• International Journal of Railway
• /
• 제5권3호
• /
• pp.129-134
• /
• 2012

Contact fatigue damages on the rail surface, such as head checks and squats are a growing problem. The fatigue cracks forming on the contact surface grow according to load and lubricating conditions and may end up breaking the rail. Rail fracture can be avoided by preventing the cracks from reaching the critical length. Therefore, the crack growth rate needs to be estimated precisely according to the conditions of the track and load to develop a maintenance plan against rail damages. Therefore, it is important to understand the mechanism of cracks initiation and growth on a rail due to repetitive rolling contact. In this study, we have investigated the crack growth behavior on the rail surface by using the twin-disc tests and the finite element analysis.

• 인터넷정보학회논문지
• /
• 제21권6호
• /
• pp.23-31
• /
• 2020

본 연구는 철도표면상에 발생하는 노후 현상 중 하나인 결함 검출을 위해 학습데이터를 생성함으로써 결함 검출 모델에서 더 높은 점수를 얻기 위해 진행되었다. 철도표면에서 결함은 선로결속장치 및 선로와 차량의 마찰 등 다양한 원인에 의해 발생하고 선로 파손 등의 사고를 유발할 수 있기 때문에 결함에 대한 철도 유지관리가 필요 하다. 그래서 철도 유지관리의 자동화 및 비용절감을 위해 철도 표면 영상에 영상처리 또는 기계학습을 활용한 결함 검출 및 검사에 대한 다양한 연구가 진행되고 있다. 일반적으로 영상 처리 분석기법 및 기계학습 기술의 성능은 데이터의 수량과 품질에 의존한다. 그렇기 때문에 일부 연구는 일반적이고 다양한 철도표면영상의 데이터베이스를 확보하기위해 등간격으로 선로표면을 촬영하는 장치 또는 탑재된 차량이 필요로 하였다. 본연구는 이러한 기계적인 영상획득 장치의 운용비용을 감소시키고 보완하기 위해 대표적인 영상생성관련 딥러닝 모델인 생성적 적대적 네트워크의 기본 구성에서 여러 관련연구에서 제시된 방법을 응용, 결함이 있는 철도 표면 재생성모델을 구성하여, 전용 데이터베이스가 구축되지 않은 철도 표면 영상에 대해서도 결함 검출을 진행할 수 있도록 하였다. 구성한 모델은 상이한 철도 표면 텍스처들을 반영한 철도 표면 생성을 학습하고 여러 임의의 결함의 위치에 대한 Ground-Truth들을 만족하는 다양한 결함을 재 생성하도록 설계하였다. 재생성된 철도 표면의 영상들을 결함 검출 딥러닝 모델에 학습데이터로 사용한다. 재생성모델의 유효성을 검증하기 위해 철도표면데이터를 3가지의 하위집합으로 군집화 하여 하나의 집합세트를 원본 영상으로 정의하고, 다른 두개의 나머지 하위집합들의 몇가지의 선로표면영상을 텍스처 영상으로 사용하여 새로운 철도 표면 영상을 생성한다. 그리고 결함 검출 모델에서 학습데이터로 생성된 새로운 철도 표면 영상을 사용하였을 때와, 생성된 철도 표면 영상이 없는 원본 영상을 사용하였을 때를 나누어 검증한다. 앞서 분류했던 하위집합들 중에서 원본영상으로 사용된 집합세트를 제외한 두 개의 하위집합들은 각각의 환경에서 학습된 결함 검출 모델에서 검증하여 출력인 픽셀단위 분류지도 영상을 얻는다. 이 픽셀단위 분류지도영상들과 실제 결함의 위치에 대한 원본결함 지도(Ground-Truth)들의 IoU(Intersection over Union) 및 F1-score로 평가하여 성능을 계산하였다. 결과적으로 두개의 하위집합의 텍스처 영상을 이용한 재생성된 학습데이터를 학습한 결함 검출모델의 점수는 원본 영상만을 학습하였을 때의 점수보다 약 IoU 및 F1-score가 10~15% 증가하였다. 이는 전용 학습 데이터가 구축되지 않은 철도표면 영상에 대해서도 기존 데이터를 이용하여 결함 검출이 상당히 가능함을 증명하는 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4763-4775
• /
• 2020

This research aims to develop a deep learning-based method that automatically detects and segments the defects on railroad surfaces to reduce the cost of visual inspection of the railroad. We developed our segmentation model by modifying a fully convolutional network model [1], a well-known segmentation model used for machine learning, to detect and segment railroad surface defects. The data used in this research are images of the railroad surface with one or more defect regions. Railroad images were cropped to a suitable size, considering the long height and relatively narrow width of the images. They were also normalized based on the variance and mean of the data images. Using these images, the suggested model was trained to segment the defect regions. The proposed method showed promising results in the segmentation of defects. We consider that the proposed method can facilitate decision-making about railroad maintenance, and potentially be applied for other analyses.

• 한국정밀공학회지
• /
• 제29권6호
• /
• pp.613-620
• /
• 2012

Rails are subjected to damage from rolling contact fatigue, which leads to defects such as cracks. Rolling contact fatigue damages on the surface of rail such as head check, squats are one of growing problems. Another form of rail surface damage, known as "Ballast imprint" has become apparent. This form of damage is associated with ballast particles becoming trapped between the wheel and the surface of rail. These defects are still one of the key reasons for rail maintenance and replacement. In this study, we have investigated whether the ballast imprint is an initiator of head check type cracks and effect of defect size using Finite element analysis. The FE analysis were used to investigate stresses and strains in subsurface of defects according to variation of defect size. Based on loading cycles obtained from FE analysis, fatigue analysis for each point was carried out.

• 한국정밀공학회지
• /
• 제27권8호
• /
• pp.42-47
• /
• 2010

In this paper, the characteristics of contact surface damage due to fretting in a press-fitted shaft below the fretting fatigue limit are proposed by experimental methods. A series of fatigue tests and interrupted fatigue tests of small scale press-fitted specimen were carried out by using rotating bending fatigue test machine. Macroscopic and microscopic characteristics were examined using scanning electron microscope (SEM), optical microscope or profilometer. It is found that fretting fatigue cracks were initiated even under the fretting fatigue limit on the press-fitted shafts by fretting damage. The fatigue cracks of press-fitted shafts were initiated from the edge of contact surface and propagated inward in a semi-elliptical shape. Furthermore, the fretting wear rates at the contact edge are increased rapidly at the initial stage of total fatigue life. After steep increasing, the increase of wear rate is nearly constant under the load condition below the fretting fatigue limit. It is thus suggested that the fretting wear must be considered on the fatigue life evaluation because the fatigue crack nucleation and propagation process is strongly related to the evolution of surface profile by fretting wear in the press-fitted structures.

• 한국정밀공학회지
• /
• 제28권5호
• /
• pp.565-571
• /
• 2011

Because most fatigue cracks in wheel and rail take place by rolling contact of wheel and rail in railroad industry, it is critical to understand the rolling contact phenomena, especially for the three-dimensional situation. This paper presents an approach to steady-state rolling contact problem of three-dimensional contact bodies, with or without tangential force, based on the finite element method. The steady-state conditions are controlled by the applied relative slip and tangential force. The three-dimensional distribution of tangential traction and contact stresses on the contact surface are investigated. Results show that the distribution of tangential traction and contact stresses on the contact surface varies rapidly as a result of the variation of stick-slip region. The tangential traction is very close in form to Carter's distribution.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2005년도 춘계 학술발표회 논문집
• /
• pp.811-818
• /
• 2005

Stability analyses on the 17 railroad cut-off soil slopes were carried out. The influences of rainfall infiltration on the slope stabilities were taken into account by seepage analyses using finite element method and by assuming ground water tables to be located adjacent to soil surface. The validity of those analyses were evaluated by comparing the slope failure characteristics between analysis results and the past failure records. The analyses were not appropriate to estimate the failure surface and the method considering only the increase of pore-water pressure (reduction of matric suction) as the influence of rainfall cannot appropriately estimate the surficial failures that occurred most of the cut-off soil slopes. For the better estimation of the surficial failure, the influence of water flows over slope surface which erode soil mass and/or increase driving force, should be evaluated and considered.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.1940-1945
• /
• 2007

The wheelsets are one of most important component: damages in wheel tread and press fitted axle are a significant cost for railway industry. Since failure in railway wheelset can cause a disaster, regular inspection of defects in wheels and axles are mandatory. Ultrasonic testing, acoustic emission and eddy current testing method and so on regularly check railway wheelset in service. However, it is difficult to use this method because of its high viscosity and because its sensitivity is affected by temperature. Also, due to noise echoes it is difficult to detect defects initiation clearly with ultrasonic testing. It is necessary to develop a non-destructive technique that is superior to conventional NDT techniques in order to ensure the safety of railway wheelset. In the present paper, the new NDT technique is applied to the detection of surface defects for railway wheelset. To detect the defects for railway wheelset, the sensor for defect detection is optimized and the tests are carried out with respect to surface and internal defects each other. The results show that the surface crack depth of 1.5 mm in press fitted axle and internal crack in wheel could be detected by using the new method. The ICFPD method is useful to detect the defect that initiated in the tread of railway wheelset.

• 대한자원환경지질학회:학술대회논문집
• /
• 대한자원환경지질학회 2007년도 춘계 지질과학기술 공동학술대회
• /
• pp.327-330
• /
• 2007

See Full Text

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.127-131
• /
• 2008

In the disk braking of the railway trains, kinetic energy of the vehicles is converted into thermal energy by friction between a brake disk and the pad materials. This can be cause of the iterative thermal shock and generates thermal cracks on the brake disk surface. In this study, we show the comparative thermal fatigue test procedures and thermal crack analysis process to evaluate the thermal fatigue characteristics of candidate materials designed for development of heat-resistant brake disk material. We carried out tests on the conventional brake disk materials used for Saemaul and Mugunghwa trains, then we comparatively analyzed the thermal crack initiation and propagation on the surface of a specimen. A thermal fatigue test procedure and a crack analysis process were suggested to evaluate the heat resistance of the developed materials at later studies.