• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.347-348
• /
• 2022

본 연구에서는 무인이동체를 활용한 철도교량의 외관조사 점검을 보다 효율적이고 객관성 있게 수행하기 위하여 무인이동체를 통해 촬영된 이미지를 딥러닝 기반 분석기술을 활용하여 손상 자동으로 분석 하기위한 기술을 연구하였다. 철도교량의 외관 손상 중 균열, 콘크리트 박리·박락, 누수, 철근노출에 대한 손상 이미지를 추출하여 딥러닝 분석 모델을 생성하고 학습한 분석 모델을 적용한 시스템을 실제 현장에 적용 테스트를 수행하였으며 학습 구현된 분석모델의 검측 재현율을 검토한 결과 평균 95%이상의 감지성능을 검토할 수 있었다. 개발 제안된 자동손상분석 기술은 기존 육안점검 결과 대비 보다 객관적이고 정밀한 손상 검측이 가능하며 철도 유지관리 분야에서 무인이동체를 활용한 외관조사 업무를 수행함에 있어 기존 대비 객관적인 결과도출과 소요시간, 비용저감이 가능할 것으로 기대된다.

• 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.

• Composites Research
• /
• v.35 no.6
• /
• pp.439-446
• /
• 2022

In this study, fiber-reinforced composite coil springs for automobiles were manufactured using the braiding method, and mechanical tests and damage evaluation were performed to confirm their safety. Through the analysis of the load-displacement behavior, the stiffness of the springs was evaluated to meet the specifications. In addition, the distribution of voids and the impregnation rate on the spring wire section were analyzed to clearly understand the criteria for the mechanical properties of the composite material. Moreover, the tested springs were visually inspected to confirm the damaged parts, and the failure mode was analyzed by observing crack initiation and propagation behavior of cross-sectional samples taken from the crack and failure adjacent areas of springs using SEM.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.276-278
• /
• 2022

자율운한선박에 설치되는 침수 및 화재 센서들의 정보를 활용하면 위기대응 상황 판단 및 안전성 분석이 가능하다. 본 연구에서는 대상 선박에 설치된 센서 정보와 대상 선박의 시뮬레이션 해석정보를 활용하여 손상 및 화재로 인한 위기 상황을 자동으로 인지하고 승조원에게 대응과 안전에 관한 정보를 전시하여 제공하는 모듈을 개발하였다.

• Nuclear Engineering and Technology
• /
• v.25 no.4
• /
• pp.515-528
• /
• 1993

In a Passive PWR, the successful actuation of Automatic Depressurization System (ADS) is essentially required so that no core damage is occurred following small LOCA. But it has been shown in the previous studies that Core Damage Frequency (CDF) from small LOCA is significantly caused by unavailability of ADS. In this study, the design vulnerabilities impacting the ADS unavailability have been identified and the design improvement items have been proposed through the system reliability assessment using the fault tree methodology The impacts on CDF according to the change of system unavailability have also been analyzed. In addition, small LOCA simulation using RELAP5/MOD3 code has been performed to show the thermal-hydraulic feasibility of the suggested design enhancements.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.1031-1036
• /
• 2000

지리정보시스템(Geographic Information System)분야에서 사회 기반 시설에 대한 요구가 증대되고, 시설물을 관리하기 위한 지리정보 데이터 베이스 구축이 필요하며, 데이터베이스 구축을 위해서는 지도 정보를 필요로 한다. 본 논문에서는 지도 정보를 자동으로 분석하여 등고선과 숫자, 기호를 추출해 내는 알고리즘에 대해 연구하였다. 지도상의 숫자, 기호를 추출하고 효율적으로 분류하기 위해 불필요한 자료를 제거하고 필요한 정보를 추출한 후 손상된 부분을 복원하는 방법과 필요한 정보만을 추출한 후 손상된 부분을 복원하는 방법을 제안하고 결과를 비교하였다. 이렇게 추출한 정보가 의미를 갖는 단위(기호, 숫자)들로 분류되도록 라벨링 방법과 무게 중심을 이용한 물체 추출 방법을 적용하여 숫자 기호들을 자동으로 분류하였으며, 여러 지역의 지형도를 입력하여 모의실험을 통해 제안한 알고리즘의 효율성을 증명하였다.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1997.05a
• /
• pp.193-198
• /
• 1997

본 논문의 목적은 현재 사용중인 원자력발전소내 금속파편 감시계통 (LMPS: Loose Part Monitoring System)에서 금속파편의 발생위치 평가시 온라인화된 방식을 제안하고 그 효용성을 알아보는 것이다. 현재 사용중인 LMPS들은 센서들을 통해서 기준 진폭수준 이상의 신호가 입력될 때 경보음이 울리고 신호가 기록되도록 되어있다. 이렇게 기록된 신호를 전문가가 분석함으로써 발생한 금속파편 위치 및 계통손상 가능성 등을 평가한다. 그러나 이러한 방법에 의한 신호평가시 경험이 풍부한 전문가에 의해 파편위치 및 손상부위를 평가해야 하므로 많은 시간이 소요되고 금속파편에 의한 손상 잠재성이 큰 경우 즉각적인 조치를 취할 수가 없어 방사능 누출 등의 위험한 상황에 처할 수 있다. 따라서 본 논문에서는 이러한 점에 착안하여 센서로부터의 입력신호 분석 및 평가를 위한 온라인 기법을 제안하고 구조물 모형을 이용한 실험결과를 통하여 그 효용성을 입증한다.

• Composites Research
• /
• v.24 no.4
• /
• pp.36-40
• /
• 2011

This paper described analysis of acoustic emission parameter for the damage evaluation of type II vehicle fuel tank during fracture test. The observation of Kaiser effect, Felicity effect and creep effect is the means of damage evaluation method. It is possible to evaluate tank damage by the ratio of hit of over 60 dB and total hit. Damage mechanism of pressure tank can be estimated by analysis of average rise time, average amplitude.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.32 no.1
• /
• pp.1-6
• /
• 2012

This study is damage evaluation for CNG fuel tank during the burst test through the analysis of acoustic emission signals. Kaiser effect until the pressure 420 bar appears, but More than 420 bar by the creep effect appears significantly damaged vessels, and 480 bar pressure, the Kaiser effect of the rising phase was missing. Resonant transducer at 540 bar than 480 bar decreased activity such as energy and count Continually, but increased wideband transducer. In addition, through the rise time or frequency analysis of composite pressure vessels in order to observe the damage mechanisms wideband transducer is more effective than resonant transducer.

• Journal of the Korea Institute of Building Construction
• /
• v.17 no.6
• /
• pp.545-557
• /
• 2017

The study is about the efficient alternative to concrete surface in the field of visual inspection technology for deteriorated infrastructure. By combining industrial drones and deep learning based image analysis techniques with traditional visual inspection and research, we tried to reduce manpowers, time requirements and costs, and to overcome the height and dome structures. On board device mounted on drones is consisting of a high resolution camera for detecting cracks of more than 0.3 mm, a lidar sensor and a embeded image processor module. It was mounted on an industrial drones, took sample images of damage from the site specimen through automatic flight navigation. In addition, the damege parts of the site specimen was used to measure not only the width and length of cracks but white rust also, and tried up compare them with the final image analysis detected results. Using the image analysis techniques, the damages of 54ea sample images were analyzed by the segmentation - feature extraction - decision making process, and extracted the analysis parameters using supervised mode of the deep learning platform. The image analysis of newly added non-supervised 60ea image samples was performed based on the extracted parameters. The result presented in 90.5 % of the damage detection rate.