Abstract:Over the past two decades, China’s high-speed trains have advanced from a follower to a global leader, achieving the highest commercial operation speed, deploying the largest fleet of high-speed trains, recording the fewest failures per 100 km, and delivering the best running stability worldwide. High-speed trains have not only become a prominent symbol of national development, but also a vivid representation of equitable access to the benefits of modernization in the new era. The key to this remarkable success lies in the exceptional system integrity achieved in China’s high- speed trains. System integrity includes structural integrity, dynamic integrity, and functional integrity. This article defines the concept of system integrity and provides a comprehensive interpretation. Intelligent operation and maintenance of high-speed trains has emerged as a major research focus in recent years. Aiming to safeguard system integrity, this article explores intelligent operation and maintenance strategies, including dynamic condition monitoring and evaluation, intelligent service life prediction, and preventive maintenance planning.

Abstract:Vibration performance of rail vehicles is a crucial factor in ensuring operational safety, enhancing ride comfort, and prolonging component service life. With the rapid development of high-speed railways and urban rail transit systems, continuous increases in train speeds, increasingly complex track environments, and growing demands for intelligent maintenance have brought both challenges and opportunities to vibration performance maintenance technologies. This paper systematically reviewed the latest research progress and future development trends in this field from five key perspectives: vibration performance evaluation standards, vibration performance design and optimization, vibration performance operation and maintenance, vibration performance degradation prediction, and technological advances in remaining useful life assessment. The study indicates that future vibration performance maintenance will place greater emphasis on preventive strategies. Through model prediction and big data analytics, it will achieve fault early warning and proactive intervention, thereby establishing a safer, smarter, more economical, and more efficient safety assurance system for rail transit. This approach will not only improve operational reliability but also provide significant support for the sustainable development of rail transportation systems.

Abstract:Aiming at the problem of high crack rate in key positions of cast traction seats for railway locomotives during long-term service, a study was conducted on the post-weld fatigue failure mechanism at key positions of cast traction seats based on fracture analysis. Firstly, a experimentally validated finite element model of the traction seat was established, and it was determined that there is a significant stress concentration area at the large arc of the base of the traction seat under standard traction braking loads. Then, a high cycle fatigue test was conducted on the traction seat based on the standard load spectrum, reproducing the initiation and propagation process of macroscopic cracks in the stress concentration area. Finally, fracture analysis, scanning electron microscopy (SEM) observation, metallographic examination, and energy dispersive spectroscopy (EDS) were per-formed on the fatigue crack failure area, indicating the presence of obvious welding repair marks and heat-treated microstructure in the crack area. The research results indicate that the fatigue cracking failure of the traction seat is the result of the combined effect of stress concentration at the base arc and defects introduced by welding repair. It is important to focus on controlling the casting quality at the large arc of the base and avoid welding repairs. The research can provide theoretical guidance for the safe and efficient operation of railway freight and the maintenance and repair of parts.

Abstract:The inversion of track irregularity using vehicle vibration responses serves as a vital method for track condition detection and a key part in achieving intelligent operation and maintenance of railway vehicles. To this end, this paper takes a railway vehicle operating at 160 km/h as an example, establishing three dynamic models for the vehicle system: lateral, vertical, and lateral-vertical coupled. The track irregularity inversion equation is derived within the state-space framework of the vehicle system. An inversion process for track irregularity based on the classical Kalman filter (KF) and adaptive Kalman filter (AKF) algorithms is presented. Finally, a detailed investigation is conducted into the influence patterns of the Kalman filter algorithms, vehicle dynamics models,and observation schemes on the inversion results of lateral and vertical track irregularities. The results indicate: Compared to single lateral or vertical models, the lateral-vertical coupled model yields the best inversion results under the KF algorithm, demonstrating its superior capability in simulating the lateral and vertical motion behaviors of the vehicle. The AKF algorithm performs better in single lateral and vertical models but fails to leverage its adaptive parameter-tuning advantages in the lateral-vertical coupled model. This suggests that adaptive strategies may not guarantee convergence to optimal solutions for complex high-dimensional coupled models, whereas simpler low-dimensional models benefit more from adaptive inversion. The observation scheme significantly impacts track irregularity inversion results. Specifically, relying solely on vibration acceleration measurements proves inadequate for effective inversion. Therefore, effective vibration responses shall be supplemented in combination with the actual situation.and observation schemes on the inversion results of lateral and vertical track irregularities. The results indicate: Compared to single lateral or vertical models, the lateral-vertical coupled model yields the best inversion results under the KF algorithm, demonstrating its superior capability in simulating the lateral and vertical motion behaviors of the vehicle. The AKF algorithm performs better in single lateral and vertical models but fails to leverage its adaptive parameter-tuning advantages in the lateral-vertical coupled model. This suggests that adaptive strategies may not guarantee convergence to optimal solutions for complex high-dimensional coupled models, whereas simpler low-dimensional models benefit more from adaptive inversion. The observation scheme significantly impacts track irregularity inversion results. Specifically, relying solely on vibration acceleration measurements proves inadequate for effective inversion. Therefore, effective vibration responses shall be supplemented in combination with the actual situation.

Abstract:To achieve accurate prediction of the remaining useful life (RUL) of brake discs, ensure train braking safety, and optimize economical maintenance, this paper proposes a prediction model based on the fusion of selfattention mechanism and long short-term memory network (BiLSTM- SA), which takes the crack propagation life as the division basis. Firstly, the test data of brake discs are collected and the working conditions are calibrated, and a thermal-mechanical coupling finite element model is established to obtain the simulation dataset. Secondly, a Time-GAN neural network is constructed, which enhances data through a double-layer LSTM generator and a physical constraint discriminator. Its distribution similarity, root mean square error and coefficient of determination are significantly better than traditional models. Finally, the BiLSTM-SA fusion prediction model is proposed, which uses bidirectional LSTM and self-attention mechanism to capture temporal dependencies and key features. In the prediction of single expanding cracks, the RMSE is reduced by 49.8% and 46.5% compared with the traditional LSTM and TCN-LSTM, respectively. In complex working conditions, the RMSE and Score are optimized by 25.5% and 51.1% , respectively, significantly improving the prediction accuracy and robustness.This study can provide a reliable technical solution for condition monitoring and preventive maintenance of highspeed train brake discs.

Abstract:In order to improve the driving safety and stability of trams passing through the S-shaped curve lines with small radius, the rational optimization of vehicle suspension parameters is proposed. Taking a tram line in Guangzhou as the engineering background, the dynamic model of vehicle-track coupling system was established by using the multi-body dynamics and finite element methods and the influence laws of vehicle suspension parameters on the operational evaluation indicators such as vehicle stability index, wheel-rail force, derailment coefficient, and wheel load reduction rate, were explored. By combining the optimal Latin hypercube sampling technique, BP neural network, and multi-objective genetic algorithm, the optimized suggestions for the tram suspension parameters were obtained. The results show that the operational evaluation indicators of the vehicle are significantly improved after the optimization. Compared with before optimization, the derailment coefficient of the vehicle has decreased by more than 10%. The research results provide theoretical support for the optimization design of suspension parameters for trams.

Abstract:When high-speed train wheels and turnouts (switches and crossings) experience wear, especially when worn wheels pass through the turnout area, the wheel-rail dynamic responses triggered by geometric discontinuities pose a threat to driving safety and severely affect passenger comfort, making it urgent to conduct research. By employing the finite element method, an in-depth investigation is carried out into the stress distribution, interaction, and their influence mechanisms between high- speed train wheels and turnouts, as well as the evolving laws with the changes in wheel wear and turnout geometric shapes. The study finds that the interaction between wheels and turnouts is influenced by multiple factors, including the wear states of wheels and turnouts, cumulative tonnage passed, and track geometric shapes. When a wheel passes through the turnout, as its position changes, the wheel- turnout contact stress and Von Mises equivalent stress fluctuate significantly. When the wheel moves from a position where the top width of the switch rail is 15 mm to one where it is 35 mm, the overall contact stress rises notably, with a growth rate of approximately 14.4%; the maximum Von Mises equivalent stress also shows an increasing trend, with a growth rate of about 4.1%. Wheel wear not only alters the shapes of the wheel rim and tread but also significantly affects the wheel-rail contact relationship and stress distribution. The wheel-rail contact point gradually deviates from the track center, and this deviation is positively correlated with the increase in operating mileage. The stress distribution along the depth direction becomes more uneven and is greater compared to that of a newly re-profiled wheel. Meanwhile, the changes in stress affect the wheel wear rate.

Abstract:Based on the theory of heat transfer and the mechanics of beam-slab-rail interaction,a refined thermomechanical coupling model for the bridge- mounted CRTS Ⅲ type ballastless track seamless lines was established to simulate the temperature field, longitudinal forces, and displacement variations of the track structure components under sustained high temperature environment ranging from 2~10 days. The findings elucidate a direct correlation between the escalation of sustained high temperature periods and the continual increase in temperature within the track structure, with an accentuated phenomenon of heat accumulation at deeper vertical strata. Additionally, there is a progressive reduction in the magnitude of the maximum positive temperature gradient, while the maximum negative temperature gradient experiences a gradual increase. Moreover, the longitudinal forces exerted on the steel rails and the longitudinal displacements of the track structure exhibit a cumulative pattern with the extension of the high-temperature regimen. In contrast, the longitudinal stresses within the track slabs, self-compacting concrete layers and slab demonstrate a decremental trend in correlation with the duration days.

Abstract:In order to obtain the safety performance index that is most suitable for the performance evaluation of high- speed trains passing through turnouts under crosswind, the operation safety domains of high- speed trains passing through turnouts in straight and side reverse directions under crosswind are proposed. By establishing the aerodynamic model of high-speed trains passing through turnouts and the dynamic model of crosswind-trainturnout coupling multi- body system, the safety of high- speed trains passing through turnouts under crosswind was deeply explored. The results show that under the action of crosswind, the pressure on the windward side increases significantly, and the obvious pressure difference is formed on both sides of the head car, which makes the head car more prone to derailment and rollover during operation. When the high-speed train passes through the turnout directly and reversely, when the crosswind wind speed is not more than 15 m/s, the high-speed train can pass through the turnout at a speed of 250 km/h; when the crosswind speed reaches 20 m/s and above, the speed of the high-speed train should be less than 250 km/h. When the crosswind speed is greater than 15 m/s, the speed of the high-speed train side should be less than 80 km/h. Under the action of crosswind, the head car is more prone to derailment and rollover when the high-speed train runs. When the high-speed train passes through the turnout directly and reversely, when the crosswind speed reaches 8 and above, the speed of the train passing through the turnout should be less than 250 km/h. When the side of the high-speed train passes through the turnout reversely, when the crosswind speed reaches 7 and above, the speed of the train passing through the turnout should be less than 80 km/h. The research results can provide reference for the smoothness and safety of highspeed trains passing through turnouts under different crosswind conditions.

Abstract:This study addresses the challenges of information asymmetry and inefficiency in the recycling of new energy vehicle batteries by exploring a blockchain-based traceability system aimed at improving recycling efficiency, transparency, and reducing environmental risks. Blockchain technology was employed in the management of the full lifecycle of power batteries. An evolutionary game model was constructed to analyze the strategic interactions among battery manufacturers, vehicle manufacturers and the government, assessing their impact on system stability. Simulation results reveal that the blockchain traceability system, supported by appropriate incentive mechanisms and policy designs, significantly improves transparency and the efficiency of battery recycling management, while mitigating the negative effects of information asymmetry. The blockchain-based traceability system provides notable advantages in enhancing the management efficiency of power battery recycling. It offers a scientific foundation for policymakers, encouraging innovation and promoting the effectiveness of new energy battery recycling systems.

Abstract:Online freight platform is one kind of typical new platform economy mode in logistics industry while risks are emerging due to the separation of cargoes property, fund, place, and time in the course of the operation process. Therefore, scientifically assessing the risks associated with online freight transportation platforms is crucial for promoting reasonable regulation on these platforms. Starting from the operational process of online freight platforms, this study constructed a risk evaluation index system including 8 aspects and 30 indicators, i.e. registration, verification, truck-cargo matching, order execution, order completion and etc. The best-worst method (BWM) was adopted to determine the weights of risk sources and experts’weights through evaluating decision makers’understanding of online freight platforms. Then, comprehensive weights were obtained through combined consideration of the two results. Risk assessment was then conducted based on the fuzzy FMEA-TOPSIS model, calculating the distances from risk factors to both positive and negative ideal solutions. The risk levels were ranked according to their relative closeness, and comparison was made with traditional FMEA to verify the effectiveness of fuzzy FMEA-TOPSIS model.

Abstract:Density peak clustering (DPC) has been widely used as an efficient and non-iterative clustering algorithm. However, studies have found that DPC struggles to select correct cluster centers, especially in datasets with non-spherical clusters and non-uniform density. Moreover, DPC is heavily influenced by the truncation distance parameter. In order to address the issue of poor performance of DPC on datasets with uneven density distributions, a density peak clustering algorithm based on natural and weighted shared nearest neighbors is proposed. It first introduced natural nearest neighbor computations to calculate weights. Then, it redefined the similarity between data objects based on the definitions of first-order and second-order shared nearest neighbors. Subsequently, by fusing the definitions of shared nearest neighbor similarity and natural nearest neighbor weights, relative density and relative distance were calculated. Finally, a novel strategy for distributing cluster centers was designed.