In current railway rails, trains are propelled by the rolling contact between iron wheels and iron rails, and the high frequency of train repetition on rails results in a significant load exertion on a very small area where the wheel and rail come into contact. Furthermore, a contact stress beyond the allowable stress of the rail may lead to cracks due to plastic deformation. The railway rail, which is the primary contact surface between the wheel and the rail, is prone to rolling contact fatigue cracks. Therefore, a thorough inspection and diagnosis of the condition of the cracks is necessary to prevent fracture. The Detailed Guideline on the Performance Evaluation of Track Facilities in South Korea specifies the detailed requirements for the methods and procedures for conducting track performance evaluations. However, diagnosing rail surface damage and determining the severity solely rely on visual inspection, which depends on the qualitative evaluation and subjective judgment of the inspector. Against this backdrop, rail surface defect detection was investigated using Fast R-CNN in this study. To test the feasibility of the model, we constructed a dataset of rail surface defect images. Through field investigation, 1300 images of rail surface defects were obtained. Aged rails collected from the field were processed, and 1300 images of internal defects were generated through SEM testing; therefore, a total of 1300 pieces of learning data were constructed. The detection results indicated that the mean average precision was 94.9%. The Fast R-CNN exhibited high efficiency in detecting rail surface defects, and it demonstrated a superior recognition performance compared with other algorithms.

To date, the spring stiffness of resilience pads was mostly evaluated based on conventional (site measurement and laboratory tests) methods. Most studies in the past analyzed the effects of the deterioration of resilience pads on track damage. To examine the deterioration of resilience pads, evaluations were conducted based on laboratory tests using site measurements and samples were collected from the site, or based on loading tests using special equipment. such as TSS. However, no methodology was proposed to prove the theoretical equations of Zimmermann which compute the reaction force at the rail support point. Hence, this study aimed to prove that the reaction force increased if spring stiffness at the rail support point increased; this was achieved by using a pressure sensor according to the theoretical equations of Zimmermann. Furthermore, we aimed to propose a method to evaluate the spring stiffness of resilience pads to predict the extent of deterioration of the pads based on the increase in the pressure measured by a pressure sensor.

Rolling contact fatigue cracks at the contact surface between a wheel and rail are evaluated based on the results of an external inspection (visual inspection). We developed a rail damage assessment technique using a fast regional convolutional neural network deep learning-based image analysis framework. We collected rail specimens from in-service tracks and performed scanning electron microscopy to correlate surface damage with subsurface crack formation, including crack depth, length, and angle. This data was input into an artificial neural network (ANN) to assess internal crack conditions using visual information obtained from rail surface damage. The resulting model achieved an average accuracy of 94.9%, outperforming other algorithms. We integrated this model into a developed rail damage diagnosis app with deep learning that links field photographs with cloud-based big data to learn, quantitatively diagnose, and present the type and scale of rail damage. We examined the field applicability of the application at a rail damage site. The standard deviation of the rail damage diagnosis results was 0.2–1.5% between different users. Appropriateness of the rail damage assessment technique using the proposed ANN image analysis technique was verified experimentally. Consistent diagnosis results could be derived regardless of the inspector, minimizing human error.

This study experimentally investigated the long-term deformation behavior of a ballasted railway turnout affected by adjacent deep excavation through an integrated multi-sensor field-monitoring approach. The monitored facility consisted of two 60 kg, #10 single turnouts located approximately 13 m from an excavation with a maximum depth of approximately 21 m. Field monitoring was conducted for approximately 640 days, from the pre-excavation stage to the completion of the underground structure. Three complementary measurement methods were employed: a track master system for track geometry, tilt-angle-based rail displacement sensors for local rail displacement, and an automatic leveling system for absolute sleeper displacement. The relative measurement methods primarily identified local rail geometry variations within approximately ±1–2 mm, whereas the absolute sleeper measurements revealed substantially larger support system movements. In particular, a maximum sleeper settlement of approximately −9.1 mm and a maximum heave of approximately +4.9 mm were observed at different locations of the T2 turnout, producing a longitudinal differential displacement of approximately 14 mm within the turnout system. The results indicate that excavation-induced turnout deformation consists of both global support system movement and local differential rail deformation, which cannot be completely characterized using a single measurement reference framework. The principal contribution of this study is the experimental clarification of the complementary roles of relative and absolute displacement measurements in distinguishing local track geometry changes from global sleeper support movement. The proposed integrated monitoring framework provides a practical basis for identifying critical deformation zones and improving the structural assessment and maintenance of turnouts affected by adjacent excavation.