Search

Defect detection of track fasteners is a prerequisite for safe and reliable railroad operation. The traditional manual visual inspection method has been unable to meet the growing demand for railroad network inspection in China. To achieve the need for accurate, fast, and intelligent detection of rail fasteners, this paper proposes a rail fastener defect detection model based on improved YOLOv5s. Firstly, the convolutional block attention module (CBAM) is added to the Neck network of the YOLOv5s model to enhance the extraction of essential features by the model and suppress the information of minor features. Secondly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to realize the multi-scale feature fusion of the model. Finally, the K-means++ algorithm is used to re-cluster the dataset to obtain the anchor box suitable for the fastener dataset and improve the positioning ability of the model. The experimental results show that the improved model achieves an average mean precision (mAP) of 97.4%, a detection speed of 27.3 FPS, and a model memory occupancy of 15.5 M. Compared with the existing target detection model, the improved model has the advantages of high detection accuracy, fast detection speed, and small model memory occupation, which can provide technical support for edge deployment of rail fastener defect detection. [ABSTRACT FROM AUTHOR]

A low-floor train–turnout coupling dynamic model considering bad alignment irregularity ahead of the turnout was established on the basis of a field test in which the dynamic performances of a low-floor train passing through a no. 6 turnout in a rail transit depot in China had been measured, as well as the line alignment and wheel and rail profiles. There are two types of wheelsets in the low-floor train: integral wheelset and independent wheelset. The model fully considers the coupling effect between the vehicle and the ballast components, and the simulated results are in consistence with measured results in the field test. Based on this, the influences of train speed, the wheel–rail friction coefficient, and the track alignment optimization of the dynamic performance of low-floor trains passing switch in facing direction are analyzed. The main results indicate that eliminating alignment irregularities before the switch can effectively improve the dynamic performance of the integrated wheelset in the switch and the lateral forces of the outer wheels of these two vehicles are reduced by about 80%, the derailment coefficients are reduced by about 70%, the vertical force is reduced by about 10–20% and wheel load is reduced by approximately 30%. [ABSTRACT FROM AUTHOR]