• Journal of Hydrogen and New Energy
• /
• v.20 no.1
• /
• pp.38-44
• /
• 2009

Recently, the research focused on fuel cell hybrid vehicles (FCHVs) is becoming an attractive solution due to environmental pollution generated by fossil fuel vehicles. The proper energy control strategy will result in extending the fuel cell lifetime, increasing of energy efficiency and an improvement of vehicle performance. Battery state of charge (SoC) is an important quantity and the estimation of the SoC is also the basis of the energy control strategy for hybrid electric vehicles. Estimating the battery's SoC is complicated by the fact that the SoC depends on many factors such as temperature, battery capacitance and internal resistance. In this paper, battery charging time estimated by SoC is studied by using the speed response and current response. Hybrid system is consist of a fuel cell unit and a battery in series connection. For experiment, speed response of vehicle and current response of battery were determined under different state of charge. As the results, the optimal battery charging time can be estimated. Current response time was faster than RPM response time at low speed and vice versa at high speed.

• Journal of KIISE:Databases
• /
• v.33 no.1
• /
• pp.1-11
• /
• 2006

It is possible to track the moving vehicle as well as to develop the location based services actively according to the progress of wireless telecommunication and GPS, to the spread of network, and to the miniaturization of cellular phone. To provide these location based services, it is necessary for an index technique to store and search too much moving object data rapidly. However the existing indices require a lot of costs to insert the data because they store every position data into the index directly. To solve this problem in this paper, we propose a buffer node operation and design a GU-tree(Group Update tree). The proposed buffer node method reduces the input cost effectively since the operation stores the moving object location data in a group, the buffer node as the unit of a non-leaf node. hnd then we confirm the effect of the buffer node operation which reduces the insert cost and increase the search performance in a time slice query from the experiment to compare the operation with some existing indices. The proposed tufter node operation would be useful in the environment to update locations frequently such as a transportation vehicle management and a tour-guide system.

• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Journal of Korean Society of Transportation
• /
• v.21 no.2
• /
• pp.63-70
• /
• 2003

Real-time information on vehicle queue at intersections is essential for optimal traffic signal control, which is substantial part of Intelligent Transport Systems (ITS). Computer vision is also potentially an important element in the foundation of integrated traffic surveillance and control systems. The objective of this research is to propose a method for detecting an exact queue lengths at signalized intersections using image processing techniques and a neural network model Fuzzy ARTMAP, which is a supervised and self-organizing system and claimed to be more powerful than many expert systems, genetic algorithms. and other neural network models like Backpropagation, is used for recognizing different patterns that come from complicated real scenes of a car park. The experiments have been done with the traffic scene images at intersections and the results show that the method proposed in the paper could be efficient for the noise, shadow, partial occlusion and perspective problems which are inevitable in the real world images.

• Journal of Information Technology and Architecture
• /
• v.10 no.1
• /
• pp.93-100
• /
• 2013

The purpose of this paper is to present Smart Virtual TRS(Trunked Radio System) service that gives the TRS function in mobile network with smart phone application and server. TRS is essential equipment of logistics vehicle so, most of trunk drivers uses TRS frequently. Developed service is based on smartphone without TRS equipment. Therefore, Smart virtual TRS included in TMS(Transportation Management System) has some effects for logistics company. i) Smart Virtual TRS gives better communication environment between office and drivers. ii) Smartphone App gives flexibility to TMS functions. iii) Smart Virtual TRS gives cost reduction effect.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.1
• /
• pp.43-56
• /
• 2013

Personal Rapid Transit(PRT), which is one of the next generation convergence transport technology, PRT system requires operation technology for controlling diverse vehicles and dealing with a variety of abnormal driving situations on a large scale trackway structures in expected operational area more efficiently and reliably. Before developing PRT control technology, it is essential that multiple testing procedures stepwise with building small scale test-tracks and develop real unmanned-vehicles. However, it is expected that the experiments demand huge amount of time and physical cost. Thus, simulation in virtual environment is efficient to develop wireless based control technology for multiple PRT vehicles prior to building real-test environment. In this paper, we propose a VR-based integrated simulator which physics engine is applied so that it enables simulation of front-wheel-steering PRT system rather than simple rail track system. The proposed simulator is also developed that it can reflect geographical features, infrastructures and network topology of expected driving region.

• Proceedings of the KIEE Conference
• /
• 2006.04b
• /
• pp.146-148
• /
• 2006

Interior permanent magnet synchronous motor(IPMSM) has become a popular choice in electric vehicle applications. This paper proposes efficiency optimization control of IPMSM drive using AFLC-FNN(Adaptive Fuzzy Learning Control Fuzzy Neural Network)controller. In order to maximize the efficiency in such applications, this paper proposes the optimal control method of the armature current. The optimal current can be decided according to the operating speed and the load conditions. This paper proposes speed control of IPMSM using AFLC-FNN and estimation of speed using ANN controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The proposed control algorithm is applied to IPMSM drive system controlled AFLC-FNN controller, the operating characteristics controlled by efficiency optimization control are examined in detail.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.56 no.2
• /
• pp.74-82
• /
• 2007

Interior permanent magnet synchronous motor(IPMSM) has become a popular choice in electric vehicle applications, due to their excellent power to weight ratio. This paper proposes efficiency optimization control of IPMSM drive using adaptive fuzzy learning control fuzzy neural network (AFLC-FNN) controller. In order to maximize the efficiency in such applications, this paper proposes the optimal control method of the armature current. The controllable electrical loss which consists of the copper loss and the iron loss can be minimized by the optimal control of the armature current. The minimization of loss is possible to realize efficiency optimization control for the proposed IPMSM. The optimal current can be decided according to the operating speed and the load conditions. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using AFLC-FNN controller. Also, this paper proposes speed control of IPMSM using AFLC-FNN and estimation of speed using ANN controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The proposed control algorithm is applied to IPMSM drive system controlled AFLC-FNN controller, the operating characteristics controlled by efficiency optimization control are examined in detail.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.4
• /
• pp.231-235
• /
• 2015

Bimodal Tram developed by KRRI is driven by a series Hybrid propulsion system which has both the CNG engine, generator and LPB(Lithium Polymer Battery) pack. It has three driving modes; Hybrid mode, Engine mode and Battery mode. Even in case of Battery mode, LPB pack to get enough power to drive the vehicle only by itself onsists of 168 LPB cells(80Ah per lcell), 650V. It is important thing to manage LPB pack in a right way, which will extend the lifetime of LPB cells and operate in the hybrid mode effectively. This paper has shown the development of battery management system(12 BMS, 1 BMS per 14cells) to manage LPB pack which is connected with CAN(Controller Area Network) each other and measure the voltage, current, temperature and also control the cooling fan inside of LPB pack. Using the measured data, BMS can show the SOC(State of Charge), SOH(State of Health) and other status of LPB pack including of the cell balancing.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.287-291
• /
• 2010

In this paper, we designed and implemented mobile object automatic system based on senor networks for telematics. For developing this system, we gather the various sensing data through wireless communication method using zigbee sensor networks and analyze them in monitoring equipment. And we enable the driver to recognize the car state information on the whole by interfacing analyzed data to telematics unit. And, we implemented automatic controller that can control temperature and humidity in car automatically by actuating air conditioner based on the data that was monitored throughout temperature sensor, humidity sensor and brightness sensor based on sensor networks.