• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.556-567
• /
• 2021

Purpose: In this study, various methods of deep learning-based automatic damage analysis technology were reviewed based on images taken through Unmanned Aerial Vehicle to more efficiently and reliably inspect the exterior inspection and inspection of railway bridges using Unmanned Aerial Vehicle. Method: A deep learning analysis model was created by defining damage items based on the acquired images and extracting deep learning data. In addition, the model that learned the damage images for cracks, concrete and paint scaling·spalling, leakage, and Reinforcement exposure among damage of railway bridges was applied and tested with the results of automatic damage analysis. Result: As a result of the analysis, a method with an average detection recall of 95% or more was confirmed. This analysis technology enables more objective and accurate damage detection compared to the existing visual inspection results. Conclusion: through the developed technology in this study, it is expected that it will be possible to analysis more accurate results, shorter time and reduce costs by using the automatic damage analysis technology using Unmanned Aerial Vehicle in railway maintenance.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.6
• /
• pp.44-56
• /
• 2019

Recently, the paradigm of SOC investment has shifted from new construction to maintenance. This shift became more important for the highway system because it is as one of the most important SOC. In Korea, highway maintenance costs are about 20% of the total annual highway construction budget, which is about two-thirds of developed countries. In addition, establishing standardized guidelines for the highway maintenance operation is not in place. Therefore, in order for domestic road construction and maintenance technology to secure competitiveness in the global construction market, it is urgent to improve the management capacity for maintenance as well as the technology and management capacity. This study examines highway maintenance practices in OECD countries such as North America, Europe, Australia, New Zealand, and Japan to identify core elements of highway maintenance practice. It is imperative to establish a comprehensive management system based upon asset management principle. Even if the budget for the highway construction is reduced, investment in maintenance needs to be maintained.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.6
• /
• pp.751-760
• /
• 2021

Most bridges in Korea are over 20 years old, and many problems linked to their deterioration are being reported. The current practice for bridge inspection mainly depends on expert evaluation, which can be subjective. Recent studies have introduced data-driven methods using building information modeling, which can be more efficient and objective, but these methods require manual procedures that consume time and money. To overcome this, this study developed an image-based automaticbridge component classification network to reduce the time and cost required for converting the visual information of bridges to a digital model. The proposed method comprises two convolutional neural networks. The first network estimates the type of the bridge based on the superstructure, and the second network classifies the bridge components. In avalidation test, the proposed system automatically classified the components of 461 bridge images with 96.6 % of accuracy. The proposed approach is expected to contribute toward current bridge maintenance practice.

• Journal of Korean Society of Disaster and Security
• /
• v.5 no.2
• /
• pp.71-79
• /
• 2012

Recently, in the total railroad construction field, the concrete slab track is adapted, not ballast track. Because the ballast track have the characteristics doing the ongoing maintenance and difficult to handle increasing maintenance costs, eventually the concrete slab track is selected as an alternative. However, owing to the hydration heat reactions and temperature affected shrinkage cracks related to concrete itself, a variety of studies to solve maintenance problems related to concrete slab track are underway. This study analysed characteristics of TQI values evaluating the track irregularity, searched the relationship between crack progress and TQI, and then evaluated of the correlation between the two values. Through this method, there is a need to complete the problems of the current method, only TQI is the main decision making tool in track maintenance, and also the need for the development of evaluation index considering the crack.

• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.1029-1034
• /
• 2009

3자원 정보모델에 기반한 건설프로세서의 혁신이 새로운 추세가 되고 있고 고속철도와 같이 시스템엔지니어링에 해당하는 경우에는 가장 좋은 활용 사례가 될 수 있다. 정보모델은 3차원 영상에 기반하고 다양한 구성요소가 가진 기본정보와 설계와 유지관리에 이르는 생애주기 정보를 저장하고 재활용할 수 있도록 한다. 이 논문에서는 호남고속철도의 한 구간을 대상으로 이미 제안된 철도시설물정보모델의 개념에 근거하여 3차원 정보모델을 구성하였다. 구성된 정보모델에 기반하여 2차원도면, 해석, 견적, 시뮬레이션 등의 각 솔루션으로의 연동성 확보를 위한 시범사업의 결과를 정리하였다. 콘크리트 박스 교량을 대상으로 하는 시범사업을 통해서 생산성 향상 및 3차원 모델의 재활용성을 확보하였다.

• 건강소식
• /
• v.37 no.12
• /
• pp.34-35
• /
• 2013

출고 건조한 요즘, 두피에도 관리경보가 발령된다. 특히 실내에서 사용하는 난방기기들은 두피의 수분을 빼앗아가는 주범이다. 안팎으로 건조한 가운데 예민하고 민감한 두피는 더욱 가렵고 따끔거릴 뿐만 아니라, 각질로 생기는 비듬이 늘고 빠지는 머리카락도 증가하게 된다. 이럴 때일수록 두피를 세심하게 관리해야 탈모를 막고 건강한 머릿결을 유지할 수 있다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.5
• /
• pp.53-60
• /
• 2020

In this study, smart precast-in-place concrete, such as continuity with Precast any technology that can be the Application of Building Structures and railway stations, civil structures. After the same way in the field installation design based on the criteria railways and derived the right section, through the Static and Dynamic Response Analysis. Dynamic sensor and the triaxial acceleration measured by attaching the sensor acceleration response according to the extent of the damage of Precast Panel Structures and mode of Precast Structures, by comparing the data. Data for the stability and improvement of the uncertainty in along a railroad and Future of Precast Panel Structures of time to replace. This is to use this data as basic data on damage prediction.

• Journal of Korean Society of Steel Construction
• /
• v.18 no.1
• /
• pp.47-51
• /
• 2006

Measuring the track geometry of a high-speed railway is the most important task in track construction and track maintenance work. Measuring accuracy is particularly sign the formulation of the maintenance plan and in the assessment of the work quality, and because it can set the train speed limit. To determine the track geometry of a high-speed railway, it is important to use KNR's track recording coach (EM-120). According to the result of the spectrum analysis, noise near the 1-m wave band was found on the track recording data. A new filter was thus applied to remove the noise from the track recording data. A similar result can be acquired when this method is used in real track geometry.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.197-199
• /
• 2021

High speed railway system is progressed to SRN(Smart Railway Network) having entirely automation function beyond each componet automations. It is necessity to use mobile communication technology of LTE-R(Long Term Evolution - Railway) and 5G-R(5th Generation - Railway) and information technology of convergence based on AI, Big Data, Deep Learning to construct this smart railway networks. In this paper, a communication structure is suggested for SRN. This suggested communication structure for SRN is composed to include safety operation of high speed train, railway system management and customer services, and also have complexing function of these each functions. Results of this study can be used for SRN construction and opeation, and development of railway communication standards.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.206-216
• /
• 2020

As the number of aging railway bridges in Korea increases, maintenance costs due to aging are increasing and continuous management is becoming more important. However, while the number of old facilities to be managed increases, there is a shortage of professional personnel capable of inspecting and diagnosing these old facilities. To solve these problems, this study presents an improved model that can detect Local damage to structures using machine learning techniques of AI technology. To construct a damage detection machine learning model, an analysis model of the bridge was set by referring to the design drawing of a non-ballasted plate-girder railroad bridge. Static strain data according to the damage scenario was extracted with the analysis model, and the Local damage index based on the reliability of the bridge was presented using statistical techniques. Damage was performed in a three-step process of identifying the damage existence, the damage location, and the damage severity. In the estimation of the damage severity, a linear regression model was additionally considered to detect random damage. Finally, the random damage location was estimated and verified using a machine learning-based damage detection classification learning model and a regression model.