A digital twin method and system for track information based on Beidou track inspection instrument

Abstract

The present invention discloses a digital twin method for track information based on a Beidou track inspection instrument, comprising: constructing a corresponding three-dimensional track model according to line design information; collecting track and surrounding data through mobile detection of a track inspection instrument equipped with multiple sensors; performing high-precision mileage positioning on the track and surrounding data; matching the track and surrounding data that has undergone high-precision mileage positioning with the track three-dimensional model; intelligently identifying track anomalies based on the differences between the dense point cloud data corresponding to the matched track and surrounding data and the track three-dimensional model, and expressing the track anomalies in multiple dimensions. Also disclosed are corresponding systems, electronic devices, and computer-readable storage media. By improving the data expression form in existing solutions, the degree of correlation between data and track real-life information is improved, and the detection data is associated with the track model, thereby solving the problems of insufficient historical traceability and weak ability to integrate multiple detection results in the current detection process.

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 a major artery in my country's transportation and economic development. In the context of Digital China, the digital economy, intelligent technology, and informatization, the development of railway informatization has naturally become a key trend in modern railway development. While significant progress has been made in railway informatization in passenger, freight, and dispatching, considerable room for improvement remains in the informatization of engineering and operation technologies. Track smoothness is a crucial foundation for safe and stable railway operation. With the growth of my country's railway operating mileage and the increase in operating speeds, the pressure on track operation and maintenance has increased. Seven key areas of focus during track operation and maintenance are track alignment, gauge, height, superelevation, level, rail bottom slope, and triangular pits. Furthermore, during train operation, attention must be paid to issues such as foreign objects intruding through building clearances, track slab damage, and fastener damage. This data must be obtained before maintenance to serve as a reference.

[0003] First, determining maintenance points requires precise positioning. Railways use mileage to represent locations, so accurate mileage data is essential. This necessitates accurate mileage data during the inspection process. However, during the inspection process, some mileage locations may show a certain degree of damage, but because the damage is minor and does not meet the repair standard, this information is not fully utilized. Instead, further remedial measures are not taken until problems arise. This lack of historical data recording and analysis is detrimental to the full lifecycle management of railway operations and maintenance.

[0004] Second, there are currently two common methods for detecting track defects. The first is dynamic inspection, which uses high-speed track inspection vehicles to collect dynamic track data, analyze track irregularities, and select measurement sections for static measurements. However, this method is costly, has a relatively fixed inspection cycle, and lacks flexibility. The second is static inspection, which can be further divided into three types: the first relies on manual measurement using tools such as hanging wires and track rulers; the second is "stop-and-go" measurement using a track inspection instrument in conjunction with a total station; and the third is mobile measurement using a track inspection instrument combined with GNSS and inertial inspection equipment. Manual measurement methods are slow and have low accuracy, and the data obtained must be recorded manually, often on paper. A track inspection instrument combined with a total station can obtain comprehensive track measurement data, which is more accurate than manual inspection methods, but its speed for single-point inspections needs to be improved. Using a track inspection instrument in conjunction with GNSS mobile measurement can increase track measurement speed while maintaining accuracy, making it more suitable for inspection by maintenance personnel. However, the above testing solutions focus on presenting the results of a single test, lacking effective management of multiple results. During the testing process, staff focus on out-of-limit data that requires action, but pay little attention to the process of its generation and development, nor to minor anomalies that do not affect operations.

[0005] Third, existing technologies lack full life cycle management of multiple inspection data, and generally use one-dimensional or 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 inspection data is insufficient. The inspection 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 inspection data is lacking. 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 small details, paying attention not only to the locations that have reached the maintenance standards, but also to the areas where signs of disease appear. 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 Beidou track inspection instruments to address the defects of the existing technology. It is a digital twin method and system suitable for track inspection instrument detection data during 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 solution, the degree of correlation between data and track real-life 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 visualize, 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 a Beidou track inspection instrument, comprising:

[0009] S1, constructing the corresponding track 3D model according to the line design information;

[0010] S2, collects track and surrounding data through mobile inspection using a track inspection device equipped with various sensors;

[0011] S3, performing high-precision mileage positioning of the track and surrounding data using 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 a multi-dimensional manner.

[0014] Preferably, the S1 includes:

[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 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 track.

[0018] Preferably, the S2 includes:

[0019] S21, after placing the track inspection instrument at the starting point of the area to be measured, 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, performing a uniform moving measurement according to a set speed of the track inspection instrument, 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 three-dimensional laser scanner is used to obtain scene information around the track, and the structured light module is used to obtain dense point cloud information of the left and right rails of the track, wherein the dense point cloud information includes fasteners and rail surfaces.

[0022] Preferably, the 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, as well as the alignment prisms installed on both sides of the track;

[0025] S33, for the rail point cloud data collected by the said linear structured 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, whether there are foreign objects invading the minimum building limit at different mileage positions is determined by the limit requirements at different heights.

[0026] Preferably, the 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 thin out the point cloud data of the surrounding environment according to the loading frame rate;

[0029] S43, matching the point cloud at the tunnel and other locations with the standard model using the least squares method.

[0030] Preferably, the S5 includes:

[0031] S51, intelligently identifying track anomalies based on differences 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 a color value through a color assignment component according to the classification;

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

[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 abnormality of 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) is used to build a corresponding track three-dimensional model according to line design information;

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

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

[0039] A data matching module (104) is used to match the track and surrounding data obtained through 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 with 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 areas are marked in red and the abnormal areas are marked in yellow, which can achieve a more intuitive display of the detection results and historical tracing.

[0045] (2) The present invention partially solves the problem of weak ability to integrate multiple test results in the current detection 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 detection 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 related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. 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 any 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 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 clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall 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," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0052] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0053] Example 1

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

[0055] S1, constructing the corresponding track 3D model according to the 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, constructing a three-dimensional track model based on 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, so that it corresponds to the actual track and facilitates updating of parts of the model when the track model changes.

[0060] As a preferred embodiment, the track three-dimensional model adopts OBJ format, GLTF format or 3D Tiles format. The track three-dimensional model is not a complete three-dimensional model; the different component units 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.

[0061] S2, collects track and surrounding data through mobile inspection using a track inspection device 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, the S2 includes:

[0064] S21, after placing the track inspection instrument at the starting point of the area to be measured, 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 a uniform moving measurement at a 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 three-dimensional laser scanner is used to obtain scene information around the track, and the structured light module is used to obtain dense point cloud information of the left and right rails of the track, wherein the dense point cloud information includes fasteners and rail surfaces.

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

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

[0069] As a preferred embodiment, the 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, as well as the alignment prisms installed on both sides of the track;

[0072] S33: For the rail point cloud data collected by the line structured light module, a composite method of straight-through filtering and cloth filtering is used to filter out the corresponding noise and outliers; 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 embodiment, 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 thin out the point cloud data of the surrounding environment according to the loading frame rate;

[0077] S43, matching the point cloud at the tunnel and other locations with the standard model using the least squares method.

[0078] In this embodiment, the least squares method is often used to solve the curve fitting problem, which seeks the best function matching the data by minimizing the sum of squares of the 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 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 abnormalities in multiple dimensions.

[0080] As a preferred embodiment, the S5 includes:

[0081] S51, intelligently identifying track anomalies based on differences 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 a color value through a color assignment component according to the classification;

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

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

[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 abnormality of the track with the coloring components.

[0086] Example 2

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

[0088] Model building module 101, used to build a corresponding track three-dimensional model according to 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 using a GNSS+inertial navigation algorithm;

[0091] A data matching module 104 is used to match the track and surrounding data obtained through 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 differences between the matched dense point cloud data corresponding to the track and surrounding data and the track three-dimensional model, and to 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 multiple instructions, and the instructions can be loaded and executed by the processor to enable the processor to execute the method as in embodiment 1.

[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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above 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 the corresponding track 3D model according to the line design information; S2, collects track and surrounding data through mobile inspection using a track inspection device equipped with various sensors; S3, performing high-precision mileage positioning of the track and surrounding data using 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 a multi-dimensional manner; Said S1 comprises: S11, a designer provides railway line design information, where the railway line design information includes track cross-section, fastener type, and line construction information; S12, constructing a three-dimensional track model based on 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 is in OBJ format, GLTF format, or 3D Tiles format and is not a complete three-dimensional model. The different components are manufactured according to design drawings or corresponding products, and then assembled together according to position matching relationships to serve as the initial three-dimensional track model in the method. The S2 includes: S21, after placing the track inspection instrument at the starting point of the area to be measured, 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, performing a uniform moving measurement according to a set speed of the track inspection instrument, 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, obtaining scene information around the track by using the three-dimensional laser scanner, and obtaining dense point cloud information of the left and right rails of the track by using the structured light module, wherein the dense point cloud information includes fasteners and rail surface; 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, as well as the alignment prisms installed on both sides of the track; S33: For the rail point cloud data collected by the line structured light module, a combined method of straight-through filtering and cloth filtering is used to filter out the corresponding noise and outliers. For the building clearance, the clearance requirements at different heights are used to determine whether there are foreign objects invading the minimum building clearance at different mileage positions. 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 thin out the point cloud data of the surrounding environment according to the loading frame rate; S43, matching the point cloud of the tunnel and the standard model using the least squares method; The S5 includes: S51, intelligently identifying track anomalies based on differences 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 a color value through a color assignment component according to the classification; S53, storing the track irregularity detection data in the track inspection instrument; the track irregularity detection data includes track gauge, track direction, height, level, and triangular pit data; matching the track irregularity detection data with the track mileage position, selecting corresponding indicators, and generating a corresponding three-dimensional line directly above the centerline Z axis of the three-dimensional track model; 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 abnormality of the track with the coloring components.

2. A track information digital twin method based on Beidou track inspection instrument according to claim 1, 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 obtain environmental information around the track.

3. A track information digital twin system based on Beidou track inspection instrument, used to implement the method described in any one of claims 1-2, characterized in that: include: A model building module (101) is used to build a corresponding track three-dimensional model according to line design information; A data acquisition module (102) is used to collect track and surrounding data through mobile detection of a track inspection instrument equipped with multiple sensors; A mileage positioning module (103) is used to perform high-precision mileage positioning of the track and surrounding data using a GNSS+inertial navigation algorithm; A data matching module (104) is used to match the track and surrounding data obtained through 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.

4. 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 configured to read the instructions and execute the method according to any one of claims 1 to 2.

5. 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 1-2.

Images