ISSN 1673-0291 CN 11-5258/U
The configuration of hot standby EMUs in high-speed railway networks directly affects emergency response efficiency and operational costs. To address issues such as coarse management and inadequate risk coverage in existing configuration approaches, this study proposes an optimization method based on comprehensive accident risk coverage across the network. First, considering both the timeliness and cost-effectiveness of emergency response, a multi-objective planning model is constructed with dual objectives to minimize emergency response time and configuration costs for hot standby EMUs. The model integrates point coverage and arc segment coverage methods to accurately represent the requirements for sequential tasks and inter-section rescue scenarios. It incorporates constraints related to emergency rescue point demands, response time limits, and full coverage of risk points, enabling effective adaptation to complex railway networks and the uncertainty of sudden incidents. Second, the ε-constraint method is used to solve the model, overcoming limitations associated with traditional weighted coefficient methods such as dimension normalization and parameter setting. This approach generates multiple sets of Pareto-optimal solutions, providing flexible options for decision-making. Finally, a case study is conducted on the high-speed railway network managed by a specific railway bureau. The research results indicate that the model produces reasonable configuration schemes aligned with various optimization objectives. As the number of hot standby EMUs increases, the maximum reduction in emergency response time reaches 29.3%, while configuration costs remain effectively controlled. Sensitivity analysis confirm the model’s strong adaptability to varying response time constraints and risk point distribution characteristics. This method provides a theoretical basis and practical guidance for the scientific configuration of hot standby EMUs and serves as a reference for enhancing the emergency management system of high-speed railways.
To address issues arising from operational interference between mainline and cross-line trains, specifically the “long-distance but short-flow” problem for cross-line trains and the “passenger flow without sufficient train supply” issue for mainline trains, this study investigates the coordinated optimization of stop patterns and passenger flow allocation for both train types. The goal is to improve the matching between train capacity and passenger demand under existing operational conditions. First, the physical high-speed rail network is simplified to focus on a corridor where mainline and cross-line trains operate concurrently. The impact of different train operation schemes on passenger flow allocation along this corridor is analyzed. Subsequently, a service network is constructed based on train operation segments, and a mixed-integer programming model is developed to jointly optimize the operation schemes of mainline and cross-line trains, minimizing both railway operational costs and passengers’ travel time loss. To enhance computational efficiency for large-scale problems, a heuristic algorithm based on Lagrangian relaxation is designed, which decomposes the original problem into simpler subproblems by relaxing coupling constraints. Finally, the Wuhan-Guangzhou section of the Beijing-Guangzhou high-speed railway is used as a case study. High-quality feasible solutions are obtained within a short computation time, validating the proposed model’s and algorithm’s effectiveness. The research results indicate that compared to the sequential optimization approach, the coordinated optimization scheme reduces the number of train services by one. Analysis of the proportion and seat occupancy rate of cross-line passengers further confirms the improved passenger flow allocation under coordinated optimization. The division of roles between mainline and cross-line trains becomes more distinct, enhancing the match between train capacity and passenger flow under current operating conditions. These findings provide valuable insights for railway operators.
To address challenges such as passenger crowding, excessive waiting times, and inefficient use of transportation resources in metro-to-high-speed rail transfer scenarios, this study proposes an optimization method for metro-to-high-speed rail passenger flow dispersion based on Multi-Agent Reinforcement Learning (MARL). The method dynamically adjusts metro timetables to enhance passenger dispersion efficiency, alleviate crowding, and improve the utilization of transportation resources. First, the metro-to-high-speed rail passenger flow dispersion optimization problem is formulated as a Markov game by integrating the spatiotemporal information of metro operations and the spatiotemporal characteristics of passenger transfers, with general state features, action space, and a reward function specifically designed. Second, a multi-agent decision-making model is then developed using the Actor-Critic (AC) framework, and an asynchronous action coordination mechanism is introduced within a centralized training and distributed execution architecture to enhance training efficiency. Finally, an optimization study is conducted using the Tianjin West railway station as a case study. Results indicate that the proposed method significantly reduces passenger waiting times and improves metro operational efficiency. The average passenger waiting time decreases by 26.80%, while the average metro operational efficiency increases by 14.11%.
To address the issue of train delays caused by uncontrollable factors during operation, this study investigates the impact of various adjustment strategies under a variable train formation operation mode on both passengers and subsequent train services. First, a train delay adjustment model is developed based on the variable formation operation framework, incorporating constraints such as train formation, arrival and departure times, rolling stock circulation, headway intervals, and passenger flow calculations. Then, the model optimizes four key decision variables, train formation status, dwell time, section running time, and headway, to achieve two main objectives: minimizing the number of stranded passengers and minimizing the deviation between the actual and scheduled timetables. Finally, using Shanghai Metro Line 16 as a case study, three distinct delay scenarios are simulated and solved using the CPLEX solver. The research results indicate that in different scenarios, for shorter delays, there is no need to implement coupling or decoupling strategies. However, for longer delays, these strategies are necessary to mitigate operational impacts. Within the same scenario, allowing coupling and decoupling operations significantly reduces both the impact on subsequent trains and the total number of stranded passengers compared to scenarios where such adjustments are not permitted.
To enhance the efficiency of bus-metro connectivity, this study conducts a coordinated optimization of the spatial-temporal distribution of passenger flows and transfer efficiency for feeder bus routes serving metro station clusters. A multi-objective optimization model is proposed, aiming to minimize the total system cost while maximizing network transfer demand. A penalty mechanism for both transfer time and number of transfers is incorporated to constrain cases involving two or more transfers, encouraging the system to reduce unnecessary transfers during route design. To solve the model, a hybrid genetic particle swarm optimization algorithm is developed, integrating an adaptive elite retention strategy and a dynamic inertia weight adjustment mechanism. Results indicate that, compared with the original bus network, the optimized system increases bus carrying capacity by approximately 23%, reduces average passenger travel cost by about 9%, and improves algorithm efficiency with a 15.4% faster runtime compared to conventional genetic algorithms. The proposed model demonstrates superior performance across multiple key indicators, including transfer appeal and travel cost, thereby validating its effectiveness in improving the operational efficiency and service quality of feeder bus networks. This work offers valuable insights for the refined management and intelligent upgrading of urban public transportation systems.
To address the challenge of accurately calculating the braking force of eddy current brakes (ECBs) in rail transit, this study proposes a three-dimensional electromagnetic model and analyzes the effects of various parameters on braking performance. First, the expression for static air-gap magnetic flux density is derived using the equivalent magnetic circuit method and Maxwell’s equations. The influence of the transverse edge effect on braking force is examined, and a correction coefficient for the conductivity of the conductor plate is derived. An equivalent eddy current density model is then established, leading to analytical expressions for both air-gap flux density and eddy current density. Subsequently, the impact of the longitudinal end effect on braking force is analyzed, and an expression for the additional air-gap flux density is derived. Based on the relationship between eddy current density and air-gap flux density, an analytical ex-pression for braking force is obtained. Finally, a three-dimensional finite element model is constructed using the design parameters of the Shanghai TR-08 high-speed maglev train’s ECB to verify the accuracy of the proposed model. The three-dimensional electromagnetic model is also used to analyze the influence of different parameters on braking performance. The results indicate that the maximum error between the three-dimensional electromagnetic model and the three-dimensional finite element model is 5.18%, with an average error of 2.35%, validating the accuracy of the three-dimensional electromagnetic model. The braking force increases initially and then decreases with rising speed, exhibiting four distinct characteristics in its variation curve: linearity, criticality, attenuation, and stabilization. The additional braking force increases with speed. Properly widening the conductor plate can effectively mitigates the influence of the transverse edge effect. The braking force increases with higher ampere-turns of the excitation winding and a wider primary core, while it first increases and then decreases with increasing conductivity and permeability of the conductor plate and with greater primary pole distance. The braking force decreases as the air-gap thickness increases, and the speed corresponding to peak braking force also increases. A thinner conductor plate slows the growth of braking force. Both increasing the air-gap thickness and reducing the conductor plate thickness contribute to a more stable braking performance.
To explore the nonlinear effects of the built environment on urban rail transit station ridership, this study takes Beijing’s rail transit stations as its focus. Leveraging multi-source data, including Point of Interest (POI) data, mobile phone signaling data, and road network data, the built environment is finely characterized from four perspectives: socio-economic and demographic attributes, land use, multimodal connectivity, and station characteristics. A Gradient Boosting Decision Tree (GBDT) model is employed to reveal the relative importance, nonlinear influences, and threshold effects of these factors on station ridership across different time periods and travel directions. Results indicate that the GBDT model outperforms the Ordinary Least Squares (OLS) model, Adaptive Boosting (AdaBoost), and Random Forest (RF) models in terms of fitting performance. Socio-economic and demographic attributes exert the greatest influence on peak-period ridership, contributing over 40% to both morning inbound and evening outbound peak-period ridership. Land use attributes have the strongest impact during off-peak periods, accounting for 33.06% and 49.10% of inbound and outbound ridership, respectively. The most influential variables exhibit pronounced nonlinear and threshold effects on station ridership. Notably, stations located 15 to 22 km from the city center show significantly higher morning inbound and evening outbound ridership. Additionally, the proportion of passengers accessing rail transit via private cars is considerably higher during peak hours than during off-peak periods. These findings provide valuable theoretical support for the planning of urban rail transit networks and the spatial layout of urban land use.
The proportion and scale of connected commercial vehicles significantly influence traffic flow speed, which in turn affects overall vehicular emissions across the road network. To address the lack of quantitative evaluation methods for the impact of connected commercial vehicle platooning on overall network emission reductions, this study develops a large-scale traffic simulation model based on SUMO to quantify emission reductions under future platooning scenarios. First, a large-scale highway simulation environment is established in SUMO by calibrating against real-world highway data. Next, within a joint SUMO-Python simulation framework, car-following and fuel consumption models for various vehicle types are configured, and emissions are calculated using the MOVES software. Using formation size and penetration rate as variables, platoons consisting of 2 to 8 commercial vehicles are simulated under free-flow conditions to analyze fuel consumption and emissions at different penetration levels. Finally, the study proposes optimal platoon sizes for the target road network at varying penetration rates. The research results indicate that average instantaneous fuel consumption of the platoon decreases as platoon size increases, reaching minimum values at platoon sizes of 4 and 8 vehicles, but rises with increasing penetration rates. Compared to a baseline scenario, higher platoon penetration rates and larger platoon sizes yield maximum reductions of 22.25% in fuel consumption, 21.09% in CO₂, 16.91% in HC, 19.36% in NOₓ, 15.23% in PM2.5, 17.39% in PM10, and 26.06% in CO emissions. Both emissions and fuel consumption decline as penetration rates rise; under fixed penetration, they further decrease with larger platoon sizes. Overall, increasing both penetration rate and platoon size leads to significant reductions in total fuel consumption and pollutant emissions from road traffic flow.
To address the complex and dynamic spatiotemporal features in traffic flow prediction, this paper proposes an Attention-based Spatiotemporal UNet with Graph Convolutional Network (AST-UNet-GCN) model for long-term traffic flow forecasting. First, for temporal modeling, a U-Net-based feature pyramid architecture is introduced to capture multi-scale temporal features. The encoder-decoder structure enables effective extraction of features across different time scales. To enhance adaptability to sudden events, a short-term temporal feature extraction module based on attention mechanisms is designed. Furthermore, a global temporal feature extraction module utilizing deformable attention mechanisms is constructed to capture long-term temporal dependencies. Then, a Squeeze-and-Excitation (SE) feature fusion module is developed to improve the expressiveness of the convolutional neural network, enabling dynamic weighting of features at different time scales and enhancing the fusion of multi-scale temporal information. This approach effectively highlights key features while suppressing redundant information. Finally, for spatial modeling, a Graph Convolutional Network (GCN) is employed. By constructing the topological graph structure of the traffic network, the model captures spatial dependencies. A sigmoid-based feature fusion mechanism is further designed to explore the intricate dynamic relationships between spatial and temporal features, enabling comprehensive spatiotemporal modeling. Experimental results demonstrate that compared to other mainstream models, the AST-UNet-GCN model achieved reductions of 8.5% and 9.4% in MAE and RMSE metrics for short-term prediction, while reductions of 10.4% and 6.5% were observed for long-term prediction, respectively. These results demonstrate the model’s strong performance in traffic flow forecasting, particularly in immediate prediction accuracy and the stability of long-term trend forecasting.
To address shortcomings of insufficient existing slow traffic systems and the lack of targeted optimization strategies, this study explores the impact of various indicators on slow traffic systems. First, based on an in-depth analysis of residents’ slow travel behavior, this study designs a questionnaire and selects the Honggutan New District of Nanchang as the case study area to perform the satisfaction survey on slow traffic system. Subsequently, hypotheses are developed and continuously refined using Structural Equation Modeling (SEM). An evaluation system comprising 20 third-level indicators is constructed across four dimensions: safety, convenience, comfort, and empathy. Standardized path coefficients are used to determine the weights of the indicators. The weights are then integrated into the Grey Clustering Model (GCM) for a comprehensive evaluation, leading to the development of a SEM-GCM-based model for assessing residents’ satisfaction with slow traffic travel. Empirical analysis is subsequently conducted to validate the model. Finally, an “Importance-Satisfaction” matrix is constructed based on the analysis of evaluation results. Optimization strategies are proposed for indicators identified as having “high importance but low satisfaction”.Results indicate that the overall satisfaction level of residents with slow traffic travel is Level 4 (Satisfied). The most influential third-level indicators are transfer convenience (0.058 8), bus stop coverage (0.058 4), and convenience of non-motorized vehicle parking (0.056 9), highlighting that convenience is the most critical factor, followed by safety, comfort, and empathy. The research findings can provide a valuable reference for enhancing satisfaction levels with slow traffic systems.
To fully utilize the transport capacity of high-speed railways, improve operational efficiency, and enhance economic benefits, this study addresses the vehicle-cargo matching optimization problem in high-speed rail express freight services. The research comprehensively considers three transport modes, passenger-freight mixed operation, reserved carriages, and dedicated EMU trains, and four categories of goods: fresh produce, urgent documents, electronic products, and valuables. A two-stage stochastic programming model is proposed. In the first stage, train operation plans are determined, including the selection of transport modes for each train and decisions on whether to dispatch dedicated EMU trains. In the second stage, based on the train plans from the first stage, optimal vehicle-cargo matching schemes are determined under various demand scenarios. To solve the model, a Mixed-Integer Programming-based Genetic Algorithm (MIP-GA) is designed. Finally, case studies are conducted using data from the Beijing-Shanghai high-speed railway, including four types of goods with stochastic demand, 5 500 containers, and 24 trains comprising a total of 254 carriages. The model is validated through analysis of the value of stochastic solutions and further tested across 12 case sizes to evaluate algorithm performance. The results show that the stochastic programming model effectively manages demand fluctuations, reducing costs by 3.8% and increasing the on-time delivery rate by 13% compared to the average-demand model. The MIP-GA significantly accelerates computation, saving an average of 75.88% in solving time, with an average optimality gap of only 0.20% compared to Gurobi, thereby enhancing computational efficiency without compromising solution quality.
To address the challenge of accurately predicting container transportation time, this study proposes a hybrid model, CNN-GRU-Attention (CGA), which integrates Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and an Attention Mechanism (Attention). Key factors influencing railway container transportation time, such as transport distance and whether the shipment crosses bureau boundaries, are selected as input features. A sliding window approach is employed to segment the data before feeding it into the model. The CNN-GRU framework is used as the main framework to extract data features and capture long-term dependencies, while the attention module enhances the model’s ability to focus on critical information. The model’s performance is evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R²), and Mean Absolute Percentage Error (MAPE). Representative machine learning and deep learning models are used as benchmarks for comparison. Results indicate that the CGA model achieves an MSE of 77.84, RMSE of 8.82, MAE of 2.72, R 2 of 0.958, and MAPE of 4.47%. Compared with other models, the CGA model has demonstrates superior prediction accuracy for railway container transportation time and delivers better overall forecasting performance.
Addressing the unclear key factors and mechanisms influencing regional freight structure optimization, this study proposes a systematic research approach. Firstly, leveraging the Latent Dirichlet Allocation (LDA) topic model, eight pivotal factors are systematically extracted and identified: socioeconomic development level, industrial structure, natural geographical conditions, energy structure, environmental awareness, techno-economic attributes, scientific and technological progress, and transportation industry policies. Secondly, based on research hypotheses, a Structural Equation Model (SEM) is formulated to analyze the effects and interrelationships of these factors on regional freight structure. Finally, elasticity analysis is introduced to quantify the contribution of each factor to freight structure adjustment. The results indicate that all eight factors significantly promote regional freight structure adjustment, with varying degrees of impact and elasticity across regions. The eastern region should focus on optimizing industrial structure, leveraging geographical advantages, enhancing environmental awareness, and promoting green freight technologies and policy guidance to build an efficient and green freight system. The central region needs to optimize geographical conditions, advance transportation infrastructure, improve freight network connectivity and efficiency, and strengthen investment guidance to enhance techno-economic characteristics and facilitate freight structure optimization. The western region should accelerate the integration of ecological protection and technological development, emphasize techno-economic improvements, promote freight technology innovation, and optimize costs to drive green and innovative freight structure development. At the overall level, efforts should strengthen the dynamic alignment of industrial structure and techno-economic characteristics, improve policy precision and coordination, and promote innovation and upgrading of transportation modes and systems.
This study addresses the integrated optimization problem of order allocation, processing sequence, and shelf access sequence in a multi-picking-station scenario of an Autonomous Mobile Robot (AMR)-based parts-to-picker picking system. The Order Allocation and Sequencing Problem (OASP) in a multi-picking-station scenario is proposed, which jointly optimizes how orders are assigned to picking stations, the processing sequence of orders at each station, and the shelf access sequence. A mixed-integer programming model is formulated with the objective of minimizing total order picking time. A Variable Neighborhood Search Algorithm (VNSA) is developed, which batches orders based on order similarity to generate a greedy initial solution. The algorithm incorporates four types of local search neighborhoods, including shelf replacement and order reallocation jitter operators, order exchange/insertion, and shelf sequence adjustments, combined with a dynamic switching mechanism to iteratively improve the solution. The performance of VNSA is compared with that of the CPLEX solver. Results demonstrate that VNSA outperforms CPLEX in solution speed and accuracy on small-scale instances, and shows significant improvements in initial solution quality on large-scale instances, verifying the effectiveness of joint optimization of order allocation and sequencing. Moreover, order picking time exhibits a negative correlation with the number and capacity of picking stations, and a positive correlation with the load balancing coefficient.
To address the challenges of complex backgrounds, deep placement and difficulty in recognizing and measuring cracks in plate rubber bearings of beam bridges, this study proposes an automatic crack detection and parameter calculation method based on dual-stage semantic segmentation using the YOLOv8-ESF framework. First, the EfficientViT backbone is integrated into the backbone network. Based on this, the Bottleneck structure within the C2f module is reconstructed to form the C2f-Faster-EMA module, which replaces part of the original C2f modules in the YOLOv8n backbone and incorporates decoupled heads, thereby enhancing the model’s ability to capture multi-scale detail features of bearing cracks. Second, the improved YOLOv8n model is employed to segment and extract the entire bearing region. Subsequently, the same model is used to further segment crack regions within the extracted bearing image. Crack parameters are then obtained by extracting the skeleton centerline and searching for the maximum outer rectangle method. Finally, the model is validated and evaluated from three aspects: network architecture, crack dataset, and segmentation accuracy. Experimental results show that YOLOv8-ESF model achieves over 85% accuracy in terms of mPA, DSC, and IoU for both bearing region and crack recognition. In field tests on real bridges, the maximum deviation between the crack parameters calculated via the dual-stage semantic segmentation method and manual measurements is less than 0.1 mm, meeting practical engineering requirements.
To address the issue of excessive ground settlement caused by improper design of tunneling parameters in slurry shield machines, this study proposes an intelligent optimization method for shield tunneling parameters that integrates machine learning algorithms. First, a five-step optimization framework is established, comprising geological information encoding, engineering data processing, shield response parameter prediction, ground settlement prediction, and control parameter optimization. Then, a data preprocessing pipeline tailored to the characteristics of shield tunneling data is developed to construct a sample database. Next, solution algorithms are respectively formulated for shield response prediction, ground settlement prediction, and control parameter optimization by applying Long Short-Term Memory (LSTM) neural networks and the Particle Swarm Optimization (PSO) algorithm. Finally, the proposed method is validated using a case study of the large-diameter slurry shield tunnel section between the Jingha Expressway and Luyuan North Street in the Beijing East Sixth Ring Road underground renovation project. The results indicate that geological encoding is an effective means of incorporating unstructured geological information into machine learning models. The shield response prediction model and ground settlement prediction model, both incorporating geological encoding as input, achieve an R² of 0.92 on the test data, demonstrating strong predictive performance. Under the settlement control standard of -10 to 5 mm, the excavation parameters generated by the intelligent optimization method reduce the average ground settlement by 29% compared to the measured data, offering valuable guidance for practical engineering applications.
To ensure the long-term safe and stable operation of railways, this study employs a self-designed permeameter to investigate the permeability of ballast aggregates under various service conditions, aiming to reveal the evolution patterns of ballast bed seepage performance. First, clean ballast aggregates meeting the premium crushed stone ballast standard are selected to analyze the effects of gradation non-uniformity coefficient and mean particle size on ballast aggregates permeability. Next, fly ash and fine sand are introduced as fouling agents and added to the upper, middle, and lower layers of clean ballast aggregates to simulate fouling distributions in existing ballast bed. The impacts of fouling degree, composition, and distribution on ballast aggregates permeability are systematically examined. Finally, by varying initial densities and applying vertical loads, the effects of initial density and applied vertical load on ballast aggregates permeability are studied. Results indicate that, in the absence of contamination within the ballast aggregates, a smaller non-uniformity coefficient and larger average particle size correspond to higher permeability and hydraulic conductivity. Conversely, the presence of contamination within the ballast aggregates, with higher contamination levels, smaller contaminant particle sizes, and more concentrated distribution, results in a smaller hydraulic conductivity and weaker permeability. Moreover, clean ballast aggregates with lower initial density result in a greater hydraulic conductivity and gradually enhanced permeability, while contaminated aggregates with lower initial density show a reduced hydraulic conductivity and diminishing permeability. Additionally, the permeability of contaminated ballast aggregates decreases with higher vertical loads due to plastic deformation during loading, preventing permeability from fully recovering after unloading.
In the inner rail of a trapezoidal sleeper track with a 400-meter radius curve, an alternating multi-wavelength rail corrugation phenomenon occurs between the middle and end of the sleepers. To investigate this issue from the perspective of wheel-rail contact resonance, a three-dimensional transient rolling contact model of the trapezoidal sleeper track is established based on the track structure. This model reveals the relationship between the natural frequencies of the wheel-rail elastic contact system and the passing frequencies of rail corrugation, as well as the resonance characteristics of the wheel-rail system. The wear behavior within the first cycle of rail corrugation contact patches under excitation by different corrugation wavelengths is analyzed. The results indicate that as wheelsets pass different positions along the trapezoidal track, distinct modes of the track system are excited. The resonance-involved modes differ, causing multi-wavelength corrugations on the rail surfaces at both the sleeper ends and the sleeper centers. Significant resonance occurs at vibration frequencies of 136.7 Hz and 248.7 Hz. At 248.7 Hz, the wheel induces rail bending vibration and sleeper corner warping modes via the sleeper ends; at 136.7 Hz, coordinated bending vibrations of the rail and sleeper are excited through the sleeper center. As the wheel traverses the corrugation excitation zone, the wear region expands progressively from the leading to the trailing edge of the contact patch. By the first cycle’s corrugation peak, the wear covers the entire contact area. Notably, wear severity at the troughs exceeds that at the peaks, providing a microscopic description of wear variation within the wheel-rail contact region. The resonance of the wheel-rail system induces rail corrugation generation, which in turn intensifies wheel-rail unstable vibrations, thereby accelerating corrugation development.
