http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
실시간 이미지 처리 방법을 이용한 개선된 차선 인식 경로 추종 알고리즘 개발
서은빈,이승기,여호영,신관준,최경호,임용섭,Seo, Eunbin,Lee, Seunggi,Yeo, Hoyeong,Shin, Gwanjun,Choi, Gyeungho,Lim, Yongseob 한국자동차안전학회 2021 자동차안전학회지 Vol.13 No.2
In this study, improved path tracking control algorithm based on pure pursuit algorithm is newly proposed by using improved lane detection algorithm through real time post-processing with interpolation methodology. Since the original pure pursuit works well only at speeds below 20 km/h, the look-ahead distance is implemented as a sigmoid function to work well at an average speed of 45 km/h to improve tracking performance. In addition, a smoothing filter was added to reduce the steering angle vibration of the original algorithm, and the stability of the steering angle was improved. The post-processing algorithm presented has implemented more robust lane recognition system using real-time pre/post processing method with deep learning and estimated interpolation. Real time processing is more cost-effective than the method using lots of computing resources and building abundant datasets for improving the performance of deep learning networks. Therefore, this paper also presents improved lane detection performance by using the final results with naive computer vision codes and pre/post processing. Firstly, the pre-processing was newly designed for real-time processing and robust recognition performance of augmentation. Secondly, the post-processing was designed to detect lanes by receiving the segmentation results based on the estimated interpolation in consideration of the properties of the continuous lanes. Consequently, experimental results by utilizing driving guidance line information from processing parts show that the improved lane detection algorithm is effective to minimize the lateral offset error in the diverse maneuvering roads.
[디젤엔진부문] 대형 LPG 단기통엔진에서의 배기성능에 관한 연구
김진호(jinjo Kim),최경호(gyeungho Choi) 한국자동차공학회 2000 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
The heavy-duty LPG single-cylinder engine was developed as fundamental experiment equipment for analyzing emission performance in the heavy-duty diesel engine. Modified pans for the single-cylinder engine were crank shaft, carnk shaft, fly wheel, crank case and cylinder head. Conventional parts for the engine were connecting rod, push rod and starting motor. Bore and stroke of the developed single-cylinder engine were \3Omm and 140mm. Single cylinder engine had compression ratio of 8, 8.5 and 9. without knocking. It is verified that heavy-duty single-cylinder engine with no-leakage in the motoring test. With the single-cylinder engine, emission performance of the LPG fuel with different spark timing and relative air-fuel ratio showed a good tendency in the relative air-fuel ratio, 1.0
[디젤엔진부문] 다기통 LPG 기관에서 배기온도 저감 연구
조웅래(Unglae Cho),최경호(Gyeungho Choi) 한국자동차공학회 2000 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
The purpose of this study was to investigate about reduction of exhaust gas temperature in LPG engine. A conventional diesel engine was modified to a LPG(Liquified Petroleum Gas) engine that LPG fuel system was set instead of diesel fuel injection pump. Study was performed with measure of exhaust gas temperature by change spark ignition timing, air-fuel ratio and compression ratio. The major conclusion of this work include; (i) exhaust gas temperature is decreased and power is increased with the advanced spark ignition timing and the high compression ratio; (ii) exhaust gas temperature is decreased with lean and rich air-fuel ratio; (iii) finally, one of the important parameters in reduction of exhaust gas temperature is spark ignition timing among the parameters in this study.
[디젤엔진부문] 대형 단기통 디젤엔진에서 Mixer 방식과 LPi 방식에 따른 연소 및 배출가스 특성에 관한 연구
김진호(jinho Kim),정연종(yonjong Chung),최경호(gyeungho Choi),이상준(sangjun Lee),이병호(byungho Lee) 한국자동차공학회 2001 한국자동차공학회 춘 추계 학술대회 논문집 Vol.2001 No.11_1
The purpose of the study is analyzing combustion and emission characteristic in Heavy-duty SCDE (Single Cylinder Diesel Engine) with Mixer and LPi(Liquid propane injection) system. The Mixer and LPi system provides LPG in vapor and liquid phase throughout intake manifold. Sensors such as crank shaft position sensor (CPS) and hall sensor supply spark and injection timing data to the ignition controller. SCDE runs with engine speed of from 800 to 1400rpm, CR of 8, λ value 0.8 ~ 1.3. The major conclusions of this work include i) LPi and Mixer system are similar to BSFC as 275g/kw-h. ii) It is shown CO emissions are lowered as value is increased in rich condition.
LPi엔진의 인젝터 연료누출이 엔진성능에 미치는 영향에 관한 연구
신성근(Seongkeun Shin),이주희(Juhee Lee),최경호(Gyeungho Choi),정연종(Yonjong Chung) 한국자동차공학회 2004 한국자동차공학회 지부 학술대회 논문집 Vol.- No.-
To follow the continually and gradually fortifying regulations for the leakage of noxious emission, the low-pollutant LPG, as fuel, rs becoming popular by days. LPi engine has better ability to excrete the exhaust gas because when the LPG is being injected to the suction port, the suction air's temperature drops by the process of potential heat. However the pressured fuel remains inside the fuel line after the engine rums off and flows into the tiny gaps of the injector. This remaining fuel creates a thick compound of gases in the intake manifold which lowers the efficiency when the engine starts. It is expected that the unburned gas will be exposed and increase the amount of harmful gas in the air. Therefore in this experiment, the basic data to research how the leaking fuel from the LPi engine affects the engine's starting ability is provided. The result of the experimentation for the critical point of the Injector leakage was 21L and the 14th cycle for the starting cycle. Also when 1 ~6L of fuel is leaked, the starting cycle increases to 3rd~7th cycle in a shape of a fan, and the discharge of HC with it as well. The engine started faster when 0.2L of fuel is leaked in the testing for leakage of less than 1L, but as the amount of fuel transpiration increased, the HC emission did the same.
[디젤엔진부문] 개조된 디젤 LPG엔진에서 부탄 및 프로판연료의 연소특성 연구
조웅래(Unglae Cho),정연종(yonjong Chung),최경호(Gyeungho Choi) 한국자동차공학회 2001 한국자동차공학회 춘 추계 학술대회 논문집 Vol.2001 No.11_1
The purpose of this study was to investigate characteristics of combustion and exhaust gas temperature with butane and propane fuel in LPG conversion engine from diesel. A conventional diesel engine was modified to a LPG(Liquified Petroleum Gas) engine that LPG fuel system was set instead of diesel fuel injection pump. Study was performed with different compositions of butane and propane such as butane 100%, propane 100%, .butane 50% propane 50%, butane 70% - propane 30% and butane 30% - propane 70% fuel blends. The major conclusion of this work include; (i) MET spark ignition timing was same with different butane/propane fuel blends except butane 1000/0, 1200 rpm condition. (ii) engine torque and power were not influenced by varied butane/propane fuel blends. (iii) finally, exhaust gas temperature was increased by higher engine speed, it also was decreased by maximum 15℃ with different butane/propane fuel blends.<br/>
배인환,김영후,김태경,오민호,주현수,김슬기,신관준,윤선재,이채진,임용섭,최경호,Bae, Inhwan,Kim, Yeounghoo,Kim, Taekyung,Oh, Minho,Ju, Hyunsu,Kim, Seulki,Shin, Gwanjun,Yoon, Sunjae,Lee, Chaejin,Lim, Yongseob,Choi, Gyeungho 한국자동차안전학회 2019 자동차안전학회지 Vol.11 No.2
This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.