• Journal of the Korea institute for structural maintenance and inspection
• /
• v.7 no.1
• /
• pp.165-172
• /
• 2003

The fatigue problem of Prestressed Concrete(PSC) bridges are more serious than the other type of concrete bridges, because the cross sectional area and self weight of PSC bridges are smaller. The endurance of strengthening methods for PSC bridges are tested in this study. Glass fiber sheeting and external post-tensioning methods were applied. 1/5 scale PSC beams were made for fatigue test, same as static test. The range of repeated load is from 10% to 80% of yielding load with sine curve. The experimental results show that the failure cycle of strengthened members are increased compare to non-strengthened members. The members strengthened with glass fiber show better enhancement in fatigue problem than the members strengthened with external post-tensioning method, though the adhesion of glass fiber and concrete is failed, as increase of crack. With these experimental results, it can be said that the strengthening methods used in this study are efficient at extending the life time of aged PSC bridges.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.8 no.3
• /
• pp.235-242
• /
• 2004

Bridge Management System (BMS) requires a more objective condition assessment over the lifespan of a given bridge. Thus, a quantitative assessment model of resistance capacity was developed here to meet the requirement for deteriorated concrete bridges. The model focuses on damage mechanisms of concrete bridges deteriorated by traffic loads and environment factors such as chloride and carbonation attacks. Also, it was applied to a typical concrete slab bridge which was severely damaged due to both load and environmental conditions. It was shown that the proposed quantitative model simulates well the deterioration level considering the two damage criteria.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.4
• /
• pp.45-52
• /
• 2019

In this study, the seismic strengthening technique considering the rocking behavior of the wall was developed. The rocking system rotates left and right around the vertical axis of the wall. The development system is a method of dissipating energy by installing a damper which was attached at a large displacement portion. The damper was made of a steel material, and the shape and height of the strut were selected as variables. Experimental results showed that in case of shorter strut make strength capacity increasement and in case of longer strut make deformation capacity increasement. As a result of comparing the abilities according to I and S type strut shapes, it was evaluated that S type has better seismic performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.705-707
• /
• 2022

인체의 흉부 X-ray 영상으로부터 척추질환과 관련된 의료 진단지표를 자동으로 추출하는 과정을 위하여 흉추조직의 정확한 분할이 필요하다. 본 연구에서는 HRNet 기반의 학습을 통하여 흉추조직을 분할하는 방법을 고찰한다. 분할 과정에서 영상 내의 상대적인 위치 정보가 효과적으로 반영될 수 있도록, 계층별로 영상의 고해상도의 표현이 그대로 유지되는 구조와 저해상도의 특징 지도로 변환되는 구조가 병렬적으로 연결되는 형태의 심층 신경망 모델을 채택하였다. 흉부 X-ray 영상에서 콥각도(Cobb's angle)를 산출하는 문제를 대상으로 흉추 분할을 위한 학습 방법, 진단지표 추출 방법 등을 소개하며, 부수적으로 피사체의 위치 변화 및 크기 변화 등에 강인한 성능을 제공하기 위하여 학습 데이터를 증강하는 방법론을 제시하였다. 총 145개의 영상을 사용한 실험을 통하여 제안된 이론의 타당성을 평가하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.480-482
• /
• 2020

동결절편검사는 수술과 연계하여 암 전이 여부를 판단하기 위한 응급한 병리검사가 필요할 때 이용된다. 합성곱 신경망은 이미지 분류에 뛰어난 성능을 보이는 딥러닝 기법으로 본 논문에서는 이를 이용하여 유방암 전이 여부를 자동적으로 진단하는 방법을 제안한다. 실험과정은 전처리, 학습, 후처리의 과정으로 구성되어 있으며, 합성곱 신경망으로는 Resnet-18 모델을 사용하였다. 실험결과 예측 정확도 및 종양의 최대 길이 정합 여부를 점수로 환산하여 약 0.514 의 결과를 보였다.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.19 no.1
• /
• pp.120-127
• /
• 2015

The purpose of this study is to improve the fire prevention performance using the fire venetian blind louver subjected to burning by fire flame. The investigation is based on testing 2 full scale specimens, which is $3m{\times}3m$ module, $850mm{\times}1,500mm$ open, and $900mm{\times}900mm{\times}175mm$ venetian blind louver. Two louver thickness (1.5 and 2.0mm) were adopted. The specimens were exposed to fire flame temperature levels of ISO834 at the lower surface of the fire venetian blind louver specimens with exposure duration of one hour in Korea Institute of Construction Technology (KICT). It was found from the test results that the values of distributed temperature, decreased for all specimens for protecting to fire flame by venetian blind louver. The results of tests were a good fire prevention performance between in initial to 6 mins. At 60 minutes around ISO 834 fire loading, the percentages of distributed temperature in 500mm and 800mm height ranged between 11 and 10% respectively, regardless of louver thickness. This study, therefore, will improve the fire venetian blind louver for fire protection and prevention performance.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.17 no.3
• /
• pp.1-9
• /
• 2013

This paper presents high-velocity impact analysis of two-way RC slabs, including steel fibers and strengthening with fiber reinforced polymer (FRP) sheets for evaluating impact resistance. The analysis uses the LS-DYNA program, which is advanced in impact analysis. The present analysis was performed similarly to the high-velocity impact tests conducted by VTT, the technical research center of Finland, to verify the analysis results. High-velocity impact loads were applied to $2100{\times}2100{\times}250$ mm size two-way RC slab specimens, using a non-deformable steel projectile of 47.5kg mass and 134.9m/s velocity. In this research, extra impact analysis of material specimens was carried out to verify the material models used to the analysis. The elastic-plastic hydrodynamic model, concrete damage model and orthotropic elastic model were used to simulate the non-linear softening behavior of steel fiber reinforced concrete (SFRC), and material properties of normal concrete and FRP sheets, respectively. It is concluded that the suggested analysis technique has good reliability, and can be effectively applied in evaluating the effectiveness of reinforcing/retrofitting materials and techniques. Also, the Steel fiber and FRP sheet strengthening systems provided outstanding performance under high-velocity impact loads.

• Journal of Korean Society of Steel Construction
• /
• v.23 no.5
• /
• pp.629-636
• /
• 2011

This paper describes the smart structural system that uses smart materials for real-time monitoring and active control of bolted joints in steel structures. The impedance-based structural health monitoring (SHM) techniques, which utilize the electro-mechanical coupling property of piezoelectric materials, was used to detect loose bolts in bolted joints. By monitoring the measured electrical impedance and comparing it with the measured baseline, a bolt loosening damage was detected. The damage was evaluated quantitatively using the damage metrics in conductance signature with respect to the healthy states. When loosening damage was detected in the bolted joint, the external heater actuated the shape memory alloy (SMA) washer. Then the heated SMA washer expanded axially and adjusted the bolt tension to restore the lost torque. An experiment was conducted by integrating the piezoelectric-material-based SHM function and the SMA-based active control function on a bolted joint, after which the performance of thesmart self-healing joint system was investigated.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.702-709
• /
• 2010

The performance of mass segmentation is greatly influenced by an initial position of a mass. Some researchers performed mass segmentation with the initial position of a mass given by radiologists. The purpose of our research is to find the initial position for mass segmentation and to notify the segmented mass to radiologists without any additional information on mammograms. The proposed system consists of breast segmentation by region growing and opening operations, decision of an initial seed with characteristics of masses, and mass segmentation by a level set segmentation. A seed for mass segmentation is set based on mass scoring measure calculated by block-based variances and masked information in a sub-sampled mammogram. We used a DDSM database to evaluate the system. The accuracy of mass detection is 78% sensitivity at 4 FP/image, and it reached 92% if multiple views for masses were considered.