Rail transit operation and maintenance method and system based on AR technology

Abstract

The present invention relates to the field of rail transit operation and maintenance technology, and in particular to a rail transit operation and maintenance method and system based on AR technology. The method comprises the following steps: performing virtual reality simulation and quality data collection and processing on the rail transit system through AR technology to obtain high-quality data on track conditions and high-quality data on rail vehicle operation; performing track structure visualization analysis on the high-quality data on track conditions to obtain a three-dimensional track structure status diagram; performing a first fault detection on the three-dimensional track structure status diagram to obtain track structure surface damage fault data; performing a second fault detection based on the high-quality data on track conditions, and performing fault location processing and fault repair labeling processing through AR technology to obtain a track fault maintenance area; performing scheduling and operation processing on the high-quality data on rail vehicle operation based on the track fault maintenance area to obtain rail vehicle scheduling and operation information data. The present invention can accurately manage the operation and maintenance of the rail transit system.

Description

Technical Field

[0001] The present invention relates to the field of rail transit operation and maintenance technology, and in particular to a rail transit operation and maintenance method and system based on AR technology. Background Art

[0002] Rail transit systems are an important part of modern urban life, and their operation and maintenance are crucial to ensuring smooth and safe urban transportation. At the same time, augmented reality (AR) technology can significantly improve the efficiency and quality of rail transit operation and maintenance by integrating real-time information, virtual simulation, remote support, and maintenance plan optimization. However, traditional rail transit operation and maintenance methods usually rely on manual inspections and a large amount of paper documents, which is inefficient, error-prone, and difficult to respond to fault maintenance in real time. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a rail transit operation and maintenance method based on AR technology to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a rail transit operation and maintenance method based on AR technology includes the following steps:

[0005] Step S1: Perform virtual reality simulation of the rail transit system through AR technology to obtain a virtual digital twin space of the rail transit; perform quality data collection and processing on the virtual digital twin space of the rail transit to obtain high-quality data on the track condition and high-quality data on the operation of rail vehicles;

[0006] Step S2: Performing track structure visualization analysis on the high-quality track condition data to obtain a three-dimensional track structure condition diagram; performing track structure damage analysis on the three-dimensional track structure condition diagram to obtain track structure damage data; performing damage and fault assessment on the three-dimensional track structure condition diagram based on the track structure damage data to obtain a track structure damage and fault factor;

[0007] Step S3: performing a first fault detection on the three-dimensional track structure condition map according to the track structure damage fault factor to obtain track structure surface damage fault data; performing potential fault assessment and analysis on the high-quality track condition data to obtain track potential fault identification factors; performing a second fault detection on the track structure surface damage fault data according to the track potential fault identification factors to obtain track structure potential fault data;

[0008] Step S4: Use AR technology to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area to obtain the rail vehicle dispatch and operation information data.

[0009] The present invention first uses AR technology to simulate the rail transit system in virtual reality to create a virtual digital twin space of the rail transit system, which allows operation and maintenance personnel to interact with the rail transit system in an augmented reality (AR) manner, which helps to provide a virtual reality environment that can be used for training, fault detection and analysis, simulated emergency situations, and vehicle operation and maintenance. At the same time, by collecting quality data on the virtual digital twin space of rail transit, high-quality track conditions and vehicle operation data can be obtained, which helps to monitor and fully understand the state of the rail system in real time, improves the visual management and data support of operations, and thus improves safety and efficiency. High-quality data has higher accuracy and credibility, which helps to ensure the reliability of system operation and maintenance decisions, thereby providing basic data guarantee for subsequent processing processes. Secondly, by performing track structure visualization analysis on high-quality track condition data, visual information data on the track structure status can be obtained, which includes the geometry, material properties, connection methods, etc. of the track, which can provide basic data for subsequent analysis, so that the geometry and structural characteristics of the track structure can be observed more clearly. In addition, the track structure damage analysis is also performed on the track three-dimensional structure status map to obtain detailed data about these damages, including information such as the type, degree, and location of the damage, which can provide a deeper understanding of the nature of the track structure problem and provide a basis for subsequent fault handling and maintenance. Moreover, the damage fault assessment of the track three-dimensional structure status map based on the track structure damage data obtained by analysis can comprehensively consider the relationship between structural damage and fault, thereby deriving the track structure damage fault factor. This factor can help operation and maintenance personnel evaluate the health of the track structure, take necessary maintenance and repair measures, and ensure the reliability and safety of the rail transit system. Then, by performing the first fault detection on the track three-dimensional structure status map according to the track structure damage fault factor, the accuracy of surface damage fault detection can be improved, ensuring that no surface damage fault problems are missed, thereby generating track structure surface damage fault data, which is helpful to evaluate the maintainability and safety of the track structure. And by performing potential fault assessment and analysis on high-quality track condition data, it is helpful to detect potential fault problems on the track, such as fatigue, deformation or other hidden faults. This step provides information data about potential track faults, provides a basis for preventive maintenance, can reduce unnecessary downtime and maintenance costs, and generates a comprehensive track potential fault identification factor, which quantifies the severity and urgency of potential faults and helps determine which potential faults need to be dealt with first. By using the track potential fault identification factor to perform a second fault detection on the track structure surface damage fault data, the existence of potential fault problems can be further confirmed, providing more conclusive evidence for maintenance decisions, helping to detect potential problems early, and thus reducing the occurrence of sudden failures.The reliability and safety of the rail transit system can be improved by jointly executing the first fault detection and the second fault detection. Finally, by using AR technology to locate the fault data of the track structure damage fault data and the potential fault data, it is highly accurate and real-time, so that the fault point of the track structure can be accurately located, which helps to quickly discover the fault problem of the track structure, improve maintenance efficiency, reduce maintenance costs, and ensure the reliability and safety of the rail transit system. In addition, by marking the fault repair of the fault point data of the track structure to ensure that no vehicle will pass through during the maintenance period, it is also possible to prevent future fault problems through this area, establish maintenance history data, track the evolution trend of the fault problem, take measures in advance, reduce future maintenance costs and downtime, and thus improve the maintainability and predictability of the rail transit system. By scheduling and operating high-quality data of rail vehicle operation according to the rail fault maintenance area, it is possible to ensure the safety and efficiency of rail vehicle operation in the maintenance area, which includes route adjustment, optimization of vehicle maintenance plan, etc., which helps to reduce the operational risks and costs during maintenance, thereby ensuring that the rail transit system can respond to maintenance problems of faults in real time and improve operation and maintenance efficiency.

[0010] Preferably, the present invention further provides a rail transit operation and maintenance system based on AR technology, which is used to execute the rail transit operation and maintenance method based on AR technology as described above, and the rail transit operation and maintenance system based on AR technology includes:

[0011] The rail transit data acquisition module is used to conduct virtual reality simulation of the rail transit system through AR technology to obtain a virtual digital twin space of rail transit; real-time acquisition and processing of the virtual digital twin space of rail transit is performed to obtain high-quality data on track conditions and rail vehicle operation;

[0012] The track structure damage assessment module is used to perform track structure visualization analysis on high-quality track condition data to obtain a three-dimensional track structure condition diagram; perform track structure damage analysis on the three-dimensional track structure condition diagram to obtain track structure damage data; perform damage and fault assessment on the three-dimensional track structure condition diagram based on the track structure damage data to obtain track structure damage and fault factors;

[0013] The track structure fault detection module is used to perform a first fault detection on the track three-dimensional structure condition map according to the track structure damage fault factor to obtain the track structure surface damage fault data; perform potential fault assessment and analysis on the high-quality track condition data to obtain the track potential fault identification factor; perform a second fault detection on the track structure surface damage fault data according to the track potential fault identification factor to obtain the track structure potential fault data;

[0014] The fault repair vehicle operation and maintenance module is used to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data through AR technology to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area, thereby obtaining the rail vehicle dispatch and operation information data.

[0015] In summary, the present invention provides a rail transit operation and maintenance system based on AR technology, which is composed of a rail transit data acquisition module, a track structure damage assessment module, a track structure fault detection module and a fault repair vehicle operation and maintenance module, and can realize any one of the rail transit operation and maintenance methods based on AR technology described in the present invention, and is used to combine the operations between the computer programs running on each module to realize a rail transit operation and maintenance method based on AR technology. The internal structures of the system cooperate with each other, and the visualization of real-time data and the three-dimensional superposition of track information are realized by introducing AR technology, which can improve the perception and decision-making ability of the operation and maintenance personnel. At the same time, the relationship between the damage to the track structure is evaluated, and the first fault detection and the second fault detection can be used to perform fault detection layer by layer from the shallow layer to the potential deep layer, so as to realize the accurate detection of the track structure fault, thereby improving the overall operation and maintenance efficiency of the rail transit system, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient rail transit operation and maintenance process, thereby simplifying the operation process of the rail transit operation and maintenance system based on AR technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0017] Figure 1 It is a schematic diagram of the steps of the rail transit operation and maintenance method based on AR technology of the present invention;

[0018] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0019] Figure 3 for Figure 2 Detailed step flow diagram of step S15;

[0020] Figure 4 A schematic diagram showing the abnormal exceeding of the track condition data points;

[0021] Figure 5 This is a schematic diagram of marking abnormal exceeding-standard points in rail vehicle operation data. DETAILED DESCRIPTION

[0022] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 5 The present invention provides a rail transit operation and maintenance method based on AR technology, the method comprising the following steps:

[0026] Step S1: Perform virtual reality simulation of the rail transit system through AR technology to obtain a virtual digital twin space of the rail transit; perform quality data collection and processing on the virtual digital twin space of the rail transit to obtain high-quality data on the track condition and high-quality data on the operation of rail vehicles;

[0027] Step S2: Performing track structure visualization analysis on the high-quality track condition data to obtain a three-dimensional track structure condition diagram; performing track structure damage analysis on the three-dimensional track structure condition diagram to obtain track structure damage data; performing damage and fault assessment on the three-dimensional track structure condition diagram based on the track structure damage data to obtain a track structure damage and fault factor;

[0028] Step S3: performing a first fault detection on the three-dimensional track structure condition map according to the track structure damage fault factor to obtain track structure surface damage fault data; performing potential fault assessment and analysis on the high-quality track condition data to obtain track potential fault identification factors; performing a second fault detection on the track structure surface damage fault data according to the track potential fault identification factors to obtain track structure potential fault data;

[0029] Step S4: Use AR technology to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area to obtain the rail vehicle dispatch and operation information data.

[0030] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the rail transit operation and maintenance method based on AR technology of the present invention. In this example, the steps of the rail transit operation and maintenance method based on AR technology include:

[0031] Step S1: Perform virtual reality simulation of the rail transit system through AR technology to obtain a virtual digital twin space of the rail transit; perform quality data collection and processing on the virtual digital twin space of the rail transit to obtain high-quality data on the track condition and high-quality data on the operation of rail vehicles;

[0032] The embodiment of the present invention projects the rail transit system into a real environment by using augmented reality (AR) technology, and designs a user-friendly virtual reality interface, including interactive elements, gesture recognition, etc., so that the operation and maintenance personnel can interact in the virtual reality environment through AR glasses to create a virtual digital twin space of the rail transit system, thereby obtaining a virtual digital twin space of rail transit. Then, by deploying a corresponding Internet of Things sensor network in the virtual digital twin space of rail transit, where the sensors include temperature sensors, humidity sensors, vibration sensors, cameras, etc., and by using the deployed physical network sensor network to collect data in the virtual digital twin space of rail transit in real time, at the same time, after performing noise reduction, anomaly detection and elimination, data dimension reduction and other processing on the collected data, a set of data quality standards are defined, including data accuracy, completeness and consistency, etc., and the processed data is quality screened to exclude low-quality or non-standard data, and finally high-quality track condition data and high-quality rail vehicle operation data are obtained.

[0033] Step S2: Performing track structure visualization analysis on the high-quality track condition data to obtain a three-dimensional track structure condition diagram; performing track structure damage analysis on the three-dimensional track structure condition diagram to obtain track structure damage data; performing damage and fault assessment on the three-dimensional track structure condition diagram based on the track structure damage data to obtain a track structure damage and fault factor;

[0034] The embodiment of the present invention uses data processing and analysis technology to identify and analyze high-quality data on track conditions to identify information data about the track structure condition in the high-quality data on track conditions, including information data such as the geometry, material properties, and connection methods of the track structure, and presents the analyzed information data in the form of graphical visualization to create a three-dimensional visualization graph of the track structure, thereby obtaining a three-dimensional structural condition diagram of the track. Then, by further analyzing the structural damage in the three-dimensional structural condition diagram of the track to determine the type, degree, and impact of the damage, the track structure damage data is obtained. Finally, the damage fault area in the three-dimensional structural condition diagram of the track is evaluated using the track structure damage data to determine the relationship between track structure damage and faults, and finally the track structure damage fault factor is obtained.

[0035] Step S3: performing a first fault detection on the three-dimensional track structure condition map according to the track structure damage fault factor to obtain track structure surface damage fault data; performing potential fault assessment and analysis on the high-quality track condition data to obtain track potential fault identification factors; performing a second fault detection on the track structure surface damage fault data according to the track potential fault identification factors to obtain track structure potential fault data;

[0036] The embodiment of the present invention firstly performs a first fault detection on the three-dimensional track structure condition map by using a laser fault scanning tool to preliminarily identify any obvious structural fault problems on the three-dimensional track structure condition map, such as cracks, corrosion or other visible damage faults. At the same time, the detected data is further analyzed by using the track structure damage fault factor to correct the false alarm of the first fault detection or identify more accurate surface damage information to ensure that no surface damage fault problems are missed, thereby obtaining the track structure surface damage fault data. Then, the high-quality track condition data is identified and analyzed by using data analysis technology to detect information identification factors that can identify hidden faults or potential fault problems in the high-quality track condition data, thereby obtaining the track potential fault identification factor. Finally, the track structure surface damage fault data is subjected to a second fault detection by using the track potential fault identification factor to further identify deeper fault problems from the track structure surface damage fault data, and finally obtain the track structure potential fault data.

[0037] Step S4: Use AR technology to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area to obtain the rail vehicle dispatch and operation information data.

[0038] The embodiment of the present invention uses augmented reality (AR) technology to overlay and visualize the actual track structure fault position of the track structure surface damage fault data and the track structure potential fault data, and analyzes the AR overlay data to accurately locate the position data of the fault point in the track structure (including the track damage fault position or the potential fault problem position), thereby obtaining the track structure fault point data. Then, the corresponding track structure fault point in the track structure fault point data is repaired to ensure that the fault problem of the track structure fault point can be solved in time, and the coordinate position of the maintenance point is marked with an early warning to mark that the track structure fault maintenance point is being repaired or has been repaired but not passed, thereby obtaining the track fault maintenance area. Finally, according to the position status of the track fault maintenance area, the corresponding vehicle operation status in the high-quality data of the rail vehicle operation is dispatched, including the route adjustment of the rail vehicle, the optimization of the operation plan of the vehicle maintenance area, etc., to ensure the safety and efficiency of the rail vehicle operation outside the maintenance area, and finally obtain the rail vehicle scheduling and operation information data.

[0039] The present invention first uses AR technology to simulate the rail transit system in virtual reality to create a virtual digital twin space of the rail transit system, which allows operation and maintenance personnel to interact with the rail transit system in an augmented reality (AR) manner, which helps to provide a virtual reality environment that can be used for training, fault detection and analysis, simulated emergency situations, and vehicle operation and maintenance. At the same time, by collecting quality data on the virtual digital twin space of rail transit, high-quality track conditions and vehicle operation data can be obtained, which helps to monitor and fully understand the state of the rail system in real time, improves the visual management and data support of operations, and thus improves safety and efficiency. High-quality data has higher accuracy and credibility, which helps to ensure the reliability of system operation and maintenance decisions, thereby providing basic data guarantee for subsequent processing processes. Secondly, by performing track structure visualization analysis on high-quality track condition data, visual information data on the track structure status can be obtained, which includes the geometry, material properties, connection methods, etc. of the track, which can provide basic data for subsequent analysis, so that the geometry and structural characteristics of the track structure can be observed more clearly. In addition, the track structure damage analysis is also performed on the track three-dimensional structure status map to obtain detailed data about these damages, including information such as the type, degree, and location of the damage, which can provide a deeper understanding of the nature of the track structure problem and provide a basis for subsequent fault handling and maintenance. Moreover, the damage fault assessment of the track three-dimensional structure status map based on the track structure damage data obtained by analysis can comprehensively consider the relationship between structural damage and fault, thereby deriving the track structure damage fault factor. This factor can help operation and maintenance personnel evaluate the health of the track structure, take necessary maintenance and repair measures, and ensure the reliability and safety of the rail transit system. Then, by performing the first fault detection on the track three-dimensional structure status map according to the track structure damage fault factor, the accuracy of surface damage fault detection can be improved, ensuring that no surface damage fault problems are missed, thereby generating track structure surface damage fault data, which is helpful to evaluate the maintainability and safety of the track structure. And by performing potential fault assessment and analysis on high-quality track condition data, it is helpful to detect potential fault problems on the track, such as fatigue, deformation or other hidden faults. This step provides information data about potential track faults, provides a basis for preventive maintenance, can reduce unnecessary downtime and maintenance costs, and generates a comprehensive track potential fault identification factor, which quantifies the severity and urgency of potential faults and helps determine which potential faults need to be dealt with first. By using the track potential fault identification factor to perform a second fault detection on the track structure surface damage fault data, the existence of potential fault problems can be further confirmed, providing more conclusive evidence for maintenance decisions, helping to detect potential problems early, and thus reducing the occurrence of sudden failures.The reliability and safety of the rail transit system can be improved by jointly executing the first fault detection and the second fault detection. Finally, by using AR technology to locate the fault data of the track structure damage fault data and the potential fault data, it is highly accurate and real-time, so that the fault point of the track structure can be accurately located, which helps to quickly discover the fault problem of the track structure, improve maintenance efficiency, reduce maintenance costs, and ensure the reliability and safety of the rail transit system. In addition, by marking the fault repair of the fault point data of the track structure to ensure that no vehicle will pass through during the maintenance period, it is also possible to prevent future fault problems through this area, establish maintenance history data, track the evolution trend of the fault problem, take measures in advance, reduce future maintenance costs and downtime, and thus improve the maintainability and predictability of the rail transit system. By scheduling and operating high-quality data of rail vehicle operation according to the rail fault maintenance area, it is possible to ensure the safety and efficiency of rail vehicle operation in the maintenance area, which includes route adjustment, optimization of vehicle maintenance plan, etc., which helps to reduce the operational risks and costs during maintenance, thereby ensuring that the rail transit system can respond to maintenance problems of faults in real time and improve operation and maintenance efficiency.

[0040] Preferably, step S1 comprises the following steps:

[0041] Step S11: Perform three-dimensional geographic scanning processing on the rail transit system to obtain high-precision three-dimensional geographic data of the rail transit;

[0042] Step S12: performing three-dimensional rendering modeling processing on the high-precision three-dimensional geographic data of rail transit to obtain a high-precision three-dimensional model of rail transit;

[0043] Step S13: Perform virtual reality simulation on the high-precision three-dimensional model of rail transit through AR technology to obtain a virtual digital twin space of rail transit;

[0044] Step S14: by deploying an IoT sensor network in the rail transit virtual digital twin space, and performing real-time collection and processing on the rail transit virtual digital twin space according to the physical network sensor network, initial track condition data and initial rail vehicle operation data are obtained;

[0045] Step S15: Perform quality screening on the initial track condition data and the initial track vehicle operation data to obtain high-quality track condition data and high-quality track vehicle operation data.

[0046] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0047] Step S11: Perform three-dimensional geographic scanning processing on the rail transit system to obtain high-precision three-dimensional geographic data of the rail transit;

[0048] The embodiment of the present invention uses high-precision three-dimensional geographic scanning equipment (such as lidar, camera, GPS, etc.) to perform a full-coverage scan of the rail transit system to obtain high-precision three-dimensional geographic information data in the area to which the rail transit system belongs, including detailed information on tracks, stations, signal equipment, and the surrounding environment, and finally obtains high-precision three-dimensional geographic data of the rail transit.

[0049] Step S12: performing three-dimensional rendering modeling processing on the high-precision three-dimensional geographic data of rail transit to obtain a high-precision three-dimensional model of rail transit;

[0050] The embodiment of the present invention converts the high-precision three-dimensional geographic data of rail transit into a high-precision three-dimensional solid model by using three-dimensional modeling software (such as AutoCAD, SketchUp, Blender, etc.), and adds texture and color to the model to increase the sense of reality, thereby finally obtaining a high-precision three-dimensional model of rail transit.

[0051] Step S13: Perform virtual reality simulation on the high-precision three-dimensional model of rail transit through AR technology to obtain a virtual digital twin space of rail transit;

[0052] The embodiment of the present invention projects a high-precision three-dimensional model of rail transit into a real environment by using augmented reality (AR) technology, and designs a user-friendly virtual reality interface, including interactive elements, gesture recognition, etc., so that operation and maintenance personnel can interact in the virtual reality environment through AR glasses to create a virtual digital twin space of the rail transit system, and finally obtain a virtual digital twin space of the rail transit.

[0053] Step S14: by deploying an IoT sensor network in the rail transit virtual digital twin space, and performing real-time collection and processing on the rail transit virtual digital twin space according to the physical network sensor network, initial track condition data and initial rail vehicle operation data are obtained;

[0054] The embodiment of the present invention deploys a corresponding Internet of Things sensor network in the virtual digital twin space of rail transit, where the sensors include temperature sensors, humidity sensors, vibration sensors, cameras, etc., to monitor the track conditions and vehicle operations in the virtual digital twin space of rail transit in real time. Then, the data in the virtual digital twin space of rail transit is collected in real time by using the deployed physical network sensor network, and finally the initial track condition data and the initial rail vehicle operation data are obtained.

[0055] Step S15: Perform quality screening on the initial track condition data and the initial track vehicle operation data to obtain high-quality track condition data and high-quality track vehicle operation data.

[0056] The embodiment of the present invention defines a set of data quality standards, including data accuracy, completeness and consistency, after performing noise reduction, anomaly detection and elimination, and data dimension reduction on the initial track condition data and the initial rail vehicle operation data. Then, the processed data is quality screened according to the defined data quality standards to exclude low-quality or non-compliant data, and finally high-quality track condition data and high-quality rail vehicle operation data are obtained.

[0057] The present invention first performs a three-dimensional geographic scanning process on the rail transit system, which means that the three-dimensional geography of the rail transit system can be scanned by using a high-precision three-dimensional geographic scanning instrument to obtain high-precision three-dimensional geographic data, which can include detailed information on tracks, stations, signal equipment and surrounding environment, so that accurate three-dimensional geographic information of rail transit can be provided for subsequent processing, which is helpful for planning, designing and maintaining rail transit systems, while improving safety and efficiency. Secondly, a high-precision three-dimensional model is created by performing three-dimensional rendering modeling on the high-precision three-dimensional geographic data of rail transit. This model can present various aspects of the rail transit system with high resolution, so that operation and maintenance personnel can better understand the structure and characteristics of the rail transit system, and can also provide a visual rail transit system model tool, which is helpful for training, planning, simulation and decision support. Then, the high-precision three-dimensional model of rail transit is simulated by using AR technology to create a virtual digital twin space of the rail transit system, which allows operation and maintenance personnel to interact with the rail transit system in an augmented reality (AR) manner, which helps to provide a virtual reality environment that can be used for training, fault detection analysis, simulated emergency situations and vehicle operation and maintenance. Next, by deploying the IoT sensor network in the rail transit virtual digital twin space, real-time data collection and processing of the rail transit virtual digital twin space can be realized, including sensors monitoring track conditions and vehicle operation. Real-time data collection through the IoT sensor network can realize real-time monitoring and collection of rail transit data, which is helpful for rapid detection and improvement of fault problems in the subsequent process to improve the safety of rail transit. Finally, by quality screening and processing the initial data of track conditions and initial data of rail vehicle operation, possible errors, abnormal data and noise can be eliminated to obtain high-quality data. High-quality data has higher accuracy and credibility, which helps to ensure the reliability of system operation and maintenance decisions, thereby providing basic data guarantee for subsequent processing processes.

[0058] Preferably, step S15 comprises the following steps:

[0059] Step S151: performing noise reduction processing on the initial track condition data and the initial track vehicle operation data to obtain track condition noise reduction data and track vehicle operation noise reduction data;

[0060] Step S152: performing anomaly detection and analysis on the track condition noise reduction data and the rail vehicle operation noise reduction data to obtain track condition abnormality data and rail vehicle operation abnormality data;

[0061] Step S153: using an abnormal peak detection calculation formula to perform abnormal calculation on the track condition abnormal data and the rail vehicle operation abnormal data to obtain an abnormal peak value of the track condition data and an abnormal peak value of the rail vehicle operation data;

[0062] Step S154: performing peak identification and filtering on the abnormal track condition data and the abnormal rail vehicle operation data according to the abnormal peak values ​​of the track condition data and the abnormal rail vehicle operation data, to obtain abnormal track condition filtered data and abnormal rail vehicle operation filtered data;

[0063] Step S155: performing data dimensionality reduction processing on the track condition abnormality filtered data and the rail vehicle operation abnormality filtered data to obtain track condition dimensionality reduced data and rail vehicle operation dimensionality reduced data;

[0064] Step S156: Perform quality assessment and screening on the track condition dimensionality reduction data and the rail vehicle operation dimensionality reduction data to obtain high-quality track condition data and high-quality rail vehicle operation data.

[0065] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S15 in FIG. 1 , in this embodiment, step S15 includes the following steps:

[0066] Step S151: performing noise reduction processing on the initial track condition data and the initial track vehicle operation data to obtain track condition noise reduction data and track vehicle operation noise reduction data;

[0067] The embodiment of the present invention performs noise reduction processing on the initial track condition data and the initial rail vehicle operation data by using noise reduction technology (such as filters, smoothing algorithms, interpolation, etc.) to reduce random or high-frequency noise in the initial track condition data and the initial rail vehicle operation data, and finally obtains the noise-reduced track condition data and the noise-reduced rail vehicle operation data.

[0068] Step S152: performing anomaly detection and analysis on the track condition noise reduction data and the rail vehicle operation noise reduction data to obtain track condition abnormality data and rail vehicle operation abnormality data;

[0069] The embodiment of the present invention uses an anomaly detection algorithm model to analyze the track condition noise reduction data and the rail vehicle operation noise reduction data after noise reduction processing to identify abnormal data in the track condition noise reduction data and the rail vehicle operation noise reduction data, and finally obtains abnormal track condition data and abnormal rail vehicle operation data.

[0070] Step S153: using an abnormal peak detection calculation formula to perform abnormal calculation on the track condition abnormal data and the rail vehicle operation abnormal data to obtain an abnormal peak value of the track condition data and an abnormal peak value of the rail vehicle operation data;

[0071] The embodiment of the present invention forms a suitable abnormal peak detection calculation formula by combining the time variable parameter of abnormal calculation, abnormal amplitude adjustment parameter, abnormal attenuation control parameter, abnormal distribution mean, abnormal distribution standard deviation and related parameters to perform abnormal calculation on track condition abnormal data and rail vehicle operation abnormal data, so as to quantify the abnormal degree of track condition abnormal data and rail vehicle operation abnormal data, and finally obtain the abnormal peak of track condition data and the abnormal peak of rail vehicle operation data. In addition, the abnormal peak detection calculation formula can also use any abnormal peak degree detection algorithm in the field to replace the abnormal calculation process, and is not limited to the abnormal peak detection calculation formula.

[0072] Step S154: performing peak identification and filtering on the abnormal track condition data and the abnormal rail vehicle operation data according to the abnormal peak values ​​of the track condition data and the abnormal rail vehicle operation data, to obtain abnormal track condition filtered data and abnormal rail vehicle operation filtered data;

[0073] The embodiment of the present invention judges the abnormal peak values ​​of the track condition data and the abnormal peak values ​​of the rail vehicle operation data respectively according to the preset abnormal peak measurement standard, and filters out the abnormal track condition data and the abnormal rail vehicle operation data corresponding to the preset abnormal peak measurement standard from the overall data set, and finally obtains the track condition abnormality filtered data and the rail vehicle operation abnormality filtered data.

[0074] Step S155: performing data dimensionality reduction processing on the track condition abnormality filtered data and the rail vehicle operation abnormality filtered data to obtain track condition dimensionality reduced data and rail vehicle operation dimensionality reduced data;

[0075] The embodiment of the present invention processes the track condition anomaly filtered data and the rail vehicle operation anomaly filtered data by using dimensionality reduction technology (such as principal component analysis (PCA) or t-distributed stochastic neighbor embedding (t-SNE)) to reduce the data dimension and complexity of the track condition anomaly filtered data and the rail vehicle operation anomaly filtered data, and finally obtains the track condition reduced dimensionality data and the rail vehicle operation reduced dimensionality data.

[0076] Step S156: Perform quality assessment and screening on the track condition dimensionality reduction data and the rail vehicle operation dimensionality reduction data to obtain high-quality track condition data and high-quality rail vehicle operation data.

[0077] The embodiment of the present invention defines a set of quality assessment criteria, including data accuracy, completeness and consistency, and then evaluates the reduced track condition data and rail vehicle operation data according to the defined quality assessment criteria to screen out high-quality data and eliminate low-quality data, ultimately obtaining high-quality track condition data and high-quality rail vehicle operation data.

[0078] The present invention first performs noise reduction processing on the initial track condition data and the initial rail vehicle operation data, which means that by applying noise signal processing and data noise reduction technology, the undesirable fluctuations and noise interference in the data caused by sensor errors, environmental noise or other factors are eliminated or reduced, so that more stable and accurate track condition and vehicle operation data can be obtained, which helps to improve the reliability and availability of the data. At the same time, by performing abnormal detection analysis on the track condition noise reduction data and the rail vehicle operation noise reduction data after noise reduction processing, this can help identify those abnormal data points, which may indicate that the sensor detection process has errors, errors or other abnormal conditions. By detecting these abnormal data, a basic data source can be provided for subsequent processing processes, thereby improving the safety and reliability of track condition data and rail vehicle operation data. Secondly, by using the abnormal peak detection calculation formula to perform further abnormal calculations on the track condition abnormal data and the rail vehicle operation abnormal data, this step helps to quantify the degree and nature of the abnormal data, such as the amplitude and duration of the abnormality, and can provide basic information data for subsequent processing processes. Then, the abnormal track condition data and the abnormal rail vehicle operation data are peak identified and filtered according to the calculated abnormal peaks of the track condition data and the abnormal rail vehicle operation data, which means that those unnecessary or irrelevant abnormal data points can be deleted to obtain cleaner and more orderly data, which helps to improve the efficiency and accuracy of anomaly detection and reduce false positives. Next, the data after abnormal filtering is processed by dimensionality reduction to reduce the complexity and storage requirements of the data, which can be achieved by applying dimensionality reduction algorithms such as principal component analysis (PCA) or t-distributed random neighbor embedding (t-SNE). Dimensionality reduction can help better understand the structure of the data, reduce redundant information, and improve the efficiency of data analysis and visualization. Finally, the track condition and vehicle operation data after dimensionality reduction are screened for quality assessment to obtain high-quality data. This includes evaluating the consistency, completeness and accuracy of the data to select the most suitable data subset and support decision making, modeling and analysis in subsequent processes. High-quality data helps ensure the reliability and safety of the system while improving the quality and effectiveness of decision-making.

[0079] Preferably, the abnormal peak detection calculation formula in step S153 is specifically:

[0080]

[0081]

[0082] Where P 1 (x a , t f ) is the abnormal peak value of track condition data, n is the number of abnormal track condition data, xa is the value of the ath track condition abnormal data, t f is the upper limit of the integral time range for abnormal calculation, t 0 is the lower limit of the integral time range for abnormal calculation, τ is the integral time parameter for abnormal calculation, exp is the exponential function, ρ 1 is the abnormal amplitude adjustment parameter of track condition abnormal data, φ 1 is the abnormal attenuation control parameter of track condition abnormal data, μ a is the mean of the abnormal distribution of the a-th track condition abnormal data, σ a is the standard deviation of the abnormal distribution of the a-th track condition abnormal data, ∈ 1 is the correction value of the abnormal peak value of the track condition data, P 2 (y b ,t f ) is the abnormal peak value of rail vehicle operation data, m is the number of rail vehicle operation abnormal data, yb is the value of the b-th rail vehicle operation abnormal data, ρ 2 is the abnormal amplitude adjustment parameter of the abnormal data of rail vehicle operation, φ 2 is the abnormal attenuation control parameter of the abnormal data of rail vehicle operation, μ b is the mean of the abnormal distribution of the abnormal data of the b-th rail vehicle operation, σ b is the standard deviation of the abnormal distribution of the b-th rail vehicle operation abnormal data, ∈ 2 It is the correction value of the abnormal peak value of rail vehicle operation data.

[0083] The present invention constructs an abnormal peak detection calculation formula for performing abnormal calculations on abnormal track condition data and abnormal rail vehicle operation data. The abnormal peak detection calculation formula adjusts the abnormal amplitude of the abnormal data by using an abnormal amplitude adjustment parameter, controls the attenuation degree of the abnormal data by using an abnormal attenuation control parameter, measures the distribution of the abnormal data by using an abnormal distribution mean and an abnormal distribution standard deviation, and also introduces a correction value to correct the error of the calculation result and other influencing factors. In summary, the abnormal peak detection calculation formula comprehensively considers factors such as the amplitude, attenuation, and distribution of the abnormality, and can be used to identify and measure abnormal peaks, help identify abnormal conditions and improve the quality of data, so as to better understand and process abnormal data. The formula considers the number n of track condition abnormal data, the value x of the ath track condition abnormal data, and the number of track condition abnormal data. a , the upper limit of the integral time range of abnormal calculation t f , the lower limit of the integral time range for abnormal calculation t 0 , the integral time parameter τ for anomaly calculation, the exponential function exp, the anomaly amplitude adjustment parameter ρ for track condition anomaly data 1 , the abnormal attenuation control parameter φ of the track condition abnormal data1 , the mean value of the abnormal distribution of the a-th track condition abnormal data μ a And the standard deviation σ of the abnormal distribution of the a-th track condition abnormal data a It constitutes an abnormal peak value P of track condition data. 1 (x a , t f )’s functional relationship:

[0084]

[0085] In addition, the number of rail vehicle operation abnormal data m, the value y of the b-th rail vehicle operation abnormal data b , the abnormal amplitude adjustment parameter ρ of the abnormal data of rail vehicle operation 2 , the abnormal attenuation control parameter φ of the abnormal data of rail vehicle operation 2 , the mean value μ of the abnormal distribution of the abnormal data of the b-th rail vehicle operation b and the standard deviation σ of the abnormal distribution of the b-th rail vehicle operation abnormal data b It constitutes an abnormal peak value P of rail vehicle operation data. 2 (y b , t f )’s functional relationship:

[0086]

[0087] This formula can realize the abnormal calculation process of track condition abnormal data and rail vehicle operation abnormal data. At the same time, the correction value of the abnormal peak value of the track condition data ∈ 1 and the correction value of the abnormal peak value of rail vehicle operation data ∈ 2 The introduction of can be adjusted according to the error situation in the calculation process, thereby improving the accuracy and stability of the abnormal peak detection calculation formula.

[0088] Preferably, step S154 includes the following steps:

[0089] Step S1541: Plotting peak graphs of abnormal peak values ​​of track condition data and abnormal peak values ​​of rail vehicle operation data to obtain abnormal peak graphs of track condition data and abnormal peak graphs of rail vehicle operation data;

[0090] The embodiment of the present invention uses a graphic visualization tool or software to graphically visualize the abnormal peak values ​​of the track condition data and the abnormal peak values ​​of the rail vehicle operation data calculated according to each abnormal data, so as to intuitively understand the abnormal distribution of the abnormal peak values ​​of the track condition data and the abnormal peak values ​​of the rail vehicle operation data, and finally obtain the abnormal peak graph of the track condition data and the abnormal peak graph of the rail vehicle operation data.

[0091] Step S1542: Peaks of the track condition data abnormal peak graph and the rail vehicle operation data abnormal peak graph are identified and marked according to a preset standard abnormal peak curve to obtain abnormal exceeding points of the track condition data and the rail vehicle operation data abnormal exceeding points;

[0092] The embodiment of the present invention uses a preset standard abnormal peak curve (including a standard abnormal peak curve of track condition data and a standard abnormal peak curve of rail vehicle operation data) to perform boundary recognition on the abnormal peak graph of track condition data and the abnormal peak graph of rail vehicle operation data, so as to identify data points exceeding the curve in the abnormal peak graph of track condition data and the abnormal peak graph of rail vehicle operation data, and mark the abnormal peak points exceeding the standard abnormal peak curve, and finally obtain the abnormal exceeding point of track condition data (such as Figure 4 as shown) and abnormal exceeding of the rail vehicle operation data (as shown Figure 5 shown).

[0093] Step S1543: performing abnormal fluctuation detection on the abnormal peak graph of the track condition data and the abnormal peak graph of the rail vehicle operation data to obtain the abnormal fluctuation area of ​​the track condition data and the abnormal fluctuation area of ​​the rail vehicle operation data;

[0094] The embodiment of the present invention detects and analyzes the abnormal peak graph of track condition data and the abnormal peak graph of rail vehicle operation data by using methods such as time series analysis and abnormal filtering technology, so as to detect the abnormal peak point area with drastic abnormal fluctuations in the abnormal peak graph of track condition data and the abnormal peak graph of rail vehicle operation data within a period of time, and finally obtains the abnormal fluctuation area of ​​track condition data and the abnormal fluctuation area of ​​rail vehicle operation data.

[0095] Step S1544: merging the track condition data abnormal exceeding points and the track condition data abnormal fluctuation areas to obtain the track condition abnormal area, and filtering out the track condition abnormal data corresponding to the track condition abnormal area to obtain track condition abnormal filtered data;

[0096] The embodiment of the present invention combines the marked track condition data abnormal exceeding point and the track condition data abnormal fluctuation area around the point to comprehensively consider the local abnormal phenomenon in the track condition data abnormal peak diagram, thereby obtaining the track condition abnormal area. Then, the corresponding track condition abnormal data in the combined track condition abnormal area is removed from the overall data set, and finally the track condition abnormality filtered data is obtained.

[0097] Step S1545: The rail vehicle operation data abnormal exceeding points and the rail vehicle operation data abnormal fluctuation areas are merged to obtain the rail vehicle operation abnormal area, and the rail vehicle operation abnormal data corresponding to the rail vehicle operation abnormal area is filtered out to obtain the rail vehicle operation abnormal filtered data.

[0098] The embodiment of the present invention merges the marked rail vehicle operation data abnormal exceeding point and the rail vehicle operation data abnormal fluctuation area appearing around the point, so as to comprehensively consider the local abnormal phenomenon in the rail vehicle operation data abnormal peak diagram, thereby obtaining the rail vehicle operation abnormal area. Then, the rail vehicle operation abnormal data corresponding to the merged rail vehicle operation abnormal area is removed from the overall data set, and finally the rail vehicle operation abnormality filtered data is obtained.

[0099] The present invention firstly draws peak graphs for the abnormal peak values ​​of the track condition data and the abnormal peak values ​​of the rail vehicle operation data obtained by calculation, so as to draw corresponding abnormal peak graphs, so as to intuitively understand the abnormal distribution of the track condition data and the rail vehicle operation data. The peak graphs obtained by drawing can provide a visualization basis for the subsequent analysis process, so that the characteristics of the abnormal data are clearer and more concise, which is helpful for further research and processing. Secondly, by using a preset standard abnormal peak curve to identify and mark the abnormal peak graph of the track condition data and the abnormal peak graph of the rail vehicle operation data, the abnormal exceeding points that deviate from the normal range in the abnormal peak graph of the track condition data and the abnormal peak graph of the rail vehicle operation data can be identified and marked. This marking process makes the abnormal data with a large degree of abnormality easier to identify, and provides basic information for subsequent abnormal processing. Then, by performing abnormal fluctuation detection on the abnormal peak graph of the track condition data and the abnormal peak graph of the rail vehicle operation data, it means not only focusing on the abnormality of a single data point, but also focusing on the volatility of the data. By detecting the abnormal fluctuation area, it is possible to find those abnormal data that fluctuate violently over a period of time, which indicates that the rail transit system has an abnormal situation in a specific time period. Next, by regionally merging the abnormal exceeding points and abnormal fluctuation areas of the track condition data, this merging method can comprehensively consider the local abnormal phenomena to more comprehensively understand the distribution of abnormal data. Then, by filtering the abnormal track condition data corresponding to these merged abnormal areas, those abnormal fluctuations or exceeding data can be removed, making the final data cleaner and more reliable. Finally, similarly, by regionally merging the abnormal exceeding points of the rail vehicle operation data and the abnormal fluctuation areas of the rail vehicle operation data, and filtering the corresponding rail vehicle operation abnormal data, it can ensure the comprehensive processing of rail vehicle operation abnormalities, and further improve the quality and availability of the data. In summary, a systematic abnormal data processing process is established through the steps of drawing peak graphs, identifying abnormal exceeding points, detecting abnormal fluctuations, regional merging and data filtering, which can accurately and comprehensively identify and process abnormal situations in track condition and vehicle operation data, which not only improves the accuracy and credibility of data analysis, but also provides strong support for subsequent decision-making and fault maintenance.

[0100] Preferably, step S2 comprises the following steps:

[0101] Step S21: performing track structure identification analysis on the high-quality track condition data to obtain track structure condition information data;

[0102] The embodiment of the present invention uses data processing and analysis technology to identify and analyze high-quality track condition data to identify information data about the track structure condition in the high-quality track condition data, including information data such as the geometry, material properties, and connection methods of the track structure, and finally obtains track structure condition information data.

[0103] Step S22: performing three-dimensional visualization analysis on the track structure status information data to obtain a three-dimensional track structure status diagram;

[0104] The embodiment of the present invention analyzes the three-dimensional information of the track structure in the track structure status information data, and presents the analyzed three-dimensional information of the track structure in the form of graphic visualization to create a three-dimensional visualization graph of the track structure, and finally obtains a three-dimensional track structure status diagram.

[0105] Step S23: performing structural damage scanning processing on the three-dimensional track structure status map to obtain the track structure damage area;

[0106] The embodiment of the present invention uses a laser scanning instrument to scan and process the three-dimensional structural status map of the track, so as to scan, identify and mark the areas with surface damage in the three-dimensional structural status map of the track, including cracks, corrosion, wear, deformation, etc., and finally obtain the damaged area of ​​the track structure.

[0107] Step S24: performing a track structure damage analysis on the track three-dimensional structure condition diagram according to the track structure damage area to obtain track structure damage data;

[0108] The embodiment of the present invention further analyzes the three-dimensional structural status map of the track based on the scanned track structure damage area to determine the type, degree and impact of the damage, and identifies and quantifies the damage data of the track structure damage area by using image processing and analysis technology, including information data such as the type, degree, and location of the damage, and finally obtains the track structure damage data.

[0109] Step S25: performing fault correlation calculation on the track structure damage data using a structural damage fault correlation calculation formula to obtain a structural damage fault correlation degree coefficient;

[0110] The embodiment of the present invention forms a suitable structural damage fault association calculation formula by combining the time variable parameter of fault association calculation, the damage index parameter of the structural damage part, the damage delay parameter, the damage attenuation parameter, the fault index parameter of the structural fault part, the fault influence smoothing parameter, the fault influence coefficient, the time correlation attenuation coefficient, the correlation influence index parameter of the damage fault correlation influence item, the correlation influence weight parameter and related parameters to perform fault association calculation on the track structure damage data to quantify the correlation degree between the track structure damage and the fault, and finally obtain the structural damage fault correlation degree coefficient. In addition, the structural damage fault association calculation formula can also use any correlation detection algorithm in the field to replace the fault association calculation process, and is not limited to the structural damage fault association calculation formula.

[0111] Step S26: performing damage and fault assessment on the track three-dimensional structural condition diagram according to the structural damage and fault correlation coefficient to obtain the track structural damage and fault factor.

[0112] The embodiment of the present invention evaluates the three-dimensional structural status diagram of the track by using the calculated structural damage and fault correlation coefficient to determine the relationship between the track structure damage and fault, and determines the damage-fault impact correlation relationship of each damaged area in the three-dimensional structural status diagram of the track according to the size of the structural damage and fault correlation coefficient, and finally obtains the track structure damage and fault factor.

[0113] The present invention firstly obtains information data on the track structure condition by performing track structure identification analysis on high-quality track condition data. These data include the geometry, material properties, connection mode, etc. of the track structure, which can provide a basis for subsequent analysis. By analyzing the track structure, the overall condition of the track, including potential structural problems, can be understood. At the same time, by performing three-dimensional visualization analysis on the track structure condition information data, the purpose of this step is to present the structure of the track in the form of a three-dimensional graphic, so that the geometry and structural characteristics of the track can be observed more clearly. Three-dimensional visualization not only provides more intuitive visual information, but also helps to detect potential structural problems, such as bending, breaking or corrosion. Secondly, by performing structural damage scanning processing on the track three-dimensional structural condition map, it means that the damaged areas in the track structure, such as cracks, wear or other defects, can be found and identified by scanning, which helps to focus on the potential damage problem areas, thereby improving the efficiency of fault detection. Then, according to the scanned track structure damage area, the track three-dimensional structural condition map is subjected to track structure damage analysis to obtain detailed data on these damages, including information such as the type, degree, and location of the damage, so as to provide a deeper understanding of the nature of the track structure problem and provide a basis for subsequent fault handling and maintenance. Next, the fault correlation calculation of the track structure damage data is performed by using a suitable structural damage fault correlation calculation formula, which aims to evaluate the degree of correlation between damage and fault. By calculating the correlation coefficient, the potential impact of track structure damage on track structure performance and safety can be determined. Finally, the damage and fault evaluation of the track three-dimensional structural condition diagram is performed based on the calculated structural damage fault correlation coefficient. The goal of this step is to comprehensively consider the relationship between structural damage and fault, so as to derive the track structure damage fault factor. This factor can help operation and maintenance personnel evaluate the health of the track structure, take necessary maintenance and repair measures, and ensure the reliability and safety of the rail transit system.

[0114] Preferably, the structural damage fault correlation calculation formula in step S25 is specifically:

[0115]

[0116] Where R is the structural damage fault correlation coefficient, T is the time range parameter of fault correlation calculation, t is the integral time variable of fault correlation calculation, N is the number of structural damage parts in the track structure damage data, and s i (t) is the damage index parameter of the i-th structural damage location in the track structure damage data at time t, λ i (t) is the damage delay parameter of the i-th structural damage location in the track structure damage data at time t, α iis the damage attenuation parameter of the i-th structural damage location in the track structure damage data, M is the number of structural failure locations in the track structure damage data, c j (t) is the fault index parameter of the jth structural fault location at time t in the track structure damage data, γ j (t) is the fault influence smoothing parameter of the jth structural fault location at time t in the track structure damage data, β j is the fault influence coefficient of the jth structural fault location in the track structure damage data, δ 1 is the time-correlated attenuation coefficient, L is the number of damage fault correlation influence items, u k (t) is the correlation influence index parameter of the kth damage fault correlation influence item at time t, θ k is the correlation influence weight parameter of the kth damage fault correlation influence item, and η is the correction value of the structural damage fault correlation degree coefficient.

[0117] The present invention constructs a structural damage fault correlation calculation formula for performing fault correlation calculation on track structure damage data. The structural damage fault correlation calculation formula uses a structural damage index parameter to represent the intensity or degree of structural damage, a damage delay parameter to represent the delayed effect of structural damage, a damage attenuation parameter to represent the degree of attenuation of structural damage over time, a fault index parameter to represent the intensity or degree of fault, a fault impact smoothing parameter to represent the smoothing effect of fault, a fault impact coefficient to represent the degree of influence of fault on structural damage, and a time-related attenuation coefficient to represent a time-related attenuation parameter to represent the attenuation effect of time on the degree of correlation. At the same time, the contribution weight of different influence items to the degree of correlation is represented by using an association impact weight parameter. In summary, the calculation process of the formula is to substitute the above parameters and related parameters for integral operation to calculate a correlation coefficient, which can be used to evaluate the correlation between the structural damage and fault of the track, so as to be used for further structural damage fault assessment. Therefore, this formula fully considers the structural damage fault correlation coefficient R, the time range parameter T of the fault correlation calculation, the integral time variable t of the fault correlation calculation, the number N of structural damage parts in the track structure damage data, and the damage index parameter s of the i-th structural damage part in the track structure damage data at time t. i (t), the damage delay parameter λ of the i-th structural damage location in the track structure damage data at time t i (t), the damage attenuation parameter α of the i-th structural damage location in the track structure damage data i , the number of structural fault locations in the track structure damage data M, the fault index parameter c of the jth structural fault location in the track structure damage data at time t j(t), the fault effect smoothing parameter γ of the jth structural fault location in the track structure damage data at time t j (t), the failure influence coefficient β of the jth structural fault location in the track structure damage data j , time-dependent attenuation coefficient δ 1 , the number of damage fault associated impact items L, the associated impact index parameter u of the kth damage fault associated impact item at time t k (t), the correlation influence weight parameter θ of the kth damage fault correlation influence item k , the correction value η of the structural damage failure correlation coefficient, constitutes a functional relationship based on the mutual correlation between the above parameters:

[0118]

[0119] The formula can realize the fault correlation calculation process of track structure damage data. At the same time, by introducing the correction value η of the structural damage fault correlation coefficient, it can be adjusted according to the error situation occurring in the calculation process, thereby improving the accuracy and applicability of the structural damage fault correlation calculation formula.

[0120] Preferably, step S3 comprises the following steps:

[0121] Step S31: performing a first fault detection on the three-dimensional track structure status diagram to obtain initial track structure fault information data; performing a fault correction detection on the initial track structure fault information data according to the track structure damage fault factor to obtain track structure surface damage fault data;

[0122] The embodiment of the present invention firstly performs the first fault detection on the three-dimensional track structure condition map by using a laser fault scanning tool to preliminarily identify any obvious structural fault problems on the three-dimensional track structure condition map, such as cracks, corrosion or other visible damage faults, thereby obtaining the initial fault information data of the track structure. Then, the initial fault information data of the track structure is further analyzed according to the track structure damage fault factor to correct the false alarm of the first fault detection or identify more accurate surface damage information to ensure that no surface damage fault problems are missed, and finally obtain the surface damage fault data of the track structure.

[0123] Step S32: performing track health detection and analysis on the high-quality track condition data to obtain track health status information data;

[0124] The embodiments of the present invention detect and analyze the health status of the track in the high-quality track condition data to analyze the overall health status of the track, and determine whether there is a problem with the health status of the track by analyzing the change trend, anomaly and healthy vibration characteristics in the high-quality track condition data, and finally obtain track health status information data.

[0125] Step S33: performing potential fault identification analysis on the track health status information data to obtain track potential fault identification information data;

[0126] The embodiment of the present invention uses data analysis technology to identify and analyze track health status information data to detect information that can identify hidden faults or potential fault problems in the track health status information data, and finally obtains track potential fault identification information data.

[0127] Step S34: performing feature analysis on the track potential fault identification information data to obtain track potential fault identification feature data;

[0128] The embodiment of the present invention analyzes the track potential fault identification information data by using the time-frequency domain analysis method to extract characteristic data related to the potential fault, such as vibration frequency, temperature gradient, etc., and determines the relationship between the characteristics and the potential fault identification information, and finally obtains the track potential fault identification characteristic data.

[0129] Step S35: performing fault identification evaluation analysis on the track potential fault identification feature data to obtain a track potential fault identification factor;

[0130] The embodiment of the present invention uses a fault identification algorithm to evaluate and analyze the track potential fault identification feature data to determine an identification factor that can effectively identify the potential fault mode, and finally obtains the track potential fault identification factor.

[0131] Step S36: performing fault mode recognition analysis on the track structure surface damage fault data to obtain the track structure surface damage fault mode;

[0132] The embodiment of the present invention analyzes the failure modes in the track structure surface damage fault data by using the fault mode recognition technology to identify the damage failure modes already existing in the track structure surface damage fault data, such as fatigue cracks, corrosion spots, etc., and finally obtains the track structure surface damage failure mode.

[0133] Step S37: performing pattern screening processing on the track structure surface damage failure mode according to the track potential fault identification factor to obtain the track structure damage potential failure mode;

[0134] The embodiment of the present invention uses the track potential fault identification factor to screen the identified track structure surface damage failure mode to screen out the failure mode related to the potential fault in the track structure surface damage failure mode, and finally obtain the track structure damage potential failure mode.

[0135] Step S38: performing a second fault detection on the track structure surface damage fault data according to the track structure damage potential fault mode to obtain the track structure potential fault data.

[0136] The embodiment of the present invention performs a second fault detection on the track structure surface damage fault data by using the screened track structure damage potential fault mode, so as to further identify deeper fault problems from the track structure surface damage fault data, and finally obtain the track structure potential fault data.

[0137] The present invention firstly performs a first fault detection on the three-dimensional structural condition diagram of the track, and can preliminarily identify any obvious structural fault problems on the three-dimensional structural condition diagram of the track, such as cracks, corrosion or other visible damage faults, so as to provide information data on the initial fault of the track structure, which helps the operation and maintenance personnel to understand the initial fault information state of the track structure. At the same time, by performing fault correction detection on the initial fault information data of the track structure according to the damage fault factor of the track structure, the accuracy of surface damage fault detection can be improved to ensure that no surface damage fault problem is missed, thereby generating surface damage fault data of the track structure, which helps to evaluate the maintainability and safety of the track structure. By performing track health detection and analysis on high-quality track condition data, the health status of the overall track can be evaluated, including the geometric characteristics, vibration characteristics, temperature distribution, etc. of the track, so as to provide the overall health status information data of the track, which helps to discover possible problems early and improve operation efficiency and safety. In addition, by performing potential fault identification analysis on the track health status information data, it helps to detect potential fault problems on the track, such as fatigue, deformation or other hidden faults. This step provides information data on potential faults of the track, provides a basis for preventive maintenance, and can reduce unnecessary downtime and maintenance costs. Secondly, by performing feature analysis on the track potential fault identification information data, it is possible to extract and analyze feature data related to potential faults, such as vibration frequency, temperature gradient, etc. These feature data help to more accurately identify potential faults and provide more information to support fault maintenance decisions. Then, by performing fault identification evaluation analysis on the track potential fault identification feature data, the feature data can be integrated to generate a comprehensive track potential fault identification factor, which quantifies the severity and urgency of the potential fault and helps to determine which potential fault problems need to be dealt with first. By performing fault pattern recognition analysis on the track structure surface damage fault data, it is helpful to identify existing damage failure modes, such as fatigue cracks, corrosion spots, etc., which helps to understand the actual condition of the track structure and provides an important basis for subsequent processing. Next, by using the track potential fault identification factor to perform pattern screening on the track structure surface damage fault mode, the identification of potential faults can be further refined, and the fault mode related to the potential fault can be screened out from the track structure surface damage fault mode, which enables the operation and maintenance personnel to formulate potential fault maintenance strategies in a targeted manner and ensure the stable operation of the rail transit system. Finally, by using the potential failure mode of track structure damage to perform a second fault detection on the track structure surface damage fault data, the existence of potential fault problems can be further confirmed, providing more conclusive evidence for maintenance decisions. By detecting the track structure surface damage fault data according to the potential failure mode of track structure damage, deeper faults can be accurately identified from the original damage fault data, ensuring the safety and reliability of the rail transit system.This also provides operation and maintenance personnel with a clear direction for formulating maintenance plans, effectively reducing system maintenance costs.

[0138] Preferably, step S4 comprises the following steps:

[0139] Step S41: performing fault location processing on the track structure surface damage fault data and the track structure potential fault data by using AR technology to obtain the track structure fault point data;

[0140] The embodiment of the present invention uses augmented reality (AR) technology to superimpose and visualize the actual track structure fault position of the track structure surface damage fault data and the track structure potential fault data, and analyzes the AR superimposed data to accurately locate the position data of the fault point in the track structure (including the track damage fault position or the potential fault problem position), and finally obtains the track structure fault point data.

[0141] Step S42: performing fault handling query processing on the track structure fault point data to obtain a track structure fault handling solution;

[0142] The embodiment of the present invention analyzes the track structure fault point data located by augmented reality (AR) technology to obtain the corresponding fault information therein, performs matching query processing on the fault information obtained by analysis and the existing fault handling solution library, screens out the appropriate fault handling solution according to the type and location of the fault information, and finally obtains the track structure fault handling solution.

[0143] Step S43: performing fault repair processing on the track structure fault point data according to the track structure fault handling plan to obtain track structure fault repair point data;

[0144] The embodiment of the present invention uses the queried track structure fault handling solution to repair the corresponding track structure fault point in the track structure fault point data to ensure that the fault problem of the track structure fault point can be solved in a timely manner, and records the coordinate data and maintenance result information data of the actual track structure fault point, and finally obtains the track structure fault maintenance point data.

[0145] Step S44: performing maintenance warning labeling processing on the track structure fault maintenance point data to obtain the track fault maintenance area;

[0146] The embodiment of the present invention analyzes the coordinates and maintenance history information of the maintenance point in the track structure fault maintenance point data, and simultaneously performs early warning marking on the analyzed maintenance history and the location of the maintenance point, so as to mark that the track structure fault maintenance point is under maintenance or has been repaired but is not passable, and finally obtains the track fault maintenance area.

[0147] Step S45: performing scheduling and operation and maintenance processing on the vehicle operation status in the high-quality data of rail vehicle operation according to the track fault maintenance area, and obtaining rail vehicle scheduling and operation and maintenance information data.

[0148] The embodiment of the present invention performs scheduling processing on the corresponding vehicle operation status in the high-quality data of rail vehicle operation according to the location status of the track fault maintenance area, including route adjustment of rail vehicles, optimization of operation plan of vehicle maintenance area, etc., so as to ensure the safety and efficiency of rail vehicles operating outside the maintenance area, and finally obtain rail vehicle scheduling operation and maintenance information data.

[0149] The present invention first uses AR technology to locate the fault data and potential fault data of the track structure damage, which has high accuracy and real-time performance, so that the fault point of the track structure can be accurately located, which helps to quickly discover the fault problem of the track structure, improve maintenance efficiency, reduce maintenance costs, and ensure the reliability and safety of the rail transit system. Secondly, by performing fault handling query processing on the fault point of the track structure, it can provide timely and effective disposal solutions for the operation and maintenance personnel. This includes the nature, priority and recommended maintenance measures of the problem, which helps to make quick decisions and actions, thus ensuring that the fault problem of the track structure can be properly handled and reducing the potential risk of rail transit system failure. Then, by using the queried track structure fault disposal solution to perform fault maintenance processing on the fault point of the track structure, it can ensure that the fault problem of the fault point is solved in time, which helps to extend the life of the track structure, reduce the maintenance cycle, and improve the availability of the rail transit system. The repaired track structure fault maintenance point regains a healthy state, which helps the continuous and stable operation of the rail transit system. Next, by performing maintenance warning marking processing on the fault maintenance point of the track structure, it can be marked to ensure that no vehicle will run through during the maintenance period, and future fault problems can be prevented through the area. By marking the fault maintenance points of the track structure, it is possible to establish maintenance history data, track the evolution trend of fault problems, take measures in advance, reduce future maintenance costs and downtime, and thus improve the maintainability and predictability of the rail transit system. Finally, by scheduling and operating high-quality data on rail vehicle operation according to the track fault maintenance area, it is possible to ensure the safety and efficiency of rail vehicle operation outside the maintenance area, including route adjustment, optimization of vehicle maintenance plans, etc., which helps to reduce operational risks and costs during maintenance, while maximizing the safety and reliable transportation of passengers and goods, thereby improving the overall operation and maintenance efficiency and service level of the rail transit system.

[0150] Preferably, the present invention further provides a rail transit operation and maintenance system based on AR technology, which is used to execute the rail transit operation and maintenance method based on AR technology as described above, and the rail transit operation and maintenance system based on AR technology includes:

[0151] The rail transit data acquisition module is used to conduct virtual reality simulation of the rail transit system through AR technology to obtain a virtual digital twin space of rail transit; real-time acquisition and processing of the virtual digital twin space of rail transit is performed to obtain high-quality data on track conditions and rail vehicle operation;

[0152] The track structure damage assessment module is used to perform track structure visualization analysis on high-quality track condition data to obtain a three-dimensional track structure condition diagram; perform track structure damage analysis on the three-dimensional track structure condition diagram to obtain track structure damage data; perform damage and fault assessment on the three-dimensional track structure condition diagram based on the track structure damage data to obtain track structure damage and fault factors;

[0153] The track structure fault detection module is used to perform a first fault detection on the track three-dimensional structure condition map according to the track structure damage fault factor to obtain the track structure surface damage fault data; perform potential fault assessment and analysis on the high-quality track condition data to obtain the track potential fault identification factor; perform a second fault detection on the track structure surface damage fault data according to the track potential fault identification factor to obtain the track structure potential fault data;

[0154] The fault repair vehicle operation and maintenance module is used to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data through AR technology to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area, thereby obtaining the rail vehicle dispatch and operation information data.

[0155] In summary, the present invention provides a rail transit operation and maintenance system based on AR technology, which is composed of a rail transit data acquisition module, a track structure damage assessment module, a track structure fault detection module and a fault repair vehicle operation and maintenance module, and can realize any one of the rail transit operation and maintenance methods based on AR technology described in the present invention, and is used to combine the operations between the computer programs running on each module to realize a rail transit operation and maintenance method based on AR technology. The internal structures of the system cooperate with each other, and the visualization of real-time data and the three-dimensional superposition of track information are realized by introducing AR technology, which can improve the perception and decision-making ability of the operation and maintenance personnel. At the same time, the relationship between the damage to the track structure is evaluated, and the first fault detection and the second fault detection can be used to perform fault detection layer by layer from the shallow layer to the potential deep layer, so as to realize the accurate detection of the track structure fault, thereby improving the overall operation and maintenance efficiency of the rail transit system, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient rail transit operation and maintenance process, thereby simplifying the operation process of the rail transit operation and maintenance system based on AR technology.

[0156] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0157] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A rail transit operation and maintenance method based on AR technology, characterized in that: The following steps are involved: Step S1: Perform virtual reality simulation of the rail transit system through AR technology to obtain a virtual digital twin space of the rail transit; Performing quality data collection and processing on the rail transit virtual digital twin space to obtain high-quality data on track conditions and high-quality data on rail vehicle operation; wherein step S1 includes the following steps: Step S11: Perform three-dimensional geographic scanning processing on the rail transit system to obtain high-precision three-dimensional geographic data of the rail transit; Step S12: performing three-dimensional rendering modeling processing on the high-precision three-dimensional geographic data of rail transit to obtain a high-precision three-dimensional model of rail transit; Step S13: Perform virtual reality simulation on the high-precision three-dimensional model of rail transit through AR technology to obtain a virtual digital twin space of rail transit; Step S14: by deploying an IoT sensor network in the rail transit virtual digital twin space, and performing real-time collection and processing on the rail transit virtual digital twin space according to the physical network sensor network, initial track condition data and initial rail vehicle operation data are obtained; Step S15: Perform quality screening on the initial track condition data and the initial track vehicle operation data to obtain high-quality track condition data and high-quality track vehicle operation data; wherein step S15 includes the following steps: Step S151: performing noise reduction processing on the initial track condition data and the initial track vehicle operation data to obtain track condition noise reduction data and track vehicle operation noise reduction data; Step S152: performing anomaly detection and analysis on the track condition noise reduction data and the rail vehicle operation noise reduction data to obtain track condition abnormality data and rail vehicle operation abnormality data; Step S153: using an abnormal peak detection calculation formula to perform abnormal calculation on the track condition abnormal data and the rail vehicle operation abnormal data, to obtain the abnormal peak value of the track condition data and the abnormal peak value of the rail vehicle operation data; wherein the abnormal peak detection calculation formula is specifically: ； ； In the formula, is the abnormal peak value of track condition data, is the number of abnormal track condition data, For the The value of track condition abnormal data, is the upper limit of the integral time range for abnormal calculation, is the lower limit of the integral time range for abnormal calculation, is the integral time parameter for abnormal calculation, is an exponential function, It is the abnormal amplitude adjustment parameter of track condition abnormal data. is the abnormal attenuation control parameter of track condition abnormal data, For the The mean of the abnormal distribution of track condition abnormal data, For the The standard deviation of the abnormal distribution of track condition abnormal data, is the correction value of the abnormal peak value of the track condition data, Abnormal peak value of rail vehicle operation data. is the number of abnormal data of rail vehicle operation, For the The value of abnormal operation data of rail vehicles, It is the abnormal amplitude adjustment parameter of the abnormal data of rail vehicle operation. is the abnormal attenuation control parameter of the abnormal data of rail vehicle operation, For the The mean of the abnormal distribution of the abnormal data of rail vehicle operation, For the The standard deviation of the abnormal distribution of the abnormal data of rail vehicle operation, It is the correction value of the abnormal peak value of the rail vehicle operation data; Step S154: performing peak identification and filtering on the abnormal track condition data and the abnormal rail vehicle operation data according to the abnormal peak values ​​of the track condition data and the abnormal rail vehicle operation data, to obtain abnormal track condition filtered data and abnormal rail vehicle operation filtered data; Step S155: performing data dimensionality reduction processing on the track condition abnormality filtered data and the rail vehicle operation abnormality filtered data to obtain track condition dimensionality reduced data and rail vehicle operation dimensionality reduced data; Step S156: performing quality assessment and screening processing on the track condition dimensionality reduction data and the rail vehicle operation dimensionality reduction data to obtain high-quality track condition data and high-quality rail vehicle operation data; Step S2: Performing track structure visualization analysis on the high-quality track condition data to obtain a three-dimensional track structure condition diagram; performing track structure damage analysis on the three-dimensional track structure condition diagram to obtain track structure damage data; performing damage and fault assessment on the three-dimensional track structure condition diagram based on the track structure damage data to obtain a track structure damage and fault factor; wherein step S2 includes the following steps: Step S21: performing track structure identification analysis on the high-quality track condition data to obtain track structure condition information data; Step S22: performing three-dimensional visualization analysis on the track structure status information data to obtain a three-dimensional track structure status diagram; Step S23: performing structural damage scanning processing on the three-dimensional track structure status map to obtain the track structure damage area; Step S24: performing a track structure damage analysis on the track three-dimensional structure condition diagram according to the track structure damage area to obtain track structure damage data; Step S25: perform fault correlation calculation on the track structure damage data using the structural damage fault correlation calculation formula to obtain a structural damage fault correlation degree coefficient; wherein the structural damage fault correlation calculation formula is specifically: ； In the formula, is the structural damage failure correlation coefficient, The time range parameter for fault correlation calculation, is the integration time variable for fault correlation calculation, is the number of structural damage locations in the track structure damage data, The track structure damage data The structural damage site at time The damage index parameters at The track structure damage data The structural damage site at time The damage delay parameter at The track structure damage data The damage attenuation parameter of the damaged part of the structure is is the number of structural failure locations in the track structure damage data, The track structure damage data The structural fault location at time The fault indicator parameters at The track structure damage data The structural fault location at time The fault at affects the smoothing parameter, The track structure damage data The failure influence coefficient of each structural fault location, is the time-dependent attenuation coefficient, is the number of damage fault associated impact items, For the The damage fault correlation influence item is in time The associated impact index parameters at For the The associated influence weight parameter of each damage fault associated influence item, is the correction value of the structural damage failure correlation coefficient; Step S26: performing damage and fault assessment on the three-dimensional track structure condition diagram according to the structural damage and fault correlation coefficient to obtain a track structure damage and fault factor; Step S3: performing a first fault detection on the three-dimensional track structure condition map according to the track structure damage fault factor to obtain track structure surface damage fault data; performing potential fault assessment and analysis on the high-quality track condition data to obtain track potential fault identification factors; performing a second fault detection on the track structure surface damage fault data according to the track potential fault identification factors to obtain track structure potential fault data; wherein step S3 includes the following steps: Step S31: performing a first fault detection on the three-dimensional track structure status diagram to obtain initial track structure fault information data; performing a fault correction detection on the initial track structure fault information data according to the track structure damage fault factor to obtain track structure surface damage fault data; Step S32: performing track health detection and analysis on the high-quality track condition data to obtain track health status information data; Step S33: performing potential fault identification analysis on the track health status information data to obtain track potential fault identification information data; Step S34: performing feature analysis on the track potential fault identification information data to obtain track potential fault identification feature data; Step S35: performing fault identification evaluation analysis on the track potential fault identification feature data to obtain the track potential fault identification factor; Step S36: performing fault mode recognition analysis on the track structure surface damage fault data to obtain the track structure surface damage fault mode; Step S37: performing pattern screening processing on the track structure surface damage failure mode according to the track potential fault identification factor to obtain the track structure damage potential failure mode; Step S38: performing a second fault detection on the track structure surface damage fault data according to the track structure damage potential fault mode to obtain the track structure potential fault data; Step S4: Use AR technology to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area to obtain the rail vehicle dispatch and operation information data.

2. The rail transit operation and maintenance method based on AR technology according to claim 1 is characterized in that: Step S154 includes the following steps: Step S1541: Plotting peak graphs of abnormal peak values ​​of track condition data and abnormal peak values ​​of rail vehicle operation data to obtain abnormal peak graphs of track condition data and abnormal peak graphs of rail vehicle operation data; Step S1542: Peaks of the track condition data abnormal peak graph and the rail vehicle operation data abnormal peak graph are identified and marked according to a preset standard abnormal peak curve to obtain abnormal exceeding points of the track condition data and the rail vehicle operation data abnormal exceeding points; Step S1543: performing abnormal fluctuation detection on the abnormal peak graph of the track condition data and the abnormal peak graph of the rail vehicle operation data to obtain the abnormal fluctuation area of ​​the track condition data and the abnormal fluctuation area of ​​the rail vehicle operation data; Step S1544: merging the track condition data abnormal exceeding points and the track condition data abnormal fluctuation areas to obtain the track condition abnormal area, and filtering out the track condition abnormal data corresponding to the track condition abnormal area to obtain track condition abnormal filtered data; Step S1545: The rail vehicle operation data abnormal exceeding points and the rail vehicle operation data abnormal fluctuation areas are merged to obtain the rail vehicle operation abnormal area, and the rail vehicle operation abnormal data corresponding to the rail vehicle operation abnormal area is filtered out to obtain the rail vehicle operation abnormal filtered data.

3. The rail transit operation and maintenance method based on AR technology according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing fault location processing on the track structure surface damage fault data and the track structure potential fault data by using AR technology to obtain the track structure fault point data; Step S42: performing fault handling query processing on the track structure fault point data to obtain a track structure fault handling solution; Step S43: performing fault repair processing on the track structure fault point data according to the track structure fault handling plan to obtain track structure fault repair point data; Step S44: performing maintenance warning labeling processing on the track structure fault maintenance point data to obtain the track fault maintenance area; Step S45: performing scheduling and operation and maintenance processing on the vehicle operation status in the high-quality data of rail vehicle operation according to the track fault maintenance area, and obtaining rail vehicle scheduling and operation and maintenance information data.

4. A rail transit operation and maintenance system based on AR technology, characterized in that: Used to execute the rail transit operation and maintenance method based on AR technology as claimed in claim 1, the rail transit operation and maintenance system based on AR technology includes: The rail transit data acquisition module is used to perform three-dimensional geographic scanning processing on the rail transit system to obtain three-dimensional geographic high-precision data of the rail transit; perform three-dimensional rendering modeling processing on the three-dimensional geographic high-precision data of the rail transit to obtain a high-precision three-dimensional model of the rail transit; perform virtual reality simulation on the high-precision three-dimensional model of the rail transit through AR technology to obtain a virtual digital twin space of the rail transit; by deploying an Internet of Things sensor network in the virtual digital twin space of the rail transit, and performing real-time acquisition and processing on the virtual digital twin space of the rail transit according to the physical network sensor network, the initial data of the track condition and the initial data of the rail vehicle operation are obtained; the initial data of the track condition and the initial data of the rail vehicle operation are subjected to noise reduction processing to obtain the noise reduction data of the track condition and the noise reduction data of the rail vehicle operation; anomaly detection and analysis are performed on the noise reduction data of the track condition and the noise reduction data of the rail vehicle operation to obtain abnormal track condition data and abnormal rail vehicle operation data; anomaly calculation is performed on the abnormal track condition data and the abnormal rail vehicle operation data using an abnormal peak detection calculation formula to obtain the abnormal peak value of the track condition data and the abnormal peak value of the rail vehicle operation data; wherein the abnormal peak detection calculation formula is specifically as follows: ； ； In the formula, is the abnormal peak value of track condition data, is the number of abnormal track condition data, For the The value of track condition abnormal data, is the upper limit of the integral time range for abnormal calculation, is the lower limit of the integral time range for abnormal calculation, is the integral time parameter for abnormal calculation, is an exponential function, It is the abnormal amplitude adjustment parameter of track condition abnormal data. is the abnormal attenuation control parameter of track condition abnormal data, For the The mean of the abnormal distribution of track condition abnormal data, For the The standard deviation of the abnormal distribution of track condition abnormal data, is the correction value of the abnormal peak value of the track condition data, Abnormal peak value of rail vehicle operation data. is the number of abnormal data of rail vehicle operation, For the The value of abnormal operation data of rail vehicles, It is the abnormal amplitude adjustment parameter of the abnormal data of rail vehicle operation. is the abnormal attenuation control parameter of the abnormal data of rail vehicle operation, For the The mean of the abnormal distribution of the abnormal data of rail vehicle operation, For the The standard deviation of the abnormal distribution of the abnormal data of rail vehicle operation, is a correction value of the abnormal peak value of the rail vehicle operation data; according to the abnormal peak value of the track condition data and the abnormal peak value of the rail vehicle operation data, the abnormal track condition data and the abnormal rail vehicle operation data are peak identified and filtered to obtain the abnormal track condition filtered data and the abnormal rail vehicle operation filtered data; the abnormal track condition filtered data and the abnormal rail vehicle operation filtered data are subjected to data dimensionality reduction processing to obtain the reduced dimensional track condition data and the reduced dimensional rail vehicle operation data; the reduced dimensional track condition data and the reduced dimensional rail vehicle operation data are subjected to quality assessment and screening processing to obtain high-quality track condition data and high-quality rail vehicle operation data; The track structure damage assessment module is used to perform track structure identification analysis on high-quality track condition data to obtain track structure condition information data; perform three-dimensional visualization analysis on the track structure condition information data to obtain a three-dimensional track structure condition diagram; perform structural damage scanning processing on the three-dimensional track structure condition diagram to obtain the track structure damage area; perform track structure damage analysis on the three-dimensional track structure condition diagram according to the track structure damage area to obtain track structure damage data; perform fault correlation calculation on the track structure damage data using the structural damage fault correlation calculation formula to obtain the structural damage fault correlation degree coefficient; wherein the structural damage fault correlation calculation formula is specifically as follows: ； In the formula, is the structural damage failure correlation coefficient, The time range parameter for fault correlation calculation, is the integration time variable for fault correlation calculation, is the number of structural damage locations in the track structure damage data, The track structure damage data The structural damage site at time The damage index parameters at The track structure damage data The structural damage site at time The damage delay parameter at The track structure damage data The damage attenuation parameter of the damaged part of the structure is is the number of structural failure locations in the track structure damage data, The track structure damage data The structural fault location at time The fault indicator parameters at The track structure damage data The structural fault location at time The fault at affects the smoothing parameter, The track structure damage data The failure influence coefficient of each structural fault location, is the time-dependent attenuation coefficient, is the number of damage fault associated impact items, For the The damage fault correlation influence item is in time The associated impact index parameters at For the The associated influence weight parameter of each damage fault associated influence item, is the correction value of the structural damage failure correlation coefficient; according to the structural damage failure correlation coefficient, the three-dimensional track structure condition diagram is subjected to damage failure assessment to obtain the track structure damage failure factor; The track structure fault detection module is used to perform a first fault detection on the track three-dimensional structure status map to obtain the initial fault information data of the track structure; perform a fault correction detection on the initial fault information data of the track structure according to the track structure damage fault factor to obtain the track structure surface damage fault data; perform a track health detection analysis on the high-quality track condition data to obtain the track health status information data; perform a potential fault identification analysis on the track health status information data to obtain the track potential fault identification information data; perform a feature analysis on the track potential fault identification information data to obtain the track potential fault identification feature data; perform a fault identification evaluation analysis on the track potential fault identification feature data to obtain the track potential fault identification factor; perform a fault pattern identification analysis on the track structure surface damage fault data to obtain the track structure surface damage fault pattern; perform a pattern screening process on the track structure surface damage fault pattern according to the track potential fault identification factor to obtain the track structure damage potential fault pattern; perform a second fault detection on the track structure surface damage fault data according to the track structure damage potential fault pattern to obtain the track structure potential fault data; The fault repair vehicle operation and maintenance module is used to perform fault location processing on the track structure surface damage fault data and the track structure potential fault data through AR technology to obtain the track structure fault point data; perform fault repair labeling processing on the track structure fault point data to obtain the track fault repair area; perform dispatch and operation processing on the high-quality data of rail vehicle operation according to the track fault repair area, thereby obtaining the rail vehicle dispatch and operation information data.

Images