Rail transit safety monitoring method and system based on Internet of Things

Abstract

The invention relates to the field of rail transit, and discloses a rail transit safety monitoring method and system based on the Internet of Things, and the method comprises the steps: carrying out the statistical analysis of passenger access related data, drawing a passenger flow change curve of each entrance, recognizing a passenger flow peak time period and a passenger flow trough time period, and extracting passenger flow features from the peak time period and the trough time period; according to the passenger travel information data and the number of passengers entering and exiting the entrances and exits, the crowdedness degree of the getting-on positions and the flow direction distribution of the passengers at the entrances and exits on the platform are analyzed, the crowdedness degree of each getting-on position in different time periods is comprehensively predicted, and the train operation plan is adjusted according to the prediction result. And getting-on safety risk analysis and detection are carried out according to prediction results of crowdedness degrees of all getting-on positions in different time periods, real-time passenger flow volume fluctuation and platform safety capacity, possible crowded getting-on positions and safety risks can be found in advance, the train running state can be flexibly adjusted according to the actual passenger flow condition, and the safety of the train is improved. And the train operation efficiency and the passenger satisfaction are improved.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and more specifically to a rail transit safety monitoring method and system based on the Internet of Things. Background Art

[0002] Many traditional rail transit safety inspections rely on manual patrols, a method that is inefficient, has limited coverage, and is easily affected by factors such as operator experience, fatigue, and subjective judgment, making it difficult to achieve real-time, comprehensive, and refined monitoring. With the rapid development of IoT technology, its application to rail transit safety monitoring methods can optimize train schedules and dispatch resources through real-time monitoring of passenger flow and equipment status. This overcomes the shortcomings of traditional monitoring methods and enables comprehensive, all-weather, real-time, and intelligent safety monitoring of rail transit systems, thereby improving the safety level, operational efficiency, and passenger experience of the entire system.

[0003] However, existing rail transit safety monitoring methods still have the following disadvantages:

[0004] First, existing rail transit safety monitoring methods use fixed passenger flow analysis models that cannot be adjusted according to real-time passenger flow changes. This results in significant deviations from actual conditions and is unable to promptly reflect dynamic changes in passenger flow during peak and trough periods.

[0005] Second, existing rail transit safety monitoring methods can only provide a rough estimate of overall platform passenger flow, making it difficult to accurately predict the degree of congestion at each boarding location at different time periods. This can lead to localized congestion when passengers board the train, affecting efficiency and safety.

[0006] Third, existing rail transit safety monitoring methods often lack scientific basis when adjusting train operation plans, relying mainly on empirical judgment. This results in train operation plans not being well adapted to passenger flow changes, resulting in wasted resources or failure to meet passenger travel needs.

[0007] Fourth, existing rail transit safety monitoring methods usually only consider passenger flow when analyzing safety risks, ignoring the impact of factors such as the degree of congestion at the boarding location and the distribution of passenger flow, resulting in incomplete safety risk analysis and failure to timely discover potential safety hazards. Summary of the Invention

[0008] In order to overcome the above-mentioned defects of the prior art, the present invention provides a rail transit safety monitoring method and system based on the Internet of Things to solve the problems existing in the above-mentioned background technology.

[0009] The present invention provides the following technical solution: a rail transit safety monitoring method based on the Internet of Things, comprising:

[0010] S1: Sensors are installed at each entrance and exit of the platform to collect real-time data on passenger entry and exit, and combined with the rail transit ticketing system to obtain passenger travel information data;

[0011] S2: Statistically analyzing the passenger entry and exit data, drawing passenger flow change curves at each entrance and exit, analyzing and identifying peak and low passenger flow periods, and extracting passenger flow characteristics therefrom;

[0012] S3: Analyze the congestion level at the boarding location and the flow distribution of passengers at the entrances and exits on the platform based on passenger travel information data and the number of passengers entering and exiting each entrance and exit;

[0013] S4: Analyze and predict the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of the passengers at the entrance and exit on the platform;

[0014] S5: Based on the predicted results of the congestion level of each boarding location in different time periods, train operation plan adjustment suggestions are automatically generated and fed back to the management terminal;

[0015] S6: Based on the predicted results of the congestion level of each boarding location in different time periods, the boarding safety risk analysis is conducted together with the real-time passenger flow fluctuations and the platform safety capacity, the risk index is calculated, and the risk analysis results are fed back to the management terminal.

[0016] Preferably, the S1 collects passenger entry and exit related data in real time by installing sensors including infrared sensors and pressure sensors at various entrances and exits of the platform, including entry gates, exit gates, emergency exits, stairwells, and escalator entrances. The passenger entry and exit related data include instantaneous flow, cumulative flow, passenger flow direction data, regional density, queue length, waiting time, and environmental data, and transmits the digital signals output by the sensors to the data processing unit in real time through the Internet of Things network, and the data processing unit receives the digital signals output by the sensors;

[0017] By combining with the rail transit ticketing system, passenger travel information data including passenger identity and ticket type information, entry and exit time and station, travel route, passenger flow and special passenger information is obtained. The passenger travel information data is exported from the rail transit ticketing system through the data interface and transmitted to the data processing unit, which receives the exported passenger travel information data.

[0018] Preferably, the S2 is based on the passenger entry and exit data, and counts the passenger entry and exit volume, passenger net flow, and passenger flow at each entrance and exit within a preset time interval. According to the statistical results, a passenger flow change curve is drawn for each entrance and exit with time as the horizontal axis and passenger flow as the vertical axis. The passenger flow change curves drawn for multiple entrances and exits are superimposed or compared for display. By monitoring the fluctuation state of the passenger flow change curve in real time, the passenger flow value on the curve is compared and analyzed with the peak threshold and the low-peak threshold.

[0019] When the passenger flow rate is greater than the peak threshold, the time point / interval is determined to be within the passenger flow peak interval;

[0020] When the passenger flow is less than the low-peak threshold, the time point / interval is determined to be a low-passenger flow interval;

[0021] When the low-peak threshold ≤ passenger flow ≤ peak threshold, the time point / interval is determined to be a flat interval;

[0022] Based on the threshold comparison results, the time axis is divided into peak passenger flow intervals, low passenger flow intervals and flat passenger flow intervals. The maximum passenger flow, peak duration, fluctuation amplitude of peak passenger flow curve and average passenger flow growth rate during peak period are extracted from the peak interval. The minimum passenger flow, low duration, fluctuation amplitude of low passenger flow curve and average passenger flow growth rate during low period are extracted from the low interval.

[0023] Preferably, the S3 integrates the number of passengers entering and exiting each entrance and exit, passenger travel information data and passenger flow characteristics, divides the passenger entry time and station information obtained by the entrance gate according to preset time intervals, and matches it with the number of entrances and exits around each boarding position in the corresponding time period, and then analyzes the congestion level of the boarding position and the flow distribution of entrance and exit passengers on the platform based on the matched data.

[0024] Preferably, the method for analyzing the crowdedness of the boarding position is:

[0025] Step S301: Divide the platform into a number of boarding area with average size according to the platform layout, and number each area as 1, 2, ..., m;

[0026] Step S302: In each time interval, the instantaneous passenger flow of each boarding location area is counted as Q j ;

[0027] Step S303: By analyzing the area of ​​the boarding location area and the number of passengers that can be accommodated per unit area, the boarding location capacity of each boarding location area is calculated as C j =A j ×ρ, where Aj represents the area of ​​the jth boarding location area, and ρ represents the number of passengers that can be accommodated per unit area;

[0028] Step S304: Calculate the congestion level of each boarding location area based on the instantaneous passenger flow and capacity:

[0029] Step S305: The boarding location congestion level is calculated based on the weighted average of the congestion levels of all boarding location areas. The specific calculation formula is: Among them, w j Represents the weight coefficient of the j-th boarding location area.

[0030] Preferably, the flow distribution of the entrance and exit passengers on the platform is analyzed in the following manner:

[0031] Step S311: Based on the passenger's entry and exit information and travel path, mark the passenger's initial location and destination on the platform plan. According to the actual passenger flow changes and demand, preset reasonable time intervals, and count the number of passenger flows N at each entrance and exit at the preset time intervals. p，v ;

[0032] Step S312: According to the number of passenger flows N at each entrance and exit p，v , calculate the total number of people entering each entrance and exit in each time interval

[0033] Step S313: Based on the number of passenger flows at each entrance and exit and the total number of passengers entering the station at each entrance and exit in each time interval, calculate the proportion of passenger flow in each direction to the total passenger flow at the entrance and exit:

[0034]

[0035] Step S314: Use the platform plan to draw a platform plan flow distribution map with arrows indicating the direction of passenger flow. The thickness of the arrows indicates the proportion of passenger flow in each direction to the total passenger flow at the entrance and exit. Use light and dark colors on the platform plan flow distribution map to indicate flow density. Darker colors indicate greater passenger flow, and lighter colors indicate less passenger flow.

[0036] Preferably, the step S4 analyzes and predicts the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of the passengers at the entrance and exit on the platform, thereby calculating a boarding location congestion prediction coefficient;

[0037] The specific analysis method of the boarding position congestion prediction coefficient is as follows:

[0038] Step S401: Based on the passenger flow characteristics of the peak interval, the crowdedness of the boarding position, and the flow distribution of the entrance passengers on the platform, the peak interval crowdedness prediction coefficient is calculated as Among them, Q max represents the maximum passenger flow, Q avg_high represents the average passenger flow during peak hours, F high Indicates the fluctuation amplitude of the peak passenger flow curve, G high represents the average passenger flow growth rate during peak hours, D represents the degree of crowdedness at the boarding location, and S represents the uniformity of passenger distribution on the platform (S = 1 represents uniform distribution, S = 0 represents concentrated distribution);

[0039] Step S402: Based on the passenger flow characteristics of the valley section, the crowdedness of the boarding position, and the flow distribution of the entrance passengers on the platform, the valley section crowdedness prediction coefficient is calculated as Among them, Q min Indicates the minimum passenger flow, Q avg_low Indicates the average passenger flow during the off-peak period, F low Indicates the fluctuation amplitude of the trough passenger flow curve, G low Indicates the average passenger flow growth rate during the off-peak period;

[0040] Step S403: The boarding position crowding degree prediction coefficient is calculated by comprehensively calculating the peak interval crowding degree prediction coefficient and the valley interval crowding degree prediction coefficient.

[0041] Preferably, the S5 transmits the generated train operation plan adjustment suggestion to the management personnel terminal through the data interface, and displays the predicted results of the congestion level of each boarding position in different time periods in the form of a chart on the terminal.

[0042] Preferably, the S6 analyzes the boarding safety risk by combining the boarding position congestion prediction coefficient with the real-time passenger flow fluctuation and the platform safety capacity, and calculates the risk index as Among them, I represents the prediction coefficient of the crowdedness of the boarding position, ΔQ represents the real-time passenger flow fluctuation value, and Q safe Indicates the platform safety capacity;

[0043] By comparing the risk index with the preset risk threshold, if the risk index is less than or equal to the preset risk threshold, it indicates that it is safe to get on the bus and no warning is needed. If the risk index is greater than the preset risk threshold, it indicates that there is a risk of getting on the bus and an early warning prompt must be triggered immediately and fed back to the management terminal.

[0044] To achieve the above objectives, the present invention provides the following technical solutions: a rail transit safety monitoring system based on the Internet of Things, implementing the above rail transit safety monitoring method based on the Internet of Things, comprising:

[0045] Data collection module: By installing sensors at each entrance and exit of the platform, real-time data on passenger entry and exit is collected, and combined with the rail transit ticketing system, passenger travel information data is obtained;

[0046] Passenger flow period identification module: by statistically analyzing the passenger entry and exit related data, drawing the passenger flow change curve of each entrance and exit, analyzing and identifying the peak and low periods of passenger flow, and extracting passenger flow characteristics from them;

[0047] Passenger flow congestion and distribution analysis module: This module uses passenger travel information data and the number of passengers entering and exiting each entrance and exit to analyze the congestion level at the boarding area and the flow distribution of passengers at the entrance and exit on the platform.

[0048] Crowding prediction module: Analyzes and predicts the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of passengers at the entrance and exit on the platform;

[0049] Train operation adjustment module: Based on the predicted results of the congestion level of each boarding location in different time periods, it automatically generates train operation plan adjustment suggestions and feeds them back to the management terminal;

[0050] Boarding safety risk analysis module: Based on the predicted results of the congestion level of each boarding location in different time periods, the boarding safety risk analysis is conducted with real-time passenger flow fluctuations and platform safety capacity, the risk index is calculated, and the risk analysis results are fed back to the management terminal.

[0051] Technical effects and advantages of the present invention:

[0052] (1) Based on the statistical analysis of the collected passenger entry and exit data, the passenger flow change curve of each entrance and exit is drawn. It can analyze and identify the peak and low periods of passenger flow in real time, and extract the passenger flow characteristics. It can make adjustments according to the real-time passenger flow changes, reduce the error between the analysis results and the actual situation, and help to timely reflect the dynamic changes of passenger flow peak and low periods.

[0053] (2) Based on passenger travel information data and the number of passengers entering and exiting each entrance and exit, the congestion level of the boarding location and the flow distribution of passengers at the entrance and exit on the platform are analyzed. Based on these data, the congestion level of each boarding location in different time periods is analyzed and predicted. This can identify possible congested boarding locations in advance and provide support for management personnel to take targeted measures.

[0054] (3) Based on the predicted results of the congestion level of each boarding location in different time periods, the train operation plan is adjusted and analyzed, and the adjustment analysis results are fed back to the management personnel terminal, making the adjustment of the train operation plan more scientific and reasonable. The train departure interval, stop points, etc. can be flexibly adjusted according to the actual passenger flow situation, thereby improving train operation efficiency and passenger satisfaction.

[0055] (4) Based on the predicted results of the congestion level of each boarding location in different time periods, the boarding safety risk analysis is conducted together with the real-time passenger flow fluctuations and the platform safety capacity, and the risk index is calculated. The risk analysis results are fed back to the management terminal, which can more comprehensively assess the safety risks of the platform and timely discover and deal with potential safety issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A diagram showing the steps of the method of the present invention.

[0057] Figure 2 This is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0058] The technical solutions of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The Internet of Things-based rail transit safety monitoring method and system involved in the present invention are not limited to the various structures described in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0059] like Figure 1 This embodiment provides a rail transit safety monitoring method based on the Internet of Things, including:

[0060] S1: By installing sensors at each entrance and exit of the platform, real-time data on passenger entry and exit is collected, and combined with the rail transit ticketing system, passenger travel information data is obtained.

[0061] In this embodiment, the S1 collects passenger entry and exit related data in real time by installing sensors including infrared sensors and pressure sensors at various entrances and exits of the platform, including entry gates, exit gates, emergency exits, stairwells, and escalator entrances. The passenger entry and exit related data includes instantaneous flow rate, cumulative flow rate, passenger flow direction data, regional density, queue length, waiting time, and environmental data. The digital signals output by the sensors are transmitted in real time to the data processing unit through the Internet of Things network, and the data processing unit receives the digital signals output by the sensors.

[0062] By combining with the rail transit ticketing system, passenger travel information data including passenger identity and ticket type information, entry and exit time and station, travel route, passenger flow and special passenger information is obtained. The passenger travel information data is exported from the rail transit ticketing system through the data interface and transmitted to the data processing unit, which receives the exported passenger travel information data.

[0063] S2: By statistically analyzing the passenger entry and exit related data, the passenger flow change curve of each entrance and exit is drawn, the peak and low periods of passenger flow are analyzed and identified, and the passenger flow characteristics are extracted therefrom.

[0064] In this embodiment, S2 counts the number of passengers entering and exiting the station, the net passenger flow, and the passenger flow at each entrance and exit within a preset time interval based on the passenger entry and exit data. Based on the statistical results, a passenger flow change curve is drawn for each entrance and exit with time as the horizontal axis and passenger flow as the vertical axis. The passenger flow change curves drawn for multiple entrances and exits are superimposed or compared for display. By monitoring the fluctuations of the passenger flow change curve in real time, the passenger flow value on the curve is compared and analyzed with the peak threshold and the low-peak threshold.

[0065] When the passenger flow rate is greater than the peak threshold, the time point / interval is determined to be within the passenger flow peak interval;

[0066] When the passenger flow is less than the low-peak threshold, the time point / interval is determined to be a low-passenger flow interval;

[0067] When the low-peak threshold ≤ passenger flow ≤ peak threshold, the time point / interval is determined to be a flat interval;

[0068] Based on the threshold comparison results, the time axis is divided into peak passenger flow intervals, low passenger flow intervals and flat passenger flow intervals. The maximum passenger flow, peak duration, fluctuation amplitude of peak passenger flow curve and average passenger flow growth rate during peak period are extracted from the peak interval. The minimum passenger flow, low duration, fluctuation amplitude of low passenger flow curve and average passenger flow growth rate during low period are extracted from the low interval.

[0069] It should be noted that the passenger flow data at each time point on the curve is set to Q = {q1, q2, ..., q n}, then the average passenger flow is calculated to be The standard deviation of passenger flow is Among them, q i represents the passenger flow value at the i-th time point. The peak threshold and trough threshold are analyzed and calculated based on the mean passenger flow and the standard deviation of passenger flow. The specific calculation formula for the peak threshold is κ 高 =μ Q +k×σ Q, the specific calculation formula for the trough threshold is κ 低 =μ Q -k×σ Q , where k represents the adjustment parameter, and the specific value is adjusted according to the data distribution.

[0070] S3: Analyze the congestion level at the boarding location and the flow distribution of passengers at the entrances and exits on the platform based on passenger travel information data and the number of passengers entering and exiting each entrance and exit.

[0071] In this embodiment, S3 integrates the number of passengers entering and exiting each entrance and exit, passenger travel information data, and passenger flow characteristics, divides the passenger entry time and station information obtained by the entrance gate according to preset time intervals, and matches it with the number of entrances and exits around each boarding location in the corresponding time period. Based on the matched data, the congestion level of the boarding location and the flow distribution of passengers at the entrance and exit on the platform are analyzed;

[0072] The method for analyzing the crowdedness of the boarding position is as follows:

[0073] Step S301: Divide the platform into a number of boarding area with average size according to the platform layout, and number each area as 1, 2, ..., m;

[0074] Step S302: In each time interval, the instantaneous passenger flow of each boarding location area is counted as Q j ;

[0075] Step S303: By analyzing the area of ​​the boarding location area and the number of passengers that can be accommodated per unit area, the boarding location capacity of each boarding location area is calculated as C j =A j ×ρ, where A j represents the area of ​​the jth boarding location area, and ρ represents the number of passengers that can be accommodated per unit area;

[0076] Step S304: Calculate the congestion level of each boarding location area based on the instantaneous passenger flow and capacity:

[0077] Step S305: The boarding location congestion level is calculated based on the weighted average of the congestion levels of all boarding location areas. The specific calculation formula is: Among them, w j represents the weight coefficient of the jth boarding location area;

[0078] The analysis method for the flow distribution of the entrance and exit passengers on the platform is as follows:

[0079] Step S311: Based on the passenger's entry and exit information and travel path, mark the passenger's initial location and destination on the platform plan. According to the actual passenger flow changes and demand, preset reasonable time intervals, and count the number of passenger flows N at each entrance and exit at the preset time intervals. p，v ;

[0080] Step S312: According to the number of passenger flows N at each entrance and exit p，v , calculate the total number of people entering each entrance and exit in each time interval

[0081] Step S313: Based on the number of passenger flows at each entrance and exit and the total number of passengers entering the station at each entrance and exit in each time interval, calculate the proportion of passenger flow in each direction to the total passenger flow at the entrance and exit:

[0082]

[0083] Step S314: Use the platform plan to draw a platform plan flow distribution map with arrows indicating the direction of passenger flow. The thickness of the arrows indicates the proportion of passenger flow in each direction to the total passenger flow at the entrance and exit. Use light and dark colors on the platform plan flow distribution map to indicate flow density. Darker colors indicate greater passenger flow, and lighter colors indicate less passenger flow.

[0084] S4: Based on the passenger flow characteristics, the congestion level of the boarding location and the flow distribution of the entrance and exit passengers on the platform, analyze and predict the congestion level of each boarding location in different time periods.

[0085] In this embodiment, S4 analyzes and predicts the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of passengers at the entrance and exit on the platform, thereby calculating a boarding location congestion prediction coefficient;

[0086] The specific analysis method of the boarding position congestion prediction coefficient is as follows:

[0087] Step S401: Based on the passenger flow characteristics of the peak interval, the crowdedness of the boarding position, and the flow distribution of the entrance passengers on the platform, the peak interval crowdedness prediction coefficient is calculated as Among them, Q max represents the maximum passenger flow, Q avg_high represents the average passenger flow during peak hours, F high Indicates the fluctuation amplitude of the peak passenger flow curve, G high represents the average passenger flow growth rate during peak hours, D represents the degree of crowdedness at the boarding location, and S represents the uniformity of passenger distribution on the platform (S = 1 represents uniform distribution, S = 0 represents concentrated distribution);

[0088] Step S402: Based on the passenger flow characteristics of the valley section, the crowdedness of the boarding position, and the flow distribution of the entrance passengers on the platform, the valley section crowdedness prediction coefficient is calculated as Among them, Q min Indicates the minimum passenger flow, Q avg_low Indicates the average passenger flow during the off-peak period, F low Indicates the fluctuation amplitude of the trough passenger flow curve, G low Indicates the average passenger flow growth rate during the off-peak period;

[0089] Step S403: The boarding position crowding degree prediction coefficient is calculated by comprehensively calculating the peak interval crowding degree prediction coefficient and the valley interval crowding degree prediction coefficient.

[0090] S5: Based on the predicted results of the congestion level of each boarding location in different time periods, the train operation plan adjustment suggestions are automatically generated and fed back to the management personnel terminal.

[0091] In this embodiment, the S5 transmits the generated train operation plan adjustment suggestion to the management personnel terminal through the data interface, and displays the predicted results of the congestion level of each boarding location in different time periods in the form of a chart on the terminal.

[0092] S6: Based on the predicted results of the congestion level of each boarding location in different time periods, the boarding safety risk analysis is conducted together with the real-time passenger flow fluctuations and the platform safety capacity, the risk index is calculated, and the risk analysis results are fed back to the management terminal.

[0093] In this embodiment, S6 analyzes the boarding safety risk by combining the boarding position congestion prediction coefficient with the real-time passenger flow fluctuation and the platform safety capacity, and calculates the risk index as follows: Among them, I represents the prediction coefficient of the crowdedness of the boarding position, ΔQ represents the real-time passenger flow fluctuation value, and Q safe Indicates the platform safety capacity;

[0094] By comparing the risk index with the preset risk threshold, if the risk index is less than or equal to the preset risk threshold, it indicates that it is safe to get on the bus and no warning is needed. If the risk index is greater than the preset risk threshold, it indicates that there is a risk of getting on the bus and an early warning prompt must be triggered immediately and fed back to the management terminal.

[0095] like Figure 2The embodiment shown provides an implementation system corresponding to the rail transit safety monitoring method based on the Internet of Things, including a data acquisition module, a passenger flow period identification module, a passenger flow congestion and distribution analysis module, a congestion level prediction module, a train operation adjustment module and a boarding safety risk analysis module. The data acquisition module is connected to the passenger flow period identification module, the data acquisition module is connected to the passenger flow congestion and distribution analysis module, the passenger flow congestion and distribution analysis module is connected to the congestion level prediction module, the passenger flow period identification module is connected to the congestion level prediction module, the congestion level prediction module is connected to the train operation adjustment module, and the congestion level prediction module is connected to the boarding safety risk analysis module.

[0096] The data acquisition module collects real-time passenger entry and exit data by installing sensors at each entrance and exit of the platform, and obtains passenger travel information data in conjunction with the rail transit ticketing system;

[0097] The passenger flow period identification module statistically analyzes the passenger entry and exit related data, draws the passenger flow change curve of each entrance and exit, analyzes and identifies the peak and low periods of passenger flow, and extracts passenger flow characteristics from them;

[0098] The passenger flow congestion and distribution analysis module analyzes the congestion level of boarding locations and the flow distribution of passengers at the entrances and exits on the platform based on passenger travel information data and the number of passengers entering and exiting each entrance and exit;

[0099] The congestion prediction module analyzes and predicts the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of the passengers at the entrance and exit on the platform;

[0100] The train operation adjustment module automatically generates train operation plan adjustment suggestions based on the prediction results of the congestion level of each boarding location in different time periods, and feeds back the train operation plan adjustment suggestions to the management terminal;

[0101] The boarding safety risk analysis module performs boarding safety risk analysis based on the predicted results of the congestion level of each boarding location in different time periods, real-time passenger flow fluctuations and platform safety capacity, calculates the risk index, and feeds back the risk analysis results to the management terminal.

[0102] 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 scope of protection of the present invention.

[0103] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A rail transit safety monitoring method based on the Internet of Things, characterized in that: include: S1: Sensors are installed at each entrance and exit of the platform to collect real-time data on passenger entry and exit, and combined with the rail transit ticketing system to obtain passenger travel information data; S2: Statistically analyzing the passenger entry and exit data, drawing passenger flow change curves at each entrance and exit, analyzing and identifying peak and low passenger flow periods, and extracting passenger flow characteristics therefrom; S3: Analyze the congestion level at the boarding location and the flow distribution of passengers on the platform at the entrances and exits based on passenger travel information data and the number of passengers entering and exiting each entrance and exit; S4: Analyze and predict the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of the passengers at the entrance and exit on the platform; S5: Based on the predicted results of the congestion level of each boarding location in different time periods, train operation plan adjustment suggestions are automatically generated and fed back to the management terminal; S6: Based on the predicted results of the congestion level of each boarding location in different time periods, the boarding safety risk analysis is conducted together with the real-time passenger flow fluctuations and the platform safety capacity, the risk index is calculated, and the risk analysis results are fed back to the management terminal.

2. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S1 collects passenger entry and exit related data in real time by installing sensors including infrared sensors and pressure sensors at each entrance and exit of the platform, including entry gates, exit gates, emergency exits, stairwells, and escalator entrances. The passenger entry and exit related data includes instantaneous flow rate, cumulative flow rate, passenger flow direction data, regional density, queue length, waiting time, and environmental data. The digital signals output by the sensors are transmitted to the data processing unit in real time through the Internet of Things network, and the data processing unit receives the digital signals output by the sensors. By combining with the rail transit ticketing system, passenger travel information data including passenger identity and ticket type information, entry and exit time and station, travel route, passenger flow and special passenger information is obtained. The passenger travel information data is exported from the rail transit ticketing system through the data interface and transmitted to the data processing unit, which receives the exported passenger travel information data.

3. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: S2, based on the passenger entry and exit data, counts the number of passengers entering and leaving the station, the net passenger flow, and the passenger flow at each entrance and exit within a preset time interval. Based on the statistical results, a passenger flow change curve is drawn for each entrance and exit with time as the horizontal axis and passenger flow as the vertical axis. The passenger flow change curves drawn for multiple entrances and exits are superimposed or compared for display. By monitoring the fluctuations of the passenger flow change curve in real time, the passenger flow value on the curve is compared and analyzed with the peak threshold and the low-peak threshold. When the passenger flow rate is greater than the peak threshold, the time point / interval is determined to be within the passenger flow peak interval; When the passenger flow is less than the low-peak threshold, the time point / interval is determined to be a low-passenger flow interval; When the low-peak threshold ≤ passenger flow ≤ peak threshold, the time point / interval is determined to be a flat interval; Based on the threshold comparison results, the time axis is divided into peak passenger flow intervals, low passenger flow intervals and flat passenger flow intervals. The maximum passenger flow, peak duration, fluctuation amplitude of peak passenger flow curve and average passenger flow growth rate during peak period are extracted from the peak interval. The minimum passenger flow, low duration, fluctuation amplitude of low passenger flow curve and average passenger flow growth rate during low period are extracted from the low interval.

4. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S3 integrates the number of passengers entering and exiting each entrance and exit, passenger travel information data and passenger flow characteristics, divides the passenger entry time and station information obtained by the entrance gate according to preset time intervals, and matches it with the number of entrances and exits around each boarding position in the corresponding time period. Based on the matched data, the congestion level of the boarding position and the flow distribution of passengers at the entrance and exit on the platform are analyzed.

5. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: The method for analyzing the crowdedness of the boarding position is as follows: Step S301: Divide the platform into a number of boarding area with average size according to the platform layout, and number each area as 1, 2, ..., m; Step S302: In each time interval, the instantaneous passenger flow of each boarding location area is counted as Q j ; Step S303: By analyzing the area of ​​the boarding location area and the number of passengers that can be accommodated per unit area, the boarding location capacity of each boarding location area is calculated as C j =A j ×ρ, where A j represents the area of ​​the jth boarding location area, and ρ represents the number of passengers that can be accommodated per unit area; Step S304: Calculate the congestion level of each boarding location area based on the instantaneous passenger flow and capacity: Step S305: The boarding location congestion level is calculated based on the weighted average of the congestion levels of all boarding location areas. The specific calculation formula is: Among them, w j Represents the weight coefficient of the j-th boarding location area.

6. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: The analysis method for the flow distribution of the entrance and exit passengers on the platform is as follows: Step S311: Based on the passenger's entry and exit information and travel path, mark the passenger's initial location and destination on the platform plan. According to the actual passenger flow changes and demand, preset reasonable time intervals, and count the number of passenger flows N at each entrance and exit at the preset time intervals. p，v ; Step S312: According to the number of passenger flows N at each entrance and exit p，v , calculate the total number of people entering each entrance and exit in each time interval Step S313: Based on the number of passenger flows at each entrance and exit and the total number of passengers entering the station at each entrance and exit in each time interval, calculate the proportion of passenger flow in each direction to the total passenger flow at the entrance and exit: Step S314: Use the platform plan to draw a platform plan flow distribution map with arrows indicating the direction of passenger flow. The thickness of the arrows indicates the proportion of passenger flow in each direction to the total passenger flow at the entrance and exit. Use light and dark colors on the platform plan flow distribution map to indicate flow density. Darker colors indicate greater passenger flow, and lighter colors indicate less passenger flow.

7. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S4 analyzes and predicts the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of the passengers at the entrance and exit on the platform, thereby calculating a boarding location congestion prediction coefficient; The specific analysis method of the boarding position congestion prediction coefficient is as follows: Step S401: Based on the passenger flow characteristics of the peak interval, the crowdedness of the boarding position, and the flow distribution of the entrance passengers on the platform, the peak interval crowdedness prediction coefficient is calculated as Among them, Q max represents the maximum passenger flow, Q avg_high represents the average passenger flow during peak hours, F high Indicates the fluctuation amplitude of the peak passenger flow curve, G high represents the average passenger flow growth rate during peak hours, D represents the degree of crowdedness at the boarding location, and S represents the uniformity of passenger distribution on the platform (S = 1 represents uniform distribution, S = 0 represents concentrated distribution); Step S402: Based on the passenger flow characteristics of the valley section, the crowdedness of the boarding position, and the flow distribution of the entrance passengers on the platform, the valley section crowdedness prediction coefficient is calculated as Among them, Q min Indicates the minimum passenger flow, Q avg_low represents the average passenger flow during the off-peak period, F low Indicates the fluctuation amplitude of the trough passenger flow curve, G low Indicates the average passenger flow growth rate during the off-peak period; Step S403: The boarding position crowding degree prediction coefficient is calculated by comprehensively calculating the peak interval crowding degree prediction coefficient and the valley interval crowding degree prediction coefficient.

8. The rail transit safety monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S5 transmits the generated train operation plan adjustment suggestion to the management terminal through the data interface, and displays the predicted results of the congestion level of each boarding position in different time periods in the form of a chart on the terminal.

9. The rail transit safety monitoring method based on the Internet of Things according to claim 1, characterized in that: The S6 analyzes the boarding safety risk by combining the boarding position congestion prediction coefficient with the real-time passenger flow fluctuation and the platform safety capacity, and calculates the risk index as Among them, I represents the prediction coefficient of the crowdedness of the boarding position, ΔQ represents the real-time passenger flow fluctuation value, and Q safe Indicates the platform safety capacity; By comparing the risk index with the preset risk threshold, if the risk index is less than or equal to the preset risk threshold, it indicates that it is safe to get on the bus and no warning is needed. If the risk index is greater than the preset risk threshold, it indicates that there is a risk of getting on the bus and an early warning prompt must be triggered immediately and fed back to the management terminal.

10. A rail transit safety monitoring system based on the Internet of Things, implementing the rail transit safety monitoring method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: include: Data collection module: By installing sensors at each entrance and exit of the platform, real-time data on passenger entry and exit is collected, and combined with the rail transit ticketing system, passenger travel information data is obtained; Passenger flow period identification module: by statistically analyzing the passenger entry and exit related data, drawing the passenger flow change curve of each entrance and exit, analyzing and identifying the peak and low periods of passenger flow, and extracting passenger flow characteristics from them; Passenger flow congestion and distribution analysis module: This module uses passenger travel information data and the number of passengers entering and exiting each entrance and exit to analyze the congestion level at the boarding area and the flow distribution of passengers at the entrance and exit on the platform. Crowding prediction module: Analyzes and predicts the congestion level of each boarding location in different time periods based on the passenger flow characteristics, the congestion level of the boarding location, and the flow distribution of passengers at the entrance and exit on the platform; Train operation adjustment module: Based on the predicted results of the congestion level of each boarding location in different time periods, it automatically generates train operation plan adjustment suggestions and feeds them back to the management terminal; Boarding safety risk analysis module: Based on the predicted results of the congestion level of each boarding location in different time periods, the boarding safety risk analysis is conducted with real-time passenger flow fluctuations and platform safety capacity, the risk index is calculated, and the risk analysis results are fed back to the management terminal.

Images