• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.93-106
• /
• 2021

Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.379-385
• /
• 2008

콘크리트 건물의 보수 작업은 표면에 발생하는 균열을 정확하게 계측함으로써 비용적인 측면과 안전성이 결정된다. 하지만 표면에 발생한 균열은 대부분 점검자에 의해 수작업으로 계측되기 때문에 시간적 측면에서 비효율적이다. 따라서 본 논문에서는 콘크리트 슬래브 표면에 발생한 균열의 밝기와 밀도 그리고 면적 특징을 이용한 균열 검출 기법을 제안한다. 제안된 균열 검출 방법은 콘크리트 슬래브 표면의 명암도와 위치 정보를 ART2 기반 양자화에 적용한 후, 균열과 인접한 배경간의 명암도 차이를 이용하여 균열과 인접한 배경을 분리한다. 균열과 인접한 배경이 분리된 영상에서 형태학적인 정보를 이용하여 세부적인 잡음을 제거한 후에 최종적으로 균열 영역을 검출한다. 실제 콘크리트 균열 영상을 대상으로 실험한 결과, 다양한 콘크리트 균열 영상에서 기존의 방법보다 균열 검출 성능이 개선되었음을 확인하였다.

• Journal of the Korea Concrete Institute
• /
• v.23 no.1
• /
• pp.109-120
• /
• 2011

This paper presents an experimental study results on the crack control of flexure-dominant reinforced concrete beams repaired with strain-hardening cement composite (SHCC). Five RC beams were fabricated and tested until failure. One unrepaired RC beam was a control specimen (CBN) and remaining four speciemens were repaired with SHCC materials. The test parameters included two types of SHCC matrix ductility and two types of repair method (patching and layering). Test results demonstrated that RC beams repaired with SHCC showed no concrete crushing or spalling until final failure, but numerous hair cracks were observed. The control specimen CBN failed due to crushing. It is important to note that SHCC matrix can improve crack-damage mitigation and flexural behavior of RC beams such as flexural strength, post peak ductility, and energy dissipation capacity. In the perspective of crack width, crack widths in RC beams repaired with SHCC had far smaller crack width than the control specimen CBN under the same deflection. Especially, the specimens repaired with SHCC of PVA0.75%+PE0.75% showed a high durability and ductility. The crack width indicates the residual capacity of the beam since SHCC matrix can delay residual capacity degradation of the RC beams.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2009.05a
• /
• pp.527-528
• /
• 2009

Effects of temperature on fatigue resistance of crack zone in concrete members repaired by injecting epoxy resin was experimentally studied. First, a fatigue machine that produces small movement similar to those observed in actual cracks was developed. It was made clear that the rise of temperature changes a mode of fracture at the repaired zone and sharply dropped fatigue resistance.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1997.05a
• /
• pp.13-18
• /
• 1997

구조물의 사용수명은 흔히 균열의 생성 및 성장과 크게 관련지어지는데, 이는 균열의 존재가 기계나 구조물의 성능에 장애를 줌은 물론 기계 전체에 치명적인 손상을 입힐 수 있기 때문이다. 그 동안의 파괴역학분야의 연구에서는 균열이 존재하는 부재의 주 모델을 해석의 편의상 두께가 균일한 부재로 간편화하여, 주로 이차원적으로 해석을 해왔다. 그러나, 실제 기계 및 구조물에는 두께가 일정한 부재 뿐 아니라, 두께가 일정하지 않고 변화하는 부재(이하 변호부재라 한다)가 현실적으로 폭넓게 사용되고 있다. (중략)

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.45-48
• /
• 2022

건축물 안전 점검은 대부분 전문가의 현장 방문을 통한 육안검사다. 그중 균열 검사는 건물 위험도를 나타내는 중요한 지표로써 발생 위치, 진행성, 크기를 조사하는데, 최근 균열 조사 방식에 대해 객관성과 체계성을 보완할 딥러닝 개발이 활발하다. 그러나 균열 이미지는 외부 현장에 모양, 규모도 많은 종류라 도메인이 다양해야 하는데 대부분 제한된 환경과 실제적인 균열 검사와는 무관한 데이터로 구성되어 실효적이지 않다. 본 연구에서는 균열 조사에 적합하고 Wild 환경에 적용 가능한 POC 데이터셋을 소개한다. 기존 균열 공인 데이터셋 4종의 특징과 한계점을 분석을 토대로 고해상도 이미지로써 균열의 세부 특징을 담았고 균열 유사 환경과 조건들을 추가 촬영해 균열 검출에 강인하게 학습되도록 지향하였다. 정제 및 라벨링 작업을 거친 POC 데이터 셋은 균열 검출모델인 YOLO-v5으로 성능을 실험하였고, mAP(mean Average Precision) 75.5%로 높은 검출률을 보였다. POC 데이터셋으로 더욱 도메인에 적응적(Domain-adapted)인 인공지능 모델을 개발하여 건물, 댐, 교량 등 각종 대형 건축물에 대한 안전하고 효과적인 안전 관리 도구로써 활용할 것을 기대한다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.2
• /
• pp.122-129
• /
• 2019

Cracks in concrete structures are inevitable phenomena caused by shrinkage, hydration heat, and external loads. These cracks facilitate the penetration of external harmful ions into the concrete, which greatly reduces its durability. Recently, self-healing concrete has been actively studied. Also, self-healing fiber-reinforced concrete have been studied to control the crack in concrete and to maximize the shelf-healing capability. In this study, mortar specimens containing PVA fiber, fly ash and crystalline admixture were fabricated. The compressive and flexural strength were evaluated. Also, the self-healing performance was evaluated by the absorption test. From the results, it was confirmed that the amount of water absorbed by healing of the crack decreased as time increased. It was also found that PVA fiber is beneficial for the production of calcium carbonate, an additional healing product.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.14 no.5
• /
• pp.23-31
• /
• 2010

In this study, a shaking table test was performed for the evaluation of the failure capacity of an anchor foundation system in the case of an aged condition. For the shaking table test, three kinds of specimens were manufactured as follows: 1) a non-damaged anchor; 2) a specimen with cracks running through the anchor; and 3) a specimen with cracks along the expected corn-shape fracture away from the anchor. A dynamic characteristic was determined through a measurement of the frequency response function (FRF), and the seismic capacity was evaluated by using a shaking table test. Failure capacities were calculated using an acceleration response and it was compared with the anchor design code.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.17 no.5
• /
• pp.1-12
• /
• 2013

This study presents the evaluations of seismic performance and displacement ductility for two types of RC columns: existing RC column without SFM (Super Flexibility Membrane) and CSF (RC columns strengthened with SFM). After they are analyzed by the experiment as well as FEM, crack patterns and load-displacement curve of CSF by the former are shown to similar to those of CSF by the latter. The flexural cracks are dominant in CSF, whereas shear cracks in CNF (existing RC column without SFM). Displacement ductility of CSF is shown significantly to increase as well as ultimate displacement, compared to those of CNF. Therefore CSF can be replaced to CNF in order to increase the seismic performance and displacement ductility.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.11a
• /
• pp.269-272
• /
• 2008

This paper reports on the cracking mitigation and flexural behavior experimentally observed in concrete prisms layered with strain-hardening cement composites (SHCCs) which is micro-mechanically designed cement composite and exhibits pseudo tensile strain-hardening behavior accompanied by multiple cracking while using a moderate amount of fiber, typically less than 2 percent in term of fiber volume fraction. In this study, SHCC is reinforced with 1.3 percent polyvinyl alcohol (PVA) and 0.20 percent polyethylene (PE) in volume fraction. Tests were conducted using $100{\times}100{\times}400mm$ long prisms supported over a simply supported span of 350mm. The four point load was applied using MTS servo control machine. The thickness patched with SHCC is the main variable for this study. Experimental study shows that when subject to monotonic flexural loading, the SHCC layered repair system showed 2.7 - 4.2 times increased load carrying capacity, and mitigated cracking damage of concrete beams layered with SHCC compared with plain concrete beams.