• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.15-22
• /
• 2020

In this study, we propose an improvement method that can create U-Net model which detect fine concrete cracks by applying a weighted loss function. Because cracks in concrete are a factor that threatens safety, it is important to periodically check the condition and take prompt initial measures. However, currently, the visual inspection is mainly used in which the inspector directly inspects and evaluates with naked eyes. This has limitations not only in terms of accuracy, but also in terms of cost, time and safety. Accordingly, technologies using deep learning is being researched so that minute cracks generated in concrete structures can be detected quickly and accurately. As a result of attempting crack detection using U-Net in this study, it was confirmed that it could not detect minute cracks. Accordingly, as a result of verifying the performance of the model trained by applying the suggested weighted loss function, a highly reliable value (Accuracy) of 99% or higher and a harmonic average (F1_Score) of 89% to 92% was derived. The performance of the learning improvement plan was verified through the results of accurately and clearly detecting cracks.

• Journal of the Korean GEO-environmental Society
• /
• v.22 no.10
• /
• pp.13-19
• /
• 2021

Cracks in asphalt pavement occur due to changes in weather or impact from vehicles, and if cracks are left unattended, the life of the pavement may be shortened, and various accidents may occur. Therefore, studies have been conducted to detect cracks through images in order to quickly detect cracks in the asphalt pavement automatically and perform maintenance activity. Recent studies adopt machine-learning models for detecting cracks in asphalt road pavement using a Convolutional Neural Network. However, their practical use is limited because they require high-performance computing power. Therefore, this paper proposes a framework for detecting cracks in asphalt road pavement by applying a small deep learning model applicable to mobile devices. The small deep learning model proposed through the case study was compared with general deep learning models, and although it was a model with relatively few parameters, it showed similar performance to general deep learning models. The developed model is expected to be embedded and used in mobile devices or IoT for crack detection in asphalt pavement.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.135-140
• /
• 2021

In this paper, we propose an on-line mechanism that simultaneously detects cracks and profiling pavement blocks to detect the displacement of ground surface adjacent to the excavation in the urban area. The proposed method utilizes a 2D laser to profile the information about pavement blocks including the depth and distance among them. In particular, it is designed to enable the detection of cracks and portholes at runtime. For the experiment, real data was collected through Gocator, and trainng was carried out using Faster R-CNN. The performance evaluation shows that our detection precision and recall are more than 90% and the pavement blocks are profiled at the same time. Our proposed mechanism can be used for monitoring management to quantitatively detect the level of excavation risk before a large-scale ground collapse occurs.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.4
• /
• pp.382-390
• /
• 2011

Smart sensors embedable in composite wind turbine blades have been required to be researched for monitoring the health status of large wind turbine blades during real-time operation. In this research, the feasibility of packaged FBG sensor probes was studied through the experiments of composite blade trailing edge specimens in order to detect cracking and debonding damages. The instants of cracking and debonding generated in the shear web were confirmed by rapid changes of the wavelength shifts from the bare FBG sensor probes. Packaged FBG sensor probes were proposed to remove the fragile property of bare FBG sensor probes attached on composite wind blade specimens. Strain and temperature sensitivity of fabricated probes installed on the skin of blade specimen were almost equal to those of a bare FBG sensor. Strain sensitivity was measured to be ${\mu}{\varepsilon}$/pm in a strain range from to 0 to 600 ${\mu}{\varepsilon}$, and the calculated temperature sensitivity was to be 48 pm/$^{\circ}C$ in the heating test up to 80 degree.

• Journal of the Korea Concrete Institute
• /
• v.19 no.4
• /
• pp.433-439
• /
• 2007

The main objective of the paper is to investigate the static behavior of a prestressed concrete (PSC) girder that has been spliced with precast box segments. A 20 m long full-scale spliced PSC girder is fabricated and tested to compare its static performance against a monolithic girder. The monolithic girder has the same geometric and material properties with respect to the spliced girder. This includes infernal strain, deflections, neutral axis position, and crack patterns for both girders. The test also consists of monitoring relative displacements occurring across the joints. Both the horizontal displacement (gap) and vertical displacement (sliding) are measured throughout the loading procedure. All results have been compared to those obtained from the monolithic girder. It has been demonstrated that the spliced girder offers close behavior with respect to the monolithic girder up to the crack load. Both girders exhibits ductile flexural failure rather than abrupt shear failure at joints.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.1
• /
• pp.32-38
• /
• 2001

Although the ultrasonic method has been developed and used widely in the fields, it has been used only for measuring the defect size and thickness loss. In this study, the relationship between surface wave attenuation through micro-crack growth and variation of velocity under repeated cyclic loading has been investigated. The specimens are adopted from 2.25Cr-1Mo steel, which is used for power plant and pipeline system, and have dimensions of $200{\times}40{\times}4mm$. The results of ultrasonic test with a 5MHz transducer show that surface wave velocity gradually decreases from the point of 60% of fatigue life and the crack length of 2mm with the increasing fatigue cycles. From the results of this study, it is found that the technique using the ultrasonic velocity change is one of very useful methods to evaluate the fatigue life nondestructively.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.04a
• /
• pp.215-215
• /
• 2014

현재 가장 많이 사용되고 있는 스프링식 안전밸브는 스프링과 설정치 드리프트, 누설 취약성, 채터링에 의한 시트 파손등의 문제점을 지니고 있다. 안전밸브 디스크에서 발생하는 유체 누설은 안전밸브 설정압력 개방에 영향을 주며, 시트(Seat)면의 이물질 삽입, 균열 및 유체에 의한 침식(Erosion) 등에 의해 밸브 핵심 부품이 쉽게 손상되어 기기 성능 저하를 초래하게 된다. 따라서 유체 누설을 조기에 탐지하고 정량화하여 해당 기기의 상태정보 제공을 통한 누설 감지 기법 연구가 요구된다. 원자력 발전소의 경우 밸브에서 유체가 누설되면 밸브의 오작동 및 운전 안정성 저해 요인이 된다. 따라서 본 연구에서는 음향방출법을 이용하여 안전밸브의 유체 누설을 평가하고, 안전밸브의 음향신호 측정 위치 선정 및 누설량에 따른 음향신호를 분석하고자 한다.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1995.05b
• /
• pp.753-760
• /
• 1995

본 보고서는 영광 3,4호기 가압기 밀림관(Surge Line)에 대한 파단전누설(Leak Before Break) 개념의 적용방법, 해석절차 및 해석결과에 대하여 기술하고 있다. 영광 3,4호기 가압기 밀림관에 대한 파단전누설해석은 배관계에 대한 정적, 동적 배관해석 결과를 토대로 큰 응력 값이 작용하는 부분에 대하여 수행하였다. 가상균열의 크기는 정상운전상태에서의 하중을 이용하여 결정하였으며 격납용기에 설치된 누설감지장치의 감지능력을 1.0gpm으로 가정하였다. 영광 3,4호기 가압기 밀림관에 대한 파단전 누설해석은 NUREG 1061,Vol.3 및 SRP3.6.3에 근거하여 수행하였으며 해석결과는 동 자료에서 제시하고 있는 적용기준을 만족하고 있는 것으로 평가되었다.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2002.05a
• /
• pp.39-43
• /
• 2002

As the concept of the smart structure, monitoring of acoustic emission (AE) can be applied to inspect the fracture of the entire structure in operating condition using built-in sensors. The objective of this study is to find the characteristics of matrix crack signals in composites due to the different specimen shapes. To detect matrix crack signals, we performed tensile tests by changing the thickness, width and length of the specimen. For the quantitative evaluation, time frequency analysis such as short-time Fourier transform (STFT) was used to characterize the matrix crack signals from PZT sensor. The experimental result shows the distinctive signal features in frequency domain due to the different specimen shapes.

• Proceedings of the KWS Conference
• /
• 2001.05a
• /
• pp.318-321
• /
• 2001

클래딩은 주요 산업분야에 내마모성, 내부식성의 향상을 위해 사용되고 있다. 그러나 클래딩 공정에서는 모재와 클래딩 재료의 물리적, 화학적 특성의 차이와 여러 가지 공정 변수의 영향으로 제품의 사용에 치명적인 손상을 줄 수 있는 균열, 슬래그 개재물, 기공등의 불연속이 발생하기 쉽다. 본 연구에서는 클래딩 시에 발생되는 불연속을 실시간으로 검출하는데 아주 우수한 검출능력을 갖고 있는 비파괴 검사 방법인 음향방출시험을 적용하고 검출된 신호에 대한 주파수 분석과 2차원 위치표정을 실시하여 균열, 기공 등의 불연속을 검출하였고 이를 주사전자현미경을 통하여 확인하였다. 음향방출법에 의해 클래딩부에서 발생하는 결함에 대한 실시간 평가가 가능함을 입증하였으며, 특히 다층 클래딩이나 넓은 면적의 클래딩시에 불연속을 가장 신속하게 감지할 수 있으므로 이를 생산공정에 활용한다면 클래딩 또는 용접부 품질감시를 위한 효과적인 방법이 될 것이다.