This paper conducts a joint analysis of monitoring data in the hidden danger areas of railway subgrade deformation using a data-driven method, thereby realizing the systematic risk identification of regional hidden dangers.

The paper proposes a regional systematic risk identification method based on Bayesian and independent component analysis (ICA) theories. Firstly, the Gray Wolf Optimization (GWO) algorithm is used to partition each group of monitoring data in the hidden danger area, so that the data distribution characteristics within each sub-block are similar. Then, a distributed ICA early warning model is constructed to obtain prior knowledge such as control limits and statistics of the area under normal conditions. For the online evaluation process, the input data is partitioned following the above-mentioned procedure and the ICA statistics of each sub-block are calculated. The Bayesian method is applied to fuse online parameters with offline parameters, yielding statistics under a specific confidence interval. These statistics are then compared with the control limits - specifically, checking whether they exceed the pre-set confidence parameters - thus realizing the systematic risk identification of the hidden danger area.

Through simulation experiments, the proposed method can integrate prior knowledge such as control limits and statistics to effectively determine the overall stability status of the area, thereby realizing the systematic risk identification of the hidden danger area.

The proposed method leverages Bayesian theory to fuse online process parameters with offline parameters and further compares them with confidence parameters, thereby effectively enhancing the utilization efficiency of monitoring data and the robustness of the analytical model.

This paper aims to systematically review the evolution of inspection technologies and equipment for heavy-haul railway infrastructure, with a focus on China's Shuohuang Railway and Daqin Railway. It summarizes the technological progression from traditional manual inspections to integrated and intelligent inspection systems, analyzes their practical application outcomes and outlines future research directions to support the safe, efficient and sustainable operation of heavy-haul railways.

The study employs a combination of historical and empirical analysis, primarily drawing on academic literature and operational data from Shuohuang Railway. The development of inspection technologies is categorized into two distinct phases: traditional inspection and integrated inspection. The comprehensive effectiveness of these technologies is evaluated based on actual inspection efficiency, defect detection capability, cost savings and other relevant data.

The adoption of integrated inspection vehicles has significantly improved inspection efficiency and accuracy. In 2014, the world's first heavy-haul integrated inspection vehicle enabled synchronous multidisciplinary inspections, greatly reducing reliance on manual labor. By 2024, the intelligent heavy-haul integrated inspection vehicle further enhanced detection precision by 30%. Practical applications demonstrate that the annual number of track defects decreased from 25,000 to 3,800, while the track quality index (TQI) remained stable below 6 mm. Additionally, annual maintenance costs were reduced by more than 40 m yuan.

This paper provides the first systematic review of the development of inspection technologies for heavy-haul railway infrastructure, highlighting China's leading achievements in integrated and intelligent inspection. It clarifies the practical value of these technologies in enhancing safety, reducing costs and optimizing maintenance operations. Furthermore, it proposes future directions for development, including system integration, onboard computing capabilities and unmanned operations, offering valuable insights for technological innovation and policymaking in the field.

This paper investigates how high-speed rail (HSR) influences socioeconomic inequality by providing the first systematic bibliometric review of research trends, methodological approaches and thematic structures. It examines whether HSR fosters balanced regional development or reinforces spatial disparities.

Using the Bibliometrix R package, 237 records were retrieved from the Web of Science (1985-2024). Citation indicators, keyword co-occurrence and collaboration networks were combined with natural language processing (NLP) to classify studies by territorial scale, methodology, economic variables and inequality outcomes.

The paper offers the first structured overview of how the literature conceptualizes the link between HSR and inequality. It highlights persistent gaps - scarcity of city-level analyses, limited socioeconomic indicators and reliance on Chinese case studies - providing a foundation for more comparative and interdisciplinary research.

This paper contributes by offering a structured overview of how the literature has conceptualized and measured the relationship between HSR and inequality. By identifying persistent research gaps - such as the scarcity of city-level analyses, limited use of socioeconomic indicators, and overreliance on Chinese case studies - it provides a foundation for more comparative and interdisciplinary approaches. The study informs policymakers and researchers on how to design future infrastructure projects that balance efficiency with equity.

In recent years, the rapid advancement of artificial intelligence (AI) has exerted profound impacts on and provided strong impetus to numerous fields in the industrial sector. Within the railway industry, AI has driven continuous upgrading and optimization of intelligent train control technology, thanks to its enhanced computational capabilities derived from advanced algorithms and models, as well as its role in improving safety performance. Integrating AI technology more extensively into train autonomous driving and control has thus become an inevitable trend in the global development of railways.

This paper, therefore, conducts a comprehensive analysis of the development progress and current status of AI technology applications in the field of train driving and control on a global scale. It systematically sorts out and analyzes the advantages of various AI technologies and the positive impacts they bring to the upgrading of train control technology, elucidates the feasibility and future prospects of applying a range of emerging AI technologies from the perspective of technical theory and provides guidance for the intelligent development of this field from a practical perspective.

The application of AI technology in the train driving and control field is still in its infancy. While a large number of AI technologies have been widely adopted, there remains significant room for further optimization and improvement of these technologies. Additionally, a variety of AI technologies that have been applied in other industrial sectors but not yet widely implemented in training autonomous driving and control have demonstrated tremendous development potential.

The research findings provide references and guidance for advancing train control technology, promoting the digital transformation of railways, accelerating the overall optimization and upgrading of railway industry technologies, and facilitating the accelerated development of global railways.

This research aims to monitor seismic intensity along railway lines, study methods for calculating the extent of earthquake impact on railways and address practical challenges in estimating intensity distribution along railway routes, thereby achieving graded post-earthquake response measures.

The seismic intensity monitoring system for railways adopts a two-level architecture, namely the seismic intensity monitoring equipment and the seismic intensity rapid reporting information center processing platform. The platform obtains measured instrumental intensity through the seismic intensity monitoring equipment deployed along railways and combines it with the National Seismic Network Earthquake Catalog to generate real-time railway seismic intensity distribution maps using the Kriging interpolation algorithm. A calculation method for railway seismic impact intervals is designed to calculate the mileage intervals where the intensity area corresponding to each contour line in the seismic intensity distribution map intersects with the railway line.

The system was deployed for practical earthquake monitoring demonstration applications on the Nanjiang Railway Line in Xinjiang. During the operational period, the seismic intensity monitoring equipment calculated and uploaded instrumental intensity values to the seismic intensity rapid reporting information center processing platform a total of nine times. Among these, earthquakes triggering the Kriging interpolation algorithm occurred twice. The system operated stably throughout the application period and successfully visualized relevant seismic impact data, such as earthquake intensity distribution maps and affected railway mileage sections. These results validate the system's practicality and effectiveness.

The seismic intensity monitoring for the railway system designed in this study can integrate the measured instrumental intensity data along railways and the earthquake catalog of the National Seismic Network. It uses the Kriging interpolation method to calculate the intensity distribution and determine the seismic impact scope, thereby addressing the issue that the seismic intensity distribution calculated by traditional attenuation formulas deviates from reality. The system can provide clear graded interval recommendations for post-earthquake disposal, effectively improve the efficiency of post-earthquake recovery and inspection and offer a decision-making basis for restoring railway operations quickly.

This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics, data sparsity and strong inter-sentence semantic dependencies. A robust entity extraction method tailored for accident texts is proposed.

This method is implemented through a dual-branch multi-task mutual learning model named R-MLP, which jointly performs entity recognition and accident phase classification. The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity. A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.

R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model's ability to capture inter-sentence semantic dependencies. Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities, significantly outperforming baseline models such as RoBERTa and MacBERT.

This demonstrates the proposed method's superior generalization and accuracy in domain-specific entity extraction tasks, confirming its effectiveness and practical value.

This study examines the effect of increased surface energy on adhesion strength. Surface modifications were made using chemical coating methods such as primer paint (primer) and cataphoresis (KTL, Kathodische Tauchlackierung). The wetting behaviour of adhesive on these surfaces and the resulting contact angles were analysed to evaluate bonding effectiveness.

Primer paint was applied to glass fibre reinforced plastic (GFRP) materials and cataphoresis coating was applied to steel. Contact angles of the coated surfaces were measured and compared to those of the uncoated (natural) surfaces.

Results showed that applying primer to GFRP and KTL to steel increased their surface energy compared to untreated surfaces. A decrease in contact angle correlated with improved wetting, suggesting enhanced adhesion potential.

While the effects of surface coatings on adhesion have been studied, there is limited research specifically on the adhesion-enhancing potential of KTL coatings. Typically used for corrosion resistance, KTL is shown here to also improve adhesion. The novelty lies in experimentally demonstrating KTL's dual role as both a protective and adhesion-enhancing layer.

This study aims to design and validate an emergency response method for high-speed railway earthquake early warning (EEW) systems based on the Propagation of Local Undamped Motion (PLUM) principle in order to enhance the timeliness and accuracy of warnings under seismic threats.

A hierarchical architecture of the railway EEW system was adopted, in which self-built stations along the railway serve as the backbone and the national seismic network provides supplementary data. Warning zones were designed along the railway using overlapping trapezoidal layouts to cover seismic stations and reduce inter-regional time delays. Offline replay experiments were conducted using 82 historical earthquake events and records from 61 seismic stations to evaluate the timeliness and accuracy of warning information.

The results indicate that the PLUM-based early warning method can issue emergency response information before destructive seismic waves arrive. Multiple earthquake experiments demonstrated high reliability and stability, with effective detection across different magnitudes and epicentral distances. Furthermore, the trapezoidal overlapping zone design improved regional consistency and significantly reduced missed alerts.

This work represents the first systematic application of the PLUM method to high-speed railway EEW in China. By integrating railway operational requirements, the proposed method provides a practical and robust emergency response strategy, offering new insights into seismic risk mitigation for China's high-speed railways.

This paper aims to analyze the transverse vibration characteristics of the high speed train window glass when passing through tunnel.

The lateral vibration acceleration response of glass chamber of high-speed train CR400BF-A on Beijing - Chengdu high-speed railway was tested at different speeds through the tunnel entrance, exit, tunnel interior, Tunnel Group and rendezvous time in the tunnel, the lateral distribution characteristics of vibration frequency and vibration power amplification coefficient of glass of high-speed train were analyzed.

The results show that: The vibration of the high-speed train glass increases significantly during the tunnel, and the amplitude of vibration acceleration in the tunnel is significantly higher than outside the tunnel as the travel speed increases; the amplitude of lateral vibration acceleration of the glass of a high-speed train does not vary with changes in tunnel length and is not affected by the aerodynamic effects of the tunnel when traveling inside the tunnel, but its vibrations create noticeable fluctuations during variations when encountering oncoming traffic; The vibration characteristics of the high-speed train glass are forced harmonic vibrations, the excitation frequency does not vary with travel speed and travel position changes inside and outside the tunnel. The lateral vibration acceleration of the glass of a high-speed train is applied vertically and uniformly to the glass surface as an "inertial force" and creates a cyclic bending vibration stress that can easily lead to fatigue damage.

The research results provide guidance for the prevention of glass failure in high-speed trains.

Type-120 relief valves are critical components of locomotive braking systems, and they rapidly discharge the air pressure during brake release to enable swift pressure relief. In order to develop type-120 relief valve rubber diaphragms with long life and high performance, the damaged faulty samples were analyzed and studied.

Finite element analysis (FEA) was used to investigate the stress distribution and failure mechanism of the rubber diaphragms within the type-120 relief valves under dynamic loading conditions. The Ogden hyperelastic constitutive model was used to fit the diaphragm data obtained from the uniaxial tensile tests, and its suitability for the modeling of large deformations was confirmed.

The FEA results indicated that, when the rubber diaphragms reached their maximum deformation, the peak stress on their upper surfaces was 5.44 MPa. Thus, this region is highly susceptible to fatigue damage. The service life of the rubber diaphragms could be extended by using rubber compounds with high tensile moduli or a fabric-reinforced rubber diaphragm.

This study provides valuable data and experience for the development of the rubber diaphragms in the type-120 valves and other long-life rubber products in the railway field.