High-precision train positioning method and system based on environment-sensitive closed-loop detection

Abstract

The invention provides a high-precision train positioning method and system based on environmental sensitive closed-loop detection, and relates to the technical field of heavy haul railway transportation, and the method comprises the steps: determining the real-time position of a current train based on the data of a plurality of positioning sensors; the positioning sensor comprises a satellite positioning sensor, an inertial measurement unit and a speedometer; based on the data of the barometer and / or the data of the inertial measurement unit, determining a plurality of key positions on the railway track through which the current train passes; matching the real-time position with the geo-fencing area of each key position, and determining a target key position through which the current train passes; and correcting the real-time position based on the position information of the target key position. According to the method and the system provided by the invention, the positioning precision of the train on the rail road of the environment sensitive area is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of heavy-load railway transportation technology, and in particular to a high-precision train positioning method and system based on environmentally sensitive closed-loop detection. Background Art

[0002] When a railway train passes through environmentally sensitive areas, such as densely populated urban high-rise areas, long-distance tunnels, mountain forests and bridges, the satellite navigation system may not be able to provide accurate and continuous positioning in real time due to signal shielding or multipath effects, which poses special challenges to the train positioning system.

[0003] Therefore, how to improve the positioning accuracy of trains in environmentally sensitive areas has become a technical problem that needs to be urgently solved in the industry. Summary of the invention

[0004] The present application provides a high-precision train positioning method and system based on environmentally sensitive closed-loop detection, which are used to solve the technical problem of how to improve the positioning accuracy of trains in environmentally sensitive areas.

[0005] The present application provides a high-precision train positioning method based on environment-sensitive closed-loop detection, comprising: Determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; Determine, based on the data of the barometer and / or the data of the inertial measurement unit, that the current train passes through a plurality of key positions on the railway track; Matching the real-time position with the geo-fenced areas of each key position to determine the target key position that the current train passes through; Based on the position information of the target key position, the real-time position is corrected.

[0006] In some embodiments, determining the real-time position of the current train based on data from multiple positioning sensors includes: When the satellite signal received by the satellite positioning sensor is greater than a preset signal threshold, based on an error state extended Kalman filter algorithm, a fusion calculation is performed on the data of the satellite positioning sensor and the data of the inertial measurement unit to obtain a first fusion calculation result; Based on the Kalman filter algorithm, the first fusion calculation result and the data of the odometer are fused and calculated to obtain the real-time position of the current train.

[0007] In some embodiments, determining the real-time position of the current train based on data from multiple positioning sensors includes: When the satellite signal received by the satellite positioning sensor is less than a preset signal threshold, based on a Kalman filter algorithm, a fusion calculation is performed on the data of the inertial measurement unit and the data of the odometer to obtain a second fusion calculation result; Based on the second fusion calculation result, dead reckoning is performed on the historical position information of the current train to obtain the real-time position of the current train.

[0008] In some embodiments, the determining that the current train passes through a plurality of key positions on the railway track based on the data of the barometer and / or the data of the inertial measurement unit includes: Based on the data of the barometer, determining the variance of the air pressure value of the sliding window corresponding to the current train at the current moment; In the case where the air pressure value variance is greater than a preset variance threshold, determining that the current train passes through a plurality of key positions on the railway track; Alternatively, based on the data of the inertial measurement unit, determining the curvature of each position on the railway track that the current train passes; Based on the curvature of each position, it is determined that the current train passes through a plurality of key positions on the railway track.

[0009] In some embodiments, matching the real-time position with the geo-fenced areas of each key position to determine the target key position passed by the current train includes: Determine the geo-fenced area of ​​each key location with each key location as the center and a preset length as the radius; Determining the distance between the real-time position and each key position; In the case where the distance is smaller than the radius of the geo-fenced area of ​​any key location, the any key location is determined as the target key location.

[0010] In some embodiments, the correcting the real-time position based on the position information of the target key position includes: Determining a position deviation between the real-time position and the target key position based on a difference in longitude and latitude between the real-time position and the target key position; Based on the position deviation, the real-time position is corrected.

[0011] In some embodiments, the correcting the real-time position based on the position deviation includes: Determine the spherical angle between the real-time position and the target key position based on the latitude and longitude coordinates of the real-time position and the target key position; Based on the spherical angle, determining an angle deviation; Based on the angle deviation and the position deviation, a distance deviation for correcting the real-time position is determined.

[0012] The present application provides a high-precision train positioning system based on environment-sensitive closed-loop detection, comprising: A position calculation module, used to determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; A position determination module, used for determining a plurality of key positions on the railway track that the current train passes through based on the data of the barometer and / or the data of the inertial measurement unit; A closed-loop detection module, used to match the real-time position with the geo-fenced area of ​​each key position to determine the target key position passed by the current train; A position correction module is used to correct the real-time position based on the position information of the target key position.

[0013] The present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the high-precision train positioning method based on environment-sensitive closed-loop detection is implemented.

[0014] The present application provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the high-precision train positioning method based on environment-sensitive closed-loop detection is implemented.

[0015] The high-precision train positioning method and system based on environmentally sensitive closed-loop detection provided by the present application determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; based on barometer data and / or inertial measurement unit data, determine multiple key positions on the railway track through which the current train passes; match the real-time position with the geographic fence area of ​​each key position to determine the target key position through which the current train passes; based on the position information of the target key position, correct the real-time position; due to the use of a multi-sensor fusion method, the advantages of different sensors can be comprehensively utilized to effectively overcome the limitations of single positioning sensor data in different environments; the key position is determined by the change in air pressure in the car or the curvature of the track, and the real-time position of the train is corrected according to the precise position information of the key position, which effectively improves the positioning accuracy of the train on the railway track in environmentally sensitive areas, and also enhances the adaptability and flexibility of the positioning system in the face of track diversity. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flow chart of a high-precision train positioning method based on environmentally sensitive closed-loop detection provided in this application.

[0019] Figure 2 It is a schematic diagram of the installation of the hardware equipment provided in this application.

[0020] Figure 3 It is a schematic diagram of multi-sensor data fusion calculation provided by this application.

[0021] Figure 4 It is a schematic diagram of the data fusion method based on error state Kalman filtering provided by this application.

[0022] Figure 5 It is a schematic diagram of the data fusion method based on Kalman filtering provided in this application.

[0023] Figure 6 It is a schematic diagram of the overall architecture of the high-precision train positioning method based on environmentally sensitive closed-loop detection provided in this application.

[0024] Figure 7 It is a structural schematic diagram of a high-precision train positioning system based on environmentally sensitive closed-loop detection provided by the present application.

[0025] Figure 8 It is a schematic diagram of the structure of the electronic device provided by this application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second" etc. in the present application are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units or modules need not be limited to those steps or units or modules clearly listed, but may include other steps or units or modules that are not clearly listed or inherent to these processes, methods, products or equipment.

[0028] There are many types of train positioning technologies at present. One type relies on sensors installed beside the track, such as track circuits, query transponders, etc. The other type is sensors installed on the train, such as odometers (Odometry), inertial measurement units (IMU), etc. They can each meet specific train positioning needs to some extent, but they also have their own inherent defects. A single positioning technology cannot fully meet the important requirements of high precision, high reliability, high maintainability, and mobile blocking of train positioning systems. In addition, environmental factors such as electromagnetic interference, temperature and air pressure changes may also affect the accuracy of sensor positioning.

[0029] In order to solve the shortcomings of related technologies, Figure 1 is a flow chart of a high-precision train positioning method based on environment-sensitive closed-loop detection provided by the present application, such as Figure 1 As shown, the method includes step 110 , step 120 , step 130 and step 140 .

[0030] Step 110: Determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units, and odometers.

[0031] Specifically, the execution subject of the method provided in the embodiment of the present application is a high-precision train positioning system. The system can be implemented by software, such as a high-precision train positioning program running on a computer or server; it can also be implemented by hardware, such as a mobile terminal, computer or server that executes the high-precision train positioning method.

[0032] The current train is a train that needs real-time positioning when running on railway tracks in environmentally sensitive areas. Environmentally sensitive areas refer to areas with more changes in electromagnetic interference, temperature, light and air pressure.

[0033] The application scenario of the method provided in the embodiment of the present application is to install multiple positioning sensors on the current train and fuse the data of the multiple positioning sensors to achieve continuous high-precision positioning of the train position.

[0034] Figure 2 This is a schematic diagram of the installation of the hardware equipment provided by this application, such as Figure 2 As shown in the figure, the train is equipped with satellite positioning sensors, inertial measurement units and odometers, and a barometer is also provided. The satellite positioning sensor can receive signals sent by Beidou navigation satellites or other navigation satellites to calculate the position and attitude of the train. The odometer usually records the cumulative distance traveled by the train from a certain reference point, and can also be used to determine the position of the train. The inertial measurement unit is mainly used to measure the acceleration and angular velocity of an object, thereby calculating its position and attitude. The barometer is used to measure the atmospheric pressure of the train when it passes through different locations.

[0035] The method provided in the embodiment of the present application adopts a method of fusing satellite positioning sensors, inertial measurement units and odometers, which can provide stable positioning services under all-weather conditions, is not restricted by light and weather conditions, and provides high-precision, continuous and stable positioning information; it is relatively independent of the external environment, can work stably under various conditions, and improves the overall reliability of the system; in addition, these sensors are lower in cost, simple to install, and easy to integrate with existing railway systems.

[0036] Step 120: Based on the data of the barometer and / or the data of the inertial measurement unit, determine that the current train passes through a plurality of key positions on the railway track.

[0037] Specifically, in a railway operation scenario, a key position refers to a specific position or a specific area that is critical to the positioning accuracy of a train. In the method provided in the present application, two types of positions on a railway track can be determined as key positions.

[0038] The first category is locations where the air pressure in the car changes significantly, such as tunnel entrances and exits. Air pressure sensors are used in the car to monitor the changes in air pressure when the train is running in real time. Since there will be significant changes in air pressure when entering and exiting the tunnel, the data monitored by the barometer is used to determine that the train has entered or left the tunnel when the standard deviation of the air pressure value in the sliding window exceeds the preset threshold. Through real-time monitoring of air pressure data, the specific location of the tunnel can be accurately calibrated even when the navigation satellite signal is lost, thereby determining the real-time position of the train.

[0039] The second category is locations where the curvature of the track changes significantly, such as the intersection of a straight line, a gentle curve, and a circular curve. The angular velocity data of the gyroscope is used to detect the change in angular velocity of the train when it switches between a straight line and a curved track. When a train enters a curved track from a straight track (or vice versa), its angular velocity changes significantly. The gyroscope will continuously monitor the angular velocity of the train. When the data shows that the angular velocity changes suddenly from one stable state to another, it can be judged that the train has passed the intersection of a straight line and a curve, and the real-time position of the train can be determined.

[0040] Step 130: Match the real-time position with the geographic fence area of ​​each key position to determine the target key position that the current train passes through.

[0041] Specifically, a geo-fence may be set around each key location. The geo-fence area may be a circular area with the key location as the center.

[0042] The real-time position of the train is matched with the geo-fenced area of ​​each key position to obtain the target key position. The target key position is the key position that the current train is passing through. By matching the real-time position with the geo-fenced area of ​​each key position, unnecessary comparisons can be significantly reduced, and calculations are only performed when the train approaches the corresponding key position, reducing the computational complexity.

[0043] Step 140: Correct the real-time position based on the position information of the target key position.

[0044] Specifically, the location information can be represented by longitude and latitude coordinates, etc. The location information of the key location of the target can be used to accurately calibrate or measure.

[0045] When the current train is detected to have reached the target key position, the real-time position of the train can be matched and corrected according to the position information of the target key position, and the sensor parameters can be modified to eliminate the accumulated errors caused by driving for a period of time, so that more accurate positioning can be performed for positions other than the key position. For example, the inertial measurement unit and odometer will produce accumulated errors due to driving, so the parameters of these two sensors can be modified according to the position information of the key position.

[0046] The high-precision train positioning method based on environmentally sensitive closed-loop detection provided in the embodiment of the present application determines the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; based on the data of the barometer and / or the data of the inertial measurement unit, multiple key positions on the railway track through which the current train passes are determined; the real-time position is matched with the geographic fence area of ​​each key position to determine the target key position through which the current train passes; the real-time position is corrected based on the position information of the target key position; due to the use of a multi-sensor fusion method, the advantages of different sensors can be comprehensively utilized to effectively overcome the limitations of single positioning sensor data in different environments; the key position is determined by the change in air pressure in the car or the curvature of the track, and the real-time position of the train is corrected according to the precise position information of the key position, which effectively improves the positioning accuracy of the train on the railway track in environmentally sensitive areas, and also enhances the adaptability and flexibility of the positioning system in the face of track diversity.

[0047] It should be noted that each implementation method of the present application can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0048] In some embodiments, the navigation satellites of the Beidou positioning system provide absolute positions, while the inertial measurement unit and odometer provide relative positions. Therefore, in areas with Beidou satellite signals, the train position is calculated by integrating Beidou, inertial measurement unit and odometer. In areas where Beidou satellite signals are interrupted, the train position is calculated by integrating inertial measurement unit and odometer. The longitude and latitude coordinates of the train at each acquisition time are obtained. As a result of positioning. Indicates location The latitude coordinate of Indicates location The longitude coordinate of .

[0049] The Beidou, inertial measurement unit, and odometer data are timestamped. The Beidou acquisition frequency is 10 Hz (Hertz), that is, once every 0.1 seconds. The inertial measurement unit and odometer acquisition frequencies are 100 Hz, that is, once every 0.01 seconds. Therefore, the Beidou positioning results are used for prediction, and the inertial measurement unit and odometer with a higher acquisition frequency are used to correct the Beidou results.

[0050] The error state Kalman filter algorithm is used to fuse the Beidou and inertial measurement unit data to obtain the longitude and latitude coordinates. The result is then fused with the odometer to obtain the real-time positioning result of the train through the Kalman filter algorithm.

[0051] In some embodiments, determining the real-time position of the current train based on data from a plurality of positioning sensors includes: When the satellite signal received by the satellite positioning sensor is greater than a preset signal threshold, the data of the satellite positioning sensor and the data of the inertial measurement unit are fused and calculated based on an error state extended Kalman filter algorithm to obtain a first fusion calculation result; Based on the Kalman filter algorithm, the first fusion calculation result and the odometer data are fused to obtain the real-time position of the current train.

[0052] Specifically, when the satellite signal received by the satellite positioning sensor is greater than the preset signal threshold, it means that the Beidou signal is available, and the data of the satellite positioning sensor, inertial measurement unit and odometer are fused together to form a multi-sensor navigation solution. In this case, the integrated system can generate a complete navigation solution at a high data rate, including position, velocity, acceleration and attitude.

[0053] Figure 3 is a schematic diagram of multi-sensor data fusion calculation provided by this application, such as Figure 3 As shown, the core part of the multi-sensor navigation system is the data fusion algorithm. The embodiment of the present application adopts a hierarchical fusion method. First, the Error State Extended Kalman Filter (ESKF) method is used in a local filter to fuse the results of the satellite positioning sensor and the inertial measurement unit. The result is then transmitted to the main filter and fused with the odometer to generate a global optimal estimate to obtain the final positioning result. Among them, the satellite positioning sensor provides the ground speed, and the angular velocity and acceleration information of the inertial measurement unit correct the speed and direction of travel determined by the satellite, and output the result. The odometer provides absolute speed information to correct the relative speed information of the inertial measurement unit. After the final fusion, a comprehensive speed and direction estimate is obtained, and the positioning result in the navigation coordinate system is calculated. This estimate takes into account the advantages and disadvantages of each sensor. The specific steps are as follows: Step 1: Based on the error state extended Kalman filter algorithm, the data of the satellite positioning sensor and the data of the inertial measurement unit are fused and calculated to obtain a first fusion calculation result.

[0054] First, the data provided by the Beidou Navigation Satellite System (BDS) and the inertial measurement unit data are fused using the ESKF algorithm. ESKF does not filter the navigation information, but filters the errors in the navigation information, because the error amount is a smaller value relative to the direct positioning information data, and is always close to 0, so it is more accurate when fitted linearly.

[0055] Figure 4Schematic diagram of the data fusion method based on error state Kalman filtering provided by this application. Figure 4 As shown, the method involves two coordinate systems, namely the body coordinate system and the navigation coordinate system.

[0056] The body coordinate system is used for the coordinate system of the inertial measurement unit system. The measured value reflects the acceleration and rotational speed relative to the object itself. It is fixed to the coordinate system of the moving object and is usually used to describe the posture and dynamics of the object. The three axes are defined as follows: X-axis: points to the direction of the object's forward movement; Y-axis: usually points to the right side of the object, perpendicular to the X-axis; Z-axis: usually points to the bottom of the object, perpendicular to both the X-axis and the Y-axis.

[0057] The navigation coordinate system (North East Down, NED) is commonly used in satellite positioning systems, etc., and is often used to describe the position and movement direction of objects on the earth's surface. The definition of NED is as follows: N axis: perpendicular to the earth's surface, indicating the horizontal direction of north; E axis: perpendicular to the N axis, pointing to the geographic east direction; D axis: perpendicular to the earth's surface, indicating the downward direction.

[0058] In navigation systems, it is usually necessary to convert the data in the body coordinate system obtained from the inertial measurement unit to the navigation coordinate system in order to use the data of global positioning systems such as the Global Positioning System (GPS) or Beidou for accurate navigation. This conversion requires the use of attitude information to convert the linear acceleration and angular velocity data measured in the body coordinate system into data in the geographic coordinate system. The real-time dynamics of the target object are combined with the absolute position in the earth coordinate system to achieve accurate position tracking and navigation.

[0059] The state equation of the inertial measurement unit can be expressed as:

[0060] In the formula, is the misalignment angle, i.e. the rotation error; is the component of the Earth's rotation angular velocity, , (radians per second), is the current latitude; = , is the component of the gyroscope bias in the body coordinate system, The conversion from the main body coordinate system to the Beidou navigation coordinate system at the current moment; It is the acceleration measured by the inertial measurement unit expressed in the navigation coordinate system; is the component of the accelerometer bias in the body coordinate system; It's speed. It's displacement.

[0061] In the Kalman filter, the state equation is:

[0062] In the formula, is the state quantity to be estimated. For the fusion system here, the displacement error is selected , speed error , attitude error , gyroscope bias error , accelerometer bias error , a total of 15 dimensions as error states, written as a vector as follows:

[0063] In the formula, the displacement error ; Speed ​​error ; Attitude error ; Gyro bias ; Accelerometer bias .

[0064] The nominal state is the directly estimated positioning state. Its update is divided into the update process of position, velocity and attitude, and the update equation group is:

[0065] In the formula, the physical meanings of each parameter are: It is the position coordinates of the GPS or Beidou device installed on the train in the current navigation coordinate system in three-dimensional space; is the speed of the train in the current navigation coordinate system; is the attitude matrix, that is, the rotation matrix of the data collected by the IMU from the body coordinate system to the navigation coordinate system; It is the three-dimensional acceleration data measured by the accelerometer device in the IMU in the body coordinate system; It is the three-dimensional angular velocity data measured by the gyroscope device in the IMU in the body coordinate system; is the gravitational acceleration vector, which is set in three-dimensional space as, ; is the time step; is the acceleration bias deviation; is the angular velocity bias deviation.

[0066] Error Status (error-state) is the difference between the estimated state and the actual state, and the influence of gravity is not considered here. , speed error status , attitude error state , acceleration bias error and angular velocity bias error Update, the update equation group is:

[0067] In the formula, the physical meaning of each parameter is: is the process noise, which represents the random error or noise in the system model; is the transformation matrix from the navigation coordinate system to the body coordinate system; is the process noise of attitude update; Process noise for acceleration bias update; is the process noise of the angular velocity bias update.

[0068] According to the IMU error equation, the state quantity Substituting into the state equation, we can get the transfer matrix :

[0069] Where:

[0070] Represent the bias noise and noise transfer matrix of the gyroscope and accelerometer in the IMU respectively:

[0071] In the formula, The physical meaning of the parameters is: They respectively represent the angular velocity noise in the x-axis, y-axis, and z-axis directions measured by the gyroscope in the body coordinate system; They respectively represent the acceleration noise measured by the accelerometer in the x-axis, y-axis, and z-axis directions in the body coordinate system.

[0072] Then the observation equation is derived, the predicted value comes from the inertial measurement unit, and the observed value comes from the Beidou system.

[0073] The observation equation can be expressed as:

[0074] in, is the observation vector, ; is the state vector, ; is the observation matrix, which is used to transform the state vector Convert to observation values ​​in observation space; is the observation noise, which represents the random error generated in the sensor measurement; is the noise matrix, which represents the influence of observation noise.

[0075] Then use the ESKF algorithm to predict and update. The predicted state quantity and the covariance corresponding to the state quantity are:

[0076] In the formula, is the state vector predicted by the system, indicating that at the current moment The predicted status of is the state vector at the previous moment; is the state transfer matrix, which represents the evolution of the system state in one time step. Map to the current moment; is the noise input matrix, which represents the noise affecting the system state; is the process noise matrix, i.e. the noise measured by the sensor; is the covariance matrix of the predicted state, which represents the uncertainty of the system state; is the covariance matrix of the system state at the previous moment; is the process noise covariance matrix.

[0077] Then the correction is performed. Kalman gain is used to balance the weight between the predicted value and the observed value:

[0078] In the formula, , and are the noise matrix, observation matrix and observation noise covariance matrix respectively.

[0079] The error of correcting the predicted state covariance can be expressed as:

[0080] The error of correcting the predicted state can be expressed as:

[0081] in, is the observed value at the current moment.

[0082] ESKF corrects the error of the state. After each iteration of ESKF, the state quantity must be Reset to zero, the covariance matrix The value of needs to be retained. After each Kalman iteration, the final error needs to be brought back to the predicted position, speed, and direction to eliminate the error.

[0083] Step 2: Based on the Kalman filter algorithm, the first fusion calculation result and the odometer data are fused to obtain the real-time position of the current train.

[0084] The positioning coordinates after the fusion of BDS and IMU (the first fusion calculation result) are then fused with the data of the odometer, using the basic Kalman filter fusion algorithm. Step-by-step fusion, by fusing different sensor data at different levels, can more flexibly handle the characteristics and uncertainties of various sensors and adapt to different application scenarios and environmental conditions.

[0085] The basic Kalman filter fusion process is divided into two steps: prediction and correction.

[0086] In the prediction phase: The state update equation can be expressed as:

[0087] The noise covariance update equation can be expressed as:

[0088] During the calibration phase: Calculate Kalman gain :

[0089] Update estimate status :

[0090] Update the covariance matrix:

[0091] In the formula, For the current The estimated value of the state vector at the moment, including position, speed, etc.; is the estimated state of the system at the previous moment; is the control transfer matrix, which indicates that the system state changes from Evolving to The transfer relationship of time; is the input transfer matrix; is the control input; is the prediction covariance matrix, which represents the uncertainty of the predicted state estimate; represents the covariance matrix of the system at the previous moment; is the process noise covariance matrix, i.e., the noise generated by the sensor measurement; is the observation matrix; is the observation noise covariance matrix; is the sensor observation value; is the updated covariance matrix, which represents the uncertainty of the updated state estimate; is the identity matrix, which is set to be consistent with the observation matrix dimension.

[0092] The high-precision train positioning method based on environmentally sensitive closed-loop detection provided in the embodiment of the present application adopts the error state extended Kalman filter fusion algorithm ESKF to replace the state fusion of the traditional extended Kalman filter for the highly complex nonlinear problem of railway train positioning. By expanding and accurately modeling the error state, it can effectively handle the estimation problem of the nonlinear system, better approximate the nonlinear problem, improve the accuracy of the filter, and thus improve the accuracy of the overall positioning system. In addition, by expanding the error state, the method can better capture the dynamic characteristics of the system and the noise characteristics of the sensor, thereby enhancing the system's resistance to noise and interference and improving the robustness of the positioning system.

[0093] In some embodiments, determining the real-time position of the current train based on data from a plurality of positioning sensors includes: When the satellite signal received by the satellite positioning sensor is less than a preset signal threshold, the data of the inertial measurement unit and the data of the odometer are fused and calculated based on the Kalman filter algorithm to obtain a second fusion calculation result; Based on the second fusion calculation result, the historical position information of the current train is dead reckoned to obtain the real-time position of the current train.

[0094] Specifically, Figure 5 is a schematic diagram of a data fusion method based on Kalman filtering provided by this application, such as Figure 5 As shown, when a train runs in a signal obstruction area such as a bridge, tunnel or station, the satellite signal quality will degrade or become unavailable.

[0095] First, the train positioning system needs to continuously monitor the signal quality of the Beidou system. Once the signal quality drops below a preset signal threshold, the system will automatically switch to the backup mode, that is, the inertial measurement unit and odometer mode. The speed and attitude results are obtained for dead reckoning, where the attitude matrix are the roll angle, pitch angle and yaw angle respectively, and the speed is .

[0096] Convert it into the velocity component in the navigation coordinate system:

[0097] The coordinates of the last point before the satellite signal lost lock, that is, The longitude and latitude coordinates after time fusion As the starting point, perform dead reckoning.

[0098]

[0099] In the formula, For trains The latitude coordinate of the time, For trains The longitude coordinate of the moment; For time difference.

[0100] The high-precision train positioning method based on environmentally sensitive closed-loop detection provided in the embodiment of the present application fuses the data of the inertial measurement unit and the data of the odometer when satellite signals are unavailable, performs dead reckoning on the historical position information of the current train, and obtains the real-time position of the current train. It comprehensively utilizes the advantages of different sensors, effectively overcomes the limitations of single positioning sensor data in different environments, and improves the accuracy of the overall positioning system.

[0101] In some embodiments, based on the data of the barometer and / or the data of the inertial measurement unit, it is determined that the current train passes through multiple key positions on the railway track, including: Based on the data of the barometer, determine the variance of the air pressure value of the sliding window corresponding to the current train at the current time; When the air pressure value variance is greater than a preset variance threshold, determining that the current train passes through a plurality of key positions on the railway track; Alternatively, based on the data from the inertial measurement unit, the curvature of each position on the railway track that the current train passes through is determined; Based on the curvature of each position, it is determined that the current train passes through multiple key positions on the railway track.

[0102] Specifically, a key position database is established for the key position information on the railway track for subsequent matching. The two types of key positions are stored as a series of , each point stores its longitude and latitude coordinates as the correct comparison result for subsequent closed-loop detection.

[0103] (1) Each key location point includes the following information

[0104] Location information (longitude, latitude, altitude): Record each key location as ; Key location type (type 1 = intersection of straight and curved tracks, type 2 = point of sudden change in air pressure); curvature (calculated based on the longitude and latitude of adjacent points); track line number , key position number .

[0105] (2) Calculation of track point curvature

[0106] For closed-loop detection of track switching points, it is necessary to continuously optimize and update during each driving process to obtain a more accurate correction position. Key locations are marked and accurate longitude and latitude coordinates are stored. First, according to the track map, the curvature of each point on the track line is calculated. The steps are as follows: Step 1: Convert latitude and longitude coordinates to spherical coordinate system

[0107] Starting point of line As the origin of the coordinate system, the radius of the earth According to the train positioning method in the above embodiment, the longitude and latitude coordinates of the train at each collection time are obtained. , and transform them into the corresponding spherical coordinates respectively .

[0108]

[0109] Step 2: Calculate the curvature of each point

[0110] according to point and its previous collection point point and the next collection point Point, the coordinates of three points, determine a circle, and get The magnitude of the curvature of the point.

[0111]

[0112] The radius of the circle determined by three consecutive points.

[0113] The barometer and gyroscope data are used to determine whether the train has reached the key locations for closed-loop detection set in this application, including tunnel entrances, tunnel exits, and track switching points. The key locations on a railway line are recorded as a group .

[0114] The first method to determine the key position: According to the data of the barometer, the variance of the air pressure value of the sliding window corresponding to the current train at the current moment is determined; when the variance of the air pressure value is greater than a preset variance threshold, it is determined that the current train passes through multiple key positions on the railway track.

[0115] Take the tunnel as an example, there are points where the air pressure value may change significantly. Record the air pressure of the train at each moment and set a short time sliding window , calculate the variance of air pressure within the sliding window , set the threshold .like , it is judged that the train has reached the critical position and closed-loop detection is required.

[0116] The second method to determine the key position: According to the data of the inertial measurement unit, the curvature of each position on the railway track that the current train passes through is determined; based on the curvature of each position, multiple key positions on the railway track that the current train passes through are determined.

[0117] The key positions here can include the intersection of straight lines, circular curves, and transition curves. The data mining method is used for automatic judgment, and the random forest algorithm is used to automatically classify the key positions of straight lines, circular curves, transition curves, and transitions. The value of the inertial measurement unit at each acquisition moment is recorded, and the curvature of each inertial measurement unit acquisition point is calculated. The curvature is used to judge whether the train is running from a straight line to a curve or from a curve back to a straight line. The curvature directly reflects the curvature of the track. The direction, curvature, angular velocity, etc. of each acquisition point are used as features for learning. The random forest method is used for classification to determine whether the train is at a key position.

[0118] The high-precision train positioning method based on environmentally sensitive closed-loop detection provided in the embodiment of the present application introduces a barometer and track curvature characteristics, proposes a key position determination method for special railway scenarios, and applies it to closed-loop detection. In view of the openness and diversity of long-distance railway transportation, tunnel entrances and exits and junctions of different track types are taken as key positions for closed-loop detection to reduce the cumulative errors caused by long-distance operation.

[0119] In some embodiments, the real-time location is matched with the geo-fenced areas of each key location to determine the target key location that the current train passes through, including: Determine the geo-fenced area of ​​each key location with each key location as the center and a preset length as the radius; Determine the distance between the real-time location and various key locations; When the distance is less than the radius of the geo-fenced area of ​​any key location, any key location is determined as a target key location.

[0120] Specifically, the geo-fenced areas for each key location include: First, identify key locations on the railway line, such as tunnel entrances / exits and track switching points.

[0121] Secondly, for each key position Set a geo-fenced area. A circular area with a key location as the center needs to set the latitude and longitude coordinates and radius of the center point. That is, each key location is defined as a triple .

[0122] Identify key target locations including: When a train is detected to have arrived at a critical location, a match is required. First, the real-time location data of the train is detected. Whether the train enters the geographical fence area preset at a key location, the distance from the point to the center of the circle is calculated to determine whether the train enters the fence area.

[0123] calculate and If the distance between two points is less than the radius , then it is judged to enter the key position within the geo-fence.

[0124] The high-precision train positioning method based on environment-sensitive closed-loop detection provided by the embodiment of the present application sets a geographic fence area around each key position. When the train is identified to arrive at the key position, the calculated longitude and latitude coordinates of the train are matched with the key position corresponding to the fence, which significantly reduces unnecessary comparisons and only performs calculations when the train approaches the corresponding key position, reducing the computational complexity.

[0125] In some embodiments, based on the position information of the target key position, the real-time position is corrected, including: Determine a position deviation between the real-time position and the target key position based on a difference in longitude and latitude between the real-time position and the target key position; Based on the position deviation, the real-time position is corrected.

[0126] Specifically, when a train is detected entering a geo-fenced area, closed-loop detection and position correction are performed. The current real-time position of the train is compared with the preset coordinates of the fence center, and the existing deviation is corrected. The corrected data is recorded and necessary analysis is performed to optimize future detections.

[0127] Use the Haversine formula to calculate the distance between the real-time position of the train and the center point of the geo-fence. Set a threshold. If the longitude and latitude coordinates between the two points are less than the set threshold, it is judged that a closed loop is formed and the train has reached the key position.

[0128] Real-time train location With key position points ( , ) Difference in longitude It can be expressed as:

[0129] The difference between the real-time position of the train and the latitude of the key location point It can be expressed as:

[0130] Position deviation between real-time position and target key position It can be expressed as:

[0131] in, is the radius of the earth, which is set here as the average radius of the earth. .

[0132] The high-precision train positioning method based on environmentally sensitive closed-loop detection provided in the embodiment of the present application corrects the real-time position according to the position information of the target key position, effectively improves the positioning accuracy of the train on the railway track in environmentally sensitive areas, and enhances the adaptability and flexibility of the positioning system when facing track diversity.

[0133] In some embodiments, based on the position deviation, the real-time position is corrected, including: Determine the spherical angle between the real-time position and the target key position based on the latitude and longitude coordinates of the real-time position and the target key position; Based on the spherical angle, the angle deviation is determined; Based on the angle deviation and the position deviation, a distance deviation for correcting the real-time position is determined.

[0134] Specifically, first, the distance between the fused positioning point A (real-time position) and the actual key position point B (target key position) is calculated according to the Haversine formula: (Position deviation). And calculate the angular deviation between the predicted position and the actual position direction . C is the spherical angle between points A and B:

[0135] Among them, the longitude and latitude coordinates of point A are expressed as ( , the longitude and latitude coordinates of point B are expressed as ( .

[0136] The calculated distance and driving direction angle deviation are used to update the subsequent fused position estimate by adding the distance deviation in the direction determined by the angle deviation to adjust the current position estimate. This is achieved through trigonometric transformation:

[0137] In the formula, and is the distance deviation.

[0138] For subsequent positioning, the original sensor output is adjusted before being input into the fusion algorithm, the deviation is brought into each fusion positioning result, and the deviation update is dynamically considered every time a key position is reached for closed-loop detection to optimize and consider more reliable data.

[0139] The high-precision train positioning method based on environmentally sensitive closed-loop detection provided in the embodiment of the present application corrects the real-time position according to the position deviation, thereby effectively improving the positioning accuracy of the train on the railway track in environmentally sensitive areas.

[0140] Figure 6 is a schematic diagram of the overall architecture of the high-precision train positioning method based on environment-sensitive closed-loop detection provided by the present application, such as Figure 6 As shown, this method combines multi-sensor fusion and closed-loop detection based on Kalman filtering.

[0141] First, the multi-sensor data fusion of the Beidou Positioning System (BDS), Inertial Navigation System (IMU) and odometer is used to achieve continuous high-precision positioning of the train position. The significant advantage of this method lies in its wide applicability: it can not only accurately locate at fixed points such as stations, but also maintain the continuity and accuracy of positioning during long-distance travel between stations and special environmental conditions, such as tunnels or bridges without satellite signals. Secondly, closed-loop detection technology is used to set up key positions in environmentally sensitive areas for error correction. The switching points with significant changes in the train and the intersection points of different track types are taken as key positions. A closed-loop detection is performed to correct the positioning deviation caused by multi-sensor fusion, thereby improving the positioning accuracy in key areas.

[0142] Furthermore, the present application introduces environmental sensing technology as a basis for judging whether a train has reached an environmentally sensitive area. Changes in external environmental pressure when a train enters or exits a tunnel can cause the air pressure sensor to record significant data fluctuations. The present application uses air pressure changes as a reliable indicator to detect the tunnel entry and exit status of a train. This strategy not only enhances the positioning system's ability to adapt to environmental changes, but also provides more key moments and position markers in closed-loop detection, effectively reducing cumulative errors in long-distance travel and special environmental conditions.

[0143] The gyroscope in the inertial measurement unit system can capture the changes in the angular velocity of the train when it is traveling on different track types. Railway tracks are divided into three types: straight track, transition curve track and circular curve track. The transition curve is one of the key factors that must be considered when designing a railway line. It connects the straight line and the circular curve. Through the continuous change of its own curvature, the curvature gradually transitions from 0 on the straight line to 1 / R on the circular curve, which plays a role in the smooth transition between different track shapes. When the train turns from a straight track to a curve, the curvature of its travel path changes, and accordingly, the angular velocity of the train also changes. By analyzing these angular velocity data, the gyroscope can accurately determine whether the train is traveling in a straight line or making a turning motion. The gyroscope data can be used to assist in correcting the positioning errors accumulated due to long-term driving on complex track conditions. For example, after a long distance of driving on a curve, the traditional positioning method may produce deviations, and the angular velocity information provided by the gyroscope can help identify and correct these deviations.

[0144] The above method mainly solves: (1) This solution uses three sensors: Beidou, inertial measurement unit, and odometer. Beidou positioning can provide high-precision positioning information. The inertial measurement unit provides position and speed updates when Beidou information is blocked, but it will produce cumulative errors. The odometer provides additional speed and distance information. The fusion of the three reduces the shortcomings of a single sensor and improves the robustness and accuracy of the system. The error extended Kalman filter (ESKF) algorithm is introduced to directly process the error of state estimation instead of directly processing the state itself. It is suitable for nonlinear systems, reduces error estimation, effectively compensates for sensor bias, noise and other error sources, and improves the positioning accuracy of the entire system.

[0145] (2) This application proposes a new closed-loop detection strategy for environmentally sensitive areas where satellite positioning is limited, such as in tunnels, under bridges, and at the intersection of straight and curved tracks. By monitoring whether the barometer and inertial measurement unit gyroscope data installed in the train have changed suddenly, it is possible to accurately determine whether the train has entered or left these specific areas. The positioning accuracy and continuity of the train in environmentally sensitive areas are improved, especially when traditional satellite positioning technology is limited. After each closed-loop detection cumulative error correction, the deviation generated by the sensor is dynamically updated and added to the subsequent point positioning, providing a new and reliable judgment basis for closed-loop detection.

[0146] (3) For the first time, a database of key track locations is established for the intersection of straight lines and curves and points where the air pressure changes significantly on the railway. The type of each point is recorded, and the precise latitude, longitude and altitude information is stored. The curvature of each track point is calculated for subsequent matching.

[0147] (4) Dynamic track type perception and positioning correction

[0148] The angular velocity data provided by the gyroscope in the inertial measurement unit is used to dynamically perceive the type of train track. The switching points between the straight track, the gentle curve track and the circular curve track are also used as correction points for closed-loop detection to respond promptly and correct positioning errors when the geometric state of the train track changes. This effectively improves the positioning accuracy of the train on the continuous curve track and enhances the adaptability and flexibility of the positioning system when facing track diversity.

[0149] The system provided in the embodiment of the present application is described below. The system described below and the method described above can be referenced to each other.

[0150] Figure 7 is a schematic diagram of the structure of a high-precision train positioning system based on environment-sensitive closed-loop detection provided by the present application, such as Figure 7 As shown, the system includes: The position calculation module 710 is used to determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; A position determination module 720 is used to determine a plurality of key positions on the railway track that the current train passes through based on the data of the barometer and / or the data of the inertial measurement unit; A closed loop detection module 730 is used to match the real-time position with the geo-fenced area of ​​each key position to determine the target key position that the current train passes through; The position correction module 740 is used to correct the real-time position based on the position information of the target key position.

[0151] The high-precision train positioning system based on environmentally sensitive closed-loop detection provided in the embodiment of the present application determines the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; based on the data of the barometer and / or the data of the inertial measurement unit, multiple key positions on the railway track through which the current train passes are determined; the real-time position is matched with the geographic fence area of ​​each key position to determine the target key position through which the current train passes; the real-time position is corrected based on the position information of the target key position; due to the use of a multi-sensor fusion method, the advantages of different sensors can be comprehensively utilized to effectively overcome the limitations of single positioning sensor data in different environments; the key position is determined by the change in air pressure in the car or the curvature of the track, and the real-time position of the train is corrected according to the precise position information of the key position, which effectively improves the positioning accuracy of the train on the railway track in environmentally sensitive areas, and also enhances the adaptability and flexibility of the positioning system in the face of track diversity.

[0152] Figure 8 is a schematic diagram of the structure of the electronic device provided by this application, such as Figure 8 As shown, the electronic device may include: a processor (Processor) 810, a communication interface (Communications Interface) 820, a memory (Memory) 830 and a communication bus (Communications Bus) 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic command in the memory 830 to execute the method described in the above embodiment, for example: The real-time position of the current train is determined based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; based on barometer data and / or inertial measurement unit data, multiple key positions on the railway track that the current train passes through are determined; the real-time position is matched with the geographic fence area of ​​each key position to determine the target key position that the current train passes through; based on the position information of the target key position, the real-time position is corrected.

[0153] In addition, the logical commands in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several commands to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0154] The processor in the electronic device provided in the embodiment of the present application can call the logic instructions in the memory to implement the above method. Its specific implementation method is consistent with the implementation method of the aforementioned method and can achieve the same beneficial effects, which will not be repeated here.

[0155] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the methods provided in the above embodiments are implemented.

[0156] Its specific implementation is consistent with the aforementioned method implementation and can achieve the same beneficial effects, so it will not be repeated here.

[0157] An embodiment of the present application provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0158] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0159] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A high-precision train positioning method based on environment-sensitive closed-loop detection, characterized in that: include: Determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; Determine, based on the data of the barometer and / or the data of the inertial measurement unit, that the current train passes through a plurality of key positions on the railway track; Matching the real-time position with the geo-fenced areas of each key position to determine the target key position that the current train passes through; Based on the position information of the target key position, the real-time position is corrected.

2. The high-precision train positioning method based on environment-sensitive closed-loop detection according to claim 1 is characterized in that: The method of determining the real-time position of the current train based on data from a plurality of positioning sensors comprises: When the satellite signal received by the satellite positioning sensor is greater than a preset signal threshold, based on an error state extended Kalman filter algorithm, a fusion calculation is performed on the data of the satellite positioning sensor and the data of the inertial measurement unit to obtain a first fusion calculation result; Based on the Kalman filter algorithm, the first fusion calculation result and the data of the odometer are fused and calculated to obtain the real-time position of the current train.

3. The high-precision train positioning method based on environment-sensitive closed-loop detection according to claim 1 is characterized in that: The method of determining the real-time position of the current train based on data from a plurality of positioning sensors comprises: When the satellite signal received by the satellite positioning sensor is less than a preset signal threshold, based on a Kalman filter algorithm, a fusion calculation is performed on the data of the inertial measurement unit and the data of the odometer to obtain a second fusion calculation result; Based on the second fusion calculation result, dead reckoning is performed on the historical position information of the current train to obtain the real-time position of the current train.

4. The high-precision train positioning method based on environment-sensitive closed-loop detection according to claim 1 is characterized in that: The method of determining that the current train passes through a plurality of key positions on the railway track based on the data of the barometer and / or the data of the inertial measurement unit includes: Based on the data of the barometer, determining the variance of the air pressure value of the sliding window corresponding to the current train at the current moment; When the air pressure value variance is greater than a preset variance threshold, determining that the current train passes through a plurality of key positions on the railway track; Alternatively, based on the data of the inertial measurement unit, determining the curvature of each position on the railway track that the current train passes; Based on the curvature of each position, it is determined that the current train passes through a plurality of key positions on the railway track.

5. The high-precision train positioning method based on environment-sensitive closed-loop detection according to claim 1 is characterized in that: The matching of the real-time position with the geographical fence area of ​​each key position to determine the target key position passed by the current train includes: Determine the geo-fenced area of ​​each key location with each key location as the center and a preset length as the radius; Determining the distance between the real-time position and each key position; In the case where the distance is smaller than the radius of the geo-fenced area of ​​any key location, the any key location is determined as the target key location.

6. The high-precision train positioning method based on environment-sensitive closed-loop detection according to claim 1 is characterized in that: The correcting the real-time position based on the position information of the target key position includes: Determining a position deviation between the real-time position and the target key position based on a difference in longitude and latitude between the real-time position and the target key position; Based on the position deviation, the real-time position is corrected.

7. The high-precision train positioning method based on environment-sensitive closed-loop detection according to claim 6 is characterized in that: The correcting the real-time position based on the position deviation comprises: Determine a spherical angle between the real-time position and the target key position based on the latitude and longitude coordinates of the real-time position and the target key position; Based on the spherical angle, determining an angle deviation; Based on the angle deviation and the position deviation, a distance deviation for correcting the real-time position is determined.

8. A high-precision train positioning system based on environmentally sensitive closed-loop detection, characterized in that: include: A position calculation module, used to determine the real-time position of the current train based on data from multiple positioning sensors; the positioning sensors include satellite positioning sensors, inertial measurement units and odometers; A position determination module, used for determining a plurality of key positions on the railway track that the current train passes through based on the data of the barometer and / or the data of the inertial measurement unit; A closed-loop detection module, used to match the real-time position with the geo-fenced area of ​​each key position to determine the target key position passed by the current train; A position correction module is used to correct the real-time position based on the position information of the target key position.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the high-precision train positioning method based on environmentally sensitive closed-loop detection as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the high-precision train positioning method based on environmentally sensitive closed-loop detection as described in any one of claims 1 to 7 is implemented.

Images