A Smart Digital Rail Transit Simulation Testing System and Method

Abstract

The application discloses an intelligent digital rail transit simulation test system based on a digital twinning technology, which comprises a digital rail simulation platform, a digital rail internal test platform and a central digital rail server, the digital rail simulation platform is a visual digital rail 3D scene model which is combined with a rubber-tyred train vehicle dynamics model and is jointly designed and built by relying on the rubber-tyred train vehicle dynamics model data and a digital rail urban construction coordinate map; the digital rail internal test platform comprises a test navigation control unit, and the test navigation control unit is preset with a digital rail mathematical model, an electronic map, magnetic code data and environment perception simulation information. The system can not only monitor the train equipment state, but also can control the train equipment state transition in real time, and the test effectiveness is improved by introducing an artificial intelligence machine learning technology; the system can simultaneously access a real vehicle and a simulation machine and is converted into an internal test platform before product release. The application further discloses an intelligent digital rail transit simulation test method based on the digital twinning technology.

Description

Technical Field

[0001] This invention relates to an intelligent digital rail transit simulation testing system and method. Background Technology

[0002] In traditional intelligent digital rail transit simulation and testing systems, the system simply monitors equipment status and cannot control changes in equipment status in real time. Combining remote sensing technology with remote control of rubber-tired trains poses a significant challenge to operational safety. Ensuring all this requires environmental perception fusion technology based on digital rail systems and 5G's ultra-low latency real-time communication technology, along with a dual early warning mechanism combining onboard human-machine interaction and remote monitoring, based on the level of safety hazard.

[0003] In traditional intelligent digital rail transit simulation and testing systems, the system simply collects massive amounts of data for model prediction. If the data is not preprocessed to remove large errors, the results are often unreliable. Given that the operational data of intelligent digital rail transit systems is subject to numerous interference factors, it is necessary to introduce artificial intelligence and machine learning technologies. These technologies have effective processing modes for noisy data and prediction confidence intervals, thus providing assistance in the parameter tuning and design of the back-calculation algorithm.

[0004] Moreover, the application of traditional digital twin technology in the intelligent transportation industry only focuses on the visualization of customer needs, and cannot focus on the simulation and testing of internal enterprise needs. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide an intelligent digital rail transit simulation test system based on digital twin technology. This system can not only monitor the status of train equipment, but also control the changes in the status of train equipment in real time. It introduces artificial intelligence machine learning technology to improve the effectiveness of testing. It can simultaneously connect to a real vehicle and a simulator, at which point the system is transformed into an internal testing platform before product release.

[0006] Another objective of this invention is to provide an intelligent digital rail transit simulation and testing method based on digital twin technology.

[0007] One technical solution to achieve the above objectives is: an intelligent digital rail transit simulation and testing system based on digital twin technology, comprising a digital track simulation platform, an internal digital track testing platform, and a central digital track server, wherein:

[0008] The digital track simulation platform is a visualized 3D scene model of digital track, which is jointly designed and built by combining the dynamic model of rubber-tired train vehicles and relying on the dynamic model data of rubber-tired train vehicles and digital track urban construction coordinate map.

[0009] The internal testing platform for digital tracks includes a test navigation control unit, which is pre-loaded with a digital track mathematical model, electronic map, magnetic coding data, and environmental perception simulation information.

[0010] The central digital track server is a digital track system management server deployed at the center, and the central digital track server has a built-in real-time database and digital track rule base;

[0011] The onboard navigation control unit of the rubber-tired train obtains the status of roadside equipment and driving data through the in-vehicle communication network, and transmits the corresponding data back to the central data track server through the 5G vehicle-to-ground communication private network, where it is stored in the real-time database of the central data track server.

[0012] The digital track simulation platform monitors the data in the real-time database of the central digital track server for any anomalies, and the platform dispatcher decides whether to remotely operate the equipment or take over the automatic operation control of the vehicle. At the same time, the digital track simulation platform calls the data in the real-time database of the central digital track server to drive the operation of the digital track 3D scene model, mapping the operating status of vehicles and roadside equipment in the real environment.

[0013] The communication between the digital track simulation platform and the test navigation control unit uses UDP / TRDP-based data packets. During the simulation, the digital track simulation platform sends the vehicle position, speed, attitude, and angular velocity information calculated in real time for each frame of the rubber-tired train vehicle dynamics model to the pre-set digital track mathematical model of the test navigation control unit in the form of network data packets. Then, based on the pre-loaded electronic map and magnetic coding data, it quickly retrieves and calculates the magnetic nail information that is closest to the current vehicle, and then adds environmental perception simulation information and integrates the magnetic nail information calculation. The calculation results are injected into the vehicle's lateral and longitudinal control algorithms. When the vehicle's lateral and longitudinal control algorithms give control commands, the lateral and longitudinal control commands are encapsulated and sent to the vehicle dynamics model through network data packets, thereby driving the vehicle dynamics model to perform the next frame of simulation calculation and operation.

[0014] The aforementioned intelligent digital rail transit simulation and testing system, wherein the digital track simulation platform acquires digital track test data and imports the digital track test data into a machine self-learning model for rubber-tired train control. Through repeated training and testing iterations, the optimized parameters are substituted into the internal testing platform of the digital track, thereby improving the effectiveness of the test and refining the algorithm design.

[0015] The aforementioned intelligent digital rail transit simulation test system includes a driving simulator within the digital rail internal test platform. Communication between the driving simulator and the digital rail simulation platform is established using a CAN / serial communication method. By simulating third-party control command input, the smoothness of driving mode switching of the digital rail mathematical model and the anti-disturbance capability of the simulation test system are verified.

[0016] A method for simulating and testing intelligent digital rail transit based on digital twin technology, characterized by the following steps:

[0017] S1, forming a 3D scene model based on a high-precision map of the digital magnetic source, and building a digital track simulation platform, specifically including the following steps:

[0018] S11, Generate a 2D scene model of the digital track: High-precision mapping of magnetic nail coordinate points, drawing a magnetic nail urban construction coordinate map using CAD, fixing the RTK antenna to the front of the rubber-tired train, and manually driving to collect high-precision GPS train running trajectory; after fitting the GPS trajectory with the magnetic nail map, a 2D scene model of the digital track is drawn.

[0019] S12, Digital Model Conversion to Generate Digital Track Simulation Platform: Based on the 2D scene model based on digital twin technology and the 3D mechanical drawings of roadside facilities and equipment, 3D visualization 1:1 modeling and restoration is carried out, and the status information of all equipment is displayed through the ECharts front end to obtain the digital track 3D scene model and build the framework of the digital track simulation platform.

[0020] S2, the scene model establishes a real-time communication mechanism with the rubber-tired train, which specifically includes the following steps:

[0021] S21, Digital Rail Vehicle-to-Ground Data Communication: When the rubber-tired train is powered on, the onboard controller, sensors, and processor transmit the driving data to the onboard navigation control unit in real time via the TRDP protocol. The roadside equipment first collects data uniformly by the roadside unit, processes it once by the edge computing unit, and then transmits the roadside data to the onboard navigation control unit via the 5G vehicle-to-ground communication network. The onboard navigation control unit fuses and calculates the driving data and roadside data, and then sends the resulting optimal control command to the vehicle actuators, causing the rubber-tired train to take corresponding actions. At the same time, the above data information is also forwarded to the central data track server via the 5G vehicle-to-ground communication network and stored in the real-time database of the central data track server. The digital track simulation platform then calls the data in the real-time database to drive the operation of the digital track 3D scene model, thereby mapping the operating status of the vehicle and roadside equipment in the real environment.

[0022] S22, Digital Track System Fault Early Warning: Based on fault code feedback provided by various devices and stored in a real-time database, corresponding status codes are assigned according to the fault level, and different colors are set to display them in the front-end visualization area of ​​the central digital track server; the fault levels are divided into operational safety faults and operational non-safety faults.

[0023] S23, Remote control of digital rail system trains: Under the condition of meeting the automatic driving operation requirements, the operating status of the rubber-tired train is remotely operated via a dedicated 5G peripheral device on the control computer. The operating status of the rubber-tired train includes starting and stopping, acceleration and deceleration, and entering / switching / exiting the lateral and longitudinal automatic control modes. At this time, combined with the fault feedback status in step S22, when an operational safety fault is reported, the system is forced to stop; when an operational non-safety fault is reported, personnel can remotely operate the train to decelerate or stop as appropriate.

[0024] S24, Historical Retrospective of Digital Track System Operation: The digital track simulation platform calls video stream data from the real-time database of the central digital track server, imports it and drives the model, and timestamps are synchronized to visualize and reproduce historical scenes.

[0025] S3. A real-time communication mechanism is established between the digital track simulation platform and the internal digital track testing platform: The internal digital track testing platform includes a test navigation control unit. Communication between the digital track simulation platform and the test navigation control unit uses data packets based on UDP / TRDP. During the simulation, the digital track simulation platform sends the vehicle position, speed, attitude, and angular velocity information calculated in real time for each frame of the rubber-tired train vehicle dynamics model to the preset digital track mathematical model of the test navigation control unit in the form of network data packets. Subsequently, based on the pre-loaded electronic map and magnetic coding data, it quickly retrieves and calculates the magnetic nail information closest to the current vehicle, then adds environmental perception simulation information and integrates the magnetic nail information calculation. The calculation results are injected into the vehicle's lateral and longitudinal control algorithms. When the vehicle's lateral and longitudinal control algorithms give control commands, the lateral and longitudinal control commands are encapsulated and sent to the vehicle dynamics model through network data packets, thereby driving the vehicle dynamics model to perform the next frame of simulation calculation and operation.

[0026] In the aforementioned intelligent digital rail transit simulation and testing method based on digital twin technology, step S3 involves adding a machine self-learning model training stage to the digital rail simulation platform. This stage is used to filter abnormal data and enhance the predictive capability of the digital rail mathematical model. First, the data is divided into training and test sets proportionally. Second, the model is trained using the training set data, parameters are adjusted to reduce training errors, and the model's predictive performance is evaluated on the test set. This process is repeated several times, and the average is taken to reduce data partitioning errors. Finally, features and the model are continuously optimized based on the prediction error to improve prediction accuracy. The key parameters of the calibrated vehicle control model state machine are output, which in turn assist in the optimization design of the algorithm.

[0027] In the above-mentioned intelligent digital rail transit simulation test method based on digital twin technology, in step S3, a driving simulator is added to the internal test platform of the digital rail. The communication between the driving simulator and the digital rail simulation platform is established by using CAN / serial communication. By simulating the input of third-party control commands, the smoothness of the driving mode switching of the digital rail mathematical model and the anti-disturbance capability of the simulation test system are verified.

[0028] The technical solution of the intelligent digital rail transit simulation test system and method of the present invention has the following beneficial effects:

[0029] (1) It solves the problem that the application of digital twin technology in the intelligent transportation industry not only focuses on data interaction (monitoring but not control). In the intelligent digital rail transit simulation test system, the system is no longer simply monitoring the equipment status, but can also control the equipment status changes in real time. Combined with remote sensing technology, the operation of rubber-tired trains can be remotely controlled. This poses a great challenge to the safety of the operation process. The premise of ensuring all this is based on the environmental perception fusion technology of digital rail and the ultra-low latency real-time communication technology of 5G, and a dual early warning mechanism of on-board human-machine + remote based on the level of safety hazards.

[0030] (2) The application of digital twin technology in the intelligent transportation industry not only involves establishing big data analysis models. In intelligent digital rail transit simulation and testing systems, the system no longer simply collects massive amounts of data for model prediction. If the data is not preprocessed to remove large-deviation error data, the results are often unreliable. Considering that the operating data of intelligent digital rail transit systems is subject to many interference factors, artificial intelligence machine learning technology is introduced, which has a good processing mode for noisy data and prediction confidence intervals. It can also provide assistance in the parameter tuning and design of the back-calculation algorithm.

[0031] (3) It addresses the issue that the application of digital twin technology in the intelligent transportation industry not only focuses on the visualization of customer needs. As the name suggests, the intelligent digital rail transit simulation and testing system incorporates the simulation and testing of internal enterprise requirements systems. A hardware-in-the-loop (HIL) simulation testing platform has been established, which can simultaneously connect to real vehicles and simulators. At this point, the system is transformed into an internal testing platform before product release. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of an intelligent digital rail transit simulation and testing system based on digital twin technology.

[0033] Figure 2 A schematic diagram illustrating the communication between the digital track simulation platform and the central digital track server;

[0034] Figure 3This is a schematic diagram illustrating the data flow between the digital track simulation platform and the digital track internal testing platform.

[0035] Figure 4 A flowchart illustrating the simulation test process of the intelligent digital rail transit simulation test system of this invention for model vehicles. Detailed Implementation

[0036] To enable those skilled in the art to better understand the technical solution of the present invention, its specific embodiments are described in detail below with reference to the accompanying drawings:

[0037] Please see Figures 1 to 3 The intelligent digital rail transit simulation and testing system of the present invention combines a rubber-tired train vehicle dynamics model and, based on the model data and digital rail urban construction coordinate map, jointly designs and builds a digital rail 3D visualization simulation platform (hereinafter referred to as "digital rail simulation platform"), which is deployed on the central digital rail system management server (hereinafter referred to as "central digital rail server").

[0038] On one hand, a real-time communication interface between the vehicle and the ground has been established. The onboard navigation control unit (NCU) of the rubber-tired train obtains the status of key operating equipment and operating data through the in-vehicle communication network, and then transmits the corresponding data back to the central digital track server through the digital track vehicle-ground dedicated network. After monitoring whether there are any abnormalities in these data, the digital track simulation test platform, through the platform dispatcher, decides whether to remotely operate the equipment or take over the automatic operation control of the vehicle. At this time, the 3D model will also reproduce the scene in real time.

[0039] On the other hand, a real-time communication interface was also established between the digital track simulation platform and the digital track hardware-in-the-loop (HIL) internal testing platform (hereinafter referred to as the "digital track internal testing platform"). After acquiring the digital track test data, the digital track simulation platform feeds the data into the machine learning model of train control. Through repeated training and testing iterations, the optimized parameters are substituted into the digital track internal testing platform. This improves the effectiveness of the testing while simultaneously refining the algorithm design.

[0040] The intelligent digital rail transit simulation and testing system based on digital twin technology of the present invention includes a digital track simulation platform 1, a digital track internal testing platform 2, and a central digital track server 3.

[0041] The Digital Track Simulation Platform 1 is a visualized 3D scene model of digital track, which is jointly designed and built by combining the dynamic model of rubber-tired train vehicles and relying on the dynamic model data of rubber-tired train vehicles and the digital track urban construction coordinate map. The Digital Track Simulation Platform 1 can be used for equipment monitoring, scene management, historical backtracking and machine learning.

[0042] The digital track internal test platform 2 includes a test navigation control unit 21, which is pre-loaded with a digital track mathematical model, electronic map, magnetic coding data, and environmental perception simulation information.

[0043] The central digital track server 3 is a digital track system management server deployed at the center. The central digital track server 3 has a built-in real-time database 31 and a digital track rule base 32.

[0044] The onboard navigation control unit of the rubber-tired train obtains the status of roadside equipment and driving data through the in-vehicle communication network, and transmits the corresponding data back to the central data track server 3 through the 5G vehicle-to-ground communication private network 4, where it is stored in the real-time database 31 of the central data track server 3.

[0045] The digital track simulation platform 1 monitors whether there are any abnormalities in the data in the real-time database 31 of the central digital track server 3, and decides whether to remotely operate the equipment or take over the automatic operation control of the vehicle through the platform dispatcher. At the same time, the digital track simulation platform 1 calls the data in the real-time database of the central digital track server to drive the operation of the digital track 3D scene model, mapping the operating status of vehicles and roadside equipment in the real environment.

[0046] Communication between the digital track simulation platform 1 and the test navigation control unit 21 uses UDP / TRDP-based data packets. During the simulation, the digital track simulation platform 1 sends the vehicle position, speed, attitude, and angular velocity information calculated in real time for each frame of the rubber-tired train vehicle dynamics model to the pre-set digital track mathematical model of the test navigation control unit 21 in the form of network data packets. Then, based on the pre-loaded electronic map and magnetic coding data, it quickly retrieves and calculates the information of the magnetic nail closest to the current vehicle, adds environmental perception simulation information, and integrates the magnetic nail information calculation. The calculation results are injected into the vehicle's lateral and longitudinal control algorithms. When the vehicle's lateral and longitudinal control algorithms give control commands, the lateral and longitudinal control commands are encapsulated and sent to the vehicle dynamics model through network data packets, thereby driving the vehicle dynamics model to perform the next frame of simulation calculation and operation.

[0047] After acquiring the digital track test data, the digital track simulation platform 1 imports the digital track test data into the machine self-learning model used for rubber-tired train control. Through repeated training and testing iterations, the optimized parameters are substituted into the internal testing platform of the digital track, thereby improving the effectiveness of the test and refining the algorithm design.

[0048] The digital track internal test platform 2 also includes a driving simulator 22. Communication between the driving simulator 22 and the digital track simulation platform 1 is established using CAN / serial communication. By simulating the input of third-party control commands, the smoothness of the driving mode switching of the digital track mathematical model is verified (the system is set to exit the automatic driving mode by pressing the brake pedal) and the anti-disturbance capability of the simulation test system are verified (if the steering wheel is accidentally turned when the vehicle is running automatically, the heading angle exceeds the preset threshold and the direction will be automatically corrected).

[0049] A method for simulating and testing intelligent digital rail transit based on digital twin technology, characterized by the following steps:

[0050] S1. Create a 3D scene model based on a high-precision map of the digital magnetic source and build a digital track simulation platform. This includes the following steps:

[0051] S11, Generate a 2D digital track scene model: High-precision mapping of magnetic nail coordinates, creation of a magnetic nail urban construction coordinate map using CAD, fixing the RTK antenna to the front of the rubber-tired train, and manually collecting high-precision GPS train trajectory data; after fitting the GPS trajectory to the magnetic nail map, create a 2D digital track scene model 5 (see...). Figure 2 );

[0052] S12, Digital Model Conversion to Generate Digital Track Simulation Platform: Based on the 2D scene model based on digital twin technology and the 3D mechanical drawings of roadside facilities and equipment, 3D visualization 1:1 modeling and restoration is carried out, and the status information of all equipment is displayed through the ECharts front end to obtain the digital track 3D scene model and build the framework of the digital track simulation platform.

[0053] S2, the scene model establishes a real-time communication mechanism with the rubber-tired train, which specifically includes the following steps:

[0054] S21, Digital Rail Vehicle-to-Ground Data Communication: When the rubber-tired train is powered on, the onboard controller, sensors, and processor transmit the driving data to the onboard navigation control unit (NCU) in real time via the TRDP protocol. The roadside equipment is first collected by the roadside unit (RSU), processed once by the edge computing unit (MEC), and then transmitted to the NCU via the 5G vehicle-to-ground communication network. The NCU fuses and calculates the driving data and roadside data, and then sends the resulting optimal control command to the vehicle actuators, causing the rubber-tired train to take corresponding actions. At the same time, the above data information is also forwarded to the central rail data server 3 via the 5G vehicle-to-ground communication network 4 and stored in the real-time database 31 of the central rail data server 3. The rail simulation platform 1 then calls the data in the real-time database 31 to drive the operation of the digital rail 3D scene model, thereby mapping the operating status of the vehicle and roadside equipment in the real environment.

[0055] S22, Digital Track System Fault Early Warning: Based on fault code feedback provided by various devices and stored in a real-time database, corresponding status codes are assigned according to the fault level, and different colors are set to display them in the front-end visualization area of ​​the central digital track server 3; the fault levels are divided into operational safety faults and operational non-safety faults;

[0056] S23, Remote control of digital rail system trains: Under the condition of meeting the automatic driving operation requirements, the operating status of the rubber-tired train is remotely operated via a dedicated 5G peripheral device on the control computer. The operating status of the rubber-tired train includes starting and stopping, acceleration and deceleration, and entering / switching / exiting the lateral and longitudinal automatic control modes. At this time, combined with the fault feedback status in step S22, when an operational safety fault is reported, the system is forced to stop; when an operational non-safety fault is reported, personnel can remotely operate the train to decelerate or stop as appropriate.

[0057] S24, Historical Retrospective of Digital Track System Operation: The digital track simulation platform calls video stream data from the real-time database of the central digital track server, imports it and drives the model, and timestamps are synchronized to visualize and reproduce historical scenes.

[0058] S3 establishes a real-time communication mechanism between the digital track simulation platform and the internal digital track testing platform.

[0059] S31, Data Communication between the Digital Track Simulation Platform and the Internal Data Platform: The digital track internal test platform includes a test navigation control unit. Communication between the digital track simulation platform and the test navigation control unit uses UDP / TRDP-based data packets. During the simulation, the digital track simulation platform sends the vehicle position, speed, attitude, and angular velocity information calculated in real time for each frame of the rubber-tired train vehicle dynamics model to the preset digital track mathematical model in the test navigation control unit in the form of network data packets. Subsequently, based on the pre-loaded electronic map and magnetic coding data, it quickly retrieves and calculates the information of the magnetic nail closest to the current vehicle (magnetic nail polarity, magnetic nail deviation, etc.), and then adds environmental perception simulation information and integrates the magnetic nail information calculation. The calculation results are injected into the vehicle's lateral and longitudinal control algorithms. When the vehicle's lateral and longitudinal control algorithms give control commands, the lateral and longitudinal control commands are encapsulated and sent to the vehicle dynamics model through network data packets, thereby driving the vehicle dynamics model to perform the next simulation calculation and operation.

[0060] S32, Digital Track Model Self-Learning Reinforcement Training Mechanism: A machine self-learning model training stage is added to the digital track simulation platform to filter abnormal data and enhance the predictive ability of the digital track mathematical model. First, the data is divided into training and test sets proportionally. Second, the model is trained using the training set data, parameters are adjusted to reduce training error, and the model's prediction effect is evaluated on the test set. The above process is repeated several times and then averaged to reduce data partitioning error. Finally, features and the model are continuously optimized based on the prediction error to improve prediction accuracy. The key parameters of the calibrated vehicle control model state machine are output, and this is used to assist in the optimization design of the algorithm.

[0061] A driving simulator 22 was added to the digital track internal test platform 2. Communication between the driving simulator 22 and the digital track simulation platform 1 was established using CAN / serial communication. By simulating the input of third-party control commands, the smoothness of the driving mode switching of the digital track mathematical model and the anti-disturbance capability of the simulation test system were verified.

[0062] The intelligent digital rail transit simulation and testing system based on digital twin technology of the present invention (hereinafter referred to as the "digital rail simulation and testing system") differs from conventional intelligent transportation simulation systems, mainly in that:

[0063] 1. The fundamental difference between rail transit and road public transport simulation systems lies in:

[0064] (1) Different vehicle types and carrying capacities. Due to the differences in chassis, the complexity of establishing simulation dynamic models and the parameter setting rules for rail trains and buses are completely different. The digital rail simulation test system uses a new type of rubber-tired train as the carrier of rubber-tired trolleybuses on the road. Its chassis design retains the core of rail trains while combining the road advantages of bus steering, traction and braking systems. When establishing the simulation kinematic model, it takes into account environmental constraints such as road bearing capacity, and ensures predictable road operating conditions such as insufficient or saturated carrying capacity.

[0065] (2) Different travel routes and operational organization. Rail transit has fixed infrastructure such as operating lines and stations, resulting in better peak-shaving and valley-filling effects. In contrast, the routes and schedules of surface buses are complex and greatly affected by traffic conditions. The digital rail simulation testing system effectively combines the advantages of fixed rail transit infrastructure (dedicated lanes built based on digital magnetic tags) and relatively simple network operation organization with the flexibility of surface bus scheduling, the ability to set green wave traffic, and signal priority control. Multiple operating conditions and strategies can be set during traffic flow simulation to improve the accuracy of the output results.

[0066] 2. Differences in virtual-real mapping and the degree of information interaction:

[0067] Conventional intelligent transportation simulation systems typically include 3D visualization rendering, dynamics / kinematic models of rubber-tired trolleys, behavioral modeling, traffic flow simulation management and control, and result analysis. However, these simulation models are often activated using historical data or delayed communication, significantly reducing the timeliness of the results.

[0068] The digital track simulation testing system relies on the dedicated communication network at the actual vehicle's location to transmit the comprehensive operational status of the rubber-tired tram back to the simulation system in real time. Control commands are input into the simulation system, and the actual vehicle responds accordingly upon receiving the information. Simultaneously, each equipment module is an independent information source, and its mapping in the simulation system not only synchronizes information but also reproduces the physical state of the equipment to a certain extent. For example, regarding information synchronization, if the actual rubber-tired tram does not detect a certain magnetic tag, the corresponding magnetic tag model icon in the simulation system will light up in a different color, and selecting the magnetic tag will automatically display its relevant information. Regarding the monitoring of the physical state of equipment, if the steering wheel of the actual rubber-tired tram turns at a certain angle, the steering wheel inside the rubber-tired tram model in the simulation system will also turn by the same angle. The mapping of the status of other facilities such as traffic lights is similar. This is a new application of digital twin technology in intelligent digital track systems.

[0069] Furthermore, the digital track simulation testing system also possesses testing and verification capabilities, as well as algorithm optimization capabilities. In principle, the system can simulate and reproduce its operating state using both static historical data and dynamic real-time communication. By incorporating noise factors to perform disturbance rejection analysis on the system's operating results, the resulting deviation data can be proportionally grouped and substituted into the training and testing sets of the algorithm model for self-learning. Based on the prediction error, the features and model are continuously optimized to improve prediction accuracy.

[0070] The intelligent digital rail transit simulation testing system and method of this invention relies on the dedicated communication network at the actual vehicle's location to transmit the comprehensive operating status of the rubber-tired trolley back to the simulation system in real time. Control commands are input into the simulation system, and the actual vehicle takes corresponding actions upon receiving the information. Simultaneously, each device module is an independent information source, and its mapping on the simulation system not only synchronizes information but also reproduces the physical state of the equipment to a certain extent. Regarding information synchronization, for example, if the actual trolley does not detect a certain magnetic tag, the corresponding magnetic tag model icon in the simulation system will light up in a different color, and selecting the magnetic tag will automatically display its relevant information. Regarding the monitoring of the physical state of the equipment, for example, if the steering wheel of the actual trolley turns a certain angle when turning, the steering wheel inside the trolley model in the simulation system will also turn by the same angle.

[0071] Please see Figure 4When testing model vehicles using the intelligent digital rail transit simulation test system of this invention, the model vehicle starts, loads the electronic map of the operating line, and displays the initial heading angle value of the simulated vehicle. In manual mode, the vehicle moves slowly and matches the entry marker. When the model vehicle meets the entry status, press the command key on the driving simulator 22 once, and the model vehicle then enters the automatic driving mode. If it is necessary to exit the automatic driving mode, simply press the brake pedal. During the automatic driving of the model vehicle, if the steering wheel is mistakenly operated while moving, the model vehicle first determines whether the changed heading angle value is within a preset threshold range. If it is within this preset threshold range, the model vehicle feeds back the heading angle information to the driving simulator 22, and the steering wheel automatically corrects the course; if it is not within this preset threshold range, the vehicle automatically applies emergency brakes and exits the automatic driving mode.

[0072] In summary, the intelligent digital rail transit simulation testing system and method of the present invention can not only monitor the status of train equipment, but also control the changes in the status of train equipment in real time. It introduces artificial intelligence machine learning technology to improve the effectiveness of testing. It can simultaneously connect to a real vehicle and a simulator, at which point the system is transformed into an internal testing platform before product release.

[0073] Those skilled in the art should recognize that the above embodiments are merely illustrative of the present invention and are not intended to limit the present invention. Any variations or modifications to the above embodiments that are within the spirit and essence of the present invention will fall within the scope of the claims of the present invention.

Claims

1. An intelligent digital rail transit simulation test system based on digital twin technology, characterized in that, Comprise a number track simulation platform, a number track internal test platform and a central number track server, wherein: The number track simulation platform is combined with a rubber-tyred train vehicle dynamics model, and is jointly designed and built on the basis of the rubber-tyred train vehicle dynamics model data and a digital track urban construction coordinate map to form a visual digital track 3D scene model. The number track internal test platform comprises a test navigation control unit, and the test navigation control unit is pre-provisioned with a digital track mathematical model, an electronic map, magnetic coding data and environment perception simulation information. The central number track server is a digital track system management server deployed in the center, and is pre-provisioned with a real-time database and a number track rule library. The on-board navigation control unit of the rubber-tyred train acquires the status of roadside equipment and driving data through an in-vehicle communication network, and transmits the corresponding data back to the central number track server through a 5G train-ground communication private network, and stores the data in the real-time database of the central number track server. The number track simulation platform monitors the data in the real-time database of the central number track server for abnormalities, and determines whether to remotely operate the equipment or take over the automatic operation control of the vehicle through a platform dispatcher, and simultaneously calls the data in the real-time database of the central number track server to drive the digital track 3D scene model to operate, and maps the running status of the vehicle and roadside equipment in the real environment. The communication between the number track simulation platform and the test navigation control unit adopts UDP / TRDP-based data packets, and in the simulation process, the number track simulation platform sends the vehicle position, speed, attitude and angular velocity information calculated in real time for each frame of the rubber-tyred train vehicle dynamics model to the digital track mathematical model pre-provisioned in the test navigation control unit in the form of network data packets, and then quickly retrieves and solves the magnetic nail information closest to the current vehicle according to the pre-loaded electronic map and magnetic coding data, and further adds environment perception simulation information and fuses the magnetic nail information to solve, and injects the solving result into the vehicle lateral and longitudinal control algorithm, and when the vehicle lateral and longitudinal control algorithm gives a control instruction, the lateral and longitudinal control instruction is packaged and sent to the vehicle dynamics model through a network data packet, so as to drive the vehicle dynamics model to perform the next frame of simulation calculation and operation.

2. The intelligent digital rail transit simulation test system of claim 1, wherein, After the number track simulation platform acquires the number track test data, the number track test data is imported into a machine self-learning model for rubber-tyred train control, and through repeated training and test iteration, the optimized parameters are substituted into the number track internal test platform, so as to improve the test effectiveness and improve the algorithm design.

3. The intelligent digital rail transit simulation test system of claim 1, wherein, The number track internal test platform further comprises a driving simulator, and a CAN / serial communication mode is adopted to establish communication between the driving simulator and the number track simulation platform, and a third-party control instruction is inputted to verify the smoothness of the driving mode switching of the digital track mathematical model and the anti-disturbance capability of the simulation test system.

4. An intelligent digital rail transit simulation test method based on digital twin technology, characterized in that, Comprise the following steps: S1, form a 3D scene model based on a digital magnetic source high-precision map, build a number track simulation platform, specifically comprising the following procedures: S11, generate a digital track 2D scene model: high-precision surveying and mapping of magnetic nail coordinate points, drawing a magnetic nail urban construction coordinate map, fixing an RTK antenna to the head of a rubber-tyred train, and collecting high-precision GPS train running tracks by manual driving; after fitting the GPS and the track of the magnetic nail map, a digital track 2D scene model is drawn; S12, digital-analog conversion to generate a digital track simulation platform: relying on the 2D scene model based on digital twinning technology and the 3D mechanical drawings of roadside facilities and equipment, 3D visual 1:1 modeling is restored, and the state information of all equipment is displayed through echarts front-end, a digital track 3D scene model is obtained, and a digital track simulation platform framework is built; S2, a real-time communication mechanism is established between the scene model and the rubber-tyred train, which includes the following procedures: S21, digital track train-ground data communication: in the powered state, the vehicle-mounted controller, sensor and processor of the rubber-tyred train transmit real-time driving data to the vehicle-mounted navigation control unit through the TRDP protocol, while the roadside equipment is first collected by the roadside unit, processed by the edge computing unit, and then transmitted to the vehicle-mounted navigation control unit through the 5G train-ground communication private network, the vehicle-mounted navigation control unit fuses and solves the driving data and the roadside data, and then sends the optimal control instructions obtained to the vehicle actuator, so that the rubber-tyred train makes corresponding actions; at the same time, the above data information is also forwarded to the central digital track server through the 5G train-ground communication private network and stored in the real-time database of the central digital track server; the digital track simulation platform calls the data in the real-time database to drive the digital track 3D scene model to run, so as to map the running state of the vehicle and the roadside equipment in the real environment; S22, digital track system fault early warning: based on the fault code feedback provided by each device stored in the real-time database, the corresponding state code is given according to the fault level, and different colors are displayed in the front-end visualization area of the central digital track server; the fault level is divided into operation safety class faults and operation non-safety class faults; S23, digital track system train remote control: under the condition of meeting the automatic driving operation, the running state of the rubber-tyred train is remotely operated through the 5G remote operation of the special peripheral equipment of the control computer, including the start-stop, acceleration-deceleration and automatic control mode entering / exiting of the rubber-tyred train; at this time, combined with the fault feedback status in step S22, when the operation safety class fault is reported, the system is forced to stop; when the operation non-safety class fault is reported, the train is slowed down or stopped by remote operation of personnel as appropriate; S24, digital track system operation history backtracking: the digital track simulation platform calls the video stream data in the real-time database of the central digital track server, imports and drives the model, and synchronously visualizes the historical scene by time stamp. S3, the numerical track simulation platform and the numerical track internal test platform establish a real-time communication mechanism: the numerical track internal test platform includes a test navigation control unit, and communication between the numerical track simulation platform and the test navigation control unit adopts a UDP / TRDP-based data packet. During simulation, the numerical track simulation platform sends vehicle position, speed, attitude, and angular velocity information calculated in real time for each frame of the rubber-tyred train vehicle dynamics model to the digital track mathematical model preset in the test navigation control unit in the form of a network data packet. Subsequently, according to the electronic map and magnetic code data loaded in advance, the current vehicle distance from the nearest magnetic nail information is quickly searched and calculated, environmental perception simulation information is added, and the magnetic nail information is calculated and fused. The calculation result is injected into the vehicle lateral and longitudinal control algorithm. When the vehicle lateral and longitudinal control algorithm gives a control instruction, the lateral and longitudinal control instruction is packaged and sent to the vehicle dynamics model through a network data packet to drive the vehicle dynamics model to perform the next frame of simulation calculation and operation.

5. The intelligent digital rail transit simulation test method based on digital twin technology according to claim 4, characterized in that, In step S3, a machine self-learning model training link is added to the numerical track simulation platform to filter abnormal data and enhance the prediction ability of the digital track mathematical model. First, the data is divided into a training set and a test set according to a proportion. Second, the training set data is used to train the model, the parameters are adjusted to reduce the training error, and the model prediction effect is evaluated on the test set. The above process is repeated several times to reduce the data division error. Finally, the features and model are continuously optimized according to the prediction error to improve the prediction accuracy, and the calibrated vehicle control model state machine key parameters are output. The algorithm optimization design is assisted in the reverse direction.

6. The intelligent digital rail transit simulation test method based on digital twin technology according to claim 4, characterized in that, In step S3, a driving simulator is added to the numerical track internal test platform. The communication between the driving simulator and the numerical track simulation platform is established by using the CAN / serial communication mode. The third-party control instruction input is simulated to verify the smoothness of the driving mode switching of the digital track mathematical model and the anti-disturbance ability of the simulation test system.

Images