Addressing the challenge of the current inability to qualitatively identify rail corrugation damage accurately from axle box acceleration data, this study proposes a novel approach. To indirectly identify rail corrugation from axle box acceleration, we introduce an improved successive variational mode decomposition (SVMD) algorithm, coupled with a deep learning model for corrugation recognition. First, a numerical model of the vehicle-rail-track slab system is established, considering rail corrugation. Indicator analysis is integrated into the SVMD. The improved SVMD is employed to decompose and reconstruct axle box acceleration, achieving noise reduction and extraction of useful components. Next, we apply the fast Continuous Wavelet Transform analysis method to effectively transform one-dimensional data into two-dimensional images. Finally, the You Only Look Once (YOLO) model serves as a classifier for the classification and recognition of corrugation with different wavelengths. The results demonstrate that the mechanism-driven improved SVMD effectively extracts corrugation components from axle box acceleration, while the YOLO model achieves rapid and efficient identification and classification of corrugation with different wavelengths. The results show that compared with other traditional models, the training time of the YOLO model is 60%–90% of the training time of the traditional algorithm, and the Recall rate is 1.15–1.45 times that of the traditional algorithm. In terms of wavelength identification, the YOLO model has a recognition rate of 98% for different wavelengths. The proposed approach offers an innovative and efficient solution for identifying rail corrugation damage in axle box acceleration data.

Cracks are one of the most common diseases of tunnel lining, and the structural dynamic response can be used to assess the health of a tunnel. Hence, this paper investigates the dynamic response of shield tunnel lining with a partly circumferential crack. The shield tunnel lining is regarded as a thin cylindrical shell and analyzed independently. The research methodology integrates the wave propagation method, the local flexibility matrix, the line spring model and the wave superposition principle. The results show that the position and depth of a partly circumferential crack can influence the natural frequency of the shield tunnel lining. Under the fixed-position load, as the distance from the monitoring point to the crack increases, the difference in displacement response amplitude between the undamaged and cracked linings diminishes. Moreover, deepening cracks enlarge the magnitude of amplitude differences. When the load approaches the crack, the radial amplitude difference first increases and then decreases as the monitor moves away from the crack. This finding helps determine the required monitor position. The displacement response of the selected monitor indicates that the closer the load position is to the crack, the larger the amplitude difference. The results aid in identifying the crack position and selecting corresponding load and monitor locations.

In recent years, urban rail transportation has rapidly developed in China and become one of the most important modes of travel. Most existing studies on the dynamic characteristics of urban rail trains have been based on single-section trains, and there have been fewer studies on marshaling urban rail trains that incorporate traction transmission systems. The dynamic performance of each carriage directly affects the operational reliability and even the running safety of urban rail trains. For this reason, in this paper, a marshaling urban rail train model with a traction transmission system was established and its accuracy was validated by field tests. This dynamics model enables the consideration of the coupling interactions between the gear transmission motion, the vertical, the lateral and the longitudinal motions of the vehicle. First, the model accuracy was validated by field tests. Then, the relationship between the motor torque and the running time of the urban rail train under traction conditions was calculated. Finally, the dynamic performance of each car of the marshaling train was studied. The research results show that there is a clear difference between the dynamics of the motor car and the trailer, and that the motor car is significantly inferior to the trailer. Among the four motor cars, the dynamic performances of the first and last moving cars were worse than those of the other motor cars. Among the two trailers, the trailer at the back was worse than the trailer at the front. The traction transmission system has a greater impact on the vertical and lateral vibration of the train bogie frame and wheelset, but the impact on the vibration of the car body is negligible. This paper provides theoretical support for the research one train dynamic performance optimization and operation safety.

Fatigue damage is the most dangerous failure behavior for gearbox suspenders in urban railway vehicles, and passenger capacity is crucial to the dynamic load characteristics of the traction transmission system. Therefore, in this paper, a dynamic model of the motor car is established, and a numerical simulation is carried out under different speeds and curve radii to investigate the effect of passenger capacity on fatigue life. The research results show that passenger capacity is an essential factor affecting the fatigue life of suspenders. As the vehicle runs at an average speed, the fatigue life of the suspender is 1.07 × 10⁶ km when the passenger capacity is 120 people; when there are 240 people, the fatigue life reduction is 60%, while it is 86% at 339 people and 92% at 389 people. The per capita fatigue damage under a straight line is 7.27 × 10⁻¹⁰ at 20 km/h but 1.23 × 10⁻⁸ at 60 km/h. The per capita fatigue damage under a curved line is 7.18 × 10⁻⁹ in the 600 m curve but 9.00 × 10⁻⁹ in the 400 m curve. It can be concluded that the effect of speed is more significant than the curve radius. This research achievement can provide theoretical support for vehicle design and maintenance decisions.

Wet friction components are critical to power transmission in petroleum drilling machinery, where their reliability directly affects system stability. Surface defects, such as scratches and plowing grooves, can significantly degrade transmission performance, highlighting the importance of interface morphology prediction for intelligent wear diagnosis. In this study, interface morphology data under different conditions are acquired using a UMT-Tribolab test platform and a white light interferometer. The Scale-Invariant Feature Transform (SIFT) algorithm is employed to achieve precise localization of microscopic regions before and after testing. Based on this, an NRBO-VMD-Transformer model is developed to predict the interface morphology of wet friction components under varying conditions. The results demonstrate that SIFT enables accurate localization of microscopic regions, while the proposed model achieves high-precision prediction of interface morphology evolution. These findings provide a reliable basis for interface morphology prediction and wear evolution analysis of wet friction components.