• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2023

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.6 no.2
• /
• pp.191-202
• /
• 1998

An electronic-hydraulic controlled line pressure system was suggested based on the mechanical controlled CVT base model. As a high level control strategy, a 3-D optimal line pressure map was obtained considering the driver's desire, driving conditions. Also, PID type low level controller was designed. Using the high level control strategy and the dynamic models of the base model CVT with electronic controlled line pressure system, performance simulations were carried out. It is seen from the simulation results that fuel economy of the electronic controlled strategy keeps the line pressure low, which results in the improved efficiency of the hydraulic system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.11
• /
• pp.2751-2757
• /
• 2015

To obtain the system requirement specification in the beginning of the precision guidance and control system development, the effectiveness and reliability analysis for the system are necessary. The main purpose of this research is to obtain the system requirement specification by carrying out the effectiveness analysis using the modeling and simulation(M&S) scheme. M&S model is constructed using 6-DOF dynamic model, environment model, guidanc -navigation & control model. Assume that the navigation sensor is consist of inertial navigation sensor(INS) and doppler velocity log(DVL), and the speed and direction of current is environment parameter. The effectiveness analysis is carried out using circular error probability(CEP) and variance analyze scheme. Also, the effectiveness analysis is utilized for cost-performance analysis considering the cost of commercial INS and DVL sensor. This paper shows the high-level INS and the low-level DVL configure a high price-performance integrated navigation system.

• Journal of Power System Engineering
• /
• v.4 no.2
• /
• pp.65-70
• /
• 2000

The shimmy phenomenon, or the radial vibration of steering wheel, happens frequently at a high speed, complicated with suspension system, steering system, vehicle body, engine, transmission and tire. In this study, the suspension system and steering system are modeled by the reference of vehicle body design coordinates(T.L.H), the coordinate system usually used by passenger car maker. In addition, the theoretical results from numerical method have been investigated and compared with the experimental ones by the correlating analysis between the tire and sub-system. The steering and suspension system modeled for the numerical analysis are both independent type. This study developed an analysis program which could forecast the shimmy level in advance by the variation of properties in each system and the change in design of new model.

• Journal of Korean Society of Transportation
• /
• v.28 no.4
• /
• pp.167-175
• /
• 2010

The ubiquitous transportation system environments make it possible to collect each vehicle's position and velocity data and to perform more sophisticated traffic flow management at the individual vehicle or platoon level through vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communication. It is necessary to develop a traffic flow management scheme to take advantage of the ubiquitous transportation system environments. This paper proposes an algorithm to advise the optimal speed for each vehicle according to the traffic flow condition. The algorithm aims to stabilize the traffic flow by advising the equilibrium speed to the vehicles speeding or crawling under freely flowing condition. And it aims to prevent or at least alleviate the shockwave propagation by advising the optimal speed that should dampen the speed drop under critical flow conditions. This paper builds a simulation testbed and performs some simulation experiments for the proposed algorithm. The proposed algorithm shows the expected results in terms of travel time reduction and congestion alleviation.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.05a
• /
• pp.1443-1448
• /
• 2006

The reduction of the vehicle interior noise has been the main interest of NVH engineers. The driver's perception on the vehicle noise is affected largely by psychoacoustic characteristic of the noise as well as the SPL. In particular, the HVAC sound among the vehicle interior noise has been reflected sensitively in the side of psychology. Even though the HVAC noise is not louder than overall noise level, it clearly affects subjective perception in the way of making a diver become nervous or annoyed. Therefore, these days a vehicle engineer takes aim at developing sound quality as well as reduction of noise. In this paper, we acquired noises in the HVAC from many vehicles. Through the objective and subjective sound quality evaluation with acquiring noises caused by the vehicle HVAC system, the simple and multiple regression models were obtained for the subjective evaluation 'Pleasant' using the sound quality metrics. The regression procedure also allows you to produce diagnostic statistics to evaluate the regression estimates including appropriation and accuracy. Furthermore, the neural network model were obtained using three inputs(loudness, sharpness and roughness) of the sound quality metrics and one output(subjective 'Pleasant'). And then the models were compared with correlations between sound quality index outputs and hearing test results for 'Pleasant'. As a result of application of the sound quality index, the neural network was verified with the largest correlation of the sound quality index.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.324-327
• /
• 1996

This paper describes the robust controller design methods applied to the problem of an automatic system for tow-vehicle/trailer combinations. This study followed an inverse Linear Quadratic Regulator(LQR) approach which combines pole assignment methods with conventional LOR methods. It overcomes two concerns associated with these separate methods. It overcomes the robustness problems associated with pole placement methods and trial and error required in the application of the LQR problem. Moreover, a Kalman filter is used as the observer, but is modified by using the loop transfer recovery (LTR) technique with modified transmission zero assignment. The proposed inverse LQG,/LTR controllers enhances the forward motion stability and maneuverability of the combination vehicles. At high speeds, where the inherent yaw damping of the vehicle system decreases, the controller operates to maintain an adequate level of yaw damping. At backward moton, both 4WS (2WS tow-vehicle, 2WS trailer) and 6WS (4WS tow-vehicle, 2WS trailer) control laws are proposed by using inverse LQG/LTR method. To evaluate the stability and robustness of the proposed controllers, simulations for both forward and backward motion were conducted using a detailed nonlinear model. The proposed controllers are significantly more robust than the previous controllers and continues to operate effectively in spite of parameter perturbations that would cause previous controllers to enters limit cycles or to loose stability.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.1
• /
• pp.82-90
• /
• 2013

In this paper, conducted emission from the MDS(Motor Drive System) of a HEV/EV was analyzed using high- frequency circuit modeling in system-level approach. The conducted emission by PWM process can cause RFI(radio- frequency interference) problems in the AM/FM frequency range. In order to mitigate this conducted emission, a high-frequency equivalent circuit model is proposed by analyzing the fundamental circuits, parasitic components in their parts and connections and non-linear characteristics of IGBTs, high-power capacitors, inverters, motors, high-power cables, and bus bars which are composed of the MDS. It is confirmed that the simulated result by the proposed model is well agreed with measured results in spite of a large-scaled analysis in system level. We are looking forward that this approach can be effectively used in the EMC design of HEV/EV.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.2
• /
• pp.133-140
• /
• 2017

In this paper, we has proposed an automatic vehicle monitoring system based on computer vision technology. The real-time display system has displayed a system that can be performed in automatic monitoring and control while meeting the essential requirements of ITS. Another advantage has that for a powerful vehicle tracking, the main obstacle handing system, which has the shadow tracking of moving objects. In order to obtain all kinds of information from the tracked vehicle image, the vehicle must be clearly displayed on the surveillance screen. Over time, it's necessary to precisely control the vehicle, and a three-dimensional model-based approach has been also necessary. In general, each type of vehicle has represented by the skeleton of the object or wire frame model, and the trajectory of the vehicle can be measured with high precision in a 3D-based manner even if the system has not running in real time. In this paper, we has applied on segmentation method to vehicle, background, and shadow. The validity of the low level vehicle control tracker was also detected through speed tracking of the speeding car. In conclusion, we intended to improve the improved tracking method in the tracking control system and to develop the highway monitoring and control system.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.