Incomplete information conditions are prevalent in subway data due to limited recorded information. This issue leads to ambiguous interpretations of passenger trip-chain inferences and presents a significant challenge to their validation, yet it is often overlooked in many inference models. This study proposes an interpretable analytical framework to quantify the significance of influencing factors in passenger trip-chain inference. First, twelve missing-data scenarios are designed to separately infer travel time and waiting time, with the XGBoost algorithm serving as the baseline model. Second, SHAP is employed to analyze feature contributions and interaction dependencies. The effects and sensitivities of different information categories on prediction performance are systematically quantified. Finally, experiments are conducted using real-world individual travel trajectory (ITT) and automatic fare collection (AFC) data from Beijing’s urban rail transit system. The results indicate that the duration of OD trips related to individual behavior and passengers’ perception of congestion have the greatest influence on trip-chain inference, with their combined contribution exceeding 80

Expressway networks represent evolving complex systems whose topological properties significantly impact regional development. This paper presents a decision support framework for addressing the expressway infrastructure sequencing problem using computational intelligence. We develop a novel framework that models expressways as L-space networks and evaluates how construction sequences create path-dependent evolutionary trajectories, introducing network science principles into infrastructure planning decisions. Our decision support framework quantifies project impacts on accessibility, connectivity, and reliability using nine topological metrics and a hybrid weighting mechanism that combines domain expertise with entropy-based uncertainty quantification. The system employs a hybrid TOPSIS algorithm that relies on geometric symmetry to simulate network evolution, capturing emergent properties in which each decision restructures possibilities for subsequent choices-a computational challenge that conventional planning approaches have not addressed. The system was validated with real-world Chongqing expressway planning data, demonstrating its ability to identify sequences that maximize synergistic network effects. Results reveal how topologically equivalent projects produce dramatically different system-wide outcomes depending on implementation order. Analysis shows that network science-informed sequencing substantially enhances system performance by exploiting structural synergies. This research advances decision support frameworks by bridging complex network theory with computational decision-making, creating a novel analytical tool that enables transportation authorities to implement evidence-based infrastructure sequencing strategies beyond the reach of conventional planning methods.

With the network-level operation for urban rail transit systems, achieving crew resource sharing is of significant importance for resource allocation optimization, operational costs reduction, and network transport efficiency enhancement. This study introduces the multi-line crew resource sharing into crew scheduling optimization without altering the existing crew rostering patterns prevalent in urban rail transit systems. Building upon single-line scheduling approaches, the personal preferences of crew members for cross-line duty and departure/arrival location preferences are considered. An integer programming optimization model for crew scheduling is proposed to achieve collaborative optimization of network-level crew schedules. The solution algorithm employs a column-generation framework, further utilizing a column fixation strategy to enhance the quality of the solutions. A rollback method is designed to improve the column fixation process by removing columns with poor quality. A case study involving three lines in a urban rail transit network is presented to demonstrate the effectiveness of the proposed model and algorithm. The implementation of crew resource sharing is shown to reduce the total number of required crew members, while accommodating personal preferences has a minimal negative impact on the potential for scale reduction.

The paper presents a virtual coupling control method to coordinate arrival maneuvers for both full-length and short-turning metro trains at turnaround stations. The objective is to enhance the coordination of virtually coupled trains by minimizing arrival time differences while ensuring operational safety. The complexity of this problem stems from nonlinear constraints caused by multi-track arrival sequencing conflicts and safety-critical switch protection requirements at junctions. To solve this problem, a model predictive control (MPC) approach is developed to optimize the trajectories of virtually coupled trains. And auxiliary logical variables are introduced to determine the sequence of train arrival and dynamically regulate hard constraints imposed by switch protection requirements. The proposed method is validated based on simulation experiments, demonstrating effective safety assurance and coordinated maneuvers. Under the short-turning priority arrival scenario, our strategy achieves $\text{9 1. 1} \%$ reduction in arrival time difference ($\text{4 0. 6}$ s to $\text{3. 6}$ s), and $\text{1 3. 5 \%}$ shorter station entry duration (59.2 s to 51.2 s). For the full-length priority arrival scenario, the arrival time difference decreases $82.7 \%(22 ~\mathrm{s}$ to 3.8 s) though station entry duration increases $20.9 \%(46 ~\mathrm{s}$ to 55.6 s).

The four-railway-network integration is the policy guidance of multi-type rail transit for intensive resource usage, transportation efficiency enhancement, and regional society and economy development. The synergia improvement concerning multi-type rail transit is an important rising of the service level of regional rail transit system and guidance for urbanization progress. Based on the summary of the current status and policy directions of the synergetic development, the concept and key indicators evaluating the degree of synergia are introduced. Four main synergetic patterns are distinguished referring to the typical cases, including independent operation, passenger service integration, cross-line operation, and regional coordination. Detailed patterns and evaluation indicators with respect to the passenger service integration and cross-line operation are further put forward respectively according to the improvement of passenger service and the difficulty of connection implementation. The proposed theoretical methods and indicators provide the firm support and active reference for the synergetic development of multi-type rail transit systems.

The high-speed railway provides a safe, punctual, and comfortable mode of transportation underpinned by stable infrastructure, fast trains, and dependable control systems. Implementing an appropriate maintenance schedule is essential for ensuring operational status and reducing the malfunction events of these systems. This study proposes a reliability-centered maintenance (RCM) strategy for high-speed railway facilities maintenance scheduling optimization. A reliability model is developed to characterize the multi-stage deterioration process of facilities, and a maintenance optimization model is put forward to minimize the maintenance cost by incorporating reasonable critical reliability with multi-level maintenance tasks. Two baseline models that typify current maintenance strategies are also formulated to illustrate the enhanced effectiveness of the RCM approach. The numerical example demonstrates that the RCM can significantly reduce maintenance schedule costs while simultaneously prolonging the lifespan of the facilities, all within the bounds of the same reliability constraints.

Severe weather events constitute a significant safety hazard for urban rail transit systems, emphasizing the importance of risk management. This paper introduces a resilience evaluation method for urban rail transit lines during adverse weather conditions, leveraging Bayesian networks. The proposed method encompasses a comprehensive resilience indicator system tailored to severe weather scenarios, encompassing topological characteristics, passenger organization, and equipment factors. A risk analysis framework utilizing a risk matrix is then applied to evaluate subsystem vulnerabilities under various weather conditions. Furthermore, a Bayesian network-based resilience evaluation approach is designed to integrate and analyze these diverse factors. To demonstrate the effectiveness of this approach, a case study is conducted using real-world data from the Changping Line of Beijing Subway, resulting in resilience scores for critical components like elevators, 400V, traction power supply, and on-board equipment, as well as an overall resilience value for the entire line. The results indicate that, on rainy days, the resilience levels of Changping Line's key indicators and the entire line are precisely predicted by the proposed method. Furthermore, the key indicators and the overall line are generally anticipated to exhibit high resilience, which closely aligns with actual operational performance. These findings not only establish the accuracy of the resilience evaluation method but also reinforce its practical relevance and applicability in real-world settings.

[Objective] Overhaul operations for urban rail transit vehicles pose challenges and bottlenecks in the organization of maintenance work. Currently, there is a lack of systematic exploration of the overhaul contents and process design tailored for maintenance. [Method] Analyzing and refining the process design for the advanced overhaul schedule of urban rail transit vehicles is essential to improving the rationality of maintenance work arrangement, and effectively address the increased maintenance work demands resulting from the expansion of line network mileage and passenger flow volume. Based on existing research achievements regarding maintenance facility layout and maintenance task sequence optimization, the current urban rail transit vehicle overhaul situation is analyzed. Features such as shift repairs between lines, concentrated component-specific repairs, and diverse maintenance strategies in the overhaul operations are summarized. Subsequently, the process characteristics of the overhaul are outlined from the perspectives of process flow, maintenance strategies, and allocation of maintenance resources. Furthermore, a flexible process for overhaul is proposed, including the introduction of parallel operations in the process flow, adjustment of maintenance strategies based on the operational capacity of the maintenance line, and the separation of maintenance equipment and personnel in the allocation of maintenance resources. A computational example analysis is carried out based on the actual overhaul process of a 6-car formation urban rail transit train. [Result & Conclusion] Under a fixed process flow, the overhaul time required for synchronous maintenance strategy is 25 days. By applying flexible process, the required maintenance time is reduced to only 17.5 days, resulting in a 7.5-day reduction in maintenance time compared to the fixed process. The reduction in maintenance time stems from the introduction of parallel operations and the avoidance of executing synchronous overhaul strategy for the entire vehicle when the maintenance facility capacity is insufficient. The computational example results indicate that applying flexible process can effectively shorten the overhaul time of trains, thereby enhancing the maintenance efficiency of urban rail transit vehicles.

The multi-mode integrated railway system, anchored by the high-speed railway, caters to the diverse travel requirements both within and between cities, offering safe, comfortable, punctual, and eco-friendly transportation services. With the expansion of the railway networks, enhancing the efficiency and safety of the comprehensive system has become a crucial issue in the advanced development of railway transportation. In light of the prevailing application of artificial intelligence technologies within railway systems, this study leverages large model technology characterized by robust learning capabilities, efficient associative abilities, and linkage analysis to propose an Artificial-intelligent (AI)-powered railway control and dispatching system. This system is elaborately designed with four core functions, including global optimum unattended dispatching, synergetic transportation in multiple modes, high-speed automatic control, and precise maintenance decision and execution. The deployment pathway and essential tasks of the system are further delineated, alongside the challenges and obstacles encountered. The AI-powered system promises a significant enhancement in the operational efficiency and safety of the composite railway system, ensuring a more effective alignment between transportation services and passenger demands.

Free-floating bike sharing (FFBS) attracts increasing research focusing on usage patterns, determining factors, and integrated transportation. However, existing researchers tend to overlook the variation in usage characteristics over various time ranges, particularly the usage pattern at night. This paper is conducted to fill the gap through a series of analysis approaches on FFSB in Beijing. The characteristics of the usage pattern, including time-varying usage and traveling distance distributions, are initially illustrated. Subsequently, the spatial patterns of FFBS are visualized and thoroughly analyzed in different time ranges and origin-destination (O-D) flows. A statistical model evaluating the environmental effects of FFBS trips revealed the source of FFBS usage. In addition to focusing on the nighttime, the usage patterns varying day and night are compared through the analysis. The findings explain the usage pattern variation and the unique pattern at night, providing valuable insight for improving the management of the FFBS system.

To grasp the trend of safety conditions in the operation process of multisystem rail transit, and allocate transport capacity and maintenance resources reasonably, the managers should master accurate and comprehensive safety evaluation of regional rail transit system. A data-driven model for safety evaluation of regional rail transit system was proposed in this study. The deep autoencoder networks were employed to reduce the dimensions of the evaluation index system. The hybrid hierarchical k-means clustering method was applied to obtain the set of all possible safety status. The tree-augmented naïve Bayes algorithm was used to evaluate the overall safety. The validity and practicality of the model were verified using actual operations data from a rail transit network in regional urban agglomeration in China. A comparison with the actual situation shows that the proposed approach can evaluate the safety level of the network effectively.

Identifying influential nodes, with pivotal roles in practical domains like epidemic management, social information dissemination optimization, and transportation network security enhancement, is a critical research focus in complex network analysis. Researchers have long strived for rapid and precise identification approaches for these influential nodes that are significantly shaping network structures and functions. The recently developed SPON (sum of proportion of neighbors) method integrates information from the three-hop neighborhood of each node, proving more efficient and accurate in identifying influential nodes than traditional methods. However, SPON overlooks the heterogeneity of neighbor information, derived from the asymmetry properties of natural networks, leading to its lower accuracy in identifying essential nodes. To sustain the efficiency of the SPON method pertaining to the local method, as opposed to global approaches, we propose an improved local approach, called the SSPN (sum of the structural proportion of neighbors), adapted from the SPON method. The SSPN method classifies neighbors based on the h-index values of nodes, emphasizing the diversity of asymmetric neighbor structure information by considering the local clustering coefficient and addressing the accuracy limitations of the SPON method. To test the performance of the SSPN, we conducted simulation experiments on six real networks using the Susceptible–Infected–Removed (SIR) model. Our method demonstrates superior monotonicity, ranking accuracy, and robustness compared to seven benchmarks. These findings are valuable for developing effective methods to discover and safeguard influential nodes within complex networked systems.

Accurately quantifying and comprehensively assessing the safety status of regional rail transit systems is critical to management decision making. These processes allow managers to understand the variations in safety status during multimodal rail transit operations and to effectively allocate transportation capacity and maintenance resources. In this study, a Big Data graphical visualization model was presented for assessing the safety of these systems that is tailored to the multi-level assessment elements of nodes, lines, and the network within regional rail systems. It uses a multidimensional scaling analysis algorithm and a hybrid hierarchical K-means clustering algorithm to visualize the distribution of safety status and provides an intuitive representation of the similarities or differences of each state feature. The assessment results minimize subjective bias and accurately reflect the actual conditions. The efficiency of the model is demonstrated using real-world operational data from typical urban agglomerations in China.

The rationally layout of connecting line is of significance for improving network efficiency and network planning. Under the background of advocating "network integration" and resource sharing, An urban rail transit connecting line planning model considering maintenance resource sharing is proposed, which minimizes the total construction cost of connecting lines and the total transfer time of trains require maintenance. A hybrid algorithm combining CPLEX and NSGA-II is applied to solving the model. The results of case study show that compared with the existing method, the proposed model achieves better effect in maintenance resource sharing based on realizing connection of all lines. Besides, key parameters of the model are discussed. The obtained results provide a consult for the layout determination of connecting lines and urban rail transit heavy repair sharing depots.

Crew scheduling, which usually has its own special requirements, is an essential part of the work undertaken by urban rail transit operators. For example, meal breaks are required during two pre-defined mealtime windows. Shifts are commonly divided into three types that have different restrictions. The ratio of the different types of shifts is determined by a predefined work pattern. Thus, it is crucial to address and solve the crew scheduling problem in urban rail transit systems efficiently after satisfying the above requirements and restrictions. A set of multilayer networks is developed herein to meet the feasibility constraints of shifts. Moreover, the crew scheduling problem is formulated into an extended set covering problem with additional constraints on the ratio of the different types of shifts and solved using the column generation method. The pricing problem of the column generation method is finally modeled as dozens of shortest-path problems based on the proposed network representation. The feasibility of this approach is demonstrated in case studies using real data from three metro lines in Beijing. The experimental results show that the proposed method is well-suited for real-life applications in urban rail transit systems.

架大修作业调度方案是影响架大修作业效率的关键,其制定的重要依据是车辆检修工艺.首先,分析以人工调度为主的车辆架大修工艺的局限,根据车辆架大修作业的项目分解结构、工艺次序关系和执行对象,建立基于灵活检修工艺的车辆架大修作业调度优化模型,实现列车库内检修作业时间最小化;其次,针对模型中存在复杂次序关系约束的特点,设计改进的遗传算法进行求解;最后,通过对多种场景下车辆架大修作业调度优化方案开展案例研究,验证模型与算法的正确性和有效性.案例研究结果表明:采用灵活检修工艺可有效缩短车辆库内检修时间,显著提高架大修的作业效率,较3种对比检修工艺,架大修平均作业时间分别下降22.3％,15.2％,11.1％;双列同步作业时,采用不同修程混合维修模式,可有效降低维修作业瓶颈的影响.

A suitable maintenance schedule is crucial for large-scale, complex multi-component systems undertaking a long-term operation to reduce failure risks and improve availability and profitability. Opportunistic maintenance is a popular solution when cost consideration is paramount. However, the extensively adopted single-level preventive maintenance action and single-stage degradation process limit the development and application of opportunistic maintenance. Multi-level preventive maintenance including both perfect and imperfect maintenance actions on multi-stage degradation is considered within an opportunistic model to address this challenge. A reliability evaluation model is first formulated to describe a multi-stage degradation process involving the effect of imperfect maintenance. An opportunistic model is then proposed to arrange reliability proportion thresholds for components in systems. The cost rate is considered as the objective function to accommodate the opportunistic model to variable scheduling horizons. A flexible dynamic strategy is developed within the opportunistic model to coordinate the schedules on the system and components by updating component schedules once a system maintenance action is executed. An improved hybrid genetic algorithm combining differential evolution is adopted to optimize the complex problem. The case studies on a locomotive system provide a better understanding of the proposed models and demonstration of its effectiveness, generality, and robustness.

Free-floating bike sharing usage for metro access provides a decent solution to the first- and last-mile problem. A fundamental and still open problem is the spatial and temporal regularities of bike sharing usage integrated with metro stations, which are crucial to achieve a seamless connection and provide an efficient transport system. In this paper, we conduct the usage of bike-and-ride in Beijing as an example to address this issue from macro-level and micro-level perspectives. First, the macroscopic usages, including distinct characteristics of time-varying trips and scaling relationships of spatial distribution, are explored in urban and suburban areas. Then, by adequately deconstructing temporal-spatial trips of bike-and-ride, the bike sharing usage is revealed to follow a power-law distribution with different exponents on weekdays and weekends. Our results suggest that scale-free behaviors for microcosmic travel demand exist across the city. These vital phenomena switch within the same region on different time ranges such as morning and evening peaks but similar scaling relations on different days. The findings improve our understanding of usage patterns and demand distribution of this emerging transport mode and supply an indication of the dynamic deployment of the free-floating bike sharing integrating with the mass transit system.

现行的地铁车辆维修制度以固定周期维修为主,存在停机时间长、考虑不同子系统的维修需求不足等问题.基于延迟时间理论,以低级维修周期和高级维修可靠度阈值为决策变量、优化更新周期内平均费用为目标,建立车辆系统内单一子系统多级维修计划优化模型,并给出基于实际数据的退化参数估计方法;以整个车辆系统为研究对象,考虑各个子系统间的经济关联性,提出基于子系统退化函数的维修活动调整惩罚函数,建立最大化全局收益的成组维修优化模型,并改进基于滚动时域和动态规划的求解算法.案例研究表明,本文模型可有效减少维修停时、节省维修成本,对运营企业制定维修计划具有一定的指导意义.

针对城市轨道交通基础设施系统组成复杂、维修任务繁多、维修资源有限的特点,在分析不同类型维修任务需求的基础上,研究资源约束下基础设施维修任务的长期安排方法。考虑作业工队、维修设备等限制条件,建立基于混合整数规划的优化模型以安排任务的开始时间和持续时间,实现任务执行费用和惩罚费用的最小化。通过引入作业时间占用约束以减少任务作业冲突并提高维修任务安排的可实施性。针对约束复杂的大规模问题,设计综合求解器和启发式方法的并行混合算法进行求解。案例研究表明:考虑维修任务作业时间对提高维修任务安排的可实施性具有重要作用,所构建模型可有效协同安排不同类型的维修任务并节省维修费用,为城市轨道交通基础设施的长期维修任务安排提供决策支持。