• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.501-516
• /
• 2023

Dynamic irregularity and acceleration of bridges subjected to high-speed trains provide crucial information for comprehensive evaluation of the health state of under-track structures. This paper proposes a novel approach for real-time estimation of vertical track dynamic irregularity and bridge acceleration using deep generative adversarial network (GAN) and vibration data from in-service train. The vehicle-body and bogie acceleration responses are correlated with the two target variables by modeling train-bridge interaction (TBI) through least squares generative adversarial network (LSGAN). To realize supervised learning required in the present task, the conventional LSGAN is modified by implementing new loss function and linear activation function. The proposed approach can offer pointwise and accurate estimates of track dynamic irregularity and bridge acceleration, allowing frequent inspection of high-speed railway (HSR) bridges in an economical way. Thanks to its applicability in scenarios of high noise level and critical resonance condition, the proposed approach has a promising prospect in engineering applications.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1624-1630
• /
• 2011

Currently the train operating environment to affect track irregularity is changed rapidly such as speed-up, linear improvement and rolling stack upgrade. The recent track maintenance criteria of track irregularity was quoted from past Japan's, and the needs of revision of criteria are increased because of the rapid change in train operating environment. In case of enhance the track irregularity criteria, it secure driving safety and riding comfort but maintenance cost are increase. And also decrease ballast durability by frequent corrective work. In case of mitigate the criteria, it decrease driving safety and riding comfort, but save the maintenance cost. The study for enacting rational criteria did not carry out so far. In this study, survey the domestic and international track irregularity and case study for track irregularity inspection results and maintenance history for guideline of enacting irregularity criteria study.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.4
• /
• pp.401-406
• /
• 2019

The three-dimensional precision numerical analysis was performed using the finite element model applied with the railway track model consisting of rails, sleepers, and track elastic springs(ballast, rail pad). As a result of analyzing the track deformation level of the existing tracks due to the excavation work adjacent to the railway facilities, it was found that the track irregularity evaluation criteria (allowed values) of both conventional and high-speed railways lines were satisfied. Based on the numerical analysis using the track model, it was analyzed that the results of the prediction of the track irregularity due to the excavation work and the level of the track deformation occurring at the actual site could be approximated as closely as possible.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.435-441
• /
• 2011

Track geometry changes by traffic loads. The bigger the changes are, the worse the riding comfort and running stability of train. This is so-called track irregularity and is the most important quality parameters of ballasted track. To objectively assess track irregularity, track geometry should be able to be measured. Practically, railway companies in Korea use various track recording equipments to measure track irregularity. But this various equipments output different data due to their geometrical structure even measured at same location. In this report, the correlation of various track recording data used in Korea was reviewed.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.268-274
• /
• 2011

In railway, Ballast plays an essential role as intermedium in transmitting train load to subgrade safely. Gyoung-Bu HSL 1st phase consists of ballasted track except for over 5km long tunnels. Ballast track occurred track irregularity by train loads and requires periodic maintenance work. However, Repetitive train operation and tamping work cause to accelerate track irregularity and ballast deterioration such as abrasion and crushing. For these reason, Track irregularity areas had occurred ballast cleaning work to improve track quality. However, for the train to run safety, ballast cleaner working area needs train speed reduction and track stabilization work due to ballast relaxation and initial settlement. In this study, according to train speed-up and cumulative traffic tonnage, we measured and analyzed the track settlement and acceleration of sleepers to evaluate of track stabilization in order to keep the ballast condition stable after cleaning work.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.783-792
• /
• 2011

The control of rail surface irregularity is very important for the high speed train service in the high speed rail. In order to manage it, initial, preventative, and maintainable rail grinding have been performed and among them, preventative rail grinding conducts in every each year. This study carried out the field test for dynamic track response according to rail surface irregularity comparing before and after rail grinding. In addition, the change of dynamic track responses according to rail grinding was analyzed and the fatigue life was estimated though Rainflow Counting Method and RMC Equivalence Stress. Therefore, it suggested that rail fatigue life should be increased by rail grinding, because amount of impact occurred on track is decreased by getting rid of rail surface irregularity.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.330-337
• /
• 2010

This paper shows an algorithm for identifying track irregularities using wavelet transfer function along the railway. An equivalent SISO wavelet transfer function is defined using continuous wavelet transform by the measured track geometry and acceleration at a bogie of a train. The estimated track geometry is made by inverse continuous wavelet transform from the regressed signals of measured acceleration signal and the pre-defined wavelet transfer function. The estimated rail irregularity geometry is evaluated by the coherence function and comparison of FRF(Frequency Response Function). As a result of evaluated outcome, This algorithm is regarded as appropriate for estimation of rail irregularity.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.310-314
• /
• 2010

Track geometry changes by traffic loads. The bigger the changes are, the worse the riding comfort and running stability of train. This is so-called track irregularity and is the most important quality parameters of ballasted track. To objectively assess track irregularity, track geometry should be able to be measured. Practically, railway companies in Korea use normal distribution as probability distribution of track irregularity. But some countries use non-normal distribution according to their own track recording system. In this report, reviewed probability distribution of Kyung-Bu high-speed line and tested normality.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.05a
• /
• pp.988-991
• /
• 2006

Rolling Stock running are making Rail Head Surface damage(corrugation, flaking, shelling, etc). It's coming out Rail Head Surface Irregularity. It increases Rolling Stock and structure vibration. Therefore, this paper analyzes the influence of Rail Head Surface Irregularity to railway vibration. And, It introduces the management method of Rail Head Surface and proposes its R&D direction in railway-run organization.

• 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.