Rail Transit Rear-End Collision Risk Assessment Method and System

Abstract

The present application discloses a method and system for evaluating the risk of rear-end collision in rail transit, which relates to the technical field of data prediction; the method includes: obtaining the status information of a reference train from a cloud server; when the status information indicates that the reference train is located in a tunnel, obtaining first information from the cloud server; based on the first information, determining the relative speed and relative distance of a target train within a first time period to obtain second information; using the second information and a prediction model to determine the risk coefficient of rear-end collision between the target train and the reference train to obtain a risk assessment result. The technical solution provided by the present application can improve the accuracy and reliability of positioning results during train operation, thereby improving the safety of rail transit operation.

Description

Technical Field

[0001] This application relates to the technical field of data prediction, and specifically to a method and system for evaluating the risk of rear-end collision in rail transit. Background Art

[0002] To ensure the safety of train operation in rail transit systems (such as subways, light rails, or trains, etc.), it is crucial to conduct real-time risk assessment on rail transit. In the prior art, the assessment of rear-end collision risk mostly relies on technologies such as the Global Positioning System (GPS) for real-time positioning of trains, and uses the Automatic Train Control System (ATC) to achieve speed control and automatic protection of trains, ensuring that the distance between the front and rear trains is not less than the minimum safety distance specified in the rail transit operation standard. However, in the process of train operation, there are often scenarios where the positioning signal is weak, such as in tunnels. Once the accurate positioning of the front train cannot be achieved, the rear train will not be able to timely obtain the distance from the front train. Especially with the full-speed increase of trains, it is impossible to accurately and timely make an assessment and execute the correct braking strategy, which will pose a great potential safety hazard to the safety of the rear train and even the entire railway system.

[0003] Therefore, how to overcome the above-mentioned technical problems and defects has become a key issue to be solved. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for evaluating the risk of rear-end collision in rail transit, so as to solve the problems raised in the above background art, and improve the accuracy and reliability of positioning results during train operation, thereby improving the safety of rail transit operation.

[0005] The technical solution of the embodiment of this application is realized as follows:

[0006] The embodiment of this application provides a method for evaluating the risk of rear-end collision in rail transit, and the method includes:

[0007] Obtain the status information of the reference train from the cloud server; the status information indicates whether the reference train is inside or outside the tunnel;

[0008] When the status information indicates that the reference train is inside the tunnel, obtain the first information from the cloud server; the first information characterizes the second operating parameters of the reference train inside the tunnel; the first information is determined based on the first operating parameters when the reference train enters the tunnel;

[0009] Based on the first information, determine the relative speed and relative distance of the target train within the first time period to obtain the second information; the first time period is determined based on the time period for the reference train to pass through the tunnel;

[0010] Using the second information and the prediction model, determine the risk coefficient of the target train and the reference train colliding from the rear, and obtain the risk assessment result.

[0011] In the above solution, the method further includes:

[0012] When the reference train enters the tunnel, upload its first operating parameter to the cloud server.

[0013] In the above solution, the method further includes:

[0014] The base station of the Global System for Mobile Communications – Railway (GSM-R) determines whether the distance between the reference train and the tunnel entrance is less than the distance threshold, and obtains the second judgment result;

[0015] When the second judgment result indicates that the distance between the reference train and the tunnel entrance is less than the distance threshold, continuously obtain the sensor data at the tunnel entrance according to a preset period;

[0016] Based on the obtained sensor data, determine the first operating parameter of the reference train, and upload it to the cloud server.

[0017] In the above solution, the method further includes:

[0018] After receiving the first operating parameter, the cloud server updates the status information of the reference train, and predicts the second operating parameter of the reference train in the tunnel based on the first operating parameter, and obtains the first information.

[0019] In the above solution, the method further includes:

[0020] After the reference train enters the tunnel, the GSM-R base station obtains the Radio Frequency Identification (RFID) information of the reference train within the first time period;

[0021] Based on the RFID information, determine the third operating parameter of the reference train, and upload the third operating parameter to the cloud server;

[0022] The cloud server corrects the second operating parameter based on the third operating parameter.

[0023] In the above solution, the first time period includes multiple sampling points; the determining the relative speed and relative distance of the target train within the first time period based on the first information to obtain the second information includes:

[0024] Based on the first information, determine the relative speed and relative distance of the target train at each sampling point according to the time axis;

[0025] Generate the second information based on the relative speed and relative distance of all sampling points.

[0026] In the above solution, the method of using the second information and the prediction model to determine the risk coefficient of the target train and the reference train colliding rear-end to obtain the risk assessment result includes:

[0027] Based on the historical operation parameters of the reference train in the second time period before entering the tunnel, determine the historical relative distance and historical relative speed of the target train in the second time period;

[0028] Based on the fluctuation degree of the historical relative distance and the historical relative speed within the second time period, determine the credibility of the second information;

[0029] Based on the credibility, the second information and the prediction model, determine the risk coefficient of the target train and the reference train colliding rear-end to obtain the risk assessment result.

[0030] In the above solution, the method of determining the credibility of the second information based on the fluctuation degree of the historical relative distance and the historical relative speed within the second time period includes:

[0031] Based on all historical relative speed data within the second time period, determine the change situation of the historical relative speed and generate a first change curve;

[0032] Based on all historical relative distance data within the second time period, determine the change situation of the historical relative distance and generate a second change curve;

[0033] Based on the fluctuation degrees of the first change curve and the second change curve, determine the credibility of the second information.

[0034] In the above solution, the method of determining the credibility of the second information based on the fluctuation degrees of the first change curve and the second change curve includes:

[0035] Based on the fluctuation frequency and fluctuation amplitude of the first change curve, determine the first credibility of the relative speed in the second information;

[0036] Based on the fluctuation frequency and fluctuation amplitude of the second change curve, determine the second credibility of the relative distance in the second information.

[0037] An embodiment of the present application further provides a rail transit rear-end collision risk assessment system, which includes a target train and a cloud server; the target train includes:

[0038] A communication unit for obtaining the status information of a reference train from a cloud server; the status information indicates whether the reference train is inside or outside a tunnel; and, for obtaining first information from the cloud server when the status information indicates that the reference train is inside the tunnel; the first information characterizes second operating parameters of the reference train inside the tunnel; the first information is determined based on first operating parameters when the reference train enters the tunnel.

[0039] A processing unit for determining a relative speed and a relative distance of a target train within a first time period based on the first information, to obtain second information; the first time period is determined based on the time period for the reference train to pass through the tunnel.

[0040] A prediction unit for using the second information and a prediction model to determine a risk coefficient of the target train and the reference train colliding, to obtain a risk assessment result.

[0041] The rail transit collision risk assessment method and system provided by the embodiments of the present application synchronize the status information and operating parameters of the leading train when it enters the tunnel to the cloud server, enabling the cloud server to estimate the position and speed of the leading train based on the received operating parameters when the position of the leading train cannot be accurately known through the positioning system, achieving the accuracy, comprehensiveness, and reliability of train positioning during the driving process; further, by obtaining the operating parameters of the leading train, the relative distance and relative speed between the front and rear trains can be calculated, and the collision risk of the rear train and the leading train can be predicted based on the relative distance and relative speed, realizing the real-time and comprehensive assessment of the collision risk during driving, improving the comprehensiveness and reliability of the safety monitoring during the train driving process, and thus ensuring the safe and stable operation of the entire rail transit system. Description of the Drawings

[0042] Figure 1 It is a schematic flow chart of a rail transit collision risk assessment method provided by an embodiment of the present application;

[0043] Figure 2 It is a schematic flow chart of correcting the second operating parameters in the rail transit collision risk assessment method of an embodiment of the present application;

[0044] Figure 3 It is a schematic flow chart of determining the second information in the rail transit collision risk assessment method of an embodiment of the present application;

[0045] Figure 4 It is a schematic flow chart of obtaining the risk assessment result in the rail transit collision risk assessment method of an embodiment of the present application;

[0046] Figure 5 It is a schematic flow chart of determining the credibility of the second information in the rail transit collision risk assessment method of an embodiment of the present application;

[0047] Figure 6 It is a schematic flow chart for determining the credibility of the second piece of information based on the fluctuation degrees of the first change curve and the second change curve in the rail transit rear-end collision risk assessment method according to the embodiments of the present application;

[0048] Figure 7 It is a schematic architecture diagram of a rail transit rear-end collision risk assessment system provided by the embodiments of the present application;

[0049] Figure 8 It is a schematic structural diagram of a target train in a rail transit rear-end collision risk assessment system provided by the embodiments of the present application. Detailed implementation manners

[0050] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0051] The embodiments of the present application provide a rail transit rear-end collision risk assessment method, which is applied to a train control system, such as Figure 1 As shown, this method may include S101 to S104. The following will give a detailed description of S101 to S104.

[0052] S101: Obtain the status information of a reference train from a cloud server; the status information indicates that the reference train is inside or outside a tunnel.

[0053] In practical applications, obtaining the status information of a reference train from a cloud server can be understood as that a target train or a train dispatching control center obtains the status information of the reference train from the cloud server; the reference train can also be called the leading train, that is, the train traveling in front among two trains traveling in the same direction, and the target train can also be called the trailing train, that is, the train traveling behind among two trains traveling in the same direction.

[0054] In practical applications, the cloud server can use positioning systems such as GPS and Beidou to obtain the position information of the reference train in real time, so as to update the status information of the reference train in time when the reference train enters the tunnel.

[0055] It should be noted that the term "entering the tunnel" described in the embodiments of the present application can be understood as the train head entering the tunnel.

[0056] In actual application, when the reference train enters the tunnel, that is, before it is about to disconnect from the cloud server, it can also send its own status information to the cloud server, so that the cloud server can know that the driving environment of the reference train changes from outside the tunnel to inside the tunnel, and then update the status information of the reference train in a timely manner.

[0057] Based on this, in one embodiment, the method may further include:

[0058] When the reference train enters the tunnel, it uploads its first operating parameter to the cloud server.

[0059] Here, compared with the method of obtaining location information in real time, since it is not necessary to continuously obtain information, but only need to update the status information of the corresponding train after receiving the operating parameters when the train enters the tunnel, it can reduce the data transmission volume between the cloud server and other devices, save spectrum resources, and reduce the data processing pressure on the cloud server.

[0060] In actual application, in order to ensure that the cloud server can accurately and timely know this information when the reference train enters the tunnel, sensors can also be set at the tunnel entrance. When the train enters the tunnel entrance, the operating parameters of the train can be obtained through the detection data of the sensors; for example, visual cameras and ultrasonic sensors can be set at the tunnel entrance to detect the image of the incoming train and the distance from the tunnel entrance; when the sensors collect the data that the reference train enters the tunnel, the collected data is sent to the GSM-R base station set at the tunnel entrance or inside the tunnel, and the GSM-R base station sends the operating parameters when the reference train enters the tunnel to the cloud through communication with the cloud server.

[0061] Based on this, in one embodiment, the method may further include:

[0062] The GSM-R base station judges whether the distance between the reference train and the tunnel entrance is less than a distance threshold to obtain a second judgment result;

[0063] When the second judgment result indicates that the distance between the reference train and the tunnel entrance is less than the distance threshold, continuously obtain the sensor data at the tunnel entrance according to a preset period;

[0064] Based on the obtained sensor data, determine the first operating parameter of the reference train and upload it to the cloud server.

[0065] In actual application, the reference train can determine whether the current distance from the tunnel entrance is less than the distance threshold according to the real-time positioning information obtained from the positioning system. When the distance is less than the distance threshold, it sends a warning signal to the GSM-R base station. After receiving the warning signal sent by the reference train, the GSM-R base station can start continuously obtaining the detection data of the sensors installed at the tunnel entrance at a preset interval duration, and judge the position and operation parameters of the reference train according to the detection data. When the reference train enters the tunnel, the operation parameters obtained at the corresponding time are sent to the cloud server.

[0066] In actual application, the first operation parameter can also be called the actual operation parameter, that is, the actual operation parameter of the reference train before entering the tunnel. The embodiments of the present application do not limit this, as long as its function can be realized.

[0067] In actual application, since both the GSM-R base station and the reference train send the first operation parameter to the cloud server, when the reference train has an abnormality and cannot communicate with the cloud server normally, and thus cannot send the first operation parameter normally, the cloud server can still receive the operation parameter of the reference train and update the status information in time, ensuring the accuracy of the status information and the reliability of the entire risk assessment result.

[0068] S102: When the status information indicates that the reference train is located in the tunnel, obtain the first information from the cloud server; the first information characterizes the second operation parameter of the reference train in the tunnel; the first information is determined based on the first operation parameter when the reference train enters the tunnel.

[0069] In actual application, after receiving the first operation parameter, the cloud server can estimate the running speed and position of the reference train in the tunnel according to the first operation parameter and the design parameters of the tunnel (such as tunnel length, speed limit requirements, etc.).

[0070] Based on this, in one embodiment, the method may further include:

[0071] After receiving the first operation parameter, the cloud server updates the status information of the reference train, and predicts the second operation parameter of the reference train in the tunnel based on the first operation parameter to obtain the first information.

[0072] In actual application, the second operation parameter can also be called the predicted operation parameter, that is, the predicted operation parameter of the reference train when passing through the tunnel. The embodiments of the present application do not limit this, as long as its function can be realized.

[0073] In actual application, RFID tags can also be arranged in the tunnel, and the position of the train in the tunnel is calculated according to the position change between the reference train and the RFID tags.

[0074] Based on this, in one embodiment, the method may further include correcting the second operating parameter; as Figure 2 shown, the correcting the second operating parameter may include:

[0075] S201: After the reference train enters the tunnel, the GSM-R base station acquires the RFID information of the reference train within a first duration;

[0076] S202: Based on the RFID information, determine the third operating parameter of the reference train and upload the third operating parameter to the cloud server;

[0077] S203: The cloud server corrects the second operating parameter based on the third operating parameter.

[0078] In practical applications, after the reference train enters the tunnel, the RFID reader set on the reference train generates identification information, that is, RFID information, after identifying RFID tags at different positions in the tunnel, and sends the acquired identification information to the GSM-R base station. The GSM-R base station determines the position of the corresponding RFID tag according to the number of the RFID tag in the identification information, so as to determine the current position of the reference train. According to the time interval and the label distance interval between the two RFID tag identification signals, the running speed of the reference train is calculated, so as to obtain the operating parameter determined according to the RFID tag position, that is, the third operating parameter; the GSM-R base station uploads the third operating parameter to the cloud server, so that the cloud server can correct the second operating parameter according to the third operating parameter, so as to improve the accuracy and reliability of the predicted second operating parameter, thereby ensuring the accuracy of the risk assessment result.

[0079] Here, when determining the third operating parameter of the reference train based on the RFID information and uploading the third operating parameter to the cloud server, the GSM-R base station may upload the third operating parameter once every time an RFID information is acquired. Specifically, after the GSM-R base station acquires the first RFID information (that is, the identification information collected by the reader when the reference train passes the first RFID tag) and calculates the train position, it uploads the third operating parameter including the current train position data to the cloud server, and starts from the second RFID information acquired, calculates the position and speed of the train and uploads them; the GSM-R base station may also upload the third operating parameter once every two RFID information is acquired; specifically, the frequency of the GSM-R base station uploading the third operating parameter may be determined according to the actual application scenario requirements, and the embodiments of the present application do not limit this.

[0080] S103: Based on the first information, determine the relative speed and relative distance of the target train within the first time period to obtain the second information; the first time period is determined based on the time period for the reference train to pass through the tunnel.

[0081] In practical applications, after determining the first information, the speed and driving trajectory of the reference train during passing through the tunnel can be obtained. At this time, the relative speed and relative distance between the two at different time points can be calculated based on the speed and driving trajectory of the target train, so as to realize the assessment of the collision risk between the two when the position of the reference train cannot be located by the positioning system.

[0082] Based on this, in an embodiment, the first time period may include multiple sampling points; as Figure 3 shown, the step of determining the relative speed and relative distance of the target train within the first time period based on the first information to obtain the second information may include:

[0083] S301: Based on the first information, determine the relative speed and relative distance of the target train at each sampling point according to the time axis;

[0084] S302: Generate the second information based on the relative speed and relative distance of all sampling points.

[0085] In practical applications, the first time period may be determined according to the estimated time for the reference train to pass through the tunnel; specifically, it may be equal to the time period for the reference train to pass through the tunnel, or may be greater than the time period for the train to pass through the tunnel.

[0086] In practical applications, the sampling point may also be referred to as the sampling time point, or may also be referred to as the sampling moment. The embodiments of the present application do not limit this, as long as its function can be realized.

[0087] S104: Use the second information and the prediction model to determine the risk coefficient of the target train and the reference train for rear-end collision to obtain the risk assessment result.

[0088] In practical applications, after determining the relative speed and relative distance of the target train relative to the reference train at each sampling point, the relative speed and relative distance can be used as the input of the prediction model, and the risk coefficient corresponding to the sampling point is output.

[0089] It should be noted that the embodiments of the present application introduce the process of determining the relative distance and relative speed when the reference train cannot be located in the tunnel. When the reference train is not outside the tunnel, the reference train can be located and its parameters can be obtained through the positioning system, and the real-time relative distance and relative speed can be calculated, so as to evaluate the corresponding rear-end collision risk according to the relative distance and relative speed at each moment.

[0090] In actual application, the reference train can also be referred to as the leading train, and the target train can also be referred to as the trailing train.

[0091] In actual application, the second operating parameter is determined based on the speed of the reference train when it enters the tunnel. Considering that the technical parameters and driving characteristics of different trains are different, therefore, the change characteristics of the speed and position during the driving of each train can be determined according to the historical driving data of each train, and the determined change characteristics can be used to optimize the predicted second operating parameter to improve the accuracy of the estimated result of the train operating parameter in the tunnel.

[0092] Based on this, in one embodiment, as Figure 4 shown, using the second information and the prediction model to determine the risk coefficient of the target train and the reference train colliding to obtain a risk assessment result may include S401 to S403. The following will detail S401 to S403 in combination with specific embodiments.

[0093] S401: Based on the historical operating parameters of the reference train in the second time period before entering the tunnel, determine the historical relative distance and historical relative speed of the target train in the second time period.

[0094] S402: Based on the fluctuation degree of the historical relative distance and the historical relative speed within the second time period, determine the credibility of the second information.

[0095] In actual application, a change curve of the relative speed and the relative distance can be established to analyze the change characteristics of the two variables.

[0096] Based on this, in one embodiment, as Figure 5 shown, the determining the credibility of the second information based on the fluctuation degree of the historical relative distance and the historical relative speed within the second time period may include:

[0097] S501: Based on all the historical relative speed data within the second time period, determine the change situation of the historical relative speed and generate a first change curve;

[0098] S502: Based on all the historical relative distance data within the second time period, determine the change situation of the historical relative distance and generate a second change curve;

[0099] S503: Based on the fluctuation degree of the first change curve and the second change curve, determine the credibility of the second information.

[0100] In actual application, the fluctuation degree of the historical relative distance and the historical relative speed can be evaluated from two dimensions of the change frequency and the change amplitude.

[0101] Based on this, in one embodiment, asFigure 6 As shown, determining the credibility of the second information based on the fluctuation degrees of the first change curve and the second change curve may include:

[0102] S601: Determine a first credibility of the relative speed in the second information based on the fluctuation frequency and fluctuation amplitude of the first change curve;

[0103] S602: Determine a second credibility of the relative distance in the second information based on the fluctuation frequency and fluctuation amplitude of the second change curve.

[0104] In practical applications, when determining the fluctuation frequency, positions on the first curve where the fluctuation amplitude exceeds the speed fluctuation amplitude threshold may be selected as speed fluctuation positions, and then the fluctuation frequency of the first curve may be calculated according to the number of speed fluctuation positions within a second time period; correspondingly, positions on the second curve where the fluctuation amplitude exceeds the distance fluctuation amplitude threshold may be selected as distance fluctuation positions, and then the fluctuation frequency of the second curve may be calculated according to the number of distance fluctuation positions within the second time period.

[0105] In practical applications, the slope corresponding to a position may be calculated based on the fluctuation amplitude of the speed fluctuation position on the first change curve, so as to obtain the speed change rate at that position. Specifically, the absolute value of the slope at that position may be used as the corresponding speed change rate, and then the first credibility may be calculated according to the mean value of all speed change rates and the corresponding fluctuation frequency; correspondingly, the slope corresponding to a position may be calculated based on the fluctuation amplitude of the distance fluctuation position on the second change curve, so as to obtain the distance change rate at that position. Specifically, the absolute value of the slope at that position may be used as the corresponding distance change rate, and then the second credibility may be calculated according to the mean value of all distance change rates and the corresponding fluctuation frequency.

[0106] In practical applications, the first credibility may also be referred to as the relative speed credibility, and the second credibility may also be referred to as the relative distance credibility. The embodiments of the present application do not limit this, as long as its function can be achieved.

[0107] Exemplarily, the relative speed credibility may be expressed as:

[0108] ;

[0109] Wherein, represents the relative speed credibility, that is, the first credibility, represents the fluctuation frequency of the first change curve, represents the mean value of the speed change rates of the first curve, , represent weight coefficients;

[0110] The relative distance credibility may be expressed as:

[0111] ;

[0112] wherein, represents the relative distance credibility, i.e., the second credibility, represents the fluctuation frequency of the second change curve, represents the average value of the distance change rate of the second curve, , represents the weight coefficient.

[0113] S403: Based on the credibility, the second information, and the prediction model, determine the risk coefficient of the target train and the reference train colliding, and obtain the risk assessment result.

[0114] In practical applications, the second information can be optimized using the credibility first, and then the optimized second information can be used as the input of the prediction model; specifically, the relative speed in the second information can be optimized using the first credibility, and the relative distance in the second information can be optimized using the second credibility.

[0115] Exemplarily, the risk coefficient can be expressed as:

[0116] ;

[0117] ;

[0118] ;

[0119] wherein, represents the risk coefficient at time represents the relative speed at time represents the relative distance at time is a constant, , are coefficients.

[0120] In practical applications, after predicting the risk coefficient of each sampling point within the first time period based on the credibility, the second information, and the prediction model, the risk assessment result of the target train can be determined according to the value of the risk coefficient and the change rule of the risk coefficient along the time axis.

[0121] Specifically, first determine whether the risk coefficient of each sampling point exceeds the risk threshold. If there is a sampling point with a risk coefficient exceeding the risk threshold within the first time period, the risk assessment result of the target train is high risk; correspondingly, if the risk coefficients of all sampling points within the first time period do not exceed the risk threshold, then determine whether the risk coefficient shows an increase along the time axis. If there is an increase, the risk assessment result of the target train is medium risk; otherwise, if there is no increase, the risk assessment result of the target train is low risk. Here, the risk threshold can be determined according to factors such as the safety standards of railway operations, historical accident data, and actual application scenarios, and this application does not make any limitations in this regard.

[0122] In summary, the rail transit rear-end collision risk assessment method provided by the embodiments of this application synchronizes the state information and operation parameters of the leading train when it enters the tunnel to the cloud server, enabling the cloud server to estimate the position and speed of the leading train based on the received operation parameters when it cannot accurately obtain the position of the leading train through the positioning system, thereby improving the accuracy, comprehensiveness, and reliability of the train positioning result. Further, by obtaining the operation parameters of the leading train to calculate the relative distance and relative speed between the front and rear trains, and predicting the rear-end collision risk of the rear train with the leading train based on the relative distance and relative speed, the real-time and comprehensive assessment of the rear-end collision risk during driving is realized, improving the comprehensiveness and reliability of the safety monitoring during the train driving process, and thus ensuring the safe and stable operation of the entire rail transit system.

[0123] To implement the rail transit rear-end collision risk assessment method of this application, the embodiments of this application also provide a rail transit rear-end collision risk assessment system, as Figure 7 shown. The system includes a cloud server 701, a reference train 702, a target train 703, and a GSM-R base station 704; as Figure 8 shown, the target train 703 may include:

[0124] A communication unit 801, configured to obtain the state information of the reference train from the cloud server; the state information indicates whether the reference train is inside or outside the tunnel; and, when the state information indicates that the reference train is inside the tunnel, obtain first information from the cloud server; the first information characterizes the second operation parameters of the reference train inside the tunnel; the first information is determined based on the first operation parameters when the reference train enters the tunnel.

[0125] A processing unit 802, configured to determine the relative speed and relative distance of the target train within the first time period based on the first information to obtain second information; the first time period is determined based on the time period for the reference train to pass through the tunnel.

[0126] A prediction unit 803, configured to use the second information and a prediction model to determine a risk coefficient of a rear-end collision between the target train and the reference train, so as to obtain a risk assessment result.

[0127] In one embodiment, the reference train may be used for:

[0128] When the reference train enters a tunnel, it uploads its first operation parameter to a cloud server.

[0129] In one embodiment, the GSM-R base station is arranged near the tunnel; the GSM-R base station may be used for:

[0130] The GSM-R base station determines whether the distance between the reference train and the tunnel entrance is less than a distance threshold, so as to obtain a second determination result;

[0131] When the second determination result indicates that the distance between the reference train and the tunnel entrance is less than the distance threshold, continuously obtain sensor data at the tunnel entrance according to a preset period;

[0132] Based on the obtained sensor data, determine the first operation parameter of the reference train, and upload it to the cloud server.

[0133] In one embodiment, the cloud server may further be used for:

[0134] After receiving the first operation parameter, the cloud server updates the status information of the reference train, and predicts a second operation parameter of the reference train in the tunnel based on the first operation parameter, so as to obtain first information.

[0135] In one embodiment, the GSM-R base station may further be used for: after the reference train enters the tunnel, the GSM-R base station obtains radio frequency identification (RFID) information of the reference train within a first time period; and based on the RFID information, determine a third operation parameter of the reference train, and upload the third operation parameter to the cloud server;

[0136] The cloud server may further be used for: correcting the second operation parameter based on the third operation parameter.

[0137] In one embodiment, the first time period includes a plurality of sampling points; the determining, based on the first information, a relative speed and a relative distance of the target train within the first time period to obtain second information may include:

[0138] Based on the first information, determine the relative speed and the relative distance of the target train at each sampling point according to a time axis;

[0139] Based on the relative speed and the relative distance of all sampling points, generate second information.

[0140] In one embodiment, using the second information and a prediction model to determine a risk coefficient of a rear-end collision between the target train and the reference train, and obtaining a risk assessment result may include:

[0141] Based on historical operation parameters of the reference train in a second time period before entering the tunnel, determining a historical relative distance and a historical relative speed of the target train in the second time period;

[0142] Based on the degree of fluctuation of the historical relative distance and the historical relative speed within the second time period, determining the credibility of the second information;

[0143] Based on the credibility, the second information, and the prediction model, determining a risk coefficient of a rear-end collision between the target train and the reference train, and obtaining a risk assessment result.

[0144] In one embodiment, the determining the credibility of the second information based on the degree of fluctuation of the historical relative distance and the historical relative speed within the second time period includes:

[0145] Based on all historical relative speed data within the second time period, determining the change situation of the historical relative speed, and generating a first change curve;

[0146] Based on all historical relative distance data within the second time period, determining the change situation of the historical relative distance, and generating a second change curve;

[0147] Based on the degree of fluctuation of the first change curve and the second change curve, determining the credibility of the second information.

[0148] In one embodiment, the determining the credibility of the second information based on the degree of fluctuation of the first change curve and the second change curve includes:

[0149] Based on the fluctuation frequency and the fluctuation amplitude of the first change curve, determining a first credibility of the relative speed in the second information;

[0150] Based on the fluctuation frequency and the fluctuation amplitude of the second change curve, determining a second credibility of the relative distance in the second information.

[0151] It should be noted that: when the above-mentioned rail transit rear-end collision risk assessment system conducts rail transit rear-end collision risk assessment, only the division of the above-mentioned program modules is used for illustration. In actual application, the above-mentioned processing can be allocated to different program modules according to needs, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the rail transit rear-end collision risk assessment system provided in the above-mentioned embodiment and the embodiment of the rail transit rear-end collision risk assessment method belong to the same concept. For the specific implementation process, please refer to the method embodiment and will not be elaborated here.

[0152] It should be noted that: "first", "second", etc. are used to distinguish similar objects and do not have to be used to describe a specific order or sequence.

[0153] In addition, the technical solutions described in the embodiments of the present application can be arbitrarily combined without conflict.

[0154] The above is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A method for evaluating the risk of rear-end collision in rail transit, characterized in that, The method includes: Obtaining the status information of a reference train from a cloud server; the status information indicates whether the reference train is inside or outside a tunnel; When the status information indicates that the reference train is inside the tunnel, obtaining first information from the cloud server; the first information characterizes second operating parameters of the reference train inside the tunnel; the first information is determined based on first operating parameters when the reference train enters the tunnel; Based on the first information, determining a relative speed and a relative distance of a target train within a first time period to obtain second information; the first time period is determined based on the time period for the reference train to pass through the tunnel; Using the second information and a prediction model to determine a risk coefficient of a rear-end collision between the target train and the reference train to obtain a risk assessment result; wherein, The method further includes: When the reference train enters the tunnel, uploading its own first operating parameters to the cloud server; A Global System for Mobile Communications - Railway (GSM-R) base station determines whether the distance between the reference train and the tunnel entrance is less than a distance threshold to obtain a second determination result; when the second determination result indicates that the distance between the reference train and the tunnel entrance is less than the distance threshold, continuously obtaining sensor data of the tunnel entrance at a preset period; based on the obtained sensor data, determining the first operating parameters of the reference train and uploading them to the cloud server; The method further includes: after receiving the first operating parameters, the cloud server updates the status information of the reference train and predicts the second operating parameters of the reference train inside the tunnel based on the first operating parameters to obtain first information; The method further includes: after the reference train enters the tunnel, the GSM-R base station obtains Radio Frequency Identification (RFID) information of the reference train within a first time period; based on the RFID information, determining third operating parameters of the reference train and uploading the third operating parameters to the cloud server; the cloud server corrects the second operating parameters based on the third operating parameters; The first time period includes multiple sampling points; the determining the relative speed and the relative distance of the target train within the first time period based on the first information to obtain second information includes: based on the first information, determining the relative speed and the relative distance of the target train at each sampling point along the time axis; generating second information based on the relative speed and the relative distance of all sampling points.

2. The method according to claim 1, characterized in that The using the second information and the prediction model to determine the risk coefficient of a rear-end collision between the target train and the reference train to obtain the risk assessment result includes: Based on historical operating parameters of the reference train in a second time period before entering the tunnel, determining a historical relative distance and a historical relative speed of the target train in the second time period; Based on the degree of fluctuation of the historical relative distance and the historical relative speed within the second time period, determining the credibility of the second information; Based on the credibility, the second information and the prediction model, determining the risk coefficient of a rear-end collision between the target train and the reference train to obtain the risk assessment result.

3. The method according to claim 2, characterized in that Determining the credibility of the second information based on the degree of fluctuation of the historical relative distance and the historical relative speed within the second time period includes: Based on all historical relative speed data within the second time period, determining the change situation of the historical relative speed and generating a first change curve; Based on all historical relative distance data within the second time period, determining the change situation of the historical relative distance and generating a second change curve; Based on the degree of fluctuation of the first change curve and the second change curve, determining the credibility of the second information.

4. The method according to claim 3, characterized in that Determining the credibility of the second information based on the degree of fluctuation of the first change curve and the second change curve includes: Based on the fluctuation frequency and fluctuation amplitude of the first change curve, determining the first credibility of the relative speed in the second information; Based on the fluctuation frequency and fluctuation amplitude of the second change curve, determining the second credibility of the relative distance in the second information.

5. A rear-end collision risk assessment system for rail transit, characterized in that, The system includes a target train, a cloud server, a reference train, and a GSM-R base station; the target train includes: A communication unit, configured to obtain the status information of the reference train from the cloud server; the status information indicates whether the reference train is inside or outside the tunnel; and, when the status information indicates that the reference train is inside the tunnel, obtaining the first information from the cloud server; the first information represents the second operating parameter of the reference train inside the tunnel; the first information is determined based on the first operating parameter when the reference train enters the tunnel; A processing unit, configured to determine the relative speed and relative distance of the target train within the first time period based on the first information, and obtain the second information; the first time period is determined based on the time period for the reference train to pass through the tunnel; A prediction unit, configured to use the second information and a prediction model to determine the risk coefficient of the target train and the reference train colliding with each other, and obtain a risk assessment result; where The reference train is configured to upload its own first operating parameter to the cloud server when entering the tunnel; The GSM-R base station is configured to determine whether the distance between the reference train and the tunnel entrance is less than a distance threshold, and obtain a second determination result; in the case where the second determination result indicates that the distance between the reference train and the tunnel entrance is less than the distance threshold, continuously obtain the sensor data of the tunnel entrance at a preset period; based on the obtained sensor data, determine the first operating parameter of the reference train and upload it to the cloud server; The cloud server is configured to update the status information of the reference train after receiving the first operating parameter, and predict the second operating parameter of the reference train inside the tunnel based on the first operating parameter, and obtain the first information; The GSM-R base station is further configured to obtain the radio frequency identification (RFID) information of the reference train within the first time period after the reference train enters the tunnel; based on the RFID information, determine the third operating parameter of the reference train and upload the third operating parameter to the cloud server; the cloud server is configured to correct the second operating parameter based on the third operating parameter; The first time period includes a plurality of sampling points; the processing unit is configured to: determine the relative speed and relative distance of the target train at each sampling point according to the time axis based on the first information; generate second information based on the relative speeds and relative distances of all sampling points.

Images