Urban rail transit information safety early warning system

Abstract

The invention relates to the technical field of urban rail transit, and discloses an urban rail transit information safety early warning system, compared with a traditional traffic safety monitoring system, the system realizes comprehensive monitoring of traffic flow, environmental conditions and risk factors through comprehensive acquisition, accurate preprocessing, scientific calculation and deep analysis, and improves the traffic safety. The data acquisition module ensures the comprehensiveness and real-time performance of information acquisition, and different from a traditional static monitoring system, the system can sense and analyze traffic and environment changes in real time, predict potential risks in advance, greatly improve the intelligence and response capability of traffic management, and improve the safety of traffic management. The integrated and intelligent early warning system not only improves the accuracy of traffic safety prevention, but also remarkably enhances the capability of dealing with complex traffic conditions and emergencies, and provides advanced technical guarantee for safety management of modern urban rail transit.

Description

Technical Field

[0001] The present invention relates to the technical field of urban rail transit, and in particular to an urban rail transit information safety early warning system. Background Art

[0002] Urban rail transit, as an important part of modern urban transportation, involves a large number of people, vehicles and environmental factors. With the acceleration of urbanization and the increase in population density, the safety, efficiency and emergency management of rail transit have become the core issues of transportation engineering and urban safety management.

[0003] The current traditional rail transit safety monitoring system usually relies on simple sensor data collection and static monitoring, which is often limited to the monitoring of a single parameter and lacks a comprehensive analysis of the complex interactive relationship between traffic, environment and risk factors. This approach is not only unable to respond to emergencies in real time, but also has potential safety hazards caused by weak early warning capabilities for complex traffic conditions. In addition, due to the lack of dynamic calculation and comprehensive evaluation of multiple risk factors, traditional systems are often unable to predict traffic bottlenecks or risk events at the earliest stage. Therefore, when facing the complex urban rail transit operating environment, the traditional traffic safety monitoring system has obvious shortcomings such as slow response speed, low prediction accuracy, and insufficient emergency response capabilities, and cannot effectively respond to the increasingly complex urban rail transit safety management needs.

[0004] Therefore, we proposed an urban rail transit information safety early warning system to solve the above-mentioned problems. Summary of the invention

[0005] The purpose of the present invention is to provide an urban rail transit information safety warning system to solve the problem that the above-mentioned background technology is limited to monitoring a single parameter and lacks a comprehensive analysis of the complex interactive relationship between traffic, environment and risk factors. This method is not only unable to respond to emergencies in real time, but also has potential safety hazards caused by its weak warning ability for complex traffic conditions. In addition, due to the lack of dynamic calculation and comprehensive evaluation of multiple risk factors, traditional systems are often unable to predict traffic bottlenecks or risk events at the earliest stage.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an urban rail transit information safety warning system, comprising a data acquisition module, a data preprocessing module, a data calculation module, a data analysis module and a feedback module;

[0007] The data collection module is used to collect traffic signals and integrate them into a first data set, a second data set and a third data set;

[0008] The data preprocessing module is used to preprocess and dimensionlessly transform the first data set, the second data set, and the third data set;

[0009] The data calculation module is used to integrate and calculate the first data set, the second data set and the third data set, so as to generate the pedestrian flow characteristic linkage coefficient S1, the vehicle flow characteristic linkage coefficient S2, the environmental characteristic linkage coefficient S3 and the pedestrian flow risk reference coefficient FX1, the vehicle flow risk reference coefficient FX2 and the environmental risk reference coefficient FX3 respectively;

[0010] The data analysis module is used to compare the pedestrian flow feature linkage coefficient S1, the vehicle flow feature linkage coefficient S2, and the environmental feature linkage coefficient S3 with the preset pedestrian flow feature linkage threshold Y1, the vehicle flow feature linkage threshold Y2, and the environmental feature linkage threshold Y3, respectively, so as to generate a first comparison result, and according to the first comparison result, determine whether it is necessary to associate the pedestrian flow feature, the vehicle flow feature, and the environmental feature with the knowledge graph, and generate a second comparison result by comparing the risk reference coefficient with the preset risk reference threshold, and according to the second comparison result, determine whether there is a risk in the current traffic;

[0011] The feedback module is used to send the first comparison result and the second comparison result to the terminal.

[0012] Preferably, the preprocessing steps of the data preprocessing module include data cleaning, noise removal and missing value filling, and dimensionless processing is performed on the preprocessed first data set, the second data set and the third data set.

[0013] Preferably, the data acquisition module acquires pedestrian flow characteristic data, vehicle flow characteristic data and environmental characteristic data in real time through a distributed sensor network, thereby generating a first data set, a second data set and a third data set;

[0014] The first data set includes total pedestrian flow A, instantaneous pedestrian flow B, and pedestrian flow density C;

[0015] The second data set includes total traffic volume D, instantaneous traffic volume E, and traffic density F;

[0016] The third data set includes real-time temperature G, real-time rainfall H, regional area I, road length J and real-time visibility K.

[0017] Preferably, the human flow characteristic linkage coefficient S1 of the data calculation module is calculated and obtained by the following formula:

[0018]

[0019] In the formula: A is the total flow of people, B is the instantaneous flow of people, C is the flow density, I is the area of ​​the region, and ln is the logarithmic function.

[0020] Preferably, the data calculation module calculates and obtains the vehicle flow characteristic linkage coefficient S2 through the following formula:

[0021]

[0022] Where: E is the instantaneous traffic flow, D is the total traffic flow, F is the traffic density, J is the road length, and ln is the logarithmic function.

[0023] Preferably, the data calculation module calculates and obtains the environmental feature linkage coefficient S3 by the following formula:

[0024]

[0025] Where: G is the real-time temperature, H is the real-time rainfall, I is the regional area, J is the road length, K is the real-time visibility, and ln is the logarithmic function.

[0026] Preferably, the data calculation module calculates and obtains the pedestrian flow risk reference coefficient FX1, the vehicle flow risk reference coefficient FX2 and the environmental risk reference coefficient FX3 respectively through the following formulas:

[0027]

[0028] In the formula: A is the total passenger flow, B is the instantaneous passenger flow, C is the passenger flow density, I is the regional area, E is the instantaneous vehicle flow, D is the total vehicle flow, F is the vehicle flow density, J is the road length, G is the real-time temperature, H is the real-time rainfall, and K is the real-time visibility.

[0029] Preferably, when S1>Y1, it means that the human flow characteristics need to be linked with the knowledge graph to analyze the risk and generate the human flow risk reference coefficient FX1. When S1≤Y1, it means that the human flow characteristics do not need to be linked with the knowledge graph to analyze the risk.

[0030] When S2>Y2, it means that the traffic flow characteristics need to be linked with the knowledge graph to analyze the risk and generate the traffic flow risk reference coefficient FX2. When S2>Y2, it means that the traffic flow characteristics do not need to be linked with the knowledge graph to analyze the risk.

[0031] When S3>Y3, it means that it is necessary to link environmental characteristics with the knowledge graph to analyze risks and generate an environmental risk reference coefficient FX3. When S3>Y3, it means that it is not necessary to link environmental characteristics with the knowledge graph to analyze risks.

[0032] Preferably, the second comparison result generated by the data analysis module is specifically as follows:

[0033] When FX1>R1, it means that the current traffic has a risk of human traffic type; when FX1≤R1, it means that the current traffic does not have a risk of human traffic type;

[0034] When FX2>R2, it means that the current traffic has a traffic flow type risk, and when FX2≤R2, it means that the current traffic does not have a traffic flow type risk;

[0035] When FX3>R3, it means that there is no environmental risk in the current traffic; when FX3≤R3, it means that there is no environmental risk in the current traffic;

[0036] R1 is the risk threshold for pedestrian flow type, R2 is the risk threshold for vehicle flow type, and R3 is the risk threshold for environment type.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. Compared with traditional traffic safety monitoring systems, this system realizes comprehensive monitoring of traffic flow, environmental conditions and risk factors through comprehensive collection, precise preprocessing, scientific calculation and in-depth analysis. The data collection module ensures the comprehensiveness and real-time nature of information collection, and the data preprocessing module provides data cleaning and standardization support to ensure data quality; the data calculation module obtains the linkage coefficient and risk reference coefficient through precise calculation, providing important evaluation indicators for the system; the data analysis module realizes threshold comparison and risk assessment, and provides intelligent decision-making support; the feedback module improves the speed and accuracy of emergency response through real-time feedback mechanism. Unlike traditional static monitoring systems, this system can perceive and analyze traffic and environmental changes in real time, predict potential risks in advance, and greatly enhance the intelligence and response capabilities of traffic management. This integrated and intelligent early warning system not only improves the accuracy of traffic safety prevention, but also significantly enhances the ability to cope with complex traffic conditions and emergencies, providing advanced technical guarantees for the safety management of modern urban rail transit.

[0039] 2. Through the dual analysis of the first comparison result and the second comparison result, the system can comprehensively consider the interactive impact of various traffic and environmental factors, comprehensively evaluate the risks of traffic flow, vehicle flow, environment and other aspects, so as to achieve comprehensive optimization management of the transportation system. For example, when the traffic pressure is high, the system may automatically adjust the operating frequency of rail transit or optimize the timing of traffic signals through multi-dimensional comparison of passenger flow, vehicle flow and environmental data to relieve traffic pressure and improve operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a system flow chart of the present invention.

[0041] In the figure: 1. Data acquisition module; 2. Data preprocessing module; 3. Data calculation module; 4. Data analysis module; 5. Feedback module. DETAILED DESCRIPTION

[0042] 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.

[0043] Example 1: Please refer to Figure 1 , an urban rail transit information safety warning system, comprising a data acquisition module 1, a data preprocessing module 2, a data calculation module 3, a data analysis module 4 and a feedback module 5;

[0044] The data collection module 1 is used to collect traffic signals and integrate them into a first data set, a second data set and a third data set;

[0045] The data preprocessing module 2 is used to preprocess and dimensionlessly transform the first data set, the second data set, and the third data set;

[0046] The data calculation module 3 is used to integrate and calculate the first data set, the second data set and the third data set, so as to generate the pedestrian flow characteristic linkage coefficient S1, the vehicle flow characteristic linkage coefficient S2, the environmental characteristic linkage coefficient S3 and the pedestrian flow risk reference coefficient FX1, the vehicle flow risk reference coefficient FX2 and the environmental risk reference coefficient FX3 respectively;

[0047] The data analysis module 4 is used to compare the pedestrian flow feature linkage coefficient S1, the vehicle flow feature linkage coefficient S2 and the environmental feature linkage coefficient S3 with the preset pedestrian flow feature linkage threshold Y1, the vehicle flow feature linkage threshold Y2 and the environmental feature linkage threshold Y3, respectively, so as to generate a first comparison result, and according to the first comparison result, determine whether it is necessary to associate the pedestrian flow feature, the vehicle flow feature and the environmental feature with the knowledge graph, and generate a second comparison result by comparing the risk reference coefficient with the preset risk reference threshold, and according to the second comparison result, determine whether there is a risk in the current traffic;

[0048] The feedback module 5 is used to send the first comparison result and the second comparison result to the terminal.

[0049] The data acquisition module 1 acquires pedestrian flow characteristic data, vehicle flow characteristic data and environmental characteristic data in real time through a distributed sensor network, thereby generating a first data set, a second data set and a third data set;

[0050] The first data set includes total pedestrian flow A, instantaneous pedestrian flow B, and pedestrian flow density C;

[0051] The second data set includes total traffic volume D, instantaneous traffic volume E, and traffic density F;

[0052] The third data set includes real-time temperature G, real-time rainfall H, regional area I, road length J and real-time visibility K.

[0053] In this embodiment: Data acquisition module 1 is responsible for real-time collection and integration of various traffic signals and environmental data. By deploying sensors, video surveillance equipment and other intelligent acquisition terminals, this module can comprehensively capture key data related to traffic flow, human flow and environmental changes. These data are organized into the first data set of human flow data, the second data set of vehicle flow data and the third data set of environmental characteristic data, providing basic data support for subsequent data processing, calculation and analysis. Through the integration and real-time collection of multi-dimensional data, it is ensured that the system can accurately reflect the current traffic status and environmental conditions, and provide a timely and reliable data source for subsequent intelligent decision-making.

[0054] The data acquisition module 1 acquires pedestrian flow characteristic data, vehicle flow characteristic data and environmental characteristic data in real time through a distributed sensor network, thereby generating a first data set, a second data set and a third data set;

[0055] The first data set includes total pedestrian flow A, instantaneous pedestrian flow B, and pedestrian flow density C;

[0056] The second data set includes total traffic volume D, instantaneous traffic volume E, and traffic density F;

[0057] The third data set includes real-time temperature G, real-time rainfall H, regional area I, road length J and real-time visibility K.

[0058] The data preprocessing module 2 is responsible for cleaning, denoising and dimensionless processing of the collected first data set, second data set and third data set. This module removes invalid information and outliers through data cleaning technology, fills in missing data, and performs dimensionless processing on the data to eliminate the impact of different dimensions and magnitudes, ensuring the consistency and comparability of the data. Dimensionless processing helps to improve the accuracy and stability of subsequent data analysis, ensuring that the calculation results are not affected by the dimension differences of the original data, thereby providing high-quality input data for subsequent calculation and analysis modules, ensuring that the system can still maintain high accuracy in a dynamically changing environment.

[0059] After completing data preprocessing, the data calculation module 3 conducts in-depth data integration and calculation to generate multiple key indicators, including the human flow characteristic linkage coefficient S1, the vehicle flow characteristic linkage coefficient S2, and the environmental characteristic linkage coefficient S3. These coefficients reflect the relationship between human flow, vehicle flow and environmental factors, and reveal potential traffic flow change trends and safety hazards. In addition, the module will also calculate the human flow risk reference coefficient FX1, the vehicle flow risk reference coefficient FX2 and the environmental risk reference coefficient FX3, which are used to comprehensively evaluate the risk status faced by the current transportation system. The core task of this module is to extract key information through scientific calculation methods and models, and provide necessary indicator basis for subsequent data analysis and decision support.

[0060] The data analysis module 4 is responsible for comparing the thresholds of the pedestrian flow characteristic linkage coefficient S1, the vehicle flow characteristic linkage coefficient S2 and the environmental characteristic linkage coefficient S3 to generate a first comparison result. By comparing the calculated coefficients with the preset pedestrian flow characteristic linkage threshold Y1, the vehicle flow characteristic linkage threshold Y2 and the environmental characteristic linkage threshold Y3, the system can evaluate whether there are abnormal fluctuations in the current traffic flow and environmental conditions, and promptly discover possible safety hazards. At the same time, the analysis module will also compare the risk reference coefficient with the preset risk reference threshold to generate a second comparison result to determine whether there is a potential safety risk in the current traffic. Through comparative analysis, this module can accurately identify the changing trend of traffic conditions, and determine whether risk response measures need to be taken based on the analysis results, thereby providing real-time and effective decision support for traffic managers.

[0061] Feedback module 5 is responsible for delivering the first comparison result and the second comparison result to the end user, ensuring that relevant personnel can obtain the system analysis results in a timely manner. Through this module, traffic management personnel can understand the current traffic safety situation in real time, especially when abnormal fluctuations occur, and can quickly take corresponding dispatching and management measures. This module enables the system to dynamically adjust traffic flow, adjust safety warning levels or initiate emergency response procedures based on real-time data, thereby improving the emergency response capabilities of the transportation system. Through the feedback mechanism, the system can ensure that the data analysis results are seamlessly delivered to decision makers, providing timely guidance for subsequent operations and responses.

[0062] Compared with traditional traffic safety monitoring systems, this system realizes comprehensive monitoring of traffic flow, environmental conditions and risk factors through comprehensive collection, precise preprocessing, scientific calculation and in-depth analysis. Data collection module 1 ensures the comprehensiveness and real-time nature of information collection; data preprocessing module 2 provides data cleaning and standardization support to ensure data quality; data calculation module 3 obtains linkage coefficient and risk reference coefficient through precise calculation, providing important evaluation indicators for the system; data analysis module 4 realizes threshold comparison and risk assessment, providing intelligent decision support; feedback module 5 improves the speed and accuracy of emergency response through real-time feedback mechanism. Unlike traditional static monitoring systems, this system can perceive and analyze traffic and environmental changes in real time, predict potential risks in advance, and greatly enhance the intelligence and response capabilities of traffic management. This integrated and intelligent early warning system not only improves the accuracy of traffic safety prevention, but also significantly enhances the ability to cope with complex traffic conditions and emergencies, providing advanced technical guarantees for the safety management of modern urban rail transit.

[0063] Example 2: Please refer to Figure 1 The data preprocessing module 2 preprocesses the data including cleaning, noise removal and missing value filling, and dimensionless processing is performed on the preprocessed first data set, the second data set and the third data set.

[0064] In this embodiment: During the data collection process, due to equipment failure, signal interference, etc., there may be abnormal data and erroneous information. The data cleaning step can effectively eliminate these invalid data and ensure the accuracy and reliability of the input data. This provides a high-quality data foundation for subsequent data calculation and analysis, thereby improving the early warning accuracy of the entire system and reducing misjudgments and omissions caused by data quality issues.

[0065] In urban rail transit systems, real-time data is often interfered by a variety of external factors, such as environmental changes, electromagnetic interference, or equipment errors. Noise removal technology can effectively filter out these interference factors, making the data smoother and more stable. This not only optimizes the data quality during the calculation process, but also improves the system's ability to respond to real-time traffic changes and avoids the adverse effects of noise on the decision-making process.

[0066] Missing values ​​may occur during data collection due to equipment failure or communication interruption. The missing value filling step fills these missing data using appropriate interpolation or prediction methods to ensure the integrity of the data set. By accurately filling missing values, the system can more comprehensively reflect traffic conditions and environmental factors, reduce analysis bias caused by incomplete data, and improve the system's prediction and risk assessment capabilities.

[0067] Data sets from different sources may have different dimensions and units, which will affect the uniformity and comparability of the data. Through dimensionless processing, the system can eliminate the differences between different data scales, so that all data can be compared and analyzed under the same standards. Dimensionless processing not only improves the effect of data integration, but also enhances the compatibility between different data sets, providing a fair basis for the subsequent calculation of linkage coefficients.

[0068] The introduction and optimization of this system greatly improves the quality and consistency of data and eliminates noise and errors that may affect the accuracy and reliability of the system. These preprocessing steps provide more accurate and stable data support for subsequent calculations, analysis and risk assessment, enabling the entire system to make more accurate and timely warnings when facing complex and changing traffic conditions and environmental factors. This improvement ensures the efficiency and reliability of the urban rail transit information safety warning system in a dynamic environment, and further enhances the ability of intelligent decision-making and the accuracy of emergency response.

[0069] Example 3: Please refer to Figure 1 , the human flow characteristic linkage coefficient S1 of the data calculation module 3 is calculated and obtained by the following formula:

[0070]

[0071] In the formula: A is the total flow of people, B is the instantaneous flow of people, C is the flow density, I is the area of ​​the region, and ln is the logarithmic function.

[0072] In this embodiment: By introducing the logarithmic function ln, the calculation formula can effectively handle the nonlinear relationship and large-scale fluctuations of the data. In the urban rail transit system, especially when the data such as passenger flow changes greatly, the data often shows the characteristics of exponential growth or decay. The logarithmic transformation can convert these nonlinear relationships into linear ones, so that the change trend of the data is smoother, reducing the impact of extreme values ​​on the calculation results, and improving the stability and accuracy of the calculation. This processing can ensure the adaptability of the system to various changes in the context of complex traffic and environment, and avoid errors caused by drastic fluctuations in data.

[0073] The calculation formula combines the total passenger flow A, instantaneous passenger flow B, passenger flow density C and regional area I. By calculating the linkage coefficient, it can fully reflect the dynamic changes of passenger flow at different time and space scales. In this way, the system can not only analyze the instantaneous traffic flow, but also reveal the relationship between passenger flow and regional size. This linkage coefficient can more accurately capture the complex interaction between traffic flow and environmental factors, help discover potential traffic safety hazards and congestion points, and provide more accurate data support for traffic management and scheduling.

[0074] By accurately calculating the linkage coefficient S1 of the pedestrian flow characteristics, the system can better evaluate the proportional relationship between different traffic flows and the impact of regional conditions on pedestrian flow. For example, when a large number of people suddenly appear in a certain period or area, the system can promptly identify the mismatch between the density of pedestrian flow and the area of ​​the area, thereby predicting possible traffic pressure and safety risks. This calculation method makes traffic monitoring not limited to surface traffic data, but goes deep into the inherent connection between various factors, thereby improving the overall risk assessment and early warning capabilities.

[0075] Since the flow and density of urban rail transit may change dramatically over time and environmental conditions, traditional calculation methods based on static data often cannot effectively capture these changes. However, by combining logarithmic functions with multidimensional data, this calculation method can flexibly respond to such changes, adjust and optimize the calculation results in real time, and improve the system's response speed and accuracy to sudden traffic changes. Through this dynamic adaptability, the system can better support real-time decision-making and ensure that traffic can remain smooth and safe during peak hours or special circumstances.

[0076] The design of this calculation formula significantly improves the system's ability to cope with complex traffic conditions. By introducing logarithmic transformation, the system can effectively eliminate extreme fluctuations in data, making the calculation results more stable and reliable. At the same time, by comprehensively considering the linkage between passenger flow, instantaneous flow, passenger density and regional area, the system can deeply analyze the changing trend of passenger flow under different conditions and provide a more accurate risk assessment basis for traffic safety management. This improvement improves the intelligence level and accuracy of the traffic monitoring system, can more effectively prevent potential safety hazards, optimize traffic flow management, and thus better ensure the smooth operation and safety of the urban rail transit system.

[0077] Example 4: Please refer to Figure 1 The data calculation module 3 calculates the vehicle flow characteristic linkage coefficient S2 through the following formula:

[0078]

[0079] Where: E is the instantaneous traffic flow, D is the total traffic flow, F is the traffic density, J is the road length, and ln is the logarithmic function.

[0080] In this embodiment: Introducing the logarithmic function ln helps to deal with the nonlinear characteristics of vehicle flow data. In urban rail transit systems, vehicle flow and vehicle flow density often show exponential changes, especially during peak hours or abnormal conditions, the fluctuation of vehicle flow may be very drastic. Through logarithmic transformation, the system can transform these nonlinear relationships into linear relationships, reduce the impact of extreme values ​​on the calculation results, and provide smoother and more stable calculation results. This enables the system to maintain high calculation accuracy and stability when facing complex and volatile traffic environments.

[0081] The calculation formula combines the instantaneous traffic volume E, the total traffic volume D, the traffic density F, and the road length J. The linkage analysis of these factors can reveal the complex relationship between traffic volume and road conditions. For example, the ratio of instantaneous traffic volume to total traffic volume reflects the current traffic density, while the relationship between traffic density and road length shows the impact of road carrying capacity on traffic flow. Through such linkage coefficients, the system can comprehensively evaluate the dynamic changes of traffic flow and more accurately judge the utilization of road resources and potential traffic congestion risks.

[0082] By comprehensively considering the relationship between traffic density and road length, the system can effectively evaluate the load of roads under different traffic conditions. When the traffic density is too high or the road length is insufficient, the system can promptly identify potential bottlenecks or high-risk areas. Through the joint analysis of traffic volume and road conditions, the system can accurately predict the changing trend of traffic flow, identify possible congestion points and safety hazards, and thus provide a scientific basis for traffic dispatch and emergency response.

[0083] The traffic volume in urban rail transit systems is usually affected by factors such as weather, events, and time, resulting in large fluctuations in traffic volume. Traditional monitoring methods may only rely on the instantaneous value or total volume of traffic volume, but fail to fully consider the dynamic changes in traffic flow. Through the linkage analysis of multiple factors such as instantaneous traffic volume, total traffic volume, and traffic density, the calculation formula can better reflect the volatility of traffic flow and improve the system's response speed to traffic changes. Especially during peak hours or when emergencies occur, the system can adjust the warning information in a timely manner to ensure that traffic managers can respond quickly.

[0084] Through logarithmic transformation and comprehensive analysis of multi-dimensional factors, this system has greatly improved the calculation accuracy of traffic flow characteristics and its adaptability to dynamic traffic environments. By combining key parameters such as traffic flow, traffic density and road length, the system can more comprehensively evaluate the current status of traffic flow and road resources, and accurately identify potential traffic risks and congestion trends. Compared with traditional traffic monitoring methods, this linkage analysis method is more intelligent and refined, and can reflect changes in traffic flow in real time, thereby providing more accurate decision-making support for traffic management. Overall, this method improves the early warning capability, dispatching efficiency and emergency response capability of the transportation system, and provides a more powerful technical guarantee for the safety management and traffic optimization of urban rail transit.

[0085] Example 5: Please refer to Figure 1 The data calculation module 3 calculates and obtains the environmental characteristic linkage coefficient S3 through the following formula:

[0086]

[0087] Where: G is the real-time temperature, H is the real-time rainfall, I is the regional area, J is the road length, K is the real-time visibility, and ln is the logarithmic function.

[0088] In this embodiment: the formula combines multiple environmental factors such as real-time temperature G, real-time rainfall H, real-time visibility K, area I and road length J for calculation, fully reflecting the impact of different environmental conditions on traffic flow and traffic safety. For example, too high or too low temperature may affect the friction of the road, too much rainfall may lead to limited sight distance, and poor visibility directly affects the driver's reaction time and safety. By integrating these environmental parameters, the system can comprehensively evaluate the comprehensive impact of the external environment on traffic safety and traffic efficiency, and provide more accurate risk warnings.

[0089] The logarithmic transformation ln in the formula can effectively process and adjust the nonlinear relationship between environmental parameters. In urban rail transit systems, changes in environmental factors such as temperature, rainfall, and visibility often show large fluctuations or nonlinear trends. Through the application of logarithmic functions, these changes can be smoothed, reducing the interference of extreme values ​​on the calculation results, and improving the stability of the data and the robustness of the system. This helps the system maintain high accuracy and reliability in a dynamically changing traffic environment, ensuring that the early warning system can still accurately predict potential risks in harsh environments.

[0090] Environmental factors such as temperature, rainfall, and visibility have a direct impact on rail transit safety and efficiency. For example, high temperatures may cause track expansion, water accumulation may cause landslides, and excessive rainfall may reduce visibility, seriously affecting the driver's judgment. Through the linkage analysis of environmental characteristics, the system can monitor environmental changes in real time, and assess its potential threats to the transportation system based on the trend of changes, and warn of possible accident risks in advance. This sensitivity enhances the system's ability to respond to extreme weather events and sudden environmental changes, and provides a scientific basis for traffic scheduling and safety management.

[0091] The calculation formula also introduces two factors related to transportation infrastructure: regional area I and road length J, reflecting the interactive effects between environmental factors and road capacity and regional scale. The area and road length of different regions may affect the distribution of traffic flow, and changes in environmental factors may have different impacts on these infrastructures. For example, in a larger area, the impact of temperature and rainfall may show regional differences; on longer roads, the impact of visibility and rainfall may be more significant. By comprehensively considering these factors, the system can more accurately predict changes in traffic flow and safety conditions under different environmental conditions, thereby more effectively scheduling and managing.

[0092] This system greatly improves the system's adaptability to complex environmental changes by integrating multiple environmental factors and traffic conditions. Through comprehensive analysis of environmental factors such as real-time temperature, rainfall, visibility, etc., the system can accurately assess traffic safety hazards and traffic flow changes under different weather and environmental conditions, thereby providing traffic managers with more sophisticated risk forecasts. Compared with traditional methods, this improvement not only improves the sensitivity to changes in the external environment, but also enhances the system's intelligent decision-making capabilities. In the face of sudden extreme weather or unstable environments, the system can adjust traffic scheduling and early warning strategies in a timely manner to ensure traffic safety and effectively improve the operational efficiency of rail transit.

[0093] Example 6: Please refer to Figure 1 The data calculation module 3 calculates and obtains the pedestrian flow risk reference coefficient FX1, the vehicle flow risk reference coefficient FX2 and the environmental risk reference coefficient FX3 respectively through the following formulas:

[0094]

[0095] Where: A is the total pedestrian flow, B is the instantaneous pedestrian flow, C is the pedestrian density, I is the area, E is the instantaneous vehicle flow, D is the total vehicle flow, F is the vehicle density, J is the road length, G is the real-time temperature, H is the real-time rainfall, and K is the real-time visibility;

[0096] S1 is the linkage coefficient of human flow characteristics, S2 is the linkage coefficient of vehicle flow characteristics, and S3 is the linkage coefficient of environmental characteristics.

[0097] In this embodiment: the calculation formula combines the human flow characteristic linkage coefficient S1, vehicle flow characteristic linkage coefficient S2 and environmental characteristic linkage coefficient S3 with multiple key factors such as traffic flow, human flow and vehicle flow, environmental conditions such as temperature, rainfall, visibility, road conditions, road length, and vehicle flow density to calculate, which can comprehensively and comprehensively analyze the risks of the transportation system. Compared with the single factor analysis method, this multi-dimensional comprehensive calculation can more accurately reflect the overall risk status of the transportation system under multiple influences, and improve the response ability of the early warning system to complex situations.

[0098] The specific refinement and product calculation of pedestrian flow, vehicle flow and environmental factors in the formula can accurately reveal the inherent connection between these factors. For example, the combination of the ratio of instantaneous pedestrian flow to total pedestrian flow, and pedestrian density to regional area can more finely evaluate the impact of pedestrian density on the overall transportation system. Similarly, the relationship between vehicle flow, vehicle density and road length can reflect the balance between road carrying capacity and vehicle flow. This sophisticated risk calculation can help the system more accurately predict potential traffic congestion, accident risks or safety hazards, thereby achieving accurate early warning and scheduling.

[0099] By linking environmental risks such as temperature, rainfall, and visibility with traffic flow, pedestrian flow, and vehicle flow, the system can promptly identify the potential impact of environmental changes on traffic flow. For example, hot weather may cause road quality to deteriorate, while rainfall or low visibility may hinder traffic flow and increase the risk of accidents. By real-time monitoring of these environmental changes, the system can automatically adjust traffic scheduling strategies according to changes in environmental conditions and issue alarms in a timely manner, thereby reducing traffic safety accidents caused by environmental factors.

[0100] This calculation formula can not only analyze the impact of a single factor on traffic flow, but also dynamically adjust the weights and interactions between different factors. As traffic flow and environmental factors change in real time, the risk reference coefficient will be dynamically adjusted, allowing the system to flexibly respond to possible traffic congestion or safety accidents at different times and under different environmental conditions. For example, when the traffic volume is large and visibility is poor during a certain period of time, the system can adjust the relevant risk coefficients to improve the sensitivity of the warning and take emergency measures in advance. This dynamic adaptability greatly enhances the system's ability to respond to emergencies and uncertain factors.

[0101] This system provides a comprehensive risk assessment model through comprehensive analysis of multi-dimensional data such as pedestrian flow, vehicle flow, and environmental factors. The risk reference coefficient can timely identify and determine whether there is a traffic risk based on this assessment model, and give corresponding warnings. Compared with traditional single indicator monitoring, this comprehensive assessment model can more accurately capture the potential multi-risks in the traffic system, allowing managers to take effective countermeasures at an earlier stage and effectively reduce the probability of accidents.

[0102] Example 7: Please refer to Figure 1 , the first comparison result generated by the data analysis module 4 is as follows:

[0103] When S1>Y1, it means that the pedestrian flow characteristics need to be linked with the knowledge graph to analyze the risk and generate the pedestrian flow risk reference coefficient FX1. When S1≤Y1, it means that it is not necessary to link the pedestrian flow characteristics with the knowledge graph to analyze the risk.

[0104] When S2>Y2, it means that the traffic flow characteristics need to be linked with the knowledge graph to analyze the risk and generate the traffic flow risk reference coefficient FX2. When S2>Y2, it means that the traffic flow characteristics do not need to be linked with the knowledge graph to analyze the risk.

[0105] When S3>Y3, it means that it is necessary to link environmental characteristics with the knowledge graph to analyze risks and generate an environmental risk reference coefficient FX3. When S3>Y3, it means that it is not necessary to link environmental characteristics with the knowledge graph to analyze risks.

[0106] The second comparison result generated by the data analysis module 4 is as follows:

[0107] When FX1>R1, it means that the current traffic has a risk of human traffic type; when FX1≤R1, it means that the current traffic does not have a risk of human traffic type;

[0108] When FX2>R2, it means that the current traffic has a traffic flow type risk, and when FX2≤R2, it means that the current traffic does not have a traffic flow type risk;

[0109] When FX3>R3, it means that there is no environmental risk in the current traffic; when FX3≤R3, it means that there is no environmental risk in the current traffic;

[0110] R1 is the risk threshold for pedestrian flow type, R2 is the risk threshold for vehicle flow type, and R3 is the risk threshold for environment type.

[0111] In this embodiment, by comparing the linkage coefficient S1 of the pedestrian flow feature, the linkage coefficient S2 of the vehicle flow feature, and the linkage coefficient S3 of the environmental feature with the preset thresholds Y1, Y2, and Y3, the system can determine whether it is necessary to link the corresponding features with the knowledge graph for analysis based on the actual traffic and environmental conditions. This mechanism enables the system to automatically identify whether there are potential safety hazards and actively call the knowledge graph for in-depth analysis.

[0112] Through threshold judgment, the system can dynamically adjust the depth and accuracy of risk analysis. If an indicator exceeds the set threshold, for example, S1>Y1, it means that the indicator has a greater impact on traffic safety. The system will automatically enter a more in-depth analysis mode to promptly identify potential safety risks. This intelligent linkage mechanism avoids over-analysis and improves the efficiency and response speed of the system. The system not only identifies potential risks, but also automatically links related traffic characteristics with knowledge graphs for analysis. Through deep learning and graph analysis, this process can identify the complex correlations and potential impacts between different factors, thereby providing decision support for subsequent emergency responses.

[0113] By comparing the pedestrian risk reference coefficient FX1, vehicle risk reference coefficient FX2 and environmental risk reference coefficient FX3 with the preset thresholds, the system can determine whether the current traffic has pedestrian risk, vehicle risk or environmental risk. If the risk reference coefficient exceeds the corresponding threshold, it means that the current traffic is facing a certain type of risk, and the system will trigger the corresponding early warning and processing mechanism.

[0114] Through detailed risk classification, the system can provide accurate early warnings for different types of risks. For example, if the traffic flow risk reference coefficient FX2 exceeds R2, the system will clearly indicate that there is a traffic flow type risk, and the relevant departments can make specific scheduling adjustments for this problem. This classified early warning method greatly enhances the effectiveness of traffic management and safety assurance, so that the early warning is not limited to a single dimension, but is based on a comprehensive assessment and response based on different types of risks.

[0115] By comparing the characteristic linkage coefficient with the preset threshold, the system can achieve automated and real-time decision support. When abnormal parameters such as traffic flow and environmental factors are detected, the system will automatically generate comparison results and initiate corresponding early warning and adjustment mechanisms based on the results. This process does not rely on human intervention, which improves the system's response speed and emergency handling capabilities. This automated decision-making process greatly reduces the delay of human intervention, allowing the system to respond quickly to emergencies or peak hours, promptly discover potential traffic safety hazards, quickly initiate early warnings and make corresponding decision adjustments, significantly improving the intelligence level of the transportation system.

[0116] Through the dual analysis of the first comparison results and the second comparison results, the system can comprehensively consider the interactive impact of various traffic and environmental factors, comprehensively evaluate the risks of traffic flow, vehicle flow, environment and other aspects, so as to achieve comprehensive optimization management of the transportation system. For example, when traffic pressure is high, the system may automatically adjust the operating frequency of rail transit or optimize traffic signal timing through multi-dimensional comparison of passenger flow, vehicle flow and environmental data to alleviate traffic pressure and improve operational efficiency.

[0117] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0118] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. 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. An urban rail transit information safety early warning system, characterized in that: It comprises a data acquisition module (1), a data preprocessing module (2), a data calculation module (3), a data analysis module (4) and a feedback module (5); The data collection module (1) is used to collect traffic signals and integrate them into a first data set, a second data set and a third data set; The data preprocessing module (2) is used to preprocess and dimensionlessly transform the first data set, the second data set and the third data set; The data calculation module (3) is used to integrate and calculate the first data set, the second data set and the third data set, so as to respectively generate a pedestrian flow characteristic linkage coefficient S1, a vehicle flow characteristic linkage coefficient S2, an environmental characteristic linkage coefficient S3, and a pedestrian flow risk reference coefficient FX1, a vehicle flow risk reference coefficient FX2 and an environmental risk reference coefficient FX3; The data analysis module (4) is used to compare the pedestrian flow feature linkage coefficient S1, the vehicle flow feature linkage coefficient S2 and the environmental feature linkage coefficient S3 with the preset pedestrian flow feature linkage threshold Y1, the vehicle flow feature linkage threshold Y2 and the environmental feature linkage threshold Y3, respectively, so as to generate a first comparison result, and judge whether it is necessary to associate the pedestrian flow feature, the vehicle flow feature and the environmental feature with the knowledge graph according to the first comparison result, and compare the risk reference coefficient with the preset risk reference threshold to generate a second comparison result, and judge whether there is a risk in the current traffic according to the second comparison result; The feedback module (5) is used to send the first comparison result and the second comparison result to the terminal.

2. The urban rail transit information safety early warning system according to claim 1 is characterized by: The data preprocessing module (2) performs preprocessing steps including data cleaning, noise removal and missing value filling, and performs dimensionless transformation on the preprocessed first data set, second data set and third data set.

3. An urban rail transit information safety warning system according to claim 2, characterized in that: The data acquisition module (1) acquires pedestrian flow characteristic data, vehicle flow characteristic data and environmental characteristic data in real time through a distributed sensor network, thereby generating a first data set, a second data set and a third data set; The first data set includes total pedestrian flow A, instantaneous pedestrian flow B, and pedestrian flow density C; The second data set includes total traffic volume D, instantaneous traffic volume E, and traffic density F; The third data set includes real-time temperature G, real-time rainfall H, regional area I, road length J and real-time visibility K.

4. The urban rail transit information safety early warning system according to claim 3 is characterized by: The human flow characteristic linkage coefficient S1 of the data calculation module (3) is calculated and obtained by the following formula: In the formula: A is the total flow of people, B is the instantaneous flow of people, C is the flow density, I is the area of ​​the region, and ln is the logarithmic function.

5. The urban rail transit information safety warning system according to claim 4 is characterized in that: The data calculation module (3) calculates and obtains the vehicle flow characteristic linkage coefficient S2 through the following formula: Where: E is the instantaneous traffic flow, D is the total traffic flow, F is the traffic density, J is the road length, and ln is the logarithmic function.

6. The urban rail transit information safety early warning system according to claim 5 is characterized by: The data calculation module (3) calculates and obtains the environmental characteristic linkage coefficient S3 through the following formula: Where: G is the real-time temperature, H is the real-time rainfall, I is the regional area, J is the road length, K is the real-time visibility, and ln is the logarithmic function.

7. The urban rail transit information safety early warning system according to claim 6 is characterized by: The data calculation module (3) calculates and obtains the pedestrian flow risk reference coefficient FX1, the vehicle flow risk reference coefficient FX2 and the environmental risk reference coefficient FX3 respectively through the following formulas: Where: A is the total pedestrian flow, B is the instantaneous pedestrian flow, C is the pedestrian density, I is the area, E is the instantaneous vehicle flow, D is the total vehicle flow, F is the vehicle density, J is the road length, G is the real-time temperature, H is the real-time rainfall, and K is the real-time visibility; S1 is the linkage coefficient of human flow characteristics, S2 is the linkage coefficient of vehicle flow characteristics, and S3 is the linkage coefficient of environmental characteristics.

8. The urban rail transit information safety warning system according to claim 7 is characterized by: The first comparison result generated by the data analysis module (4) is specifically as follows: When S1>Y1, it means that the pedestrian flow characteristics need to be linked with the knowledge graph to analyze the risk and generate the pedestrian flow risk reference coefficient FX1. When S1≤Y1, it means that it is not necessary to link the pedestrian flow characteristics with the knowledge graph to analyze the risk. When S2>Y2, it means that the traffic flow characteristics need to be linked with the knowledge graph to analyze the risk and generate the traffic flow risk reference coefficient FX2. When S2>Y2, it means that the traffic flow characteristics do not need to be linked with the knowledge graph to analyze the risk. When S3>Y3, it means that it is necessary to link environmental characteristics with the knowledge graph to analyze risks and generate an environmental risk reference coefficient FX3. When S3>Y3, it means that it is not necessary to link environmental characteristics with the knowledge graph to analyze risks.

9. An urban rail transit information safety warning system according to claim 8, characterized in that: The second comparison result generated by the data analysis module (4) is specifically as follows: When FX1>R1, it means that the current traffic has a risk of human traffic type; when FX1≤R1, it means that the current traffic does not have a risk of human traffic type; When FX2>R2, it means that the current traffic has a traffic flow type risk, and when FX2≤R2, it means that the current traffic does not have a traffic flow type risk; When FX3>R3, it means that there is no environmental risk in the current traffic; when FX3≤R3, it means that there is no environmental risk in the current traffic; R1 is the risk threshold for pedestrian flow type, R2 is the risk threshold for vehicle flow type, and R3 is the risk threshold for environment type.

Images