• Smart Structures and Systems
• /
• 제31권2호
• /
• pp.131-140
• /
• 2023

As well-known, the extended Kalman filter (EKF) is a powerful tool for parameter identification with limited measurements. However, traditional EKF is not applicable when the external excitation is unknown. By using least-squares estimation (LSE) for force identification, an EKF with unknown input (EKF-UI) approach was recently proposed by the authors. In this approach, to ensure the influence matrix be of full column rank, the sensors have to be deployed at all the degrees-of-freedom (DOFs) corresponding to the unknown excitation, saying collocated measurements are required. However, it is not easy to guarantee that the sensors can be installed at all these locations. To circumvent this limitation, based on the idea of first-order-holder discretization (FOHD), an improved EKF with unknown input (IEKF-UI) approach is proposed in this study for the simultaneous identification of structural parameters and unknown excitation. By using projection matrix, an improved observation equation is obtained. Few displacement measurements are fused into the observation equation to avoid the so-called low-frequency drift. To avoid the ill-conditioning problem for force identification without collocated measurements, the idea of FOHD is employed. The recursive solution of the structural states and unknown loads is then analytically derived. The effectiveness of the proposed approach is validated via several numerical examples. Results show that the proposed approach is capable of satisfactorily identifying the parameters of linear and nonlinear structures and the unknown excitation applied to them.

• 국제학술발표논문집
• /
• The 4th International Conference on Construction Engineering and Project Management Organized by the University of New South Wales
• /
• pp.229-233
• /
• 2011

Recently, the scale of buildings has been increasing because of the high-rise trend and complexity of underground spaces. A significant number of steel structures have therefore been adopted for building construction. Since workers need to work in high places to install steel beams, many industrial accidents easily occur during steel-frame work. Furthermore, considering the increasing trend of building steel structures, the safety of the workers during the steel beam erection work is of concern. To improve the safety, a new type of joint, located between the steel column and beam, which can eliminate the need for working at the elevated height during steel beam erection has been developed in Korea. Using the newly developed technology in the construction field, the safety performance needs to be evaluated. This study presented the safety evaluation approach for the newly developed technology from the literature review, and applied the method to a self-supported steel joint. The result showed that applying the self-supported steel joint improved the safety of the steel erection work in terms of working posture, working environment, and risk exposure time.

• 한국안전학회지
• /
• 제23권5호
• /
• pp.1-6
• /
• 2008

`SOS', Simulator Of Safety assessment for fire, was developed to simulate fire safety assessment for a structure which is geometrically complex. The program(SOS) is intended to use for searching as well as designing tools to analyse the evacuation safety through a wide range of structure conditions. The computer program has a function which importing FDS's calculating results to each individual resident in the structure. These attributes include a walking speed reduction by producing visibility reduction for each person on the fire. $A^*$ pathfinding algorithm is adopted to calculate the simulation of escape movement, overtaking, route deviation, and adjustments individual speeds in accordance with the proximity of crowd members. This SOS program contributes to a computer package that evaluates the fire safety assessment of individual occupants as they walk towards, and through the exits especially for building, underground spaces like a subway or tunnel.

• 국제초고층학회논문집
• /
• 제12권3호
• /
• pp.203-208
• /
• 2023

The implementation of artificial intelligence (AI) design for tall building structures is an essential solution for addressing critical challenges in the current structural design industry. Generative AI technology is a crucial technical aid because it can acquire knowledge of design principles from multiple sources, such as architectural and structural design data, empirical knowledge, and mechanical principles. This paper presents a set of AI design techniques for building structures based on two types of generative AI: generative adversarial networks and graph neural networks. Specifically, these techniques effectively master the design of vertical and horizontal component layouts as well as the cross-sectional size of components in reinforced concrete shear walls and frame structures of tall buildings. Consequently, these approaches enable the development of high-quality and high-efficiency AI designs for building structures.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 춘계 학술논문 발표대회
• /
• pp.131-132
• /
• 2019

In the Public Notice No. 2019-15 of the Ministry of Employment and Labor, the safety net and regulations on them have been deleted. The performance criterion of the debris net, which also functions as a horizontal safety net in the regulations on the criteria of occupational safety and health, is unclear. When installing a debris net that also functions as a horizontal safety net, a net that meets the performance criteria of KS F 8082 must be installed in accordance with KOSHA C-31-2017. The Korean Standard Specification for Construction Works, which specifies debris net and horizontal safety net, should be revised as soon as possible.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 추계 학술논문 발표대회
• /
• pp.197-198
• /
• 2019

In this study, the study was conducted to derive the utility of the safety management system applying block chain technology and big data technology to improve the problems of construction sites where concealment and operation of safety accidents occur. If block chain technology and big data technology are applied to construction safety management, transparent data can be collected, and based on the collected data, it is possible to predict accidents that can occur at the construction site and establish countermeasures. It can also be an opportunity to strengthen the safety awareness of construction workers and managers, and can clearly identify the responsibility in the event of a safety accident. This study suggests that the application of the 4th Industrial Revolution technology could be a great opportunity to innovate the construction industry which is less than other industries.

• 한국재난정보학회 논문집
• /
• 제18권4호
• /
• pp.754-768
• /
• 2022

연구목적: 본 연구는 교통안전 향상을 위해 적용중인 스마트 교통안전 시스템에 대하여 이용자의 만족도 분석을 통한 개선 사항을 도출하는데 목적이 있다. 연구방법: 설문조사 기반의 IPA 분석을 통해 운전자와 보행자 그룹의 시스템 및 서비스 개선 항목을 도출하였다. 연구결과: 분석 결과, 운전자와 보행자 그룹 모두 Quadrant 1(Keep up the Good Work)은 '위정정보 인지성', Quadrant 3(Low priority)은 '주의정보의 정시성'으로 나타났다. 반면 운전자 그룹에서 Quadrant 1(Keep up the Good Work)로 분석된 'AI 디스플레이 적합성'이 보행자 그룹에서는 Quadrant 3(Low priority)으로 나타났다. 결론: 스마트 보행안전시스템은 이용자에 따라 만족 요인이 달라질 수 있으며, 이용자 중심의 시스템 구축 및 서비스 제공이 필요할 것으로 판단된다.

• 한국화재소방학회논문지
• /
• 제25권3호
• /
• pp.28-41
• /
• 2011

우리나라의 피난방화규정은 1962년 건축법 제정 이후 현재에 이르기까지 많은 변화를 겪어 왔다. 그러나, 과거에 비해 화재안전성능이 어느 정도 개선되었는지, 그리고 현재의 규정은 어느 정도의 화재안전성능을 확보하고 있는지에 대한 정량적인 평가가 이루어지지 않고 있다. 이 연구에서는 과거 화재사례로 비추어 화재발생시 인명피해가 높을 것으로 예상되는 숙박시설 중 호텔건물을 모델로 하여 피난방화규정의 제/개정 시기별 화재안전성능을 평가해 보았다. 그 결과 과거에 비해 화재안전성능이 개선되고는 있으나, 특히 저층부분에서의 거실 및 층피난안전성에서 취약함을 확인할 수 있었다. 숙박시설의 경우 재실자의 화재 인지가 늦어 피난시간이 상대적으로 지연되는 문제점이 있기 때문에, 내부마감재료와 방화문 그리고, 방화구획(면적별/층별) 등의 규정을 보완하여 연기층하강시간을 지연시킬 수 있는 현실적인 방안을 마련 할 필요가 있다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2020년도 봄 학술논문 발표대회
• /
• pp.169-170
• /
• 2020

Occupational Safety and Health Management Cost, used to protect workers in Korean construction worksites and to create safe working environments, is a legally managed expense item. As this cost item is grounded on the Occupational Safety and Health Act, it is always implemented. However, because there is a ceiling on its rates, insufficient amounts of Safety Management Costs are often allocated to worksites, with the money not being used to areas essential to worker safety. As such, the current study raises the need to develop a set of standards to enable some items under the Occupational Safety and Health Management Costs-appropriated under the rate of indirect costs-to be appropriated as direct construction costs. As a preliminary step in this effort, the current study will provide basic data that can be used to create construction cost calculation standards for items that can be calculated as direct construction costs.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.893-903
• /
• 2022

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.