• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.501-511
• /
• 2022

Three-dimensional (3D) models have become crucial for improving civil infrastructure analysis, and they can be used for various purposes such as damage detection, risk estimation, resolving potential safety issues, alarm detection, and structural health monitoring. 3D point cloud data is used not only to make visual models but also to analyze the states of structures and to monitor them using semantic data. This study proposes automating the generation of high-quality 3D point cloud data and removing noise using deep learning algorithms. In this study, large-format aerial images of civilian infrastructure, such as cut slopes and dams, which were captured by drones, were used to develop a workflow for automatically generating a 3D point cloud model. Through image cropping, downscaling/upscaling, semantic segmentation, generation of segmentation masks, and implementation of region extraction algorithms, the generation of the point cloud was automated. Compared with the method wherein the point cloud model is generated from raw images, our method could effectively improve the quality of the model, remove noise, and reduce the processing time. The results showed that the size of the 3D point cloud model created using the proposed method was significantly reduced; the number of points was reduced by 20-50%, and distant points were recognized as noise. This method can be applied to the automatic generation of high-quality 3D point cloud models of civil infrastructures using aerial imagery.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.341-353
• /
• 2022

Pipelines are buried in urban area, and the position (depth and orientation) of buried pipeline should be clearly identified before ground excavation. Although various geophysical methods can be used to detect the buried pipeline, it is not easy to identify the exact information of pipeline due to heterogeneous ground condition. Among various non-destructive geo-exploration methods, ground penetration radar (GPR) can explore the ground subsurface rapidly with relatively low cost compared to other exploration methods. However, the exploration data obtained from GPR requires considerable experiences because interpretation is not intuitive. Recently, researches on automated detection technology for GPR data using deep learning have been conducted. However, the lack of GPR data which is essential for training makes it difficult to build up the reliable detection model. To overcome this problem, we conducted a preliminary study to improve the performance of the detection model using finite difference time domain (FDTD)-based numerical analysis. Firstly, numerical analysis was performed with homogeneous soil media having single permittivity. In case of heterogeneous ground, numerical analysis was performed considering the ground heterogeneity using fractal technique. Secondly, deep learning was carried out using convolutional neural network. Detection Model-A is trained with data set obtained from homogeneous ground. And, detection Model-B is trained with data set obtained from homogeneous ground and heterogeneous ground. As a result, it is found that the detection Model-B which is trained including heterogeneous ground shows better performance than detection Model-A. It indicates the ground heterogeneity should be considered to increase the performance of automated detection model for GPR exploration.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.21 no.5
• /
• pp.421-427
• /
• 2008

A robot crane truck is developed by the Bridge Inspection Robot Development Interface(BRIDI) for an automated and/or teleoperated bridge inspection. This crane truck looks similar to the conventional bucket crane, but is much smaller in size and light-weight. At the end of the telescoping boom which is 12m long, a robot platform is mounted which allows the operator to scan the bridge structure under the deck trough the camera. Boom vibration induced by wind and deck movement can cause serious problems in this scanning system. This paper presents a control system to mitigate such vibration of the robot boom. In the proposed control system, an actuator is installed at the end of the working boom. This control system is studied using a mathematical model analysis with LQ control algorithm and a scaled model test in the laboratory. The study indicates that the proposed system is efficient for the vibration control of the robot booms, thereby demonstrating its immediate applicability in the field.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.4
• /
• pp.48-59
• /
• 2012

Gangform, compared to the traditional forms, is a systemized form which can reduce construction duration and cost by the advantage of using it repeatedly. However, transportation and climbing process of the Gangform is highly dependant on the performance of tower crane. Gangform climbing process takes one day out of six to seven days of a structural work cycle. Tower cranes can not be used in other lifting works when they lift the Gangform during the structural work cycle, causing the delay in the construction project. Numerous efforts and researches have been done in domestic and international industry to solve such limitations of Gangform climbing process. Especially, "A Study on the Development of Automatic Gangform Climbing System for Apartment Housing Construction"has suggested a conceptual model which can climb the Gangform system without a tower crane. In this paper, the technical and economical feasibilities of previously proposed Automatic Gangform climbing system are examined by evaluating its structural stability and lifting load reduction effect.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.5
• /
• pp.301-308
• /
• 2021

It is important to develop a digital SOC (Social Overhead Capital) maintenance system for preemptive maintenance in response to the rapid aging of social infrastructures. Abnormal signals induced from structures can be detected quickly and optimal decisions can be made promptly using IoT sensors deployed on the structures. In this study, a digital SOC monitoring system incorporating a multimetric IoT sensor was developed for long-term monitoring, for use in cloud-computing server for automated and powerful data analysis, and for establishing databases to perform : (1) multimetric sensing, (2) long-term operation, and (3) LTE-based direct communication. The developed sensor had three axes of acceleration, and five axes of strain sensing channels for multimetric sensing, and had an event-driven power management system that activated the sensors only when vibration exceeded a predetermined limit, or the timer was triggered. The power management system could reduce power consumption, and an additional solar panel charging could enable long-term operation. Data from the sensors were transmitted to the server in real-time via low-power LTE-CAT M1 communication, which does not require an additional gateway device. Furthermore, the cloud server was developed to receive multi-variable data from the sensor, and perform a displacement fusion algorithm to obtain reference-free structural displacement for ambient structural assessment. The proposed digital SOC system was experimentally validated on a steel railroad and concrete girder bridge.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.371-393
• /
• 2023

Crack detection in structures plays a vital role in ensuring their safety, durability, and reliability. Traditional crack detection methods sometimes need significant manual inspections, which are laborious, expensive, and prone to error by humans. Deep learning algorithms, which can learn intricate features from large-scale datasets, have emerged as a viable option for automated crack detection recently. This study presents an in-depth review of crack detection methods used till now, like image processing, traditional machine learning, and deep learning methods. Specifically, it will provide a comparative analysis of crack detection methods using deep learning, aiming to provide insights into the advancements, challenges, and future directions in this field. To facilitate comparative analysis, this study surveys publicly available crack detection datasets and benchmarks commonly used in deep learning research. Evaluation metrics employed to check the performance of different models are discussed, with emphasis on accuracy, precision, recall, and F1-score. Moreover, this study provides an in-depth analysis of recent studies and highlights key findings, including state-of-the-art techniques, novel architectures, and innovative approaches to address the shortcomings of the existing methods. Finally, this study provides a summary of the key insights gained from the comparative analysis, highlighting the potential of deep learning in revolutionizing methodologies for crack detection. The findings of this research will serve as a valuable resource for researchers in the field, aiding them in selecting appropriate methods for crack detection and inspiring further advancements in this domain.

• Asia pacific journal of information systems
• /
• v.17 no.3
• /
• pp.105-130
• /
• 2007

Recently, there is a substantial interest in implementing Business Process Management System(BPMS) among enterprises with the purpose of business process innovation. BPMS redesigns and coordinates business processes in terms of both automated steps and human involvement in order to maximize the value of both involved people and systems. The reason why BPMS is getting attention from top managers is that it has the possibility to optimize the business processes by cycling the process of modeling, execution, monitoring, evaluation, and redesigning work processes. Thus, it has created high expectations about not only productivity improvement but also business process innovation. However. having an innovative nature, which is used for process innovation, BPMS implementation has great potential to stir up employee resistance. The analysis and the discussion about the prevention of the resistance against IS(Information Systems) is important because IS change the way people work and also alter the power structure within the organization, in general. The purpose of this study is to investigate factors that have an impact on the effective adoption of BPMS at the enterprise level. To find out these factors, this study considers two characteristics of BPMS: First. BPMS shares some characteristics with other enterprise-wide IS such as ERP. Second, it has special BPMS-specific characteristics. Due to the lack of previous research on BPMS adoption, interviews were carried out with IT-consultants and CIOs who conducted BPMS projects previously to find out BPMS-specific features that would make BPMS unique when compared to other enterprise-wide IS. As a result, the monitoring function was chosen as the main BPMS-specific factor. Thus, this paper reviewed studies both on enterprise-wide IS adoptions, which applied Technology Acceptance Model (TAM) and secondly on computer based monitoring to find out factors that would influence the employees' perception on the monitoring function of BPMS. Based on the literature review, the study suggested three factors that would have an impact on the employee's perception of the monitoring function: fairness of enterprise evaluation system, fairness of the boss, and self-efficacy of their work. Three factors that would impact the enterprise-wide IS adoption were also set: the shared belief in the benefit of BPMS, training, and communication. Then, these factors were integrated with TAM. Structural equation modeling was used to test hypotheses, out factors that would impact the employees' perception on the monitoring function of BPMS. Based on the literature review the study suggested three factors that would have an impact on the employee's perception of the monitoring function: fairness of enterprise evaluation system, fairness of the boss, and self-efficacy of their work. Three factors that would impact the enterprise-wide IS adoption were also set: the shared belief in the benefit of BPMS, training, and communication. Then, these factors were integrated with TAM. Structural equation modeling was used to test hypotheses. The data analysis results showed that two among three monitoring function related factors - enterprise evaluation system and fairness of the boss - were significant. This implies that employees would worry less about the BPMS implementation as long as they perceive the monitoring results will be used fairly for their performance evaluation. However, employees' high self-efficacy on their job was not a significant factor in their perception of the usefulness of BPMS. This is related to cases that showed employees resisted against the information systems because they automated their works (Markus, 1983). One specific case was an electronic company, where the accounting department workers were requested to redefine their job because their working processes were automated due to BPMS implementation.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.6
• /
• pp.407-414
• /
• 2023

In this study, an automated jack-up system, applicable to various fields, was employed for 3D concrete printing and developed as a simultaneous liftable 3D concrete printing system. This developed printing system enables safe and precise jack-up by monitoring the measured jack-up distance using Pearson correlation coefficient analysis and a hydraulic system with interquartile range analysis in real-time during 3D concrete printing operations. It is possible to secure the quality of 3D concrete printing structures, which is essential for expanding the application of 3D concrete printing to construct larger structures. Specimens were printed using both conventional 3D concrete printing and simultaneous liftable 3D concrete printing to evaluate the system performance. The printed specimens were investigated using a 3D scanner. The layer-wise diameter and angle of intersection of the scanned specimens were measured, and an analysis was performed to verify the advantages of the simultaneous liftable 3D concrete printing.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.565-570
• /
• 2024

Recently, due to adjacent excavation work such as new buildings and common tunnel expansion concentrated around the urban railway, deformation of the underground box and tunnel structure of the urban railway built underground has occurred, and as a result, repair and reinforcement work is frequently carried. In addition, the subway is responsible for large-scale transportation, so ensuring the safety and drivability of underground structures is very important. Accordingly, an automated measurement system is being introduced to manage the safety of underground box structures. However, there is no analysis of structural damage vulnerabilities caused by subsidence or uplift of underground box structures. In this study, we aim to analyze damage vulnerabilities for safety monitoring of underground box structures. In addition, we intend to analyze major core monitoring locations by modeling underground box structures through numerical analysis. Therefore, we would like to suggest sensor installation locations and damage vulnerable areas for safety monitoring of underground box structures in the future.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.51 no.spc1
• /
• pp.166-173
• /
• 2006

Soyasaponins are phytochemicals of major interest fur their health benefits. Chemical investigation of a soybean phytochemical concentrate resulted in the isolation and identification of triterpenoid saponins. The MeOH extraction of defatted hypocotyl separated from soybeans was peformed by the automated solvent extractor (ASE). Fractionation was performed on a flash column ($150mm{\times}40mm$ i.d.) packed with a preparative $C_{18}$ reverse phase bulk packing material $(125\AA,\;55-105{\mu}m)$ and monitored at 210 nm, and collected 14 fractions. Consequent Fsat preparative column liquid chromatography (Fast PCLC) was performed for the purification of Fraction-I (Fr-I) collected from the fraction 8 and 9 of flash chromatography. Fsat PCLC was performed on a Luna $C_{18}\;10{\mu}m,\;100{\AA}$, semipreparative reverse phase column ($250cm{\times}50mm$ i.d.) for the purification of isolated unknown compound (Fr-I-2). Chemical structure of acetyl soyasaponin $A_1\;(MW:1436.6,\;C_{67}H_{104}O_{33})$ was identified and determined by a combination of extensive NMR ($^1H-NMR$, 400 MHz; $^{13}C-NMR$, 100 MHz; DEPT), IR, UV, and ESI-MS analysis.