Rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twinning, medium and equipment

Abstract

The invention discloses a rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twinning, a medium and equipment. The rail transit equipment monitoring system architecture sequentially comprises a multi-source data supporting layer, a data service governance layer, a model construction layer, a virtual and real digital twinning layer and a scene application layer from bottom to top. The multi-source data support layer transmits the collected real-time data to the data service management layer for feature extraction to obtain feature data; the model construction layer constructs a panoramic digital tunnel base model by using the feature data; the virtual and real digital twinborn layer simulates the feature data and simulates the working state of the physical equipment under the normal condition and the abnormal condition; and the scene application layer is used for realizing specific application in different scenes. According to the invention, data from different data sources can be integrated, processed and analyzed, rapid and accurate diagnosis and response measures can be provided when a rail transit system fault occurs, and the method has significant advantages.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit system fault processing, and specifically to a rail transit equipment monitoring system architecture, medium and equipment based on multi-source fusion data governance and digital twins. Background Art

[0002] The multi-source fusion data governance method mainly includes measures such as data stream input, data stream mapping, and stream processor processing, which realizes the integration, processing and analysis of data from different data sources. Among them, data stream input mainly receives data from various data sources, including sensors, log files, databases, etc.; data stream mapping can divide large-scale data streams into sub-data streams according to different characteristics of the stream, thereby improving the efficiency and accuracy of data processing; stream processor processing performs various algorithm operations, logical operations, and function operations on stream data according to different specific business scenarios and transmits the processed results to different destinations, such as databases, file systems, and message queues.

[0003] Digital twin is a comprehensive technology based on computer graphics and 3D models as well as a variety of advanced technologies (such as sensor technology, Internet of Things technology, virtual reality technology, artificial intelligence technology, etc.). Among them, the state of the virtual entity represented by the digital twin can be synchronized with the observed state of the physical entity, so that the virtual space and the physical space monitoring objects maintain consistency in physical space and logical state. Finally, combined with stream data processing technology, the processing results are visualized in different dimensions to achieve real-time monitoring of the data and ensure the fidelity of the virtual space.

[0004] Nowadays, more and more rail transit equipment needs to run 24 hours a day, which puts high demands on the maintainability, fault detectability and status monitoring of rail transit equipment. Therefore, it is necessary to design a rail transit equipment monitoring system to overcome the above problems.

[0005] It should be understood that the above statements merely provide background technology related to the present invention and do not necessarily constitute prior art. Summary of the invention

[0006] The purpose of the present invention is to provide a rail transit equipment monitoring system architecture, media and equipment based on multi-source fusion data governance and digital twins, to integrate, process and analyze data from different data sources, and to provide fast and accurate diagnosis and response measures when rail transit system failures occur.

[0007] In order to achieve the above-mentioned objectives, the first aspect of the present invention provides a rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins, which includes, from bottom to top: multi-source data support layer, data business governance layer, model building layer, virtual-reality digital twin layer and scenario application layer.

[0008] Among them, the multi-source data support layer transfers the real-time data generated daily by the rail transit equipment to the data business management layer for feature extraction to obtain feature data after feature extraction; the model construction layer uses the feature data to construct a panoramic digital tunnel base model; the virtual-reality digital twin layer is used to simulate the feature data to simulate the working status of the physical equipment under normal and abnormal conditions; the scenario application layer is used to use the constructed panoramic digital tunnel base model in actual scenarios, and combined with the feature data after real-time feature extraction by the data business management layer, to realize specific applications in different scenarios.

[0009] Preferably, the multi-source data support layer is provided with a programmable logic controller, a data acquisition and monitoring control system and an industrial robot; wherein the programmable logic controller collects real-time data of signal equipment; the data acquisition and monitoring control system collects real-time data of vehicle equipment; and the industrial robot collects real-time data of power supply equipment.

[0010] Preferably, the signal equipment includes a switch, a signal machine and a track circuit; the vehicle equipment includes a pantograph; and the power supply equipment includes a contact network.

[0011] Preferably, the multi-source data support layer is also provided with a wireless Bluetooth device or a geographic information system, which can identify the spatial position of the rail transit equipment based on the location service data.

[0012] Preferably, the stream processing framework used in the data service governance layer is the Apache Flink framework.

[0013] Preferably, the panoramic digital tunnel base model includes a static model and a mechanism model.

[0014] Preferably, the static model is constructed based on a building information model, a physical model, and a dynamic model to obtain a switch machine model, a signal machine model, a track circuit model, a pantograph three-dimensional model, a contact network three-dimensional model, and a train automatic operation system model.

[0015] Preferably, the mechanism model is an accident simulation and status assessment model, which is constructed based on railway operation data, equipment status data, historical accident records and environmental factor data. The accident simulation and status assessment model can autonomously analyze the feature data after real-time feature extraction of the data business governance layer and obtain abnormal data, realize abnormal data playback and real-time assessment of equipment status.

[0016] Preferably, the accident simulation and status assessment model comprises: a data preprocessing module, a quantitative grading assessment module, a hierarchical fitting evaluation module and an accident simulation module.

[0017] Among them, the data preprocessing module transfers the processed feature data to the quantitative grading evaluation module for comprehensive grading analysis and integration; the hierarchical fitting evaluation module performs fitting evaluation on the feature data after comprehensive grading analysis and integration, generates evaluation results and data visualization effects, and predicts the equipment status; the accident simulation module replays and traces the generated evaluation results and data visualization effects to predict the accident scenarios and their consequences, and provide support for the formulation of preventive measures.

[0018] Preferably, the virtual-reality digital twin layer implements simulation by mapping real-time feature data generated by indoor and outdoor equipment entities to digital indoor and outdoor equipment models.

[0019] Preferably, the mapping method includes: a physical entity interaction drive interface, a twin model interaction drive interface or a service interface.

[0020] Preferably, specific applications in different scenarios include: intelligent maintenance of rail transit equipment, simulation of multi-environment train operations, emergency "sand table" command of emergency situations during train travel, and multi-professional collaborative repair of faulty trains.

[0021] The second aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins is implemented.

[0022] The third aspect of the present invention provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins is implemented.

[0023] In summary, compared with the prior art, the rail transit equipment monitoring system architecture, medium and equipment based on multi-source fusion data management and digital twin provided by the present invention have at least the following beneficial effects:

[0024] (1) The present invention can fuse and process various types of collected data and construct a virtual model through digital twin technology, thereby simulating and analyzing the operation of physical equipment in a virtual environment;

[0025] (2) The present invention has self-learning and self-adaptation capabilities, and can continuously optimize monitoring strategies and maintenance plans based on historical data and real-time feedback, thereby improving the operating efficiency and safety of rail transit equipment;

[0026] (3) The present invention breaks down the barriers of rail transit data by integrating real-time data of rail transit, enhances the readability of data, and can automatically generate strategy reports, thereby improving the operational efficiency and service level of the rail transit system;

[0027] (4) The present invention can not only effectively prevent and reduce the occurrence of rail transit system failures, but also provide rapid and accurate diagnosis and response measures when rail transit system failures occur, greatly improving the maintenance efficiency and emergency response capabilities of the rail transit system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a structural schematic diagram of the rail transit equipment monitoring system architecture of the present invention;

[0029] Figure 2 It is a flow chart of the multi-professional collaborative emergency repair application in the application layer of the present invention. DETAILED DESCRIPTION

[0030] The following is combined with Figures 1-2 , the present invention is further explained by describing a preferred specific embodiment in detail.

[0031] It should be noted that the drawings are in a very simplified form and use non-precise proportions. They are only used to conveniently and clearly assist in explaining the embodiments of the present invention, and are not used to limit the conditions for the implementation of the present invention. Therefore, they have no substantive technical significance. Any structural modification, change in proportional relationship or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical content disclosed by the present invention.

[0032] It should be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only the elements explicitly listed, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0033] like Figure 1 As shown, the present invention provides a rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins, which includes, from bottom to top: a multi-source data support layer, a data business management layer, a model construction layer, a virtual-real digital twin layer, and a scenario application layer. Among them, the multi-source data support layer transfers the real-time data generated daily by the rail transit equipment collected to the data business management layer for feature extraction to obtain feature data after feature extraction; the model construction layer uses the feature data to build a static model and a mechanism model, and combines the two into a panoramic digital tunnel base model; the virtual-real digital twin layer can use the feature data for simulation to simulate the working state of the physical equipment under normal and abnormal conditions; the scenario application layer is used to use the constructed panoramic digital tunnel base model in actual scenarios, and combined with the feature data after real-time feature extraction of the data business management layer, to achieve specific applications in different scenarios.

[0034] The multi-source data support layer is used to collect a large amount of real-time data generated daily by rail transit equipment. The multi-source data support layer is provided with a programmable logic controller (PLC), a supervisory control and data acquisition system (SCADA) and an industrial robot. Specifically, in this embodiment, the PLC collects real-time data of signal equipment such as switch machines, signal machines, and track circuits through the Modbus communication protocol; the SCADA collects real-time data of vehicle equipment such as pantographs through the Profibus communication protocol; and the industrial robot collects real-time data of power supply equipment such as contact lines through the RS-232 / RS-485 communication protocol.

[0035] Furthermore, the multi-source data support layer is also provided with a wireless Bluetooth device or a Geographic Information System (GIS), which can identify the spatial position of the rail transit equipment based on location-based services (LBS) to obtain the LBS data of the rail transit equipment.

[0036] The data service governance layer performs feature extraction on the real-time data collected in the multi-source data support layer through the stream processing framework to obtain feature data after feature extraction. Specifically, in this embodiment, the data service governance layer performs feature extraction on the relevant real-time data of the switch machine, including: gap monitoring data, action rod motion parameters, indication rod motion parameters, motor motion parameters, electric light and electricity parameters, etc.; performs feature extraction on the relevant real-time data of the signal machine, including: voltage level, traction current, impedance, capacitance, insulation strength, etc.; performs feature extraction on the relevant real-time data of the track circuit, including: output voltage, output current, etc.; performs feature extraction on the relevant real-time data of the pantograph and the contact network, including: contact resistance, current transmission capacity, static contact force, dynamic contact force, etc.; and performs feature extraction on the real-time data based on location services, including: LBS data.

[0037] In a preferred embodiment of the present invention, the stream processing framework is the Apache Flink framework.

[0038] It should be noted that the feature data after feature extraction has the common dynamic characteristics of sequential, large-scale, fast and continuous; the various types of feature data collected and extracted at each same time point within a period of time are subjected to ETL (Extract-Transform-Load) operations, that is, the various types of feature data collected at each same time point within the period of time are extracted, transformed and loaded, so as to obtain a set of feature data at each same time point within the period of time.

[0039] Among them, the ETL operation is carried out in the data business governance layer; the ETL extraction operation means extracting the feature data using the ETL tool (i.e., the Apache Flink framework); the ETL conversion operation means translating the extracted feature data into "readable" data after data cleaning, data deduplication, data denoising, data filling, and data mapping; the ETL loading operation means verifying the converted "readable" feature data, and after the verification is completed, constructing a suitable table model for loading, as well as data storage and forwarding according to the actual business scenario.

[0040] Furthermore, the feature data after ETL processing is used to construct static models and mechanism models. The static model is based on the building information model (Building Information Modeling, BIM), physical model, and dynamic model, and the feature data of the switch machine, the feature data of the signal machine, the feature data of the track circuit, the feature data of the pantograph, the feature data of the contact network, and the LBS data are constructed respectively, and finally the switch machine model, the signal machine model, the track circuit model, the pantograph three-dimensional model, the contact network three-dimensional model, and the train automatic operation system model (smart digital train basic unit) are constructed. The mechanism model is an accident simulation and status assessment model, which is constructed based on railway operation data, equipment status data, historical accident records, and environmental factor data. Therefore, the model can autonomously analyze the feature data after the real-time feature extraction of the data business governance layer, such as data classification, data dimensionality reduction, and obtain abnormal data, thereby realizing abnormal data playback and real-time evaluation of equipment status.

[0041] Specifically, the railway operation data includes: train operation records, signal system data and dispatching command records, etc.; the equipment status data includes: characteristic data of track circuits, characteristic data of vehicle equipment, characteristic data of signal machines and switch machines, etc.; the historical accident records include: accident type, cause of accident and consequences of accident, etc.; the environmental factor data includes: weather conditions, geological conditions and environment along the line, etc.

[0042] The model building layer combines the constructed static model and mechanism model to construct a panoramic digital tunnel base model, effectively integrating and linking the "people, things, and objects" in the spatial data to form a complete "people, things, and objects" spatial digital twin system. Among them, the static model provides basic data support, while the mechanism model provides in-depth analysis and understanding. Through the combination of the two, various elements in the spatial data are intelligently managed and optimized, making the relationship between "people, things, and objects" clearer and more orderly, and realizing digital twins.

[0043] Among them, the switch machine model is used to simulate the physical structure and operating logic of the switch machine, and is used to analyze and optimize the switch process of the turnout; the signal machine model is used to simulate the display status and control logic of the signal machine to ensure that the train receives the signal indication at the right time; the track circuit model is used to simulate the electrical characteristics and working principle of the track circuit, and is used to detect the position and status of the train; the pantograph three-dimensional model is used to accurately simulate the shape, size and motion trajectory of the pantograph to ensure good contact with the contact network; the contact network three-dimensional model is used to construct the geometric shape and electrical characteristics model of the contact network, which is used to analyze the power supply quality and reliability; the train automatic operation system model is used to receive real-time data collected by ground signal equipment, thereby simulating the train's operating environment, ensuring the train's driving safety and optimizing operational efficiency.

[0044] Among them, the accident simulation and status assessment model includes: a data preprocessing module, a quantitative grading assessment module, a hierarchical fitting evaluation module, and an accident simulation module. The data preprocessing module can receive the original rail transit signal feature data, and perform preliminary processing and cleaning to improve the quality and availability of the data. The quantitative grading assessment module is used to perform further quantitative analysis and grading evaluation on single structured data. The hierarchical fitting evaluation module can use a multi-factor fitting evaluation method to fit the rail transit data, generate evaluation results and data visualization effects, and while predicting the equipment status, give the health status and maintenance recommendations of the equipment to ensure the stable operation and safety of the system. The accident simulation module uses the data playback function to simulate and deduce accidents, predict possible accident scenarios and consequences, and provide a basis for the formulation of preventive measures.

[0045] It should be noted that in the accident simulation and status assessment model, the data preprocessing module passes the processed feature data, such as the alarm time, alarm content and alarm type of the turnout, to the quantitative grading assessment module for comprehensive grading analysis and integration. Subsequently, the feature data after comprehensive grading analysis and integration will be fitted and evaluated by the hierarchical fitting evaluation module to generate evaluation results and data visualization effects, and predict the equipment status. Finally, the evaluation results and data visualization effects generated by the accident simulation module are replayed and traced to predict possible accident scenarios and their consequences, thereby providing support for the formulation of preventive measures. Among them, through the playback function of the accident simulation module, users can view past data and events to understand the overall picture and details of the accident; through the tracing function of the accident simulation module, users can find the root cause of the problem and provide strong support for subsequent improvements and prevention.

[0046] The virtual-reality digital twin layer injects the feature data set after ETL operation in the data business governance layer into the panoramic digital tunnel base model, thereby enabling the real-time feature data generated by indoor and outdoor equipment entities to be mapped to the digital indoor and outdoor equipment model through the physical entity interactive drive interface, or the twin model interactive drive interface, or the service interface, etc., to realize real-time monitoring, management and simulation of the working status of the physical equipment, thereby simulating the working status of the physical equipment under normal and abnormal conditions, discovering potential problems in advance and making corresponding adjustments and optimizations.

[0047] The scenario application layer uses the constructed panoramic digital tunnel base model in actual scenarios to realize applications in different scenarios, including intelligent maintenance of rail transit equipment, simulation of multi-environment train operations, emergency "sand table" command of emergency situations during train travel, and multi-professional collaborative repair of faulty trains.

[0048] Further, such as Figure 2 As shown, the multi-professional collaborative repair refers to the process in which technicians of different professions quickly gather and work together to complete the repair task when equipment failure or emergency occurs. In the multi-professional collaborative repair, firstly, the static model (including the switch machine model, the signal machine model, the track circuit model, the pantograph three-dimensional model, the contact network three-dimensional model and the train automatic operation system model) in the panoramic digital tunnel base model performs real-time mapping of the data in the train operation in the virtual space, and performs comprehensive classification analysis and integration through the quantitative classification evaluation module in the accident simulation and state evaluation model. When abnormal data is monitored, the abnormal data is fed back to the rail transit signal equipment or the physical entity of the train, and the equipment failure position of the train in the physical space is located; when the static model maps the physical entity data and fluctuates continuously within a certain range, the hierarchical fitting evaluation module in the accident simulation and state evaluation model is used to predict and diagnose the data and give corresponding diagnostic suggestions; then, through the multi-professional self-service command dispatching platform, according to the type and severity of the equipment failure, the corresponding professional technicians and maintenance resources are automatically deployed, and the information of the virtual space and the physical space is comprehensively considered to formulate maintenance plans and decisions in different spaces, times, forms and cycles, complete the formulation of multi-space maintenance decisions, and ensure the smooth progress of collaborative repair work.

[0049] It can be understood that the panoramic digital tunnel base model can monitor the train in different scenarios in real time and view the running status of the train at the train dispatching command center, thereby realizing the intelligent maintenance of rail transit equipment and the simulation of multi-environment train operation.

[0050] The following are some examples to illustrate the application of the architecture of the present invention in different scenarios:

[0051] In one embodiment of the present invention, the switch machine model in the static model detects the switch machine data, and the accident deduction model and the state assessment model judge the switch machine data detected by the switch machine model. When the gap between the gaps on both sides of the switch machine exceeds the standard value of 1.45 mm, or the gap between the gaps on both sides of the switch machine plus the point rail and the base rail are more than 7 mm, the accident deduction model and the state assessment model will generate an alarm message, thereby informing the dispatching commander in the dispatching room that the switch machine equipment has failed. The dispatching commander then identifies the location of the faulty equipment in combination with the LBS data, so that the "sand table" command can be remotely carried out in the dispatching room, and the emergency situation occurring during the train movement can be handled in a timely manner, which not only shortens the time to solve the fault, but also ensures the operational safety, so that "people, things, and objects" are integrated in different spaces.

[0052] In another embodiment of the present invention, when a pantograph-catenary fault occurs during train operation, the static pantograph model and the contact network model need to be analyzed in combination with a dynamic mechanism model (accident simulation and status assessment model) to map the working status of the physical equipment and determine the location where the pantograph-catenary fault occurs; first, the contact resistance, voltage value, current value and contact area between the pantograph and the contact network during train operation are detected according to the pantograph model and the contact network model, and the accident simulation and status assessment model determines the specific cause of the pantograph-catenary model fault through the aforementioned detected data, and provides corresponding maintenance suggestions or solutions after autonomous diagnosis, and then, through a multi-professional self-service command dispatching platform, according to the type and severity of the equipment fault, automatically deploys technical personnel and maintenance resources of the corresponding profession, and comprehensively considers the information of virtual space and physical space, formulates maintenance plans and decisions in different spaces, times, forms and cycles, completes the formulation of multi-space maintenance decisions, ensures the smooth progress of collaborative repair work, and promptly resolves the pantograph-catenary fault that occurred during the operation of this train.

[0053] Based on the same inventive concept, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins is described.

[0054] Based on the same inventive concept, the present invention also provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins is implemented.

[0055] In summary, the rail transit equipment monitoring system architecture, medium and equipment based on multi-source fusion data management and digital twins of the present invention can fuse and process various types of collected data, and build a virtual model through digital twin technology, so as to simulate and analyze the operation of physical equipment in a virtual environment; at the same time, the system architecture of the present invention also has self-learning and self-adaptive capabilities, and can continuously optimize monitoring strategies and maintenance plans based on historical data and real-time feedback, so as to improve the operating efficiency and safety of rail transit equipment. In addition, the present invention also breaks the rail transit data barrier and enhances the readability of data by integrating real-time data of rail transit, and can automatically generate strategy reports, thereby improving the operating efficiency and service level of the rail transit system; it can not only effectively prevent and reduce the occurrence of faults, but also provide fast and accurate diagnosis and response measures when faults occur, greatly improving the maintenance efficiency and emergency response capabilities of the rail transit system.

[0056] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. A rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins, including from bottom to top: Multi-source data support layer, data business governance layer, model building layer, virtual-reality digital twin layer, and scenario application layer; The multi-source data support layer transmits the collected real-time data generated daily by rail transit equipment to the data business management layer for feature extraction to obtain feature data after feature extraction; The model building layer uses the feature data to build a panoramic digital tunnel base model; The virtual-real digital twin layer is used to simulate the characteristic data to simulate the working state of the physical device under normal and abnormal conditions; The scenario application layer is used to apply the constructed panoramic digital tunnel base model to actual scenarios, and combines the feature data extracted by the data service governance layer in real time to realize specific applications in different scenarios.

2. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as described in claim 1 is characterized in that: The multi-source data support layer is provided with a programmable logic controller, a data acquisition and monitoring control system and an industrial robot; Among them, the programmable logic controller collects real-time data of signal equipment; the data acquisition and monitoring control system collects real-time data of vehicle equipment; and the industrial robot collects real-time data of power supply equipment.

3. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as described in claim 2 is characterized in that: The signal equipment includes switch machines, signal machines and track circuits; The vehicle equipment includes a pantograph; the power supply equipment includes a contact network.

4. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as described in claim 3 is characterized in that: The multi-source data support layer is also provided with a wireless Bluetooth device or a geographic information system, which can identify the spatial position of the rail transit equipment based on the location service data.

5. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as claimed in claim 1 is characterized in that: The stream processing framework used in the data service governance layer is the Apache Flink framework.

6. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as claimed in claim 4 is characterized in that: The panoramic digital tunnel base model includes a static model and a mechanism model.

7. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as claimed in claim 6 is characterized in that: The static model is constructed based on a building information model, a physical model, and a dynamic model to obtain a switch machine model, a signal machine model, a track circuit model, a pantograph three-dimensional model, a contact network three-dimensional model, and a train automatic operation system model.

8. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as claimed in claim 6 is characterized in that: The mechanism model is an accident simulation and status assessment model, which is constructed based on railway operation data, equipment status data, historical accident records and environmental factor data. The accident simulation and status assessment model can autonomously analyze the feature data after real-time feature extraction at the data business governance layer and obtain abnormal data, realize abnormal data playback and perform real-time assessment of equipment status.

9. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as claimed in claim 8 is characterized in that: The accident simulation and status assessment model comprises: a data preprocessing module, a quantitative grading assessment module, a hierarchical fitting evaluation module and an accident simulation module; The data preprocessing module transmits the processed feature data to the quantitative grading evaluation module for comprehensive grading analysis and integration; The hierarchical fitting evaluation module performs fitting evaluation on the feature data integrated after comprehensive grading analysis, generates evaluation results and data visualization effects, and predicts the equipment status; The accident simulation module will replay and trace the generated evaluation results and data visualization effects to predict the accident scenarios and their consequences, and provide support for the formulation of preventive measures.

10. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins according to claim 1, characterized in that: The virtual-reality digital twin layer realizes simulation by mapping the real-time feature data generated by the indoor and outdoor equipment entities to the digital indoor and outdoor equipment models.

11. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins as claimed in claim 10, characterized in that: The mapping method includes: a physical entity interaction drive interface, a twin model interaction drive interface or a service interface.

12. The rail transit equipment monitoring system architecture based on multi-source fusion data management and digital twins according to claim 1, characterized in that: Specific applications in different scenarios include: intelligent maintenance of rail transit equipment, simulation of multi-environment train operations, emergency "sand table" command of emergency situations during train operation, and multi-professional collaborative repair of faulty trains.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins as described in any one of claims 1 to 12 is implemented.

14. An electronic device, characterized in that: It includes a processor and a memory, and a computer program is stored in the memory. When the computer program is executed by the processor, the rail transit equipment monitoring system architecture based on multi-source fusion data governance and digital twins as described in any one of claims 1 to 12 is implemented.

Images