• 한국건축시공학회지
• /
• 제17권6호
• /
• pp.545-557
• /
• 2017

이 연구는 사회 기반 구조물의 노후화에 대한 안전점검 기술분야에서 구조물 외관점검 기술의 효율적 대안에 관한 연구이다. 기존 육안점검 및 조사를 대신하여 산업용 드론과 딥 러닝기반의 이미지 분석 기법을 접목함으로써 막대한 인력과 시간소요 및 비용을 절감하고 높은 구역 및 돔 구조물의 접근 한계를 극복하고자 하였다. 구조물의 0.3mm 이상의 균열 손상을 검지할 수 있는 고 해상도 카메라와 라이다 센서, 임베디드 이미지 프로세서 모듈로 구성된 탑재체를 제작하여 산업용 드론에 탑재하였다. 이를 현장 시험에 적용하여 자동비행항법을 통해 시편의 손상 이미지를 촬영하였다. 또한 균열경을 이용하여 기존 육안 점검 방법으로 백태, 박리박락과 같은 면적형 손상과 선형 손상인 균열의 폭과 길이를 측정하여 최종 이미지 분석 검출 결과와 비교하고자 하였다. 촬영된 이미지 중 80장의 샘플을 골라 이미지 분석 기법을 적용하여 사전처리작업(pre-processing)-분리작업(segmentation)-특징점 추출작업(feature extraction)-분류 작업(Classification)-지도학습작업(supervised learning) 등의 과정을 거쳐 손상을 분리하고, 이를 딥러닝 기반 플랫폼으로 지도학습하여 분석 파라미터를 추출하였다. 지도학습을 수행하지 않은 임의의 이미지 샘플 60장을 신규로 추가하여 추출된 파라미터를 기반으로 이미지 분석을 수행한 결과, 손상 검출율의 90.5%로 나타났다.

• 대한안전경영과학회지
• /
• 제18권1호
• /
• pp.1-8
• /
• 2016

This study was conducted by survey and inspection of stair passage leading lights in shopping buildings which are more than 5 stories and have an underground parking lot located at Pyeongtaek-si and Seongnam-si. Number of shopping building for this study is 30 and of stair passage leading light inspected by two lights in each shopping building is 60. The result of this study is that the type of installed leading lights is LED(77%), and 60% of leading lights has problem such as no cleaning, scratch and discoloration, etc. The height of installed leading lights meets the fire law which is less than 1m from the floor. Visible condition of leading lights is good except some leading lights which have a little visible problem due to banner advertisement. 37% of standby power has flickered and went out. 93% of total leading lights meets the fire law which is more than 1lux from 0.5m distance, but cold cathode fluorescent lamps(CCFLs) have the problem which not meets proper brightness level based on fire law. In additional measurement result, zero lux of leading lights is 32%(from 1m distance), 68%(from 1.5m distance) and 98%(from 2m distance). Leading light is very important facility because it is eyes and guide when emergency. Therefore, proper fire facility operating function inspection and total detailed inspection are important to keep the good condition of leading light except simple visual check, and also improvement in law system of type approval, fire construction inspection and illumination level will be needed.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2001년도 춘계학술대회논문집
• /
• pp.577-582
• /
• 2001

Identification of damage of structures has recently received considerable attention in the light of maintenance and safety assessment under service loads. In buildings, the current techniques of safety assessment largely depend on partial experiments such as visual inspection, destructive and nondestructive tests which lead to overconsumption of time and cost as well as higher labor intensity. Therefore, a new trial for safety assessment is urgently needed today. In this respect, the vibration characteristics of buildings have been applied steadily to obtain a damage index of the whole building, but it cannot be established as a practical method until now. This study is aimed at investigating the application of damage identification methods using vibration characteristics of building. Numerical tests are performed on a apartment building. From the test results, it is observed that severity and location of damage can be estimated with a relatively small error by using natural frequency and mode shape data.

• Smart Structures and Systems
• /
• 제31권1호
• /
• pp.79-88
• /
• 2023

As the number of deteriorated buildings increases, the importance of safety diagnosis, maintenance, and the repair of buildings also increases. Traditionally, building condition assessments are performed by one person or one company and various inspections are needed. This entails a subjective judgment by the inspector, resulting in different assessment results, poor objectivity and a lack of reliability. Therefore, this study proposed a method to bring about accurate grading results of building conditions. The limitations of visual inspection and condition assessment processes previously conducted were identified by reviewing existing studies. Building defect data was collected using the reverse-engineered three-dimensional (3D) model. The accuracy of the results was verified by comparing them with the actual evaluation results. The results show a 50% time-saving to the same area with an accuracy of approximately 90%. Consequently, defect data with high objectivity and reliability were acquired by measuring the length, area, and width. In addition, the proposed method can improve the efficiency of the building diagnosis process.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1116-1120
• /
• 2004

In the nuclear power plant, there are several cylindrical vessels such as reactor vessel, pressuriser and so on. The vessels are usually constructed by welding large rolled plates, forged sections or nozzle pipes together. In order to assure the integrity of the vessel, these welds should be periodically inspected using sensors such as ultrasonic transducer or visual cameras. This inspection is usually conducted under water to minimize exposure to the radioactively contaminated vessel walls. The inspections have been performed by using a conventional inspection machine with a big structural sturdy column, however, it is so huge and heavy that maintenance and handling of the machine are extremely difficult. It requires much effort to transport the system to the site and also requires continuous use of the utility's polar crane to move the manipulator into the building and then onto the vessel. Setup beside the vessel requires a large volume of work preparation area and several shifts to complete. In order to resolve these problems, we have developed an underwater mobile robot guided by the laser pointer, and performed a series of experiments both in the mockup and in the real reactor vessel. This paper introduces our robotic inspection system and the laser guidance of the mobile robot as well as the results of the functional test.

• 한국건축시공학회지
• /
• 제23권3호
• /
• pp.327-336
• /
• 2023

The focus of this research was to devise a conceptual methodology for drone usage and to assess the viability of safety checklist items specific to drone application in safety oversight. The appraisal was grounded in a focus group interview involving professionals from construction management and safety fields. The proposed process was segmented into four stages: 1) pre-flight phase for flight plan development, 2) drone flight phase for safety condition inspection utilizing checklist items, 3) post-flight phase for visual asset analysis, and 4) documentation and management phase. Furthermore, the research scrutinized the applicability of 32 distinct safety checklist items for drone operations. The primary aim of this investigation was to probe the possible deployment of drones as part of construction safety inspections at work sites. However, it bears mentioning that subsequent research should strive to gather a more extensive sample size through questionnaire surveys, thereby facilitating quantitative analysis. Administering such surveys would yield more comprehensive data compared to a focus group interview, which was constrained by a limited participant count. In summation, this study lays a foundational groundwork for understanding the potential advantages and challenges associated with integrating drones into construction safety management.

• Advances in concrete construction
• /
• 제4권2호
• /
• pp.89-105
• /
• 2016

The post - fire investigation is conducted on a fire-affected reinforced concrete shear wall building to ascertain the level of its strength degradation due to the fire incident. Fire incident took place in a three-storey building made of reinforced concrete shear wall and roof with operating floors made of steel beams and chequered plates. The usage of the building is to handle explosives. Elevated temperature during the fire is estimated to be $350^{\circ}C$ based on visual inspection. Destructive (core extraction) and non-destructive (rebound hammer and ultrasonic pulse velocity) tests are conducted to evaluate the concrete strength. X-ray diffraction (XRD) and Field Emission Scanning Electron Microscopy (FESEM) are used for analyzing micro structural changes of the concrete due to fire. Tests are conducted for concrete walls and roof slab on both burnt and unburnt locations. The analysis of test results reveals no significant degradation of the building after the fire which signifies that the structure can be used with full expectancy of performance for the remaining service life. This document can be used as a reference for future forensic investigations of similar fire affected concrete structures.

• 국제초고층학회논문집
• /
• 제9권4호
• /
• pp.351-360
• /
• 2020

Monitoring civil structures periodically is necessary for ensuring the fitness of the structures. Cracks on inner and outer surfaces of the building plays a vital role in indicating the health of the building. Conventionally, human visual inspection techniques were carried up to human reachable altitudes. Monitoring of high rise infrastructures cannot be done using this primitive method. Also, there is a necessity for more accurate prediction of cracks on building surfaces for ensuring the health and safety of the building. The proposed research focused on developing an efficient crack classification model using Transfer Learning enabled EfficientNet (TL-EN) architecture. Though many other pre-trained models were available for crack classification, they rely on more number of training parameters for better accuracy. The TL-EN model attained an accuracy of 0.99 with less number of parameters on large dataset. A bench marked METU dataset with 40000 images were used to test and validate the proposed model. The surfaces of high rise buildings were investigated using vision enabled Unmanned Arial Vehicles (UAV). These UAV is fabricated with TL-EN model schema for capturing and analyzing the real time streaming video of building surfaces.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.73-74
• /
• 2022

Concrete structures occupy the largest proportion of modern infrastructure, and concrete structures often have cracking problems. Existing concrete crack diagnosis methods have limitations in crack evaluation because they rely on expert visual inspection. Therefore, in this study, we design a deep learning model that detects, visualizes, and outputs cracks on the surface of RC structures based on image data by using a CNN (Convolution Neural Networks) model that can process two- and three-dimensional data such as video and image data. do. An experimental study was conducted on an algorithm to automatically detect concrete cracks and visualize them using a CNN model. For the three deep learning models used for algorithm learning in this study, the concrete crack prediction accuracy satisfies 90%, and in particular, the 'InceptionV3'-based CNN model showed the highest accuracy. In the case of the crack detection visualization model, it showed high crack detection prediction accuracy of more than 95% on average for data with crack width of 0.2 mm or more.

• 한국건축시공학회지
• /
• 제21권6호
• /
• pp.665-676
• /
• 2021

노후 건축물의 수가 증가함에 따라, 건물의 안전진단, 유지 보수에 대한 중요성이 증가하고 있다. 기존 외관 조사는 점검자의 주관적인 판단이 수반되어 평가 결과가 다르고 객관성과 신뢰성이 떨어진다. 따라서 본 연구는 기존 연구를 통해 기실시된 외관 조사 및 상태 평가 프로세스의 한계를 제시하였으며, UAV, Laser Scanner를 통해 3D Point Cloud 데이터를 수집하였다. 또한, Reverse Engineering 기술을 이용하여 3D 모델을 생성한 후 객관적인 상태평가 데이터를 취득하였다. 이후 기존의 정밀검사 데이터와 정밀 안전진단 데이터를 활용하여 DNN 구조를 생성하고, 고정밀도 측정 장치를 이용하여 얻은 상태평가 데이터를 적용하여 객관적인 건물안전등급을 산출하였다. 자동화된 프로세스는 20개의 노후된 건축물에 적용되며 동일 면적 건축물 기준 수작업으로 실시되는 안전진단의 시간에 비해 약 50% 감소하였다. 이후 본 연구에서는 안전등급 결과값과 기존값을 비교하여 안전등급 산출과정의 정확성을 검증하고 약 90%의 높은 정확도를 가진 DNN을 구축하였다. 이는 향후 노후 건물의 안전등급 산정의 신뢰성이 향상되고 비용과 시간을 절약해 경제성이 향상될 것으로 기대된다.