• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.680-685
• /
• 2006

Bridges are an integral part of Transportation that is always open to traffic.To effectively manage bridges today, more needs to be done to assess the day-to-day condition and behavior of bridges, and the deterioration rates of their components, so that efficient and proactive measures can be taken. Conventional methods consumemore time and they lack flexibility to reach all locations in high convoluted structures which most bridges offer. Instead, this work uses a new concept of robot, termed as Bridge inspecting robot, which, as its name suggests, possesses superior ability to flex, reach, and approach all points on the bridge. This study also provides economical feasibility model for the same and a comparison with existing bridge inspection and automated inspection work. Finally, we have uncovered few issues and did not analyze some information because of limitation to data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.198-198
• /
• 2021

최근 자연적, 사회적, 정책적 관점에서 하천관리의 중요성이 증대되면서 국가하천 정비를 통한 하천시설 관리의 책임이 증대되고 있다. 국가하천 5대강 본류의 친수지구 이용도 변화를 살펴보면 2015년에 비해 2019년에 면적당 이용객 수가 630,813(명/km²)이 증가하였음을 알 수 있었고(국토교통부, 2020) 본 연구에서는 이용자 수 증가율이 높은 편인 한강 내 하천이용시설을 대상으로 선정하여 해당 지역을 기계학습 기반의 수위예측 알고리즘에 적용하였다. 하천이용시설은 하천이용자가 편리하게 하천을 이용하기 위하여 설치한 시설로 공원시설(강서, 난지, 양화, 망원, 여의도, 이촌, 반포, 잠원, 뚝섬, 잠실, 광나루, 구리)을 위주로 분석하였다. 해당 시설의 침수피해를 고려하기 위해 시계열 자료에 특화된 LSTM(Long Short-term Memory)기법을 활용하여 수위예측 알고리즘을 개발하였고 이를 통해 도출된 홍수 예보로 재난을 대비하고 시설물을 체계적으로 관리하는 유지관리의 효과를 분석하고자 하였다. 입력 자료(input data)는 수위 (EL.m), 팔당댐 방류량 (m³/s), 강화대교의 조위(EL.m)를 사용하였으며 수위예측 알고리즘을 통해 6시간 후 예측 수위값을 도출하여 기존 2단계(주의보, 경보)였던 홍수 예보 단계에서 4단계(관심, 보행자통제, 차량통제, 경계)로 구축하였다. 기존과 세분화된 홍수예보를 적용했을 경우의 유지관리 비용과 편익을 산정하여 하천이용시설의 경제성을 비교·분석한 결과, 유지관리 비용이 기존 대비 약 5% 이상 절감되었고 편익은 약 1.5배 이상 증가하였으며 관리등급은 평균 C등급(보통) 이상 달성하였다. 이는 수위예측 알고리즘의 적용으로 하천이용 활성화 및 투자의 효율성에 목적을 두었으며 향후 분석결과를 토대로 경제성모델을 개발하여 국가하천 내 관리그룹에 적용하면 효율적인 유지관리체계를 제시할 수 있을 것으로 기대된다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.593-599
• /
• 2023

There is risk of derailment due to various factors such as vehicle-track load imbalance in curved parts, so urban railways install and operate derailing prevent guard rails. The angle-type derailing prevent guard rail is composed of various parts including the guard angle. Even if derailment does not occur, various damages occur in the components, so continuous maintenance is required. Through the damage status analysis, the components of the angle-type derailing prevent guard rail with high damage frequency were classified, and conditions for the occurrence of various damages were investigated. In addition, a numerical analysis using a precise 3D numerical model was performed to analyze the cause of the damage analytically. In order to analytically simulate the derailment situation, the static ultimate load condition was applied, and the actual drawing of the angle-type derailing prevent guard rails, rails, and wheels was used for modeling. By analyzing the results of the damage status investigation and finite element analysis, we tried to investigate the damage of the components.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.4
• /
• pp.1269-1278
• /
• 2014

The urban highway, which is a motorway constructed to solve traffic issues, has the characteristic of extremely high damage to life during traffic accidents because the speed of vehicles is higher than typical roadways. In particular, because traffic accidents involving serious injuries hold a very important place among overall traffic accidents, analysis on factors affecting the occurrence of traffic accidents involving serious injuries must be considered with priority when establishing a reduction measure. Therefore, the study built a model that was capable of distinguishing the degree of the factors as part of microscopic analysis for investigating the complex effect of many elements concerning the occurrence of traffic accidents involving serious injuries in urban highways. The results are as follows. First, discriminant model showed a comparatively high level in overall accuracy rates, and, considering the correlation ratio, the models were determined to be valid, as all characteristics of the factors were clearly distinguished. Second, the problems of traffic accidents involving serious injuries on urban highways according to each factor, were clearly drawn out through the discriminant model. Third, the improvement measure for the problems drawn out from the discriminant models were clearly proposed.

• Journal of the Korean Society for Railway
• /
• v.18 no.3
• /
• pp.212-222
• /
• 2015

The characteristics of noise emission from tram systems should be investigated in order to design and construct an urban tram network that raises fewer environmental noise problems. In this paper, the characteristics of rolling noise from a tram were studied and a desired stiffness of the rail supports was proposed using a noise prediction model. The mobilities of embedded rails and resilient wheels were predicted using the Timoshenko beam model and the finite element model, respectively. The predicted mobilities were compared with the measured results. Compared with the measured values, the calculated noise level near the track showed small errors for frequencies higher than 300 Hz. Then, the source strengths of rail and wheel components were examined by varying the rail supporting stiffness and the slab supporting stiffness so that suitable stiffness values could be estimated that would reduce noise radiated from rails and wheels but that would not greatly increase the ground vibration.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.3
• /
• pp.95-106
• /
• 2015

Unused land is a new load of building and a linear improvement, expanding the loss of function of the road abandoned road construction sites, as well as existing roads is possible additional advantage. However, some space is overcharge checkpoints, materials yard, make this vehicle utilization and maintenance of the unfavorable situation, as vehicle rest area but unused land most of the space required for the use of the system management plan. We are analyzed the location, topographical features, cultural property and in the space which is geospatail open platform set up to classify the type of unused land. Depending on the type of unused land using the geospatial open platform performs a 3D model and a proposed model development and application taking into account the environment and landscape. To derive the Gangwon development Plan and design of future route unused land was becoming helps you make better use of unused land.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3A
• /
• pp.305-313
• /
• 2008

A reliability based calibration of dynamic load allowance (DLA) of highway bridge is performed by numerical dynamic analysis of various types of bridges taking into account of the road surface roughness and bridge-vehicle interaction. A total of 10 simply supported bridges with three girder types in the form of prestressed concrete girder, steel plate girder, and steel box girder is analyzed. The cross sections recommended in "The Standardized Design of Highway Bridge Superstructure" by the Korean Ministry of Construction are used for the prestressed concrete girder bridges and steel plate girder bridges while the box girder bridges are designed by the LRFD method. Ten sets of road surface roughness for each bridge are generated from power spectral density (PSD) function by assuming the roadway as "Average Road". A three dimensionally modeled 5-axle tractor-trailer with its gross weight the same as that of DB-24 design truck is used in the dynamic analysis. For the finite element modeling of superstructure, beam elements for the main girder, shell elements for concrete deck, and rigid links between main girder and concrete deck are used. The statistical mean and coefficient of variation of DLA are obtained from a total of 100 DLA results for 10 different bridges with each having 10 sets of road surface roughness. Applying the DLA statistics obtained, the DLA is finally calibrated in a reliability based LRFD format by using the formula developed in the calibration of OHBDC code.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_2
• /
• pp.841-850
• /
• 2019

The purpose of this study is to strengthen the capability of rapid mapping for disaster through improving the positioning accuracy of mapping and fusion of multi-sensing point cloud data derived from Unmanned Aerial Vehicles (UAVs) and disaster investigation vehicle. The positioning accuracy was evaluated for two procedures of drone mapping with Agisoft PhotoScan: 1) general geo-referencing by self-calibration, 2) proposed geo-referencing with optimized camera model by using fixed accurate Interior Orientation Parameters (IOPs) derived from indoor camera calibration test and bundle adjustment. The analysis result of positioning accuracy showed that positioning RMS error was improved 2~3 m to 0.11~0.28 m in horizontal and 2.85 m to 0.45 m in vertical accuracy, respectively. In addition, proposed data fusion approach of multi-sensing point cloud with the constraints of the height showed that the point matching error was greatly reduced under about 0.07 m. Accordingly, our proposed data fusion approach will enable us to generate effectively and timelinessly ortho-imagery and high-resolution three dimensional geographic data for national disaster management in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.38-45
• /
• 2020

A magnetically levitating capsule train, which runs inside the sub-vacuum tube, can reach ultra-fast speeds by dramatically reducing the aerodynamic drag and friction. The capsule train uses the superconductor electrodynamic suspension (SC-EDS) method for levitation. The SC-EDS method has advantages, such as a large levitation gap and free of gap control, which could reduce the infra-construction cost. On the other hand, disadvantages, such as the large variation of the levitation-guidance gap and small damping characteristics in levitation-guidance force, could degrade the running stability and ride comfort of the capsule train. In this study, a dynamic analytical model of a capsule train based on the SC-EDS was developed to analyze the running dynamic characteristics. First, as important factors in the capsule train dynamics, the levitation and guidance stiffness in the SC-EDS system were derived, which depend non-linearly on the velocity and gap variation. A 3D dynamic analysis model for capsule trains was developed based on the derived stiffness. Through the developed model, the effects of the different running speeds on the ride comfort were analyzed. The effects of a disturbance from infrastructure, such as the curve radius, tube sag, and connection joint difference, on the running stability of the capsule train, were also analyzed.