The intelligent diagnosis of wheel flat based on vibration image classification is a promising research subject for performance maintenance of railway vehicles. However, the image representation method of vibration signal and classification network construction under small samples have become two obstacles to intelligent diagnosis of wheel flat. This paper presents a novel frequency-domain Gramian angular field (FDGAF) algorithm to encode the vibration signal of wheel flat to featured images. Furthermore, a modified transfer learning network is introduced to classify these featured images under small samples without any involvement of prior knowledge. The proposed FDGAF can calculate the Gramian angular matrix of axle box acceleration signal in frequency domain and assign frequency position dependence to the featured images to preserve original characteristic information. Then, these featured images can be intelligent classified by a transfer learning network under the condition of 30 sample without require of prior knowledge. To verify the efficiency of this proposed method, 12 cases of artificial wheel flats are processed on a scaled railway test rig, and their axle box acceleration signals are collected to obtain visual diagnosis results. The verfication proves that FDGAF is able to obtain accurate diagnostic results with high separability, for separability indexes of FDGAF reaches 10.8, 8.7, 14.9, and 5.8. We anticipate that this method will find use in the performance maintenance of railway vehicles and the improvement of industrial condition monitoring.

Gear–wheelset system is a crucial substructure in railway vehicles which affects the operation safety and system reliability, especially in the process of traction and braking conditions. Unlike the general gear transmission system, the gear–wheelset system of railway vehicles operates under an environment with several nonsmooth factors; therefore, it is necessary to analyze the nonsmooth dynamics of the gear–wheelset system for understanding dynamic characteristics better. Herein, a planar dynamic model of the gear–wheelset system of railway vehicles considering motor-driving torque, braking torque, wheel–rail nonlinear interaction forces, nonlinear meshing damping, and piecewise continuous time-varying meshing stiffness is proposed. Then, the proposed model is validated by a simpack model using wheelset's longitudinal velocity. Subsequently, two numerical simulations were performed to reveal the nonsmooth dynamic characteristics under traction and braking conditions. The simulation results indicate that the dynamic stationary point exists in nonsmooth dynamics under traction and braking conditions, which is a critical boundary for transiting any state to a dynamic equilibrium. Besides, the results exhibit the inseparable relationship between time-frequency dynamic characteristics, slip velocity, and wheel–rail nonlinear interaction forces. The effects of harmonic torque under traction conditions and compound braking behavior under braking conditions significantly affect these dynamic characteristics. Additionally, sufficient driving torque can increase the proportion of forward contact and improve the smoothness of the rotation, and the intermittent gear contact phenomenon occurs alternately and frequently in the traction condition. Conversely, only reverse contact occurs in the braking condition.

The differences between tri-axial vibration signals are often considered to be too small to affect the accuracy of gearbox fault diagnosis. Thus, the traditional approach of vibration signal processing based on one particular single axis is often used, which is often chosen by the accelerometer’s orientation relative to the fault location (vertical or horizontal) or the signal’s sensitivity to fault characteristics. This can cause some uncertainty and incompleteness in accurate diagnosis. To tackle this problem, we proposed a novel tri-axial signal information fusion model. In this model, measured vibration signals on three axes were analyzed at three levels to show their differences, and the visualized results were illustrated with histograms. Based on the comparison of the differences, the fusion model was used to analyze differences between the three different axes quantitatively based on the cross-approximate entropy, and such quantitative differences were utilized as adaptive weight coefficients to fuse three orthogonal axial signals. Through this process, the proposed model could transfer differences between different axial signals as adaptive fusion weights. To verify the superiority of the proposed strategy, a classical fuzzy C-means method was used to classify the fused signals from the model. With the measured gear fault signals under variable working conditions from the test bench, the reliability and superiority of the information fusion model proposed were proven through a comparison to fault diagnosis based on traditional signal axis selection.

Wheel faults are the main causes of safety issues in railway vehicles. The modeling and analysis of wheel faults is crucial for determining and studying the dynamic characteristics of railway vehicles under variable speed conditions. Hence, a vehicle–track coupled dynamics model was established for analysis and calculations. The results showed that the dynamic features of the wheel with a flat fault were more pronounced under traction and braking conditions, whereas the variations in the features under coasting conditions were insignificant. In this paper, a short-time fast Fourier transform and reassignment method was used to process the signals, because the results were unclear when the time–frequency graph was processed only by short time Fourier transform, especially under braking conditions. The variation in the fault frequency under variable speed conditions was determined. Finally, statistical indicators were used to describe the vibration behaviors caused by the wheel flat fault.

City disaster resilience and urban environmental cleanliness are two representative indicators used to assess the safety of human settlements in China’s Sustainability Development Goals (SDGs). Traditional research on SDGs mainly concentrated at large-scale spatial level, such as global level or national level. It brings unclear significance to the implementation of SDGs in the county-level. The goal of this paper is to find a new calculation method to apply the index of urban disaster resilience and urban environmental cleanliness to the evaluation of county-level areas. A localization of county-level city disaster resilience and urban environmental cleanliness based on Deqing County’s situation was carried out. With quantification and projections of local data, the assessments of city disaster resilience and urban environmental cleanliness have completed. The evaluation showed that city disaster resilience is maintained at a low level, while indicators of urban cleanliness are lower than standards. The prediction of urban per capita environmental impact index based on Grey Time-Series Prediction Model was finished. The forecast showed that the urban per capita impact indicators in the next three years have not exceeded the standard line. The two indicators used to assess the safety of human settlements were consistent with the sustainable development of urban settlement. Partial results of this research were reported as a “county sample” at the first UN Geographic Information Conference held in Deqing in 2018.

In the signal processing of real subway vehicles, impacts between wheelsets and rail joint gaps have significant negative effects on the spectrum. This introduces great difficulties for the fault diagnosis of gearboxes. To solve this problem, this paper proposes an adaptive time-domain signal segmentation method that envelopes the original signal using a cubic spline interpolation. The peak values of the rail joint gap impacts are extracted to realize the adaptive segmentation of gearbox fault signals when the vehicle was moving at a uniform speed. A long-time and unsteady signal affected by wheel–rail impacts is segmented into multiple short-term, steady-state signals, which can suppress the high amplitude of the shock response signal. Finally, on this basis, multiple short-term sample signals are analyzed by time- and frequency-domain analyses and compared with the nonfaulty results. The results showed that the method can efficiently suppress the high-amplitude components of subway gearbox vibration signals and effectively extract the characteristics of weak faults due to uniform wear of the gearbox in the time and frequency domains. This provides reference value for the gearbox fault diagnosis in engineering practice.