Against the backdrop of urban rail transit shifting from large-scale expansion to quality improvement of existing assets, increasing uncertainty in land and property development revenues, and rising long-term operational pressures, the notion that "building rail transit is building the city" has become an urban governance proposition during the transition from intensive rail construction to long-term operation. This paper takes the 30-year development of Shenzhen rail transit as a case study and adopts qualitative interviews based on first-hand materials and case analysis to examine how rail transit is embedded in urban spatial organization and governance processes, thereby being transformed into a form of city-building capacity. Based on the correspondence between different stages of rail transit development and urban transformation in Shenzhen, the study systematically analyzes the functional mechanisms of rail transit in terms of public-interest positioning, network organization, station-area functions, and coordinated implementation, and further examines the operational logic of the "building rail transit is building the city" model. The findings suggest that the urban value of rail transit is not directly derived from network scale or property-led development along rail corridors, but is progressively realized through improved accessibility, spatial restructuring, and interdepartmental coordination; the key to the operation of this model lies in the recirculation of spatial value generated by public investment and benefit-sharing mechanisms, rather than in simple market-oriented development activities. In the context of existing-asset-oriented development, the continued role of rail transit in "building the city" should shift from scale expansion and development-revenue orientation to improving the efficiency of existing networks during the stable operation phase, station-area renewal, and strengthening public service provision.

To bridge the gap between AI technological breakthroughs and industrial value release in urban rail transit and foster new-quality productive forces as well as high-quality sustainable development, this paper studies AI implementation with the technical logic of "perception-decision-making-execution" and the connotation of new-quality productive forces, based on academic literature, patents and industry questionnaire data. It targets practical problems including fragmented AI implementation, lagging factor allocation and insufficient knowledge transformation, and puts forward a holistic AI implementation framework with three core innovations. The study concludes that a high-quality urban rail transit knowledge base is the top priority, data elements are the core of innovative factor allocation, and 1-to-N scenario expansion is the inevitable path for urban rail transit AI to translate technological breakthroughs into industrial value.

With the continued expansion of urban rail transit networks and the increasing complexity of operating scenarios, passenger demand exhibits more complex spatiotemporal patterns, posing higher requirements for train operation organization and passenger flow control. Short-term passenger flow prediction is an important basis for urban rail transit operation management and provides key support for operational decision-making. In recent years, artificial intelligence-based methods have become an important technical approach for improving short-term passenger flow prediction performance, owing to their strong capability to extract complex spatiotemporal features. This review focuses on artificial intelligence-based methods for short-term passenger flow prediction in urban rail transit systems. It first constructs a task analysis framework from five dimensions: prediction scenarios, prediction targets, data sources, prediction methods, and evaluation metrics. Second, the development trajectory of prediction models is systematically reviewed. Furthermore, recent studies and major challenges are summarized for different prediction tasks, including station inflow and outflow passenger flow prediction, origin-destination passenger flow prediction, section passenger flow prediction, multi-type passenger flow collaborative prediction, and multimodal traffic prediction with rail transit as the backbone. Finally, future research directions are discussed from the perspectives of large language models, trustworthy and interpretable prediction, an end-to-end predict-and-optimize learning framework, and world models. This review shows that short-term passenger flow prediction in urban rail transit is evolving from single-flow-type, single-metric, and single-task prediction toward integrated development featuring multi-source perception, multi-type passenger flow collaboration, and multi-metric evaluation. Future research should further emphasize general adaptability, uncertainty awareness, trustworthy risk assessment, decision-oriented prediction, and world-model-driven dynamic deduction, with the aim of building an integrated intelligent prediction and simulation framework for complex operational scenarios and supporting refined operational decision-making in urban rail transit.

To explore in depth the technological evolution logic and independent innovation path of metro in China from combat readiness assistance to modern urban engine transformation. Focusing on five key components: rail and continuously welded rail, fasteners, turnouts, monolithic track bed, and vibration-damping track structures, the technological progress in each area is elaborated: in addition to the adoption of high-speed rail technologies based on project requirements, the characteristics of metro systems—such as numerous small-radius curves and frequent overloading—have also driven the application of wear-resistant rails in locations like sharp curves and turnout sections; fasteners have diversified into a standardized system represented by series such as DT、ZX、WJ, with continuous improvements in design and manufacturing; turnouts have evolved from national railway standards to urban rail series such as Cheng Gui suited to metro engineering needs; the monolithic track bed has established a standard system centered on concrete long-sleeper embedded types, alongside new structural forms such as prefabricated and assembled technologies; and vibration-damping track structures have formed a diversified technical system covering fasteners, sleepers, and track-bed solutions. Looking ahead, track structure technology will continue to advance in design, construction, maintenance, and upgrading of in-service lines, while China's metro technical standards are progressively moving toward internationalization.

In response to the need for a systematic understanding of the development trajectory, market characteristics, and practical challenges of China's overseas urban rail transit infrastructure market, this study focuses on urban rail transit infrastructure projects launched overseas by Chinese enterprises between 2005 and 2025. It conducts a comprehensive statistical analysis of project numbers, host countries, route mileage, construction status, regional distribution, system types, and development stages, and further examines the formation of the overseas urban rail transit market landscape, its evolutionary trajectory, and the major problems faced by Chinese enterprises. On this basis, the study proposes systematic solutions from seven dimensions: regional market positioning, industrial chain extension, risk prevention and control, financing models, cost management, rules and standards, and technological and talent reserves. These solutions include implementing tiered and targeted market strategies based on regional potential, developing a TOD-based "urban rail transit + integrated development along the corridor" overseas ecosystem, establishing a country-specific, tiered geopolitical risk prevention and early-warning system, innovating diversified self-sustaining financing models supported by multilateral finance and station-area property development, building localized benchmark databases and implementing full life-cycle cost control mechanisms, strengthening "soft connectivity" through rules and standards, and enhancing core technologies such as autonomous operation and intelligent maintenance, together with international talent reserves. The results show that from 2005 to 2025, Chinese enterprises constructed 55 urban rail transit lines in 21 countries across five continents, with a total completed and under-construction mileage of 984.2 km. Geographically, the overseas market is highly concentrated in three major regions: Southeast Asia, West Asia and North Africa, and Sub-Saharan Africa. In terms of system type, large-capacity metro systems remain dominant. The development process has gone through three stages: initial exploration, Belt and Road Initiative-driven expansion, and transition toward high-quality development. It also exhibits a shift from civil engineering contracting to full industrial chain output, and from short-term operation and maintenance services to long-term concession-based operation. Meanwhile, Chinese overseas urban rail transit projects still face problems such as delays in project implementation, a significant increase in bidding failures, and losses in some projects. Overall, China's overseas urban rail transit industry is at a critical stage of transition from extensive scale expansion to sustainable value-oriented output. It is therefore necessary to enhance the overall competitiveness and sustainable development capacity of overseas urban rail transit projects through targeted market positioning, integrated development models, proactive risk control, diversified financing mechanisms, full life-cycle cost management, alignment of rules and standards, and the development of core technologies and international talent systems, so as to better support Belt and Road infrastructure connectivity and the building of a global community of shared future in transport cooperation.

With the transition of urban rail transit toward networked operations, the scientific planning of transit networks is critical for ensuring operational efficiency and service quality. This systematically the research progress on optimization models and methodologies for urban rail transit networks, based on relevant studies published from 2015 to 2025. Current rail transit network optimization models suffer from idealized assumptions and insufficient characterization of practical constraints. Moreover, the three mainstream solution approaches—exact algorithms, intelligent heuristic algorithms, and deep reinforcement learning—each have respective drawbacks in computation efficiency, stability, generalization capacity and other aspects. The paper begins by establishing a taxonomy of transit network planning problems from three perspectives: planning scenarios, modeling formulations, and solution method. Then, in terms of optimization models, the evolution from single-objective to multi-objective formulations is reviewed, highlighting the development of multi-dimensional objective systems involving efficiency, cost, equity, and resilience. This paper further summarizes the main advances in initial network generation models and existing network expansion optimization models. On the algorithmic side, the paper covers exact methods, metaheuristic algorithms, surrogate-assisted optimization, and the emerging deep reinforcement learning (DRL) paradigm, with particular attention to studies that formulate network design as a Markov Decision Process (MDP). It is concluded that the existing optimization models generally have structural defects and deviate from engineering practice. They fail to fully characterize practical constraints such as transfer layouts, capacity limits and time-varying passenger flows, which greatly reduces their practical application value. Five research directions are therefore proposed to improve relevant research: constructing a hybrid optimization framework for large-scale networks, establishing an integrated supply-demand coordination model, developing collaborative optimization theories for multi-mode rail transit systems, forming a low-carbon sustainable optimization system, and building a digital twin-driven dynamic decision-making model.

To address the limitation of the traditional Node-Place model in capturing actual passenger-flow vitality and its variation across travel scenarios, this study introduces a vitality dimension and develops a Node-lace-vitality model to identify urban rail transit station-area types and examine their differences across travel scenarios. Taking 211 urban rail transit stations in Xi'an as the sample, this study integrates multi-source data, including rail transit network topology, station facilities, feeder transport services, built environment characteristics, population activities, point of interest (POI) functional facilities, and hourly origin-destination (OD) ridership. An evaluation indicator system covering the three dimensions of node, place, and vitality is established. A combined weighting method is used to determine indicator weights, and a Gaussian mixture model is applied to identify station-area types under workday and National Day holiday scenarios. The transition characteristics of station-area types across different scenarios are then analyzed. The results show that the node, place, and vitality scores of Xi'an rail transit stations generally exhibit a spatial pattern of "high values in the central urban area and low values along peripheral lines". Under the National Day holiday scenario, some stations show a significant increase in passenger flow vitality. The station areas can be classified into five types: hub-integrated stations, station-city coordinated stations, vitality-responsive stations, place-supporting stations, and basic-cultivation stations. Their spatial distribution presents a clear concentric pattern characterized by "central agglomeration and peripheral differentiation". Station-area types remain generally stable between workday and holiday scenarios. Among the 211 stations, 192 stations retain the same type, accounting for 91.00%, while 19 stations experience type transitions, accounting for 9.00%. These transitions mainly occur between place-supporting stations and basic-cultivation stations, and are primarily distributed outside the Second Ring Road. The findings provide a scientific basis for station-area functional optimization, peripheral station cultivation, differentiated development under the Transit-Oriented Development (TOD) framework, and refined rail transit operations management.

There are significant differences in passenger flow distribution patterns between metropolitan rapid rail transit and metro systems. How to conduct a scientific and reasonable evaluation is crucial to the healthy development of metropolitan areas and urban agglomerations in China, and thus deserves in-depth exploration. This paper systematically defines the connotation, calculation methods, and applicable boundaries of passenger transport intensity and passenger flow density based on the Urban rail transit operation indicator system (GB/T38374—2019) and the 2025 annual statistical data of the China Urban Rail Transit Association. It compares and analyzes the differences between metropolitan rapid rail transit and metro in terms of travel space, time, demand, and operational characteristics. Using data from 34 operational metropolitan rapid rail transit in 22 cities across the country and typical lines in multiple cities as examples, this paper conducts a quantitative empirical analysis. The results show that in 2025, the average passenger transport intensity of medium-capacity system category including metropolitan rapid rail transit in China was only 1.8 thousand person-times/km·day, far lower than the 7.3 thousand person-times/km·day for metro systems, while the passenger flow density reached 24.6 thousand person·km/km·day, indicating that its transport efficiency was underestimated. The average travel distance of metropolitan rapid rail transit is generally greater than 30 km, which is the core factor causing the evaluation deviation between the two indicators. Passenger flow density is more capable of matching the functional positioning of long-distance transportation of metropolitan rapid rail transit. The passenger flow density indicator is also applicable to metro lines with shorter travel distances in central urban areas, but due to the relatively short average travel distance of metro, passenger transport intensity and passenger flow density are highly positively correlated. Building on a systematic review of existing studies, this paper proposes a multi-dimensional evaluation framework for metropolitan rapid rail transit, with passenger flow density as its core while incorporating average travel distance and spatiotemporal convergence benefits. The objectivity of the proposed framework is validated through theoretical analysis, empirical testing, and comprehensive benefit assessment. Optimization recommendations are further offered to provide theoretical support and reference for the planning approval, operational assessment, and high-quality sustainable development of metropolitan rail transit.

To review the research progress of Virtual Coupling (VC) technology in rail transit transportation organization and identify its applications in train operation plan optimization and rescheduling, this paper presents a comprehensive literature review of recent studies in the field. From an operational and service-oriented perspective, 42 representative publications published between 2022 and 2025 were collected from major academic databases, including Web of Science, Scopus, IEEE Xplore, and CNKI. Research on train operation plan design, timetable optimization, integrated timetable and rolling stock circulation planning, as well as train delay rescheduling, disruption management during disruption and recovery phases, was reviewed and compared. The results indicate that VC technology can significantly enhance line capacity and operational flexibility through reduced train headways and dynamic coupling and decoupling operations. In terms of operation planning, existing studies have evolved from isolated timetable optimization to integrated optimization of timetables, stopping patterns, train routing, and rolling stock circulation. In terms of operation rescheduling, VC has demonstrated considerable potential in improving transportation organization resilience and passenger evacuation efficiency under disruption scenarios. However, current research still faces several limitations, including insufficient integration among planning elements, limited consideration of complex rail networks, inadequate investigation of multi-strategy collaborative rescheduling, and a lack of unified frameworks covering the entire disruption process. Future research should focus on integrated optimization of timetables, stopping patterns, train routing, and rolling stock circulation; integrated modeling of train operation organization, dispatching, and control; multi-strategy collaborative rescheduling; full-process disruption rescheduling; and the application of intelligent optimization approaches such as deep reinforcement learning in VC-enabled rail transit systems.

To improve the operational safety of urban rail transit trains, mitigate train operation risks under extreme weather conditions, and address the significant performance decline of traditional wheel-rail adhesion-based braking methods, this paper investigates the vibration generation mechanism and dynamic response characteristics of high-suspension magnetic track brakes under emergency braking conditions. Based on its working principle of electromagnetic adhesion and friction braking, the vibration characteristics are identified by simulating the effects of rainy and snowy weather on the track. The vibration transmission path consisting of the braking device, bogie, and car body is established. Vertical and lateral vibration data under various working conditions are collected via triaxial acceleration sensors, and a quantitative evaluation of vehicle running safety and ride comfort is conducted based on ride smoothness and stability indices. The results show that under wet track conditions in rainy and snowy weather, the peak vibration acceleration of the high-suspension magnetic track brake is less than 2.5 m/s². Vibration is transmitted through the bogie-car body path and exerts a minor impact on the service life of on-board electronic equipment. The braking mode of the high-suspension magnetic track brake has little effect on vehicle ride smoothness. Adding magnetic track brakes is of great engineering value for ensuring the high-speed, safe, and comfortable operation of urban rail transit under diverse complex meteorological conditions.

To address the challenges of weak feature extraction capability and poor adaptability to multi-source data encountered by by intelligent inspection algorithms in urban rail transit equipment rooms under complex environments, this paper proposes an innovative inspection scheme based on large vision models. This scheme leverages the powerful deep semantic modeling capability of large vision models to perform multi-granularity feature extraction equipment-room monitoring images, while simultaneously introducing an adaptive multi-scale fusion module to optimize feature representation capability. To balance computational efficiency and detection accuracy, a cloud-edge collaborative architecture is designed. The cloud hosts the complete large vision model and is responsible for high-precision inference in complex scenarios and model iteration, while the edge side deploys a lightweight inference module for preprocessing, real-timedetection, and fault early warning of inspection images, ensuring the timeliness and safety of equipment room operation and maintenance. To validate the effectiveness of the proposed scheme, tests are conducted using real operational data from the equipment room of Dalian North Station on Dalian Metro Line 1, covering various equipment types. Experimental results show that the algorithm achieves an mAP@50 of 0.923 and an F1-score of 0.915 in equipment state detection tasks, outperforming mainstream inspection algorithms in overall detection performance. Economic benefit analysis indicates that the scheme incurs an average annual operating cost of approximately RMB 440,000 yuan, representing an annual saving of about RMB 460,000 yuan per year compared with traditional manual and periodic maintenance approaches, demonstrating sound economic feasibility. Furthermore, the scheme adopts a general-purpose industrial hardware acquisition architecture, standardized data access protocols, and a modular algorithm design, offering strong scenario adaptability. It is not limited to urban rail transit equipment rooms and can be extended to other rail transit scenarios such as subway tunnels and stations.

To address the problems of high manual dependence, complex data processing, and low construction efficiency in constructing knowledge graphs for rail transit operation and maintenance, this paper proposes an automated knowledge graph construction method based on large language models. First, two-stage domain-specific prompt templates for rail transit operation and maintenance are designed for domain concept layer generation and operation and maintenance data extraction, respectively. Second, the zero-shot learning capability of large language models is employed to automatically generate knowledge graph data that conform to RDF syntax specifications. Finally, a prompt-driven knowledge graph construction framework is developed to automatically transform rail transit operation and maintenance metadata into RDF knowledge graphs and support integration with existing knowledge graphs. The experimental results show that, compared with the general prompt, the proposed method improves entity extraction accuracy from 81.2% to 93.8%, an increase of 12.6 percentage points; the completeness of the concept layer increases from 68.4% to 91.6%; and the accuracy of complex relation extraction increases from 46.7% to 78.9%. In the comparison with three triple extraction methods, namely OpenNRE, the Language Technology Platform (LTP), and Bert4Keras,

With advancement of intelligent urban rail transit, automatic train operation needs to achieve an effective balance between energy efficiency and punctuality. However, existing dispatching regulations are mostly expressed in natural language, making them difficult to directly incorporate into control modeling. To address this problem, this paper proposes an automated train operation control method integrating large language models (LLMs) and proximal policy optimization (PPO). The proposed method employs an LLMs to perform semantic parsing of dispatching regulations and operational experience, and automatically constructs a Markov decision process (MDP) model under the constraints of a knowledge graph (KG). The generated MDP includes the state space, action set, reward function, and safety constraints. On this basis, an action masking mechanism and an adaptive reward-weight adjustment strategy are introduced, and PPO is used to train a safe and controllable automated train operation policy in a simulation environment. Simulation results show that, compared with conventional rule-based control, Model Predictive Control (MPC), and Deep Q-Network (DQN), the proposed method reduces the average traction energy consumption by approximately 2.5%, 1.5%, and 1.0%, respectively, and reduces the average delay time by approximately 13.7%, 19.6%, and 16.3%, respectively. In addition, the average jerk is reduced to 0.59 m/s³. These results verify the effectiveness of combining LLM-based semantic modeling with reinforcement learning for automated train operation control. Further hardware-in-the-loop tests indicate that KG-based consistency checking can reduce rule omissions and physical inconsistencies in semantic parsing. The action masking mechanism embeds hard constraints, including speed limits and safe headway distances, into policy execution, while the adaptive reward-weight mechanism adjusts the trade-off among energy consumption, punctuality, and ride comfort according to operational feedback. The proposed method therefore establishes a closed-loop framework of semantic modeling, policy optimization, and feedback adjustment, providing an interpretable approach for incorporating natural-language dispatching knowledge into automated train operation control.

To assess the equity performance of an urban rail-transit-oriented public transport system and identify potential issues, this study uses mobile phone signaling data from Shenzhen to build a job accessibility equity evaluation framework integrating spatial and group equity, and proposes a "spatial-disparity identification first, population-characteristic summarization second" approach. Absolute and relative job accessibility are jointly measured under different commuting scenarios; transport-disadvantaged units are identified using the "dual-disadvantage" criterion of low absolute and high relative accessibility; K-medoids clustering is used to characterize socioeconomic attributes; and a decomposable Theil index is applied to identify sources of inequity. Results show a distinctive pattern in Shenzhen's job accessibility: unequal spatial access to job opportunities alongside convergent commuting time. Rail transit shortens commuting time, but job opportunities remain concentrated in station core areas and locationally advantaged areas, while transport-disadvantaged units increase with distance from rail stations. Four disadvantaged groups are identified—multidimensionally disadvantaged groups, experience-based labor groups, traditional labor groups, and high-income, high-education commuting-mismatch groups—revealing diverse mechanisms of disadvantage. Inequity is driven mainly by within-group disparities, while between-group differences are largely driven by education and income. The study provides new insights for equity measurement and sustainable operation of urban rail transit-oriented public transport systems.

Expansive soils, due to the water sensitivity of clay minerals such as montmorillonite and their lattice swelling characteristics, are prone to significant swelling and shrinkage deformation, which seriously threatens the safety and stability of urban rail transit engineering structures such as tunnels and subgrades. In response to issues such as high energy consumption, high carbon emissions, and insufficient durability associated with traditional cementitious material stabilization techniques, this study proposes an active performance regulation method for weakly expansive soils. By developing a novel environmentally friendly stabilizer and a cement-lime composite regulating agent, the macro- and micro-mechanical properties of weakly expansive soils are dynamically regulated, achieving comprehensive improvements in their mechanical performance, durability, and environmental friendliness. Based on multi-scale testing methods, it is revealed that the stabilizer can actively regulate the soil microstructure and mechanical properties through the synergistic effects of multiple mechanisms, including ion exchange, gel network formation, physical filling, and skeleton reinforcement. The results indicate that the cement-lime-stabilizer composite system significantly enhances the mechanical properties and durability of expansive soil. The core mechanism lies in the targeted filling of pores by cementitious materials at the microscopic level and the construction of a three-dimensional network structure. The recommended optimal mix ratio for engineering improvement is cement : lime : stabilizer = 3% : 3% : 0.02%. This ratio ensures the effectiveness of improvement while substantially reducing the amounts of cement and lime used, effectively controlling engineering costs. From the perspective of chemical-physical synergistic regulation, this study provides theoretical support and a technical pathway for the green and efficient improvement of expansive soils.

Against the background of the rapid development of autonomous train operation and virtual coupling, the traditional independent design of vehicle and signaling systems and the distributed control system adopted on the vehicle side have led to problems such as lengthy on-board Automatic Train Operation (ATO) control links, large response delays, and low control accuracy. This paper proposes a multi-system fusion-based closed-loop control method for train braking deceleration. Firstly, an integrated hardware and software platform integrating vehicle control and signaling control functions is established to construct a multi-system fusion control architecture. secondly, based on this platform, the functional redistribution of the entire process of train automatic operation control is carried out, and the core links such as ATO control, traction/braking force collaborative distribution, and closed-loop feedback control are deeply integrated to reconstruct the control closed-loop; Finally, on-vehicle tests are conducted to verify the control performance of the proposed method. The test results show that, compared with the traditional distributed train control system, the control accuracy under ATO mode is increased by 35% with a 25% reduction in response delay; the accuracy of pure electric braking is improved by 70% with a 20% delay reduction; and the accuracy of electro-pneumatic blended braking is raised by 30% with a 14% delay reduction. The integrated architecture effectively improves train braking stability and stopping accuracy, providing critical technical support for the safe and efficient intelligent and autonomous operation of trains.

Under high-density operating conditions, single-point failures in metro vehicle braking systems may escalate from equipment-level faults to operation-level risks. Taking an imported braking system applied in the Beijing Metro as a case study, this paper proposes a system analysis and optimization method for engineering implementation. Driven by a typical operational delay event and based on system decomposition, function-structure mapping, and on-vehicle fault simulation, the propagation paths and amplification mechanisms of key risks, such as exhaust solenoid valve sticking in the brake control valve, strong coupling between the main air line and the parking brake, and braking system-TCMS signal interface mismatches, are systematically identified. A combined Failure Mode and Effects Analysis (FMEA) and Fault Tree Analysis (FTA) approach is then adopted to quantitatively evaluate these risks, with the results serving as direct constraints for system reconfiguration. Coordinated optimization measures are proposed at the software, pneumatic, and human-machine interaction levels, including an HMI-triggered braking system self-test and self-reset mechanism, feedforward diagnosis of low brake cylinder pressure, reconstruction of the parking brake air supply path using check valves, and an operation-disposal-oriented TCMS fault classification and early warning strategy. Multi-line on-vehicle validation demonstrates that, compared with the pre-optimization scheme, the proposed method increases the identification accuracy of three typical single-point faults by an average of 34.3 percentage points and reduces emergency handling time by an average of 3.1 min, significantly mitigating operational impacts such as passenger evacuation, speed-restricted operation, and delays. The established "fault simulation-risk quantification-system reconfiguration" framework provides an engineering reference for resilience-oriented design and proactive risk management of metro braking systems and other critical systems.

To address the problem of elevated stray current caused by insulation deterioration in running rail sections of urban rail transit, which seriously endangers the safety of the traction power supply system and surrounding underground metallic structures, this paper investigates the dynamic distribution patterns of stray current and corresponding protection methods under such insulation deterioration. First, a high-insulation protection scheme for urban rail line sections is designed, and a stray current mitigation strategy for high-insulation sections is proposed, which includes the installation of unidirectional conducting devices and the definition of high-insulation zones. Then, a multi-train dynamic operation simulation model of the urban rail power supply system is established under section insulation deterioration, taking into account the sectional protection control characteristics of the return system. A unified chain-type system model and a power flow solution are developed accordingly. Finally, based on the parameters of an actual domestic urban rail transit line, simulations are performed to analyze the dynamic distribution of stray current and rail potential along the entire line under section insulation deterioration, and the control effectiveness of sectional protection for both stray current and rail potential is evaluated. The results show that insulation deterioration in a section leads to rail potential clamping and an increase in stray current in that section. By adopting sectional protection, which isolates the return current from outside the section while maintaining high insulation within the section, the stray current amplitude in the section can be significantly suppressed, and the rail potential clamping problem induced by insulation deterioration is effectively resolved. The proposed methods can be applied to stray current protection for critical sections of urban rail lines.

To address the insufficient fusion of multi-granularity temporal features and inadequate modeling of spatial heterogeneity among stations in short-term metro inbound passenger flow forecasting, this paper proposes the Multi-Granularity and Attention-enhanced Passenger Flow Prediction model (MGAPF). In the temporal dimension, four one-dimensional convolutional branches with different receptive fields are constructed, and a granularity attention mechanism is used to adaptively fuse multi-scale temporal features. In the spatial dimension, a graph attention mechanism is introduced to dynamically learn the correlation strengths among adjacent stations. External temporal contextual features, including holidays, weekends, and weather conditions, are also incorporated. A gated fusion structure, residual connections, and a Transformer encoder are further combined to perform spatiotemporal feature interaction and generate prediction outputs. Experimental results based on real operational data from Hangzhou Metro show that MGAPF achieves MAPE values of 16.93% and 9.52% in the 10-minute and 30-minute forecasting tasks, respectively, representing error reductions of approximately 4.5% and 7.8% compared with the second-best baseline model. MGAPF also performs better in terms of MAE, RMSE, and prediction stability, indicating that the fusion of multi-granularity temporal features, spatial correlations among stations, and external factors can effectively improve the accuracy and stability of short-term metro inbound passenger flow prediction.

In response to the problems of obscured fault characteristics of metro bogie bearings under complex conditions, the susceptibility of original vibration signals to noise interference, and the poor generalization and high complexity of traditional diagnostic methods, an intelligent bearing fault diagnosis method integrating Eulerian Feature Extraction (EFE) and shallow convolutional neural networks is proposed. This method achieves dimensionless normalization and standardization of vibration signals through adaptive interval mapping, converts linear time series signals into a polar-coordinate phase representation using geometric phase encoding, and then constructs two feature expressions, FirstEuler and SecondEuler, through dual Eulerian feature fusion to achieve deep integration of time-domain and phase-domain features, effectively enhancing the discriminability of weak fault features. The features extracted by EFE can be directly used as input to a one-dimensional convolutional neural network or converted into grayscale images as input to a two-dimensional convolutional neural network, enabling the construction of shallow diagnostic models that balance diagnostic accuracy and efficiency. Using the Case Western Reserve University bearing dataset, fault diagnosis experiments were conducted under single-condition, multi-condition, and variable-speed operating conditions, and the proposed method was compared with traditional feature extraction algorithms such as VMD, EMD, and HT. Experimental results show that in a -6 dB strong noise environment, the EFE method improves one-dimensional diagnostic accuracy by more than 7.8% compared with the raw signals. In single-condition two-dimensional diagnosis, the accuracy is approximately 19.5% higher than that obtained using the raw data, and after secondary enhancement of features extracted by VMD, EMD, and other algorithms, the diagnostic accuracy reaches up to 100%. Under multi-condition and variable-speed operating conditions, secondary feature extraction by EFE increases the diagnostic accuracy by more than 15% on average; in particular, VMD combined with FirstEuler achieves 100% diagnostic accuracy for the full variable-speed condition combination. The proposed method effectively suppresses noise interference and highlight weak fault features, demonstrating excellent generalization ability and feature extraction performance under complex conditions such as constant load, variable load, and variable speed. In addition, the shallow CNN model reduces computational complexity, providing a new technical solution for efficient fault diagnosis of metro bogie bearings.

From the perspective of rail transit enterprise management, this study addresses the problem of coordinating and balancing rolling stock circulation efficiency, train load factor, and operational economics in cross-line operation, and constructs a multi-dimensional collaborative optimization model for cross-line train timetables with the objective of minimizing operational train-kilometers. The study focuses on the economic optimization of the spatiotemporal allocation of transport resources. By integrating core elements such as timetable scheduling, turnaround operations, depot operation plans, and cross-line connections, a linkage constraint mechanism between maximum headway and train load factor is established, enabling coordinated control of operating costs and service reliability. To improve solution efficiency, the FSAE-CLO (fast solution algorithm for engineering-cross line operation) algorithm is proposed, which transforms cross-line timetable optimization into a combinatorial search problem for cross-line decisions, gradually screens feasible schemes according to the sequence of trains available for cross-line operation, and adjusts cross-line decisions based on an iterative probability update mechanism, thereby compressing the solution space while reducing ineffective searches. Taking the morning peak hours of Beijing Metro Fangshan Line and Line 9 as an example, the empirical results show that, compared with the single-line operation mode, the proposed scheme reduces train-kilometers by 6.83%; compared with the genetic algorithm, it reduces operational mileage by 4% and shortens solution time by 24%. This study provides a new theoretical method and practical support from the perspective of cost reduction and efficiency improvement for transport enterprises in making decisions on adopting cross-line transportation organization methods, and its resource coupling optimization mechanism has reference value for improving the benefits of networked operation.

To achieve accurate identification and intelligent monitoring of metro rail corrugation, this study proposes a novel method combining WPD and 1DCNN for rail corrugation identification. Based on the vertical axle-box acceleration signals collected from in-service metro trains, sixteen sub-band energy features were extracted through four-level WPD and normalized to construct energy vectors. A lightweight 1DCNN architecture was designed to perform multiscale feature learning using the energy vectors as input. Three corrugation types—no corrugation, long-wavelength corrugation, and short-wavelength corrugation—were selected as classification labels for model training and testing. Based on the differences in energy distribution among different corrugation types in low- and high-frequency sub-bands, the feature extraction results were analyzed. The results demonstrated that the proposed method achieved an average recognition accuracy of 97.60%, with a recall rate of 100% for long-wavelength corrugation. Compared with SVM, LSTM, and 2DCNN models, the 1DCNN model exhibited higher accuracy and stronger generalization capability. It enables intelligent rail corrugation identification under in-service operating conditions without reliance on specialized inspection systems. The consistency between the wavelength-domain evaluation framework of conventional rail corrugation testing and the identification results of this study was analyzed, and a complementary engineering application workflow integrating online identification with on-site precision measurement was proposed. This study verified the effectiveness of the WPD-1DCNN fusion method in metro rail corrugation recognition and provided a new approach for online monitoring and intelligent maintenance of track conditions.