Deep reinforcement learning-based energy management strategy integrating physics information and expert system: efficient regenerative braking energy recovery in urban rail transit traction power system

Flexible crew scheduling optimization with a zonal duty strategy for fully automatic urban rail transit systems

Human-like hierarchical decision-making for real-time train regulation strategies in urban rail transit lines

Vibration-damping tracks of an urban rail transit vibrate under train loads and are a source of acoustic sound radiation in urban rail transit. In addition, they exhibit their own vibration amplification phenomenon during service. To evaluate the acoustic properties of damping tracks, this study considered acoustic wave superposition (AWSM) and examined a steel-spring floating-slab track (SSFST). This study focused on floating-slab (FS) acoustic radiation prediction and proposed a fast prediction method for the acoustic radiation of a track structure with a more regular shape. The influence of the structural parameters of FS on its acoustic characteristics was analysed and suggestions regarding the application of acoustic vibration characteristics were provided. The steady-state frequency-domain acoustic radiation prediction method exhibited high solution efficiency compared with the acoustic boundary element method, and was combined with the vehicle-track coupled dynamics theory and AWSM. The proposed method can be used to predict the acoustic radiation characteristics of regular structures and quickly evaluate the acoustic radiation effects. In addition, the FS has a strong low-frequency acoustical sound radiation ability, rendering it an important low-frequency acoustical sound radiation source for urban rail transit. The length and thickness of the FS significantly affected its acoustic vibration characteristics; therefore, a longer FS can be considered for sections with higher requirements for low-frequency noise. In the standard range, selecting a thicker FS offers advantages in terms of the acoustic sound radiation and vibration characteristics.

ABSTRACT Rail transit station areas function as high-traffic nodes that merge mobility with commerce, services, and public life. However, existing research disproportionately emphasises traditional public spaces such as streets and parks, overlooking station areas as critical loci of activity. Using the GTWR model and hourly Baidu Heatmap data, this study investigates how urban characteristics shape vitality in Tianjin's rail station areas, capturing fine-scale spatiotemporal variations in human activity. Findings show that centrally located, commercially concentrated stations exhibit heightened vitality, typically following a bimodal daily rhythm. Variables such as public service density, floor area ratio, and bus route integration exert significant yet location-sensitive impacts. By combining spatiotemporal modelling with real-time population proxies, this research contributes an adaptable methodology and practical guidance for revitalising transit-adjacent urban areas. The findings provide practical insights to improve the vitality and efficiency of station-adjacent urban environments.

As urban rail transit networks become increasingly dense, new tunnels frequently undercross existing operational lines. The cyclic loads from existing double-track trains pose a threat to the structural safety of the underlying sections. This paper proposes a computationally efficient analytical model for the 'double-track train-soil layer-underpass tunnel section' system. In this model, the double-track train is represented as a moving two-degree-of-freedom (2-DOF) sprung mass system, the soil is modeled as a spring-damper system, and the underpass tunnel roof structure is treated as an Euler-Bernoulli simply supported beam. The system response is solved using the modal superposition method. Key parameters are calibrated via displacement back analysis, and the model's predictive capability is validated against FLAC3D simulations and independent field measurement data. A systematic parametric study investigates the influence of train speed, tunnel beam length, overburden thickness, equivalent stiffness, and soil mechanical parameters. The analysis reveals the underlying mechanisms of system resonance and critical design parameters. For the specific case study, resonance peaks were observed at speeds around 48km/h and 72km/h, a dual-peak resonance phenomenon emerged at beam lengths of approximately 25m and 45m, and a vibration amplification effect was identified at a soil cover thickness near 5m. These findings highlight the resonance mechanisms that should be avoided in design, while the specific critical parameter values are case-dependent and should be re-calibrated for other projects. Increasing the equivalent beam stiffness can effectively suppress the vibration response, while grouting reinforcement modulated the system's dynamic response. This study provides a theoretical framework and an efficient preliminary assessment tool for understanding vibration mechanisms and aiding early-stage design in similar projects.

This study examines the optimization of electrochemical characteristics of Li-ion batteries to enhance regenerative energy recovery in multimodal transportation systems. Growing energy demands and environmental concerns highlight the importance of efficient energy storage and recovery solutions for sustainable mobility. The research develops a modeling and optimization framework that considers key battery parameters, including internal resistance, state of charge (SOC), operating temperature, voltage behavior, and charge-discharge rates. The model also accounts for energy losses, thermal dynamics, and degradation processes, enabling a realistic representation of battery performance under varying operating conditions. The proposed approach is applicable across different transport modes such as rail, road, and urban transit systems. Simulation results indicate that the optimized parameter configuration improves energy recovery efficiency, reduces heat-related losses, and extends battery service life compared to traditional control methods. In particular, temperature regulation and resistance reduction emerge as critical factors for system performance. Moreover, the inclusion of adaptive control strategies allows stable operation under fluctuating loads. The findings suggest that effective electrochemical optimization can contribute to both technical efficiency and environmental sustainability in modern transport systems.

Existing timetable optimisation models for urban rail transit predominantly adopt operator-oriented objectives with assumed passenger-related weights. This paper proposes a passenger satisfaction-oriented timetable optimisation framework in which satisfaction weights are empirically derived from confirmatory factor analysis and Cramér’s V analysis of survey data collected from 439 passengers on Nanning Rail Transit Line 1. Seven scheduling-related service attributes are formally expressed as functions of timetable decision variables, establishing a direct linkage between passenger perception and scheduling decisions. A multi-objective model minimises a weighted combination of passenger dissatisfaction, operational cost, and stranded passenger ratio, solved by a Passenger Satisfaction-oriented Adaptive Dispatch Heuristic (PS-ADH) integrating simulated annealing with a passenger flow simulation module. Case study results demonstrate simultaneous improvements of 3.78% in composite objective value, 3.25% in passenger dissatisfaction, and 3.25% in operational cost, with a 27.4% reduction in stranded passengers. The optimised strategy is selected consistently across all ten random initialisations (CV = 0.13%). Sensitivity analysis reveals a structural break at cost weight β=0.4, beyond which the optimal strategy shifts qualitatively toward cost minimisation at the expense of service quality. The framework provides a transferable methodology for integrating passenger perception data into rail transit scheduling for emerging urban rail systems.

To meet the extreme measurement accuracy requirements of the Polymorphic Coupled Rail Transit Dynamic Model Test Platform under complex design conditions-namely ultra-high speeds of up to 1,500km/h and ambient pressures ranging from 0.005 to 1.0 standard atmospheres-this study addresses the lack of a systematic accuracy control theory for installation measurements of ultra-high-speed maglev vacuum-tube supports. As the fundamental positioning elements of the vacuum maglev tube system, support installations directly govern track smoothness and tube airtightness. However, a comprehensive accuracy control framework for this domain has yet to be established, substantially constraining reliable engineering implementation. Here, a "reverse" accuracy allocation strategy is proposed, taking support design parameters as the starting point and integrating the law of error propagation, Least Squares Collocation theory, and computer-based virtual observation simulations. This approach establishes a complete accuracy transfer chain, linking support design accuracy to measurement-control point accuracy, station-setting accuracy, and ultimately to the precision of the offline control network. On this basis, a three-dimensional free-station adjustment model for total station that incorporates the prior accuracy of known points is developed, effectively mitigating the influence of control-point errors on station-setting precision. Through dense grid-based simulation experiments, the spatial distribution characteristics of station-setting accuracy are systematically revealed, providing a theoretical foundation for optimal station placement in field operations. Case studies validate the feasibility and applicability of the proposed methodology, demonstrating that it delivers a rigorously derived accuracy control framework for measurement scheme design under varying tube parameters, instrument precisions, and control network configurations. The accuracy derivation system established in this work offers a complete technical pathway-from theoretical formulation to engineering application-for support installation measurements in China's ultra-high-speed vacuum maglev transportation systems. It also provides an important reference for promoting the standardized and theory-driven application of precision measurement technologies in major engineering projects.

ABSTRACT With the rapid development of rail transit in China, elevated bridge lines have been widely adopted due to their high space utilization efficiency. However, the associated environmental noise issues have become increasingly prominent. Particularly in steel box girder bridges, the noise from the track system and the structure-borne noise from the bridge exhibit high similarity in both spectral characteristics and sound pressure levels, with comprehensive sound levels reaching 80–90 dB or above. This makes traditional single-method noise control strategies less effective. This paper focuses on the ‘Vehicle-steel bridge-noise barrier’ coupled system. Using an integrated approach of field tests, theoretical modelling, and numerical simulation, it systematically investigates the system’s noise radiation mechanisms, energy transfer paths, and spatial distribution characteristics. A vehicle-track-bridge coupled dynamics model and a statistical energy analysis (SEA) noise prediction model were established and validated. The results indicate that bridge structure-borne noise plays a dominant role in the overall noise emission, and the noise barrier provides significant insertion loss of 16–20 dB, particularly in the mid-to-high frequency range. The findings of this study can serve as a theoretical basis for noise prediction and the optimized design of noise barriers in rail transit steel bridge applications.

Challenges of spatial integration and sustainability in urban mass transit systems: evidence from Addis Ababa light rail transit (LRT)

How can we capture the value of rail transit to improve spatial equity across income groups?

Urban rail transit systems encounter challenges in short-term passenger flow prediction due to complex spatiotemporal data and dynamic travel patterns. Traditional models often struggle to capture these complexities. This study introduces a hybrid prediction framework that employs a two-stage feature selection strategy and multiscale decomposition to enhance forecasting accuracy. Key innovations include (1) a two-stage feature selection combining correlation analysis and recursive feature elimination, enabling the identification of the most influential temporal, spatial, and external features; (2) complete ensemble empirical mode decomposition with adaptive noise for isolating multiscale patterns; (3) parallel modeling with modern temporal convolutional networks and extended long short-term memory; and (4) a cross-attention mechanism for spatiotemporal feature fusion. Tested on 22 stations of Fuzhou Rail Transit Line 2 (8 million automatic fare collection records), the proposed model significantly outperforms classical and deep learning baselines. An ablation analysis further validates the contribution of each module to the overall performance. By bridging advanced AI methodologies with practical transit management needs, this work advances scalable, data-driven decision-making for sustainable urban mobility systems.

A scoping review of spatial coupling mechanisms between urban rail transit stations and land use: Bibliometric mapping with AI insights

Fusing emergency data and seasonal effects for urban rail transit safety assessment: A severity probability distribution model

Integrating non-motorized transportation with light rail transit: travel demand models for Rayong, Thailand

SubTOPO: integrating multi-routing strategy with express/local patterns for efficient operation of suburban rail transit

A mathematical analysis combined with machine-learning optimal control method for bidirectional converter devices of urban rail transit system

Speed sensorless control is essential for linear induction machines (LIMs) in urban rail transit. However, it is difficult to obtain the accurate speed when the mutual inductance of LIM is changed nonlinearly due to the end effect, especially in high-speed flux-weakening (FW) region. To enhance the robustness of the sensorless control system against such parameter changes, an improved speed sensorless control based on full-order terminal sliding mode (FOTSM) observer with adaptive gain is proposed in this paper. Firstly, to implement the minimum use of parameters affected by end effect, an active flux observer with improved FOTSM is constructed in the back electromotive force (EMF)-primary current model. Then, an adaptive gain is designed to guarantee the stability and effectively attenuate the chattering. After acquiring the accurate estimated active flux, a novel speed observer based FOTSM is established, where the mutual inductance and estimated active flux are decoupled. Finally, comprehensive simulation and experimental results have demonstrated the effectiveness and feasibility of the proposed method.

Assessing the impact of urban rail transit on urban ecological resilience in China