Virtual coupling technology with an independent train as the transportation unit can solve the problem that it is difficult to match the passenger flow and capacity, and fully exploit the advantages of virtual coupling technology. In urban rail transit, trains need frequent traction and braking, and the minimum tracking distance between trains constantly change with the train status. However, current research on tracking control technology for station approach scenarios primarily focuses on fixed tracking distances. Few in-depth studies have been conducted on adaptive tracking distance techniques, and passenger comfort has not been thoroughly considered. In this paper, a tracking distance calculation model incorporating the traction transmission system is established under various train operational conditions, and a nonlinear model predictive control (NMPC) tracking algorithm with variable-weight jerk constraints is designed. The optimization objective integrates the adaptive tracking distance and a variable penalty factor based on urban rail standard, aiming to achieve smooth distance reduction during station approach and precise docking at the platform, while enhancing passenger comfort. The results demonstrate that the proposed algorithm can smoothly reduce the tracking distance, achieve precise stopping for train units during station approach, ensure compliance with jerk limits, and provide a technical reference for the efficient cooperative control of virtual coupling trains in station scenarios.

This study investigates the decoupling relationship between meteorological comfort and urban rail transit ridership in China. Daily meteorological data and passenger volume data from 28 major cities were processed to construct a meteorological comfort index using the entropy weighting method, in which precipitation levels were converted into continuous values based on national standards. A decoupling model was then applied to examine the dynamic interaction between weather comfort and transit use. The analysis identifies three classes of decoupling states: Class A, where passenger travel remains stable despite unfavorable weather; Class B, where moderate sensitivity to meteorological variation is observed; and Class C, where travel is strongly influenced by weather conditions. Results show that most cities predominantly fall under Class B, but with notable fluctuations across seasons and regions. The findings highlight that meteorological comfort does not uniformly determine ridership, but instead reveals differentiated patterns of resilience and vulnerability across urban rail systems. This contributes to a deeper understanding of how external environmental factors interact with public transit demand and provides methodological guidance for improving the robustness of transport planning under climate variability.

During rush hours, the capacity of metro in megacities is insufficient to meet the travel demand, resulting in oversaturation and high risk on platform in stations, especially transfer stations. This paper addresses this problem through the joint optimization of some operational interventions, aiming to alleviate passenger overloads while maintaining travel efficiency. To make the model more realistic, the stochastic characteristics of passengers are considered, including the probability distribution of passenger arrival time, inbound and transfer walking times. To provide a high-quality solution for the complex constraint model, three cooperative agents—governing passenger inflow, transfer flows, and train skip-stopping mode—are architected within improved Double Deep Q learning Network (IDDQN) to form a multi-agent reinforcement learning solution. Empirical validation on Beijing Metro Line 13 and Changping Line demonstrates that the multi-agent framework proposed in this paper can eliminate 100% of passenger over-limit flow while reducing the average waiting time of passengers. It also has a significant improvement in reducing stochastic characteristic impact and accelerating convergence.

Analyzing route choice behavior and understanding the heterogeneous impacts on passenger decisions are key to improving transportation service quality in integrated suburban railway and metro networks. While existing studies focus on metro systems using Mixed Logit (MXL) models or clustering methods with Multinomial Logit models, these approaches struggle to capture the diverse factors in travel scenarios and the complex nonlinear relationships in decision-making. This study integrates Latent Dirichlet Allocation with Machine-Learning models like eXtreme Gradient Boosting (XGBoost), Support Vector Machine, and Random Forest to analyze passenger behavior within Shanghai’s composite rail network. It identifies key influencing factors such as socio-economic demographic characteristics, travel purposes, and the express-to-local departure ratio. XGBoost outperforms other models, including the traditional MXL, in predictive performance. The study highlights significant heterogeneity in route choices across different passenger groups, underscoring the need for personalized transportation solutions. Based on these findings, this study proposes the following actionable suggestions for suburban railway in the composite network: In terms of operational optimization, it is proposed to add express train overtaking stations in key commuting corridors and optimize the timetable to reduce transfer waiting times, thereby improving overall travel efficiency. Besides, time-of-day differentiated pricing and combined-ticket discounts are proposed to improve the rationality of the ticket-price structure. Finally, it is recommended to enhance the personalized route recommendation system.

Real-time prediction of dynamic origin–destination (OD) passenger flows is essential for efficient passenger flow management in urban rail transit (URT) systems. Existing studies have primarily focused on commuting OD flows, which exhibit strong regularity and are supported by abundant data samples. In contrast, non-commuting OD flows—especially those generated by irregular passengers with limited historical data—are characterized by high stochasticity and data sparsity and have received relatively little attention, with existing studies often reporting unsatisfactory predictive performance. To address these challenges, this study proposes a novel real-time OD flow prediction framework for irregular non-commuting passengers through multi-source data fusion and feature extraction. Specifically, individual-level spatiotemporal behavioral features are extracted from metro AFC data using a density-based clustering algorithm. Land-use and geo-economic data are then integrated to characterize individual travel preferences and construct a multidimensional behavioral indicator system. Building upon these features, hierarchical clustering and machine learning models are employed to perform personalized destination prediction. Empirical experiments conducted on Nanjing Metro data demonstrate that the proposed framework substantially improves prediction accuracy for non-commuting passengers and provides new insights into dynamic OD modeling. The results highlight the strong applicability and potential of the method for real-time passenger flow prediction in complex urban rail systems.

Smart card data (SCD) from Automatic Fare Collection (AFC) systems provide fine-grained insights into urban mobility rhythms. Yet most existing studies focus on static ridership, with limited attention to the relationship between station-level travel rhythms and the surrounding built environment. This study develops a spatiotemporal and data-driven framework to classify urban rail transit (URT) stations and examine their land-use determinants. Using two weeks of AFC data from 128 stations in Nanjing, China, a two-stage approach is implemented. First, a Gaussian Mixture Model (GMM) is applied to cluster stations based on weekday ridership profiles, yielding six distinct categories: residential oriented, employment oriented, hub comprehensive, spatial mismatched, predominantly residential mixed use, and predominantly employment mixed use. These categories reveal a clear transition from mixed and hub functions in the city center to residential-dominated stations in suburban areas. Second, a Random Parameter Logit (RPL) model is employed to assess the influence of socio-demographic, land-use, and amenity variables, capturing heterogeneity more effectively than the conventional Multinomial Logit (MNL) model. Results highlight the decisive roles of population density, housing prices, and employment land in shaping employment- and hub-oriented stations, while community-oriented facilities, such as healthcare and daily services, exert stronger effects on residential-oriented stations. These findings enrich theoretical understanding of station heterogeneity and provide empirical evidence for transit-oriented development (TOD), land-use coordination, and multimodal integration. The proposed framework is transferable to other rapidly urbanizing cities, offering practical guidance for building efficient and sustainable URT systems.