http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 박재홍 ( Jaehong Park ) (검색결과 173 건)
- 무료
- 기관 내 무료
- 유료
-
Vehicle Sensor 자료를 이용한 후미 추돌사고의 주행 안전성 평가 방법론 개발
박재홍(PARK, Jaehong),이건우(LEE, Gunwoo),오철(OH, Cheol),김재헌(KIM, Jae Hun),윤덕근(YUN, Dukgeun) 대한교통학회 2021 대한교통학회지 Vol.39 No.6
도로를 주행하는 차량은 인접 차량과의 끊임없는 상호 작용을 통해 차량의 주행 안전성을 확보하고자 한다. 차량의 주행 안전성은 교통안전대체지표를 사용하여 평가 할 수 있으나, 교통안전대체지표를 사용하기 위해서는 상호 작용을 형성하고 있는 주체 차량 및 선행 차량의 모든 주행 정보를 취득해야 한다. 그러나 실도로의 주행 환경에서는 주체 차량을 선행하거나 인접하고 있는 모든 차량의 주행 정보를 수집할 수 없으므로, 주체 차량의 주행 안전성을 평가하는데 한계가 존재한다. 본 연구에서는 이러한 한계점을 보완하기 위하여, 주체 차량의 주행 정보만을 이용하여 차량의 주행 안전성을 평가 할 수 있는 방법론을 개발하였다. 주체 차량의 주행 정보는 속도, 가속도, Jerk를 사용하였으며, 교통안전대체지표에는 선행 차량과 후행 차량의 정지 거리를 비교하여 주행 안전성을 평가하는 Stopping Distance Index(SDI)를 사용하였다. 또한, 주행 안전성을 평가하는 분류기로써 Support Vector Machine(SVM)을 사용했으며, 차량의 주행 정보와 SDI를 입 ‧ 출력 변수로써 사용하였다. 또한, 오차 행렬에서 산출된 분류 정확도, 특이도, 정밀도, 재현율을 기준으로 분류기의 성능을 검증하였다. 분석 결과, 주행 안전성 평가 분류기의 분류 정확도는 80.1%로 나타났으며, 본 연구에서 개발한 주행 안전성 평가 방법론에 대한 타당성을 확보했다는 결론을 제시하였다. Surrogate Safety Measure (SSM) is safety evaluation frameworks designed to evaluate the driving safety of a subject vehicle that is constantly interacting with other adjacent vehicles. To apply these approaches, the trajectory data of all adjacent vehicles, as well as the subject vehicle, must be obtained. Because it is nearly impossible to obtain the trajectory data from all adjacent vehicles in the real world, it is required to develop a novel approach for evaluating the driving safety that does not rely on data from adjacent vehicles. The purpose of this study is to develop a methodology to evaluate driving safety using only the subject vehicle’s trajectory data. To evaluate the driving safety of the subject vehicle, the speed, acceleration, and jerk of the subject vehicle were utilized as driving information, and the Stopping Distance Index (SDI) was employed as a SSM. Furthermore, for the development of the driving safety evaluation algorithm, Support Vector Machine (SVM), a machine learning technique, was utilized as a classifier. As a result, the derived accuracy of the classifier was at 80.1%, and therefore, it was concluded that the validity of the proposed methodology was satisfied.
-
자율주행차량의 도로환경 인식기술 지원을 위한 우선순위 선정 방안
박재홍(Jaehong Park),윤덕근(Duk Geun Yun) 한국산학기술학회 2018 한국산학기술학회논문지 Vol.19 No.2
운전자가 차량 조작에 개입하지 않고, 차량 스스로 주행하는 자율주행차량의 시대가 도래하였다. 자율주행차량 시대에서는 자율주행차량이 도로환경을 정확히 인식함으로써, 자율주행 차량의 안전성을 확보 할 수 있다. 그러나, 도로환경을 구성하고 있는 요소는 도로안전시설, 교통관리시설, 횡단구성으로 구분 할 수 있으며, 각각을 구성하고 있는 종류, 형태 및 규격은 다양하다. 따라서, 도로환경을 구성하고 있는 시설물 중에서 우선적으로 취득해야 하는 도로시설물에 대한 우선순위결정이 필요하다. 본 연구에서는 전문가 설문 및 AHP(Analytical Hierarchy Process)기법을 이용하여 도로시설물 인식에 대한 우선선위를 결정하였다. AHP 분석을 위해 항목을 2계층으로 구분했으며, 1계층은 도로안전시설, 교통관리시설, 횡단구성, 2계층은 시선유도시설을 포함한 26개의 항목을 구분하였다. 분석 결과, 1계층에서는 도로안전시설, 교통관리시설, 횡단구성중 교통관리시설이 가장 우선순위가 높은 것으로 나타났으며, 2계층에서는 방호울타리(도로안전시설), 교통신호기(교통관리시설), 중앙분리대(횡단구성)의 우선순위가 높게 나타났다. 또한, AHP 분석 기법을 이용하여 도출된 고정환경을 추출하는 사례를 제시하였다. 본 연구에서 제시한 도로시설물에 대한 우선순위 선정 결과는 자율주행차량을 위한 인식기술 지원 연구에 도움이 될 것으로 기대된다. The era of autonomous vehicles, which drive themselves and in whose operation the driver does not intervene, is fast approaching. The safety of autonomous vehicles can be guaranteed only if they recognize the road infrastructure. However, the road infrastructure consists of road safety facilities, traffic operation systems, and cross-sectional concerns, which include a variety of components, such as types, shapes, and sizes. Therefore, it is necessary to prioritize the road information. This study was conducted to select the priority with which the road infrastructure attributes should be acquired using the AHP (Analytical Hierarchy Process) method. The road infrastructure attributes were categorized into 2 levels, levels 1 and 2, which consisted of 3 and 26 types of attributes, respectively. As a result of the AHP analysis, it was found that the highest priorities of the road infrastructure are the road safety facilities, traffic operation systems and cross sectional concerns. Also, in level-2, the priorities of the safety barriers (road safety facilities), traffic signals (traffic operation systems), and the median (cross sectional) are the highest. Also, this study provides application examples of road infrastructure extraction with the Point Cloud. The results are expected to support the recognition of technology for autonomous vehicles.
-
-
베어링강의 경도에 따른 DLC박막의 트라이볼로지적 특성
박재홍(JaeHong Park),YoungGoo Jung,김석삼(SeockSam Kim) 한국트라이볼로지학회 2008 한국트라이볼로지학회 학술대회 Vol.2008 No.11
DLC (Diamond Like Carbon) films have predominant mechanical properties like a high hardness, low friction and high chemical resistance; therefore, DLC films are applied in a wide range of industry fields. Especially, we tribologically evaluated characteristics of DLC films deposited on bearing steel that is generally applied to mechanical parts such as Automobile and shipping building etc. We studied on the DLC films deposited on bearing steel (bearing steel) having different hardness. DLC films are deposited on bearing steel having different hardness by RF-PECVD (Radio Frequency - Plasma Enhanced Chemical Vapor Deposition) method. As interlayer, Si-interlayer is deposited on bearing steel to improve adhesion strength by RF -Sputtering method. The DLC film structures were analyzed with Raman spectra and evaluated to Gaussian function. And also, adhesion strength of DLC films was measured with a Scratch tester and we performed wear test with a Tribo-meter to measure coefficient of friction. As a result, DLC films deposited on bearing steel under same deposition condition have typical structure DLC films regardless of hardness of bearing steel. Adhesion strength of DLC film deposited on bearing steel is increased with a hardness of bearing steel. Friction coefficient of DLC film showed lower at the high hardness of bearing steel.
-
-
이동 로봇을 위한 전정안반사 기반 비젼 추적 시스템의 인식 성능 평가
박재홍(Jaehong Park),반욱(Wook Bhan),최태영(Tae-Young Choi),권현일(Hyunil Kwon),조동일(Dong-il Cho),김광수(Kwangsoo Kim) 제어로봇시스템학회 2009 제어·로봇·시스템학회 논문지 Vol.15 No.5
This paper presents a recognition performance of VOR (Vestibular-Ocular Reflex) based vision tracking system for mobile robot. The VOR is a reflex eye movement which, during head movements, produces an eye movement in the direction opposite to the head movement, thus maintaining the image of interested objects placed on the center of retina. We applied this physiological concept to the vision tracking system for high recognition performance in mobile environments. The proposed method was implemented in a vision tracking system consisting of a motion sensor module and an actuation module with vision sensor. We tested the developed system on an x/y stage and a rate table for linear motion and angular motion, respectively. The experimental results show that the recognition rates of the VOR-based method are three times more than non-VOR conventional vision system, which is mainly due to the fact that VOR-based vision tracking system has the line of sight of vision system to be fixed to the object, eventually reducing the blurring effect of images under the dynamic environment. It suggests that the VOR concept proposed in this paper can be applied efficiently to the vision tracking system for mobile robot.
-
-
탑승자 안전도를 고려한 교각 방호시설물 개발에 관한 연구
박재홍 ( Jaehong Park ),성정곤 ( Jung Gon Sung ),남민균 ( Min Gyun Nam ),윤덕근 ( Duk Geun Yun ) 한국안전학회(구 한국산업안전학회) 2018 한국안전학회지 Vol.33 No.5
The traffic accident types are largely classified into vehicle to vehicle accident, vehicle-to-person accident and single-vehicle. Especially, the single-vehicle accident types are severe when the vehicle crashed into road facilities such as bridge, piers, utility poles. The severity of single-vehicle accidents are ten times higher than that of all other accidents types. It is needed to consider to reduce accident severity. This study was conducted to develop crash worthy safety design facility to ensure the vehicle occupant safety. The simulation and the crash tests were conducted for assessment of the safety performance to check the criteria of CC2(Crash Cushion 2) level. THIV(Theoretical Head Impact Velocity) and PHD(Post-impact Head Deceleration) were used to assess occupant impact severity for crashes. The non-redirection collision test conditions for 900 kg and 1,300 kg-head on crash tests, 900 kg-1/4 offset crash tests, 1,300 kg-head on crash test with 15°angle were conducted. The simulation and experiment test result showed that THIV values were below 44 km/h criterion, PHD values were below the 20G. The development non-redirective crash cushion is expected to be used for the fixed object such as bridge piers for assuring occupant safety.
-
인공신경망을 활용한 10 mN급 홀추력기 성능 예측 연구
박재홍(Jaehong Park),도근태(Guentae Doh),이동호(Dongho Lee),김영호(Youngho Kim),최원호(Wonho Choe) 한국추진공학회 2021 한국추진공학회 학술대회논문집 Vol.2021 No.5
본 연구에서는 인공신경망을 이용하여 홀 전기추력기의 추력 및 방전전류 예측 모델링을 수행하였다. 학습데이터는 일차원 하이브리드 파티클-인-셀 기법을 통해 생성되었다. 학습된 인공신경망은 검증을 위한 10 mN급 홀추력기를 대상으로 수행한 전산모사 결과들과 동일하게 0.9999 값의 R-squared를 보여주며 성공적으로 결과 예측의 가능성을 보여 주었다. 특히 제논 양극유량 0.98 mg/s 및 양극전압 250 V조건에서 인공신경망은 10 mN급 홀추력기의 방전전류 및 추력을 각각 0.83 A 및 12.7 mN으로 측정값 대비 5% 이내의 정확도로 성능을 예측했다. A neural network is applied to predict thrusts and discharge currents of Hall thrusters. The training set was generated by the one-dimensional hybrid Particle-In-Cell method. The trained network effectively generalized numerical simulation results by showing that both training and test set had an R-squared of 0.9999, where the test set was a 10 mN class Hall thruster. At the 0.98 mg/s of Xe anode flow rate and 250 V of anode voltage, the network predicted the discharge current and thrust of 10 mN class Hall thruster as 0.83 A and 12.7 mN respectively, which was within 5% of accuracy with measured values.
-
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
