PURPOSES : This study develops a model that can estimate travel speed of each movement flow using deep-learning-based probe vehicles at urban intersections. METHODS : Current technologies cannot determine average travel speeds for all vehicles passing through a specific real-world area under obseravation. A virtual simulation environment was established to collect information on all vehicles. A model estimate turning speeds was developed by deep learning using probe vehicles sampled during information processing time. The speed estimation model was divided into straight and left-turn models, developed as fully-offset, non-offset, and integrated models. RESULTS : For fully-offset models, speed estimation for both straight and left-turn models achieved MAPE within 10%. For non-offset models, straight models using data drawn from four or more probe vehicles achieved a MAPE of less than 15%. The MAPE for left turns was approximately 20%. CONCLUSIONS : Using probe-vehicle data(PVD), a deep learning model was developed to estimate speeds each movement flow. This, confirmed the viability of real-time signal control information processing using a small number of probe vehicles.

PURPOSES : This study uses deep learning image classification models and vehicle-mounted cameras to detect types of pavement distress — such as potholes, spalling, punch-outs, and patching damage — which require urgent maintenance. METHODS : For the automatic detection of pavement distress, the optimal mount location on a vehicle for a regular action camera was first determined. Using the orthogonal projection of obliquely captured surface images, morphological operations, and multi-blob image processing, candidate distressed pavement images were extracted from road surface images of a 16,036 km in-lane distance. Next, the distressed pavement images classified by experts were trained and tested for evaluation by three deep learning convolutional neural network (CNN) models: GoogLeNet, AlexNet, and VGGNet. The CNN models were image classification tools used to identify and extract the combined features of the target images via deep layers. Here, a data augmentation technique was applied to produce big distress data for training. Third, the dimensions of the detected distressed pavement patches were computed to estimate the quantity of repair materials needed. RESULTS : It was found that installing cameras 1.8 m above the ground on the exterior rear of the vehicle could provide clear pavement surface images with a resolution of 1 cm per pixel. The sensitivity analysis results of the trained GoogLeNet, AlexNet, and VGGNet models were 93 %, 86 %, and 72 %, respectively, compared to 62.7 % for the dimensional computation. Following readjustment of the image categories in the GoogLeNet model, distress detection sensitivity increased to 94.6 %. CONCLUSIONS : These findings support urgent maintenance by sending the detected distressed pavement images with the dimensions of the distressed patches and GPS coordinates to local maintenance offices in real-time.

In this research, a simulation program is developed in order to investigate non steady-state cornering performance of 6WD/6WS special-purpose vehicles. 6WD vehicles are believed to have good performance on off-the-road maneuvering and to have fail-safe capabilities. But the cornering performances of 6WS vehicles are not well understood in the related literature. In this study, 6WD/6WS vehicles are modeled as a 18 DOF system which includes non-linear vehicle dynamics, tire models, and kinematic effects. Then the vehicle model is constructed into a simulation program using the MATLAB/SIMULINK so that input/output and vehicle parameters can be changed easily with the modulated approach. Cornering performance of the 6WS vehicle is analyzed for brake steering and pivoting, respectively. Simulation results show that cornering performance depends on the middle-wheel steering as well as front/rear wheel steering. In addition, a new 6WS control law is proposed in order to minimize the sideslip angle. Lane change simulation results demonstrate the advantage of 6WS vehicles with the proposed control law.

This research has been conducted to design upright parts of hand-made vehicles with the purpose of reducing material and machining cost while ensuring structural safety. Aluminum knuckles were modelled with three parts in order to enhance design flexibility as well as to reduce CNC machining cost. A vehicle model was constructed in CAD program and simulated in ADAMS View in order to estimate joint forces developing during 20 degree step steering condition at 60km/h. The joint forces obtained in the vehicle dynamics simulation were used for the structural analysis in ANSYS and dimensions of knuckle parts were adjusted until the lowest safety factor reached 2.0. The weight of knuckle decreased by 50% compared to the previous version that was designed without the structural analysis. The overall manufacturing cost decreased by 33% due to the reduction in the material as well as the CNC machining effort.

PURPOSES: This paper develops a new stochastic approach to analyze the pavement-vehicle interaction model with a certain roughness and elasticity for the pavement foundation, thereby accommodating the deflection of the pavement, and to identify the road subsidence zone represented with a sudden changes in the elasticity of the foundation. METHODS: In the proposed model, a quarter-car model was combined with a filtered white noise model of road roughness and a two-layer foundation (Euler-Bernoulli beam for the top surface and Winkler foundation to represent the sub-structure soil). An augmented state-space model for the subsystems was formulated. Then, because the input is White noise and the system is represented as a single system, the Lyapunov equation governing the covariance of the system’s response was solved to obtain a structurally weak zone index (WZI). RESULTS: The results showed that the WZI from the pavement-vehicle interaction model is sensitive enough to identify road subsidence. In particular, the WZI rapidly changed with a small change in foundation elasticity, indicating that the model has the potential to detect road subsidence in the early stage. CONCLUSIONS: Beacause of the simplicity of the calculation, the proposed approach has potential applications in managing road conditions while a vehicle travels along the road and detecting road subsidence using a device with an on-board computational capability, such as a smart phone.

미국 AASHTO LRFD(AASHTO, 2012)나 국내의 도로교설계기준(2012)의 차랑충돌에 대한 교각설계기준을 참조하면 교각 설계 시 차량충돌에 대해 정적인 하중을 고려하도록 제시하고 있다. 한편 2003년 미국 네브래스카 주에 트럭이 교각에 충돌하여 교각 및 교량 상부구조가 붕괴되는 사고가 발생하는 등 차량충돌에 의한 교량붕괴사고는 홍수에 의한 교량붕괴사고에 이은 두 번째 요인으로 분류되기도 한다. 화물차량의 대형화와 도로시스템의 개선으로 인하여 이러한 사고가 발생할 가능성이 중가하고 있다고 볼 수 있다. 본 연구에서는 교각 설계시 차량충돌에 대한 동적 해석을 수행하게 되면 많은 비용과 시간이 소요되어 실용적인 측면에서 연구결과가 쉽게 반영되지 못하고 있으므로 충돌해석 비용과 시간을 저감할 수 있는 모델축소법(model reduction)을 이용한 해석방법을 개발하였으며 그 효용성을 최종변위에 대해 직접충돌해석결과와 비교함으로써 평가하였다.

To estimate fuel consumption of a vehicle, a car can be tested on chassis dynamometer. In this case, test causes a lot of time and money. To predict the fuel efficiency of vehicles in the design stage or early stage of development, the development of computer simulation model is necessary. Using simulation to predict the fuel consumption, the driving model which consists of time-velocity profile and time-grade profile is necessary In this study, vehicle model is developed in MatLab/simulink to estimate real driving fuel consumption rate with time-velocity profile, time-shift gear profile and time-grade profile. Vehicle model consists of driver model, engine model, power train model, and so on. On-road vehicle tests to verify the vehicle model are carried out for analyzing the result of simulation and comparing with those of the experiments.

A study of fuelcell hybrid electronic vehicle for improve fuel consumption is used one wheel dynamic vehicle model and make a profound study of control strategy for cuts fuel consumption. For this reason there is a limit to study of real vehicle fuel consumption increase with weight transfer. This study perform a precision multi-body fuelcell hybrid electronic vehicle modeling using functional suspension model have fast analysis time. Verify a improve fuel consumption in urban driving cycle compare with one wheel dynamic model and demonstrate a power loss decrease by weight transfer is causes of fuel consumption rise.

본 연구에서는 고속철도차량(TGV)이 교량 상을 통과할 경우 교량의 동적 거동을 해석하기 위한 단순화된 3차원 차량-교량 상호작용해석 모델을 제시한다. 축하중 편심 모델링 방법을 도입하여 교량에 작용하는 축하중에 의한 비틀림력과 교량의 비틀림 회전변위의 영향을 고려하여 보다 정확한 교량의 거동에 대한 해석 결과를 얻는다. 앞기관차, 뒷기관차, 객차들에 대해서 운동에너지, 포텐셜에너지, 감쇠에너지를 차량과 교량의 자유도로 각각 나타내고, Lagrange의 운동방정식을 적용하여 차량과 교량의 운동방정식을 유도한다. 또한, 차량-교량 사이에 상호작용을 고려하여 교량에 작용하게 되는 하중에 관한 식을 유도하며, 이러한 하중을 받는 교량의 운동 방정식이 구성된다. 시간경과에 따라 차량의 위치를 결정하면서 그 위치에 따른 차량-교량 시스템의 질량행렬, 강성행렬, 감쇠행렬, 그리고 하중벡터를 구성할 수 있고, Newmark의 방법(평균가속도법)을 이용하여 전체 차량-교량 시스템의 거동을 해석한다.

The purpose of this study is to develop a method to assess the expected damage and loss of vehicle by flood disaster. To this end, we designed the inventory (exposure) DB to define spatial location and distribution by vehicle type, and presented the construction procedure of inventory DB. Vehicle asset value required for quantifying loss was taken into account depreciation in the replacement cost of each representative vehicles. The vehicle vulnerability curve is used to analyze the percent damage due to flood depth. It is classified the vehicle into three types based on the vehicle height, developed the vulnerability curve from the opinion of the expert group. The method proposed in this study is part of f lood loss assessment model. It will be used for flood risk assessment and economic analysis of flood mitigation projects.

This paper has developed a Derailment Containment Provision(DCP) between rails to prevent derailed accident of the train. And developed DCP under impact loading was analytically evaluated using LS-Dyna. This paper was simulated using Mat_72R3 and Mat_CSCM for concrete material. To modify the developed DCP, this paper was suggested suitable and reasonable analytical concrete material model.

The bridges with damage can be a huge threat to human society. However, AASHTO (2012) and Korean Highway Bridge Design Code (2012) do not account for dynamic impacts for bridge column design under the impact loading. It recommends static force for bridge column design due to high computational cost and analysis time. In this study, in order to reduce the computational cost and time for the dynamic analysis, low dimensional model for the dynamic analysis was developed and residual displacements were compared with direct impact analysis.

This paper presents a laboratory validation for a Finite Element model updating method using moving vehicle input-deflection output measurements. In conventional FE model updating, a few natural frequencies measured from field experiments have been used to update the FE model based on the assumption that the mass matrix is known accurately. The proposed approach can update the stiffness matrix without the assumption by using static input-output measurements and can even update the mass matrix by using a few natural frequencies obtained from dynamic measurements. Laboratory experiments were carried out for a scaled model of Samseung Bridge located in the test road of Korea Highway Corporation. For a simplicity of experiments, a mass (11kgf) was located in four different locations on the deck and two deflections were measured by laser displacement meters: one at the center girder, and the other in at the outer girder, both in mid-span. Results showed that the proposed methods was capable to estimate Young's Modulus and the mass density of the model bridge accurately while natural-frequency-based updating may result in significant error when higher modes (2nd, 3rd) were used.

Recent developments in robotics and intelligent vehicle area, bring interests of people in an autonomous driving ability and advanced driving assistance system. Especially fully automatic parking ability is one of the key issues of intelligent vehicles, and accurate parked vehicles detection is essential for this issue. In previous researches, many types of sensors are used for detecting vehicles, 2D LiDAR is popular since it offers accurate range information without preprocessing. The L shape feature is most popular 2D feature for vehicle detection, however it has an ambiguity on different objects such as building, bushes and this occurs misdetection problem. Therefore we propose the accurate vehicle detection method by using a 3D complete vehicle model in 3D point clouds acquired from front inclined 2D LiDAR. The proposed method is decomposed into two steps: vehicle candidate extraction, vehicle detection. By combination of L shape feature and point clouds segmentation, we extract the objects which are highly related to vehicles and apply 3D model to detect vehicles accurately. The method guarantees high detection performance and gives plentiful information for autonomous parking. To evaluate the method, we use various parking situation in complex urban scene data. xperimental results shows the qualitative and quantitative performance efficiently.

본 연구의 목적은 기존의 컨테이너터미널 이송차량의 기술대안을 분석하여 터미널 생산성을 높일 수 있는 고생산성이송차량 모델을 개발하는 것이다. 대안 개발을 위해 YT(Yard Tractor), S/C(Straddle Carrier), SHC(Shuttle Carrier), AGV(Automated Guided Vehicle) 등의 이송차량에 대한 기술적 사양을 분석하며, 이송차량의 기술단계별 세대를 분류하기 위하여 운영현황과 성능을 조사한다. 본 연구에서 제시하는 이송차량의 개발 대안은 향후 고생산성의 진보된 컨테이너 터미널에 유용하게 활용될 것이다.

차량동역학제어시스템은 복잡하고 비선형이므로 잠금방지 제동시스템 및 자동주행시스템 개발에 어려움이 있다. 차량절대속도를 추정하기 위해 퍼지 로직 기법이 최근 적용되어 정상적인 조건에서 만족할 만한 결과를 얻고 있다. 그러나 급격한 제동시 추정오차가 크게 발생되었다. 본 논문에서는 휠 속도 센서를 이용하여 무인 컨테이너 운송차량의 절대속도를 추정하기 위해, 뉴럴 네트워크 모델의 방사대칭 기저함수와 주성분 분석법을 적용하여 10개의 추정 알고리즘중 오차를 4％ 이내로 추정할 수 있는 알고리즘을 제시하였다.