• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.989-995
• /
• 2010

This paper is focused on a simplified measurement of rail irregularity by some axle-box accelerometers for high-speed rail condition monitoring with in-service high-speed trains. Generally, the rail condition monitoring has been done by a special railway inspection vehicle with a 10m versine method. But, the monitoring method needs some expensive measurement system, and have been performed only at night due to its speed limit. In this research, a simplified measurement of rail irregularity using axle-box accelerometers is proposed to monitor the rail condition with in-service high-speed trains. The acceleration is measured by using two accelerometers on a axle-box, and stored in an on-board data acquisition system. The displacement is estimated from the acceleration data by a combination of Kalman filter and the frequency selective filter. The estimated results are compared with the measurement from a laser rail inspection system which is near the axle-box. From the comparison, the proposed method shows promise as a tool for the simplified measurement of rail irregularity at high-speed.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.5 no.2
• /
• pp.163-174
• /
• 2001

This paper is to study the characteristics of axial force behavior that operates to the part of turnout when it makes the turnout and the continuous welded rail unifying. The study is to model by using the 50kgN rail No. 15 turnout used in the domestic national railway and the UIC60 rail No. 18 turnout used in the rapid transit railway as the finite elements for analyzing the axial force behavior of the turnout by the continuous welded rail. It is to analyze the characteristics of behavior according to the change of creep resistance, ballast resistance and the change of parameter valuables of heel joint by the axial force simulation in making the continuous welded rail and then, it is to present the result. As the result of research on the parameter valuables through the analysis, it shows that the maximum axial force of turnout by the continuous welded rail are largely subordinated to the maximum resistance of heel joint and the fitting devices than the ballast resistance. Also it shows that the maximum axial force produced changes a lot according to the characteristics of creep resistance of the fitting part and the ballast resistance.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.285-286
• /
• 2007

This paper presents a robust controller in order to handle the guide rail vibrations of Bridge Inspection System. While a Bridge Inspection Robot moves on guide rails with vibration by weight occurs. Therefore, Guide rail as structure like cantilever beam appears vibration by weight of Bridge Inspection Robot. The Z axis of Bridge Inspection Robot operates with Scissors structure. Bridge Inspection Robot is used 'PID Controller based on Sliding Mode control' for position control with Z axis. At the result of, this paper is applied to simulation about position control regarding vibration to occur with Z axis.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.505-510
• /
• 2024

Since rolling contact fatigue cracks can always occur on the rail surface, which is the contact surface between wheels and rails, railway rails require thorough inspection and diagnosis to thoroughly inspect the condition of the cracks and prevent breakage. Recent detailed guidelines on the performance evaluation of track facilities present the requirements for methods and procedures for track performance evaluation. However, diagnosing and grading rail surface damage mainly relies on external inspection (visual inspection), which inevitably relies on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we conducted a deep learning model study for rail surface defect detection using Fast R-CNN. After building a dataset of rail surface defect images, the model was tested. The performance evaluation results of the deep learning model showed that mAP was 94.9%. Because Fast R-CNN has a high crack detection effect, it is believed that using this model can efficiently identify rail surface defects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6043-6062
• /
• 2019

Low-rank matrix decomposition has shown its capability in many applications such as image in-painting, de-noising, background reconstruction and defect detection etc. In this paper, we consider the texture background of rail track images and the sparse foreground of the defects to construct a low-rank matrix decomposition model with block sparsity for defect inspection of rail tracks, which jointly minimizes the nuclear norm and the 2-1 norm. Similar to ADM, an alternative method is proposed in this study to solve the optimization problem. After image decomposition, the defect areas in the resulting low-rank image will form dark stripes that horizontally cross the entire image, indicating the preciselocations of the defects. Finally, a two-stage defect extraction method is proposed to locate the defect areas. The experimental results of the two datasets show that our algorithm achieved better performance compared with other methods.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.26 no.6
• /
• pp.411-416
• /
• 2006

The critical subject of transverse crack detection in a rail head is treated in this paper. Conventional bulk wave ultrasonic techniques oftenfail because of shelling and other surface imperfections that shield the defects that lie below the shelling. A guided wave inspection technique is introduced here that can send ultrasonic energy along the rail under the shelling with a capability of finding the deleterious transverse crack defects. Dispersion curves are generated via a semi analytical finite element technique along with a hybrid guided wave finite element technique to explore the most suitable modes and frequencies for finding these defects. Sensor design and experimental feasibility experiments are also reported.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.7 no.1
• /
• pp.251-258
• /
• 2003

This study is to understand the characteristics of axial force behavior that operates to the part of continuous welded rail and to investigate the basic data for secure the structure's stability and retrofit of the track. To develop the FEM model that type of plate girder which is used in the domestic national railway among servicing railway type. It is to analyze the characteristics of axial force behavior according to equip of the expansion joint and support placing by using the axial force simulation in making the continuous welded rail. As the result of research on the parametric valuables through the analysis, it is investigated that 'FMFM type' is more efficient than the other support type. Also, it conclude that structures are having the expansion joint is the most safe condition.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.2
• /
• pp.40-48
• /
• 2016

To observe the rail-slab interaction in continuous welded railway(CWR) bridge when earthquake occurs, additional axial rail stresses and relative longitudinal displacements between rail and bridge deck were calculated with input of various load combinations and 3 different types of seismic loads to an analytical model. As results of analysis, it can be found that standard response spectrum proposed by Korea Rail(KR) network authority for earthquake design showed less additional axial rail stresses than allowable levels, but greater relative longitudinal displacement between rail and bridge deck, which means that adjustment of relative longitudinal displacement within a standard level is much more difficult than axial train stress. Additionally, if a large-scaled earthquake as occurred at Kobe, Japan comes up, then both of additional axial rail stress and relative displacement in rail-bridge deck may exceed allowable levels, which indicates to make proper design guides against sudden earthquake occurrence.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.511-516
• /
• 2024

The recently enacted detailed guidelines on the performance evaluation of track facilities presented the necessary requirements regarding the evaluation procedures and implementation methods of track performance evaluation. However, the grade of rail surface damage is determined by external inspection (visual inspection), and there is no choice but to rely only on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we attempted to develop a diagnostic application that can diagnose rail internal defects using rail surface damage. In the field investigation, rail surface damage was investigated and patterns were analyzed. Additionally, in the indoor test, SEM testing was used to construct image data of rail internal damage, and crack length, depth, and angle were quantified. In this study, a deep learning model (Fast R-CNN) using image data constructed from field surveys and indoor tests was applied to the application. A rail surface damage diagnosis application (App) using a deep learning model that can be used on smart devices was developed. We developed a smart diagnosis system for rail surface damage that can be used in future track diagnosis and performance evaluation work.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.115-118
• /
• 2007

The geometry of wheel and rail profiles is the primary contributor to wheel and rail interaction. These profiles interact to influence truck steering, vehicle lateral stability, wheel/rail wear and surface damage. Maintaining good control of the profiles is one of the keys to ensuring preferred wheel and rail interaction. Transportation Technology Center, Inc., Pueblo, Colorado, is developing an automated measurement system for wheel/rail contact condition inspections supported by AAR(Association of American Railroads). The system uses a modified version of $WRTOL^{TM}$ (Wheel/Rail Tolerances)--software that performs extensive analysis of wheel and rail contact conditions