• 유공압시스템학회:학술대회논문집
• /
• 2010.06a
• /
• pp.93-97
• /
• 2010

Wheel skids may occur during train operations due to low adhesion at the wheel-rail contact point abnormally, and the skids, in turn, result in flats appearing on the wheels, which affect safety and ride comfort significantly. Thus, anti-skid control has a crucial role for safe braking and prevention from flats that could cause a disastrous train accident. This paper presents simulation studies on an anti-skid control unit (ASCU) with a brake system of a rolling stock including a pneumatic model for brake power supply and dump valve operation.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.23 no.1
• /
• pp.45-52
• /
• 2010

This paper estimated the impact factor using the finite element program to confirm the dynamic behavior of new type of bridges constructed by introduction of new vehicles and compared the design criteria about the impact factor applied to domestic as well as each country. The study estimated effects of the impact factor according to pipe truss types modeled as respectively 34m, 44m, 54m and span length. The vehicle models are vehicle for bimodal tram of two axis and three axis which passes on actual bridge and dump truck model proposed by Park Young suk(1997). Each vehicle is estimated the impact factor according to velocity from 10 to 100(km/h) and examined. Also, the study investigated and compared the design regulation of domestic and a foreign country based on the impact factor on span center calculated in accordance with vehicle and span length.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.419-432
• /
• 2019

Most of deep learning model training was proceeded by supervised learning, which is to train labeling data composed by inputs and corresponding outputs. Labeling data was directly generated manually, so labeling accuracy of data is relatively high. However, it requires heavy efforts in securing data because of cost and time. Additionally, the main goal of supervised learning is to improve detection performance for 'True Positive' data but not to reduce occurrence of 'False Positive' data. In this paper, the occurrence of unpredictable 'False Positive' appears by trained modes with labeling data and 'True Positive' data in monitoring of deep learning-based CCTV accident detection system, which is under operation at a tunnel monitoring center. Those types of 'False Positive' to 'fire' or 'person' objects were frequently taking place for lights of working vehicle, reflecting sunlight at tunnel entrance, long black feature which occurs to the part of lane or car, etc. To solve this problem, a deep learning model was developed by simultaneously training the 'False Positive' data generated in the field and the labeling data. As a result, in comparison with the model that was trained only by the existing labeling data, the re-inference performance with respect to the labeling data was improved. In addition, re-inference of the 'False Positive' data shows that the number of 'False Positive' for the persons were more reduced in case of training model including many 'False Positive' data. By training of the 'False Positive' data, the capability of field application of the deep learning model was improved automatically.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.1
• /
• pp.63-70
• /
• 2019

The number of vehicle-to-barrier collisions has increased due to improved driving environments. In addition, it is reported that the number of accidents led to impact severity larger than current capacity of a median barrier has increased. It is required to develop a high performance median barrier in order to secure expressway safety. This paper aims at proposing impact loading model and locations for a high performance median barrier based on analysis of median-barrier-related accident history. The SB6 test level (Impact severity: 420 kJ, Mass: 25 ton, Impact speed: 80 km/h, Impact angle: $15^{\circ}$) was suggested for target impact severity based on statistical data analysis. The suitable locations also were proposed from investigation of driver behaviors for installation and rehabilitation of high performance median barrier.

• Journal of Korean Society of Transportation
• /
• v.25 no.3
• /
• pp.77-85
• /
• 2007

The number of accidents occurring at railway crossings is less than the accidents on other sections of roads but they cause enormous socio-economic damages. The geometric aspects of the railway crossing have to allow the drivers to recognize the crossings and take precautions against collisions. Therefore, ensuring visibility for the vehicle approaching the railway crossing is necessary for safe operation of the crossing. However, as there is little research related to railway crossing visibility in Korea. validating visibility and maintaining visibility based on the validation is badly needed. This research develops a visibility validation model to support improving visibility and to reduce accidents at railway crossings to improve safety for the crossing users.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.339-339
• /
• 2017

손상함수란 건물, 차량, 농작물 등과 같은 피해대상물에 재난강도에 따른 취약도(vulnerability)를 정량화한 함수로, 재난리스크 모델에서 널리 사용되는 개념이다. 홍수재난에서 손상함수는 일반적으로 피해지역에서 조사된 경험적 피해자료(empirical data)를 활용하거나, 표준화된 피해대상물에 대한 손상성을 전문가의 의견(expert opinion)을 참고하여 개발된다. 이때, 취약도를 설명하는 설명변수는 일반적으로 침수심(inundation depth)이 사용되며, 그에 따른 취약도는 손상률(percent damage)로서 상대함수 형태가 일반적이다. 본 연구는 주거건물(residential building)에 대한 손상함수 개발을 위해 자연재난 손해사정 경력자(8인)를 대상으로 표준화된 주거건물(단독주택, 아파트, 연립/다세대주택)에 대해 침수에 따른 건물 손상성을 조사하였다. 주거건물 손상성을 설명하는 최대범위는 건물내부 바닥고를 기준으로 침수심 3m까지이며, 침수심 변화에 따른 손상성을 건물신축 공종에 따라 질의하고 이를 종합하였다. 조사과정은 (1) 표준건물에 대한 정의, (2) 공종별 침수에 따른 손상여부 질의, (3) 공종별 최대 손상률 평가 및 주요 피해내역 토의, (4) 공종별 침수심에 따른 손상률 평가, (5) 결과종합의 단계로 진행되었고, 이를 통해 주거건물 유형에 따른 손상함수를 개발할 수 있었다. 본 연구에서 개발된 손상함수는 다양한 침수높이에서 주거건물에 대한 취약도를 설명하는 데 장점이 있으나, 그 결과는 향후 홍수피해지역을 대상으로 수집된 다양한 피해조사 결과와 비교하여 보완될 필요가 있다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.5
• /
• pp.717-732
• /
• 2017

Recently, the construction of underground structure such as a double-deck tunnel is increasing to manage rapid growth of roadway traffic volume. Double-deck tunnel includes middle slab to separate upper and lower road inside, and various sources affect the dynamic behaviour of middle slab due to dynamic loading of vehicle. Therefore, it is important to investigate the dynamic response of middle slab precisely to apply it to design and analysis of double-deck tunnel. In this study, dynamic analysis model of middle slab considering structural type, design velocity, vehicle load, and surface roughness, etc. is built. 3-dimensional dynamic analysis is performed to assess dynamic response of middle slab. Consequently, Dynamic Magnification Factor which represents dynamic response of middle slab shows maximum in case of elastomeric bearings (EB) and average roughness (Grade C). It is also expected that dynamic response can be reduced under the condition of good roughness (Grade B) and fixed bearings (FB).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.469-472
• /
• 2022

With the recent development of intelligent transportation systems, various technologies applying deep learning technology are being used. To crackdown on illegal vehicles and criminal vehicles driving on the road, a vehicle type classification system capable of accurately determining the type of vehicle is required. This study proposes a vehicle type classification system optimized for mobile traffic control systems using YOLO(You Only Look Once). The system uses a one-stage object detection algorithm YOLOv5 to detect vehicles into six classes: passenger cars, subcompact, compact, and midsize vans, full-size vans, trucks, motorcycles, special vehicles, and construction machinery. About 5,000 pieces of domestic vehicle image data built by the Korea Institute of Science and Technology for the development of artificial intelligence technology were used as learning data. It proposes a lane designation control system that applies a vehicle type classification algorithm capable of recognizing both front and side angles with one camera.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.165-175
• /
• 2004

본 고는 대전광역시 첨단교통모델도시 건설사업의 일환으로 구축된 DSRC(Dedicated Short Range Communication) 기술을 활용한 교통정보시스템 구축 사례를 소개함을 목적으로 한다. 공공부문에서의 구간정보 수집 및 가공 체계 구축은 본 대전 ITS 사업이 처음이며 더욱이 DSRC 기술을 구간정보 수집에 적용한 최초의 시도이다. 이에 시스템 구축과정에서 적지 않은 쟁점이 도출되었고, 많은 시행착오를 통해 그 해법을 찾아가며 현재 운영중인 시스템을 완공하게 되었다. 노변기지국(RSE)과 차량장치(OBE)간의 통신에 의해 수집된 자료는, 필터링, 검지기 지점정보, 패턴데이터 등과의 자료합성, 평활화, 통계정보 및 패턴정보 생성 등의 과정을 거쳐 구간소통정보가 산출된다. 현재 운영중인 본 시스템은 향후 지속적으로 보완 발전시켜 나가야 하며, 이를 위해 프로브 수집체계 보완, 시스템의 성능평가, 패턴데이터의 적절한 유지관리, 알고리즘의 지속적 발전 등을 향후과제로서 제시하였다. 본 고는 ITS사업에 있어 중요 쟁점중에 한 분야인 소통정보의 가공 절차를 공유함으로써, 관련 분야의 기술개발 촉진과 향후 유사시스템 구축의 시행착오를 줄이는데 기여할 수 있으리라 판단된다.