Rail transit hub emergency control method and system based on real-time simulation

Abstract

This invention discloses a real-time simulation-based emergency control method and system for rail transit hubs, relating to the fields of intelligent transportation and rail transit emergency management. The method includes: synchronizing real-time passenger flow data with train operation status data to generate a hub status dataset; constructing a multi-level simulation model to simulate the evolution of passenger flow distribution by pre-setting passenger evacuation behaviors and train operation constraints; based on the output of the multi-level simulation model, using a bottleneck identification algorithm to locate capacity-limiting nodes in each evacuation path, calculating passenger flow carrying capacity, and generating optimal path control parameters with the goal of minimizing evacuation time; converting the optimal path control parameters into train automatic control system commands and passenger flow guidance display commands, which are then distributed to each line control unit through the hub centralized dispatching system to adjust train operation frequency and passenger evacuation direction. This invention achieves intelligent and collaborative emergency control of rail transit hubs.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation and rail transit emergency management technology, and in particular to an emergency control method and system for rail transit hubs based on real-time simulation. Background Technology

[0002] Traditional passenger flow management and train dispatching systems primarily rely on static contingency plans and human experience-based decision-making, making it difficult to cope with complex scenarios such as sudden surges in passenger flow and equipment failures. Existing technologies, such as offline simulation based on historical data and rule-driven control strategies, are gradually evolving towards dynamic and intelligent approaches. For example, multi-agent systems (MAS) are used to simulate passenger behavior, or train timetable adjustment algorithms are combined to optimize dispatching efficiency. However, these methods still have significant limitations in real-time data fusion accuracy, multi-level model coupling, and dynamic path optimization. Especially in scenarios involving large-scale passenger evacuation, existing technologies often struggle to achieve coordinated optimization of passenger flow distribution evolution and train dispatching strategies, leading to low emergency response efficiency.

[0003] CN115796509A discloses a rail transit emergency dispatch auxiliary decision-making system and method. This system uses parallel simulation technology to simulate and evaluate multiple decision-making schemes under emergency scenarios. Although this technology improves the scientific nature of dispatching and command, its simulation model lacks a detailed characterization of the dynamic distribution characteristics of passenger flow and does not establish a closed-loop optimization mechanism for passenger evacuation paths and train dispatching instructions.

[0004] CN106355516A proposes a power grid dispatching and control system based on real-time simulation. This technology generates preventative operation commands through a risk assessment unit. However, its model architecture and optimization algorithm are mainly designed for steady-state analysis of power systems, making it difficult to directly apply to the passenger flow evacuation problem in rail transit, which has strong spatiotemporal coupling characteristics. The shortcomings of existing technologies are mainly reflected in: 1) the decoupling of passenger flow simulation and train dispatching model leads to insufficient coordination between evacuation strategies and capacity allocation; 2) bottleneck node identification is mostly based on static topology analysis, without considering the dynamic impact of time-varying passenger flow characteristics on path capacity; 3) the generation of control commands lacks a multi-objective optimization framework and has not established a command security verification mechanism, which may lead to secondary congestion risks. Summary of the Invention

[0005] In view of the problems of low model coupling, insufficient dynamic optimization capability and lack of command security in existing emergency control methods for rail transit, especially the problems of insufficient strategy synergy caused by the decoupling of passenger flow simulation and train scheduling model, the inability of static bottleneck identification methods to adapt to dynamic changes in passenger flow, and the lack of a safe and reliable command generation mechanism, this invention is proposed.

[0006] Therefore, the problem to be solved by this invention is how to achieve high-precision real-time coupled simulation of dynamic passenger flow distribution and train operation status, and establish a dynamic bottleneck identification and path optimization mechanism based on time-varying characteristics, so as to significantly improve the collaborative scheduling efficiency and evacuation safety of rail transit hubs in emergency scenarios such as large passenger flow.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, embodiments of the present invention provide an emergency control method for rail transit hubs based on real-time simulation, comprising,

[0009] Collect real-time passenger flow data, synchronize the real-time passenger flow data with train operation status data in time, and generate a hub status dataset including passenger flow density distribution and train location information;

[0010] A multi-level simulation model was constructed to simulate the evolution of passenger flow distribution by pre-setting passenger flow evacuation behavior and train operation constraints.

[0011] Based on the output of the multi-level simulation model, the bottleneck identification algorithm is used to locate the capacity-limiting nodes in each evacuation route, calculate the passenger flow carrying capacity of each evacuation route, and generate the optimal route control parameters with the goal of minimizing evacuation time.

[0012] The optimal route control parameters are converted into train automatic control system commands and passenger flow guidance display commands, which are then sent to the control units of each line through the hub centralized dispatching system to adjust the train operation frequency and passenger flow evacuation direction.

[0013] As a preferred embodiment of the real-time simulation-based emergency control method for rail transit hubs described in this invention, the method includes: constructing a multi-level simulation model to simulate the evolution of passenger flow distribution by pre-setting passenger evacuation behaviors and train operation constraints, including:

[0014] Based on the hub status dataset, a multi-level simulation model is established, which includes a passenger flow behavior simulation layer and a train scheduling simulation layer.

[0015] In the passenger flow behavior simulation layer, a passenger movement model based on cellular automata is constructed. The hub space is divided into cellular grids, and the passenger distribution state of the cellular grids is initialized according to the passenger flow density distribution to establish a passenger movement rule matrix.

[0016] In the train scheduling simulation layer, an event-driven train operation model is constructed, and the position and status of each train are initialized according to the train position information to establish a train operation event queue;

[0017] Establish a set of passenger flow evacuation behavior parameters, a set of train operation constraints, and a set of emergency control strategy parameters, and then start the multi-level simulation model.

[0018] Record the calculation results of the multi-level simulation model under different emergency control strategies to generate passenger flow distribution evolution data.

[0019] As a preferred embodiment of the real-time simulation-based emergency control method for rail transit hubs described in this invention, the multi-level simulation model adopts a layered coupling structure; the passenger flow behavior simulation layer calculates the location of passengers at the next moment based on the passenger flow evacuation behavior parameter set and the current personnel distribution status; the train scheduling simulation layer calculates the train operation status based on the train operation constraint set and the emergency control strategy parameter set.

[0020] As a preferred embodiment of the real-time simulation-based emergency control method for rail transit hubs described in this invention, the method comprises: based on the output results of the multi-level simulation model, using a bottleneck identification algorithm to locate capacity-limiting nodes in each evacuation path, calculating the passenger flow carrying capacity of each evacuation path, and generating optimal path control parameters with the goal of minimizing evacuation time, including:

[0021] Extract the passenger flow distribution evolution matrix output by the multi-level simulation model, perform peak detection on the passenger flow density data of the passenger flow distribution evolution matrix, and identify the spatiotemporal coordinate points where passenger flow density is abnormally concentrated;

[0022] Based on the aforementioned spatiotemporal coordinates, a bottleneck identification algorithm is used to traverse all evacuation paths within the hub to obtain capacity-limited nodes.

[0023] The capacity-limited nodes are classified and labeled, and the physical geometric parameters and design capacity parameters of each type of capacity-limited node are obtained;

[0024] Based on the physical geometric parameters and design capacity parameters, and combined with the passenger flow density change trend in the passenger flow distribution evolution matrix, the dynamic capacity correction coefficient of the capacity-limited node in different time periods is calculated.

[0025] Based on the dynamic capacity correction coefficient, the minimum cut algorithm is used to calculate the passenger flow carrying capacity of the evacuation path of each capacity-limited node;

[0026] With the shortest evacuation time as the objective function and the passenger flow carrying capacity as the constraint, a linear programming model is established, and the simplex method is used to solve for the passenger flow allocation ratio and the corresponding train departure interval parameters for each evacuation route.

[0027] Based on the train departure interval parameters and the passenger flow capacity of each line, a greedy algorithm is used to determine the opening status parameters of each platform.

[0028] The optimal route control parameters are generated by combining the train departure interval parameters and platform open status parameters.

[0029] As a preferred embodiment of the real-time simulation-based emergency control method for rail transit hubs described in this invention, wherein: based on the spatiotemporal coordinates, a bottleneck identification algorithm is used to traverse all evacuation paths within the hub to obtain capacity-limited nodes, including:

[0030] Extract the spatial location information of spatiotemporal coordinate points and establish an evacuation route detection network within the hub;

[0031] Based on the evacuation path detection network, the starting point and termination condition of the bottleneck identification algorithm are set, and the bottleneck identification algorithm is started to traverse from each starting node of the evacuation path detection network.

[0032] Based on the load status and congestion indicators of the detection nodes, candidate nodes with capacity-limited characteristics are identified, and the capacity-limited intensity index of the candidate nodes is calculated to obtain the capacity-limited nodes.

[0033] As a preferred embodiment of the real-time simulation-based emergency control method for rail transit hubs described in this invention, the optimal path control parameters are converted into train automatic control system commands and passenger flow guidance display commands, which are then distributed to the control units of each line through the hub centralized dispatching system to adjust train operating frequency and passenger flow evacuation direction, including:

[0034] The train departure interval parameters and platform open status parameters of the optimal path control parameters are analyzed, and the train departure interval parameters are converted into train automatic control system instructions containing departure time, target interval and execution period according to the communication protocol format of each line control unit.

[0035] The platform opening status parameters are encoded according to the platform number and opening direction to generate passenger flow guidance display instructions;

[0036] Conflict detection is performed on the train automatic control system commands and the passenger flow guidance display commands. A timing logic check algorithm is used to identify command combinations that cause conflicts in passenger evacuation paths, and time offset adjustments are made to the conflicting commands.

[0037] Based on the priority level of each line control unit, the adjusted train automatic control system commands are divided into high-priority commands and ordinary-priority commands according to their urgency, and a hierarchical issuance queue is established.

[0038] The train automatic control system commands are sent to the corresponding line control units through the communication network of the hub centralized dispatch system, according to the priority order of the hierarchical dispatch queue, and the command dispatch timestamp and target unit identifier are recorded at the same time.

[0039] The passenger flow guidance display instructions are sent to the LED display devices of each platform and passageway through the hub centralized dispatch system;

[0040] Adjust the train operation frequency according to the train departure interval parameters and feed back the instruction execution status to the hub centralized dispatching system;

[0041] Establish an instruction execution monitoring mechanism. By comparing the instruction issuance timestamp with the execution feedback time, calculate the instruction transmission delay and execution effect deviation, and generate feedback data for the next round of optimal path control parameter optimization.

[0042] As a preferred embodiment of the real-time simulation-based emergency control method for rail transit hubs described in this invention, the method employs a timing logic check algorithm to identify command combinations that cause conflicts in passenger evacuation routes, including:

[0043] When the same station receives conflicting station open status parameters simultaneously within the same time window, it is identified as a combination of path conflict instructions by the timing logic check algorithm and marked as a high-priority conflict event.

[0044] When the departure time commanded by the automatic train control system conflicts with the current platform's preset minimum safety interval, it is determined to be a scheduling command conflict. The system then suspends the issuance of this command and requests updated scheduling parameters.

[0045] When the LED display device receives passenger flow guidance instructions from multiple directions at the same time, and the guided channels have intersecting or merging relationships, the path conflict check mechanism is triggered, and the scheduling system determines the primary guidance direction and adjusts the time offset of the display instructions for the secondary directions.

[0046] Secondly, the present invention provides an emergency control system for rail transit hubs based on real-time simulation, comprising:

[0047] The data acquisition module is used to collect real-time passenger flow data, synchronize the real-time passenger flow data with train operation status data in time, and generate a hub status dataset including passenger flow density distribution and train location information.

[0048] The simulation module is used to build multi-level simulation models and simulate the evolution of passenger flow distribution by pre-setting passenger flow evacuation behavior and train operation constraints.

[0049] The calculation module, based on the output of the multi-level simulation model, uses a bottleneck identification algorithm to locate the capacity-limiting nodes in each evacuation path, calculates the passenger flow carrying capacity of each evacuation path, and generates the optimal path control parameters with the goal of minimizing evacuation time.

[0050] The conversion and adjustment module is used to convert the optimal path control parameters into train automatic control system instructions and passenger flow guidance display instructions, which are then sent to the control units of each line through the hub centralized dispatching system to adjust the train operation frequency and passenger flow evacuation direction.

[0051] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of the emergency control method for rail transit hubs based on real-time simulation as described in the first aspect of the present invention.

[0052] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of the emergency control method for rail transit hubs based on real-time simulation as described in the first aspect of the present invention.

[0053] Compared with existing technologies, the advantages of this invention are as follows: A high-precision hub status dataset is established through real-time passenger flow data and train operation status synchronization, solving the problems of poor data timeliness and data asynchrony between different systems in traditional methods; a multi-level simulation model with hierarchical coupling is adopted, using cellular automata to accurately simulate passenger flow behavior, combined with an event-driven train operation model, to achieve dynamic interactive simulation of passenger flow evacuation and train scheduling, overcoming the shortcomings of isolated models and poor coordination in existing technologies; in the dynamic optimization stage, a bottleneck identification algorithm based on spatiotemporal coordinate points combined with a dynamic capacity correction coefficient achieves accurate positioning and dynamic evaluation of capacity-limited nodes on evacuation paths, and then the optimal path control parameters are generated through a minimum cut algorithm and a linear programming model, significantly improving the timeliness and feasibility of the evacuation plan; through an instruction conflict detection mechanism and a hierarchical issuance strategy, the safe and reliable execution of control instructions is ensured, while an execution feedback mechanism is established to form an optimization closed loop. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0055] Figure 1 This is a flowchart of an emergency control method for rail transit hubs based on real-time simulation. Detailed Implementation

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0057] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0059] As mentioned in the background section, the shortcomings of existing technologies are mainly reflected in the following aspects: 1) the decoupling of passenger flow simulation and train scheduling model leads to insufficient coordination between evacuation strategies and capacity allocation; 2) bottleneck node identification is mostly based on static topology analysis, without considering the dynamic impact of time-varying passenger flow characteristics on path capacity; 3) the generation of control instructions lacks a multi-objective optimization framework and has not established a safety verification mechanism for instructions, which may lead to secondary congestion risks. In response to the above problems, this invention proposes an emergency control method and system for rail transit hubs based on real-time simulation. By constructing a passenger flow-train coupled simulation model and combining a dynamic bottleneck identification algorithm and path optimization strategy, safe and reliable emergency control instructions are generated.

[0060] Figure 1 This is a flowchart illustrating a laboratory intelligent solution preparation control method based on the Internet of Things (IoT) according to an embodiment of the present invention. Figure 1 As shown, a laboratory intelligent liquid preparation control method based on the Internet of Things includes,

[0061] S1: Collect real-time passenger flow data, synchronize the real-time passenger flow data with train operation status data in time, and generate a hub status dataset including passenger flow density distribution and train location information.

[0062] S1.1: Deploy passenger flow density detection sensors, infrared counters, and video surveillance equipment at key nodes of the hub station.

[0063] It should be noted that the passenger flow density detection sensors are pressure-sensitive floor sensors, arranged in a 2m x 2m grid in areas such as platforms, passageways, and entrances / exits; infrared counters are installed on the top of each passageway / entrance / exit; and video surveillance equipment covers all passenger activity areas, forming a three-dimensional passenger flow data collection network.

[0064] Preferably, the personnel density values ​​in each grid area are obtained by a passenger flow density detection sensor and recorded as a passenger flow density matrix; the bidirectional passenger flow of each channel is obtained by an infrared counter and recorded as a channel flow vector; the personnel behavior trajectory is collected by a video monitoring device and generated as behavior trajectory data after being processed by an image recognition algorithm; the real-time passenger flow data includes the passenger flow density matrix, channel flow vector and behavior trajectory data.

[0065] S1.2: The position coordinates, speed, passenger capacity and direction of travel of each train are obtained through the on-board equipment of the automatic train control system and recorded as train state vectors; the arrival time, stopping time and departure time of each train at each station are obtained through the signal system and recorded as timetable data. Train operation status data includes train state vectors and timetable data.

[0066] S1.4: Set the time base for the hub system and use the GPS clock synchronization method to calibrate the timestamps of real-time passenger flow data and train operation status data to the system time base, thereby eliminating time deviations between subsystems.

[0067] S1.5: Resample the passenger flow density matrix, channel flow vector, behavior trajectory data, train status vector, and timetable data at the same time interval, setting the sampling interval to 1 second, and generate a time-synchronized data set.

[0068] S1.6: Based on the passenger flow density matrix and the channel flow vector, a spatial interpolation algorithm is used to calculate the passenger flow density distribution in each area of ​​the hub.

[0069] It should be noted that the passenger flow density distribution reflects the change in the number of people per square meter area over time.

[0070] S1.7: Extract the real-time position coordinates of each train from the train state vector, and combine them with the platform position information in the timetable data to generate train position information.

[0071] It should be noted that the train location information includes the train's precise location on the track and the platform section it is on.

[0072] S1.8: Associate passenger flow density distribution and train location information with timestamps to construct a hub status dataset containing passenger flow density distribution and train location information.

[0073] S2: Construct a multi-level simulation model to simulate the evolution of passenger flow distribution by pre-setting passenger evacuation behavior and train operation constraints.

[0074] S2.1: Based on the hub status dataset, establish a multi-level simulation model, which includes a passenger flow behavior simulation layer and a train scheduling simulation layer.

[0075] It should be noted that the multi-level simulation model adopts a layered coupling structure, including an upper passenger flow behavior simulation layer and a lower train dispatching simulation layer. The two layers interact with each other through a data interface. The passenger flow behavior simulation layer handles personnel movement and evacuation behavior, while the train dispatching simulation layer handles train operation and dispatching decisions.

[0076] S2.2: In the passenger flow behavior simulation layer, a passenger movement model based on cellular automata is constructed. The hub space is divided into cellular grids, and the passenger distribution state of the cellular grids is initialized according to the passenger flow density distribution to establish a passenger movement rule matrix.

[0077] It should be noted that the personnel movement rule matrix defines the probability of personnel moving in adjacent cell grids; the cell grid is a 1m × 1m cell grid, and each cell corresponds to a state value, 0 represents idle, 1 represents occupied by personnel, and 2 represents an obstacle.

[0078] S2.3: Construct an event-driven train operation model in the train scheduling simulation layer, and initialize the position and status of each train according to the train position information to establish a train operation event queue.

[0079] It should be noted that the train operation event queue includes train arrival events, stopping events, departure events, and section operation events. Each event includes event type, trigger time, train number, and related parameters.

[0080] S2.4: Establish a set of parameters for passenger flow evacuation behavior, a set of parameters for train operation constraints, and a set of parameters for emergency control strategies, and start a multi-level simulation model.

[0081] Preferably, the passenger flow evacuation behavior parameter set includes personnel movement speed, evacuation route selection weight, congestion avoidance coefficient, and emergency response factor; the train operation constraint set includes minimum departure interval, maximum operating speed, platform parking time, and passenger capacity limit; and the emergency control strategy parameter set includes train frequency increase strategy, platform flow restriction strategy, dynamic adjustment strategy for evacuation routes, and passenger flow guidance strategy.

[0082] Specifically, the range of personnel movement speed is set from 0.8 to 1.5 meters per second based on their age, physical condition, and psychological state; the minimum departure interval is set at 90 seconds according to the safety requirements of the signal system; the maximum operating speed is set at 80 kilometers per hour according to the line conditions; and the platform stopping time is dynamically adjusted according to passenger flow and boarding / alighting needs. The train frequency increase strategy increases capacity by shortening departure intervals; the platform flow control strategy avoids overcrowding by controlling the number of people entering the station; and the dynamic adjustment strategy for evacuation routes adjusts the evacuation direction according to real-time passenger flow conditions.

[0083] Furthermore, the passenger flow behavior simulation layer calculates the location of people at the next moment based on the passenger flow evacuation behavior parameter set and the current personnel distribution status; the train dispatching simulation layer calculates the train operation status based on the train operation constraint condition set and the emergency control strategy parameter set.

[0084] It should be noted that the passenger flow behavior simulation layer and the train dispatching simulation layer exchange passenger boarding and alighting data and train passenger information through an interface, and calculate in a loop according to a 1-second time step.

[0085] S2.5: Record the calculation results of the multi-level simulation model under different emergency control strategies, and generate passenger flow distribution evolution data.

[0086] It should be noted that the passenger flow distribution evolution data includes the spatial distribution of people at each time point, changes in passenger flow along each evacuation route, passenger flow concentration at each platform, and changes in train occupancy rates.

[0087] S3: Based on the output results of the multi-level simulation model, the bottleneck identification algorithm is used to locate the capacity-limiting nodes in each evacuation path, calculate the passenger flow carrying capacity of each evacuation path, and generate the optimal path control parameters with the goal of minimizing evacuation time.

[0088] S3.1: Extract the passenger flow distribution evolution matrix output by the multi-level simulation model, perform peak detection on the passenger flow density data of the passenger flow distribution evolution matrix, and identify the spatiotemporal coordinate points where passenger flow density is abnormally concentrated.

[0089] S3.2: Based on spatiotemporal coordinates, a bottleneck identification algorithm is used to traverse all evacuation paths within the hub to obtain capacity-limited nodes.

[0090] S3.2.1: Extract the spatial location information of spatiotemporal coordinate points and establish an evacuation path detection network within the hub.

[0091] Preferably, when the spatiotemporal coordinate point distribution density is greater than 2 points per square meter, dense detection nodes are set in this area; when the spatiotemporal coordinate points are sparsely distributed and the density is less than 0.5 points per square meter, detection nodes are set at standard intervals; when the spatiotemporal coordinate points are located in passageways, staircases, or entrances / exits, key detection nodes are forcibly set in these locations; key detection nodes are connected to adjacent detection nodes through paths to form an evacuation path detection network.

[0092] S3.2.2: Based on the evacuation path detection network, set the traversal start point and termination condition of the bottleneck identification algorithm, start the bottleneck identification algorithm, and start traversing from each starting node of the evacuation path detection network.

[0093] Specifically, when there are multiple entrance and exit nodes in the evacuation route detection network, all entrance and exit nodes are set as the traversal termination point; if the number of detection nodes in the evacuation route detection network exceeds 100, a partitioned parallel traversal strategy is adopted; if the distance between detection nodes is less than 5 meters, the traversal step size is set to 1 meter; if the distance between detection nodes is greater than 20 meters, intermediate detection points are inserted between nodes to improve traversal accuracy.

[0094] Furthermore, during the traversal, the ratio of real-time passenger flow to theoretical capacity is calculated for each detection node. If this ratio is greater than 0.8, the detection node is marked as a high-load node; if the ratio is between 0.7 and 0.8, it is marked as a medium-load node; and if the ratio is less than 0.7, it is marked as a low-load node. Simultaneously, the passenger dwell time at each detection node is calculated. If the dwell time exceeds twice the normal passage time, a congestion indicator is added to this detection node.

[0095] S3.2.3: Based on the load status and congestion indicators of the detection nodes, identify candidate nodes with capacity-limited characteristics, calculate the capacity-limited intensity index of the candidate nodes, and obtain the capacity-limited nodes.

[0096] Furthermore, if a detection node is marked as a high-load node and has a congestion indicator, then this detection node is included in the capacity limit candidate node list; if a detection node is a medium-load node but its three consecutive upstream nodes are all high-load nodes, then this detection node is included in the candidate node list; if the passenger backlog length of a candidate node exceeds 10 meters, then its priority in the candidate node list is increased.

[0097] Specifically, the capacity restriction intensity index comprehensively considers passenger flow throughput, the proportion of extended dwell time, and the size of the impact area. When the capacity restriction intensity index of a candidate node is greater than 0.8, the candidate node is confirmed as a severely restricted capacity node; if the capacity restriction intensity index is in the range of 0.5-0.8, it is confirmed as a moderately restricted capacity node; if the capacity restriction intensity index is in the range of 0.3-0.5, it is confirmed as a lightly restricted capacity node; if the capacity restriction intensity index is less than 0.3, the candidate node is removed from the list.

[0098] It should be noted that capacity-limited nodes include severely capacity-limited nodes, moderately capacity-limited nodes, and lightly capacity-limited nodes.

[0099] S3.3: Classify and label capacity-limited nodes, and obtain the physical geometric parameters and design capacity parameters of each type of capacity-limited node.

[0100] Furthermore, the spatial coordinate information of the capacity-limiting nodes is obtained, and they are initially classified according to their functional area location within the hub. If the capacity-limiting node is located in the platform area, it is classified as a platform-type capacity-limiting node; if the capacity-limiting node is located at the passageway connection, it is classified as a passageway-type capacity-limiting node; if the capacity-limiting node is located at the stairs, escalators, or lifting equipment, it is classified as a vertical transportation-type capacity-limiting node; if the capacity-limiting node is located in the entrance / exit gate area, it is classified as an entrance / exit-type capacity-limiting node; and if the capacity-limiting node is located in the transfer passageway, it is classified as a transfer-type capacity-limiting node.

[0101] Furthermore, the capacity-restricted nodes that have completed the initial classification are further subdivided based on their physical geometric characteristics. If the width of a platform-type capacity-restricted node is less than 3 meters, it is subdivided and marked as a narrow platform-type capacity-restricted node; if the net width of a passageway-type capacity-restricted node is less than 2 meters, it is subdivided and marked as a narrow passageway-type capacity-restricted node; if a vertical transportation-type capacity-restricted node is a one-way staircase and its width is less than 1.5 meters, it is subdivided and marked as a narrow staircase-type capacity-restricted node; if the number of turnstiles in an entrance / exit-type capacity-restricted node is less than 4, it is subdivided and marked as a few turnstile-type capacity-restricted node; if the transfer distance of a transfer-type capacity-restricted node exceeds 200 meters, it is subdivided and marked as a long-distance transfer-type capacity-restricted node.

[0102] Specifically, based on the classification and labeling results of capacity-limited nodes, the physical geometric parameters of each type of capacity-limited node are collected. If the capacity-limited node is a narrow platform type, its platform length, effective width, column spacing, and elevation difference parameters are obtained. If the capacity-limited node is a narrow passage type, its passage length, net width, net height, and corner radius parameters are obtained. If the capacity-limited node is a narrow stair type, its stair width, number of steps, slope angle, and rest platform area parameters are obtained. If the capacity-limited node is a type with few turnstiles, its number of turnstiles, turnstile width, buffer zone area, and queuing area length parameters are obtained. If the capacity-limited node is a long-distance transfer type, its transfer passage length, width variation, slope, and number of intermediate nodes parameters are obtained.

[0103] Furthermore, based on physical geometric parameters, the design throughput parameters for various types of capacity-restricted nodes are obtained in accordance with national standards and industry specifications. If the effective width of a narrow platform-type capacity-restricted node is within the range of 2-3 meters, its design throughput is set to 60-90 people per minute. If the net width of a narrow passage-type capacity-restricted node is within the range of 1.5-2 meters, its design throughput is set to 45-70 people per minute. If a narrow staircase-type capacity-restricted node is in the upward direction, its design throughput is calculated as 0.8 times the downward capacity. If a capacity-restricted node with few turnstiles is equipped with automatic turnstiles, the design throughput of a single turnstile is 25-30 people per minute. If a long-distance transfer-type capacity-restricted node includes a ramp, its design throughput needs to be corrected according to the slope; for every 1% increase in slope, the throughput decreases by 3%.

[0104] S3.4: Based on physical geometric parameters and design capacity parameters, and combined with the passenger flow density change trend in the passenger flow distribution evolution matrix, calculate the dynamic capacity correction coefficient of the capacity-limited node at different time periods.

[0105] S3.5: Based on the dynamic capacity correction coefficient, the minimum cut algorithm is used to calculate the passenger flow carrying capacity of the evacuation path of each capacity-limited node;

[0106] It should be noted that passenger flow carrying capacity indicates the maximum number of passengers that can be safely evacuated via this evacuation route per unit time.

[0107] The preferred formula for passenger flow carrying capacity is as follows:

[0108]

[0109] Among them, Λ capacity C represents the passenger flow carrying capacity value. base The basic carrying capacity value, Q is the capacity-limited number of nodes, and R is the basic carrying capacity value. m R represents the congestion level of the m-th capacity-limited node. max To achieve the maximum permissible level of congestion, λ m Let S be the influence coefficient of the m-th node, S be the number of evacuation path segments, and D be the influence coefficient of the m-th node. n Let D be the passenger flow density of the nth route segment. threshold This is the density threshold.

[0110] Furthermore, when the passenger flow carrying capacity value is close to the basic carrying capacity value, it indicates that the carrying capacity of the evacuation routes has reached its theoretical maximum value and all capacity-limiting nodes are operating well; when the passenger flow carrying capacity value is within 0.8 of the basic carrying capacity value, it indicates that the carrying capacity is excellent and the evacuation efficiency is high; when the passenger flow carrying capacity value is between 0.8 and 0.4 of the basic carrying capacity value, it indicates that the carrying capacity is moderate and there are certain bottlenecks; when the passenger flow carrying capacity value is close to zero, it indicates that the carrying capacity of the evacuation routes is seriously insufficient and emergency control measures are required.

[0111] S3.6: With the shortest evacuation time as the objective function and passenger flow carrying capacity as the constraint, a linear programming model is established, and the simplex method is used to solve for the passenger flow allocation ratio and the corresponding train departure interval parameters for each evacuation route.

[0112] S3.7: Based on the train departure interval parameters and the passenger flow carrying capacity of each line, a greedy algorithm is used to determine the open status parameters of each platform.

[0113] It should be noted that the platform opening status parameters include the opening time period and the opening direction.

[0114] S3.8: Combine train departure interval parameters and platform open status parameters to generate optimal route control parameters.

[0115] It should be noted that the optimal route control parameters and the passenger flow carrying capacity of each evacuation route form a one-to-one set of control strategies.

[0116] S4: Convert the optimal path control parameters into train automatic control system commands and passenger flow guidance display commands, and send them to the control units of each line through the hub centralized dispatching system to adjust the train operation frequency and passenger flow evacuation direction.

[0117] S4.1: Analyze the train departure interval parameters and platform open status parameters of the optimal path control parameters, and convert the train departure interval parameters into train automatic control system instructions containing departure time, target interval and execution period according to the communication protocol format of each line control unit.

[0118] It should be noted that the train automatic control system commands include departure time, target interval, and execution period.

[0119] Preferably, the optimal train departure intervals are categorized and organized according to line number to generate a departure interval parameter table for each line; the optimal platform opening status is categorized and organized according to platform number to generate a platform opening status control table; the platform opening status control table records the opening time period and the number of people allowed at each platform.

[0120] S4.2: Encode the platform opening status parameters according to the platform number and opening direction to generate passenger flow guidance display instructions.

[0121] It should be noted that the passenger flow guidance display instructions include the display content, display location, and display duration; the passenger flow guidance display instructions adopt a unified LED display control protocol format.

[0122] S4.3: Conflict detection is performed on the train automatic control system commands and passenger flow guidance display commands. A timing logic check algorithm is used to identify command combinations that cause conflicts in passenger evacuation paths, and time offset adjustments are made to conflicting commands.

[0123] Prioritize that when the same platform receives conflicting platform open status parameters simultaneously within the same time window, the timing logic check algorithm identifies it as a combination of path conflict instructions and marks it as a high-priority conflict event. When the departure time of the train automatic control system instruction conflicts with the current platform's preset minimum safety interval, it is determined to be a scheduling instruction conflict, and the system suspends the issuance of this instruction and requests updated scheduling parameters. When the LED display device receives passenger flow guidance instructions from multiple directions simultaneously, and the guided channels have intersecting or merging relationships, the path conflict check mechanism is triggered, and the scheduling system determines the primary guidance direction and adjusts the time offset of the secondary direction display instructions.

[0124] S4.4: Based on the priority level of each line control unit, the adjusted train automatic control system commands are divided into high-priority commands and ordinary-priority commands according to their urgency, and a hierarchical issuance queue is established.

[0125] S4.5: The train automatic control system commands are sent to the corresponding line control units through the communication network of the hub centralized dispatching system, according to the priority order of the hierarchical dispatching queue, and the command dispatch timestamp and target unit identifier are recorded at the same time.

[0126] S4.6: Passenger flow guidance display instructions are sent to the LED display equipment of each platform and passageway through the hub centralized dispatch system.

[0127] It should be noted that the displayed content is adjusted to guide passenger flow in the evacuation direction determined by the optimal path control parameters.

[0128] S4.7: Adjust the train operation frequency according to the train departure interval parameters and feed back the instruction execution status to the hub centralized dispatching system.

[0129] S4.8: Establish an instruction execution monitoring mechanism. By comparing the instruction issuance timestamp with the execution feedback time, calculate the instruction transmission delay and execution effect deviation, and form feedback data for the next round of optimal path control parameter optimization.

[0130] In summary, this invention establishes a high-precision hub status dataset by synchronizing real-time passenger flow data with train operation status, solving the problems of poor data timeliness and data asynchrony between different systems in traditional methods. It employs a layered, coupled, multi-level simulation model, accurately simulating passenger flow behavior through cellular automata, combined with an event-driven train operation model, to achieve dynamic interactive simulation of passenger evacuation and train scheduling, overcoming the shortcomings of isolated models and poor coordination in existing technologies. In the dynamic optimization stage, a bottleneck identification algorithm based on spatiotemporal coordinates, combined with a dynamic capacity correction coefficient, achieves accurate location and dynamic evaluation of capacity-limited nodes on evacuation paths. Then, the minimum cut algorithm and linear programming model generate optimal path control parameters, significantly improving the timeliness and feasibility of the evacuation plan. Through an instruction conflict detection mechanism and a hierarchical issuance strategy, the safe and reliable execution of control instructions is ensured, while an execution feedback mechanism is established to form an optimization closed loop.

[0131] Furthermore, this embodiment also provides an emergency control system for rail transit hubs based on real-time simulation, including:

[0132] The data acquisition module is used to collect real-time passenger flow data, synchronize the real-time passenger flow data with train operation status data in time, and generate a hub status dataset that includes passenger flow density distribution and train location information.

[0133] The simulation module is used to build multi-level simulation models and simulate the evolution of passenger flow distribution by pre-setting passenger flow evacuation behavior and train operation constraints.

[0134] The calculation module, based on the output of the multi-level simulation model, uses a bottleneck identification algorithm to locate the capacity-limiting nodes in each evacuation route, calculates the passenger flow carrying capacity of each evacuation route, and generates the optimal route control parameters with the goal of minimizing evacuation time.

[0135] The conversion and adjustment module is used to convert the optimal route control parameters into train automatic control system commands and passenger flow guidance display commands, which are then sent to the control units of each line through the hub centralized dispatching system to adjust the train operation frequency and passenger flow evacuation direction.

[0136] This embodiment also provides a computer device applicable to the emergency control method for rail transit hubs based on real-time simulation, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the emergency control method for rail transit hubs based on real-time simulation as proposed in the above embodiment.

[0137] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0138] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for emergency control of rail transit hubs based on real-time simulation, characterized in that, include: Collect real-time passenger flow data, synchronize the real-time passenger flow data with train operation status data in time, and generate a hub status dataset including passenger flow density distribution and train location information; A multi-level simulation model was constructed to simulate the evolution of passenger flow distribution by pre-setting passenger flow evacuation behavior and train operation constraints. Based on the output of the multi-level simulation model, the bottleneck identification algorithm is used to locate the capacity-limiting nodes in each evacuation route, calculate the passenger flow carrying capacity of each evacuation route, and generate the optimal route control parameters with the goal of minimizing evacuation time. The optimal route control parameters are converted into train automatic control system commands and passenger flow guidance display commands, which are then sent to the control units of each line through the hub centralized dispatching system to adjust the train operation frequency and passenger flow evacuation direction. Extract the passenger flow distribution evolution matrix output by the multi-level simulation model, perform peak detection on the passenger flow density data of the passenger flow distribution evolution matrix, and identify the spatiotemporal coordinate points where passenger flow density is abnormally concentrated; Based on the aforementioned spatiotemporal coordinates, a bottleneck identification algorithm is used to traverse all evacuation paths within the hub to obtain capacity-limited nodes. The capacity-limited nodes are classified and labeled, and the physical geometric parameters and design capacity parameters of each type of capacity-limited node are obtained; Based on the physical geometric parameters and design capacity parameters, and combined with the passenger flow density change trend in the passenger flow distribution evolution matrix, the dynamic capacity correction coefficient of the capacity-limited node in different time periods is calculated. Based on the dynamic capacity correction coefficient, the minimum cut algorithm is used to calculate the passenger flow carrying capacity of the evacuation path where each capacity-limited node is located. With the shortest evacuation time as the objective function and the passenger flow carrying capacity as the constraint, a linear programming model is established, and the simplex method is used to solve for the passenger flow allocation ratio and the corresponding train departure interval parameters for each evacuation route. Based on the train departure interval parameters and the passenger flow capacity of each line, a greedy algorithm is used to determine the opening status parameters of each platform. The optimal route control parameters are generated by combining the train departure interval parameters and platform open status parameters.

2. The emergency control method for rail transit hubs based on real-time simulation as described in claim 1, characterized in that: A multi-level simulation model is constructed to simulate the evolution of passenger flow distribution by pre-setting passenger evacuation behaviors and train operation constraints, including: Based on the hub status dataset, a multi-level simulation model is established, which includes a passenger flow behavior simulation layer and a train scheduling simulation layer. In the passenger flow behavior simulation layer, a passenger movement model based on cellular automata is constructed. The hub space is divided into cellular grids, and the passenger distribution state of the cellular grids is initialized according to the passenger flow density distribution to establish a passenger movement rule matrix. In the train scheduling simulation layer, an event-driven train operation model is constructed, and the position and status of each train are initialized according to the train position information to establish a train operation event queue; Establish a set of passenger flow evacuation behavior parameters, a set of train operation constraints, and a set of emergency control strategy parameters, and then start the multi-level simulation model. Record the calculation results of the multi-level simulation model under different emergency control strategies to generate passenger flow distribution evolution data.

3. The emergency control method for rail transit hubs based on real-time simulation as described in claim 2, characterized in that: The multi-level simulation model adopts a layered coupling structure; the passenger flow behavior simulation layer calculates the location of people at the next moment based on the passenger flow evacuation behavior parameter set and the current personnel distribution status; the train scheduling simulation layer calculates the train operation status based on the train operation constraint set and the emergency control strategy parameter set.

4. The emergency control method for rail transit hubs based on real-time simulation as described in claim 1, characterized in that: Based on the aforementioned spatiotemporal coordinates, a bottleneck identification algorithm is used to traverse all evacuation paths within the hub to obtain capacity-limited nodes, including: Extract the spatial location information of spatiotemporal coordinate points and establish an evacuation route detection network within the hub; Based on the evacuation path detection network, the starting point and termination condition of the bottleneck identification algorithm are set, and the bottleneck identification algorithm is started to traverse from each starting node of the evacuation path detection network. Based on the load status and congestion indicators of the detection nodes, candidate nodes with capacity-limited characteristics are identified, and the capacity-limited intensity index of the candidate nodes is calculated to obtain the capacity-limited nodes.

5. The emergency control method for rail transit hubs based on real-time simulation as described in claim 4, characterized in that: The optimal route control parameters are converted into train automatic control system commands and passenger flow guidance display commands, which are then distributed to the control units of each line through the hub centralized dispatching system to adjust train operation frequency and passenger flow evacuation direction, including: The train departure interval parameters and platform open status parameters of the optimal path control parameters are analyzed, and the train departure interval parameters are converted into train automatic control system instructions containing departure time, target interval and execution period according to the communication protocol format of each line control unit. The platform opening status parameters are encoded according to the platform number and opening direction to generate passenger flow guidance display instructions; Conflict detection is performed on the train automatic control system commands and the passenger flow guidance display commands. A timing logic check algorithm is used to identify command combinations that cause conflicts in passenger evacuation paths, and time offset adjustments are made to the conflicting commands. Based on the priority level of each line control unit, the adjusted train automatic control system commands are divided into high-priority commands and ordinary-priority commands according to their urgency, and a hierarchical issuance queue is established. The train automatic control system commands are sent to the corresponding line control units through the communication network of the hub centralized dispatch system, according to the priority order of the hierarchical dispatch queue, and the command dispatch timestamp and target unit identifier are recorded at the same time. The passenger flow guidance display instructions are sent to the LED display devices of each platform and passageway through the hub centralized dispatch system; Adjust the train operation frequency according to the train departure interval parameters and feed back the instruction execution status to the hub centralized dispatching system; Establish an instruction execution monitoring mechanism. By comparing the instruction issuance timestamp with the execution feedback time, calculate the instruction transmission delay and execution effect deviation, and generate feedback data for the next round of optimal path control parameter optimization.

6. The emergency control method for rail transit hubs based on real-time simulation as described in claim 5, characterized in that: A timing logic check algorithm is used to identify instruction combinations that cause conflicts in passenger evacuation routes, including: When the same station receives conflicting station open status parameters simultaneously within the same time window, it is identified as a combination of path conflict instructions by the timing logic check algorithm and marked as a high-priority conflict event. When the departure time commanded by the automatic train control system conflicts with the current platform's preset minimum safety interval, it is determined to be a scheduling command conflict. The system then suspends the issuance of this command and requests updated scheduling parameters. When the LED display device receives passenger flow guidance instructions from multiple directions at the same time, and the guided channels have intersecting or merging relationships, the path conflict check mechanism is triggered, and the scheduling system determines the primary guidance direction and adjusts the time offset of the display instructions for the secondary directions.

7. A real-time simulation-based emergency control system for rail transit hubs, based on the real-time simulation-based emergency control method for rail transit hubs as described in any one of claims 1 to 6, characterized in that, include: The data acquisition module is used to collect real-time passenger flow data, synchronize the real-time passenger flow data with train operation status data in time, and generate a hub status dataset including passenger flow density distribution and train location information. The simulation module is used to build multi-level simulation models and simulate the evolution of passenger flow distribution by pre-setting passenger flow evacuation behavior and train operation constraints. The calculation module, based on the output of the multi-level simulation model, uses a bottleneck identification algorithm to locate the capacity-limiting nodes in each evacuation path, calculates the passenger flow carrying capacity of each evacuation path, and generates the optimal path control parameters with the goal of minimizing evacuation time. The conversion and adjustment module is used to convert the optimal path control parameters into train automatic control system instructions and passenger flow guidance display instructions, which are then sent to the control units of each line through the hub centralized dispatching system to adjust the train operation frequency and passenger flow evacuation direction.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the emergency control method for rail transit hubs based on real-time simulation as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the emergency control method for rail transit hubs based on real-time simulation as described in any one of claims 1 to 6.

Images