• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.2
• /
• pp.32-43
• /
• 2004

In this paper, a system which can effectively recognize the plate image extracted from camera set on a moving car is proposed. To extract car licence plate from moving vehicles, multiple candidates are maintained based on the strong vertical edges which are found in the region of car licence plate. A candidate region is selected among them based on the ratio of background and characters. We also make a comparative study of recognition performance between support vector machines and modular neural networks. The experimental results lead us to the conclusion that the former is superior to the latter. For a better recognition rate, a simple method combining the support vector machine with modular neural network where the output of the latter is used as the input of the former is suggested and evaluated. As we expected, the hybrid one shows the best result among those three methods we have mentioned.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.4 s.247
• /
• pp.428-434
• /
• 2006

Pulse laser welding of AISI 304 stainless steel plate was simulated to find optimal welding conditions by using commercial finite element code MARC. Due to geometric symmetry, a half model of AISI 304 stainless steel plate was considered and user subroutines were applied to boundary condition for the heat transfer. Material properties such as conductivity, specific heat, mass density and latent heat were given as a function of temperature. A moving heat source was designed on the basis of experimental data. As a result, Nd:YAG laser welding for AISI 304 stainless steel was successfully simulated and it should be useful to determine optimal welding condition.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.04b
• /
• pp.300-304
• /
• 1993

Chip formation control is an important problem in the automation of manufacturing process, since the continuous chip can cause catastrophic failures of the tooling and entangle the workpiece causing damage. However, it is impossible to predict chip form correctly due to the complex nature of cutting process. In order to detect the chip form for unmanned manufacturing, a new identification method is proposed. The feasibility of using acoustic emission signals from the sensing plate for identification of chip form is investigated. Experiments were conducted under the various cutting conditions. When the acoustic emission sensor is attached to the sensing plate, it turns out that the moving averaged AE signals correlated well with the collision of segmented chips with the plate. The sensitivity of moving averaged AE signals to chip congestions due to continuous chip formation is illustrated as well.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.12 no.1
• /
• pp.59-75
• /
• 1975

The thermal stresses due to a heat source moving crosswise on a finite breadth plate, which is much more like to the practical welding problems, were studied. The temperature distributions in the plate were obtained analytically using the mirror image method, and the thermal stresses were calculated by the finite-difference method. Some numerical calculations for temperature distributions and thermal stresses were performed. The temperature distributions were also obtained by experiment. It was found that the theory was in good agreement with the result of experiment, and the calculated thermal stresses were resonable.

• Journal of Welding and Joining
• /
• v.16 no.3
• /
• pp.44-54
• /
• 1998

In this study a new arc sensor algorithm for automatic weld seam tracking was proposed, which uses the relative welding current variation according to the tip-to-workpiece distance in GMA welding. Since the new developed arc sensor algorithm is not sensitive to unstable factors of arc signal, the system is expected to get rid of the problems of already existing arc sensor system which include the difficulty of modeling the process for various welding conditions and limitation of application to thick plate welding. Thus the system is applicable not only to thick plate welding but also to thin plate welding. To implement the new arc sensor algorithm the system parameters which include sampling time, averaging range, weighting factor of moving averaging, basic compensation time, and basic compensation distance were determined by experimental analysis. Consequently this system has shown the successful tracking capability for the various welding conditions.

• Journal of Industrial Technology
• /
• v.19
• /
• pp.313-320
• /
• 1999

Steel railway bridge gets vibration from moving load ; additionally, this kind of moving load is going to be a sufficient reason, which causes fatigue damage to steel railway bridge. Fatigue damage and stress curve were raised by moving load depends on span length in steel railway bridge. In other words, stress curve appears index regarding every axial load in short span, but self weight lets stress curve's change decrease in proportion to increasing span length. Thereby, we have studied that how the steel railway bridge appear fatigue damage in proportion to span length of steel railway bridge. Dynamic strain was measured in 4 steel plate-girder railway bridge during the trains was passing, which is located on the line of Kyoung-chun railway. And time history response analysis has been done in order to ensure actual survey. The results of this study show the decreased of the fatigue damage in steel railway bridge according to length of span. This paper ends is bases research of fatigue design in steel railway bridges according to span length.

• 한국전산유체공학회:학술대회논문집
• /
• 2006.05a
• /
• pp.47-48
• /
• 2006

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.50 no.9
• /
• pp.471-475
• /
• 2001

ln this paper, a micromachined micromechanical switch is presented. The presented switch is operated in the vertical direction to the substrate by an electrostatic force between two parallel plates. The moving plate is pulled down to connect the bumps of the bias node$(V_{DD}/ or GND)$ to the bumps of the output node when a oltage difference exists between the moving plate and the input plate. The switch was designed to operate at a low switching voltage$(\risingdotseq5V)$ by including a large-area, narrow-gap, parallel plate capacitor A theoretical analysis of the designed switch was performed in order to determine its geometry fitting the desired pull-in voltage and release voltage. The designed switch was fabricated by surface micromachining combined with Ni electroplating. From the experimental results of the fabricated switch, its pull-in voltage came Out to be less than 5V and the measured maximum allowable current was 150mA. The measured average ON-state resistance was about 8$\Omega$, and the OFF-state resistance was too high to be measured with digital multimeter.

• Journal of Korean Port Research
• /
• v.13 no.2
• /
• pp.303-312
• /
• 1999

The automated gate operating system is developed in this paper that controls the information of container at gate in the ACT. This system can be divided into three parts and consists of container identifier recognition car plate recognition container deformation perception. We linked each system and organized efficient gate operating system. To recognize container identifier the preprocess using LSPRD(Line Scan Proper Region Detection)is performed and the identifier is recognized by using neural network MBP When car plate is recognized only car image is extracted by using color information of car and hough transform. In the port of container deformation perception firstly background is removed by using moving window. Secondly edge is detected from the image removed characters on the surface of container deformation perception firstly background is removed by using moving window. Secondly edge is detected from the image removed characters on the surface of container. Thirdly edge is fitted into line segment so that container deformation is perceived. As a results of the experiment with this algorithm superior rate of identifier recognition is shown and the car plate recognition system and container deformation perception that are applied in real-time are developed.

• Steel and Composite Structures
• /
• v.42 no.2
• /
• pp.243-256
• /
• 2022

A coupled finite element method (FEM)-boundary element method (BEM) for analyzing the hydroelastic response of functionally graded carbon nanotube-reinforced composite (FG-CNTRC) floating plates under moving loads is firstly introduced in this article. For that aim, the plate displacement field is described utilizing a generalized shear deformation theory (GSDT)-based FEM, meanwhile the linear water-wave theory (LWWT)-relied BEM is employed for the fluid hydrodynamic modeling. Both computational domains of the plate and fluid are coincidentally discretized into 4-node Hermite elements. Accordingly, the C1-continuous plate element model can be simply captured owing to the inherent feature of third-order Hermite polynomials. In addition, this model is also completely free from shear correction factors, although the shear deformation effects are still taken into account. While the fluid BEM can easily handle the free surface with a lower computational effort due to its boundary integral performance. Material properties through the plate thickness follow four specific CNT distributions. Outcomes gained by the present FEM-BEM are compared with those of previously released papers including analytical solutions and experimental data to validate its reliability. In addition, the influences of CNT volume fraction, different CNT configurations, water depth, and load speed on the hydroelastic behavior of FG-CNTRC plates are also examined.