• Korean Journal of Construction Engineering and Management
• /
• v.24 no.6
• /
• pp.63-65
• /
• 2023

BIM and AR technologies have been assessed as a means of enhancing productivity within the construction industry, through the provision of effortless access to critical data on site, achieved via the projection of 3D models and associated information onto actual structures. However, most of the previous researches for applying AR technology in construction quality management has been performed for construction projects in general, resulting in only overall on-site management solutions. Also, a few previous researches for the application of AR in the quality management of specific elements like reinforcements focused only on simple projection, so conducting specific quality inspection was impossible. Hence, this study aimed to develop a practically applicable BIM-based AR quality management system targeted for reinforcements. For the development of this system, the reinforcement inspection items on the quality checklist used at railway construction sites were analyzed, and four types of AR functions that can effectively address these items were developed and installed. The validation result of the system for the actual railway bridge showed a degradation of projection stability. This problem was solved through model simplification and enhancement of the AR device's hardware performance, and then the normal operation of the system was validated. Subsequently, the final developed reinforcement quality inspection system was evaluated for practical applicability by on-site quality experts, and the efficiency of inspection would significantly increase when using the AR system compared to the current inspection method for reinforcements.

• Journal of KIBIM
• /
• v.8 no.1
• /
• pp.15-23
• /
• 2018

Geometry control of precast members is the most important technology for modular construction. In this paper, image-based modeling and rendering (IBMR) technology was adopted for 3D modeling of precast elements. It is necessary to use match-casting method for precast post-tensioned column assembly. Preassembly using 3D models created by image processing can minimize construction error. Augmented reality devices are used to check the geometry of the segment. Laboratory-scale tests were performed. The proposed process has been applied to the real precast bridge pier segments.

• IE interfaces
• /
• v.25 no.2
• /
• pp.216-228
• /
• 2012

BIM-based 4D simulation makes people easily understand complex construction process using 3D graphics model and helps them review and identify the construction schedule in each phase of the construction process. Moreover, 4D simulation can be used as reference data to determine the validity of the process in the design phase and will be utilized as a measure for checking the construction process. Therefore 4D simulation of construction improves efficiency of project management. However, current commercial applications available for 4D simulation do not provide sufficient functions for connection of 3D models and process information. In this paper, we propose an automated generation method through the definition of the process based on a work method template and developed the template based schedule generation system (TSGS).

• Journal of KIBIM
• /
• v.6 no.3
• /
• pp.15-23
• /
• 2016

The purpose of this study is to present the possibility of adopting beacons to implement the fire evacuation guidance system in order to reduce the evacuation time for a fire in complex buildings. A beacon-based evacuation system can quickly detect a fire's origin, optimal path of evacuation involved with the exits and the location of evacuees using information collected by the proposed system. The assessment is conducted by integrating different scenario models including fire simulation. Based on the research result, beacon is an effective tool to warn potential hazards or to provide early detection and a safe escape.

• Journal of KIBIM
• /
• v.8 no.4
• /
• pp.13-22
• /
• 2018

Future performance prediction of bridges is challenging task for structural engineers. Well-organized information from design, construction and operation stages is essential for the assessment of structures. Digital twin model is a new concept to realize more reliable data platform for management of infrastructures. Damage history including degradation of material, cracking, corrosion, etc. needs to be accumulated in the digital model. The digital model is linked to the analysis model for the assessment of structural performance considering changed mechanical properties of structural components. In this paper, initial definition digital twin model of a PSC-I girder bridge is proposed.

• Journal of KIBIM
• /
• v.8 no.4
• /
• pp.34-40
• /
• 2018

As the number of aged bridges increases, the development of efficient bridge maintenance techniques is becoming more important. Particularly, there have been many studies on digital-twin models of bridges for maintenance and SHM (Structure Health Monitering). However, in order to use the digital-twin model for maintenance of the bridge, the model updating process that matches the structural response between the real bridge and the digital-twin bridge model must be done. This study presents a model updating method that adjusts bridge's stiffness and boundary condition with genetic algorithm (GA) using static displacements and verified proposed updating method through field test on PSC girder bridge. This study also proposes a conceptual idea to construct an efficient bridge maintenance system by applying the updated numerical analysis model to the digital-twin model.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.6
• /
• pp.549-557
• /
• 2017

In order to improve the productivity in the civil engineering field, efforts to apply BIM have been continuing, however, research on information modeling of tunnel structures considering alignment is insufficient. In this study, we proposed the method of building tunnel models reflecting curved alignment by transferring point data to BIM Authoring Tools(BAT) through discretization of alignment in Alignment-centered Modeling Tools(AMT). IFC data schema was derived to consider the physical and spatial elements of tunnel structures and alignment and IFC-based information management for tunnel alignment, tunnel structures and ground conditions was possible by referring to the extended data schema and including meanings in IFC property sets. The ratings for ground condition in Rock Mass Rating(RMR) and Q-system was automatically derived by using generated information model according to the proposed method.

• Spatial Information Research
• /
• v.20 no.2
• /
• pp.1-11
• /
• 2012

In the current construction planning and designing process, an architectural miniature model was designed to verify the interior or exterior spatial sense of a building structure, but building of the miniature model is demand much more effort and time; in addition to this it has limitation to identify interior information of the building. For a complement of it, CAD would be used in the existing planning and designing process to visualize the building information, but its visualization is not satisfactory for the 3D volume which could be easily verified with the miniature model. CAD is the specific software for designing building structures and the 3D results are usually rendered on 2D monitor screen. Therefore, there is a shortage of cognitive immersion for the 3D space. In this paper, we introduce the conversion process of BIM shape data into the Augmented Reality contents by using a series of softwares. As a result of modification on construction plan or design we reduced the cost and time to reconstruct the final visualization. We have shown that the interior or exterior information of the building structures are easily visualized with BIM shape data on augmented reality environment. Several proposed interaction methods, such as rem oval of building components, and slice-cut operation, provide the user for the effective manipulation of models on the augmented reality environment.

• Land and Housing Review
• /
• v.14 no.3
• /
• pp.145-155
• /
• 2023

Recently, with the widespread adoption of Building Information Modeling (BIM) technology in the construction industry, various object detection algorithms have been used to verify errors between 3D models and actual construction elements. Since the characteristics of objects vary depending on the type of construction facility, such as buildings, bridges, and tunnels, appropriate methods for object detection technology need to be employed. Additionally, for object detection, initial object images are required, and to obtain these, various methods, such as drones and smartphones, can be used for image acquisition. The study uses a 360° camera optimized for internal tunnel imaging to capture initial images of the tunnel structures of railway and road facilities. Various object detection methodologies including the YOLO, SSD, and R-CNN algorithms are applied to detect actual objects from the captured images. And the Faster R-CNN algorithm had a higher recognition rate and mAP value than the SSD and YOLO v5 algorithms, and the difference between the minimum and maximum values of the recognition rates was small, showing equal detection ability. Considering the increasing adoption of BIM in current railway and road construction projects, this research highlights the potential utilization of 360° cameras and object detection methodologies for tunnel facility sections, aiming to expand their application in maintenance.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.5
• /
• pp.1047-1057
• /
• 2024

Recently, deep neural network-based reinforcement learning models have been applied in various advanced industrial fields such as autonomous driving, smart factories, and home networks, but it has been shown to be vulnerable to malicious adversarial attack. In this paper, we applied deep reinforcement learning models, DQN and PPO, to the autonomous driving simulation environment HighwayEnv and conducted three adversarial attacks: FGSM(Fast Gradient Sign Method), BIM(Basic Iterative Method), PGD(Projected Gradient Descent) and CW(Carlini and Wagner). In order to respond to adversarial attack, we proposed a method for deep learning models based on reinforcement learning to operate normally by removing noise from adversarial images using a bilateral filter algorithm. Furthermore, we analyzed performance of adversarial attacks using two popular metrics such as average of episode duration and the average of the reward obtained by the agent. In our experiments on a model that removes noise of adversarial images using a bilateral filter, we confirmed that the performance is maintained as good as when no adversarial attack was performed.