A rail transit passenger flow safety monitoring management method and system

Abstract

The invention discloses a rail transit passenger flow safety monitoring and management method and system, which specifically relates to the field of rail transit safety management, including: real-time measurement of passenger flow crowd data, generating a two-dimensional plane density heat map; analyzing the two-dimensional plane density heat map, judging whether a sudden drop occurs in the crowd distribution entropy in the waiting platform area; marking the crowded units in the monitoring unit, and establishing a combination field of speed and density of the crowded units; establishing an extrusion force distribution model, and calculating the extrusion force in each crowded unit according to the real-time speed gradient and density gradient of adjacent units in the combination field; calculating the overall longitudinal extrusion force of the crowded unit, and judging whether there is a risk of a pushing effect in the longitudinal extrusion force; after a warning line control module receives a high-risk signal of a pushing effect, calculating the theoretical sliding distance of people in the crowded unit under the action of the pushing force, and dynamically adjusting the position of the warning line.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit safety management, and more specifically, to a rail transit passenger flow safety monitoring and management method and system. Background Art

[0002] In the crowded scenes of rail transit platforms, the location control of the cordon is an important part of ensuring passenger safety. However, with the continuous increase in the passenger flow of rail transit, especially during peak hours or emergencies, the platform area is prone to form local high-density crowded areas, resulting in the occurrence of a crowding effect. The location setting of traditional fixed cordons is often based on experience-based design, which makes it difficult to respond to the dynamic changes in passenger flow in real time. Especially in emergencies, the cordon may not be adjusted in time to avoid safety hazards caused by excessive crowding. The crowding effect of high-density passenger flow will not only significantly increase the squeezing force in local areas, but may also cause safety hazards such as people falling, sliding, or even falling off the platform.

[0003] In addition, even in the case of variable cordon lines (such as warning belts), the adjustment of cordon lines is mostly done by staff through visual inference of crowd distribution and density, relying on manual decision-making and intervention, and requiring personnel to perform operations on site. This not only increases the response time, but may also lead to escalated risks due to human misjudgment or delayed action. Therefore, how to realize an intelligent dynamic cordon management method based on automatic passenger flow monitoring is an urgent problem to be solved.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a rail transit passenger flow safety monitoring and management method to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] S1: Set up a dynamic passenger flow sensor array at the rail transit station platform to measure passenger flow data in real time and generate a two-dimensional plane density heat map;

[0008] S2: Analyze the two-dimensional plane density heat map to determine whether the crowd distribution entropy in the waiting platform area has dropped suddenly. If so, send a crowd distribution entropy drop signal to the central processing module;

[0009] S3: When the central processing module receives a signal of a sudden drop in crowd distribution entropy, it marks the crowded units in the monitoring unit and establishes a combined field of speed and density of the crowded units;

[0010] S4: Establish a squeezing force distribution model, and calculate the squeezing force in each crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field;

[0011] S5: Calculate the overall longitudinal squeezing force of the crowded unit, determine whether the longitudinal squeezing force has a risk of a pushing effect, and if so, send a high risk signal of a pushing effect;

[0012] S6: After receiving the high-risk signal of the pushing effect, the warning line control module calculates the theoretical sliding distance of the people in the crowded unit under the action of the pushing force and dynamically adjusts the position of the warning line.

[0013] In a preferred embodiment, in S1, a dynamic passenger flow sensing device array is set at the rail transit station platform to measure passenger flow crowd data in real time, and generating a two-dimensional plane density heat map specifically includes:

[0014] Use laser scanning equipment to accurately measure the rail transit platform area and form a three-dimensional model of the platform monitoring area;

[0015] The monitoring area is divided into two-dimensional monitoring units according to the three-dimensional model layout of the platform area, and dynamic passenger flow sensing devices are arranged in an array form based on the distribution of the monitoring units;

[0016] An initial collection frequency is set for the sensor array. The sensor array collects passenger flow data in the waiting platform area at the set initial collection frequency. The passenger flow data includes individual positions, number of individuals in the crowd, and speed of individuals in the crowd in each monitoring unit. The passenger flow data is uploaded to the central processing module in real time through the edge computing device.

[0017] The central processing module performs denoising on the passenger flow data uploaded by the edge computing device, and calculates and updates the crowd density speed of each monitoring unit in real time based on the denoised data;

[0018] The crowd density data is divided into different density levels, and the corresponding color is marked according to the density level of each monitoring unit. At the same time, the interpolation algorithm is used to smooth the density changes between adjacent monitoring units;

[0019] A visual two-dimensional heat map is generated and updated in real time based on the same update frequency as the data collection frequency of each monitoring unit, which is marked as a two-dimensional plane density heat map.

[0020] In a preferred embodiment, analyzing the two-dimensional plane density heat map to determine whether the crowd distribution entropy in the waiting platform area has dropped suddenly, and if so, sending a crowd distribution entropy drop signal to the central processing module specifically includes:

[0021] Set the crowd distribution trend monitoring time window T, and the central processing module will integrate and time-series-mark the passenger flow data uploaded by all monitoring units within the monitoring time window T;

[0022] Obtain a set of passenger flow crowd data of monitoring units with the same time series mark, and calculate the time series density probability of each monitoring unit according to the proportion of the crowd density of each monitoring unit in the set to the total crowd density;

[0023] Based on the time series density probability of each monitoring unit and the distribution entropy calculation formula, the change of the crowd time series distribution entropy of the two-dimensional plane density heat map is calculated. The distribution entropy calculation formula is:

[0024] ;

[0025] In the formula, is the crowd distribution entropy in the waiting platform area at the tth monitoring time point within the dynamic monitoring time window T, is the density probability of the ith monitoring unit at the tth monitoring time point, is the total number of divided monitoring units;

[0026] Analyze the change of time series distribution entropy within the monitoring time window T. When the distribution entropy continues to decrease within the monitoring time window T and the overall decrease exceeds the set sudden drop threshold, send a distribution entropy sudden drop signal to the central processing module.

[0027] In a preferred embodiment, in S3, when the central processing module receives a signal indicating a sudden drop in crowd distribution entropy, marking the crowded units in the monitoring unit, and establishing a combined field of speed and density of the crowded units specifically includes:

[0028] The crowding density of the monitoring unit is set. When the central processing module receives a signal of a sudden drop in crowd distribution entropy, it selects all monitoring units in the two-dimensional density heat map whose marked colors correspond to density levels above the set crowding density and marks them as crowded units.

[0029] Reset the frequency of collecting passenger flow data of the sensor array in the crowded unit, collect passenger flow data in real time, and calculate the real-time density and speed of the crowd in the crowded unit;

[0030] A two-dimensional density field is formed based on the time series density changes of all crowded units. At the same time, a two-dimensional velocity field is formed according to the individual speed and position changes of the crowd. The two-dimensional density field and the two-dimensional velocity field are superimposed into a combined field. The position information of each crowded unit in the combined field is expressed in two-dimensional coordinates. express.

[0031] In a preferred embodiment, the squeezing force distribution model is established, and the squeezing force in each crowded unit is calculated according to the real-time velocity gradient and density gradient of adjacent units in the combined field, specifically including:

[0032] Based on the density changes and speed changes of adjacent crowded units in the combined field, the crowd density gradient and speed gradient are calculated for all crowded units;

[0033] The squeezing force distribution model is established based on crowd dynamics. The density gradient and velocity gradient are introduced into the squeezing force distribution model to calculate the squeezing force of each crowded unit. The squeezing force distribution model expression is:

[0034] ;

[0035] In the formula, is the two-dimensional coordinate position The squeezing force of the crowded unit, , They are the two-dimensional coordinate positions The density gradient and velocity gradient, , , They are the influence coefficients of the set density gradient, velocity gradient and the coupling effect of velocity and density gradient on the extrusion pressure.

[0036] In a preferred embodiment, calculating the overall longitudinal squeezing force of the crowded unit and determining whether the longitudinal squeezing force has a risk of a squeezing effect, and if so, sending a high risk signal of a squeezing effect specifically includes:

[0037] The squeezing force of the crowded unit is evaluated as a whole, and the total pressure component of the time-series crowd squeezing force with a set time step perpendicular to the platform cordon direction is calculated, which is marked as the time-series longitudinal squeezing force;

[0038] The minimum squeezing force for the crowd to maintain balance is set. When the longitudinal squeezing force is greater than the minimum balanced squeezing force, it is judged that there is a risk of a pushing effect, and a high-risk signal of a pushing effect is sent to the warning line control module.

[0039] In a preferred embodiment, after receiving the high risk signal of the pushing effect, the warning line control module calculates the theoretical sliding distance of the person in the crowded unit under the pushing force, and dynamically adjusts the position of the warning line specifically including:

[0040] After receiving the high risk signal of the pushing effect, the warning line control module sets the waiting warning line control cycle;

[0041] Calculate the theoretical maximum longitudinal sliding distance of the personnel in the crowded unit closest to the edge of the cordon under the longitudinal pushing force during the cordon control cycle, and move the cordon forward an equal distance away from the edge of the platform through the dynamic warning indicator light according to the sliding distance;

[0042] Continue to dynamically adjust the waiting warning line until the high-risk signal of the pushing effect in the warning line control module disappears and the adjustment is completed.

[0043] On the other hand, the present invention provides a rail transit passenger flow safety monitoring and management system, including a parameter acquisition module, a central processing module, an extrusion force calculation module, and a warning line control module:

[0044] Parameter collection module: An array of dynamic passenger flow sensing devices is set up at the rail transit station platform. Based on the dynamic setting of data collection frequency, passenger flow crowd data is measured in real time and uploaded to the central processing module;

[0045] Central processing module: denoises the passenger flow data uploaded by the edge computing device, and monitors whether the crowd distribution entropy in the waiting platform area has dropped suddenly;

[0046] Extrusion force calculation module: establishes an extrusion force distribution model, and calculates the extrusion force in each crowded unit and the overall longitudinal extrusion force of the crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field;

[0047] Warning line control module: After receiving the high-risk signal of the pushing effect, it calculates the theoretical sliding distance of the people in the crowded unit under the action of the pushing force, and dynamically adjusts the position of the warning line.

[0048] The technical effects and advantages of a rail transit passenger flow safety monitoring and management method and system of the present invention are as follows:

[0049] By deploying an array of dynamic passenger flow sensing devices at the waiting platform, the distribution status of the crowd on the platform can be captured in real time, and a density heat map can be generated to accurately reflect the crowd's aggregation characteristics and dynamic change trends. When the crowd distribution entropy in the platform area drops suddenly, it often indicates that a significant density aggregation has occurred in the local area, which may be accompanied by the generation of uneven flow, forming a hidden danger of high-density pushing effect. By calculating the squeezing force distribution and longitudinal squeezing force of the crowded unit, the risk level of the pushing effect can be further determined, and the position of the platform cordon can be dynamically adjusted to provide a scientific basis for crowd evacuation and risk control. The above technical solution can significantly improve the safety monitoring and emergency response capabilities of rail transit platforms, and provide strong support for the intelligent management of modern transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a rail transit passenger flow safety monitoring and management method of the present invention;

[0051] Figure 2 It is a structural schematic diagram of a rail transit passenger flow safety monitoring and management system of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0053] Figure 1 The present invention provides a rail transit passenger flow safety monitoring and management method, which includes the following steps:

[0054] S1: Set up a dynamic passenger flow sensor array at the rail transit station platform to measure passenger flow data in real time and generate a two-dimensional plane density heat map;

[0055] S2: Analyze the two-dimensional plane density heat map to determine whether the crowd distribution entropy in the waiting platform area has dropped suddenly. If so, send a crowd distribution entropy drop signal to the central processing module;

[0056] S3: When the central processing module receives a signal of a sudden drop in crowd distribution entropy, it marks the crowded units in the monitoring unit and establishes a combined field of speed and density of the crowded units;

[0057] S4: Establish a squeezing force distribution model, and calculate the squeezing force in each crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field;

[0058] S5: Calculate the overall longitudinal squeezing force of the crowded unit, determine whether the longitudinal squeezing force has a risk of a pushing effect, and if so, send a high risk signal of a pushing effect;

[0059] S6: After receiving the high-risk signal of the pushing effect, the warning line control module calculates the theoretical sliding distance of the people in the crowded unit under the action of the pushing force and dynamically adjusts the position of the warning line.

[0060] In S1, a dynamic passenger flow sensing device array is set up at the rail transit station platform to measure passenger flow data in real time and generate a two-dimensional plane density heat map.

[0061] High-precision laser scanners are deployed in the waiting platform area to cover the entire monitoring range. The laser scanner captures the spatial layout and structural characteristics of the platform through point cloud data, including the length, width, and obstacle locations of the platform. Point cloud data processing software (such as ReCap or CloudCompare) is used to clean and model the data, generate a complete 3D model of the waiting platform, and mark the key areas of the platform (such as waiting areas, passages, edge areas, etc.).

[0062] Based on the plane projection of the three-dimensional model, the platform monitoring area is divided into several two-dimensional monitoring units. The unit size can be adjusted according to the density requirements of the platform (such as 0.5m×0.5m per unit). Dynamic passenger flow sensing devices (such as infrared sensors, millimeter wave radars or video analysis equipment) are deployed in the center or corner of each monitoring unit to form a regular array layout.

[0063] Set an initial collection frequency (such as 2Hz, which can be flexibly set according to the equipment and system processing performance) for the sensor array. The sensor array collects passenger flow data in the waiting platform area at the set initial collection frequency to ensure that all devices collect passenger flow data synchronously. Passenger flow data includes the individual position of the crowd in each monitoring unit (the real-time position of the individual in the monitoring unit), the number of individuals in the crowd (the total number of individuals in the monitoring unit), and the speed of the individuals in the crowd (the speed of all individuals in the monitoring unit). The sensor performs preliminary calculations on the raw data (such as position normalization and quantity statistics), and transmits the processed data to the central processing module in real time through the edge computing device.

[0064] The central processing module denoises the passenger flow data uploaded by the edge computing device, removes abnormal data points that may be caused by equipment errors or environmental interference, and calculates and updates the crowd density speed of each monitoring unit in real time based on the denoised data.

[0065] The density is divided into multiple levels (such as low, medium, high, and extremely high) according to the preset threshold, and a corresponding color (such as green, yellow, red, and dark red) is assigned to each level. At the same time, an interpolation algorithm is used to smooth the density changes between adjacent monitoring units to reduce the jumps between monitoring units.

[0066] The density matrix is ​​mapped to a color matrix and colored according to the density level. A visual two-dimensional heat map is generated and updated in real time based on the same update frequency of the data collection frequency of each monitoring unit, which is marked as a two-dimensional plane density heat map.

[0067] In S2, the two-dimensional plane density heat map is analyzed to determine whether the crowd distribution entropy in the waiting platform area has dropped suddenly. If so, a crowd distribution entropy drop signal is sent to the central processing module.

[0068] Set the crowd distribution trend monitoring time window T (the default setting is 30s), and the central processing module will integrate and time-series-mark the passenger flow data uploaded by all monitoring units within the monitoring time window T.

[0069] When the color coverage area of ​​high crowd density in the two-dimensional density heat map exceeds the set proportion of the entire map (such as 50%), obtain the passenger flow crowd data set of the monitoring unit with the same time series mark, and calculate the time series density probability of each monitoring unit according to the proportion of the crowd density of each monitoring unit in the set to the total crowd density.

[0070] Based on the time series density probability of each monitoring unit and the distribution entropy calculation formula, the change of the crowd time series distribution entropy of the two-dimensional plane density heat map is calculated. The distribution entropy calculation formula is:

[0071] ;

[0072] In the formula, is the crowd distribution entropy in the waiting platform area at the tth monitoring time point within the dynamic monitoring time window T, is the density probability of the ith monitoring unit at the tth monitoring time point, is the total number of divided monitoring units.

[0073] Analyze the changes in the time series distribution entropy within the monitoring time window T. When the distribution entropy continues to decrease within the monitoring time window T, and the overall decrease exceeds the set sudden drop threshold, it often indicates that significant density aggregation has occurred in the local area, corresponding to the scenario where the train is about to enter the station and prompts passengers to queue or rush into the channel. At this time, a distribution entropy sudden drop signal is sent to the central processing module.

[0074] In S3, when the central processing module receives a signal of a sudden drop in crowd distribution entropy, it marks the crowded units in the monitoring unit and establishes a combined field of speed and density of the crowded units.

[0075] The crowding density of the monitoring unit is set (less than 5.4 people / square meter. Studies have shown that the crowd speed will drop to zero when the crowd density reaches 5.4 people / square meter). When the central processing module receives a signal of a sudden drop in crowd distribution entropy, it selects all monitoring units in the two-dimensional density heat map whose marked colors correspond to density levels above the set crowding density and marks them as crowded units.

[0076] For the sensing devices marked as crowded units, the data collection frequency is increased (for example, from the original 2 Hz to 5 Hz), passenger flow data is collected in real time, and the real-time density and speed of the crowd in the crowded unit are calculated.

[0077] A two-dimensional density field is formed based on the time series density changes of all crowded units. At the same time, a two-dimensional velocity field is formed according to the individual speed and position changes of the crowd. The two-dimensional density field and the two-dimensional velocity field are superimposed into a combined field. The position information of each crowded unit in the combined field is expressed in two-dimensional coordinates. It means that in the combined field, each crowded unit contains its density value and velocity vector (with the center of the crowded unit as the origin, all velocity vectors are decomposed into x and y directions, and the velocity is the average value of the sum of the velocities of all individuals in the monitoring unit).

[0078] In S4, a squeezing force distribution model is established to calculate the squeezing force in each crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field.

[0079] Based on the density change and speed change of adjacent crowded units in the combined field, the crowd density gradient and speed gradient are calculated for all crowded units. The calculation methods are as follows: as well as ,in , are the velocity components in the x and y directions respectively, for Abbreviation for position coordinates Density value, , They are the two-dimensional coordinate positions density gradient and velocity gradient.

[0080] The squeezing force distribution model is established based on crowd dynamics. In high-density areas, crowd behavior exhibits the following characteristics:

[0081] , that is, the extrusion pressure is positively correlated with the local density (the higher the density, the greater the extrusion pressure);

[0082] , that is, the velocity gradient describes the rate of change of the local velocity field. The larger the gradient, the more unstable the flow of the crowd and the more significant the squeezing force.

[0083] , that is, the density gradient reflects the drastic change in the local population density distribution. The greater the density difference, the stronger the squeezing force;

[0084] The density gradient and velocity gradient are introduced into the extrusion force distribution model to calculate the extrusion force of each crowded unit. The extrusion force distribution model expression is:

[0085] ;

[0086] In the formula, is the two-dimensional coordinate position The squeezing force of the crowded unit, , , The influence coefficients of the set density gradient, velocity gradient and the coupling of velocity and density gradient on the extrusion force are respectively used to balance the contribution of velocity gradient, density gradient and the coupling of the two to the extrusion force. The distribution data of historical crowd pressure, density and velocity gradient are collected through scene experiments for linear regression analysis, and comprehensive settings are made based on the analysis results.

[0087] In S5, the overall longitudinal squeezing force of the crowded unit is calculated to determine whether there is a risk of a pushing effect in the longitudinal squeezing force. If so, a high risk signal of a pushing effect is sent.

[0088] All non-connected crowded units are partitioned, with the platform cordon as a reference, and the direction perpendicular to the cordon is defined as the longitudinal direction. In each crowded unit, the time-series squeeze force vector The components are decomposed into longitudinal components , ,in, is the set time step of the series, For every time you pass The angle between the extrusion force vector and the longitudinal direction after the time length is calculated, and the magnitude of the longitudinal component of the extrusion force is marked as the temporal longitudinal extrusion force.

[0089] The minimum squeezing force for a crowd to maintain balance is set based on experiments or actual experience. When the longitudinal squeezing force is greater than the minimum balanced squeezing force, it is judged that there is a risk of a pushing effect, and a high-risk signal of a pushing effect is sent to the warning line control module.

[0090] In S6, after receiving the high-risk signal of the pushing effect, the warning line control module calculates the theoretical sliding distance of the people in the crowded unit under the action of the pushing force and dynamically adjusts the position of the warning line.

[0091] After the warning line control module receives the high risk signal of the pushing effect, it sets the waiting warning line control cycle .

[0092] Calculate the theoretical maximum longitudinal sliding distance of the personnel in the crowded unit closest to the edge of the cordon during the cordon control cycle under the longitudinal pushing force. The adjustment is terminated after the high risk signal of the pushing effect in the cordon control module disappears.

[0093] For people in edge crowded units, the expression for calculating the longitudinal pushing force is: , where is the set time step of the series, For every time you pass The longitudinal pushing force calculated after the time, is the area of ​​the crowded unit closest to the edge of the cordon, based on the control cycle Each time step corresponds to Calculate the average value within the control cycle, and use the result express.

[0094] Get the friction coefficient of the platform ground , and set the individual calculation reference mass m, and calculate the sliding distance d through the friction balance formula. The specific calculation expression is: According to the sliding distance d, the warning line is moved forward an equal distance away from the edge of the platform through the dynamic warning indicator light.

[0095] Continuously dynamically adjust the waiting cordon, for example, set a continuous LED warning indicator line along the waiting area on the platform floor to mark the boundary of the passenger safe waiting area. The LED warning line uses dynamic color change or dynamic movement to indicate the adjustment of the cordon. During the cordon adjustment process, the voice broadcast system in the platform reminds passengers to stay away from the edge of the platform and clearly informs them of the new safe waiting area. Example

[0096] The difference between Example 2 of the present invention and Example 1 is that this example introduces a rail transit passenger flow safety monitoring and management system. Figure 2 A schematic diagram of the structure of a rail transit passenger flow safety monitoring and management system of the present invention is given, which includes a parameter acquisition module, a central processing module, an extrusion force calculation module, and a warning line control module:

[0097] Parameter collection module: An array of dynamic passenger flow sensing devices is set up at the rail transit station platform. Based on the dynamic setting of data collection frequency, passenger flow crowd data is measured in real time and uploaded to the central processing module;

[0098] Central processing module: denoises the passenger flow data uploaded by the edge computing device, and monitors whether the crowd distribution entropy in the waiting platform area has dropped suddenly;

[0099] Extrusion force calculation module: establishes an extrusion force distribution model, and calculates the extrusion force in each crowded unit and the overall longitudinal extrusion force of the crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field;

[0100] Warning line control module: After receiving the high-risk signal of the pushing effect, it calculates the theoretical sliding distance of the people in the crowded unit under the action of the pushing force, and dynamically adjusts the position of the warning line.

[0101] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0102] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0103] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0105] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0106] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0108] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0109] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0110] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rail transit passenger flow safety monitoring and management method, characterized in that: The steps include: S1: Set up a dynamic passenger flow sensor array at the rail transit station platform to measure passenger flow data in real time and generate a two-dimensional plane density heat map; S2: Analyze the two-dimensional plane density heat map to determine whether the crowd distribution entropy in the waiting platform area has dropped suddenly. If so, send a crowd distribution entropy drop signal to the central processing module; S3: When the central processing module receives a signal of a sudden drop in crowd distribution entropy, it marks the crowded units in the monitoring unit and establishes a combined field of speed and density of the crowded units; S4: Establish a squeezing force distribution model, and calculate the squeezing force in each crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field; S5: Calculate the overall longitudinal squeezing force of the crowded unit, determine whether the longitudinal squeezing force has a risk of a pushing effect, and if so, send a high risk signal of a pushing effect; S6: After receiving the high risk signal of the pushing effect, the warning line control module calculates the theoretical sliding distance of the personnel in the crowded unit under the pushing force, and dynamically adjusts the position of the warning line; In S4, a squeezing force distribution model is established. According to the real-time velocity gradient and density gradient of adjacent cells in the combined field, the squeezing force in each crowded cell is calculated. Specifically, it includes: Based on the density changes and speed changes of adjacent crowded units in the combined field, the crowd density gradient and speed gradient are calculated for all crowded units; The squeezing force distribution model is established based on crowd dynamics. The density gradient and velocity gradient are introduced into the squeezing force distribution model to calculate the squeezing force of each crowded unit. The squeezing force distribution model expression is: ； In the formula, is the two-dimensional coordinate position The squeezing force of the crowded unit, , They are the two-dimensional coordinate positions The density gradient and velocity gradient, , , They are the influence coefficients of the set density gradient, velocity gradient and the coupling effect of velocity and density gradient on the extrusion pressure.

2. A rail transit passenger flow safety monitoring and management method according to claim 1, characterized in that: In S1, a dynamic passenger flow sensor array is set up at the rail transit station platform to measure passenger flow data in real time and generate a two-dimensional plane density heat map, which specifically includes: Use laser scanning equipment to accurately measure the rail transit platform area and form a three-dimensional model of the platform monitoring area; The monitoring area is divided into two-dimensional monitoring units according to the three-dimensional model layout of the platform area, and dynamic passenger flow sensing devices are arranged in an array form based on the distribution of the monitoring units; An initial collection frequency is set for the sensor array. The sensor array collects passenger flow data in the waiting platform area at the set initial collection frequency. The passenger flow data includes individual positions, number of individuals in the crowd, and speed of individuals in the crowd in each monitoring unit. The passenger flow data is uploaded to the central processing module in real time through the edge computing device. The central processing module performs denoising on the passenger flow data uploaded by the edge computing device, and calculates and updates the crowd density speed of each monitoring unit in real time based on the denoised data; The crowd density data is divided into different density levels, and the corresponding color is marked according to the density level of each monitoring unit. At the same time, the interpolation algorithm is used to smooth the density changes between adjacent monitoring units; A visual two-dimensional heat map is generated and updated in real time based on the same update frequency as the data collection frequency of each monitoring unit, which is marked as a two-dimensional plane density heat map.

3. A rail transit passenger flow safety monitoring and management method according to claim 2, characterized in that: In S2, the two-dimensional plane density heat map is analyzed to determine whether the crowd distribution entropy in the waiting platform area has dropped suddenly. If so, a crowd distribution entropy drop signal is sent to the central processing module, which specifically includes: Set the crowd distribution trend monitoring time window T, and the central processing module will integrate and time-series-mark the passenger flow data uploaded by all monitoring units within the monitoring time window T; Obtain a set of passenger flow crowd data of monitoring units with the same time series mark, and calculate the time series density probability of each monitoring unit according to the proportion of the crowd density of each monitoring unit in the set to the total crowd density; Based on the time series density probability of each monitoring unit and the distribution entropy calculation formula, the change of the crowd time series distribution entropy of the two-dimensional plane density heat map is calculated. The distribution entropy calculation formula is: ； In the formula, is the crowd distribution entropy in the waiting platform area at the tth monitoring time point within the dynamic monitoring time window T, is the density probability of the ith monitoring unit at the tth monitoring time point, is the total number of divided monitoring units; Analyze the change of time series distribution entropy within the monitoring time window T. When the distribution entropy continues to decrease within the monitoring time window T and the overall decrease exceeds the set sudden drop threshold, send a distribution entropy sudden drop signal to the central processing module.

4. A rail transit passenger flow safety monitoring and management method according to claim 3, characterized in that: In S3, when the central processing module receives a signal of a sudden drop in crowd distribution entropy, it marks the crowded unit in the monitoring unit and establishes a combined field of speed and density of the crowded unit, specifically including: The crowding density of the monitoring unit is set. When the central processing module receives a signal of a sudden drop in crowd distribution entropy, it selects all monitoring units in the two-dimensional density heat map whose marked colors correspond to density levels above the set crowding density and marks them as crowded units. Reset the frequency of collecting passenger flow data of the sensor array in the crowded unit, collect passenger flow data in real time, and calculate the real-time density and speed of the crowd in the crowded unit; A two-dimensional density field is formed based on the time series density changes of all crowded units. At the same time, a two-dimensional velocity field is formed according to the individual speed and position changes of the crowd. The two-dimensional density field and the two-dimensional velocity field are superimposed into a combined field. The position information of each crowded unit in the combined field is expressed in two-dimensional coordinates. express.

5. A rail transit passenger flow safety monitoring and management method according to claim 4, characterized in that: In S5, the overall longitudinal squeezing force of the crowded unit is calculated to determine whether there is a risk of a squeezing effect in the longitudinal squeezing force. If so, sending a high risk signal of a squeezing effect specifically includes: The squeezing force of the crowded unit is evaluated as a whole, and the total pressure component of the time-series crowd squeezing force with a set time step perpendicular to the platform cordon direction is calculated, which is marked as the time-series longitudinal squeezing force; The minimum squeezing force for the crowd to maintain balance is set. When the longitudinal squeezing force is greater than the minimum balanced squeezing force, it is judged that there is a risk of a pushing effect, and a high-risk signal of a pushing effect is sent to the warning line control module.

6. A rail transit passenger flow safety monitoring and management method according to claim 5, characterized in that: In S6, after receiving the high risk signal of the pushing effect, the warning line control module calculates the theoretical sliding distance of the personnel in the crowded unit under the pushing force, and dynamically adjusts the position of the warning line, specifically including: After receiving the high risk signal of the pushing effect, the warning line control module sets the waiting warning line control cycle; Calculate the theoretical maximum longitudinal sliding distance of the personnel in the crowded unit closest to the edge of the cordon under the longitudinal pushing force during the cordon control cycle, and move the cordon forward an equal distance away from the edge of the platform through the dynamic warning indicator light according to the sliding distance; Continue to dynamically adjust the waiting warning line until the high-risk signal of the pushing effect in the warning line control module disappears and the adjustment is completed.

7. A rail transit passenger flow safety monitoring and management system, used to implement a rail transit passenger flow safety monitoring and management method according to any one of claims 1 to 6, characterized in that: Including parameter acquisition module, central processing module, extrusion force calculation module, warning line control module: Parameter collection module: An array of dynamic passenger flow sensing devices is set up at the rail transit station platform. Based on the dynamic setting of data collection frequency, passenger flow crowd data is measured in real time and uploaded to the central processing module; Central processing module: denoises the passenger flow data uploaded by the edge computing device, and monitors whether the crowd distribution entropy in the waiting platform area has dropped suddenly; Extrusion force calculation module: establishes an extrusion force distribution model, and calculates the extrusion force in each crowded unit and the overall longitudinal extrusion force of the crowded unit according to the real-time velocity gradient and density gradient of adjacent units in the combined field; Warning line control module: After receiving the high-risk signal of the pushing effect, it calculates the theoretical sliding distance of the people in the crowded unit under the action of the pushing force and dynamically adjusts the position of the warning line.

Images