Digital twinning state monitoring method for maglev line track by fusing air-track-ground multi-dimensional information

Abstract

The invention belongs to the technical field of track monitoring, and provides a digital twinning state monitoring method for a maglev line track fusing air-track-ground multi-dimensional information, and the method comprises the steps: building a three-dimensional model of a segmented line track based on the aerial photography information of an unmanned plane and a BIM technology; acquiring surface feature data of the selected segmented line track by using a section scanner, and reconstructing a three-dimensional model of the selected segmented line track by combining attitude and position information of an inertial navigation system; and finally splicing the reconstructed three-dimensional model and the non-reconstructed segmented line track model to obtain a line track geometric model, improving the modeling precision, constructing a database based on the qualified holographic state data, and constructing a behavior and rule model of the magnetic levitation line track digital base in combination with the constructed geometric model. Information fusion is carried out on isomorphic and heterogeneous holographic state data by using a Kalman filtering fusion algorithm, and diversified intelligent monitoring of the magnetic levitation line track is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of track monitoring, and specifically relates to a digital twin state monitoring method for a maglev line track integrating multi-dimensional information of air, rail and ground. Background Art

[0002] Maglev transportation is the forefront of rail transportation technology development in the post-high-speed rail era, and it embodies the country's high-end manufacturing and R&D capabilities. Maglev transportation is highly integrated and tightly coupled, and has the characteristics of both civil structures and electromechanical facilities on the maglev line track system. Therefore, it is of great significance to conduct intelligent monitoring of its maglev transportation. From a macro perspective, drone technology monitoring provides basic protection for the safety along the maglev line, and is a prerequisite for the development of digital twin integration. After the drone ensures the safety of the maglev line track construction limit, the on-orbit monitoring equipment conducts data collection and analysis on the existing maglev line inspection problems and high-precision requirements, and the compensation modeling and ground fixed-point monitoring from the on-orbit microscopic perspective effectively make up for the lack of structural performance analysis of the maglev line at the aerial and track surface levels, and ensure the overall normal structural performance under all-weather conditions from the perspective of health monitoring.

[0003] At the data fusion level, multi-source data collected by multiple sensors are preprocessed, and data missing and noise problems are solved through interpolation algorithms and filtering methods (such as mean filtering). After data cleaning, the multi-source original data is fused using a data fusion algorithm as the basic data for fusion information. In feature fusion technology, multi-source data are reduced in dimension and feature extracted through feature extraction algorithms (such as PCA and LDA), feature data from different information sources are fused, data of different dimensions are transformed into the same feature space, and multi-source features are unified modeled with deep learning to meet the model's high-precision state information requirements. At the decision-making level, combined with the data analysis results of different dimensions of space, orbit and ground, a variety of decision fusion methods (such as DS evidence theory and voting mechanism) are used to integrate and output multi-dimensional decisions based on the cleaned data.

[0004] In the existing technology, the inspection and maintenance work of the current maglev operating track line is still mainly based on patrols under the security beams during operating hours and manual inspections on the beams during window hours. It has the defects of low efficiency, limited maintenance and inspection time, poor working environment, and inability to accurately and real-time reflect the system status, which cannot meet the needs of the development of maglev transportation.

[0005] To this end, the present invention provides a digital twin status monitoring method for a maglev line track that integrates multi-dimensional information of air, rail and ground. In view of the high degree of linearity of the maglev line and the potential safety hazards when shuttling through urban areas, unmanned aerial vehicles are used for monitoring and image acquisition. In view of the high precision requirements of the track, on-orbit equipment such as structured light scanning and cross-sectional scanners are used to provide fine-scale monitoring of the facilities. In combination with ground health monitoring (industrial cameras, ground fixed-point monitoring), the deficiencies of on-orbit equipment in monitoring structural performance and on-orbit equipment through skylight inspection are compensated, thereby effectively improving the monitoring efficiency and level of the maglev line track.

[0006] In this monitoring method, the air-rail-ground multi-dimensional information is first collected and processed, and the information is collected and analyzed from multiple angles and full dimensions, so as to monitor the track status from the overall to the details, and realize all-round status monitoring and early warning. Then, the progressive information fusion process enables the monitoring data to be orderly connected from the refined processing of basic data to feature extraction and then to the final comprehensive decision, ensuring the scientificity and reliability of the decision. Finally, the digital twin platform serves as the hub of information transmission and processing, organically combining the fusion and analysis results of multi-dimensional data with the final monitoring decision, ensuring the closed loop and efficient operation of the monitoring process and a comprehensive and intuitive monitoring interface for users. Summary of the invention

[0007] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0008] The technical solution adopted by the present invention to solve the technical problem is: a method for monitoring the state of a digital twin of a maglev line track by integrating multi-dimensional information of air, rail and ground, comprising:

[0009] Based on the aerial photography information of the UAV and the BIM technology, a three-dimensional model of the segmented line track is established and preliminarily spliced, and the overlapping area between the three-dimensional models of adjacent segmented line tracks after splicing and the performance data of the overlapping area are obtained, wherein the performance data includes the area of ​​the overlapping area and the number of point cloud points, and the segmented line track is selected based on the processing and analysis of the performance data; the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, and the attitude and position information of the inertial navigation system is combined, and the three-dimensional model of the selected segmented line track is reconstructed by using the BIM technology; the high-precision three-dimensional model of the reconstructed segmented line track is finally spliced ​​with the unreconstructed segmented line track model, and exported to a common format to obtain a line track geometric model;

[0010] Based on the air-track-ground multi-dimensional information collection system, the holographic state data of the maglev line track is obtained. Based on the processing and analysis of the holographic state data, the data missing values ​​are obtained. According to the data missing values, the holographic state data is evaluated. Based on the evaluated qualified holographic state data, a database is built. Combined with the completed geometric model, the behavior and rule model of the digital base of the maglev line track is constructed using BIM technology.

[0011] Based on qualified holographic state data, the Kalman filter fusion algorithm is used to fuse the homogeneous and heterogeneous holographic state data within the holographic state data;

[0012] An intelligent monitoring platform for maglev line tracks is constructed based on the fusion of qualified holographic status data and the geometric model, behavior and rule model of the line track.

[0013] As a further technical solution of the present invention, the process of selecting the segmented line track is as follows:

[0014] The obtained point cloud distribution performance value DYB and overlap degree CD are processed by data, and the formula is: The model reconstruction value CG is obtained, where a1 and a2 are both preset proportional coefficients;

[0015] Compare the model reconstruction value CG with the model reconstruction threshold;

[0016] If the model reconstruction value CG is greater than or equal to the model reconstruction threshold, it means that the overlap degree of the overlapping area is high and the point cloud is evenly distributed and the density is qualified, then no operation is performed;

[0017] If the model reconstruction value CG is less than the model reconstruction threshold, it means that the overlap degree of the overlapping area is low and the point cloud distribution is uneven and the density is unqualified, then the two segmented line tracks corresponding to the overlapping area are selected for model reconstruction.

[0018] As a further technical solution of the present invention, the overlap degree CD is obtained in the following manner:

[0019] Use feature point detection and description algorithms to extract key feature points in the model, and use feature point matching algorithms to find similar feature points in adjacent models; obtain the overlapping area between models through feature point indication;

[0020] Obtain the area of ​​the overlapping region and the area of ​​the minimum circumscribed rectangle corresponding to the model, perform a ratio process on the area of ​​the overlapping region and the area of ​​the minimum circumscribed rectangle corresponding to the model to obtain the degree of overlap, and mark it as CD;

[0021] The minimum enclosing rectangle refers to a minimum rectangle that can enclose all target points, and its width and height are determined by the maximum and minimum values ​​of the target points.

[0022] As a further technical solution of the present invention, the point cloud distribution performance value DYB is obtained by:

[0023] The protrusion overlap ratio CS and the protrusion overlap degree value CZ are processed by the formula: The point cloud density non-uniform value DJ is obtained, where s1 and s2 are both preset proportional coefficients;

[0024] The point cloud density non-uniform value DJ and the point cloud deviation ratio are summed to obtain the point cloud distribution performance value, which is marked as DYB;

[0025] The point cloud deviation ratio is obtained as follows:

[0026] Point cloud processing software is used to perform point cloud analysis on the overlapping area to obtain the number of point cloud points in the overlapping area, and the point cloud density of the overlapping area is obtained by ratio processing between the number of point cloud points in the overlapping area and the area of ​​the overlapping area. The point cloud density of the overlapping area is subjected to difference processing with the point cloud set density of the overlapping area, and the absolute value of the difference is taken to obtain the point cloud density difference of the overlapping area. The point cloud density difference of the overlapping area is subjected to ratio processing with the point cloud set density of the overlapping area to obtain the point cloud deviation ratio.

[0027] As a further technical solution of the present invention, the method for obtaining the protrusion overlap ratio CS is as follows:

[0028] The overlapping area is divided into several overlapping sub-areas with equal areas, the number of point clouds in the overlapping sub-areas is obtained, and the number of point clouds in the overlapping sub-areas is processed by ratio processing with the area of ​​the overlapping sub-areas to obtain the point cloud density of the overlapping sub-areas;

[0029] The point cloud densities of all overlapping sub-areas are summed and averaged to obtain the point cloud density mean, the point cloud density in the overlapping sub-area is subtracted from the point cloud density mean, and the absolute value of the difference is taken to obtain the point cloud density deviation of the overlapping sub-area, the point cloud density deviations of all overlapping sub-areas are summed and averaged to obtain the point cloud density deviation mean, and the point cloud density deviation of the overlapping sub-area is compared with the point cloud density deviation mean;

[0030] If the point cloud density deviation of the overlapping sub-region is greater than the mean value of the point cloud density deviation, the overlapping sub-region is marked as a prominent overlapping sub-region;

[0031] If the point cloud density deviation of the overlapping sub-region is less than or equal to the mean value of the point cloud density deviation, the overlapping sub-region is marked as a non-prominent overlapping sub-region;

[0032] The number of prominent overlapping sub-regions is counted and the ratio is processed with the number of overlapping sub-regions to obtain the prominent overlapping number ratio, which is marked as CS.

[0033] As a further technical solution of the present invention, the method for obtaining the protrusion overlap degree value CZ is:

[0034] The overlapping sub-area is subjected to difference processing with the mean of the point cloud density deviation to obtain the mean deviation of the point cloud density in the overlapping sub-area. The mean deviations of the point cloud density in all overlapping sub-areas are summed and averaged to obtain the relative deviation of the mean of the point cloud density. The relative deviation of the mean of the point cloud density is ratioed with the mean of the point cloud density deviation to obtain the value of the degree of prominent overlap, which is marked as CZ.

[0035] As a further technical solution of the present invention, the collection process of the holographic state data includes:

[0036] A1, technical means of high-altitude measurement: drones conduct regular automatic route inspections to quickly detect the status information of cable trenches, turnout houses, and substation line ancillary facilities;

[0037] A2, Technical means of dynamic track inspection: on-track machine vision inspection and structured light scanning. The on-track machine vision inspection system refers to an industrial camera and edge computer as the main components. It uses high-speed shooting and machine learning algorithms to identify the following information: structural seam identification, foreign body intrusion in functional areas, stator surface wear, lower structure defects, and record the mileage information and abnormality type of the identified location; use a structured light profile scanner to accurately scan the stator surface, measure the stator surface deviation and fold angle by point cloud processing, and describe the geometric shape deviation;

[0038] A3. Select typical track beams to establish a fixed structural health monitoring system and build an all-weather fixed-point monitoring network for track structure and environmental conditions. The monitoring objects include: track beam end inclination, mid-span vibration response characteristics, surface temperature distribution, and environmental conditions.

[0039] As a further technical solution of the present invention, the data missing value QP is obtained in the following manner:

[0040] Setting a collection cycle, dividing the collection cycle into a number of time analysis nodes, acquiring holographic state data at the time analysis nodes, and comparing the holographic state data at the time analysis nodes with standard holographic state data;

[0041] If the total amount of data contained in the holographic state data at the time analysis node is not equal to the total amount of data contained in the standard holographic state data, the time analysis node is marked as an abnormal acquisition node;

[0042] If the total amount of data contained in the holographic state data at the time analysis node is equal to the total amount of data contained in the standard holographic state data, no processing is performed;

[0043] Count the number of abnormal collection nodes and compare it with the number of time analysis nodes to obtain the abnormal collection number ratio, which is marked as SL;

[0044] Perform difference processing on the total amount of data contained in the holographic state data at the abnormal acquisition node and the total amount of data contained in the standard holographic state data to obtain the amount of data missing at the abnormal acquisition node, sum and average the amount of data missing at all abnormal acquisition nodes to obtain the mean of data missing amount, perform ratio processing on the mean of data missing amount and the total amount of data contained in the standard holographic state data to obtain the abnormal acquisition missing ratio, and mark it as QS;

[0045] The obtained abnormal collection quantity ratio SL and abnormal collection missing ratio QS are processed by data, and the formula is: The data missing value QP is obtained, where z1 and z2 are both preset proportional coefficients.

[0046] As a further technical solution of the present invention, the process of performing data evaluation on the holographic state data according to the data missing value is: comparing the data missing value QP with the data missing threshold;

[0047] If the data missing value QP is greater than or equal to the data missing threshold, it means that the holographic state data collected during the collection period is highly missing and unqualified;

[0048] If the data missing value QP is less than the data missing threshold, it means that the holographic state data collected during the collection period has a low degree of missingness and is qualified.

[0049] As a further technical solution of the present invention, the specific process of integrating and constructing the intelligent monitoring platform for the maglev line track is as follows:

[0050] H1, use MATLAB or Python data analysis software to analyze the holographic state data of the maglev line track system, the specific analysis is:

[0051] Track geometry: including track geometry, alignment, levelness, and height difference;

[0052] Structural health status: monitoring the stress, strain, vibration and temperature parameters of track beams, supports and connectors;

[0053] Environmental parameters: such as temperature, humidity, wind speed, rainfall;

[0054] Equipment status: operating status and performance parameters of signal system, power supply system, and communication system equipment;

[0055] H2, using decentralized edge computing technology, performs preliminary data preprocessing on the physical end to reduce the amount of data transmission, improve the efficiency of cloud-to-physical information transmission, and reduce cloud processing pressure. Specifically:

[0056] Gross error determination: Perform a preliminary screening of the collected data at the object end to eliminate data with obvious errors;

[0057] Data cleaning: remove duplicate data, fill missing values, process outliers, and improve data quality;

[0058] H3 uses the cloud computing platform as the basis, imports the line track model, and completes the construction of the intelligent monitoring platform, including:

[0059] Model display: Import the geometric model, behavior and rule model of the track on the cloud platform to display the structure and status of the maglev track system;

[0060] Data download: Provides a data download interface, allowing users to download raw data or processed data as needed;

[0061] Database management: Design and implement an efficient database management system to store and manage various data of the maglev line track system;

[0062] Login and authority management: Provide user login and authority allocation functions to ensure system security and data confidentiality.

[0063] The beneficial effects of the present invention are as follows:

[0064] 1. Based on the aerial photography information of the UAV and BIM technology, a three-dimensional model of the segmented line track is established and preliminarily spliced, and the overlapping area between the three-dimensional models of adjacent segmented line tracks after splicing and the performance data of the overlapping area are obtained. Based on the processing and analysis of the performance data, the segmented line track is selected; the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, combined with the attitude and position information of the inertial navigation system, and the high-precision three-dimensional model of the selected segmented line track is reconstructed by using BIM technology; the high-precision three-dimensional model of the reconstructed segmented line track is finally spliced ​​with the unreconstructed segmented line track model, and exported to a common format to obtain the line track geometric model. The modeling through UAV aerial photography has a good macro modeling foundation, and can be used to model the maglev line and surrounding facilities as a whole and realize the relevant protection within the building limit. Due to the high maneuverability of the UAV, the modeling process has a high modeling efficiency and protection capability; and the compensatory reconstruction of the line track model is realized by combining the cross-sectional scanner and the inertial navigation system to meet the requirements of the fine modeling accuracy of the maglev, which has practical engineering significance for the modeling process of the maglev line track and is conducive to the intelligent monitoring of the line track.

[0065] 2. Based on the air-track-ground multi-dimensional information acquisition system, the holographic state data of the maglev line track is obtained, and the data missing values ​​are obtained based on the processing and analysis of the holographic state data. The holographic state data is evaluated according to the data missing values, and a database is constructed based on the holographic state data that has passed the evaluation. In combination with the constructed geometric model, the behavior and rule model of the digital base of the maglev line track is constructed using BIM technology. Based on the qualified holographic state data, the Kalman filter fusion algorithm is used to fuse the information of the isomorphic and heterogeneous holographic state data in the holographic state data. The present invention realizes the construction of the behavior and rule model of the digital base of the maglev line track, completes the monitoring of the maglev line track, and fuses its diversified holographic state data, thereby realizing diversified intelligent monitoring of the maglev line track.

[0066] 3. Based on the collected qualified holographic state data and the geometric model, behavior and rule model of the line track, an intelligent monitoring platform for the maglev line track is constructed. First, through the image acquisition of the drone, not only can the accurate construction of the line track model be realized, but also the model construction efficiency can be improved. Secondly, the acquisition and monitoring of the drone can overcome the problem of untimely monitoring and low monitoring efficiency caused by the long line track. In addition, the data collected by the structured light scanning and cross-section scanner for model construction and fusion monitoring are conducive to meeting the high requirements of track accuracy monitoring. The health monitoring system composed of industrial cameras and ground fixed-point monitoring is conducive to breaking through the limitations of the traditional line track structure itself. The present invention realizes the intelligent monitoring of the line track from a multi-dimensional level, improves the convenience and efficiency of the maglev line track monitoring, and the present invention first collects and processes information from the air, rail and ground in multiple dimensions, builds the track model, and realizes the detailed all-round monitoring of the track state. Then, through data processing, the orderly connection of basic data is realized to ensure the accuracy and scientificity of the data, such as data anomaly analysis, and finally the fusion of multi-dimensional data, the analysis results and the final monitoring decision are organically combined through the digital twin platform to form a complete intelligent monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The present invention will be further described below in conjunction with the accompanying drawings.

[0068] Figure 1 It is a flowchart of the steps of the method for monitoring the digital twin state of a maglev line track by integrating multi-dimensional information of air, rail and ground according to an embodiment of the present invention;

[0069] Figure 2 It is a judgment flow chart of three-dimensional model reconstruction in the digital twin state monitoring method of a maglev line track integrating multi-dimensional information of air, rail and ground described in an embodiment of the present invention;

[0070] Figure 3 This is a model comparison diagram after modeling is completed in the embodiment of the present invention;

[0071] Figure 4 Schematic diagram of structured light scanning monitoring used in an embodiment of the present invention;

[0072] Figure 5 A schematic diagram of an industrial camera detection method according to an embodiment of the present invention;

[0073] Figure 6 This is a schematic diagram of ground fixed-point monitoring in an embodiment of the present invention;

[0074] Figure 7 This is a module diagram of the digital twin status monitoring system for a maglev line track that integrates multi-dimensional information of air, rail and ground as described in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0076] Example 1

[0077] like Figure 1 As shown, the method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground described in an embodiment of the present invention includes:

[0078] Step 1: Based on the aerial photography information of the drone and BIM technology, a three-dimensional model of the segmented line track is established and preliminarily spliced, and the overlapping area between the three-dimensional models of adjacent segmented line tracks after splicing and the performance data of the overlapping area are obtained, wherein the performance data includes the area of ​​the overlapping area and the number of point cloud points, and the segmented line track is selected based on the processing and analysis of the performance data; the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, and the attitude and position information of the inertial navigation system is combined, and the three-dimensional model of the selected segmented line track is reconstructed by using BIM technology; the high-precision three-dimensional model of the reconstructed segmented line track is finally spliced ​​with the unreconstructed segmented line track model, and exported to a common format to obtain a line track geometric model;

[0079] It should be noted that the specific operations before constructing the three-dimensional model of the segmented line track also include:

[0080] S1, survey the entire mileage range of the maglev line, record the areas where drones are restricted from flying and the corresponding mileage information, and arrange image control points based on this information and make corresponding marks;

[0081] S2, combining the effective operation time of a single UAV flight, the flight restricted mileage location and the minimum coverage requirements of the image control points, reasonably planning the inspection area and flight times based on the coordinate information in the route design stage, and unifying the standards for single flight route design;

[0082] S3, using GNSS base stations to measure the coordinate information of each image control point along the line, which is used for adjustment and correction before the three-dimensional model of the segmented line track is established;

[0083] like Figure 2 As shown, in some embodiments, key feature points are extracted from the model using a feature point detection and description algorithm (such as SIFT, SURF, ORB, etc.), and similar feature points in adjacent models are found using a feature point matching algorithm (such as FLANN, BFMatcher, etc.); the overlapping area between the models is obtained through feature point indication;

[0084] Obtain the area of ​​the overlapping region and the area of ​​the minimum bounding rectangle (MBR) corresponding to the model, perform a ratio process on the area of ​​the overlapping region and the area of ​​the minimum bounding rectangle corresponding to the model to obtain the degree of overlap, and mark it as CD;

[0085] Among them, the minimum bounding rectangle (MBR) means: a minimum rectangle that can enclose all target points (in this scenario, the target points are all vertices of the model), and its width and height are determined by the maximum and minimum values ​​of the target points;

[0086] Point cloud analysis is performed on the overlapping area using point cloud processing software to obtain the number of point cloud points in the overlapping area, the number of point cloud points in the overlapping area is processed by ratio with the area of ​​the overlapping area to obtain the point cloud density of the overlapping area, the point cloud density of the overlapping area is processed by difference with the point cloud setting density of the overlapping area, and the absolute value of the difference is taken to obtain the point cloud density difference of the overlapping area, and the point cloud density difference of the overlapping area is processed by ratio with the point cloud setting density of the overlapping area to obtain the point cloud deviation ratio;

[0087] It should be noted that the point cloud setting density is set in advance by those skilled in the art according to the model construction requirements;

[0088] The overlapping area is divided into several overlapping sub-areas with equal areas, the number of point clouds in the overlapping sub-areas is obtained, and the number of point clouds in the overlapping sub-areas is processed by ratio processing with the area of ​​the overlapping sub-areas to obtain the point cloud density of the overlapping sub-areas;

[0089] The point cloud densities of all overlapping sub-areas are summed and averaged to obtain the point cloud density mean, the point cloud density in the overlapping sub-area is subtracted from the point cloud density mean, and the absolute value of the difference is taken to obtain the point cloud density deviation of the overlapping sub-area, the point cloud density deviations of all overlapping sub-areas are summed and averaged to obtain the point cloud density deviation mean, and the point cloud density deviation of the overlapping sub-area is compared with the point cloud density deviation mean;

[0090] If the point cloud density deviation of the overlapping sub-region is greater than the mean value of the point cloud density deviation, the overlapping sub-region is marked as a prominent overlapping sub-region;

[0091] If the point cloud density deviation of the overlapping sub-region is less than or equal to the mean value of the point cloud density deviation, the overlapping sub-region is marked as a non-prominent overlapping sub-region;

[0092] Count the number of prominent overlapping sub-regions and compare it with the number of overlapping sub-regions to obtain the prominent overlapping number ratio, which is marked as CS;

[0093] The overlapped sub-regions are subjected to difference processing with the mean of the point cloud density deviation to obtain the mean deviation of the point cloud density of the overlapped sub-regions. The mean deviations of the point cloud density of all the overlapping sub-regions are summed and averaged to obtain the relative deviation of the mean of the point cloud density. The relative deviation of the mean of the point cloud density is subjected to ratio processing with the mean of the point cloud density deviation to obtain the value of the degree of prominent overlap, which is marked as CZ.

[0094] The protrusion overlap ratio CS and the protrusion overlap degree value CZ are processed by the formula: The point cloud density non-uniform value DJ is obtained, where s1 and s2 are both preset proportional coefficients;

[0095] The point cloud density non-uniform value DJ and the point cloud deviation ratio are summed to obtain the point cloud distribution performance value, which is marked as DYB;

[0096] The obtained point cloud distribution performance value DYB and overlap degree CD are processed by data, and the formula is: The model reconstruction value CG is obtained, where a1 and a2 are both preset proportional coefficients;

[0097] It should be noted that the meaning of the model reconstruction value CG is: the model reconstruction value CG is calculated by the point cloud distribution performance value DYB and the overlap degree CD, wherein the overlap degree reflects the degree of overlap between the spliced ​​segmented line track models, and the point cloud distribution performance value DYB reflects the point cloud distribution density of the overlapped area between the spliced ​​segmented line track models. The larger the model reconstruction value CG is, the more accurate the construction of the spliced ​​segmented line track model is.

[0098] In some embodiments, the model reconstruction value CG is compared with a model reconstruction threshold;

[0099] If the model reconstruction value CG is greater than or equal to the model reconstruction threshold, it means that the overlap degree of the overlapping area is high and the point cloud is evenly distributed and the density is qualified, then no operation is performed;

[0100] If the model reconstruction value CG is less than the model reconstruction threshold, it means that the overlap degree of the overlapping area is low and the point cloud distribution is uneven and the density is unqualified, then the two segmented line tracks corresponding to the overlapping area are selected for model reconstruction;

[0101] Based on the selected segmented line track, the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, and the attitude and position information of the inertial navigation system is combined, and the three-dimensional model of the selected segmented line track is reconstructed by using BIM technology, such as Figure 3As shown in the figure (the left figure reflects the measured track entity, and the right figure reflects the track 3D model after modeling), the high-precision 3D model of the reconstructed segmented line track and the unreconstructed segmented line track model are finally spliced ​​and exported to a common format to obtain the line track geometry model;

[0102] Exemplarily, the surface feature data of the selected segmented track is obtained by using a cross-sectional scanner, combined with the attitude and position information of the inertial navigation system, specifically:

[0103] The cross-sectional scanner is used to scan the surface characteristics of the track and obtain surface characteristic data such as the shape, size and profile of the track section;

[0104] The inertial navigation system can collect and process data such as the attitude, velocity, and acceleration of an object in motion in real time, providing accurate attitude and position information for estimating the object's position in space;

[0105] The data collected by the cross-sectional scanner and the inertial navigation system are stitched, registered and reconstructed to generate a three-dimensional model of the track;

[0106] It should be noted that through the data fusion of the cross-sectional scanner and the inertial navigation system, data splicing, registration and reconstruction can be achieved to generate a consistent and high-precision three-dimensional track model; this data fusion not only improves the limitations of a single system, but also achieves more comprehensive and accurate monitoring through the comprehensive use of multi-source data. The efficient fusion and registration of data is a key step to ensure the accuracy of the model and can better reflect the real situation of the track;

[0107] The technical solution of this embodiment is as follows: based on the aerial photography information of the UAV and the BIM technology, a three-dimensional model of the segmented line track is established and preliminarily spliced, the overlapping area between the three-dimensional models of adjacent segmented line tracks after splicing and the performance data of the overlapping area are obtained, and the segmented line track is selected based on the processing and analysis of the performance data; the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, and the attitude and position information of the inertial navigation system is combined, and the three-dimensional model of the selected segmented line track is reconstructed by using the BIM technology; the high-precision three-dimensional model of the reconstructed segmented line track is finally spliced ​​with the unreconstructed segmented line track model, and exported to a common format to obtain a line track geometric model. The modeling through the aerial photography of the UAV has a good macroscopic modeling foundation, and the line and surrounding facilities can be modeled as a whole. Due to the high maneuverability of the UAV, the modeling process has a high modeling efficiency; and the compensatory reconstruction of the line track model is realized in combination with the cross-sectional scanner and the inertial navigation system to improve the modeling accuracy. It has practical engineering significance for the modeling process of the maglev line track and is conducive to the intelligent monitoring of the line track.

[0108] Example 2

[0109] like Figure 1 As shown, based on Example 1, the method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground described in an embodiment of the present invention includes:

[0110] Step 2: Based on the air-track-ground multi-dimensional information collection system, the holographic state data of the maglev line track is obtained. Based on the processing and analysis of the holographic state data, the data missing values ​​are obtained. According to the data missing values, the holographic state data is evaluated. Based on the qualified holographic state data, a database is constructed. Combined with the completed geometric model, the behavior and rule model of the digital base of the maglev line track is constructed using BIM technology;

[0111] It should be noted that the multi-dimensional information collection system of air, rail and ground is composed of aerial collection by drones, dynamic track collection and a fixed structural health monitoring system established by typical track beams;

[0112] The collection process of holographic state data includes:

[0113] A1, technical means of high-altitude measurement: drones conduct regular automatic route inspections to quickly detect the status information of line ancillary facilities such as cable trenches, turnout houses, and substations;

[0114] A2, Technical means of dynamic track inspection: on-track machine vision inspection and structured light scanning. The on-track machine vision inspection system refers to an industrial camera and edge computer as the main components. It uses high-speed shooting and machine learning algorithms to identify the following information: structural seam identification, foreign body intrusion in functional areas, stator surface wear, lower structure defects, and record the mileage information and abnormality type of the identified location; use a structured light profile scanner to accurately scan the stator surface, measure the stator surface deviation and fold angle by point cloud processing, and describe the geometric shape deviation;

[0115] The first exemplary one is, Figure 4 As shown in the figure, structured light scanning monitoring: structured light profile scanning can obtain information such as the shape, size and topological structure of an object by measuring and reconstructing the surface of the object with high precision. This technology is based on the principle of structured light, uses a light source to project the surface of the object, and then uses a camera to shoot and analyze the projected image to eventually form a three-dimensional model of the surface of the object. It has the advantages of high scanning accuracy, fast scanning speed and easy operation. The high-precision three-dimensional data provided by structured light scanning can be "microscopically" integrated with the data of other monitoring systems such as the data of the inertial navigation system. Through comprehensive analysis of the data, comprehensive monitoring of the track condition can be achieved.

[0116] The second exemplary example is Figure 5As shown in the figure, industrial camera detection: by acquiring object images at high speed, using digital signal processing (DSP) chips for real-time image preprocessing and algorithm calculation, it can quickly and accurately analyze, classify and identify defects of objects, and generate statistical data and alarm information to feed back to operators or downstream links; the detection mainly targets high-speed maglev tracks, and the detection items include: structural seam identification, sliding surface anomaly detection, etc.

[0117] A3, select typical track beams to establish a fixed structural health monitoring system, and build an all-weather fixed-point monitoring network for track structure and environmental conditions. The monitoring objects include: track beam end inclination, mid-span vibration response characteristics, surface temperature distribution, and environmental conditions;

[0118] For example, Figure 6 As shown in the figure, the ground fixed-point monitoring in the fixed structural health monitoring system includes:

[0119] (1) Structural performance service status assessment: Through long-term monitoring and analysis of data such as acceleration, strain, and inclination of the track structure, the performance status of the track during service is assessed. The main contents of the assessment include identifying potential structural damage, fatigue, and deformation to ensure the safety and reliability of the track;

[0120] (2) Calculation of train passing time, running direction and line operation schedule: Analyze the time when the train passes a specific monitoring point using sensor data, and calculate the train's running direction and speed in combination with the dynamic response data on the track. Furthermore, by aggregating this information, the line operation schedule can be constructed and optimized to improve operational efficiency.

[0121] (3) Research on the vibration path of train-induced vibration: Through the spatiotemporal analysis of vibration data, the vibration path of the track caused by train operation is studied to identify the vibration source and its propagation path. The research conducted helps to understand the impact of train operation on the track and its surrounding environment and take effective vibration reduction measures;

[0122] (4) Data fusion of multiple physical quantities: Fusion of multi-source heterogeneous data from different sensors to obtain more comprehensive and accurate track monitoring information. The information fusion algorithm can effectively integrate the sampling data of different sensors, improve the accuracy and consistency of the overall data, and enhance the real-time monitoring capability of the track status;

[0123] (5) Interaction between trains and the environment: Analyze the impact of train operation on the environment (including parameters such as noise and electromagnetic field strength), and study the impact of environmental factors such as temperature, humidity, wind speed, etc. on track structure and train operation. Based on these studies, train operation and track maintenance strategies can be further optimized to improve the sustainability of the system.

[0124] In some embodiments, a collection period is set, the collection period is divided into a number of time analysis nodes, the holographic state data at the time analysis nodes are acquired, and the holographic state data at the time analysis nodes are compared with the standard holographic state data;

[0125] If the total amount of data contained in the holographic state data at the time analysis node is not equal to the total amount of data contained in the standard holographic state data, the time analysis node is marked as an abnormal acquisition node;

[0126] If the total amount of data contained in the holographic state data at the time analysis node is equal to the total amount of data contained in the standard holographic state data, no processing is performed;

[0127] It should be noted that the standard holographic state data represents the holographic state data of the maglev line track that needs to be collected according to the actual needs of accurately building the behavior and rule model;

[0128] Count the number of abnormal collection nodes and compare it with the number of time analysis nodes to obtain the abnormal collection number ratio, which is marked as SL;

[0129] Perform difference processing on the total amount of data contained in the holographic state data at the abnormal acquisition node and the total amount of data contained in the standard holographic state data to obtain the amount of data missing at the abnormal acquisition node, sum and average the amount of data missing at all abnormal acquisition nodes to obtain the mean of data missing amount, perform ratio processing on the mean of data missing amount and the total amount of data contained in the standard holographic state data to obtain the abnormal acquisition missing ratio, and mark it as QS;

[0130] The obtained abnormal collection quantity ratio SL and abnormal collection missing ratio QS are processed by data, and the formula is: Get the data missing value QP, where z1 and z2 are both preset proportional coefficients;

[0131] In some embodiments, the data missing value QP is compared with a data missing threshold;

[0132] If the data missing value QP is greater than or equal to the data missing threshold, it means that the holographic state data collected during the collection period is highly missing and unqualified;

[0133] If the data missing value QP is less than the data missing threshold, it means that the holographic state data collected during the collection period has a low degree of missingness and is qualified;

[0134] It should be noted that, based on the failure of data quantification, the missing data can be filled by interpolation;

[0135] Based on the qualified holographic status data, it is imported into the track geometry model constructed using BIM technology to complete the establishment of the maglev line system behavior model;

[0136] At the same time, the collected holographic state data are processed and analyzed using Matlab data analysis tools, including: identifying patterns, trends and outliers in the holographic state data, and using Matlab data analysis tools to extract characteristic variables useful for building rule models; based on the data analysis results, building a rule model for the maglev line;

[0137] Step 3: Based on qualified holographic state data, the Kalman filter fusion algorithm is used to fuse the homogeneous and heterogeneous holographic state data in the holographic state data to achieve diversified intelligent monitoring of the maglev line track;

[0138] The technical solution of the embodiment of the present invention is: based on the multi-dimensional information collection system of air, rail and ground, the holographic state data of the maglev line track is obtained, based on the processing and analysis of the holographic state data, the data missing values ​​are obtained, the holographic state data is evaluated according to the data missing values, and a database is constructed based on the holographic state data that has passed the evaluation, and in combination with the completed geometric model, the behavior and rule model of the digital base of the maglev line track is constructed by using the BIM technology, and based on the qualified holographic state data, the Kalman filter fusion algorithm is used to fuse the information of the isomorphic and heterogeneous holographic state data in the holographic state data. The present invention realizes the construction of the behavior and rule model of the digital base of the maglev line track, completes the monitoring of the maglev line track, and fuses its diversified holographic state data, thereby realizing diversified intelligent monitoring of the maglev line track.

[0139] Example 3

[0140] like Figure 1 As shown, based on Example 1 and Example 2, the method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground described in an embodiment of the present invention includes:

[0141] Step 4: Construct a maglev line track intelligent monitoring platform based on the collected qualified holographic state data and the geometric model, behavior and rule model of the line track;

[0142] Specifically include:

[0143] H1, use MATLAB or Python data analysis software to analyze the holographic state data of the maglev line track system, the specific analysis is:

[0144] Track geometry: including track geometry, alignment, levelness, and height difference;

[0145] Structural health status: monitoring parameters such as stress, strain, vibration, temperature, etc. of structural components such as track beams, supports, and connectors;

[0146] Environmental parameters: such as temperature, humidity, wind speed, rainfall;

[0147] Equipment status: operating status and performance parameters of signal systems, power supply systems, communication systems and other equipment;

[0148] H2, using decentralized edge computing technology, performs preliminary data preprocessing at the object end (i.e., sensor or data acquisition device end) to reduce the amount of data transmission, improve the efficiency of cloud-to-object information transmission, and reduce cloud processing pressure. Specifically:

[0149] Gross error determination: Perform a preliminary screening of the collected data at the object end to eliminate data with obvious errors;

[0150] Data cleaning: remove duplicate data, fill missing values, process outliers, etc. to improve data quality;

[0151] H3 uses cloud computing platforms (such as AWS, Azure, Alibaba Cloud, etc.) as the basis, imports the line track model, and completes the construction of the intelligent monitoring platform, including:

[0152] Model display: Import the geometric model, behavior and rule model of the track on the cloud platform to display the structure and status of the maglev track system;

[0153] Data download: Provides a data download interface, allowing users to download raw data or processed data as needed;

[0154] Database management: Design and implement an efficient database management system to store and manage various data of the maglev line track system;

[0155] Login and authority management: Provide user login and authority allocation functions to ensure system security and data confidentiality.

[0156] The technical solution of the embodiment of the present invention is: based on the collected qualified holographic state data and the geometric model, behavior and rule model of the line track, an intelligent monitoring platform for the maglev line track is constructed. The present invention realizes the intelligent monitoring of the line track and improves the convenience and efficiency of the maglev line track monitoring. The present invention first collects and processes information from the air, rail and ground in multiple dimensions, and while constructing the track model, it realizes detailed and all-round monitoring of the track state, and then realizes the orderly connection of basic data through data processing to ensure the accuracy and scientificity of the data, such as data anomaly analysis, and finally organically combines the fusion of multi-dimensional data and the analysis results with the final monitoring decision through the digital twin platform to form a complete intelligent monitoring system.

[0157] Example 4

[0158] like Figure 7 As shown, the digital twin state monitoring system for maglev line track integrating multi-dimensional information of air, rail and ground described in the embodiment of the present invention includes:

[0159] Line model construction module: Based on the aerial photography information of the UAV and BIM technology, a three-dimensional model of the segmented line track is established and preliminarily spliced, and the overlapping area between the three-dimensional models of adjacent segmented line tracks after splicing and the performance data of the overlapping area are obtained, where the performance data includes the area of ​​the overlapping area and the number of point cloud points. Based on the processing and analysis of the performance data, the segmented line track is selected; the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, combined with the attitude and position information of the inertial navigation system, and the three-dimensional model of the selected segmented line track is reconstructed using BIM technology; the high-precision three-dimensional model of the reconstructed segmented line track is finally spliced ​​with the unreconstructed segmented line track model, and exported to a common format to obtain a line track geometric model;

[0160] Behavior and rule model construction module: Based on the air-track-ground multi-dimensional information collection system, the holographic state data of the maglev line track is obtained, and the data missing values ​​are obtained by processing and analyzing the holographic state data. The holographic state data is evaluated according to the data missing values, and a database is constructed based on the holographic state data that has been evaluated to be qualified. Combined with the completed geometric model, the behavior and rule model of the digital base of the maglev line track is constructed using BIM technology;

[0161] Multi-source data fusion module: Based on qualified holographic state data, the Kalman filter fusion algorithm is used to fuse the homogeneous and heterogeneous holographic state data within the holographic state data;

[0162] Smart monitoring platform building module: Build a maglev line track smart monitoring platform based on qualified holographic status data and the integration of the line track's geometric model, behavior and rule model.

[0163] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for monitoring the state of a digital twin of a maglev line track by integrating multi-dimensional information of air, rail and ground, characterized by: include: Based on the aerial photography information of the UAV and the BIM technology, a three-dimensional model of the segmented line track is established and preliminarily spliced, and the overlapping area between the three-dimensional models of adjacent segmented line tracks after splicing and the performance data of the overlapping area are obtained, wherein the performance data includes the area of ​​the overlapping area and the number of point cloud points, and the segmented line track is selected based on the processing and analysis of the performance data; the surface feature data of the selected segmented line track is obtained by using a cross-sectional scanner, and the attitude and position information of the inertial navigation system is combined, and the three-dimensional model of the selected segmented line track is reconstructed by using the BIM technology; the high-precision three-dimensional model of the reconstructed segmented line track is finally spliced ​​with the unreconstructed segmented line track model, and exported to a common format to obtain a line track geometric model; Based on the air-track-ground multi-dimensional information collection system, the holographic state data of the maglev line track is obtained. Based on the processing and analysis of the holographic state data, the data missing values ​​are obtained. According to the data missing values, the holographic state data is evaluated. Based on the evaluated qualified holographic state data, a database is built. Combined with the completed geometric model, the behavior and rule model of the digital base of the maglev line track is constructed using BIM technology. Based on qualified holographic state data, the Kalman filter fusion algorithm is used to fuse the homogeneous and heterogeneous holographic state data within the holographic state data; An intelligent monitoring platform for maglev line tracks is constructed based on the fusion of qualified holographic status data and the geometric model, behavior and rule model of the line track.

2. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 1 is characterized by: The process of selecting the segmented line track is as follows: The obtained point cloud distribution performance value DYB and overlap degree CD are processed by data, and the formula is: The model reconstruction value CG is obtained, where a1 and a2 are both preset proportional coefficients; Compare the model reconstruction value CG with the model reconstruction threshold; If the model reconstruction value CG is greater than or equal to the model reconstruction threshold, it means that the overlap degree of the overlapping area is high and the point cloud is evenly distributed and the density is qualified, then no operation is performed; If the model reconstruction value CG is less than the model reconstruction threshold, it means that the overlap degree of the overlapping area is low and the point cloud distribution is uneven and the density is unqualified, then the two segmented line tracks corresponding to the overlapping area are selected for model reconstruction.

3. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 2 is characterized in that: The overlap degree CD is obtained as follows: Use feature point detection and description algorithms to extract key feature points in the model, and use feature point matching algorithms to find similar feature points in adjacent models; obtain the overlapping area between models through feature point indication; Obtain the area of ​​the overlapping region and the area of ​​the minimum circumscribed rectangle corresponding to the model, perform a ratio process on the area of ​​the overlapping region and the area of ​​the minimum circumscribed rectangle corresponding to the model to obtain the degree of overlap, and mark it as CD; The minimum enclosing rectangle refers to a minimum rectangle that can enclose all target points, and its width and height are determined by the maximum and minimum values ​​of the target points.

4. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 2 is characterized by: The point cloud distribution performance value DYB is obtained as follows: The protrusion overlap ratio CS and the protrusion overlap degree value CZ are processed by the formula: The point cloud density non-uniform value DJ is obtained, where s1 and s2 are both preset proportional coefficients; The point cloud density non-uniform value DJ and the point cloud deviation ratio are summed to obtain the point cloud distribution performance value, which is marked as DYB; The point cloud deviation ratio is obtained as follows: Point cloud processing software is used to perform point cloud analysis on the overlapping area to obtain the number of point cloud points in the overlapping area, and the point cloud density of the overlapping area is obtained by ratio processing between the number of point cloud points in the overlapping area and the area of ​​the overlapping area. The point cloud density of the overlapping area is subjected to difference processing with the point cloud set density of the overlapping area, and the absolute value of the difference is taken to obtain the point cloud density difference of the overlapping area. The point cloud density difference of the overlapping area is subjected to ratio processing with the point cloud set density of the overlapping area to obtain the point cloud deviation ratio.

5. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 4 is characterized in that: The method for obtaining the protrusion overlap ratio CS is as follows: The overlapping area is divided into several overlapping sub-areas with equal areas, the number of point clouds in the overlapping sub-areas is obtained, and the number of point clouds in the overlapping sub-areas is processed by ratio processing with the area of ​​the overlapping sub-areas to obtain the point cloud density of the overlapping sub-areas; The point cloud densities of all overlapping sub-areas are summed and averaged to obtain the point cloud density mean, the point cloud density in the overlapping sub-area is subtracted from the point cloud density mean, and the absolute value of the difference is taken to obtain the point cloud density deviation of the overlapping sub-area, the point cloud density deviations of all overlapping sub-areas are summed and averaged to obtain the point cloud density deviation mean, and the point cloud density deviation of the overlapping sub-area is compared with the point cloud density deviation mean; If the point cloud density deviation of the overlapping sub-region is greater than the mean value of the point cloud density deviation, the overlapping sub-region is marked as a prominent overlapping sub-region; If the point cloud density deviation of the overlapping sub-region is less than or equal to the mean value of the point cloud density deviation, the overlapping sub-region is marked as a non-prominent overlapping sub-region; The number of prominent overlapping sub-regions is counted and the ratio is processed with the number of overlapping sub-regions to obtain the prominent overlapping number ratio, which is marked as CS.

6. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 4 is characterized in that: The method for obtaining the protrusion overlap value CZ is as follows: The overlapping sub-area is subjected to difference processing with the mean of the point cloud density deviation to obtain the mean deviation of the point cloud density in the overlapping sub-area. The mean deviations of the point cloud density in all overlapping sub-areas are summed and averaged to obtain the relative deviation of the mean of the point cloud density. The relative deviation of the mean of the point cloud density is ratioed with the mean of the point cloud density deviation to obtain the value of the degree of prominent overlap, which is marked as CZ.

7. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 1 is characterized by: The process of collecting the holographic state data includes: A1, technical means of high-altitude measurement: drones conduct regular automatic route inspections to quickly detect the status information of cable trenches, turnout houses, and substation line ancillary facilities; A2, Technical means of dynamic track inspection: on-track machine vision inspection and structured light scanning. The on-track machine vision inspection system refers to an industrial camera and edge computer as the main components. It uses high-speed shooting and machine learning algorithms to identify the following information: structural seam identification, foreign body intrusion in functional areas, stator surface wear, lower structure defects, and record the mileage information and abnormality type of the identified location; use a structured light profile scanner to accurately scan the stator surface, measure the stator surface deviation and fold angle by point cloud processing, and describe the geometric shape deviation; A3. Select typical track beams to establish a fixed structural health monitoring system and build an all-weather fixed-point monitoring network for track structure and environmental conditions. The monitoring objects include: track beam end inclination, mid-span vibration response characteristics, surface temperature distribution, and environmental conditions.

8. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 1 is characterized by: The data missing value QP is obtained as follows: Setting a collection cycle, dividing the collection cycle into a number of time analysis nodes, acquiring holographic state data at the time analysis nodes, and comparing the holographic state data at the time analysis nodes with standard holographic state data; If the total amount of data contained in the holographic state data at the time analysis node is not equal to the total amount of data contained in the standard holographic state data, the time analysis node is marked as an abnormal acquisition node; If the total amount of data contained in the holographic state data at the time analysis node is equal to the total amount of data contained in the standard holographic state data, no processing is performed; Count the number of abnormal collection nodes and compare it with the number of time analysis nodes to obtain the abnormal collection number ratio, which is marked as SL; Perform difference processing on the total amount of data contained in the holographic state data at the abnormal acquisition node and the total amount of data contained in the standard holographic state data to obtain the amount of data missing at the abnormal acquisition node, sum and average the amount of data missing at all abnormal acquisition nodes to obtain the mean of data missing amount, perform ratio processing on the mean of data missing amount and the total amount of data contained in the standard holographic state data to obtain the abnormal acquisition missing ratio, and mark it as QS; The obtained abnormal collection quantity ratio SL and abnormal collection missing ratio QS are processed by data, and the formula is: The data missing value QP is obtained, where z1 and z2 are both preset proportional coefficients.

9. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 1 is characterized by: The process of performing data evaluation on the holographic state data according to the data missing value is: comparing the data missing value QP with the data missing threshold; If the data missing value QP is greater than or equal to the data missing threshold, it means that the holographic state data collected during the collection period is highly missing and unqualified; If the data missing value QP is less than the data missing threshold, it means that the holographic state data collected during the collection period has a low degree of missingness and is qualified.

10. The method for monitoring the state of a digital twin of a maglev line track integrating multi-dimensional information of air, rail and ground according to claim 1 is characterized by: The specific process of integrating and constructing the intelligent monitoring platform for the maglev line track is as follows: H1, use MATLAB or Python data analysis software to analyze the holographic state data of the maglev line track system, the specific analysis is: Track geometry: including track geometry, alignment, levelness, and height difference; Structural health status: monitoring the stress, strain, vibration and temperature parameters of track beams, supports and connectors; Environmental parameters: such as temperature, humidity, wind speed, rainfall; Equipment status: operating status and performance parameters of signal system, power supply system, and communication system equipment; H2, using decentralized edge computing technology, performs preliminary data preprocessing on the physical end to reduce the amount of data transmission, improve the efficiency of cloud-to-physical information transmission, and reduce cloud processing pressure. Specifically: Gross error determination: Perform a preliminary screening of the collected data at the object end to eliminate data with obvious errors; Data cleaning: remove duplicate data, fill missing values, process outliers, and improve data quality; H3 uses the cloud computing platform as the basis, imports the line track model, and completes the construction of the intelligent monitoring platform, including: Model display: Import the geometric model, behavior and rule model of the track on the cloud platform to display the structure and status of the maglev track system; Data download: Provides a data download interface, allowing users to download raw data or processed data as needed; Database management: Design and implement an efficient database management system to store and manage various data of the maglev line track system; Login and authority management: Provide user login and authority allocation functions to ensure system security and data confidentiality.

Images