• 디지털산업정보학회논문지
• /
• 제17권4호
• /
• pp.103-108
• /
• 2021

Knowledge graph is a technology that improves search results by using semantic information based on various resources. Therefore, due to these advantages, the knowledge graph is being defined as one of the core research technologies to provide AI-based services recently. However, in the case of the knowledge graph, since the form of knowledge collected from various service domains is defined as plain text, it is very important to be able to analyze the text and understand its meaning. Recently, various lexical dictionaries have been proposed together with the knowledge graph, but since most lexical dictionaries are defined in a language other than Korean, there is a problem in that the corresponding language dictionary cannot be used when providing a Korean knowledge service. To solve this problem, this paper proposes an ontology based on the parts of speech of Korean. The proposed ontology uses 9 parts of speech in Korean to enable the interpretation of words and their semantic meaning through a semantic connection between word class and word class. We also studied various scenarios to apply the proposed ontology to vehicle services.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.215-221
• /
• 2022

In the manufacturing process of the bus treated as the commercial vehicle, after making the bare chassis which is the basic frame of the vehicle body, the part in which passengers ride is connected. In addition, the necessary parts such as the engine and transmission required for the operation of the bus are connected to the bare chassis. The element connecting the parts such as the boarding part of the passengers, the engine, the suspension and the transmission is the bracket. The device required for driving and operating the vehicle is mounted on the bare chassis using the bracket, which should ensure stability during bus operation. In this study, we were performed stress analysis to evaluate the stability of three types of brackets connecting the bare chassis of a new type of 30-seater bus in the development process and components required for driving and operation. The stress analysis should be preceded by the analysis of boundary conditions considering the loads applied to the brackets according to the material of the bracket to be analyzed and the driving type of the bus. The finite element model for structural analysis of brackets according to the driving type of the bus was used by Altair's Hypermesh 2017, and the solver used for structural analysis was Altair's Optistruct. The stress analysis was performed to present the safe and vulnerable parts of the three brackets.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.51.2-51
• /
• 2001

A vehicle driving simulator is a virtual reality device which makes a human being feel as if the one drives a vehicle actually. The driving simulator is effectively used for studying interaction of a driver-vehicle and developing the vehicle system of new concepts. The driving simulator consists of a motion platform, a motion controller, a visual and audio system, a vehicle dynamic analysis system, a vehicle operation system and etc. The vehicle dynamic analysis system supervises overall operation of the simulator and also simulates dynamic motion of a multi-body vehicle model in real-time. In this paper, the main procedures to develop the driving simulator are classified by 4 parts. First, a vehicle motion platform and a motion controller, which generates realistic motion using a six degree of freedom Stewart platform driven hydraulically. Secondly, a visual system generates high fidelity visual scenes which are displayed on a screen ...

• 한국ITS학회 논문지
• /
• 제18권4호
• /
• pp.80-95
• /
• 2019

최근 들어 센서 및 통신기술의 발달로 국내외 연구자들은 장비나 시스템의 상태정보를 수집하여 진단 및 예측 기법을 통한 유지보수를 결정하는 방법론에 대해 연구를 활발히 진행하고 있다. 본 연구에서는 이러한 연구 문헌 고찰을 통해 현시점의 차량부품 상태를 바탕으로 미래 시점까지의 차량부품 상태변화 추이를 예측하여 유지보수 의사결정을 수행하는 시스템 프레임워크를 제시하였다. 또한, 유지보수 활동에 따른 전과 후의 차량부품 상태변화 추적을 통해서 상태 진단 및 예측 데이터 조정이 가능하도록 구성하였다. 향후 본 연구 결과의 적용을 통해 대중버스를 이용하는 시민들의 안전과 차량의 상태기반 유지보수 체계 활성화에 조금이나마 기여할 수 있기를 기대한다.

• 한국전자통신학회논문지
• /
• 제9권2호
• /
• pp.219-230
• /
• 2014

철도차량에 RFID 시스템을 도입함으로써 철도 부품관리 등을 포함한 철도차량의 스마트한 운영관리가 가능하도록 하는 것은 경제적, 산업적 뿐 아니라 사회적으로도 많은 필요성이 대두되고 있다. 본 논문에서는 해외의 RFID 연구 및 개발 활용사례를 조사 분석하였다. 철도 뿐 아니라 다양한 산업분야에 RFID 기술이 적용된 사례에 관해서도 조사하였다. 철도분야에서는 주로 차량위치 검지, 차량인식 등에 RFID 시스템이 사용된 경우가 거의 대부분이었고 부품의 단순이력 관리 등에 응용한 사례도 있었다. 본 연구를 통해, 세계적으로 이미 여러 산업분야에서 RFID 기술이 활용되고 있고 철도분야에서도 여러 국가에서 RFID 기술을 활용한 운영이 활성화되어 있으나 이러한 기술 활용은 주로 차량운행과 관련된 분야에 국한되어 있고 철도부품의 유지보수 등의 분야에서는 RFID 기술개발 및 활용이 미흡하다는 것을 알 수 있었다. 따라서 국내의 철도차량의 스마트한 운영관리를 위해서는 RFID 기술을 철도부품의 유지보수 및 이력관리에 적용할 수 있는 시스템이 반드시 필요하다.

• 한국수소및신에너지학회논문집
• /
• 제29권6호
• /
• pp.661-667
• /
• 2018

Electric vehicles are taken a long time to charge and are restricted driving where charging infrastructure was not sufficiently constructed. The vehicle developed to solve these problems is a plug-in hybrid vehicle. It is possible to drive a certain distance by using electric motor and when the battery runs out, it operate the engine. Plug-in hybrid vehicle have a complicated structure and a lot of parts comparing a general vehicle because the electric parts and the internal combustion engine are installed together. Therefore, as the aging (mileage) of the plug-in hybrid vehicle, the influence which change of fuel consumption is expected to be larger than a general vehicle, but an experimental data are lacking. In this paper, we cumulate a mileage of the plug-in hybrid vehicle about 15,000 km and measured the fuel economy when the cumulated distance reached within 160 km, 6,500 km, 15,000 km respectively, by using domestic public test method. For measuring fuel economy of the vehicle, CD mode (driving distance on a single charge) which use only motor and the CS mode which operate motor and combustion engine were measured respectively. As a result, the fuel economy slightly increased at cumulated mileage of 6,500 km compared to the 160 km and the fuel economy of 15,000 km was similar to 160 km.

• 한국자동차공학회논문집
• /
• 제20권6호
• /
• pp.92-99
• /
• 2012

It is often thought that because no-start motor vehicles cannot start an engine, a fire cannot occur for motor vehicle causes. However, although the engine cannot start up, some parts may be live with electricity if a battery is connected. If the parts have problems, a fire can occur. This study analyzed the causes of fires occurring when a motor vehicle was loaded onto a tow truck to service no-start. It is suggested that no-start motor vehicles should separate a battery terminal to prevent a fire. And this fire is related to automotive products liability.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.187-193
• /
• 2015

When developing a vehicle control system, simulation methods are widely used to validate the whole system in the early development phase. With this regard, the simulator should correctly behave just like the real parts that are not yet implemented while interacting with already implemented parts in real-time. However, most simulators cannot provide functionally and temporally accurate behaviors of the target system. In order to overcome this limitation, this paper proposes a novel real-time simulation technique that can efficiently simulate the temporal behavior as well as the functional behavior of the simulation target system.

• 한국자동차공학회논문집
• /
• 제22권4호
• /
• pp.160-164
• /
• 2014

Recently, there has been an active study about friction force of moving parts for automotive. This study is development and evaluation of oil pockets for journal bearing and tappet valve for range extended electric vehicle. Specially, oil pockets are effect on friction force depend on pitch, size, depth. In this study, fine oil pocket was formed using by etched texturing on the journal bearing and tappet valve. And oil pocket analyzed by SEM and friction force test was carried out by tensile tester. Finally, in this study, it was suggested by round and plane part which journal besring and tappet valve.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.