• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.4
• /
• pp.549-557
• /
• 2022

Due to harsh conditions of construction site, understanding of current feature of terrain and other infrastructures is critical issue for site managers. However, because of difficulties in acquiring the geographical information of the construction sites such as large sites and limited capability of construction workers, comprehensive site investigation of current feature of construction site is not an easy task for construction managers. To address these circumstances of construction sites, this study deduce difficulties and applicabilities of unmanned aerial vehicle in the area of construction site management. To confirm applicability of UAV in civil construction project, case study have been conducted on the road construction project. The result of case study proved that the developed system is one of promising technologies that has been studied in construction site management. To improve applicability of UAV for construction and process management information, law and technical issues will be an important area of future study.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.1
• /
• pp.99-107
• /
• 2023

Recently, the rate of death and safety accidents at construction sites is the highest among all kinds of industries. In order to apply artificial intelligence technology to construction sites, it is essential to secure a dataset which can be used as a basic training data. In this paper, a number of image data were collected through actual construction site, for which major construction equipment objects mainly operated in civil engineering sites were defined. The optimal training dataset construction was completed by annotation process of about 90,000 image dataset. Reliability of the dataset was verified with the mAP of over 90 % in use of YOLO, a representative model in the field of object detection. The construction equipment training dataset built in this study has been released which is currently available on the public data portal of the Ministry of Public Administration and Security. This dataset is expected to be freely used for any application of object detection technology on construction sites especially in the field of construction safety in the future.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.661-670
• /
• 2006

The utilization of simulation has been limited in planning construction process because it is difficult to collect data and build a model using simulation method. This study collects construction operation data and analyzes the characteristics of its distribution. Through the statistical analysis on the empirical data, this study identifies Beta distribution functions is one of the most proper in duplicating the characteristics of construction equipment operation data into a computer simulation. The information obtained in this study can support preparing input data for another simulation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.4
• /
• pp.461-468
• /
• 2021

The role of drones is increasing day by day in smart construction that manages construction sites with 3D data in every life cycles. This is because both the digital surface model (DSM) and the orthoimage obtained for the construction site through the drone are made of point cloud data. This study aims to develop standard work types for drone use in order to systematically utilize drones in expressway construction sites. For the study, two expressway construction sites in Korea were set as test beds, and construction types applicable to drones were derived and verified through a pilot project. As a result of the study, three construction work types were developed for road planning, road design and maintenance, respectively, and in road construction, twenty-one detailed construction types were developed for five construction work types. It is expected that drones can be used more systematically not only at expressway construction sites, but also at other road construction sites by utilizing the "standard work type at expressway construction site for drone use" developed in this study.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.5
• /
• pp.599-606
• /
• 2022

Strain gauges and the bridge weigh-in-motion (BWIM) method are the representative field measurement methods used for fatigue evaluationsof a steel bridge-in-service. For a fatigue reliability evaluation to assess fatigue damage accumulation, the effective stress range and the number of stress cycles applied as the fatigue details can be estimated based on the AASHTO Manual for Bridge Evaluations with the field measurement data of the target bridge. However, the procedure for estimating the effective stress range and the stress cycles from field measurement data has not been explicitly presented. Furthermore, studies that quantitatively compare differences in fatigue evaluation results according to the field measurement data type or processing method used are still insufficient. Here, a fatigue reliability evaluation is conducted using strain and BWIM data that are measured simultaneously. A frame model and a shell-solid model were generated to examine the effect of the accuracy of the structural analysis model when using BWIM data. Also, two methods of handling BWIM data when estimating the effective stress range and average daily cycles are defined. As a result, differences in evaluation results according to the type of field measurement data used, the accuracy of the structural analysis model, and the data handling method could be quantitatively confirmed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2C
• /
• pp.125-131
• /
• 2008

Ground stiffness(shear wave velocity) is one of the key parameters in geotechnical earthquake engineering. An In-situ seismic technique has its own advantages and disadvantages over the others in stiffness measurements. By combining the crosshole and seismic cone techniques and utilizing favourable features of bender elements, a new hybrid probe has been developed in order to enhance data quality and easiness of testing. The basic structure of the probe, called "MudFork" is a fork composed of two blades, on each of which source and receiver bender elements were mounted respectively. To evaluate the disturbance caused by the penetration of the probe, shear wave velocity measurements were carried out in the Kaolinite slurry in the laboratory. Finally, the probe was penetrated in coastal mud near Incheon, Korea, using SPT(standard penetration test)rods pushed with a routine boring machine and shear wave velocity measurements were carried out. The results were verified with data from laboratory and cone testing. The performance of the probe turns out to be excellent in terms of data quality and testing convenience.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.286-286
• /
• 2023

물의 전체 순환 구조에서 토양수분이 차지하는 정량적 비중은 상대적으로 작지만, 강우-유출 과정의 비선형에 영향을 미치는 지배적 요인 중 하나이고, 토양 침식과 산사태, 농업생산량, 기후 변화 대응 등 광범위한 주제와 연관되어 있어, 토양수분의 물리과정에 대한 이해 증진과 예측 기술의 지속적인 개선이 필요하다. 본 연구에서는 금오공과대학교 유역 내에서 토양수분과 기상 요소를 실시간 관측하고, 기계학습 기법을 이용하여 토양수분을 단기 예측하는 기술을 개발하고 평가한다. 구체적으로는, 토양 관측 장비인 TEROS를 사용하여 표층 지점의 10cm, 심층 지점의 40cm에서의 토양수분, 토양장력과 토양온도를, 기상 관측 장비인 ATMOS를 사용하여 태양복사, 강수량, 기온, 풍속, 대기압 등 다양한 기상 요소를, 실시간 클라우드 방식으로 1여 년간 수집한 데이터를 활용한다. 또한, 과거 및 실시간 데이터를 기반으로 LSTM(Long-Short Term Memory) 기법을 사용하여 토양수분 예측 모형을 구축하고, 선행 예측 시간에 따른 모의 정확도를 평가한다. 기상 요소의 누적 등 자료 분석 방법이 표층 및 심층 토양수분 예측에 미치는 영향, 그리고 예측 모형 개선 방향에 대해 토의한다. 실시간 현장 관측 자료 및 인공지능 기반 단기 토양수분 예측 모의 기술은 소규모 유역의 수문순환 분석 및 물리기반 모형의 개선 등 다양한 분야에서 활용할 수 있을 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.136-136
• /
• 2023

우리나라의 강우 특성은 하절기에 집중되어 있으며 최근 이상강우와 기상이변에 따른 집중호우 발생으로 여를철 탁수 문제 발생 빈도가 높아지고 있는 추세이다. 과거 '02년 태풍 루사', '03년 태풍 매미', '06년 에위니아'부터 20년 마이삭, 하이선과 같은 태풍 및 장마에 의해 탁수 유입이 급증되어 수중 탁도가 높아지며 저수지 탁수 문제가 발생하였다. 특히 우리나라 경우 하천 및 저수지에서 물 사용량의 대부분을 이용하고 있기에 탁수 문제가 장기화 될 시 댐 하류 지역의 농업, 공업, 수생태 등 사회적, 비용적, 환경적 문제를 발생시킨다. 이러한 문제를 파악, 대응을 위한 탁수 모의에 대한 연구가 활발히 진행되고 있다. 탁수를 모의하기 위해서는 유량, 수온, SS, 탁도 데이터가 필요하며 이를 위해 국가측정망에서 하천 및 댐 저수지 내 SS를 측정하여 탁수를 측정 하고 있다. 하지만 현재 측정의 경우 채수를 통한 점단위의 측정으로 데이터 해상도가 낮다는 한계점이 있다. 이러한 데이터 취득의 한계로 기존 조사를 통한 탁도-SS 관계식을 통해 탁수를 예측하고 있으나 과거 2003년 이후 자료를 바탕으로 산정된 식으로 불확도가 존재한다. 탁수 모의 정확도 개선을 위한 데이터 해상도 및 탁도-SS 관계식 문제를 해결 하기 위해 기존 데이터 분석을 통한 미계측 기간에 대한 보간을 필요로 하며 현장 계측을 통한 탁도, SS 자료를 취득하여 탁도-SS 관계식을 최신화 할 필요가 있다. 따라서, 본 연구에서는 탁도를 측정 센서 YSI와 SS 측정센서 레이저부유사측정기(LISST: Laser In-Situ Scattering and Transmissometry)를 활용하여 자료를 취득하고 탁도-SS 산정식을 최신화 하였다. 또한 기존 국가 수질 측정망 데이터 및 기상 자료 데이터를 취득하여 데이터 분석을 통해 미계측 기간에 대한 데이터를 보간하여 탁수 모의 입력자료를 개선하였고 이를 기반으로 탁수 모의 정확도를 개선하고자 하였다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.6
• /
• pp.843-852
• /
• 2022

Despite continuous safety management, the death rate of construction workers is not decreasing every year. Accordingly, various studies are in progress to prevent construction site accidents. In this paper, we developed an AI-based priority inspection target selection model that preferentially selects sites are expected to cause construction accidents among construction sites with construction costs of less than 5 billion won (KRW). In particular, Random Forest (90.48 % of accident prediction AUC-ROC) showed the best performance among applied AI algorithms (Classification analysis). The main factors causing construction accidents were construction costs, total number of construction days and the number of construction performance evaluations. In this study an ROI (return of investment) of about 917.7 % can be predicted over 8 years as a result of better efficiency of manual inspections human resource and a preemptive response to construction accidents.

• Journal of the Korean GEO-environmental Society
• /
• v.12 no.9
• /
• pp.35-45
• /
• 2011

This paper is to analyze the behaviors of tunnel support by TDR(Time Domain Reflectometry) sensor using electrical pulse. To analysis the behaviors of tunnel support, Copper tape as sensing materials was studied for on-site installation. Copper tape to the top of the glass tape, foam tape, and shielding the lower part was used electromagnetic shield sheet. For a high sensitivity to load and fill out the measurement noise emissions has been developed for the production of materials. This sensing material through the tunnel model tests for the change by surcharge load in TDR data were analyzed. Varing stiffness and support of conditions were determined the change of TDR data through PVC pipe tunnel section model tests. By comparing TDR data and finite element analysis, the behaviors of the tunnel support materials were analyzed qualitatively.