• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.197-207
• /
• 2023

Concrete is a widely used material due to its excellent compressive strength and durability. However, depending on the surrounding environment and the characteristics of the materials used in the construction, various defects may occur, such as cracks on the surface and subsidence of the structure. The detects on the surface of the concrete structure occur after completion or over time. Neglecting these cracks may lead to severe structural damage, necessitating regular safety inspections. Traditional visual inspections of concrete walls are labor-intensive and expensive. This research presents a deep learning-based semantic segmentation model designed to detect cracks in concrete walls. The model addresses surface defects that arise from aging, and an image augmentation technique is employed to enhance feature extraction and generalization performance. A dataset for semantic segmentation was created by combining publicly available and self-generated datasets, and notable semantic segmentation models were evaluated and tested. The model, specifically trained for concrete wall fracture detection, achieved an extraction performance of 81.4%. Moreover, a 3% performance improvement was observed when applying the developed augmentation technique.

• Smart Media Journal
• /
• v.13 no.1
• /
• pp.60-66
• /
• 2024

The Internet of Things, which began by connecting sensors through a network, is developing into an intelligent IoT by combining it with artificial intelligence technology. Elevators are essential for high-rise buildings in the city, and elevators move from floor to floor and perform the functions of transporting goods and moving users. It is necessary to provide safe and convenient services for elevator users in high-rise buildings or special environments (hospitals, etc.). In an environment where rapid patient transportation is important, such as large hospitals, there is a problem that hospital staff and the general public often use the elevator for patients. In particular, when moving patients where golden time is important, the waiting time to board the elevator is a major hindrance. In order to solve this problem, this study proposes an intelligent IoT system for elevator calling using smartphone Bluetooth. First, we experimented with the elevator calling IoT system using smartphone Bluetooth, and as a result of the experiment, it was confirmed that it can authenticate elevator users and reduce unnecessary waiting time for boarding. In addition, we propose an intelligent IoT system that connects with intelligent IoT.

• 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.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1996.04a
• /
• pp.215-220
• /
• 1996

원자력발전소의 주증기관은 증기발생기와 터빈을 연결하는 주요 계통으로서 여기서 발생하는 배관진동은 주요기기의 연결부, 밸브, 배관지지물과 건물 등에 복합적인 반복하중을 가하여 관련 지지물 및 구조물에 열화현상을 발생시켜 발전소의 안전운전에 심각한 영향을 초래할 가능성을 항상 내포하고 있다. 그럼에도 불구하고 배관진동 대책은 대부분 지지물을 추가로 설치하여 진동준위만 낮추고 있는 실정이다. 따라서 구체적인 배관진동의 예측, 측정 및 평가, 감쇠방안에 이르는 종합적이고 체계적인 연구가 요구되고 있다. 본 연구에서는 지지물의 열화현상 및 부분적인 파손으로 진동준위가 높아진 것으로 추정되는 원자력발전소 주증기관의 진동특성 및 요인을 분석하여 진동감쇠 방안을 도출하고 검증함으로써 배관 및 주변 구조물의 건전성을 확보하고 설비의 신뢰성을 확보하고자 하였다. 이를 위하여 주증기관을 모델링하여 해석하였으며, 발전소의 기동 및 정상운전시의 진동준위를 측정하였다. 또한 발전소의 정진기간중 일부 배관계에 대한 실험적 모우드 해석을 수행하였다. 여러가지 진동감쇠 방안을 검토하여 탄성지지 및 에너지 흡수효과를 동시에 발휘할 수 있는 특수 지지물(WEAR$_{TM}$)을 설치하는 방안을 도출하였으며, 현장에 설치한 후 배관의 진동상태를 확인함으로서 효과적인 방안임을 검증하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.487-488
• /
• 2021

시설물 점검은 사람이 직접 들어가거나 올라가 확인하는 방식이 일반적이다. 본 연구에서는 시설물 점검을 보다 안전하고 신속하게 하는 것을 전제로 하여 현재 상용화 되고 있는 드론과 아두이노를 이용한 센서를 적용하고자 한다. 본 논문은 기존의 어려운 조작의 드론에 건물 내부에서 호버링이 가능하게 하는 옵티컬 플로어 센서를 장착아여 조작을 보다 쉽게 한다. 또한, 외부 비행 시 GPS센서를 사용하여 좌표지정을 통한 자동비행을 가능하게 하고 아두이노의 센서와 펌프를 적용한 "오토파일럿이 가능한 시설물 관리 드론" 기술을 제안한다. 기존의 드론과 다르게 카메라와 센서를 이용해 시설물 관리를 대신하고, 외부 시설물 관리나 농업 등에서 사용할 때 좌표를 지정해 사용자가 직접 조작하지 않아도 지정한 좌표로 드론이 이동하여 관리 및 임무를 수행한다. 센서들의 값을 앱으로 전송받아 핸드폰으로 받아 볼 수 있다.

• Explosives and Blasting
• /
• v.28 no.2
• /
• pp.99-107
• /
• 2010

Domestic explosive demolition techniques have been developed and applied for low-rise structures up to now. However, the demand for the development of those techniques that can be applied economically, safely and environment-friendly rapidly increases because the old high-rise RC rahmen structures that were built since around 1970s are now required to rebuild. As a result, element technologies of explosive demolition for low-rise structures were applied to take advantage of technology in high-rise structures that performed application testing at Chungang Department demolition field in Daejeon city. It could judge elements technology establishment for high-rise structure demolition and field application and suggest the improvements when the problems occurred to develop High-rise building demolition techniques for method of protection a field test and the dust reduction test. The water cannon test was applied to reduce the dust site and the drilling tests are performed to select the best components for explosives demolition elements techniques of the reliability. This paper shows that we have the ability to remove a high-rise building using environmentally friendly safe and economical explosives demolition method. It would contribute to prevent a foreign company from entering the domestic market and should contribute to acquire competitiveness of domestic demolition industry.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.161-168
• /
• 2021

Cracks affect the robustness of infrastructures such as buildings, bridge, pavement, and pipelines. This paper presents an automated crack detection system which detect cracks in diverse surfaces. We first constructed the combined crack dataset, consists of multiple crack datasets in diverse domains presented in prior studies. Then, state-of-the-art deep learning models in computer vision tasks including VGG, ResNet, WideResNet, ResNeXt, DenseNet, and EfficientNet, were used to validate the performance of crack detection. We divided the combined dataset into train (80%) and test set (20%) to evaluate the employed models. DenseNet121 showed the highest accuracy at 96.20% with relatively low number of parameters compared to other models. Based on the validation procedures of the advanced deep learning models in crack detection task, we shed light on the cost-effective automated crack detection system which can be applied to different surfaces and structures with low computing resources.

• Journal of Korean Society of Disaster and Security
• /
• v.16 no.4
• /
• pp.61-66
• /
• 2023

In this study, we analyzed the flooded area around Samcheok Middle School caused by typhoons MAYSAK·HAISHEN in September 2020. To analyze the confluence of Samcheok Osipcheon, local stream Deungbongcheon, we utilized Iber, a two-dimensional hydraulic model. We simulated the water depth and flood extent based on the peak flows on September 3 and September 7, 2020, and the 80 year and 100 year frequency floods. The simulation results showed that the 80-year frequency flood and the 100-year frequency flood on September 7 were insignificantly different, but the maximum flow rate from September 3 to September 7 was significantly different at 401 m³/s, resulting in a difference of 0.8 m in water depth and 7.1 m² in flood area. In addition, the analysis that considered only the contour lines using contour lines predicted inundation of not only the Samcheok Middle School playground but also the building, confirming the need to apply DSM.

• Fire Science and Engineering
• /
• v.28 no.3
• /
• pp.10-19
• /
• 2014

The fast evacuation from fire floors to evacuation floors in high-rise building fires can minimize the human damage. In this study, an evacuation instrument, which are applicable to the high-rise buildings of adaptable escape mechanisms by the current NFSC 301 (national fire safety code 301), were selected to analyze the applicability in the high-rise buildings over 11th floor through the site adaptability test. The results of the site test were as follows. The elevator type evacuation instrument of new concept developed as a new technology by compensating the defect of evacuation instrument limiting in the high-rise buildings over 11th floor had completed the stability test and the performance certification test in fire stations, which there were no problems in the introduction of the elevator type evacuation instrument as an escape mechanism in the high-rise buildings. The elevator type evacuation instrument using escapers' weight without using electric power was an escape mechanism that many people could evacuate in a short period of time when a fire broke out in the high-rise buildings. In particular, The elevator type evacuation instrument operated by nonpower had the adaptability as a customized escape mechanism considering user characteristics in the buildings for the disabled or patients with an advanced disease.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.3
• /
• pp.307-317
• /
• 2011

This paper is to investigate the possibility of the elastic seismic design for highrise buildings through seismic performance evaluation for potential earthquakes that wind-designed highrise buildings located in strong wind zone and low seismicity can be experienced. Highrise steel diagrid frames which is the most loved structural system in recent years were wind-designed and the substantial system overstrength due to wind design procedure is verified, For the highrise steel diagrid frames, the response spectrum analysis and the seismic performance evaluation by various soil sites were conducted. It was showed that highrise steel diagrid frames with slenderness of greater than 5.2 under strong wind and low seismic zones such as Korea peninsula can resist elastically for the 500 year return period earthquake and have the possibility of seismic design for the 2400 year return period earthquake. In the member level, highrise steel diagrid frames with slenderness of greater than 5.2 all presented the immediate occupancy level regardless of soil sites for the 500 year return earthquake and excluding the $S_E$ soil site for the even 2400 year return period earthquake. In the system level, highrise steel diagrid frames with slenderness of greater than 5.2 showed the immediate occupancy level for $S_A$ and $S_B$ soil sites and the life safety for $S_C$ to $S_E$ soil site in the 500 year return period. The seismic performance level of highrise steel diagrid frames for the 2400 year return period earthquake displayed one step lower than the 500 year return period earthquake.