• 한국전자통신학회논문지
• /
• 제16권2호
• /
• pp.319-328
• /
• 2021

본 논문에서는 풍력 발전 수익 극대화 및 비용 최소화를 위해 설치하는 ESS에 대하여 정확한 용량 산정을 하기 위한 목적으로 풍력 단지용 전력량 예측을 다층 퍼셉트론을 이용하여 수행한다. 풍력 발전량을 예측하기 위해 풍속, 풍향, 공기밀도를 변수로 하고 그 변수를 병합하고 정규화한다. 모델을 훈련시키기 위해 병합된 변수를 70% 대 30% 비율로 훈련 및 테스트 데이터로 나눈다. 그런 다음 학습 데이터를 사용하여 모델을 학습시키고 테스트 데이터를 사용하여 모델의 예측 성능도 평가한다. 마지막으로 풍력량 예측 결과를 제시한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 춘계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.234-236
• /
• 2007

Even though the existing train route controlling method, using track circuits, ensures the sufficient number of operation, it still has problems such as discordance between train numbers which was planned for operating and train numbers being operated on the track, and allowing only one train entering for one route. To solve those problems, we study and develop the Smart train route controlling system which uses the real-time informations of train positions. This system enables improve the coefficient of utilization in a certain train route controlling section, and the safety level of train route controlling, but we should ensure satisfying reliability of data about tracks operated by trains. In addition, there is a need to protect accidents caused by erroneous information of train position, by reflecting changes of tracks, for example maintenance, improvement, expansion of tracks. In this paper, we describes data structure of a developed program which required to change CAD files to wiring diagrams and to generate them to data of tracks. And we show the result that the simulator, using the data structure, controls speed and route of trains without problems.

• 한국군사과학기술학회지
• /
• 제26권5호
• /
• pp.392-399
• /
• 2023

This research paper investigates the effectiveness of using computer graphics(CG) based synthetic data for deep learning in military vehicle detection. In particular, we explore the use of synthetic image generation techniques to train deep neural networks for object detection tasks. Our approach involves the generation of a large dataset of synthetic images of military vehicles, which is then used to train a deep learning model. The resulting model is then evaluated on real-world images to measure its effectiveness. Our experimental results show that synthetic training data alone can achieve effective results in object detection. Our findings demonstrate the potential of CG-based synthetic data for deep learning and suggest its value as a tool for training models in a variety of applications, including military vehicle detection.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 추계학술대회 논문집
• /
• pp.1999-2004
• /
• 2008

This study is about to constructing BOM for managing and integrating information, which is drawing, technical data, attribution, design, ordering, cost, weight, process, service, etc. based on train's system, elements, substructure, assembly, components, parts during whole train's lifetime of the next generation. The BOM is the mostly basic structure information as hierarchical data what are parts consisted specific products. The BOM was utilized as essential elements for collectively managing through informing all of the business activity from ordering to supplying. The BOM in railroad is consist of two parts. One is Engineering BOM for design, the other is Production BOM for production, which are utilized in development calculating the quantity of materials. Also the Maintenance BOM is applied to suppling parts and managing malfunction in railroad corporation like the Seoul Metro. There are many kind of BOMs, because of the special character for each step. Therefore We have need to develop BOM which is able to integrate drawing, technical data for helping good circulation between RAMS applied maintenance using database and helpful know-how for development and production. Also the BOM of the next generation must be consisted regard to whole life-cycle.

• 대한기계학회논문집A
• /
• 제29권9호
• /
• pp.1183-1190
• /
• 2005

This paper presents a dynamic model of railway vehicle for the development of a 6-axis tilting train simulator. The tilting train simulator will be used to verify the tilting electronics and tilting control algorithm that are to be applied to the Korean tilting train. The tilting train simulator is composed of 6 electric-driven actuators, a track generation system, a graphic user interface, and a visualization system with a 1600mm-diameter dome screen. The each system shares the data by means of ethernet network in realtime. In this study, a train model of 9-DOF with a force generation system to tilt train body has been developed. The dynamic analysis for the straight track running and curve negotiation of a railway vehicle can be performed in the model. In this study, a verification study for the application of the model to the simulator has been conducted under curving situation on the track with different radii.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.2684-2690
• /
• 2011

The bogie is one of the most important components in a railway vehicle. So a lot of study has been carried out for safety and reliability of the bogie frame in experimental and simulation. In this paper, Presents an experimental study on health monitoring of next generation high-speed train bogie frame. The ultimate objective of this paper is to estimate the sensor located for health monitoring of bogie. The result from this study might be used essential data in order to construct the next generation high speed train bogie frame health monitoring.

• 한국철도학회논문집
• /
• 제18권3호
• /
• pp.186-193
• /
• 2015

본 연구에서는 차세대 고속열차의 신뢰성 성장률 분석에 대한 연구를 수행하였다. 차세대 고속열차의 신뢰성 평가를 효과적으로 수행하기 위해서 6개의 서브시스템으로 분류를 하였으며, 이에 대한 기능블록선도와 신뢰성블록선도를 도출하였다. 또한 안정화 시험 중에 수행된 시험결과를 바탕으로 고장정보분석을 수행하였다. 그리고 Duane 모델에 기반한 신뢰성 성장률 분석을 차세대 고속열차의 실험 결과에 적용하였다. 본 연구를 통해서 지속적인 차량의 유지 보수 활동이 신뢰성 성장에 영향을 미치고 있음을 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.1018-1020
• /
• 2008

Since radio communications based train control system requires considerable amount of information than track circuits based signalling system and these information have significant effects on train control system safety, it is essential to ensure information integrity. In addition, when track information has to be added or changed due to track installation, track maintenance (both corrective and preventive), any information changes must be reported to train control system as soon as possible. In this paper, we provide explanation on the equipment and its data structure. Also, we represent the results of a simulator application to check the information integrity generated by the equipment.

• 한국산학기술학회논문지
• /
• 제18권10호
• /
• pp.681-687
• /
• 2017

본 논문은 고속철도 차량 주행풍에 기반한 풍력 발전의 가능성을 분석한다. 저자는 풍속계와 데이터 분석 프로그램을 포함한 풍속 측정 장비를 구성하였으며, 이를 활용해 실제 고속 철도 차량 노선 부근에서 주행풍의 특성을 측정하였다. 저자는 반복적인 측정을 통해 주행풍 특성의 변화를 야기할 수 있는 다양한 요인들의 영향을 고려하였다. 우선적으로, 저자는 터널의 유무 및 계곡 지형 요인에 의해 구분되는 세 지점에서 개별적으로 주행풍의 풍속 및 지속 시간을 측정하여, 지형 요인에 따른 주행풍의 특성 차이를 분석한다. 또한 세 단계에 걸쳐 높이를 점증시키며 주행풍의 특성을 측정해, 차량과의 상대적인 높이에 따른 주행풍의 변화를 분석한다. 나아가 주행 차량의 특성을 고려하여, 길이와 중량에서 차이가 있는 Korean Train eXpress (KTX) 차량과 Super Rapid Train (SRT) 차량에 따른 주행풍의 차이를 분석한다. 끝으로 측정된 주행풍의 풍속 및 지속 시간을 토대로, 실제 풍력 발전에 도입할 경우 얻을 수 있는 풍력 에너지 수준을 도출하고, 이를 통해 기대되는 효용성에 대해 논의한다.

• 한국철도학회논문집
• /
• 제4권4호
• /
• pp.147-154
• /
• 2001

A high-speed rail system represents a typical example of large-scale multi-disciplinary systems, consisting of subsystems such as train, electrical hardware, electronics, control, information, communication, civil technology etc. The Systems Engineering, as a methodology for engineering and management of today's ever-growing complex system, must be applied to development of such systems. This paper presents systems engineering framework model to have to be applied to the systems engineering technology development task for the korean next-generation high-speed railway systems in progress and demonstrates data models and schema for computer-aided systems engineering software, RDD-100, for use in its development and management.