• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.153-163
• /
• 2017

This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.6 no.1
• /
• pp.151-162
• /
• 1998

During a straight driving and cornering maneuver by a vehicle various forces and moments are exerted on the tire's footprint. A cornering properties, handling and stability performances of vehicle can be predicted by these forces and moments values. Therefore, on this study, a lateral force and a aligning torque are predicted by these forces and moments values. Therefore, on this study, a lateral force and a aligning torque are predicted using a finite element method. Contact area of the tire between bead and wheel are fixed to simplify of a finite element model. Lateral force is exerted on the rigid surface as a real load with Coulum friction after inflate and load vertically. Then, rotate the tire's axle to simulate a free rolling untill taken the equilibrium of a aligning torque. Also, experimental observations are made to test a reliability of a FE analysis conducted in this study. The finite element analysis said that good agreement was obtained with experimental results of these cornering properties, giving confidence within about one percent. So it os recommended that a finite element analysis can be used as a good tool to predicted the tire cornering properties.

• Journal of Power Electronics
• /
• v.15 no.6
• /
• pp.1640-1653
• /
• 2015

This study presents a model of a drivetrain for an integrated design of a light electric vehicle (EV). For the drivetrain of each front wheel of the single-person, battery-powered EV tricycle consists of a battery, an inverter, and an outer rotor permanent magnet synchronous motor (PMSM), which is connected to an in-wheel gearbox. The efficiency of the inverter, motor, and gearbox is analyzed over the New European Driving Cycle. To calculate the losses and efficiency of the PMSM, the power electronics in the inverter and gearbox are used. The analytical models provide a fast, but less accurate result, useful for optimization purposes. To accurately predict the efficiency of the PMSM, a finite element model is used. The models are validated by test setups. Correspondingly, a good agreement between the measurements and the calculated results is achieved. A parameter study is performed to investigate the influence of the detailed component parameters (i.e., outer rotor radius, gear ratio, and number of pole pairs and stator slots) on the average efficiency of the drivetrain.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.4
• /
• pp.689-694
• /
• 2016

The objective of this study is to identify the requirements for a energy metering device and develop a real-time energy metering device for measuring energy (electricity) consumption of the electric railway vehicle during its operation. The study also evaluated the performance of the AC voltage sensor, current sensor, and data meter for the device and performed EMC tests such as surge and EFT (Burst). The performance tests showed that the percent errors of the AC voltage sensor and current sensor were ${\leq}0.1%$, and ${\leq}0.5%$ under 10~127V, and 10~250A, respectively. The result of surge and EFT (Burst) tests also indicated that the device had no malfunction in any wave (combination and ring waves) under the treat level with 2kV. The result of the field test also confirmed that the device had no malfunction in data metering.

• Journal of Positioning, Navigation, and Timing
• /
• v.7 no.1
• /
• pp.43-52
• /
• 2018

In recent years, the need of high accuracy navigation for vehicles has increased due to the development of autonomous driving vehicles and increase in land transportation convenience. This study is performed for vehicle users to achieve a performance of centimeter-level positioning accuracy by utilizing Compact Network Real-time Kinematic (RTK) that is applicable as a national-level infrastructure. To this end, medium-baseline RTK was implemented in real time to estimate accurate integer ambiguities between reference stations for reliable generation of Network RTK correction using the linear combination of carrier-phase observations and L1/L2 pseudo-range measurements. The residual tropospheric error was estimated in real time to improve the accuracy of double-differenced integer ambiguity resolution between network configuration reference stations that have at least 30 km or longer baseline distance. In addition, C++ based software was developed to enable real-time generation and broadcasting of Compact Network RTK correction information by utilizing an accurately estimated double-differenced integer ambiguity values. As a result, the horizontal and vertical 95% accuracy was 2.5cm and 5.2cm, respectively, without performance degradation due to user's position change within the network.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.1255-1261
• /
• 2010

An operating information and fault recode of train is very important information for safety driving and maintenance. And these information is increased and need high speed as the number of trains is increased. Wireless LAN or CDMA network is efficient to report more complicated and various information from vehicle to server in control center. Existing wireless transmission system has weakness due to transmission system is separated with TDCS and standalone. At first, standalone system needs space to be installed and cost is increased. And data transmission capacity and speed is limited by complicated structure that transmission system receive data thru serial communication like RS232 and then data transmission system send data to server in control center. This article is study to develop embedded & wireless fault code transmission device to be installed in TDCS to overcome weakness of space and to have more cost effective and simple structure. It is adapted 802.11b/g WiFi for wireless communication and OS is used embedded Linux that can easily implement wireless communication environment and ensure TCP/IP communication’s security. We also implement simple server to test wireless communication between embedded & wireless fault code transmission device and server in control center.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.7
• /
• pp.653-658
• /
• 2016

As this paper is related to the relay and its driving control method, it explains about the relay which connects or interrupts the DC high voltage battery's power to drive the electric car's inverter. The paper suggests a sub-relay which prevents strong sparks from relay's contact point when the relay connects to the DC high voltage battery and also compensates for the increasing internal resistance value that is caused by deterioration at contact point. The relay's rated power is approximately 10KW and the relay's electric property has been verified through electrical instantaneous power short test, etc.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.5
• /
• pp.65-70
• /
• 2012

Torque fluctuation of engine generate gear rattle noise of transmission and many researches have been studied to decrease rattle noise by adjusting clutch damper system. So design optimization of clutch system is very important to decrease rattle noise and need knowing clutch dynamic torque at real vehicle driving condition. This makes it possible to measure clutch dynamic torque by using a small-size magnetic sensor. We install a small-size magnetic sensor on the input shaft of the transmission and measure the relative angular displacement between clutch hub and disc plate. We can obtain the clutch torque correspond to the angular displacement in the clutch torsional characteristics test. The object of this research is to measure clutch dynamic torque on real vehicle condition. Therefore, Clutch dynamic torque is very useful for investigating operating range of clutch according to engine torque and predicting the damping performance of torsional vibration on the powertrain.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.1
• /
• pp.68-75
• /
• 1998

The Intelligent Cruise Control system, ICC, is a driver assisting system for controlling relative speed and distance between two vehicles in the same lane. The ICC may be considered as an extension of a traditional cruise control, not only keeping a fixed speed of the vehicle, but correcting the speed also to that of a slower one ahead. This paper presents a real-time self-tuning fuzzy control algorithm to develop ICC. The self-tuning fuzzy control law is adopted to reduce the effects of nonlinearities of the vehicle and various road environments. In the self-tuning algorithm an interior penalty method is applied to preserve the inherent order of membership functions and is modified as an on-line algorithm for real time application. Via simulations, the performance of the suggested control algorithm is compared with a PID and a fuzzy control without self-tuning. The suggested control algorithm is implemented on PRV III and the results of the test driving on a local road are given.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.21 no.5
• /
• pp.34-39
• /
• 2013

The gear shifting timing of a manual transmission vehicle is influencing fuel economy. This paper focuses on an gear shifting indicator of an city bus with manual transmission, which can improve fuel economy. The shift indicator is supposed to collect the vehicle data during driving, calculate and compare fuel economy with and without gear shifting, and indicate the proper gear shifting timing. The H/W and S/W of the shift indicator are developed and tested on city bus in this research. The experiments are carried out on real road by 3 different drivers and the results show the improvement of fuel economy from 6.0% to 21.4%. The average engine torque and speed are reduced due to early gear shifting and the usage of highest gear is increased. The results of chassis test are also performed and show 7.5% improvement of fuel economy.