Narrow Results

Passenger evacuation time prediction is a crucial basis for subway station management to better formulate safety control measures. It becomes possible to reasonably plan the flow of passengers within the station and configure safety devices such as signage and sprinkler systems with a known and explicit time framework, thereby reducing passenger congestion and panic. However, methods based on crowd dynamics simulation require a significant amount of time and effort to build models, and the rapidity of time prediction is challenging to ensure. Real human evacuation experiments involve ethical, safety and practical operational issues. To address this challenge, an evacuation time prediction model for subway passengers is established based on the CPA-SVR machine learning method, enhancing the speed and accuracy of prediction. The reliability of simulation results is validated by comparing observed values of passenger alighting and boarding time and traffic time at stairs with simulation values from MassMotion software. Fourteen factors related to the subway station structure, passengers and train status are selected as influence factors for evacuation time. A foundation data set for the evacuation time prediction model is obtained through 179 evacuation experiments under different influence factors using the MassMotion simulation system at 32 constructed stations. The SHAP interpretation method is applied to identify the importance of influence factors in the experimental results. A CPA-SVR passenger evacuation time prediction model is established, with accuracy concentrated between 85%–100%, based on training and validation sets. Further testing with 45 additional sets of fresh experimental data demonstrates the model’s strong predictive capability for new data, indicating good generalization ability. Finally, a focused analysis of passenger evacuation behaviors at bottlenecks such as stairs, gates and exits is conducted, accompanied by relevant optimization strategies.

Pedestrian heterogeneity is one of the important factors affecting evacuation efficiency in subway stations. This paper mainly studies the impact of pedestrian heterogeneity on evacuation based on simulations. With the help of Massmotion, the Qingdao Jinggangshan Road subway station is modeled. The social force model is used as the pedestrian dynamics model and the minimum cost model is used as the decision-making mechanism of pedestrian path selection. The models are verified by comparing the field data with the corresponding simulation data. Fully considering the impact of different pedestrian attributes on evacuation efficiency, pedestrians are divided into three categories with different speed levels and three categories with different body size levels. Simulation experiments are carried out by adjusting the proportional relationship of the number of pedestrians with different attributes. The simulation results indicate that the larger the proportion of fast pedestrians under the same number of evacuees, the higher the evacuation efficiency to a certain extent. The evacuation efficiency could be reduced accordingly with the increase in the proportion of pedestrians with large body sizes. When the pedestrian density is large, the impact of pedestrian heterogeneity on evacuation cannot be clearly reflected. Moreover, the quantitative fitting relationship between evacuation time and pedestrian quantity could be obtained. This paper provides a theoretical basis for the determination of evacuation strategy for the heterogeneous crowd.

With the increasing threat of terrorism attack, the probability of explosion inside the subway is very large. Reinforced concrete columns are the main supporting members of subway stations. If the columns of a subway station were subjected to near-field explosions, their damages can affect the safety of the subway after explosion. By using the finite element method, this paper established a coupling “explosive-air-concrete” model and verified the feasibility of the model through experiments. This model can be used in the damage assessment of subway station columns in terms of the bearing capacity, by which the damage of a reinforced concrete column can be divided into different levels. Furthermore, the effect of different parameters on the damage and bearing capacity of the subway station is discussed. The results demonstrate that the stirrup reinforcement ratio of a reinforced concrete is the key factor in determining the column damage under blast loadings. The present study therefore provides a key reference for assessing the damage of subway structures after terrorist attack.

Rapid seismic damage evaluation of subway stations is critical for the efficient decision on the repair methods to damaged subway stations caused by earthquakes and rapid recovery of subway networks without much delay. However, the current methods to evaluate the damage state of a subway station after earthquakes are mainly field investigation by manual or computer vision, which is dangerous and time-consuming. Given this, a novel methodology that adopts machine learning techniques as the classification model to rapidly and accurately evaluate the post-earthquake damage state of subway stations is proposed. Four machine learning techniques including artificial neural networks (ANNs), support vector machine (SVM), random forest (RF), and logistic regression (LR) are adopted. The interrelated intensity measures of ground motions (IMs) and their uncorrelated principal components (PCs) are, respectively, taken as the input to find the most suitable classification model as well as to investigate how the correlation among IMs affects the performance of these models. The results show that the LR taking IMs as inputs provides the best performance as it has the highest accuracy (87.7%) as well as stable performance. Additionally, taking PCs as input can improve the performance of RF, while for ANN, SVM, and LR, taking PCs as input will reduce their prediction performance. The research conclusions can provide a reference for the selection of the machine learning technique and its inputs when establishing a rapid assessment model for the post-earthquake damage state of subway stations.

Shaking table tests were conducted on typical models of subway structures subjected to several seismic shaking time histories to study seismic response of subway structures in soft ground as well as to provide data for validation of seismic design methods for underground structure. Three types of tests were presented herein, namely green field test, subway station test, and test for joint structure between subway station and tunnel. The similitude and modeling aspects of the 1g shaking table test are discussed. The seismic response of Shanghai clay in different depths was examined under different input waves to understand the acceleration amplification feature in both green field and in the presence of underground structure. Damage situation was checked on internal sections of both subway station and tunnels by halving the model structure. Structure deformation was investigated in terms of element strain under different earthquake loadings. The findings from this study provides useful pointers for future shaking table tests on underground structures/facilities, and the seismic response characteristic of underground structure derived from the shaking table test could be helpful for validating seismic design method for subway station.

As a relatively new means of transportation, the subway has become an important tool for the sustainable development of many cities. Being buried deep in soil under the weight of vital infrastructure, subway stations can be vulnerable to seismic excitations. Considering the high randomness of ground motions, it is important to research the failure probability and seismic performance of the subway station based on stochastic dynamic analysis. In this paper, a probability density evolution method (PDEM) coupled with a spectral representation random function is used to analyze the stochastic dynamic response and seismic probability of a subway station. First, according to the improved power spectral density model and the seismic design code of urban rail transit structures in China (GB 50909-2014), a set of nonstationary ground motions consistent with the code spectrum are obtained. Then, a great deal of deterministic dynamic calculations for Daikai subway station considering soil–structure interaction based on elastic–plastic methods are performed. In addition, the nonlinear stochastic response analysis and the dynamic probability analysis are obtained for the subway station by solving the PDEM equation. Finally, the probability density function (PDF) and cumulative distribution function (CDF) of the subway station under stochastic earthquake excitations are obtained based on three performance indices, including drift angle in the middle column, relative vertical displacement between floor and roof, and damage area ratio (DAR). The results show that the stochastic dynamic analysis and the probability density evolution method can analyze seismic response and evaluate seismic performance of subway stations effectively. The proposed method will serve as an effective tool for the seismic design of underground structures.

Based on a rectangle underground station structure, two-dimensional finite element models are established in this study to explore the effectiveness of different seismic reduction and isolation measures for underground structure, where Davidenkov model is adopted to consider the soil nonlinearity and the underground structure is considered elastic. The performances of the seismic reduction and isolation measures are evaluated by assessing the structure internal force and deformation responses. Depending on the ratio of wave impedance between the isolation layer and the structure, the isolation layers are divided into rigid and flexible types. The effects of the length and elastic modulus of rigid isolation layer as well as that of the thickness and shear modulus of flexible isolation layer are investigated. The results show that the seismic reduction effect of rigid isolation layer is better with the increase of stiffness, and the effect of flexible isolation layer is more obvious with the decrease of stiffness, which are consistent with the classical impedance theory. Furthermore, the middle column of subway station is usually the most vulnerable during seismic shakings, and one viable way to improve its seismic behavior is to reduce the column end constraints. Therefore, different column constraints consisting of swing, hinge, sliding connection and isolation bearing are considered. The numerical results suggest that among the different column end constraints considered, the sliding connection is comparatively more favorable, which can effectively limit the lateral deformation of column while imposing no horizontal reaction force.

In a bid to evaluate the train wind pressure on platform screen door installed on the platform of the subway station, the field test was conducted in existing Seoul Metropolitan Subway Line 2 in operation now. Variations in wind pressure on platform screen door, which were caused by the running train were measured depending on four different train operation patterns. The highest pressure of 28.1 kgf/m² was indicated on platform screen doors while two trains were passing the platform in different directions at a speed of 60 km/h.

In order to get and analysis the passenger flow information timely and accurately, this article introduces a passenger flow detection system applied at the subway station. The system uses video analysis method based on the depth information, realizing the detection of the real-time passenger flow and extracting the parameter of passenger flow. After image preprocessing, background segmentation, target detection and tracking, the extraction of traffic parameters and other function modules, the pedestrians detection program of system gets and then sends passenger flow parameter information, and later the data receiver program of system receives the passenger flow parameters and finishes data storage management. After debugging when used at a transfer of Beijing subway station, the system can get and save passenger flow parameters timely and accurately.