• Journal of Platform Technology
• /
• v.11 no.6
• /
• pp.13-20
• /
• 2023

Regularly inspecting vehicle tires' condition is imperative for driving safety and comfort. Poorly maintained tires can pose fatal risks, leading to accidents. Unfortunately, manual tire visual inspections are often considered no less laborious than employing an automatic tire inspection system. Nevertheless, an automated tire inspection method can significantly enhance driver compliance and awareness, encouraging routine checks. Therefore, there is an urgency for automated tire inspection solutions. Here, we focus on developing a deep learning (DL) model to predict cracked tires. The main idea of this study is to demonstrate the comparative analysis of DenseNet121, VGG-19 and EfficientNet Convolution Neural Network-based (CNN) Transfer Learning (TL) and suggest which model is more recommended for cracked tire classification tasks. To measure the model's effectiveness, we experimented using a publicly accessible dataset of 1028 images categorized into two classes. Our experimental results obtain good performance in terms of accuracy, with 0.9515. This shows that the model is reliable even though it works on a dataset of tire images which are characterized by homogeneous color intensity.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.6
• /
• pp.267-278
• /
• 2000

Vehicle dynamic models in handing and stability analysis are divided into three groups: bicycle model, roll axis model and full vehicle model. Bicycle model is a simple linear model, which hag two wheels with load transfer being ignored. Roll axis model treats left and right wheels independently. In this model, load transfer has a great effect on nonlinearity of tire model. Effects of suspension system can be analyzed by using full vehicle model, which is included suspension stroke motions. In this paper, these models are validated and compared through comparison with road test, and the effects of suspension kinematics and compliance characteristics on vehicle motion are analyzed. In handling and stability analysis, roll axis model can simulate the real vehicle motion more accurately than full vehicle model. Compliance steer has a significant effect, but the effect of suspension kinematics is negligible.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.565-570
• /
• 2001

Vehicle dynamics control (VDC) system requires more information on driving conditions compared with ABS and/or TCS. In order to develop the VDC system, tire slip angles, vehicle side-slip angle, and vehicle lateral velocity as well as road friction coefficient are needed. Since there are not any cheap and reliable sensors, recent researches on parameter estimation have given rise to a number of parameter estimation techniques. This paper presents new vehicle model to estimate vehicle's yaw rate. This model is improved from the conventional 2 degrees of freedom vehicle model, so-called bicycle model, taking nonlinear effects into account. These nonlinear effects are: (i) tyre nonlinearity; (ii) lateral load transfer during cornering; (iii) variable gear ratio with respect to vehicle velocity. Estimation results are validated with the experimental results.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.415-420
• /
• 2007

The objective of this study analyzes the influence of shimmy & shake phenomena due to tire design parameters which are RFV(radial force variation), DB(dynamic balance), RRO(radial run out) and air pressure. These parameters are inspection items for Q.C. after tires are manufactured. In order to analyze these parameters on this study, vehicle driving tests were achieved. The test modes are two type which are constant speed and coast-down driving. On this tests the dynamic characteristics of shimmy & shake are measured by the 3-axises accelerometers at the various positions that are knuckle(left & right), rack pinion, seat and steering wheel. In according to analyzed results, the longitudinal vibration of knuckle parts affects the lateral vibration of rack pinion and this vibration affects the lateral vibration of steering wheel that is the shimmy phenomena. Also the over and under DB by comparison with normal DB and the increment of RRO affect the occurrence of shimmy & shake phenomena.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.2
• /
• pp.111-119
• /
• 2017

This paper presents a method to determine the rear steering angle in integrated chassis control with electronic stability control (ESC) and rear wheel steering (RWS). A control yaw moment needed to stabilize a vehicle should be distributed into the tire forces generated by the ESC and RWS. Weighted pseudo-inverse control allocation (WPCA) is adopted to determine the tire forces. Four methods are proposed to calculate the rear wheel steering angle. To validate the proposed methods, a simulation is performed using a vehicle simulation software package, CarSim. The simulation results show that the proposed method for determining the rear wheel steering angle improves the performance of the integrated chassis control.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.6
• /
• pp.234-240
• /
• 2002

This paper treats the problem of estimating the longitudinal velocity of a braking vehicle using measurements from an accelerometer and wheel speed data from standard anti-lock braking wheel speed sensors. We develop and experimentally test three velocity estimation algorithms of increasing complexity. The algorithm that works the best gives peak errors of less than 3 percent even when the accelerometer signal is significantly biased.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.1
• /
• pp.106-111
• /
• 2012

Recently the usage of bicycle has increased steeply in Korea owing to traffic culture of well- being. In a car to bicycle accident investigation, the throw distance of bicycle is very important factor for reconstructing of the accident. The variables that influence on the throw distance of bicycle can be classified into the factors of vehicle and bicycle. Simulations and collision tests in actual car to bicycle accident were executed for obtaining throw distance of bicycle. The simulations were done by PC-$CRASH^{TM}$ and for actual crash tests sand bags were used for the behavior of bicyclist instead of dummy. Factors considered were vehicle velocity and the moving angles of bicycle, also the types of bicycle and vehicle were fairy cycle and automobile, respectively. From the results, the throw distances of a head-on tire collision of $0^{\circ}$ direction was longer than that of tire crash test of $45^{\circ}$ direction, and the throw distances of a head -on frame crash test of $90^{\circ}$ direction was longer than that of frame crash test of $45^{\circ}$ direction. In addition restitution coefficient between vehicle and bicycle was estimated as about 0.1 with based on actual crash tests. Finally the increaser vehicle velocity the longer the throw distances of bicycle, and the results of simulation were relatively good agreement to the experimental results.

• Journal of Digital Convergence
• /
• v.10 no.1
• /
• pp.379-384
• /
• 2012

In order to show the assembly process in detail, we used Script languages and it's simulation tried to do an automobile assembly process with 3D. 3D View techniques is the method of the optimum which helps the studying activity from industrial site. We developed 3D View in order to show a assembly process with 3D about engine part and tire part. Specially we experimented the user will be able to study actually using touch screen on the working.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.1
• /
• pp.195-206
• /
• 1997

In this study, a simulation tool is developed in order to investigate non steadystate cornering performance of 4WD/4WS vehicles. The 4WD/4WS vehicles are modeled as a 8-th order dynamic system which includes complex non-linear vehicle dynamics and tire models. The vehicle models are constructed into a modulated simulation tool and are utilized for analyzing cornering performance such as combined braking and steering, cornering on the icy read and $\mu$-split braking, The whole analysis is done with the simulation tool which consists of a number of subsystems and offers graphic environment. Simulation results show that this tool is useful and cost-effective in the dynamic analysis of the combustion-engine vehicles as well as electrically driven vehicles.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.4
• /
• pp.361-370
• /
• 2015

There will inevitably be errors and uncertainties in tire yaw mark related critical speed formula, which is derived merely from the relationship between the centrifugal force and the friction force acting on the point-mass vehicle. Constructing and measuring yaw marks through appropriate simulation works have made it possible to perform uncertainty analysis in calculation of critical speeds under variation of variety of conditions and parameters while existing yaw mark experimental tests have not performed properly. This paper does not present only the critical speed analysis results for parametric sensitivity and uncertainty of chord and middle ordinate, coefficient of friction and road grade, but also modeling uncertainty such as variation of braking level during turning and vehicle size. The yaw mark analysis methods and results may be now applied in practice of traffic accident investigation.