To study the static‒dynamic characteristics and vibration fatigue failure mechanism of railway fastening clips, the modal characteristics of the clip in free and installed states are obtained via field experiments, and a refined finite element model of the fastening system is established and verified. Then, static‒dynamic analysis and frequency response analysis are carried out based on the numerical model, and the effects of the system excitation with varied amplitudes and frequencies on the vibration fatigue life of the clip and the distribution characteristics of clip fatigue damage peril points (CFDPPs) are investigated. Eventually, method of dividing the clip vibration fatigue sensitive frequency range (CVFSFR) is proposed. The results show that the fatigue life of the clip is significantly affected by resonance, and the resonance at the 2nd-order natural frequency caused by high-frequency excitation is an important reason for the fatigue failure of the fastening clip.

In order to study the effects of wheel-rail impacts on the fatigue damage of the fastening clips at the rail joints of a high-speed railway, field tests were carried out on the wheel-rail impacts at the rail joints of a high-speed railway in China. On the basis of the track irregularities at the rail joints obtained from field measurements, a nonlinear vehicle-track coupling dynamics three-dimensional (3D) model with consideration of Timoshenko beam elements and a refined finite element model of WJ-8 fastening system were constructed. And combined with the theory of cumulative damage and the method of fatigue analysis, the effects of wheel-rail impact at the rail joints on the fatigue life of fastening clips were analyzed. The results showed that the impacts of the wheel-rail in the joint area caused high-frequency fluctuations in the stress-time curves of the clips, which significantly increased the amplitude of stress cycle and increased a lot of stress cycles, of which the amplitudes were reached at a large level; the clips in the area where a rail joint was located suffered the most serious fatigue damage and had the shortest fatigue life; in the actual operation line, besides the clips in the rail joint area, it is also necessary to be concerned about the fatigue performance of fastening clips near the rail joint area.

The combination model of the vehicle and ladder track system that accounts for the wheel–rail interface has been developed to analyze the wheelset and ladder track vibration characteristics in the frequency and time domains. In the wheel–rail interface, the vertical contact is represented by contact stiffness derived from the Hertz theory of normal elastic contact, and lateral contact is idealized by linear contact used Kalker linear rolling contact theory. The considerable noise and vibration frequency of the ladder track is determined by experimental investigation results. Then the effect of the most significant ladder track parameters on the track vibration is analyzed in time domain using the vehicle–track coupling model. Based on the results of the parametric study, an optimization of the mechanical properties of the ladder track to reduce the track vibrations is performed using the multipoint approximation method. The results of the optimization are presented and discussed.

In recent years, deep residual networks (ResNets) have been successfully used to detect structural damage. However, the performance of ResNets greatly depends on large high-quality datasets for learning, which can be difficult to obtain in actual engineering scenarios. In addition, in order to improve identification accuracy, vibration signals from multiple positions can be fused together to train the ResNets. On the one hand, vibration signals from multipositions can increase the quantity of the training data. On the other hand, hidden correlations among multivibration signals may also reflect some features improving identification accuracy. However, traditional vibration acquisition methods, such as accelerometers, cannot ensure that the vibration signals from multipositions are synchronized in the temporal domain, causing the correlations among multivibration signals not to be fully recorded. To solve the above problems, this study presents a novel structural health monitoring method by combining phase-based motion estimation (PME) with the use of ResNets. With the PME method, each pixel in a video can be regarded as a displacement sensor; thus, it is possible to obtain millions of vibration signals from a single video; in addition, all vibration signals obtained from a single video are perfectly synchronized, greatly facilitating ResNet applications. Here, an open gearbox mechanism was used for experimental validation of our approach. With the proposed method, only one video sample obtained under each structural condition was required to train a ResNet model for detecting gear misalignment (difference of only 0.2°) with 100% accuracy, indicating the outstanding performance of the proposed method.

Rail weld irregularities are one of the primary excitation sources for vehicle-track interaction dynamics in modern high-speed railways. They can cause significant wheel-rail dynamic interactions, leading to wheel-rail noise, component damage, and deterioration. Few researchers have employed the vehicle-track interaction dynamic model to study the dynamic interactions between wheel and rail induced by rail weld geometry irregularities. However, the cosine wave model used to simulate rail weld irregularities mainly focuses on the maximum value and neglects the geometric shape. In this study, novel theoretical models were developed for three categories of rail weld irregularities, based on measurements of the high-speed railway from Beijing to Shanghai. The vertical dynamic forces in the time and frequency domains were compared under different running speeds. These forces generated by the rail weld irregularities that were measured and modeled, respectively, were compared to validate the accuracy of the proposed model. Finally, based on the numerical study, the impact force due to rail weld irrregularity is modeled using an Artificial Neural Network (ANN), and the optimum combination of parameters for this model is found. The results showed that the proposed model provided a more accurate wheel/rail dynamic evaluation caused by rail weld irregularities than that established in the literature. The ANN model used in this paper can effectively predict the impact force due to rail weld irrregularity while reducing the computation time.

In railway systems, layered structures could be induced in wheel–rail contact interfaces due to several causes, such as head hardening, work hardening, plastic deformation, and mechanical or thermal excursion-induced phase transformation. This study proposes an explicit finite element (FE) method for investigating elastic layer effects in wheel–rail rolling contact. The proposed method is first validated by comparing its solution with that of Kalker’s boundary element method (BEM) when the layer is not present, with a focus on the tractive rolling contact. To investigate general layer effects, the rail is assumed to consist of two layers, i.e., the top layer and the matrix material. The top layer is assumed to have different elastic moduli from the matrix material and then the top elastic layer effects on contact characteristics such as contact stress, contact patch, and subsurface stress are investigated. Different layer thicknesses are also considered. It is observed that a harder layer tends to introduce larger contact pressure and surface shear stress, but a smaller contact patch. A harder layer also produces larger subsurface stresses. A thicker layer may intensify these effects. The results suggest that in engineering applications, the analysis of wheel–rail rolling contact consequences such as wear and rolling contact fatigue (RCF) may need to consider the layered structures using appropriate methods.