Track information digital twinning method and system based on Beidou track inspection tester

Abstract

The invention discloses an orbit information digital twinning method based on a Beidou orbit inspection tester. The method comprises the following steps: constructing a corresponding orbit three-dimensional model according to line design information; track and surrounding data are detected and collected through movement of a track detector carrying various sensors; carrying out high-precision mileage positioning on the track and peripheral data; matching the track subjected to high-precision mileage positioning and peripheral data with the track three-dimensional model; and intelligently identifying the abnormal condition of the track based on the difference between the dense point cloud data corresponding to the matched track and peripheral data and the track three-dimensional model, and carrying out multi-dimensional expression on the abnormal condition of the track. The invention further discloses a corresponding system, electronic equipment and a computer readable storage medium, the data expression form in an existing scheme is improved, the association degree of the data and the track real scene information is improved, and the detection data and the track model are associated, so that the problem of insufficient historical traceability in the current detection process is solved, and the detection efficiency is improved. And the capability of integrating various detection results is weak.

Description

Technical Field

[0001] The present invention relates to the technical field of railway operation and maintenance management, and in particular to a track information digital twin method and system based on a Beidou track inspection instrument. Background Art

[0002] Railways are the main arteries of my country's transportation development and economic construction. Under the general environment of digital China, digital economy, intelligence and informatization, the development of railway informatization has naturally become one of the main trends in the development of modern railways. At present, railway informatization has made great progress in passenger, freight and dispatching, but there is still a lot of room for improvement in the informatization of engineering operation and maintenance technology. Track smoothness is an important basic condition to ensure the safe and stable operation of railways. With the increase of my country's railway operating mileage and the increase of operating speed, the pressure on railway track operation and maintenance has increased. There are seven key points to focus on in track operation and maintenance: track direction, track gauge, height, superelevation, level, rail bottom slope and triangular pit. In addition, during the operation of the train, attention should be paid to the intrusion of foreign objects in the building limit, damage to the track plate, damage to the fasteners and other problems. These data need to be obtained before maintenance as a reference for maintenance.

[0003] First, the determination of maintenance points requires accurate positioning. Railways use mileage to indicate location, so accurate mileage data is needed, which requires accurate mileage data to be obtained during the inspection process. However, during the inspection process, some mileage locations have a certain degree of damage, but because the degree is low and does not meet the repair standards, this part of the information is not fully utilized, but further remedial measures are not taken until the problem occurs. The lack of recording and analysis of historical data is not conducive to the full life cycle management of railway operation and maintenance.

[0004] Second, there are two common methods for track defect detection. One is dynamic detection, which uses a high-speed track inspection vehicle to dynamically detect and collect track dynamic data, analyze the uneven characteristics of the track, and select the measurement section for static measurement. However, this method is costly, the detection cycle is relatively fixed, and the flexibility is insufficient; the second is static detection, of which static detection can be divided into three types. The first is to rely on manual measurement with the help of tools such as hanging wires and track rulers; the second is to use a track inspection instrument with a total station for "stop-and-go" measurement; the third is to use a track inspection instrument with GNSS and inertial inspection equipment to achieve mobile measurement. Among them, the manual measurement method has a low detection speed and low measurement accuracy. The data obtained needs to be recorded manually, and most of them are paper data; the track inspection instrument with a total station can obtain comprehensive measurement data of the track, which is more accurate than the detection method of manual tools, but its detection speed in single-point situations needs to be improved. The use of a track inspection instrument with GNSS mobile measurement can increase the speed of track measurement while ensuring accuracy, and is relatively more suitable for inspection by maintenance personnel. However, the above detection schemes focus on the presentation of single-test results, and lack effective management of multi-period results. During the detection process, the staff focuses on the over-limit data that needs to be handled, but does not pay attention to the process of its generation and development, nor does it pay attention to the minor anomalies that do not affect operations.

[0005] Third, the existing technology lacks full life cycle management of multiple test data, and generally uses one-dimensional and two-dimensional methods such as tables and wave line diagrams as the way to present the results. The correlation with the track is not strong enough, and it is difficult to intuitively reflect the location of track defects; and the historical traceability of the test data is insufficient. The test data is generally organized and managed according to the file management method through tables, images, etc.; and the ability to integrate the results of multiple test data is lacking, and the data at the time of data collection is generally analyzed separately.

[0006] With the development of refined operations, it is necessary to see the big picture from the details, paying attention not only to the locations that have reached the maintenance standards, but also to the areas where signs of disease are showing. Therefore, it is necessary to build new information methods and systems for engineering operation and maintenance technology. Summary of the invention

[0007] The purpose of the present invention is to construct a digital twin method and system for track information based on the Beidou track inspection instrument in response to the defects of the prior art. The method and system are suitable for the digital twin of track inspection instrument detection data in the process of railway engineering operation and maintenance. The digital twin includes modules such as track inspection instrument data acquisition, track inspection instrument data analysis, and track inspection instrument data storage. By improving the data expression form in the existing scheme, the degree of correlation between the data and the real-life track information is improved, and the detection data is associated with the track model, what you see is what you get is achieved, which can quickly locate and perceive the image, while still retaining the characteristics of the original data expression and analysis, thereby solving the problems of insufficient historical traceability and weak ability to integrate multiple detection results in the current detection process.

[0008] The first aspect of the present invention is to provide a track information digital twin method based on Beidou track inspection instrument, comprising:

[0009] S1, constructing a corresponding track three-dimensional model according to line design information;

[0010] S2, collects track and surrounding data through mobile inspection of track inspection devices equipped with various sensors;

[0011] S3, performing high-precision mileage positioning of the track and surrounding data through GNSS+inertial navigation algorithm;

[0012] S4, matching the track and surrounding data obtained through high-precision mileage positioning with the track three-dimensional model;

[0013] S5, intelligently identifying track anomalies based on the differences between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model, and expressing the track anomalies in multiple dimensions.

[0014] Preferably, the S1 comprises:

[0015] S11, a designer provides the railway line design information, wherein the railway line design information includes track cross-section, fastener type and line construction information;

[0016] S12, completing the construction of the track three-dimensional model according to the track cross-section, fastener type and line construction information, the track three-dimensional model is a discrete three-dimensional model composed of different components; the track three-dimensional model adopts OBJ format, GLTF format or 3D Tiles format, and the track three-dimensional model is not a complete three-dimensional model; the different components are made according to design drawings or corresponding products, and then assembled together according to position matching relationships, as the initial track three-dimensional model in the method.

[0017] Preferably, a GNSS receiver and an inertial navigation measurement device are fixedly installed on the track inspection instrument; the various sensors carried include a three-dimensional laser scanner and a structured light module; wherein the three-dimensional laser scanner is used to obtain information about the rails and / or obtain environmental information around the track.

[0018] Preferably, S2 includes:

[0019] S21, after placing the track inspection instrument at the starting point of the area to be tested, turn on the GNSS receiver, receive satellite signals for a certain period of time, determine the current position information and record the current mileage information;

[0020] S22, moving the track inspection instrument at a constant speed according to the set speed, and continuing to use the GNSS receiver to perform a satellite signal reception test for a certain period of time at the end point of the measurement to determine the location information and mileage location information of the end point;

[0021] S23, during the operation of the track inspection instrument, the scene information around the track is obtained by the three-dimensional laser scanner, and the dense point cloud information of the left and right rails of the track is obtained by the structured light module, wherein the dense point cloud information includes fasteners and rail surfaces.

[0022] Preferably, S3 includes:

[0023] S31, unifying the coordinate system of the dense point cloud information;

[0024] S32, completing the position alignment of the overall data based on the starting point position and mileage information, and the alignment prisms installed on both sides of the track;

[0025] S33, for the rail point cloud data collected by the line structure light module, the corresponding noise and outliers are filtered out by a composite method of straight-through filtering and cloth filtering; for the building limit, the limit requirements at different heights are used to determine whether there are foreign objects invading the minimum building limit at different mileage positions.

[0026] Preferably, S4 includes:

[0027] S41, matching the high-precision mileage positioning information based on the track and surrounding data with the mileage of the track three-dimensional model;

[0028] S42, using a nearest neighbor algorithm to appropriately perform thinning processing on the point cloud data of the surrounding environment according to the loading frame rate;

[0029] S43, matching the point cloud at the tunnel and the like with the standard model according to the least squares method.

[0030] Preferably, S5 includes:

[0031] S51, intelligently identifying track abnormalities based on the difference between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model;

[0032] S52, classifying the abnormal situation and assigning color values ​​through a color assignment component according to the classification;

[0033] S53, storing the detection data of track unevenness in the track inspection instrument; the detection data of track unevenness includes track gauge, track direction, height, level and triangular pit data, matching the detection data of track unevenness with the track mileage position, selecting corresponding indicators, and generating corresponding three-dimensional lines just above the centerline Z axis of the three-dimensional model of the track;

[0034] S54, click on the mileage position in the three-dimensional model of the track to view and download a common two-dimensional line graph, and match the relevant point cloud screenshots of the abnormal places on the track with the coloring components.

[0035] The second aspect of the present invention is to provide a track information digital twin system based on the Beidou track inspection instrument, which is used to implement the method of the first aspect, including:

[0036] A model building module (101), used to build a corresponding three-dimensional track model according to line design information;

[0037] A data collection module (102) is used to collect track and surrounding data through mobile detection of a track inspection device equipped with multiple sensors;

[0038] A mileage positioning module (103), used for performing high-precision mileage positioning of the track and surrounding data by using a GNSS+inertial navigation algorithm;

[0039] A data matching module (104) is used to match the track and surrounding data after high-precision mileage positioning with the track three-dimensional model;

[0040] The anomaly recognition module (105) is used to intelligently identify track anomalies based on the difference between the dense point cloud data corresponding to the track and surrounding data after matching and the track three-dimensional model, and to express the track anomalies in multiple dimensions.

[0041] A third aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores a plurality of instructions, and the processor is configured to read the instructions and execute the method described in the first aspect.

[0042] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a plurality of instructions, and the plurality of instructions can be read by a processor to execute the method described in the first aspect.

[0043] Beneficial effects of the method and system of the present invention:

[0044] (1) A digital twin method for track information is proposed, which associates the track model with the detection results and marks the problem points through graded colors. Compared with the traditional method, it focuses on long-term operation and maintenance management. In particular, through the layered coloring method, the problem area is marked in red and the abnormal area is marked in yellow, which can achieve a more intuitive display and historical traceability of the detection results.

[0045] (2) The present invention partially solves the problem of weak ability to integrate multiple test results in the current test process by integrating multiple test results into the rail model. The method of color grading and multi-period historical data recording solves the problem of insufficient historical traceability in the current test and can help railway maintenance personnel locate key sections. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A flow chart of a track information digital twin method based on a Beidou track inspection instrument provided according to the prior art;

[0048] Figure 2 This is an architecture diagram of a track information digital twin system based on a Beidou track inspection instrument according to an embodiment of the present invention;

[0049] Figure 3 A structural diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0052] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" 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 a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0053] Embodiment 1

[0054] like Figure 1 As shown, this embodiment provides a track information digital twin method based on Beidou track inspection instrument, including:

[0055] S1, constructing a corresponding track three-dimensional model according to line design information;

[0056] In this embodiment, this step is the preliminary work of all the steps and is the first step in the method. Its function is to provide a model basis for this method.

[0057] As a preferred embodiment, the S1 includes:

[0058] S11, a designer provides the railway line design information, wherein the railway line design information includes track cross-section, fastener type and line construction information;

[0059] S12, completing the construction of a three-dimensional track model according to the track cross section, fastener type and line construction information, wherein the three-dimensional track model is a discrete three-dimensional model formed by combining different component units, so as to correspond to the actual track and facilitate updating of part of the model when the subsequent track model changes;

[0060] As a preferred implementation, the track three-dimensional model adopts OBJ format, GLTF format or 3D Tiles format, and the track three-dimensional model is not a complete three-dimensional model; the different component units are manufactured according to design drawings or corresponding products, and then assembled together according to position matching relationships, as the initial track three-dimensional model in the method.

[0061] S2, collects track and surrounding data through mobile inspection of track inspection devices equipped with various sensors;

[0062] As a preferred embodiment, a GNSS receiver and an inertial navigation measurement device are fixedly installed on the track inspection instrument; the multiple sensors carried include a three-dimensional laser scanner and a structured light module; wherein the three-dimensional laser scanner is used to obtain information about the rails and / or obtain environmental information around the tracks (in the method of this embodiment, the environmental information around the tracks mainly corresponds to obtaining building clearance information).

[0063] As a preferred embodiment, S2 includes:

[0064] S21, after placing the track inspection instrument at the starting point of the area to be tested, turn on the GNSS receiver, receive satellite signals for a certain period of time (five minutes in this embodiment), determine the current position information and record the current mileage information;

[0065] S22, performing uniform moving measurement according to the set speed of the track inspection instrument (3 km / h in this embodiment), and continuing to use the GNSS receiver to perform a satellite signal reception test for a certain period of time (five minutes in this embodiment) at the end point of the measurement to determine the location information and mileage location information of the end point;

[0066] S23, during the operation of the track inspection instrument, the scene information around the track is obtained by the three-dimensional laser scanner, and the dense point cloud information of the left and right rails of the track is obtained by the structured light module, wherein the dense point cloud information includes fasteners and rail surfaces.

[0067] S3, performing high-precision mileage positioning of the track and surrounding data through GNSS+inertial navigation algorithm;

[0068] In this embodiment, after the track and surrounding data are collected, technicians are required to post-process the collected data to complete high-precision positioning of the data.

[0069] As a preferred implementation, S3 includes:

[0070] S31, unifying the coordinate system of the dense point cloud information;

[0071] S32, completing the position alignment of the overall data based on the starting point position and mileage information, and the alignment prisms installed on both sides of the track;

[0072] S33, for the rail point cloud data collected by the line structure light module, the corresponding noise and outliers are filtered out by a composite method of straight-through filtering and cloth filtering; for the building limit (for example, the tunnel in this embodiment), the limit requirements at different heights are used to determine whether there are foreign objects invading the minimum building limit at different mileage positions.

[0073] S4, matching the track and surrounding data obtained through high-precision mileage positioning with the track three-dimensional model;

[0074] As a preferred implementation, the S4 includes:

[0075] S41, matching the high-precision mileage positioning information based on the track and surrounding data with the mileage of the track three-dimensional model;

[0076] S42, using a nearest neighbor algorithm to appropriately perform thinning processing on the point cloud data of the surrounding environment according to the loading frame rate;

[0077] S43, matching the point cloud at the tunnel and the like with the standard model according to the least squares method.

[0078] In this embodiment, the least square method is often used to solve the curve fitting problem. It finds the best function matching of the data by minimizing the sum of squares of errors.

[0079] S5, intelligently identifying track abnormalities (for example, the abnormalities in the embodiment of the present invention include track wear and missing fasteners, etc.) based on the difference between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model, and expressing the track abnormalities in multiple dimensions.

[0080] As a preferred implementation, S5 includes:

[0081] S51, intelligently identifying track abnormalities based on the difference between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model;

[0082] S52, classifying the abnormal situation and assigning color values ​​through a color assignment component according to the classification;

[0083] In this embodiment, component units that need maintenance are set to red, those that are abnormal but not serious enough to affect driving safety are marked in yellow, and normal areas are not colored.

[0084] S53, storing the detection data of track unevenness in the track inspection instrument; the detection data of track unevenness includes track gauge, track direction, height, level and triangular pit data, matching the detection data of track unevenness with the track mileage position, selecting corresponding indicators, and generating corresponding three-dimensional lines just above the centerline Z axis of the three-dimensional model of the track;

[0085] S54, click on the mileage position in the three-dimensional model of the track to view and download a common two-dimensional line graph, and match the relevant point cloud screenshots of the abnormal places on the track with the coloring components.

[0086] Embodiment 2

[0087] like Figure 2 As shown, this embodiment provides a track information digital twin system based on Beidou track inspection instrument, including:

[0088] A model building module 101 is used to build a corresponding three-dimensional track model according to the line design information;

[0089] The data acquisition module 102 is used to collect track and surrounding data through mobile detection of a track inspection device equipped with various sensors;

[0090] The mileage positioning module 103 is used to perform high-precision mileage positioning of the track and surrounding data through GNSS+inertial navigation algorithm;

[0091] A data matching module 104 is used to match the track and surrounding data after high-precision mileage positioning with the track three-dimensional model;

[0092] The anomaly identification module 105 is used to intelligently identify track anomalies based on the difference between the dense point cloud data corresponding to the track and surrounding data after matching and the track three-dimensional model, and express the track anomalies in multiple dimensions.

[0093] The present invention also provides a memory storing a plurality of instructions, wherein the instructions are used to implement the method as in the first embodiment.

[0094] like Figure 3 As shown, the present invention also provides an electronic device, including a processor 301 and a memory 302 connected to the processor 301, the memory 302 stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the method as in the first embodiment.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A track information digital twin method based on Beidou track inspection instrument, characterized in that: include: S1, constructing a corresponding track three-dimensional model according to line design information; S2, collects track and surrounding data through mobile inspection of track inspection devices equipped with various sensors; S3, performing high-precision mileage positioning of the track and surrounding data through GNSS+inertial navigation algorithm; S4, matching the track and surrounding data obtained through high-precision mileage positioning with the track three-dimensional model; S5, intelligently identifying track anomalies based on the differences between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model, and expressing the track anomalies in multiple dimensions.

2. According to claim 1, a track information digital twin method based on Beidou track inspection instrument is characterized in that: The S1 includes: S11, a designer provides the railway line design information, wherein the railway line design information includes track cross-section, fastener type and line construction information; S12, completing the construction of a three-dimensional track model according to the track cross-section, fastener type and line construction information, the three-dimensional track model is a discrete three-dimensional model composed of different components; the three-dimensional track model adopts OBJ format, GLTF format or 3D Tiles format, and the three-dimensional track model is not a complete three-dimensional model; the different components are made according to design drawings or corresponding products, and then assembled together according to position matching relationships, as the initial three-dimensional track model in the method.

3. According to claim 2, a track information digital twin method based on Beidou track inspection instrument is characterized in that: The track inspection instrument is fixedly installed with a GNSS receiver and an inertial navigation measurement device; the various sensors carried include a three-dimensional laser scanner and a structured light module; wherein the three-dimensional laser scanner is used to obtain information about the rails and / or environmental information around the track.

4. According to claim 3, a track information digital twin method based on Beidou track inspection instrument is characterized in that: The S2 includes: S21, after placing the track inspection instrument at the starting point of the area to be tested, turn on the GNSS receiver, receive satellite signals for a certain period of time, determine the current position information and record the current mileage information; S22, moving the track inspection instrument at a constant speed according to the set speed, and continuing to use the GNSS receiver to perform a satellite signal reception test for a certain period of time at the end point of the measurement to determine the location information and mileage location information of the end point; S23, during the operation of the track inspection instrument, the scene information around the track is obtained by the three-dimensional laser scanner, and the dense point cloud information of the left and right rails of the track is obtained by the structured light module, wherein the dense point cloud information includes fasteners and rail surfaces.

5. A track information digital twin method based on Beidou track inspection instrument according to claim 4, characterized in that: The S3 includes: S31, unifying the coordinate system of the dense point cloud information; S32, completing the position alignment of the overall data based on the starting point position and mileage information, and the alignment prisms installed on both sides of the track; S33, for the rail point cloud data collected by the line structure light module, the corresponding noise and outliers are filtered out by a composite method of straight-through filtering and cloth filtering; for the building limit, the limit requirements at different heights are used to determine whether there are foreign objects invading the minimum building limit at different mileage positions.

6. A track information digital twin method based on Beidou track inspection instrument according to claim 5, characterized in that: The S4 includes: S41, matching the high-precision mileage positioning information based on the track and surrounding data with the mileage of the track three-dimensional model; S42, using a nearest neighbor algorithm to appropriately perform thinning processing on the point cloud data of the surrounding environment according to the loading frame rate; S43, matching the point cloud at the tunnel and the like with the standard model according to the least squares method.

7. A track information digital twin method based on Beidou track inspection instrument according to claim 6, characterized in that: The S5 includes: S51, intelligently identifying track abnormalities based on the difference between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model; S52, classifying the abnormal situation and assigning color values ​​through a color assignment component according to the classification; S53, storing the detection data of track unevenness in the track inspection instrument; the detection data of track unevenness includes track gauge, track direction, height, level and triangular pit data, matching the detection data of track unevenness with the track mileage position, selecting corresponding indicators, and generating corresponding three-dimensional lines just above the centerline Z axis of the three-dimensional model of the track; S54, click on the mileage position in the three-dimensional model of the track to view and download a common two-dimensional line graph, and match the relevant point cloud screenshots of the abnormal places on the track with the coloring components.

8. A track information digital twin system based on Beidou track inspection instrument, used to implement any method of claims 1-7, characterized in that: include: A model building module (101), used to build a corresponding three-dimensional track model according to line design information; A data collection module (102) is used to collect track and surrounding data through mobile detection of a track inspection device equipped with multiple sensors; A mileage positioning module (103), used for performing high-precision mileage positioning of the track and surrounding data by using a GNSS+inertial navigation algorithm; A data matching module (104) is used to match the track and surrounding data after high-precision mileage positioning with the track three-dimensional model; The anomaly recognition module (105) is used to intelligently identify track anomalies based on the difference between the dense point cloud data corresponding to the track and surrounding data after matching and the track three-dimensional model, and to express the track anomalies in multiple dimensions.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a plurality of instructions, and the processor is used to read the instructions and execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the plurality of instructions can be read by a processor to execute the method according to any one of claims 1 to 7.

Images