Rail Transit Safety Detection Device and Evaluation Method during Shield Tunnel Construction under High-Speed Railway

Abstract

The present invention relates to the technical field of railway traffic safety, and particularly relates to a driving safety detection device and an evaluation method for high-speed trains passing through shield construction tunnels, including a point cloud acquisition module, a laser indication module, and a processing module. The point cloud acquisition module can acquire the point cloud model of the high-speed railway subgrade area to be detected. The laser indication module can measure the center coordinates of the target board on the point cloud acquisition module. The processing module is electrically connected to the point cloud acquisition module and the laser indication module respectively to receive the point cloud model data and the center coordinate data of the target board and process them to obtain the reliability of high-speed train driving, thereby realizing the real-time detection of the reliability of high-speed train driving. Moreover, the point cloud acquisition module includes at least four point cloud acquisition components evenly distributed on both sides of the driving track, effectively ensuring the accuracy of the detection results.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit safety, and particularly relates to a driving safety detection device and an evaluation method for high-speed trains passing through shield construction tunnels. Background Art

[0002] As a high-speed rail transit system, high-speed trains have extremely high requirements for the stability and safety of the line. In urban or complex geological environments, shield construction tunnels often need to pass through or approach high-speed rail lines (such as high-speed rail bridges, tunnels or subgrades) at close range. This situation may bring about formation disturbance, track deformation, settlement risks, and even affect the safety of high-speed train operation. Therefore, how to evaluate and control the impact of shield construction on the driving safety of high-speed trains has become an important research issue in the fields of civil engineering, rail transit, and intelligent monitoring.

[0003] Traditional technologies mainly use the three-dimensional finite element method to establish a shield construction - formation - high-speed rail track interaction model, and analyze the influence of different construction stages (such as excavation, segment assembly, soil loss) on track settlement and stress distribution. Or use the Peck formula, Loganathan method, Knothe method to estimate the settlement impact of shield construction on high-speed rail tracks.

[0004] Currently commonly used methods such as the Peck formula, Loganathan method, and Knothe formula are mainly based on statistical experience, applicable to homogeneous soil layers and simple construction conditions, but have low accuracy in complex geological environments (such as soft soil, water-rich sand layers) or special construction conditions (such as deep excavation, asymmetric loading). These methods usually assume that the formation deformation mode is fixed and cannot adapt to the dynamically changing construction environment, resulting in large prediction errors.

[0005] Finite element analysis is a commonly used refined analysis method at present, but the calculation process is complex, requiring high-quality geological data and construction parameters, and the calculation takes a long time. However, finite element simulation is very sensitive to soil parameters, shield construction parameters, and initial conditions. Slight deviations may lead to distorted calculation results. Due to the high timeliness requirements of shield construction, FEM calculations usually take several hours or even several days to obtain evaluation results, which cannot meet the real-time monitoring needs of high-speed train driving safety.

[0006] Currently, devices such as GNSS, total station, laser rangefinder, and fiber Bragg grating commonly used for high-speed rail track and shield construction monitoring have the following problems: monitoring data usually needs to be processed manually, the data update frequency is low, and it is impossible to achieve second-level response. Sensor installation is complex and the cost is high, making it difficult to promote on a large scale. Most monitoring data are discrete point data, making it difficult to construct a complete three-dimensional track settlement evolution model, resulting in insufficiently fine analysis of track deformation. Summary of the Invention

[0007] The object of the present invention is to provide a driving safety detection device and evaluation method for high-speed trains passing through shield tunneling construction tunnels, which can accurately and efficiently perform reliability detection. The specific technical solutions are as follows:

[0008] The present invention provides a driving safety detection device for high-speed trains passing through shield tunneling construction tunnels, which is used to detect the driving reliability of shield tunneling under the high-speed railway subgrade section. The device includes a point cloud acquisition module, a laser indication module and a processing module. The point cloud acquisition module includes at least four point cloud acquisition components evenly arranged on both sides of the driving track, and target plates are respectively arranged on both sides of the point cloud acquisition components. The point cloud acquisition components are used to scan and obtain the point cloud model of the high-speed railway subgrade area to be detected;

[0009] The laser indication module includes two laser indication components arranged diagonally. The two laser indication components are respectively arranged in the long-term non-deformation areas on both sides of the driving track, and the laser indication component includes at least four laser indicators. The laser indicators are arranged in one-to-one correspondence with the target plates. The laser indicators are used to measure the central coordinates of the corresponding target plates;

[0010] The processing module is electrically connected to the point cloud acquisition components and the laser indicators respectively. The processing module is used to process the point cloud model collected by the point cloud acquisition components and the central coordinates of the target plates measured by the laser indicators to obtain the driving reliability of the high-speed train.

[0011] Optionally, the point cloud acquisition component includes a support rod and a lidar. The support rod is vertically arranged on the ground, and the target plates are respectively arranged on both sides of the support rod; the lidar is arranged on the support rod. The point cloud model formed by accumulating each lidar covers at least 100 meters of the driving track length.

[0012] Optionally, the laser indicator includes a mounting base, a rotary servo, a pitching servo, a laser ranging element and an IMU element. The mounting base is arranged on the ground in the long-term non-deformation area; the rotary servo is horizontally arranged on the mounting base; the pitching servo is connected to the output shaft of the rotary servo, and the rotary servo can drive the pitching servo to rotate in the horizontal plane; the laser ranging element is connected to the output shaft of the pitching servo, and the pitching servo can drive the laser ranging element to rotate in the vertical plane. The laser ranging element is used to measure the distance between the laser emission point and the target plate, and a laser indicator light for illumination is arranged on the laser ranging element; the IMU element is arranged on the laser ranging element, and the IMU element is used to measure the azimuth angle and pitching angle of the laser ranging element.

[0013] Optionally, the laser indicator further includes a control element disposed on the mounting base. The control element includes a single-chip microcomputer chip, a data transmission unit, and a control unit. The single-chip microcomputer chip is electrically connected to the rotary servo and the pitching servo. The data transmission unit is electrically connected to the laser ranging element, the IMU element, and the processing module respectively, and is used to transmit the measurement data of the laser ranging element and the IMU element to the control unit. The control unit can calculate the center coordinates of the target board based on the measurement data of the laser ranging element and the IMU element, and transmit them to the processing module.

[0014] The present invention also provides a method for evaluating the driving safety of a high-speed train passing through a shield construction tunnel, which uses the driving safety detection device for a high-speed train passing through a shield construction tunnel as described above, and includes the following steps:

[0015] S1. When the shield tunnel has not affected the high-speed railway subgrade section, arrange the driving safety detection device for a high-speed train passing through a shield construction tunnel in the high-speed railway subgrade area to be detected;

[0016] S2. Establish a high-speed railway track recognition model, specifically: make a track label point cloud data set according to the N point cloud models obtained by the point cloud acquisition module scanning the shield tunneling section under the high-speed railway subgrade N times, and use the RandLA-Net model to establish a high-speed railway track recognition model, where: N is a set threshold;

[0017] S3. Use the high-speed railway track recognition model to recognize the planar point cloud data at the top of the track;

[0018] S4. Calculate the track deformation amount according to the difference between the planar point cloud data before and after the shield tunnel affects the high-speed railway subgrade section by using the K-D tree nearest neighbor search algorithm and the Euclidean distance algorithm;

[0019] S5. Establish a high-speed railway operation state prediction model by using a train operation aerodynamics simulation model, a train-track dynamics model, and a PSO-XGBoost prediction model, and input the current running speed of the high-speed train, the current driving conditions, and the track deformation amount in S4 into the high-speed railway operation state prediction model, and output the vertical acceleration, derailment coefficient, and wheel load reduction rate when the high-speed train is running in the high-speed railway subgrade area to be detected, where: the current driving conditions refer to single-train running or two-train meeting running;

[0020] S6. Input the vertical acceleration, derailment coefficient, and wheel load reduction rate in S5 into an existing reliability model to obtain the reliability of the high-speed train when running in the lower shield construction area. If the reliability is less than zero, there is an overturning risk for the high-speed train to pass through this area at the current speed and state; otherwise, repeat S3 to S6 every M minutes, where: M is a set threshold.

[0021] Optionally, S1 includes:

[0022] When the shield tunnel construction does not affect the high - speed railway subgrade section, at least four point cloud acquisition components are arranged at a distance of 10m to 15m from the center line of the subgrade. The four point cloud acquisition components are evenly arranged on both sides of the running track of the high - speed railway subgrade area to be detected. Among them: the scanning ranges of the two point cloud acquisition components on the same side of the running track overlap;

[0023] One laser indication component is respectively arranged in the areas on both sides of the running track at a distance of 100m to 150m from the center line of the subgrade and with no long - term surface deformation, and the laser indication components on both sides of the running track are arranged diagonally.

[0024] Optionally, S3 includes:

[0025] S3.1. Calculate the coordinates of each lidar according to the center coordinates of the target board measured by the laser indication module, and use each lidar to scan the surface of the high - speed railway subgrade at time t to obtain the point cloud coordinate data of the high - speed railway subgrade surface;

[0026] S3.2. According to the coordinates of each lidar, use the Euclidean transformation to convert the point cloud coordinate data of the high - speed railway subgrade surface scanned by each lidar into the same coordinate system to obtain the high - speed railway subgrade point cloud model at time t;

[0027] S3.3. Use the high - speed railway track recognition model to identify the track point cloud data in the high - speed railway subgrade point cloud model to obtain the track point cloud data model, and use the region growing algorithm to extract the planar point cloud data at the top of the track in the track point cloud data model.

[0028] Optionally, in S3.1, the calculation steps of the lidar coordinates are as follows:

[0029] ①. Adjust the high - precision laser indication device so that its laser point falls on the center point of the target board;

[0030] ②. Use the total station to measure the three - dimensional geodetic coordinates of the laser ranging element ; and use the laser ranging element to measure the distance between the laser emission point and the center of the target board , and the azimuth angle of the laser ranging element is measured by the assigned IMU module and the pitch angle ;

[0031] ③. Calculate the coordinates of the laser points on the two target boards in the point cloud acquisition component, that is, the center coordinates of the target board, according to the three - dimensional geodetic coordinates of the laser ranging element, the distance between the laser emission point and the center of the target board, the azimuth angle and the pitch angle. The specific calculation formula is as follows:

[0032] ;

[0033] Wherein: is the azimuth angle in the x-axis direction of the geodetic coordinate system in the area where the laser ranging element is located;

[0034] ④. Calculate the lidar coordinates according to the center coordinates of the two target plates. Specifically:

[0035] When the shield tunnel construction does not affect the high-speed railway subgrade section, calculate the corresponding coordinates of the lidar corresponding to the center coordinates of the two target plates respectively, and use the average value of the corresponding coordinates of the two lidars as the lidar coordinates;

[0036] When the shield tunnel construction affects the high-speed railway subgrade section, repeat ① to ③ to obtain the center coordinates of the two target plates in the point cloud acquisition component after the shield tunnel affects the high-speed railway subgrade section, and calculate the lidar coordinates according to the average value of the center coordinate deformation amounts of the target plates before and after the shield tunnel affects the high-speed railway subgrade section.

[0037] In the technical solution of the present invention, the point cloud acquisition module can adopt the point cloud model of the area of the high-speed railway subgrade to be detected, the laser indication module can measure the center coordinates of the target plate on the point cloud acquisition module, and the processing module is electrically connected to the point cloud acquisition module and the laser indication module respectively to receive the point cloud model data and the center coordinate data of the target plate and process them to obtain the reliability of high-speed railway operation, thus realizing the real-time detection of the reliability of high-speed railway operation. Moreover, the point cloud acquisition module includes at least four point cloud acquisition components evenly distributed on both sides of the driving track, effectively ensuring the accuracy of the detection result.

[0038] In addition to the purposes, features and advantages described above, the present invention has other purposes, features and advantages. The following will refer to the drawings and further elaborate on the present invention in detail. Brief Description of the Drawings

[0039] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0040] Figure 1 is the structural schematic diagram of the driving safety detection device when the high-speed railway passes through the shield construction tunnel in the embodiment of the present invention;

[0041] Figure 2 is the structural schematic diagram of the point cloud acquisition module in the embodiment of the present invention;

[0042] Figure 3 is the structural schematic diagram of the laser indicator in the embodiment of the present invention.

[0043] Explanation of the Reference Numerals in the Drawings:

[0044] 1 Traveling track, 1.1 Track surface, 2 Point cloud acquisition component, 2.1 Support rod, 2.2 LiDAR, 2.3 Target board, 3 Laser indication component, 3.1 Laser indicator, 3.1.1 Mounting base, 3.1.2 Rotating servo, 3.1.3 Pitching servo, 3.1.4 Laser ranging element, 3.1.5 IMU element, 3.1.6 Control element. Detailed implementation manners

[0045] To make the objectives, features, and advantages of the present invention more obvious and understandable, the following provides a detailed description of the specific implementation manners of the present invention with reference to the accompanying drawings. Several embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein.

[0046] In the present invention, unless otherwise clearly defined and limited, terms such as "mount", "connect", "couple", "fix", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0047] In the present invention, unless otherwise clearly defined and limited, the first feature being "on" or "under" the second feature may include the first and second features being in direct contact, or may include the first and second features not being in direct contact but being in contact through other features therebetween. Moreover, the first feature being "above", "over", and "on top of" the second feature includes the first feature being directly above and obliquely above the second feature, or merely indicating that the first feature has a higher horizontal height than the second feature. The first feature being "under", "beneath", and "underneath" the second feature includes the first feature being directly below and obliquely below the second feature, or merely indicating that the first feature has a lower horizontal height than the second feature. Terms such as "vertical", "horizontal", "left", "right", "up", "down", and similar expressions are only for the purpose of illustration and do not indicate or imply that the indicated device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation to the present invention.

[0048] The following provides a detailed description of the embodiments of the present invention with reference to the accompanying drawings. However, the present invention can be implemented in many different ways defined and covered by the claims.

[0049] Embodiment 1

[0050] Refer to Figures 1 to 3 , this embodiment provides a driving safety detection device for high-speed trains when passing through shield construction tunnels, which is used to detect the driving reliability of high-speed trains in the section where the shield passes under the high-speed railway subgrade. It includes a point cloud acquisition module, a laser indication module and a processing module. The point cloud acquisition module includes at least four point cloud acquisition components 2 evenly distributed on both sides of the driving track 1, and target plates 2.3 are respectively arranged on both sides of the point cloud acquisition component 2. The point cloud acquisition component 2 is used to scan and obtain the point cloud model of the high-speed railway subgrade area to be detected; the laser indication module includes two laser indication components 3 arranged diagonally, and the two laser indication components 3 are respectively arranged in the long-term non-deformation areas on both sides of the driving track 1, and the laser indication component 3 includes at least four laser indicators 3.1, and the laser indicators 3.1 are arranged in one-to-one correspondence with the target plates 2.3. The laser indicator 3.1 is used to measure the central coordinates of the corresponding target plate 2.3; the processing module is electrically connected to the point cloud acquisition component 2 and the laser indicator 3.1 respectively. The processing module is used to process the point cloud model collected by the point cloud acquisition component 2 and the central coordinates of the target plate 2.3 measured by the laser indicator 3.1 to obtain the driving reliability of the high-speed train. In actual operation, the point cloud acquisition module can adopt the point cloud model of the high-speed railway subgrade area to be detected, the laser indication module can measure the central coordinates of the target plate 2.3 on the point cloud acquisition module, and the processing module is electrically connected to the point cloud acquisition module and the laser indication module respectively to receive the point cloud model data and the central coordinate data of the target plate 2.3 and process them to obtain the driving reliability of the high-speed train, thus realizing the real-time detection of the driving reliability of the high-speed train. Moreover, the point cloud acquisition module includes at least four point cloud acquisition components 2 evenly distributed on both sides of the driving track 1, effectively ensuring the accuracy of the detection results.

[0051] The point cloud acquisition component 2 includes a support rod 2.1 and a lidar 2.2. The support rod 2.1 is vertically arranged on the ground, and target boards 2.3 are respectively arranged on both sides of the support rod 2.1; the lidar 2.2 is arranged on the support rod 2.1, and the point cloud model formed by accumulating each lidar 2.2 covers at least more than 100 meters of the length of the driving track 1. The lidar 2.2 can pitch at 360° circumferentially and plus or minus 90°, ensuring that at least 100m of the track area can be scanned, the scanning accuracy can reach the mm level, and the distance between adjacent points is 1mm; moreover, the point cloud model obtained by scanning the lidar 2.2 is a point with coordinates in the coordinate system with the position where the lidar 2.2 is located as the reference point; the lidar 2.2 is arranged at the top of the vertical rod, and two target boards 2.3 are arranged back to back in the middle. The target board 2.3 is a plastic white board with a grid, and the size is about 0.5m * 0.5m * 0.01m. The target board 2.3 is fixedly installed on the straight rod; the bottom of the straight rod is fixed on the ground around the track. When the ground subsides, the whole straight rod subsides. The lidars 2.2 in the four point cloud acquisition components 2 cooperate to scan to ensure the scanning accuracy and are beneficial to accurately detecting the deformation of the track surface 1.1. In this embodiment, the lidar 2.2 is configured with a control module for processing point cloud data.

[0052] The laser indicator 3.1 includes a mounting base 3.1.1, a rotary servo 3.1.2, a pitching servo 3.1.3, a laser ranging element 3.1.4 and an IMU element 3.1.5. The mounting base 3.1.1 is arranged on the ground in a long-term non-deformable area; the rotary servo 3.1.2 is horizontally arranged on the mounting base 3.1.1; the pitching servo 3.1.3 is connected to the output shaft of the rotary servo 3.1.2, and the rotary servo 3.1.2 can drive the pitching servo 3.1.3 to rotate in the horizontal plane; the laser ranging element 3.1.4 is connected to the output shaft of the pitching servo 3.1.3, and the pitching servo 3.1.3 can drive the laser ranging element 3.1.4 to rotate in the vertical plane. The laser ranging element 3.1.4 is used to measure the distance between the laser emission point and the target board 2.3, and a laser indicator for illumination is arranged on the laser ranging element 3.1.4; the IMU element 3.1.5 is arranged on the laser ranging element 3.1.4, and the IMU element 3.1.5 is used to measure the azimuth angle and pitching angle of the laser ranging element 3.1.4. Setting the laser indicator facilitates the staff to determine whether the area where the laser ranging is located is the area of the target board 2.3; by adjusting the azimuth angle and pitching angle of the laser ranging element 3.1.4 through the rotary servo 3.1.2 and the pitching servo 3.1.3, the laser landing point of the laser ranging element 3.1.4 coincides with the center point of the target board 2.3, so as to obtain the center coordinates of the target board 2.3. The laser indicator 3.1 can measure the center coordinates of the target board 2.3 in real time before and after the section where the shield tunnel affects the high-speed railway subgrade, so as to obtain the track deformation amount through the difference in the center coordinates of the target board 2.3.

[0053] The laser indicator 3.1 further includes a control element 3.1.6 which is arranged on the mounting base 3.1.1. The control element 3.1.6 includes a single-chip microcomputer chip, a data transmission unit and a control unit. The single-chip microcomputer chip is electrically connected to the rotary steering gear 3.1.2 and the pitching steering gear 3.1.3. The data transmission unit is respectively electrically connected to the laser ranging element 3.1.4, the IMU element 3.1.5 and the processing module, and is used for transmitting the measurement data of the laser ranging element 3.1.4 and the IMU element 3.1.5 to the control unit. The control unit can calculate the center coordinates of the target board 2.3 according to the measurement data of the laser ranging element 3.1.4 and the IMU element 3.1.5 and transmit them to the processing module. Through the control element 3.1.6, the automatic control of each component can be realized without manual participation, which is beneficial to saving labor costs and improving work efficiency.

[0054] Embodiment 2

[0055] This embodiment provides a method for evaluating the driving safety of a high-speed train passing through a shield construction tunnel, which adopts the above-mentioned driving safety detection device for a high-speed train passing through a shield construction tunnel, and includes the following steps:

[0056] S1. When the shield tunnel has not affected the high-speed railway subgrade section, arrange the driving safety detection device for a high-speed train passing through a shield construction tunnel in the high-speed railway subgrade area to be detected;

[0057] S1 includes:

[0058] When the shield tunnel construction has not affected the high-speed railway subgrade section, arrange at least four point cloud acquisition components 2 at a distance of 10 m to 15 m from the center line of the subgrade. The four point cloud acquisition components 2 are evenly arranged on both sides of the driving track 1 in the high-speed railway subgrade area to be detected, where: the scanning ranges of the two point cloud acquisition components 2 on the same side of the driving track 1 overlap; Figure 1 The dotted line in is the scanning range of the point cloud acquisition component 2.

[0059] Arrange a laser indicator assembly 3 in the areas on both sides of the driving track 1 at a distance of 100 m to 150 m from the center line of the subgrade and with no long-term ground deformation, and the laser indicator assemblies 3 on both sides of the driving track 1 are arranged diagonally.

[0060] S2. Establish a high-speed railway track recognition model, specifically: make a track label point cloud data set according to the N point cloud models obtained by the point cloud acquisition module scanning the shield tunneling under the high-speed railway subgrade section N times, and establish a high-speed railway track recognition model by using the RandLA-Net model, where: N is a set threshold; the recommended process of the high-speed railway track recognition model in this embodiment can refer to the article "Railway Bridge Point Cloud Component-Level Segmentation Method Based on Improved RandLA-Net".

[0061] S3. Identify the planar point cloud data at the top of the track using the high-speed rail track recognition model;

[0062] S3 includes:

[0063] S3.1. Calculate the coordinates of each lidar 2.2 based on the center coordinates of the target board 2.3 measured by the laser indication module, and use each lidar 2.2 to scan the surface of the high-speed railway subgrade at time t to obtain the point cloud coordinate data of the high-speed railway subgrade surface;

[0064] In S3.1, the calculation steps of the lidar 2.2 coordinates are as follows:

[0065] ①. Adjust the high-precision laser indication device so that its laser point falls on the center point of the target board 2.3;

[0066] ②. Use the total station to measure the three-dimensional geodetic coordinates of the laser ranging element 3.1.4 ; and use the laser ranging element 3.1.4 to measure the distance between the laser emission point and the center of the target board 2.3 , and the affiliated IMU module measures the azimuth angle and pitch angle ;

[0067] ③. Calculate the coordinates of the laser points on the two target boards 2.3 in the point cloud acquisition component 2, that is, the center coordinates of the target board 2.3, respectively, according to the three-dimensional geodetic coordinates of the laser ranging element 3.1.4, the distance between the laser emission point and the center of the target board 2.3, the azimuth angle, and the pitch angle , and the specific calculation formula is as follows:

[0068] ;

[0069] Where: is the azimuth angle of the x-axis direction of the geodetic coordinate system in the area where the laser ranging element 3.1.4 is located;

[0070] ④. Calculate the lidar 2.2 coordinates according to the center coordinates of the two target boards 2.3. Specifically:

[0071] When the shield tunnel construction does not affect the high-speed railway subgrade section, calculate the corresponding coordinates of the lidar 2.2 corresponding to the center coordinates of the two target boards 2.3 respectively , and use the average value of the corresponding coordinates of the two lidars 2.2 as the lidar 2.2 coordinates;

[0072] When the shield tunnel construction affects the high-speed railway subgrade section, repeat ① to ③ to obtain the central coordinates of the two target plates 2.3 in the point cloud acquisition component 2 after the shield tunnel affects the high-speed railway subgrade section, and calculate the coordinates of the lidar 2.2 based on the average value of the deformation of the central coordinates of the target plate 2.3 before and after the shield tunnel affects the high-speed railway subgrade section. Specifically:

[0073] When the high-speed railway subgrade section undergoes settlement deformation, the driving safety detection device during the high-speed railway passing through the shield construction tunnel will also be deformed as a whole. However, since each module is fixedly installed, the deformation of each part point of the driving safety detection device during the high-speed railway passing through the shield construction tunnel is synchronous and the same. Therefore, when the laser ranging element 3.1.4 is deformed, the coordinates of the new laser landing point on the target plate 2.3 can be calculated, that is, the central coordinates of the deformed target plate 2.3. The coordinate difference between the central coordinates of the target plate 2.3 before and after deformation is the deformation amount of the corresponding point cloud acquisition component 2. According to the deformation amounts calculated from the landing points of the two target plates 2.3 on both sides, the corresponding average deformation amount can be obtained. This average deformation amount can be considered as the movement amount of the coordinates of the lidar 2.2 device. Thus, the coordinates of the lidar 2.2 can be adjusted as follows:

[0074] ;

[0075] After the coordinates of the lidar 2.2 are adjusted by the deformation amount, rescan the high-speed railway subgrade section to ensure that the corresponding point cloud coordinates are also in the same coordinate system as the initial point cloud coordinates.

[0076] S3.2. Convert the point cloud coordinate data of the high-speed railway subgrade surface scanned by each lidar 2.2 to the same coordinate system using the Euclidean transformation according to the coordinates of each lidar 2.2 to obtain the high-speed railway point cloud model at time t;

[0077] S3.3. Use the high-speed railway track recognition model to recognize the track point cloud data in the high-speed railway point cloud model to obtain the track point cloud data model, and use the region growing algorithm to extract the planar point cloud data at the top of the track in the track point cloud data model.

[0078] S4. Calculate the track deformation amount according to the difference between the planar point cloud data before and after the shield tunnel affects the high-speed railway subgrade section using the K-D tree nearest neighbor search algorithm and the Euclidean distance algorithm;

[0079] S5. Establish a high-speed rail operation state prediction model using the train operation aerodynamics simulation model, the train-track dynamics model, and the PSO-XGBoost prediction model. Input the current running speed of the high-speed rail, the current driving conditions, and the track deformation amount in S4 into the high-speed rail operation state prediction model, and output the vertical acceleration, derailment coefficient, and wheel load reduction rate when the high-speed rail is running in the subgrade area to be detected. Among them: the current driving conditions refer to single-train driving or two-train meeting driving;

[0080] The above model has been established and implemented in the relevant paper "Safety of Existing High-Speed Rail Meeting during Shield Tunneling Considering Random Fields", and no additional description is required.

[0081] The specific process of establishing the high-speed rail operation state prediction model is as follows: First, use the existing train operation aerodynamics simulation model and train-track dynamics model to simulate the operation state of the train according to different track deformation amounts, driving conditions, and driving speeds, and obtain at least K groups of simulation data; then, the simulation data includes the corresponding train vertical acceleration, derailment coefficient, and wheel load reduction rate; finally, use the PSO-XGBoost prediction model to learn the extended simulation data to establish a high-speed rail operation state prediction model; in this embodiment, use the Kriging surrogate model to expand the simulation data, and the expanded data volume is at least 1000 groups of data, and then use the PSO-XGBoost prediction model to learn the data to establish prediction models for the high-speed rail vertical acceleration, derailment coefficient, and wheel load reduction rate respectively. Among them: K is 300.

[0082] S6. Input the vertical acceleration, derailment coefficient, and wheel load reduction rate in S5 into the existing reliability model to obtain the reliability of the high-speed rail when running in the lower shield construction area. If the reliability is less than zero, the high-speed rail has an overturning risk when passing through this area at the current speed and state; otherwise, repeat S3 to S6 every M minutes, where: M is a set threshold. In this embodiment, M = 30 min, and the establishment of the reliability model can refer to "Random Reliability Assessment Method for High-Speed Rail Operation Safety during Shield Tunneling".

[0083] The train operation safety evaluation method during the construction of shield tunnels crossed by high-speed railways in this embodiment combines laser point cloud acquisition, track surface 1.1 recognition, settlement calculation, PSO-XGBoost prediction model and reliability calculation model, and has the following remarkable technical advantages in the rapid evaluation of train operation safety when high-speed railways cross shield tunnels in close proximity: The point cloud acquisition module and the laser indication module can provide high-resolution track settlement data, accurately identify the deformation of the track surface 1.1, and based on the PSO-XGBoost model, can quickly predict key indicators such as the vertical acceleration and derailment coefficient of high-speed trains; Through the reliability calculation model, various factors are comprehensively analyzed to provide accurate evaluation of train operation safety reliability. Compared with the traditional finite element analysis, this method can achieve low-cost and high-efficiency safety evaluation, can be applied in different geological and construction environments, supports long-term dynamic monitoring and evaluation, and at the same time has the capabilities of automatic evaluation and real-time warning, providing data-driven decision-making support for the operation safety of high-speed railways. Generally speaking, by integrating laser point cloud technology, machine learning and reliability calculation models, this method greatly improves the accuracy, real-time performance and intelligent level of high-speed train operation safety evaluation, providing a more scientific and efficient solution for the train operation safety when high-speed railways cross shield tunnels.

[0084] This embodiment also includes a readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the train operation safety evaluation method during the construction of shield tunnels crossed by high-speed railways as described above is implemented.

[0085] It should be noted that the device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0086] This embodiment also includes an electronic device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, the train operation safety evaluation method during the construction of shield tunnels crossed by high-speed railways as described above.

[0087] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0088] The electronic device may be a computing device such as a mobile phone, a desktop computer, a notebook, a handheld computer, and a cloud server. The electronic device may include, but is not limited to, a processor and a memory. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0089] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and circuits.

[0090] The memory may be used to store the computer program and / or modules. The processor realizes the computer program by running or executing the computer program and / or modules stored in the memory, and by invoking the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0091] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0092] The foregoing are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for evaluating the driving safety when a high-speed train passes through a shield construction tunnel, which uses a driving safety detection device for a high-speed train passing through a shield construction tunnel, is characterized in that, It includes the following steps: S1. When the shield tunnel has not affected the high-speed railway subgrade section, arrange the driving safety evaluation method for the shield construction tunnel under the high-speed railway in the high-speed railway subgrade area to be detected; S2. Establish a high-speed railway track recognition model. Specifically: make a track label point cloud data set according to the N point cloud models obtained by the point cloud acquisition module scanning the high-speed railway subgrade section under the shield for N times, and use the RandLA-Net model to establish a high-speed railway track recognition model, where: N is a set threshold; S3. Use the high-speed railway track recognition model to identify the planar point cloud data at the top of the track; The said S3 includes: S3.

1. Calculate the coordinates of each lidar (2.2) according to the central coordinates of the target board (2.3) measured by the laser indication module, and use each lidar (2.2) to scan the surface of the high-speed railway subgrade at time t to obtain the point cloud coordinate data of the high-speed railway subgrade surface; In the said S3.1, the calculation steps of the lidar (2.2) coordinates are as follows: ①. Adjust the high-precision laser indication device so that its laser point falls on the center point of the target board (2.3); ②. Determine the three-dimensional geodetic coordinates of the laser ranging element (3.1.4) using a total station ; and measure the distance between the laser emission point and the center of the target board (2.3) using the laser ranging element (3.1.4) , and the assigned IMU module measures the azimuth angle of the laser ranging element (3.1.4) and pitch angle ; ③. Calculate the coordinates of the laser points on the two target plates (2.3) in the point cloud acquisition component (2) based on the three-dimensional geodetic coordinates of the laser ranging element (3.1.4), the distance, azimuth angle, and elevation angle between the laser emission point and the center of the target plate (2.3), that is, the center coordinates of the target plate (2.3). , and the specific calculation formula is as follows: ； Wherein: is the azimuth angle in the x-axis direction of the geodetic coordinate system in the area where the laser ranging element (3.1.4) is located; ④. Calculate the lidar (2.2) coordinates according to the central coordinates of the two target boards (2.3). Specifically: When the shield tunnel construction has not affected the high-speed railway subgrade section, calculate the corresponding coordinates of the lidar (2.2) corresponding to the central coordinates of the two target boards (2.3) respectively, and use the mean value of the corresponding coordinates of the two lidars (2.2) as the lidar (2.2) coordinates; When the shield tunnel construction affects the high-speed railway subgrade section, repeat ① to ③ to obtain the central coordinates of the two target boards (2.3) in the point cloud acquisition component (2) after the shield tunnel affects the high-speed railway subgrade section, and calculate the lidar (2.2) coordinates according to the mean value of the central coordinate deformation amounts of the target boards (2.3) before and after the shield tunnel affects the high-speed railway subgrade section; Calculate the coordinates of the new laser landing point on the target board (2.3), that is, the center coordinates of the deformed target board (2.3). The coordinate difference between the center coordinates of the target board (2.3) before and after deformation is the deformation amount of the corresponding point cloud acquisition component (2.). According to the deformation amounts calculated from the landing points of the target boards (2.3) on both sides, the corresponding average deformation amount can be obtained. , This average deformation amount can be regarded as the movement amount of the coordinates of the lidar (2.2) device. Thus, the coordinates of the lidar (2.2) can be adjusted as follows: ； S3.

2. According to the coordinates of each lidar (2.2), use the Euclidean transformation to convert the point cloud coordinate data of the high-speed railway subgrade surface scanned by each lidar (2.2) into the same coordinate system to obtain the high-speed railway point cloud model at time t; S3.

3. Use the high-speed railway track recognition model to identify the track point cloud data in the high-speed railway point cloud model to obtain a track point cloud data model, and use the region growing algorithm to extract the planar point cloud data at the top of the track in the track point cloud data model; S4. Calculate the track deformation amount according to the difference between the planar point cloud data before and after the shield tunnel affects the high-speed railway subgrade section by using the K-D tree nearest neighbor search algorithm and the Euclidean distance algorithm; S5. Use the train running aerodynamics simulation model, the train-track dynamics model and the PSO-XGBoost prediction model to establish a high-speed railway operation state prediction model, and input the current running speed of the high-speed railway, the current driving conditions and the track deformation amount in S4 into the high-speed railway operation state prediction model, and output the vertical acceleration, derailment coefficient and wheel load reduction rate when the high-speed railway is running in the high-speed railway subgrade area to be detected, where: the current driving conditions refer to single train running or two-train meeting running; S6. Input the vertical acceleration, derailment coefficient, and wheel load reduction rate in S5 into the existing reliability model to obtain the reliability when the high-speed rail travels in the lower shield construction area. If the reliability is less than zero, there is an overturning risk for the high-speed rail to pass through this area at the current speed and state; otherwise, repeat S3 to S6 every M minutes, where M is a set threshold.

2. The driving safety evaluation method during shield tunneling construction for high-speed rail tunneling according to claim 1, wherein, The driving safety detection device for high-speed rail passing through a shield construction tunnel includes a point cloud acquisition module, a laser indication module, and a processing module. The point cloud acquisition module includes at least four point cloud acquisition components (2) evenly distributed on both sides of the driving track (1), and target plates (2.3) are respectively arranged on both sides of the point cloud acquisition component (2). The point cloud acquisition component (2) is used to scan and obtain the point cloud model of the high-speed railway subgrade area to be detected. The laser indication module includes two laser indication components (3) arranged diagonally. The two laser indication components (3) are respectively arranged in the long-term non-deformable areas on both sides of the driving track (1), and the laser indication component (3) includes at least four laser indicators (3.1). The laser indicators (3.1) are arranged in one-to-one correspondence with the target plates (2.3), and the laser indicators (3.1) are used to measure the central coordinates of the corresponding target plates (2.3). The processing module is electrically connected to the point cloud acquisition component (2) and the laser indicator (3.1) respectively. The processing module is used to process the point cloud model collected by the point cloud acquisition component (2) and the central coordinates of the target plate (2.3) measured by the laser indicator (3.1) to obtain the driving reliability of the high-speed rail.

3. The method for evaluating the driving safety during the shield tunneling construction when the high-speed rail passes through, as claimed in claim 2, is characterized in that The point cloud acquisition component (2) includes a support rod (2.1) and a lidar (2.2). The support rod (2.1) is vertically arranged on the ground, and the target plates (2.3) are respectively arranged on both sides of the support rod (2.1); the lidar (2.2) is arranged on the support rod (2.1), and the point cloud model formed by the accumulation of each lidar (2.2) covers at least 100 meters of the length of the driving track (1).

4. The method for evaluating the driving safety during the shield tunneling construction for high-speed rail passing through, as claimed in claim 3, is characterized in that The laser indicator (3.1) includes a mounting base (3.1.1), a rotary servo (3.1.2), a pitching servo (3.1.3), a laser ranging element (3.1.4), and an IMU element (3.1.5). The mounting base (3.1.1) is arranged on the ground in the long-term non-deformable area; the rotary servo (3.1.2) is horizontally arranged on the mounting base (3.1.1); the pitching servo (3.1.3) is connected to the output shaft of the rotary servo (3.1.2), and the rotary servo (3.1.2) can drive the pitching servo (3.1.3) to rotate in the horizontal plane; the laser ranging element (3.1.4) is connected to the output shaft of the pitching servo ( 3.1.3), and the pitching servo ( 3.1.3) It is capable of driving the laser ranging element (3.1.4) to rotate in the vertical plane. The laser ranging element (3.1.4) is used to measure the distance between the laser emission point and the target board (2.3), and a laser indicator for illumination is provided on the laser ranging element (3.1.4); the IMU element (3.1.5) is arranged on the laser ranging element (3.1.4), and the IMU element (3.1.5) is used to measure the azimuth angle and pitch angle of the laser ranging element (3.1.4).

5. The driving safety evaluation method during shield tunneling construction for high-speed rail tunneling according to claim 4, characterized in that The laser indicator (3.1) further includes a control element (3.1.6). The control element (3.1.6) is arranged on the mounting base (3.1.1). The control element (3.1.6) includes a single-chip microcomputer chip, a data transmission unit and a control unit. The single-chip microcomputer chip is electrically connected to the rotary servo (3.1.2) and the pitch servo ( 3.1.3). The data transmission unit is electrically connected to the laser ranging element (3.1.4), the IMU element (3.1.5) and the processing module respectively, and is used to transmit the measurement data of the laser ranging element (3.1.4) and the IMU element (3.1.5) to the control unit; the control unit can calculate the center coordinates of the target board (2.3) according to the measurement data of the laser ranging element (3.1.4) and the IMU element (3.1.5), and transmit them to the processing module.

6. The method for evaluating the driving safety during the shield tunneling construction for high-speed rail passing through, according to claim 5, is characterized in that The S1 includes: When the shield tunnel construction does not affect the high-speed railway subgrade section, at least four point cloud acquisition components (2) are arranged at a distance of 10 m to 15 m from the center line of the subgrade. The four point cloud acquisition components (2) are evenly arranged on both sides of the running track (1) of the high-speed railway subgrade area to be detected. Among them: the scanning ranges of the two point cloud acquisition components (2) on the same side of the running track (1) overlap; One laser indication component (3) is respectively arranged in the areas on both sides of the running track (1) at a distance of 100 m to 150 m from the center line of the subgrade and with no long-term ground deformation, and the laser indication components (3) on both sides of the running track (1) are arranged diagonally.

Images