• International conference on construction engineering and project management
• /
• 2022.06a
• /
• 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.

• Land and Housing Review
• /
• v.15 no.2
• /
• pp.9-17
• /
• 2024

The prototypical building energy model is very useful in building energy policies, research, and technology development. A prototypical apartment model for detailed energy analysis was proposed by Seo et al. in 2014, but sufficient verification was not possible due to the lack of reliable measurement data in predicting the model's energy consumption. However, verification is now possible thanks to a recent study that analyzed the Household Energy Panel Survey (HEPS) data that is released annually by the Korea Energy Economics Institute (KEEI) and published apartment complex benchmark data. The data was used to calibrate the prototypical apartment energy model located in the central region and constructed between 1990 and 1999. The calibrated model was used to verify the other apartment building groups with respect to region and year of completion. Meteorological data for five representative cities each in the central and southern regions were used for the simulation. A majority of the 18 groups produced results that satisfied the MBE and cv(RMSE) criteria.

• Korean Journal of Computational Design and Engineering
• /
• v.21 no.1
• /
• pp.31-41
• /
• 2016

Building Information Modeling (BIM) has been adopted in variety domain of construction industry. In this circumstances, interest of BIM model quality has been increased. In many countries, automated building code checking system by Industry Foundation Classes (IFC) has been developed and studied to use web based building permission systems. IFC is international standard of BIM format. However, the data structure of IFC does not include all of objects and properties about national building codes. In this paper, we developed the information specification between IFC data structure and national building code to increase interoperability. First, we drew the criteria from literature review to analyze the building code. And then, we analyzed building code and sorted objects and properties for automated building code checking. After that we made mapping table between the sorted data and IFC specification. Using the mapping table, we developed pre-specification about building codes information that does not exist in IFC specification. And the defined information can be used to develop the BIM modeling guide and national building permission system. The pre-specification support increasing the interoperability between user and automated building code checking system. Increasing thee interoperability makes improvement accuracy and reliability about result of automated building code checking.

• Asian Journal of Atmospheric Environment
• /
• v.11 no.3
• /
• pp.153-164
• /
• 2017

Odor dispersion around a cubic building from rooftop odor emissions was investigated using computational fluid dynamics (CFD). The Shear Stress Transport (here after SST) $k-{\omega}$ model in FLUENT CFD code was used to simulate the flow and odor dispersion around a cubic building. The CFD simulations were performed for three different configurations of cubic buildings comprised of one building, two buildings or three buildings. Five test emission rates were assumed as 1000 OU/s, 2000 OU/s, 3000 OU/s, 4000 OU/s and 5000 OU/s, respectively. Experimental data from wind tunnels obtained by previous studies are used to validate the numerical result of an isolated cubic building. The simulated flow and concentration results of neutral stability condition were compared with the wind tunnel experiments. The profile of streamline velocity and concentration simulation results show a reasonable level of agreement with wind tunnel data. In case of a two-building configuration, the result of emission rate 1000 OU/s illustrates the same plume behavior as a one-building configuration. However, the plume tends to the cover rooftop surface and windward facet of a downstream building as the emission rate increases. In case of a three-building configuration, low emission rates (<4000 OU/s) form a similar plume zone to that of a two-building configuration. However, the addition of a third building, with an emission rate of 5000 OU/s, creates a much greater odorous plume zone on the surface of second building in comparison with a two-building configuration.

• Wind and Structures
• /
• v.2 no.1
• /
• pp.25-40
• /
• 1999

In this paper, artificial neural networks, a new kind of intelligent method, are employed to model and predict amplitude dependent damping in buildings based on our full-scale measurements of buildings. The modelling method and procedure using neural networks to model the damping are studied. Comparative analysis of different neural network models of damping, which includes multi-layer perception network (MLP), recurrent neural network, and general regression neural network (GRNN), is performed and discussed in detail. The performances of the models are evaluated and discussed by tests and predictions including self-test, "one-lag" prediction and "multi-lag" prediction of the damping values at high amplitude levels. The established models of damping are used to predict the damping in the following three ways : (1) the model is established by part of the data measured from one building and is used to predict the another part of damping values which are always difficult to obtain from field measurements : the values at the high amplitude level. (2) The model is established by the damping data measured from one building and is used to predict the variation curve of damping for another building. And (3) the model is established by the data measured from more than one buildings and is used to predict the variation curve of damping for another building. The prediction results are discussed.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.11a
• /
• pp.114-115
• /
• 2013

The maintenance and repair period consists the largest part of a construction project life cycle cost. However, it has been analyzed that the repairing plan relies on regulations and the officers' experience mostly that sometimes lead to performing unnecessary work. Moreover, the data occurred during repairing have not been stored in a system that can be used in future plans. Therefore, the purpose of this study is to suggest a repairing cost and time predicting model by applying the properties of the building.

• The Journal of Engineering Geology
• /
• v.25 no.3
• /
• pp.395-401
• /
• 2015

An investigation of the tunnel face, as well as related measurement data collected during tunneling, is necessary for rock classification and to determine tunnel stability and the cost efficiency of tunneling. However, systematic management and efficient use of such data have yet to be successfully implemented domestically, and the number of experts in this field in Korea is limited. Thus, measures to develop and implement systematic management and effective use of data and expertise are urgently needed. This study aimed to develop measures to efficiently provide online tunnel design and construction data using a building information model (BIM)-based data visualization approach, based on an integrated 3D tunnel model generation module and a web viewer module. The development technology was verified through ○○ tunnel design and construction. Directions for future study and system improvement are proposed.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.05a
• /
• pp.37-38
• /
• 2018

BIM(Building Information Modeling) in the architecture, VDC(Virtual Design and Construction) defined CIFE(Center for Integrated Facility Engineering) of Stanford university in USA, and Data-driven design definition issued by TECDOC-1284 of IAEA are doing data-level design generated by 3D CAD technology, integrating and managing related information based on the 3D model, and Using 3D models effectively during nuclear power plant life cycle. 3D model of domestic nuclear power industry is using interference review between design fields, 4D system linked 3D construction model and schedule activity, but the 3D model generated in the design phase is effectively not utilized during the construction, operation, decommissioning. therefore, This study is aimed to suggest 3D model LOD(Level of Detail) advancement method through the analysis of existing literature, 2D drawings, and 3D models throughout nuclear power plant lifecycle.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1093-1099
• /
• 2022

The number of buildings is increasing day by day. The next logical footstep is tackling challenges regarding scarcity of resources and sustainability, as well as shifting focus on existing building structures to renovate and retrofit. Many existing old and heritage buildings lack documentation, such as building models, despite their necessity. Technological advances allow us to use virtual reality, augmented reality, and mixed reality on mobile platforms in various aspects of the construction industry. For these purposes, having a BIM model or high detail 3D model is not always necessary, as a simpler model can serve the purpose within many mobile platforms. This paper streamlines a framework for generating a lightweight 3D model for mobile platforms. In doing so, we use an existing structure's site survey data for the foundation data, followed by mobile VR implementation. This research conducted a pilot study on an existing building. The study provides a process of swiftly generating a lightweight 3D model of a building with relative accuracy and cost savings.

• Earthquakes and Structures
• /
• v.7 no.6
• /
• pp.1093-1118
• /
• 2014

A sophisticated story-wise stiffness identification method for a shear building structure is applied to the case where the shear building is subjected to an actual micro-tremor. While the building responses to earthquake ground motions are necessary in the previous method, it is shown that micro-tremors can be used for identification within the same framework. This enhances the extended usability and practicality of the previously proposed identification method. The difficulty arising in the limit manipulation at zero frequency in the previous method is overcome by introducing an ARX model. The weakness of small SN ratios in the low frequency range is avoided by using the ARX model together with filtering and introducing new constraints on the ARX parameters.