• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.149-154
• /
• 2022

In recent years, the application of deep learning method to computer vision has shown to achieve great performances. Thus, many research projects have also applied deep learning technology to railroad defect detection. In this paper, we have reviewed the researches that applied computer vision based deep learning method to railroad defect detection and inspection, and have discussed the current trend and the direction of those researches. Many research projects were targeted to operate automatically without visual inspection of human and to work in real-time. Therefore, methods to speed up the computation were also investigated. The reduction of the number of learning parameters was considered important to improve computation efficiency. In addition to computation speed issue, the problem of annotation was also discussed in some research projects. To alleviate the problem of time consuming annotation, some kinds of automatic segmentation of the railroad defect or self-supervised methods have been suggested.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• 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.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.7
• /
• pp.619-625
• /
• 2015

There is a large interest to find reliable and automatic methods for crack detection and quantification in the railway bogie frame. The non-destructive inspection of railway bogie frame has been performed by ultrasonic and magnetic particle testing in general inspection. The magnetic particle method has been utilized in the defect inspection of the bogie frame but the grinding process is required before inspection and the dust is developed resulting from the processing. The objective of this paper is to apply the inspection method of bogie frame using infra-red thermography. The infra-red thermography system using the excitation of eddy current was performed for the defect evaluation of weld specimen inserted artificial defects. The result shows that the infra-red thermography method can detect the surface and inner defects in weld specimen for bogie frame.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• 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.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.6
• /
• 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.

• Journal of the Korean Society for Railway
• /
• v.18 no.5
• /
• pp.401-409
• /
• 2015

Defects generated in a railroad track that guides the railroad vehicle have the characteristic of growing fast; as such, the detection technology for railroad track defects is very important because defects can eventually cause mass disasters like derailments. In this study, a speed-up test facility was fabricated to investigate the feasibility of using magnetic flux leakage (MFL) technology for defect detection in a railroad track under speed-up condition; a test was conducted using a railroad track specimen with defects. For this purpose, an MFL sensor head dedicated to the configuration of the railroad was designed and test specimens with artificial defects on their surfaces were manufactured. Using the test facility, a speed-up test ranging from 4km/h to 12km/h was performed and defects including locations were successfully detected from MFL signals induced by defects with enhanced visibility by differentiating raw MFL signals. In the future, it should be possible to apply this system to a high-speed railroad inspection car by improving the lift-off stability that is necessary for speed-up of the developed MFL sensor system.

• International Journal of Railway
• /
• v.1 no.1
• /
• pp.1-5
• /
• 2008

The railway system requires safety and reliability of service of all railway vehicles. Suitable technical systems and working methods adapted to it, which meet the requirements on safety and good order of traffic, should be maintained. For detection of defects, non-destructive testing methods-which should be quick, reliable and cost-effective - are most often used. 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 detect a crack initiation clearly with ultrasonic testing due to noise echoes. 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 railway wheelset.

• International Journal of Railway
• /
• v.5 no.2
• /
• pp.84-88
• /
• 2012

Derailment due to wheel failure would cause a tremendous social and economical cost in service operation. It is necessary to evaluate quantitatively the safety with respect to high-speed train. Although the safety of railway wheel has been ensured by an regular inspection, all critical defects cannot be detected in inspection cycles and the wheel has been replaced because a defect quickly become critical for safety. Therefore, it is important to calculate quantitatively the fracture limit and remnant life of damaged railway wheel in wheel-rail system. In present paper, the critical crack size of wheel for high-speed train is simulated based on fracture scenario and the safety of wheel is evaluated.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.9
• /
• pp.1078-1085
• /
• 2011

Prediction of a minimum crack size for growth, which is defined as a crack size that grows fast enough to keep ahead of its removal by contact wear and periodic grinding, is the most demanding work to prevent rail from fatigue failure and develop cost effective railway maintenance strategy In this study, we investigated the wheel load increment due to a rail defect during a train ran over it, and its effect on the minimum crack size for growth. For this purpose, we developed simulation software based on the Fletcher and Kapoor's "2.5D" model and measured wheel load increment during a train passed over a defect. A maximum contact pressure and contact patch size were calculated by 3D FEM and crack growth analyses were performed by varying two of dominant contact contributors; surface friction coefficient(0.1, 0.2, 0.3 and 0.4) and crack aspect ratio. The minimum crack sizes for growth were calculated from 0.29 to 1.44mm depending on the contact conditions. They were decreasing with increasing surface friction coefficient and decreasing with crack aspect ratio(a/b).