Intelligent monitoring and early warning method and system for high-speed railway disasters

Abstract

The present invention relates to the technical field of data processing, and provides an intelligent monitoring and early warning method and system for high-speed railway disasters, comprising: constructing a high-speed railway monitoring and positioning network and establishing a high-speed railway monitoring database by setting up high-speed railway ultrasonic anemometers and piezoelectric rain gauges and other equipment; extracting periodic monitoring data in the database to evaluate the disaster coefficient, and when a preset disaster coefficient is reached, high-speed railway disaster positioning is performed, high-speed railway data in the disaster area is obtained, and data are analyzed and traced to determine the high-speed railway tracing disaster information, and early warning information is sent, thereby solving the technical problem that the accuracy and timeliness of disaster early warnings in specific high-speed railway scenarios are insufficient, and effective early warnings for various natural disasters cannot be given in a timely manner, and achieving the technical effect of timely and accurately discovering possible disasters and improving the safety and reliability of high-speed railways through real-time and all-weather monitoring of the environment along the high-speed railway.

Description

Technical Field

[0001] The present invention relates to the technical field related to data processing, and in particular to an intelligent monitoring and early warning method and system for high-speed railway disasters. Background Art

[0002] At present, the construction and operation of high-speed railways have made great progress. However, force majeure factors such as natural disasters still pose a serious threat to railway transportation safety. Common disaster prevention measures often focus on post-event handling rather than pre-event warning, so they cannot effectively prevent the occurrence of disasters. Therefore, developing a monitoring and early warning method for high-speed railway disasters can detect and warn of possible disasters in advance, which is of great significance to ensuring the safe operation of high-speed railways.

[0003] Generally, regular inspections are carried out on the equipment, roadbed, tracks, etc. of high-speed rail lines to identify potential hazards and problems. The advantage is that potential problems can be discovered early, but due to the lack of effective monitoring methods and intelligent analysis of monitoring data, the existing early warning systems are often unable to accurately predict the occurrence of disasters.

[0004] In summary, the existing technology has technical problems such as insufficient accuracy and timeliness of disaster warnings directly collected in specific scenarios of high-speed railways, and inability to provide effective warnings for various natural disasters in a timely manner. Summary of the invention

[0005] This application provides an intelligent monitoring and early warning method and system for high-speed railway disasters, aiming to solve the technical problems in the prior art of insufficient accuracy and timeliness of disaster warnings in specific high-speed railway scenarios, and the inability to effectively warn of various natural disasters in a timely manner.

[0006] In view of the above problems, the present application provides an intelligent monitoring and early warning method and system for high-speed railway disasters.

[0007] The first aspect disclosed in the present application provides an intelligent monitoring and early warning method for high-speed railway disasters, wherein the method includes: constructing a high-speed railway monitoring and positioning network based on the set high-speed railway ultrasonic anemometer and piezoelectric rain gauge; connecting the high-speed railway monitoring and positioning network to establish a high-speed railway monitoring database; extracting periodic monitoring data from the high-speed railway monitoring database, and evaluating the disaster coefficient of the monitored wind and rain data information and high-speed railway operation data information; when the preset disaster coefficient is reached, locating the high-speed railway disaster through the high-speed railway monitoring and positioning network, and obtaining the high-speed railway data in the disaster area; conducting disaster analysis and tracing on the high-speed railway data and disaster coefficient in the disaster area, determining the high-speed railway tracing disaster information, and sending early warning information.

[0008] Another aspect disclosed in the present application provides an intelligent monitoring and early warning system for high-speed railway disasters, wherein the system includes: a monitoring and positioning network module, which is used to build a high-speed railway monitoring and positioning network based on the set high-speed railway ultrasonic anemometer and piezoelectric rain gauge; a database establishment module, which is used to connect the high-speed railway monitoring and positioning network to establish a high-speed railway monitoring database; a disaster coefficient assessment module, which is used to extract periodic monitoring data in the high-speed railway monitoring database, and perform disaster coefficient assessment on the wind and rain data information and high-speed railway operation data information obtained by monitoring; a high-speed railway disaster positioning module, which is used to locate high-speed railway disasters through the high-speed railway monitoring and positioning network when a preset disaster coefficient is reached, and obtain high-speed railway data in the disaster area; an early warning information sending module, which is used to perform disaster analysis and tracing on the high-speed railway data and disaster coefficient in the disaster area, determine the high-speed railway tracing disaster information, and send early warning information.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By utilizing high-speed rail ultrasonic anemometers and piezoelectric rain gauges, a high-speed rail monitoring and positioning network is constructed, and a high-speed rail monitoring database is established; periodic monitoring data in the database is extracted, and disaster coefficient assessment is performed on wind and rain data information as well as high-speed rail operation data information; when the disaster coefficient reaches a preset value, high-speed rail disaster positioning is performed, high-speed rail data in the disaster area is obtained, disaster analysis and source tracing are performed, high-speed rail disaster information is determined, and early warning information is sent, thereby achieving the technical effect of timely and accurate detection of possible disasters and improving the safety and reliability of high-speed rail through real-time, all-weather monitoring of the environment along the high-speed rail.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A possible flow chart of an intelligent monitoring and early warning method for high-speed railway disasters is provided for the embodiment of the present application;

[0013] Figure 2 A possible flow chart of disaster coefficient evaluation in an intelligent monitoring and early warning method for high-speed railway disasters is provided for the embodiment of the present application;

[0014] Figure 3 A possible structural schematic diagram of an intelligent monitoring and early warning system for high-speed railway disasters is provided for the embodiment of the present application.

[0015] Explanation of the reference numerals: monitoring and positioning network module 100, database establishment module 200, disaster coefficient assessment module 300, high-speed rail disaster positioning module 400, early warning information sending module 500. DETAILED DESCRIPTION

[0016] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the embodiment of the present application provides an intelligent monitoring and early warning method for high-speed railway disasters, wherein the method includes:

[0019] Step-1: Build a high-speed rail monitoring and positioning network based on the high-speed rail ultrasonic anemometer and piezoelectric rain gauge.

[0020] Step-2: Connect to the high-speed rail monitoring and positioning network to establish a high-speed rail monitoring database;

[0021] Various sensors are deployed along the high-speed railway, such as high-speed railway ultrasonic wind speed and direction meters, piezoelectric rain gauges, geological sensors, etc., and natural disaster monitoring and early warning are realized through analysis of sensor data. The advantage is that it can monitor in real time and detect potential disasters in time. In this scenario, intelligent monitoring and early warning of various natural disasters can be carried out;

[0022] High-speed rail ultrasonic anemometer is a device that measures wind speed and direction, using the propagation speed and direction changes of ultrasonic waves to measure wind speed and direction; piezoelectric rain gauge is a device that measures rainfall, using the piezoelectric effect to measure rainfall. By setting up high-speed rail ultrasonic anemometers and piezoelectric rain gauges, real-time monitoring of environmental parameters along the high-speed rail can be achieved, and the data obtained in real-time monitoring can be transmitted to the data processing center, building a high-speed rail monitoring and positioning network to monitor the high-speed rail operating environment.

[0023] The high-speed rail monitoring database refers to a database that stores high-speed rail monitoring data. By connecting to the high-speed rail monitoring and positioning network, a large amount of monitoring data can be collected and processed in real time, and a complete high-speed rail monitoring database can be established. The high-speed rail monitoring database can provide a comprehensive grasp of the high-speed rail operating environment, equipment status and other information, providing important data support for the operation management and maintenance of the high-speed rail.

[0024] Step-3: extracting the periodic monitoring data from the high-speed rail monitoring database, and evaluating the disaster coefficient of the wind and rain data information and the high-speed rail operation data information obtained by monitoring;

[0025] Step-4: When the preset disaster coefficient is reached, high-speed rail disaster positioning is performed through the high-speed rail monitoring and positioning network to obtain high-speed rail data in the disaster area;

[0026] Step-5: Conduct disaster analysis and source tracing on the high-speed rail data and disaster coefficients in the disaster area, determine the high-speed rail disaster information, and send warning information

[0027] The periodic monitoring data refers to the monitoring data collected in a certain time period, and the periodic monitoring data includes the collection timestamp; the wind and rain data information refers to the data information related to wind and rain, including wind speed, wind direction, rainfall, etc.; the high-speed rail operation data information refers to various data information during the operation of the high-speed rail, such as speed, position, equipment status, etc.; the disaster coefficient is a coefficient used to evaluate the degree of impact of disasters on the operation of the high-speed rail. By extracting the periodic monitoring data in the high-speed rail monitoring database, the disaster coefficient of the wind and rain data information and the high-speed rail operation data information is evaluated, and the impact of disasters on the operation of the high-speed rail is timely understood, providing a basis for subsequent disaster response and rescue work.

[0028] When the preset disaster coefficient is reached, the high-speed rail disaster is located through the high-speed rail monitoring and positioning network to obtain high-speed rail data in the disaster area.

[0029] The preset disaster coefficient generally refers to a custom-set disaster coefficient threshold; the high-speed rail monitoring and positioning network refers to a network composed of multiple monitoring devices, which is used to monitor the high-speed rail operating environment and equipment status in real time. Compare the disaster coefficient with the preset disaster coefficient: when the disaster coefficient does not reach the preset disaster coefficient, continue monitoring; when the disaster coefficient reaches the preset disaster coefficient, the high-speed rail disaster can be located through the high-speed rail monitoring and positioning network, and the high-speed rail data in the disaster area can be quickly obtained to provide data support for subsequent disaster analysis and tracing.

[0030] Step 3: Conduct disaster analysis and source tracing on the high-speed rail data and disaster coefficients in the disaster area, determine the high-speed rail disaster information, and send early warning information.

[0031] Disaster analysis and tracing refers to the process of analyzing the causes and processes of disasters and tracing back to the source of the disasters; the high-speed rail disaster tracing information includes the specific situation of the high-speed rail disaster and the scope of impact. By analyzing and tracing the high-speed rail data and disaster coefficients in the disaster area, the impact and scope of the disaster on the high-speed rail are determined, the affected high-speed rail equipment and lines are determined, and early warning information is sent to relevant personnel in a timely manner, providing important support for subsequent emergency rescue and decision-making.

[0032] Furthermore, if Figure 2 As shown, extracting the periodic monitoring data in the high-speed rail monitoring database, and evaluating the disaster coefficient of the wind and rain data information and the high-speed rail operation data information obtained by monitoring, the application method includes:

[0033] Dividing nodes according to a preset period to extract periodic monitoring data from the high-speed rail monitoring database;

[0034] The extracted periodic monitoring data are analyzed for unidirectional and multi-directional impact relationships with high-speed rail operation data according to wind direction, wind speed, and rainfall, and a multi-dimensional cost function relationship is obtained by fitting.

[0035] The multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model, and the disaster coefficient assessment model is used to perform disaster coefficient assessment.

[0036] The preset period division node includes a start division node and an end division node. Commonly, it can be set as a period from the start time (i.e., the start division node) to the end time (i.e., the end division node) of a storm, which can generally be set as a period of time, such as one hour or one day, wherein a node refers to a time point within the preset period. By setting the preset period and node, periodic monitoring data is extracted based on the time axis of the high-speed rail monitoring database to provide data support for subsequent analysis;

[0037] Wind direction, wind speed and rainfall are three dimensions that describe natural weather, namely wind direction, speed and rainfall intensity; high-speed rail operation data refers to data such as the travel speed and line status of high-speed rail. Among them, the unidirectional influence relationship refers to the influence of a certain dimension (such as wind direction) on the high-speed rail operation data, and the multi-directional influence relationship refers to the influence of multiple dimensions (such as wind direction and wind speed) on the high-speed rail operation data. The multi-dimensional cost function relationship is obtained by fitting, which can be refined as follows:

[0038] The monitoring data are divided into multiple dimensions according to wind direction, wind speed, and rainfall, that is, the data are classified and analyzed according to different dimensions; each dimension is analyzed for its unidirectional impact relationship with the high-speed rail operation data, for example, the impact of the wind direction dimension on the high-speed rail operation speed, the impact of the wind speed dimension on the high-speed rail operation safety, and the impact of the rainfall dimension on the punctuality of the high-speed rail operation; the impact of multiple dimensions on the high-speed rail operation data is comprehensively considered, for example, the impact of simultaneous changes in wind direction and wind speed on the high-speed rail operation speed, and the impact of simultaneous changes in rainfall and wind speed on the safety of high-speed rail operation; by analyzing the unidirectional and multidirectional impact relationships, a multidimensional cost function relationship is obtained by fitting; by analyzing the periodic monitoring data according to the three dimensions of wind direction, wind speed, and rainfall, and fitting a multidimensional cost function relationship, the specific impact of different meteorological factors on the high-speed rail operation can be understood.

[0039] In the embodiment of the present application, fusion refers to fusing the multi-dimensional cost function relationship together to form a disaster coefficient assessment model, wherein the disaster coefficient refers to an indicator for assessing the possibility of disaster occurrence, and the disaster coefficient along the high-speed railway within a certain time range is assessed through the disaster coefficient assessment model. The disaster coefficient assessment model is obtained to achieve accurate assessment of the disaster coefficient along the high-speed railway, thereby providing guarantee for the safe operation of the high-speed railway.

[0040] Furthermore, the multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model. The method of the present application includes:

[0041] Based on the multi-dimensional cost function relationship, a unidirectional cost function relationship and a multi-directional cost function relationship are obtained, wherein the unidirectional relationship is an influence relationship of a single dimension, and the multi-directional relationship is a cross-overlapping influence relationship of at least two dimensions;

[0042] Based on the multi-directional cost function relationship, performing overlapping difference calculation on the unidirectional cost function relationship including the dimension, and determining the adjustment coefficient;

[0043] The one-way cost function relationships are superimposed, and the adjustment coefficients are used to make correction adjustments to generate the disaster coefficient assessment model.

[0044] The one-way cost function relationship refers to a relationship obtained by calculating the cost function relationship of a certain dimension as an independent variable and the cost function relationship of other dimensions as a constant (similar to the control variable method); the multi-way cost function relationship refers to a cost function relationship involving at least two dimensions of cross-overlapping influence relationships; in the multi-dimensional cost function relationship, variable statistics are performed on each cost function relationship: if the number of variables u=1, the corresponding cost function relationship is a one-way cost function relationship; if the number of variables u≥2, the corresponding cost function relationship is a multi-way cost function relationship; by obtaining one-way cost function relationships and multi-way cost function relationships based on multi-dimensional cost function relationships, a more comprehensive understanding of the mutual influence relationship between different dimensions can be achieved.

[0045] Overlapping difference refers to the overlapping parts between cost function relationships in different dimensions. By calculating the differences of these overlapping parts, the degree of mutual influence between different dimensions can be determined. Among them, the adjustment coefficient refers to the coefficient used to correct the unidirectional cost function relationship. Its size depends on the degree of influence of each dimension in the multi-directional cost function relationship. In simple terms, multi-directional is the influence relationship of several factors superimposed. Sometimes multiple factors put together will enhance the influence effect 1+1 greater than 2. For example, wind and rain have an impact on temperature. Generally, the temperature drop rate after wind and rain are superimposed is much greater than the temperature drop rate of wind plus the temperature drop rate of rain. By calculating the overlapping difference and determining the adjustment coefficient based on the multi-directional cost function relationship, an accurate description of the mutual influence relationship between different dimensions can be achieved, and an accurate basis can be provided for the subsequent disaster coefficient assessment.

[0046] Superposition refers to merging multiple one-way cost function relationships according to certain rules to obtain an overall cost function relationship; correction adjustment refers to using the adjustment coefficient to correct and optimize the superimposed cost function relationship to make it more in line with the actual situation. Each one-way cost function relationship is superimposed, and each adjustment coefficient is used to perform correction adjustment (similarly, the adjustment coefficient is used as a weight value to perform weighted adjustment on each one-way cost function relationship) to generate the disaster coefficient assessment model. By superimposing each one-way cost function relationship and using the adjustment coefficient to perform correction adjustment, a more accurate and comprehensive disaster coefficient assessment model is obtained, thereby achieving an accurate assessment of the disaster coefficient along the high-speed rail line, thereby providing protection for the safe operation of the high-speed rail.

[0047] Furthermore, the high-speed rail disaster location is performed through the high-speed rail monitoring and positioning network to obtain high-speed rail data in the disaster area. The present application method includes:

[0048] Obtain the high-speed rail line and the operating equipment around the line, and establish a high-speed rail line positioning network by using the computing equipment around the line as marking points and the high-speed rail line as a connecting line;

[0049] Obtaining the monitoring radiation range of the high-speed rail ultrasonic anemometer and piezoelectric rain gauge, and marking the radiation range of the high-speed rail monitoring and positioning network based on the monitoring radiation range;

[0050] The high-speed rail line positioning network is superimposed on the high-speed rail monitoring and positioning network, and the high-speed rail data in the disaster area is determined using the positioning information of the high-speed rail monitoring data.

[0051] High-speed rail lines refer to the track lines on which high-speed trains travel, and peripheral operating equipment refers to equipment associated with high-speed rail lines, such as overhead lines, track signal systems, etc.; marking points refer to places or locations used to mark peripheral equipment of high-speed rail lines; connecting lines refer to networks or lines that connect marking points; obtain high-speed rail lines and peripheral operating equipment of the lines, use the peripheral computing equipment of the lines as marking points and the high-speed rail lines as connecting lines, connect the marking points, and finally obtain the high-speed rail line positioning network. By obtaining information on high-speed rail lines and peripheral operating equipment, using these devices as marking points, and using connecting lines to establish a high-speed rail line positioning network, it is possible to achieve visual management and monitoring of high-speed rail lines and their peripheral equipment.

[0052] The ultrasonic anemometer is a device for measuring wind speed and direction, and the piezoelectric rain gauge is a device for measuring rainfall; the monitoring radiation range refers to the range or area that the monitoring equipment can monitor; marking refers to marking or identifying the monitoring range of these devices on the high-speed rail monitoring and positioning network; obtaining the monitoring radiation range of the high-speed rail ultrasonic anemometer and piezoelectric rain gauge, and marking the monitoring radiation range on the high-speed rail monitoring and positioning network. By obtaining the monitoring radiation range of the ultrasonic anemometer and piezoelectric rain gauge and marking it on the high-speed rail monitoring and positioning network, the monitoring range of these devices can be visualized and managed, making it easier to understand their coverage and usage.

[0053] Superimposing the high-speed rail line positioning network with the high-speed rail monitoring and positioning network simply means merging or superimposing two or more different data or information to obtain more comprehensive or more accurate information. The positioning information of the high-speed rail monitoring data refers to the information related to the position of the high-speed rail train obtained by the monitoring equipment, and the high-speed rail data in the disaster area refers to the high-speed rail data related to the disaster and in the disaster area. Using the positioning information of the high-speed rail monitoring data, the edge coordinate set of the disaster can be determined, and then the high-speed rail data in the disaster area can be circled. By superimposing the high-speed rail line positioning network with the high-speed rail monitoring and positioning network, and using the positioning information of the high-speed rail monitoring data to determine the high-speed rail data in the disaster area, it is possible to quickly obtain information such as the train position, speed, and operating status in the disaster area, providing timely and accurate data support for disaster response and rescue work.

[0054] Furthermore, the disaster analysis and source tracing are performed on the high-speed rail data and disaster coefficients in the disaster area to determine the high-speed rail disaster information. The application method includes:

[0055] According to the high-speed rail data in the disaster area, analyze the regional equipment accommodation environment and equipment abnormal sensitivity, and evaluate the risk tolerance coefficient of risk equipment in the disaster area;

[0056] The difference value is calculated using the disaster coefficient and the risk tolerance coefficient, and the risk equipment is sequenced according to the risk excess coefficient to determine the high-speed rail retrospective disaster information.

[0057] According to the high-speed rail data in the disaster area, analyze the regional equipment accommodation environment and equipment abnormal sensitivity, and evaluate the risk tolerance coefficient of risk equipment in the disaster area;

[0058] The regional equipment accommodation environment refers to the environmental conditions of the equipment location, such as temperature, humidity, pressure, etc.; the equipment abnormal sensitivity refers to the sensitivity of the equipment to abnormal conditions or interference; and the risk tolerance coefficient refers to the equipment's ability to withstand risks or interference. By analyzing the regional equipment accommodation environment and equipment abnormal sensitivity of the high-speed rail data in the disaster area, the operating environment and operating status of the equipment in the disaster area can be determined, and its sensitivity to abnormal conditions can be evaluated.

[0059] The disaster coefficient refers to a coefficient for assessing the impact of disasters on high-speed rail operations; the risk excess coefficient refers to a coefficient for assessing the risk equipment's tolerance beyond the normal range; the normalization process refers to sorting the risk equipment according to the size of the risk excess coefficient. The larger the difference value corresponding to the disaster coefficient, the higher the risk index; the smaller the difference value corresponding to the disaster coefficient, the lower the risk index; the risk equipment is normalized according to the risk excess coefficient (large difference value → small difference value) to determine the high-speed rail retrospective disaster information. By calculating the difference between the disaster coefficient and the risk tolerance coefficient, the difference between the degree of impact of the disaster on the high-speed rail operation and the equipment's tolerance can be understood. At the same time, by normalizing the risk equipment according to the risk excess coefficient, it can be determined which equipment is most susceptible to the impact of the disaster, thereby determining the high-speed rail retrospective disaster information, providing a reference for subsequent disaster response and rescue work, and then quickly locating the affected areas and affected high-speed rail equipment, taking timely response measures, and reducing the impact of disasters on high-speed rail operations.

[0060] Furthermore, according to the high-speed rail data in the disaster area, the regional equipment accommodation environment and equipment abnormal sensitivity analysis are performed, and the risk tolerance coefficient of the risk equipment in the disaster area is evaluated. The application method includes:

[0061] Determine the environmental resistance range according to the equipment accommodation environment in the area, wherein the environmental resistance range includes a wind direction resistance range, a wind speed resistance range, and a rainfall resistance range;

[0062] Conduct abnormal sensitivity analysis on regional equipment based on wind direction, wind speed, and rainfall to determine the abnormal sensitivity of each dimension;

[0063] Based on the wind direction resistance range, wind speed resistance range, and rainfall resistance range, fitting a resistance logic relationship;

[0064] Fit the logical relationship of wind and rain impact according to the abnormal sensitivity of each dimension;

[0065] Based on the periodic monitoring data, the periodic time series relationship is determined, the resistance logic relationship and the wind and rain impact logic relationship are added to the time series node as the reward value, and the wind direction, wind speed and rainfall monitoring values ​​in the monitoring data are used as node behaviors to construct a Markov chain model;

[0066] Based on the Markov chain model, the state of regional equipment is predicted for periodic monitoring data to obtain the risk probability coefficient of regional equipment at each time series node, and the wind direction tolerance coefficient of regional equipment is obtained according to the state prediction probability value of the periodic final time series node.

[0067] The regional equipment accommodation environment refers to the environmental conditions of the equipment location, including wind direction, wind speed, rainfall, etc.; the environmental resistance range refers to the range or ability of the equipment to withstand various environmental factors, including wind direction resistance range, wind speed resistance range, and rainfall resistance range; the environmental resistance range is determined based on the regional equipment accommodation environment. For example, on a rainy day, the area with fixed shelters is the rainfall resistance range. By analyzing the regional equipment accommodation environment, we can understand the operating environment and operating status of the equipment in the disaster area, and determine its resistance range or tolerance to different environmental factors, such as wind direction, wind speed, rainfall, etc.

[0068] Wind direction, wind speed, and rainfall are three dimensions that describe natural weather; the abnormal sensitivity refers to the sensitivity of the equipment when facing abnormal conditions or interference; based on the wind direction, wind speed, and rainfall, the abnormal sensitivity of regional equipment is analyzed to determine the abnormal sensitivity of each dimension. For example, a suitable statistical model or machine learning model is selected, such as regression analysis, support vector machine, neural network, etc., to evaluate the abnormal sensitivity of regional equipment in different dimensions of wind direction, wind speed, and rainfall, and analyze the relationship between the wind direction, wind speed, and rainfall and the abnormal sensitivity of regional equipment. For example, when the wind speed is high, it is necessary to strengthen the reinforcement measures for the equipment. By performing abnormal sensitivity analysis of regional equipment in multiple dimensions of wind direction, wind speed, and rainfall, we can understand the sensitivity of the equipment in different dimensions, so as to better evaluate its ability to withstand abnormal conditions or interference.

[0069] The resistance logic relationship refers to the logical relationship or correlation between the resistance capabilities of the equipment when facing different environmental factors. By fitting the wind direction resistance range, wind speed resistance range, and rainfall resistance range, the logical relationship or correlation between the resistance capabilities of the equipment under different environmental factors can be understood.

[0070] The logical relationship of wind and rain impact refers to the logical relationship or correlation between the degree of influence of different environmental factors on the operation of the equipment, and the logical relationship of wind and rain impact is fitted according to the abnormal sensitivity of each dimension. The periodic monitoring data refers to the monitoring data collected according to a certain period, and the time series relationship refers to the relationship between time series. The Markov chain model is used to describe the transition probability between events. The periodic time series relationship is determined based on the periodic monitoring data, and the resistance logical relationship and the wind and rain impact logical relationship are added to the time series node as a reward value. The wind and rain data information obtained from the monitoring is used as the current state, and the wind direction, wind speed, and rainfall monitoring in the monitoring data are used as node behaviors to construct a Markov chain model. The state transition probability of regional equipment is described by constructing a Markov chain model.

[0071] The state prediction refers to predicting the future state or trend based on historical data; the risk probability coefficient refers to the coefficient that describes the probability of risk occurrence; the wind direction tolerance coefficient refers to the coefficient that evaluates the equipment's tolerance to abnormal wind direction or interference. By predicting the state of regional equipment based on periodic monitoring data based on the Markov chain model, the risk probability coefficient of the regional equipment at each time series node can be obtained, so as to better evaluate its tolerance to abnormal situations or interference that may occur in the future. At the same time, the wind direction tolerance coefficient of the regional equipment can be obtained based on the state prediction probability value of the final time series node of the periodicity, providing a reference for related decisions (for example, optimizing the layout to improve the wind direction tolerance coefficient).

[0072] Furthermore, the present application also includes:

[0073] According to the high-speed rail, the disaster-affected information is traced and the information of the inspection and maintenance equipment is located;

[0074] Performing a maintenance level assessment based on the risk excess coefficient to determine an equipment maintenance level, wherein the equipment maintenance level represents the maintenance degree of the equipment, wherein the equipment maintenance level is obtained by analyzing historical equipment maintenance data;

[0075] Based on the inspection and maintenance equipment information and the equipment maintenance level, inspection feedback guidance information is generated.

[0076] High-speed rail tracing disaster information refers to the disaster information in the disaster area obtained through the high-speed rail monitoring system, including the location of the disaster, the affected area, the affected high-speed rail equipment, etc.; inspection and maintenance equipment information refers to the relevant information for regular inspection and maintenance of high-speed rail equipment, including equipment location, status, maintenance history, etc. The inspection and maintenance equipment information is located according to the location of the disaster and the affected area in the high-speed rail tracing disaster information; based on the high-speed rail tracing disaster information, the disaster-stricken area and the affected high-speed rail equipment can be quickly located, and relevant inspection and maintenance equipment information can be obtained.

[0077] The risk excess coefficient refers to the coefficient used to assess the risk equipment's ability to withstand risks beyond the normal range; the equipment maintenance level refers to the maintenance level divided according to the risk level of the equipment, which is used to guide the maintenance work of the equipment. The maintenance level is assessed based on the risk excess coefficient to determine the equipment maintenance level. By analyzing the risk excess coefficient, the risk level of the equipment and the degree of maintenance required are assessed, and then the equipment maintenance level is determined. The determination of the equipment maintenance level provides clear guidance for subsequent maintenance work, helps ensure timely maintenance and repair of high-speed rail equipment, and improves the reliability and safety of the equipment.

[0078] The equipment maintenance level represents the maintenance degree of the equipment, that is, the maintenance demand degree of the equipment; historical equipment maintenance data refers to the relevant data of the maintenance of high-speed rail equipment in the past, including maintenance time, maintenance content, maintenance effect, and historical equipment maintenance level; the equipment maintenance level represents the maintenance degree of the equipment, wherein the equipment maintenance level is obtained by performing correlation analysis based on the historical equipment maintenance data, including: the correlation is analyzed by the TOPSIS method (Technique for Order Preference by Similarity to ideal Sulution, superior and inferior solution distance method), specifically, the indicators in the historical equipment maintenance data and the indicators in the inspection and maintenance equipment information are normalized, the optimal matching features and the worst matching features are found by the cosine method, and then the distance between the indicators in the inspection and maintenance equipment information and the optimal matching features and the worst matching features is calculated, and the historical equipment maintenance level corresponding to the historical equipment maintenance data with the highest similarity is determined, and the historical equipment maintenance level corresponding to the historical equipment maintenance data with the highest similarity is used as the equipment maintenance level. By analyzing the historical equipment maintenance data, the maintenance needs and change trends of the equipment can be understood, and then the maintenance level of the equipment can be determined, which is helpful to formulate a more reasonable and effective maintenance plan according to the actual situation of the equipment, and improve the maintenance quality and efficiency of the equipment.

[0079] The inspection feedback guidance information refers to the relevant guidance information generated based on the inspection and maintenance equipment information and equipment maintenance level, which is used to guide the inspection and maintenance work. By integrating the inspection and maintenance equipment information and equipment maintenance level, specific inspection feedback guidance information can be generated, which helps to ensure the accuracy and effectiveness of inspection and maintenance work and improve the reliability and safety of high-speed rail equipment.

[0080] In summary, the intelligent monitoring and early warning method and system for high-speed railway disasters provided in the embodiments of the present application have the following technical effects:

[0081] 1. Through real-time, all-weather monitoring and intelligent analysis, more accurately predict the occurrence of disasters and improve the accuracy of early warnings.

[0082] 2. Real-time monitoring of the environment along the high-speed rail line, once a possible disaster is discovered, timely warning can be issued to minimize the losses caused by the disaster.

[0083] 3. The disaster information of high-speed rail is traced back to locate the inspection and maintenance equipment information; the maintenance level is evaluated based on the risk excess coefficient to determine the equipment maintenance level. The equipment maintenance level represents the maintenance degree of the equipment. Among them, the equipment maintenance level is obtained by analyzing the historical equipment maintenance data; based on the inspection and maintenance equipment information and equipment maintenance level, the inspection feedback guidance information is generated. By integrating the inspection and maintenance equipment information and the equipment maintenance level, specific inspection feedback guidance information can be generated, which helps to ensure the accuracy and effectiveness of the inspection and maintenance work and improve the reliability and safety of high-speed rail equipment.

[0084] Embodiment 2

[0085] Based on the same inventive concept as the intelligent monitoring and early warning method for high-speed railway disasters in the aforementioned embodiment, Figure 3 As shown, the embodiment of the present application provides an intelligent monitoring and early warning system for high-speed railway disasters, wherein the system includes:

[0086] The monitoring and positioning network module 100 is used to build a high-speed rail monitoring and positioning network based on the set high-speed rail ultrasonic anemometer and piezoelectric rain gauge;

[0087] A database establishment module 200 is used to connect to the high-speed rail monitoring and positioning network to establish a high-speed rail monitoring database;

[0088] The disaster coefficient evaluation module 300 is used to extract the periodic monitoring data in the high-speed rail monitoring database and evaluate the disaster coefficient of the wind and rain data information and the high-speed rail operation data information obtained by monitoring;

[0089] The high-speed rail disaster positioning module 400 is used to locate the high-speed rail disaster through the high-speed rail monitoring and positioning network when a preset disaster coefficient is reached, and obtain the high-speed rail data of the disaster area;

[0090] The warning information sending module 500 is used to perform disaster analysis and source tracing on the high-speed rail data and disaster coefficient in the disaster area, determine the high-speed rail disaster information, and send warning information.

[0091] Furthermore, the system also includes:

[0092] Dividing nodes according to a preset period to extract periodic monitoring data from the high-speed rail monitoring database;

[0093] The extracted periodic monitoring data are analyzed for unidirectional and multi-directional impact relationships with high-speed rail operation data according to wind direction, wind speed, and rainfall, and a multi-dimensional cost function relationship is obtained by fitting.

[0094] The multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model, and the disaster coefficient assessment model is used to perform disaster coefficient assessment.

[0095] Furthermore, the system also includes:

[0096] Based on the multi-dimensional cost function relationship, a unidirectional cost function relationship and a multi-directional cost function relationship are obtained, wherein the unidirectional relationship is an influence relationship of a single dimension, and the multi-directional relationship is a cross-overlapping influence relationship of at least two dimensions;

[0097] Based on the multi-directional cost function relationship, performing overlapping difference calculation on the unidirectional cost function relationship including the dimension, and determining the adjustment coefficient;

[0098] The one-way cost function relationships are superimposed, and the adjustment coefficients are used to make correction adjustments to generate the disaster coefficient assessment model.

[0099] Furthermore, the system also includes:

[0100] Obtain the high-speed rail line and the operating equipment around the line, and establish a high-speed rail line positioning network by using the computing equipment around the line as marking points and the high-speed rail line as a connecting line;

[0101] Obtaining the monitoring radiation range of the high-speed rail ultrasonic anemometer and piezoelectric rain gauge, and marking the radiation range of the high-speed rail monitoring and positioning network based on the monitoring radiation range;

[0102] The high-speed rail line positioning network is superimposed on the high-speed rail monitoring and positioning network, and the high-speed rail data in the disaster area is determined using the positioning information of the high-speed rail monitoring data.

[0103] Furthermore, the system also includes:

[0104] According to the high-speed rail data in the disaster area, analyze the regional equipment accommodation environment and equipment abnormal sensitivity, and evaluate the risk tolerance coefficient of risk equipment in the disaster area;

[0105] The difference value is calculated using the disaster coefficient and the risk tolerance coefficient, and the risk equipment is sequenced according to the risk excess coefficient to determine the high-speed rail retrospective disaster information.

[0106] Furthermore, the system also includes:

[0107] Determine the environmental resistance range according to the equipment accommodation environment in the area, wherein the environmental resistance range includes a wind direction resistance range, a wind speed resistance range, and a rainfall resistance range;

[0108] Conduct abnormal sensitivity analysis on regional equipment based on wind direction, wind speed, and rainfall to determine the abnormal sensitivity of each dimension;

[0109] Based on the wind direction resistance range, wind speed resistance range, and rainfall resistance range, fitting a resistance logic relationship;

[0110] Fit the logical relationship of wind and rain impact according to the abnormal sensitivity of each dimension;

[0111] Based on the periodic monitoring data, the periodic time series relationship is determined, the resistance logic relationship and the wind and rain impact logic relationship are added to the time series node as the reward value, and the wind direction, wind speed and rainfall monitoring values ​​in the monitoring data are used as node behaviors to construct a Markov chain model;

[0112] Based on the Markov chain model, the state of regional equipment is predicted for periodic monitoring data to obtain the risk probability coefficient of regional equipment at each time series node, and the wind direction tolerance coefficient of regional equipment is obtained according to the state prediction probability value of the periodic final time series node.

[0113] Furthermore, the system also includes:

[0114] According to the high-speed rail, the disaster-affected information is traced and the information of the inspection and maintenance equipment is located;

[0115] Performing a maintenance level assessment based on the risk excess coefficient to determine an equipment maintenance level, wherein the equipment maintenance level represents the maintenance degree of the equipment, wherein the equipment maintenance level is obtained by analyzing historical equipment maintenance data;

[0116] Based on the inspection and maintenance equipment information and the equipment maintenance level, inspection feedback guidance information is generated.

[0117] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0118] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent monitoring and early warning method for high-speed railway disasters, characterized in that: include: Based on the high-speed rail ultrasonic anemometer and piezoelectric rain gauge, a high-speed rail monitoring and positioning network is constructed; Connecting to the high-speed rail monitoring and positioning network to establish a high-speed rail monitoring database; Extracting periodic monitoring data from the high-speed rail monitoring database, and evaluating the disaster coefficient of the wind and rain data information and the high-speed rail operation data information obtained from the monitoring; When the preset disaster coefficient is reached, high-speed rail disaster positioning is performed through the high-speed rail monitoring and positioning network to obtain high-speed rail data in the disaster area; Conduct disaster analysis and source tracing on the high-speed rail data and disaster coefficients in the disaster area, determine the high-speed rail disaster information, and send early warning information; The process of extracting periodic monitoring data from the high-speed rail monitoring database and evaluating the disaster coefficient of the wind and rain data information and the high-speed rail operation data information obtained by monitoring includes: Dividing nodes according to a preset period to extract periodic monitoring data from the high-speed rail monitoring database; The extracted periodic monitoring data are analyzed for unidirectional and multi-directional impact relationships with high-speed rail operation data according to wind direction, wind speed, and rainfall, and a multi-dimensional cost function relationship is obtained by fitting. The multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model, and the disaster coefficient assessment model is used to perform disaster coefficient assessment; The multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model, including: Based on the multi-dimensional cost function relationship, a unidirectional cost function relationship and a multi-directional cost function relationship are obtained, wherein the unidirectional relationship is an influence relationship of a single dimension, and the multi-directional relationship is a cross-overlapping influence relationship of at least two dimensions; Based on the multi-directional cost function relationship, performing overlapping difference calculation on the unidirectional cost function relationship including the dimension, and determining the adjustment coefficient; The one-way cost function relationships are superimposed, and the adjustment coefficients are used to make correction adjustments to generate the disaster coefficient assessment model.

2. The method according to claim 1, characterized in that High-speed rail disaster positioning is performed through the high-speed rail monitoring and positioning network to obtain high-speed rail data in the disaster area, including: Obtain the high-speed rail line and the equipment running around the line, and establish a high-speed rail line positioning network by taking the equipment running around the line as the marking points and the high-speed rail line as the connecting line; Obtaining the monitoring radiation range of the high-speed rail ultrasonic anemometer and piezoelectric rain gauge, and marking the radiation range of the high-speed rail monitoring and positioning network based on the monitoring radiation range; The high-speed rail line positioning network is superimposed on the high-speed rail monitoring and positioning network, and the high-speed rail data in the disaster area is determined using the positioning information of the high-speed rail monitoring data.

3. The method according to claim 2, characterized in that Conduct disaster analysis and source tracing on the high-speed rail data and disaster coefficients in the disaster area to determine the high-speed rail disaster information, including: According to the high-speed rail data in the disaster area, analyze the regional equipment accommodation environment and equipment abnormal sensitivity, and evaluate the risk tolerance coefficient of risk equipment in the disaster area; The difference value is calculated using the disaster coefficient and the risk tolerance coefficient, and the risk equipment is sequenced according to the risk excess coefficient to determine the high-speed rail retrospective disaster information.

4. The method according to claim 3, characterized in that According to the high-speed rail data in the disaster area, the regional equipment accommodation environment and equipment abnormal sensitivity analysis are carried out, and the risk tolerance coefficient of the risk equipment in the disaster area is evaluated, including: Determine the environmental resistance range according to the equipment accommodation environment in the area, wherein the environmental resistance range includes a wind direction resistance range, a wind speed resistance range, and a rainfall resistance range; Conduct abnormal sensitivity analysis on regional equipment based on wind direction, wind speed, and rainfall to determine the abnormal sensitivity of each dimension; Based on the wind direction resistance range, wind speed resistance range, and rainfall resistance range, fitting a resistance logic relationship; Fit the logical relationship of wind and rain impact according to the abnormal sensitivity of each dimension; Based on the periodic monitoring data, the periodic time series relationship is determined, the resistance logic relationship and the wind and rain impact logic relationship are added to the time series node as the reward value, and the wind direction, wind speed and rainfall monitoring values ​​in the monitoring data are used as node behaviors to construct a Markov chain model; Based on the Markov chain model, the state of regional equipment is predicted for periodic monitoring data to obtain the risk probability coefficient of regional equipment at each time series node, and the wind direction tolerance coefficient of regional equipment is obtained according to the state prediction probability value of the periodic final time series node.

5. The method according to claim 3, characterized in that Also includes: According to the high-speed rail, the disaster-affected information is traced and the information of the inspection and maintenance equipment is located; Performing a maintenance level assessment based on the risk excess coefficient to determine an equipment maintenance level, wherein the equipment maintenance level represents the maintenance degree of the equipment, wherein the equipment maintenance level is obtained by analyzing historical equipment maintenance data; Based on the inspection and maintenance equipment information and the equipment maintenance level, inspection feedback guidance information is generated.

6. Intelligent monitoring and early warning system for high-speed railway disasters, characterized by: The intelligent monitoring and early warning method for high-speed railway disasters according to any one of claims 1 to 5 comprises: The monitoring and positioning network module is used to build a high-speed rail monitoring and positioning network based on the set high-speed rail ultrasonic anemometer and piezoelectric rain gauge; A database establishment module, used to connect to the high-speed rail monitoring and positioning network to establish a high-speed rail monitoring database; A disaster coefficient evaluation module is used to extract the periodic monitoring data in the high-speed rail monitoring database and evaluate the disaster coefficient of the wind and rain data information and the high-speed rail operation data information obtained by monitoring; A high-speed rail disaster positioning module is used to locate high-speed rail disasters through the high-speed rail monitoring and positioning network when a preset disaster coefficient is reached, and obtain high-speed rail data in the disaster area; An early warning information sending module is used to analyze and trace the disaster source of the high-speed rail data and disaster coefficient in the disaster area, determine the high-speed rail tracing disaster information, and send early warning information; Wherein, the disaster coefficient assessment module is also used for: Dividing nodes according to a preset period to extract periodic monitoring data from the high-speed rail monitoring database; The extracted periodic monitoring data are analyzed for unidirectional and multi-directional impact relationships with high-speed rail operation data according to wind direction, wind speed, and rainfall, and a multi-dimensional cost function relationship is obtained by fitting. The multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model, and the disaster coefficient assessment model is used to perform disaster coefficient assessment; The multi-dimensional cost function relationship is integrated to generate a disaster coefficient assessment model, including: Based on the multi-dimensional cost function relationship, a unidirectional cost function relationship and a multi-directional cost function relationship are obtained, wherein the unidirectional relationship is an influence relationship of a single dimension, and the multi-directional relationship is a cross-overlapping influence relationship of at least two dimensions; Based on the multi-directional cost function relationship, performing overlapping difference calculation on the unidirectional cost function relationship including the dimension, and determining the adjustment coefficient; The one-way cost function relationships are superimposed, and the adjustment coefficients are used to make correction adjustments to generate the disaster coefficient assessment model.

Images