks with variable size, whereas most of the montmorillonite-bearing rocks have polygons which are relatively consistent in size and shape. The majority of the fracture patterns observed in the nontronite-bearing outcrops are interpreted to be a result of unloading stresses. While the polygonal fractures developed in the montmorillonite-bearing layers appear to be a product of desiccation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.125-137
• /
• 2009

Acoustic emission-based techniques are being used for the nondestructive inspection of mechanical systems used in service. For reliable fault monitoring related to the crack growth, it is important to identify the dynamical characteristics as well as transient crack-related signals. Widely used methods which are based on physical phenomena of the three damage stages for detecting the crack growth have a problem that crack-related acoustic emission activities overlap in time, therefore it is insufficient to estimate the exact crack growth time. The proposed pattern recognition method uses the dynamical characteristics of acoustic emission as inputs for minimizing false alarms and miss alarms and performs the temporal clustering to estimate the crack growth time accurately. Experimental results show that the proposed method is effective for practical use because of its robustness to changes of acoustic emission caused by changes of pressure levels.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.13 no.2
• /
• pp.135-139
• /
• 1993

It was found in a series of test sections constructed in Houston, Texas that (1) concrete placement in hot season resulted in much more early-age cracks than that in cool season, and that, (2) for the hot season placement, pavements placed in the morning showed more early-age cracks than those placed in the afternoon. Early-age cracks, in this study, are defined as cracks occurring within a few days after construction. Since the early-age cracks have a tendency to be meandering and the crack widths are relatively wide, they may give an adverse effect on the long-term performance of the pavement. The objectives of this study are to recognize the effects of placement time on the early-age crack patterns and to find the reason of the effects. The effects are explained in this study by relating hydration of cement and surrounding temperature conditions.

• Journal of the Korean Society for Railway
• /
• v.20 no.3
• /
• pp.374-381
• /
• 2017

Concrete sleepers, installed on majority of railroad track in this nation can, if not maintained properly, threaten the safety of running trains. In this paper, an algorithm for automatically identifying cracks in a sleeper image, taken by high-resolution camera, is developed based on Adaboost, known as the strongest adaptive algorithm and most actively utilized algorithm of current days. The developed algorithm is trained using crack characteristics drawn from the analysis results of crack and non-crack images of field-installed sleepers. The applicability of the developed algorithm is verified using 48 images utilized in the training process and 11 images not used in the process. The verification results show that cracks in all the sleeper images can be successfully identified with an identification rate greater than 90%, and that the developed automatic crack identification algorithm therefore has sufficient applicability.

• Journal of the Korean Society for Railway
• /
• v.17 no.4
• /
• pp.270-280
• /
• 2014

In this study, to examine the causes of cracks in continuously reinforced concrete tracks (CRCTs) and the main factors affecting cracking, a field survey on the status of cracks and crack patterns in the Gyeong-bu high speed line was conducted, and the crack patterns of CRCT due to the temperature difference between the top of the slab (TCL) and the bottom of the subbase (HSB) and the drying shrinkage of concrete were predicted by a nonlinear finite element model considering the structure of CRCT. The results of the numerical analysis show that cracks will be developed at the interface between the sleeper and the TCL, and under the sleeper due to the temperature difference and concrete shrinkage. This corresponds well to the crack locations found in the field. Also, it is found that the most significant factors are the coefficient of thermal expansion with respect to the temperature difference, and the drying shrinkage strain with respect to shrinkage. According to the results, the reinforcement ratio should be carefully determined considering the structures of CRCT because the crack spacing is not always proportional to the reinforcement ratio due to the sleepers embedded in the TCL.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.377-380
• /
• 2023

본 논문에서는 합성곱 신경망(Convolutional Neural Networks, CNN)과 탄성왜곡(Elastic Distortion) 기법을 통한 데이터 증강 기법을 활용하여 학습 데이터를 구축하는 프레임워크를 제안한다. 실제 균열 이미지는 정형화된 형태가 없고 복잡한 패턴을 지니고 있어 구하기 어려울 뿐만 아니라, 데이터를 확보할 때 위험한 상황에 노출될 우려가 있다. 이러한 데이터베이스 구축 문제점을 본 논문에서 제안하는 데이터 증강 기법을 통해 비용적, 시간적 측면에서 효율적으로 해결한다. 세부적으로는 DeepCrack의 데이터를 10배 이상 증가하여 실제 균열의 특징을 반영한 메타 데이터를 생성하여 U-net을 학습하였다. 성능을 검증하기 위해 균열 탐지 연구를 진행한 결과, IoU 정확도가 향상되었음을 확인하였다. 데이터를 증강하지 않았을 경우 잘못 예측(FP)된 경우의 비율이 약 25%였으나, 데이터 증강을 통해 3%까지 감소하였음을 확인하였다.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.3 s.151
• /
• pp.378-385
• /
• 2006

To release fashion trends in an efficient way, many of the apparel business and fashion educational institutes in land adopt fashion shows employing fashion models. Modeling rather than flat pattern making realizes the majority of the complicated design works for the fashion shows. However, for the different measurements between the dress form and the real human model, problems often occur during the modeling and fitting processes. Researches on the standard dress form development representing professional fashion models' features are therefore in urgent need to enable the related apparel business and fashion institutes to make appropriate use of the dress form in their jobs. The study has been conducted as a preliminary study using a questionnaire method ultimately to develop the female dress form. A questionnaire in the research aimed at an investigation into the actual conditions of and satisfaction with the usage and the body measurements of existed dress forms. Approximately 30 fashion-related educational institutes and 10 apparel companies responded to the survey. Data derived from the survey was analyzed using SPSS version 10.1, the statistics tool. The results throughout the research were discussed in terms of largely three categories that are; (1) the general conditions of the usage of the dress form to prepare fashion shows: e.g. the frequency of holding the fashion show in an annual term, the proportion of professional and amateur models employed for the fashion show, the methods to construct garments, types and number of dress forms utilized and etc.; (2) factors considered to purchase the dress form e.g. its functionality, shapes, sizes, duration, price, A/S condition and etc.; and(3) satisfaction with the similarity between the dress form and the human body in the relation to the body measurements. Measurements in length wise, front and back waist lengths, neck to bust point on the dress forms were apparently differed from the ones of the actual body. In particular, differed torso length measurements cause the problem to have to alter the whole silhouette, consequently, the resultant patterns as well. In girth measurements, in order of bust and waist girths, the satisfaction was low.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.2
• /
• pp.200-207
• /
• 2021

The purpose of this study is to investigate experimentally the effects of type of superplasticizer on tensile behavior and cracking pattern of alkali-activated slag-based cementless composite. Three mixtures were prepared according to type of superplasticizer, and the compressive strength and tension tests were performed. Test results showed that differences of tensile strength, tensile strain capacity, and toughness of composites were up to 28.1%, 39.1%, and 66.2%, respectively, according to type of superplasticizer, although fiber balling or poor dispersion of fibers in fresh composites was not observed. It was also observed that the type of superplasticizer influenced number of cracks and maximum fiber bridging stress.