Subway Station Research Articles

Multi-sensor fault detection and correction for automated IAQ monitoring in smart buildings through attention-aware autoencoders with spatial prediction module

The integration of interconnected monitoring and control devices has significantly enhanced the management of indoor building environments, notably in underground subway stations. In these sophisticated settings, the accuracy of monitoring systems is critical, as data-driven control systems rely extensively on sensor feedback. However, sensor faults arising from hardware damage, wear, and cyberattacks compromise the reliability of these complex systems. Despite extensive efforts, existing methods still face challenges in accurately detecting and reconstructing faults, particularly when dealing with multiple sensor failures. This study introduces a hybrid sensor validation framework that combines a multi-head attention-based denoising autoencoder (AE) with a deep learning prediction module. The performance assessment of the proposed gated recurrent unit (GRU) integrated attention-based fault detection, and reconstruction network (GADRN) shows a significant 33 % and 21 % improvement in critical success index compared to Independent Component Analysis and GRU-AE frameworks. GADRN consistently identified faulty sensors across various fault periods, achieving the lowest false alarm rate of 11 % against several conventional and machine learning-based models. A ventilation control analysis highlights the significance of incorporating a sensor validation framework in modern buildings. The outputs by the GADRN led to a 22.5 % decrease in energy consumption by preventing unnecessary resource use attributed to sensor faults.

Elastic Local Buckling Analysis of a Sandwich Corrugated Steel Plate Pipe-Arch in Underground Space

In underground spaces, corrugated steel plate (CSP) pipe-arches may experience local buckling instability, which can subsequently lead to the failure of the entire structure. Recently, sandwich CSP pipe-arches have been used to enhance the stability of embedded engineering outcomes, and their buckling behaviors require in-depth research. In this paper, we establish a theoretical model by simplifying soil support and using Hoff sandwich plate theory to focus on the local buckling stability of the straight segment in embedded sandwich CSP pipe-arches using the Rayleigh–Ritz method. Through stability analysis, the instability criteria for embedded sandwich CSP pipe-arches are analytically determined. Numerical calculations reveal that the critical buckling load of a sandwich CSP pipe-arch is affected by several factors, including the elastic modulus, thickness, Poisson’s ratio, rotational constraint stiffness, and the length of the straight segment. Specifically, increasing the thickness of the sandwich CSP pipe-arch can substantially enhance the critical buckling load. Meanwhile, the wavenumber is affected by the elastic modulus and the length of the straight segment. The analytical results are in agreement with those obtained from finite element analysis. These findings provide a theoretical basis and guidance for the application of sandwich CSP pipe-arches in fields such as subway stations, tunnel construction, underground passages, and underground parking facilities.

Study on Parking Adaptability in Urban Complexes on Top of Subways Based on Shared Parking Spaces

Urban complexes on top of subways as a function of intensive building groups, including residential, office, business, and other types nature of land use where parking time differences are obvious, can implement shared parking spaces, thereby reducing the index of parking allotment. Currently, the parking space allocation index for complexes is only a simple superposition of different land uses, resulting in an over-allocation of parking allotments, leading to a waste of land resources and a low utilization rate of parking allotments. Considering the factor of shared parking spaces, this paper conducted an in-depth analysis of the parking adaptability of urban complexes on top of subways and selected five urban complexes on top of subway stations in Wuhan to conduct a parking survey to analyze the parking demand characteristics. This study also investigated the parking behavior of parkers and analyzed the characteristics of parking behavior in urban complexes on top of subways as well as the current parking demand prediction methods and models, establishing a parking demand prediction model based on shared parking spaces and conducting an adaptability analysis. Finally, using five urban complexes in Wuhan as examples, the number of parking spaces demanded by urban complexes on top of subways in 2025 was predicted, and Wuhan Golden Harvest Fashion Plaza was used as an example to verify the feasibility and implementation ability of the theoretical and applied research in this paper.

Numerical Analysis of Flood Invasion Path and Mass Flow Rate in Subway Stations under Heavy Rainfall Conditions

The occurrence of extreme weather, such as heavy rainfall and sudden increases in precipitation, has led to a notable rise in the frequency of flooding in subway stations. By conducting numerical simulations of flood disasters in subway stations under heavy rainfall conditions and gaining insights into the patterns of flood invasion inside the stations, it is possible to develop practical and feasible drainage designs for the stations. This paper employs the computational fluid dynamics (CFD) method, utilising the volume of fluid function (VOF) method and the renormalization k-ε group model within the vortex viscosity model. The complete process of flood invasion into subway stations with varying water levels (1500 mm, 2000 mm, and 2450 mm) is modelled, and the distribution of floods at different times under varying operational conditions is analysed to identify the evolutionary patterns of station flood history. The simulation calculations yielded the mass flow rate time history curve at the tunnel entrance and exit, which was then subjected to an analysis of its development trend over time. The total accumulated water in the subway station is calculated by integrating the difference in mass flow rate between the entrance and the tunnel exit, using the mass flow rate curve. In conclusion, the paper proposes drainage measures that provide valuable insights into pumping strategies when floodwaters infiltrate subway stations. The results indicate that the speed of flood spreading in subway stations increases with higher groundwater levels, and that the mass flow rate of floodwater entering the tunnels increases over time, eventually reaching a stable state. It was observed that, at certain times, the mass flow rate of floodwater into the tunnels exhibited a linear relationship with time.

Spatial heterogeneity and nonlinearity study of bike-sharing to subway connections from the perspective of built environment

Bike-sharing has become an effective solution to address the "last mile" challenge in public transit. Existing studies insufficiently consider architectural environmental factors from a design perspective in impacting bike-sharing-to-subway connection(BSC) behavior, and often relying on subjective assessments to explain the spatial heterogeneity of the built environment on BSC travel. To investigate the impact mechanisms of the built environment on BSC behaviors, this study used weekly data on bike-sharing travel trajectories from April 7 to April 14, 2021, in Shenzhen, China, as the research sample. By integrating large-scale urban point of interest(POI), street-view images and road-network data from Shenzhen, this study examines the mechanisms by which the built environment influences BSC travel. This study initially applied linear regression and multiscale geographically weighted regression (MGWR) to analyze the spatial heterogeneity of built environment impacts on BSC travel. Then, XGBoost's nonlinear relationships were used to explain and validate the MGWR results. This study reveals that functional diversity is the most significant factor influencing BSC travel. At subway stations where it is difficult to enhance functional diversity, improvements in road connectivity, vegetation, and enclosure can enhance BSC commuting. These findings are crucial for decreasing the reliance on motor vehicles and fostering sustainable urban growth.

Comparative analysis of the seismic performance of ECC jacket reinforced columns with different cross-sectional forms subject to different load modes

Based on the high tensile strength and tensile strain of (engineered cementitious composites) ECC, it is applied to the weak link central columns of subway stations to enhance their seismic resilience. In this study, the effects of the column's cross-sectional shape, ECC jacket form, and the vertical gravity load and vertical dynamic load during seismic action on the hysteretic performance of the column were thoroughly analyzed. A constrained constitutive model for cementitious materials, a reinforced hysteresis constitute model, and a calculated damage factor for concrete were adopted to establish a three-dimensional refined column model with an experimentally verified error of less than 10 %. After that, the damage distribution and damage degree of the columns, as well as the changes in hysteretic performance such as hysteretic curve, skeleton curve, energy dissipation, and stiffness degradation were analyzed by the static model analysis. The results showed that the columns had higher damage levels under high frequency and high amplitude of dynamic axial compression ratio in the vertical direction compared to the constant high axial compression ratio, and the ECC jacket could effectively reduce the damage levels of the columns, but the use of the in-built ECC (IB-ECC) jacket was better than the out-sourced ECC (OS-ECC) jacket. In addition, the IB-ECC jacket did not significantly improve the peak bearing capacity of the columns, but significantly improved the ultimate bearing capacity and displacement ductility of the columns, while the OS-ECC jacket significantly improved the peak bearing capacity of the columns. The ECC jacket was also effective in slowing down the stiffness degradation of the columns. This study significantly contributes to the design strategies for enhancing the resilience of columns in subway stations.

Joints mechanical characteristics of prefabricated subway station considering bending stiffness difference

In prefabricated subway stations, the presence of joints leads to an uneven circumferential distribution of structural stiffness. However, there has been limited research focusing on the variability in bending stiffness of joints so far. Therefore, this paper proposes a theoretical framework to study deformation characteristics considering the differences in bending stiffness. This study aim to analyze the deformation characteristics of prefabricated structures, with a specific focus on the impact of variations in bending stiffness on the overall structural behavior. The research scope includes the calculation methods for the bending stiffness of joints, predicting maximum settlement of the top plate, and analyzing the influence of key parameters such as joint positions, geometric shapes, and dimensions, overburden density γ, lateral earth pressure coefficient λ, overburden thickness hf, and concrete density ρ on the joint bending stiffness. Results validate the reliability of the proposed method for calculating joint bending stiffness and demonstrate the key factors contributing to differences in bending stiffness.

Investigating the Nonlinear Effect of Land Use and Built Environment on Public Transportation Choice Using a Machine Learning Approach

Understanding the relationship between the demand for public transportation and land use is critical to promoting public-transportation-oriented urban development. Taking Beijing as an example, we took the Public Transportation Index (PTI) during the working day’s early peak hours as the dependent variable. And 15 land use and built environment variables were selected as the independent variables according to the “7D” built environment dimensions. According to the Modifiable Areal Unit Problem (MAUP), the size and shape of the spatial units will affect the aggregation results of the dependent variable and the independent variables. To find the ideal spatial unit division method, we assess how well the nonlinear model fits several spatial units. Extreme Gradient Boosting (XGBoost) was utilized to investigate the nonlinear effects of the built environment on PTI and threshold effects based on the ideal spatial unit. The results show that (1) the best spatial unit division method is based on traffic analysis zones (TAZs); (2) the top four explanatory variables affecting PTI are, in order: mean travel distance, residential density, subway station density, and public services density; (3) there are nonlinear relationships and significant threshold effects between the land use variables and PTI. The priority regeneration TAZs were identified according to the intersection analysis of the low PTI TAZs set and the PTI-sensitive TAZs set based on different land use variables. Prioritized urban regeneration TAZs require targeted strategies, and the results of the study may provide a scientific basis for proposing strategies to renew land use to increase PTI.

Deformation Effects of Deep Foundation Pit Excavation on Retaining Structures and Adjacent Subway Stations

Deformation Effects of Deep Foundation Pit Excavation on Retaining Structures and Adjacent Subway Stations

Assessment of air quality in the Philadelphia, Pennsylvania subway.

Subways are popular and efficient modes of transportation in cities. However, people are exposed to high levels of particulate matter (PM) in subways. Subway air quality in the United States has been investigated in a few cities, but data is lacking on simultaneous measurement of several pollutants, especially ultrafine particles (UFP) and black carbon (BC), in combination with different size fractions of PM. The goals of this study are to assess air quality in a belowground subway and compare it with outdoor ambient levels, to examine temporal variability of PM in the subway, and to analyze the correlation between PM and BC. Particulate matter of varying sizes (PM1, PM2.5, PM10), UFP, and BC were measured using DustTrak, nanoparticle detector, and micro aethalometer, respectively. Measurements were made at the belowground subway platform and the aboveground street level at 15th Street subway station in Philadelphia during summer 2022. Belowground mean PM1, PM2.5, and PM10 were 112.2 ± 61.3 µg/m3, 120 ± 65.5 µg/m3, and 182.1 ± 132 µg/m3, respectively, which were 5.4, 5.7, and 7.6 times higher than the respective aboveground street levels. The UFP lung deposited surface area (LDSA) (59.4 ± 36.2 µm2/cm3) and BC (9.5 ± 5.4 μg/m3) belowground were 1.7 times and 10.7 times higher than the aboveground. The pollutant concentration varied from day-to-day on both the locations. A higher positive correlation was found between the belowground BC and PM2.5 (r = 0.51, p < 0.05) compared to the aboveground (r = 0.16, p < 0.05). This study showed high levels of particulate matter exposure at a belowground subway station in Philadelphia. Particulate matter levels were about 5 to 8 times higher at belowground subway station than the corresponding aboveground street level. Higher levels were also observed for UFP lung deposited surface area (LDSA), while black carbon levels showed the highest concentration at the belowground level by a factor of ten compared to the aboveground level. The study shows the need for air quality management at belowground subways to reduce particulate matter exposure for the commuters.

A Disaster Response Complex for training of emergency responders in the Northwest United States.

The Disaster Response Complex (DRC) is a year-round training complex that specializes in training emergency responders in realistic indoor and outdoor environments. The outdoor site is comprised of 3 acres of secured customizable space for various exercises. The indoor site is designed to include an indoor facility with a full-size city street, complete with storefronts and motor vehicles that can be configured for emergency response training exercises, and a train or subway station where mockups of derailments can be simulated. The DRC includes large parking areas to accommodate multiple vehicles, allowing trainees the space needed to set up equipment and tactical operations. In addition, a campus office space is also available for an off-site operations center.

Spatial and Temporal Variation of Subway Ridership before and during the COVID-19 Period in Beijing

The outbreak of COVID-19 in 2019 caused a huge impact on people’s lives. Uncovering the variation of public traffic daily patterns during the pre-pandemic and pandemic periods would help interpret the impact of the pandemic on people’s routine activity and promote the sustainable development of public transport systems. By collecting subway traffic data during the pre-pandemic and pandemic periods in Beijing, China, this paper analyzes the spatial and temporal variation of subway ridership and seeks to find out what sort of environment variables related to the variation of subway ridership during the two periods. The results show that the ridership of Beijing subway during the pandemic period decreased by 91.69% compared with the pre-pandemic period. On working days and non-working days during the pandemic period, the subway stations experiencing huge ridership reductions were mainly distributed within the core urban areas, while in the morning peak hours, the stations experiencing huge ridership reduction were located within suburban areas. The origin-destination stations with a large decrease in ridership were mainly distributed along the central to northern directions of Beijing but, on non-working days, they were mainly distributed along the central to northwestern directions of Beijing. The results of the regression analysis indicated that, during the pandemic period, the industrial parks were significantly positively correlated with subway ridership, while the pedestrian road network density was significantly negatively correlated with subway ridership.

Seismic Response and Mitigation Analysis of a Subway Station in the Site with Weak Interlayers

Challenges related to seismic performance and seismic mitigation are more pronounced in the presence of weak interlayers compared to typical layered soil conditions. This study focuses on a double-layer double-span rectangular frame subway station structure. A coupled static–dynamic finite element analysis model of the soil-structure system is established by using the finite element software ABAQUS/CAE V 6.14. The research investigates the influence of factors such as interlayer thickness, location, and strength on the seismic response of subway station structures. Furthermore, in order to evaluate the effectiveness of FPB in mitigating seismic effects in the weak interlayer ground, two different schemes are proposed in this paper. One is the structure without FPB and the other is the structure with FPB on the top of the central column. The findings reveal that weak interlayers exert a significant influence on the seismic response of subway station structures, especially when these lower-strength weak interlayers are located within the central portion of the subway station structure and exhibit considerable thickness. The FPB on the top of the central column can reduce the overall lateral stiffness of the subway station structure. This, in turn, results in a slight increase in the deformation of sidewall and inter-story displacement angles, accompanied by a marginal exacerbation of sidewall damage. However, the implementation of FPB effectively reduces the deformation of the central column and substantially mitigates the extent of damage to the central column.

Experimental investigation on cooling load caused by unorganized ventilation in subway station: A case study

Unorganized ventilation significantly increases the energy consumption of subway stations. However, the quantitative description of cooling load caused by the unorganized ventilation in subway stations with platform screen doors (PSDs) still needs to be explored in depth. This study firstly proposed an experiment-based method to determine the airflow rate of unorganized ventilation, and then the corresponding cooling load is determined. Based upon this method, a series of field tests were conducted at a subway station in Shanghai. By analyzing the experimental data, the characteristic of unorganized ventilation at PSDs and entrance/exit passages was obtained. As for PSDs, the volume of unorganized ventilation in a cycle (the period from the upward train entering the station to the next upward train starting to approach the station) from the tunnel to the platform and from the platform to the tunnel is 2112.24 m3 and 4219.31 m3, respectively. With regard to entrance/exit passages, the volume of unorganized ventilation is 2655 m3 in a cycle. Thereafter, the above-mentioned results were used to determine cooling load. Owing to the difference in the departure density of train on weekdays and weekends, two typical summer days were selected for the purpose of cooling load analysis. The overall cumulative value of the cooling load caused by unorganized ventilation was 1416 kWh on a working day and 1718 kWh for the weekend, which accounted for 16.74 % and 19.19 % of the daily cooling load, respectively.

Contribution of built environment factors and their interactions with subway station ridership

Contribution of built environment factors and their interactions with subway station ridership

Integrated Optimization of Route and Frequency for Rail Transit Feeder Buses under the Influence of Shared Motorcycles

In this paper, we develop a multi-objective integrated optimization method for feeder buses of rail transit based on realistic considerations. We propose a bus stop selection method that considers the influence of shared motorcycles, which can score the importance of alternative bus stops and select those with the highest scores as objectives. The objective of the model in this paper is to minimize both the travel costs of passengers and the operating costs of the bus company. This is achieved by optimizing feeder bus routes, the frequency of departures, and interchange discounts to enhance the connectivity between feeder buses and rail transit. In addition, to ensure the feasibility of generated routes in the real road network, a genetic algorithm encoded with priority is used to solve this model. We use the Xingyao Road subway station in Kunming as an example, and the results show that the optimization method is effective.

Characteristics analysis of leakage diseases of Beijing underground subway stations based on the field investigation and data statistics

With a continuous increasing of the underground water level of Beijing, many leakage diseases induced by the structural defect have been exposed in the subway tunnels that have been put into operation. The leakage diseases of underground subway stations may severely cause the safety and durability problems of the structure. Moreover, it could affect the passenger experience and seriously threaten the operation safety. Therefore, this paper collected the leakage states of a total of 258 underground subway stations in 16 lines of Beijing by field investigation, which include the number of average leakage points, leakage types and classification, distribution scenes of leakage, the construction methods and operation ages of subway stations and so on. Besides, in order to further investigate the causes of the leakage diseases, three typical cases of Beijing subway stations with severe leakage diseases, which were constructed by different methods, were selected to carry out the statistical analysis of leakage disease. The typical positions of leakage diseases of Beijing subway stations with different construction methods were presented by three-dimensional modelling, and the leakage characteristics of each station were analyzed. Finally, based on the field investigation and data statistics, a data-based Bayesian network leakage prediction model to evaluate the leakage risk of subway stations was constructed. This research can provide an intuitive reference for early warning, monitoring and prevention of leakage diseases of metro subways in operation.

A Sustainable Dynamic Capacity Estimation Method Based on Bike-Sharing E-Fences

Increasing urban traffic congestion and environmental pollution have led to the embrace of bike-sharing for its low-carbon convenience. This study enhances the operational efficiency and environmental benefits of bike-sharing systems by optimizing electronic fences (e-fences). Using bike-sharing order data from Shenzhen, China, a data-driven multi-objective optimization approach is proposed to design the sustainable dynamic capacity of e-fences. A dynamic planning model, solved with an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II), adjusts e-fence capacities to match fluctuating user demand, optimizing resource utilization. The results show that an initial placement of 20 bicycles per e-fence provided a balance between cost efficiency and user convenience, with the enterprise cost being approximately 76,000 CNY and an extra walking distance for users of 15.1 m. The optimal number of e-fence sites was determined to be 40 based on the solution algorithm constructed in the study. These sites are strategically located in high-demand areas, such as residential zones, commercial districts, educational institutions, subway stations, and parks. This strategic placement enhances urban mobility and reduces disorderly parking.

Dynamic response and regular analysis of adjacent buildings under blasting construction across foundation pits of subway stations

To study the impact of cross-pit blasting on nearby buildings, a numerical model was used based on the case of a subway station excavation. The analysis focused on the vibration response patterns at monitoring points, considering different lengths, widths, depths, and positions of the adjacent foundation pit (AFP) and varying blasting foundation pit (BFP) depths. Additionally, a data-driven method was adopted to improve numerical calculation efficiency under multiple scenarios. In this method, leave-one-out cross-validation is used to enhance the accuracy of the XGBoost vibration reduction prediction model, and the model's hyperparameters are optimized using Bayesian algorithms. Furthermore, employing the established LOO-BO-XGBoost model in combination with the physical equations for charge control, the data-physical hybrid dynamic design method for cross-pit blasting charge is developed. The results indicate that, among the size parameters of the AFP, depth has the greatest impact on peak particle velocity (PPV), followed by length and width. When the size of the AFP is the same, the closer it is to the building, the more significant its vibration reduction effect. The deeper the excavation of the BFP, the lesser the impact of the blasting on the building. The LOO-BO-XGBoost model outperforms the XGBoost and ANN models, achieving higher accuracy (training dataset: R² = 0.93, RMSE = 0.023; testing dataset: R² = 0.90, RMSE = 0.021). Subsequently, the data-physical hybrid dynamic design method optimizes the charge in the cross-pit blasting case. As the AFP is excavated from 11 m to 15 m, the single-hole charge is increased from 9 kg to 10 kg according to this method. And the measured PPV still meets the requirements. Therefore, considering the vibration reduction effect of the AFP, it is important to expedite construction and reduce time costs. The research method proposed in this paper can serve as a valuable guide for similar projects.

Nonlinear Relationship of Multi-Source Land Use Features with Temporal Travel Distances at Subway Station Level: Empirical Study from Xi’an City

The operation of the subway system necessitates a comprehensive understanding of passenger flow characteristics at station locations, as well as a keen awareness of the average travel distances at these stations. Moreover, the travel distances at the station level bear a direct relationship with the built environment composed of land use characteristics within the station’s catchment area. To this end, we selected the land use features within an 800 m radius of the station (land use area, distribution of points of interest, and the surrounding living environment) as the influencing factors, with the travel distances at peak hours on the subway network in Xi’an as the research subject. An improved SSA-XGBOOST-SHAP interpretable machine learning framework was established. The research findings demonstrate that the proposed enhanced model outperforms traditional machine learning or linear regression methods in terms of R-squared, MAE, and RMSE. Furthermore, the distance from the city center, road network density, the number of public transit routes, and the land use mix have a pronounced influence on travel distances, reflecting the significant impact that mature built environments can have on passenger attraction. Additionally, the analysis reveals a notable nonlinear relationship and threshold effect between the built environment variables comprising land use and the travel distances during peak hours. The research results provide data-driven support for operational strategy management and line capacity optimization, as well as theoretical underpinnings for enhancing the efficiency and sustainability of the entire subway system.