Digital twinning system, method and device for traction transmission system of rail transit vehicle

Abstract

The invention provides a digital twin system, method and device for a traction transmission system of a rail transit vehicle, and the system comprises a multi-time-scale digital twin architecture composed of a physical entity layer, an interactive perception layer, a vehicle-mounted virtual body layer, a ground virtual body layer and a smart cloud platform layer. A vehicle-mounted digital twinborn board card is used for depicting a vehicle-mounted small-time-scale real-time digital twinborn body, the high requirements of an electrical model in a traction transmission system of a rail transit vehicle for discretization frequency and resolving real-time performance are met, and the sampling precision of data is guaranteed; in a ground virtual body layer, a server is used for describing a ground-level large-time-scale real-time digital twinborn body at a cloud end, when an actual traction system is abnormal, early warning and adjustment can be carried out in time, the consistency of a model calculation result and an actual system state is ensured, communication with other digital twinborn bodies can be carried out, and the real-time performance of the traction system is improved. Safe and reliable operation of a traction transmission system is guaranteed, and finally reliability improvement, data mining and information fusion of all key systems of the whole vehicle are promoted.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a digital twin system, method and device for a rail transit vehicle traction drive system. Background Art

[0002] At present, the digital twin projects that have been applied in the field of rail transit are mainly concentrated in station comprehensive situation monitoring, vehicle operation and maintenance, traction power supply system, and vehicle braking system. All twins are installed on ground servers and modeled and operated in the cloud. Among them, station comprehensive situation monitoring and traction power supply systems are stationary physical objects. Therefore, high-speed data communication means can be selected to transmit data results to high-performance ground servers to build complex and sophisticated digital models to meet the high requirements of real-time and accuracy of virtual body solution. Although vehicle operation and maintenance and vehicle braking systems are high-speed moving physical objects, most of their digital twin applications are aimed at modeling the large-time scale dynamic processes of large inertia physical objects, and have low requirements for real-time model solution. Therefore, despite the limitations of real-time vehicle-ground data transmission, low-bandwidth data transmission and building models in high-performance ground servers can also meet the needs.

[0003] However, since the traction drive system is a high-speed mobile equipment, it is limited by the rate, delay, bandwidth and packet loss rate of wireless transmission of vehicle-to-ground data. The modeling methods in the existing technology cannot meet the requirements of sampling precision, accuracy and real-time performance of the input data of the digital twin model of the traction system, and cannot meet the real-time perception of the current state of the actual system. When an abnormality occurs in the actual traction system or the parameters change, the model solution results will have large errors and be inconsistent with the actual system state. Summary of the invention

[0004] One object of the present invention is to provide a digital twin system of a traction drive system of a rail transit vehicle, which uses a multi-time scale digital twin architecture composed of a physical entity layer, an interactive perception layer, a vehicle-mounted virtual body layer, a ground virtual body layer and a smart cloud platform layer, and uses a vehicle-mounted digital twin board to realize the characterization of a vehicle-level small time scale real-time digital twin, which meets the high requirements of the electrical model in the traction drive system of the rail transit vehicle for the discrete frequency and the real-time performance of the solution, and ensures the sampling accuracy, accuracy and real-time performance of the data, and provides a good platform foundation for the application of digital twin technology in the traction drive system of the rail transit vehicle; at the same time, in the ground virtual body layer, a server is used to realize the characterization of the ground-level large time scale real-time digital twin in the cloud, which meets the real-time perception of the current state of the actual system, and when an abnormality occurs in the actual traction system, it can be timely warned and adjusted to ensure the consistency of the model solution result with the actual system state, and can also communicate with other digital twins, and provide information feedback in time to ensure the safe and reliable operation of the traction drive system, and finally help improve the reliability, data mining and information fusion of the key systems of the entire vehicle. Another object of the present invention is to provide a digital twin method for the traction drive system of a rail transit vehicle. Another object of the present invention is to provide a digital twin device of a rail transit vehicle traction drive system. Another object of the present invention is to provide a computer readable medium. Another object of the present invention is to provide a computer device.

[0005] In order to achieve the above objectives, the present invention discloses a digital twin system of a rail transit vehicle traction drive system, the system comprising: a physical entity layer, an interactive perception layer, an on-board virtual body layer, a ground virtual body layer and a smart cloud platform layer;

[0006] The physical entity layer includes traction converter, traction motor and traction control system. The traction control system is used to control the operation of traction converter and traction motor.

[0007] The interactive perception layer is used to detect the operating status data of the physical entity layer;

[0008] The vehicle-mounted virtual body layer is used to perform time-scale real-time simulation calculations based on the operating status data and the acquired digital quantity information through the pre-built real-time digital twin model of the traction drive system, and generate simulation external feature quantities and internal parameter information;

[0009] The ground virtual volume layer is used to generate key component monitoring data based on the operating status data and internal parameter information through the preset visualized geometric real-time digital twin model of the key components of the traction drive system;

[0010] The smart cloud platform layer is used to generate warning messages based on the warning signals sent by the vehicle-mounted virtual body layer, and send the warning messages to the stored digital twins of each traction drive system.

[0011] Preferably, the operating status data includes actual external characteristic quantities and calculated status data, and the traction control system further includes an analog quantity acquisition board;

[0012] The interactive perception layer is used to detect various types of signals from the traction converter, traction motor and traction control system through various types of sensors to generate sensor signal data;

[0013] The interactive perception layer is used to convert data based on the sensor signal data through the analog quantity acquisition board to generate actual external characteristic quantities; it performs edge computing based on the actual external characteristic quantities, the received control instructions and the preset self-control parameters to generate computing status data.

[0014] Preferably, the interactive perception layer is also used to preprocess the running status data to generate preprocessed running status data, and the preprocessing includes noise reduction, alignment and screening.

[0015] Preferably, the vehicle-mounted virtual body layer is used to iteratively update the model's internal parameter information according to digital quantity information, actual external characteristic quantities and calculated state data through a particle swarm algorithm and a preset objective function, so as to construct a real-time digital twin model of the traction drive system.

[0016] Preferably, the vehicle-mounted virtual body layer is also used to obtain the initial value and update value of the internal parameter information of the real-time digital twin model of the traction transmission system; perform anomaly detection based on the initial value and update value; if an abnormality in the internal parameter information is detected, generate a warning signal, and send the warning signal to the smart cloud platform layer.

[0017] Preferably, the ground virtual body layer is used to construct a visualized geometric real-time digital twin model of key components of the traction drive system based on three-dimensional lightweight technology and according to internal parameter information and operating status data output by the real-time digital twin model of the traction drive system.

[0018] Preferably, the ground virtual body layer is used to perform abnormality detection on key components through preset key component indicator thresholds, based on key component monitoring data and internal parameter information detection results; if a key component abnormality is detected, a warning signal is generated and sent to the smart cloud platform layer.

[0019] Preferably, the ground virtual body layer is also used to construct an offline digital twin model by performing offline iterative calculations based on acquired historical data, multi-physical field coupling parameters, actual external characteristic quantities, internal parameter information and key component monitoring data through a particle swarm algorithm.

[0020] Preferably, the ground virtual body layer is also used to perform offline simulation prediction based on input simulation instruction data through an offline digital twin model to generate simulation prediction results.

[0021] The present invention also discloses a digital twin method for a rail transit vehicle traction drive system, which is applied to the above-mentioned rail transit vehicle traction drive system digital twin system, and the method comprises:

[0022] Detecting the operation status data of the physical entity layer, the physical entity layer includes a traction converter, a traction motor and a traction control system, and the traction control system is used to control the operation of the traction converter and the traction motor;

[0023] Through the pre-built real-time digital twin model of the traction drive system, real-time simulation calculations are performed on a time scale based on the operating status data and the acquired digital quantity information to generate simulation external characteristic quantities and internal parameter information;

[0024] Generate key component monitoring data based on operating status data and internal parameter information through the preset visual geometric real-time digital twin model of key components of the traction drive system;

[0025] A warning message is generated according to the warning signal sent by the vehicle-mounted virtual body layer, and the warning message is sent to the stored digital twins of each traction drive system.

[0026] The present invention also discloses a digital twin device of a rail transit vehicle traction drive system, comprising:

[0027] The detection unit is used to detect the operating status data of the physical entity layer. The physical entity layer includes a traction inverter, a traction motor and a traction control system. The traction control system is used to control the operation of the traction inverter and the traction motor.

[0028] A real-time simulation unit is used to perform time-scale real-time simulation calculations based on the operating status data and the acquired digital quantity information through a pre-built real-time digital twin model of the traction drive system, and generate simulation external characteristic quantities and internal parameter information;

[0029] A key component monitoring unit is used to generate key component monitoring data based on operating status data and internal parameter information through a preset visual geometric real-time digital twin model of key components of the traction drive system;

[0030] The early warning unit is used to generate an early warning message according to the early warning signal sent by the vehicle-mounted virtual body layer, and send the early warning message to each stored digital twin of the traction drive system.

[0031] The present invention also discloses a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0032] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and the processor implements the above method when executing the program.

[0033] The present invention also discloses a computer program product, including a computer program / instruction, and the method described above is implemented when the computer program / instruction is executed by a processor.

[0034] The present invention uses a multi-time-scale digital twin architecture consisting of a physical entity layer, an interactive perception layer, an on-board virtual body layer, a ground virtual body layer and an intelligent cloud platform layer, and uses an on-board digital twin board to realize the characterization of on-board small-time-scale real-time digital twins, so as to meet the high requirements of the electrical model in the traction drive system of rail transit vehicles for discrete frequency and real-time solution, ensure the sampling precision, accuracy and real-time performance of the data, and provide a good platform foundation for the application of digital twin technology in the traction drive system of rail transit vehicles; at the same time, in the ground virtual body layer, a server is used to realize the characterization of ground-level large-time-scale real-time digital twins in the cloud, so as to meet the real-time perception of the current state of the actual system, and when an abnormality occurs in the actual traction system, it can timely warn and adjust to ensure the consistency between the model solution result and the actual system state, and can also communicate with other digital twins to provide timely information feedback to ensure the safe and reliable operation of the traction drive system, and ultimately help improve the reliability, data mining and information fusion of various key systems of the entire vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A schematic diagram of the architecture of a digital twin system of a rail transit vehicle traction drive system provided by an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of the structure of a physical entity of a rail transit vehicle traction drive system provided by an embodiment of the present invention;

[0038] Figure 3 A signal flow diagram of a digital twin architecture of a rail transit vehicle traction drive system provided by an embodiment of the present invention;

[0039] Figure 4 A flowchart of another digital twin method of a rail transit vehicle traction drive system provided by an embodiment of the present invention;

[0040] Figure 5 A schematic diagram of the structure of a digital twin device of a rail transit vehicle traction drive system provided by an embodiment of the present invention;

[0041] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] In order to facilitate the understanding of the technical solution provided by this application, the relevant contents of the technical solution of this application are explained below. Digitalization, networking, and intelligence are the prominent features of the new round of scientific and technological revolution, and are also the core of the new generation of information technology. Digital twins have attracted the attention of the rail transit industry with their deep integration of information technology and digital models. Through the interaction of physical objects and virtual models, digital twins can characterize the multi-dimensional attributes, actual behaviors and states of physical objects, predict the future development trends of physical objects, and invert the historical failure processes of physical objects, thereby realizing the actual functional services and application needs such as monitoring, simulation, prediction, and optimization of physical objects. Digital twins make full use of data such as physical models, sensor updates, and operation history, integrate multi-disciplinary, multi-physical quantities, multi-scale, and multi-probability simulation processes, and complete mapping in virtual space, thereby reflecting the full life cycle process of the corresponding physical equipment. The core of digital twins is a high-precision digital model, which can be a mathematical model based on physical equations or a data-driven model based on machine learning and artificial intelligence. The digital model is updated and synchronized with the real-time data of the actual physical system, so that it can accurately reflect the operating status, working performance, and service life of the physical system throughout its life cycle in real time.

[0044] In recent years, with the rapid development of the rail transit industry, the concepts of smart stations, digital trains, active safety control and intelligent operation and maintenance have been proposed one after another, which has put forward higher requirements for data mining and information fusion of key systems of stations and vehicles. Nowadays, digital twin technology has been introduced and applied in related majors such as station comprehensive situation monitoring, vehicle operation and maintenance, traction power supply system, and vehicle braking system, bringing people a more convenient, safe and comfortable travel experience. As an important subsystem of the vehicle, the traction drive system is the power source for vehicle operation. With the goal of achieving state perception, fault inversion, health management, performance prediction, etc., it is of great significance to build a digital twin system for it. However, due to the wide variety of components in the traction drive system and the existence of electromechanical, electromagnetic and thermal multi-physics field coupling, it is a complex system with multiple time scales and rich dynamic characteristics, such as: nanosecond-level power electronic switch dynamic process, microsecond-level electromagnetic transient process, millisecond-level to second-level electromechanical conversion process, and minute-level to hour-level long-term temperature or shape change process. Short-time-scale electrical models have high requirements for modeling discretization frequency and real-time solution. In view of this, for rail transit vehicle traction drive systems with high-speed movement, multi-physical field coupling, multiple time scales, and rich dynamic characteristics, the present application provides a digital twin architecture that combines real-time and offline models and is driven by both mechanism and data to solve the problem that the existing digital twin architecture cannot adapt to the characteristics of rail transit vehicle traction drive systems with high-speed movement, multi-physical field coupling, multiple time scales, and rich dynamic characteristics, as well as the high requirements for data acquisition accuracy, discretization frequency, and real-time solution of real-time twin model characterization.

[0045] Figure 1 A schematic diagram of the architecture of a digital twin system of a rail transit vehicle traction drive system provided by an embodiment of the present invention, such as Figure 1 As shown in the figure, the system architecture includes: physical entity layer, interactive perception layer, vehicle-mounted virtual body layer, ground virtual body layer and intelligent cloud platform layer. By adding the vehicle-mounted virtual body layer, the digital twin models of different time scales can be deployed in the vehicle-mounted virtual body layer and the ground virtual body layer respectively.

[0046] like Figure 1 As shown in the figure, the physical entity layer is the target object of the digital twin system of the rail transit vehicle traction drive system, including the physical entity of the vehicle traction drive system. The physical entity layer includes traction converters, traction motors and traction control systems. The traction converter includes but is not limited to reactance, capacitors, resistors, power modules, circuit breakers, contactors and fans.

[0047] like Figure 1As shown, the interactive perception layer is the basis of the digital twin system of the rail transit vehicle traction drive system. It connects the physical entity layer and the on-board virtual body layer, and is used to realize the interaction of information between the physical entity layer and the on-board virtual body layer. The interactive perception layer includes measurement perception and interactive feedback, where measurement perception includes but is not limited to temperature sensors, speed sensors, vibration sensors, voltage sensors, current sensors and edge computing; interactive feedback includes but is not limited to command control and operation and maintenance warning. The control system uses the output information of the digital twin model of the on-board virtual body layer and the digital twin model of the ground virtual body layer to perform command control and operation and maintenance warning on the physical entity layer.

[0048] Specifically, measurement perception refers to detecting the operating status data of the physical entity layer through the traction control system and various types of sensors in the traction control system. The operating status data includes actual external feature quantities and calculated status data, and the traction control system also includes an analog quantity acquisition board.

[0049] The interactive perception layer is used to detect various types of signals on the traction converter, traction motor and traction control system through various types of sensors to generate sensor signal data. The sensor signal data includes but is not limited to the traction converter power module temperature, traction inverter output current, traction converter grid-side current, intermediate DC side voltage, traction motor stator temperature, and traction motor speed.

[0050] It is worth noting that although installing more sensors in the traction drive system can directly enhance the understanding of the system's operating status, the cost-effectiveness issue often needs to be considered in engineering practice: the potential benefits of installing different numbers of sensors, initial investment, sensor failure rate and subsequent maintenance costs, equipment box space, weight, size, etc. need to be studied, analyzed and verified in practice. Therefore, the concept and technology of digital twins can be fully utilized to combine the sensor signal data with the control system's own control parameters and the received control instructions based on physical laws, perform edge computing in each board of the traction control system, enhance perception capabilities, and obtain real-time operating data of the sensorless part of the physical entity layer, that is, computing status data.

[0051] Specifically, the interactive perception layer is used to convert the sensor signal data into a voltage signal recognizable by the chip through the analog quantity acquisition board, and generate the actual external characteristic quantity; perform edge calculation according to the actual external characteristic quantity, the received control instruction and the preset self-control parameters to generate the calculation state data. Among them, the control instruction is externally input, such as: traction instruction, braking instruction, direction instruction; the self-control parameters include the power module drive pulse PWM; the calculation state data includes but is not limited to the support capacitor current, traction motor stator voltage, traction motor rotor resistance, traction motor output torque, filter reactance internal resistance; the actual external characteristic quantity includes but is not limited to the grid-side current, intermediate DC voltage, traction inverter output current, and traction motor speed.

[0052] Furthermore, the interactive perception layer is also used to preprocess the running status data to generate preprocessed running status data, and the preprocessing includes but is not limited to noise reduction, alignment and screening to ensure the accuracy of the data. The preprocessed running status data is sent to the vehicle-mounted virtual body layer, and then uploaded to the ground virtual body layer through the vehicle-ground data transmission channel through the vehicle-mounted virtual body layer, thereby realizing real-time and offline digital twin model characterization and update.

[0053] like Figure 1 As shown in the figure, the vehicle-mounted virtual body layer is the core component of the digital twin system of the traction drive system. The main task is to complete the construction of a simplified real-time digital twin model of the traction drive system based on the operating status data obtained by the interactive perception layer and using the high-performance vehicle-mounted digital twin board in the traction control system, so as to simplify the description of the electrical parts of the system with a small time scale, such as the traction transformer, the main circuit of the traction converter, the traction motor, etc., and use the actual external feature quantity and the particle swarm optimization algorithm to complete the iterative update of the model. Through the comparison and analysis of the simulated external feature quantity output by the real-time digital twin model and the actual external feature quantity, the health status and performance indicators of the system are evaluated online in real time.

[0054] Specifically, the on-board virtual body layer is used to perform time-scale real-time simulation calculations based on the running status data and the acquired digital quantity information through the pre-built real-time digital twin model of the traction drive system, and generate simulated external characteristic quantities and internal parameter information. The on-board virtual body layer is used to iteratively update the model's internal parameter information based on the digital quantity information, actual external characteristic quantities and calculated status data through the particle swarm algorithm and the preset objective function, and build a real-time digital twin model of the traction drive system. The on-board virtual body layer is also used to obtain the initial value and update value of the internal parameter information of the real-time digital twin model of the traction drive system; perform anomaly detection based on the initial value and update value; if anomalies in the internal parameter information are detected, generate a warning signal, and send the warning signal to the smart cloud platform layer.

[0055] like Figure 1 As shown in the figure, the ground virtual layer is an important part of the digital twin system of the traction drive system. Its main task is to receive data information obtained by the on-board virtual layer and the interactive perception layer, and use high-performance ground servers to complete the construction of a three-dimensional (3D) visualized geometry and physical real-time digital twin model of the ground-level traction drive system in the cloud, so as to describe the physical and geometric parts of the system on a large time scale, such as: traction electronic stator / rotor side temperature, filter reactor temperature, traction motor insulation status, traction converter box, and the appearance of key electrical components.

[0056] Specifically, the ground virtual body layer is used to construct a visualized geometric real-time digital twin model of the key components of the traction drive system based on the three-dimensional lightweight technology and according to the internal parameter information and operating status data output by the real-time digital twin model of the traction drive system; through the visualized geometric real-time digital twin model of the key components of the traction drive system, the key component monitoring data is generated according to the operating status data and internal parameter information; through the preset key component indicator thresholds, the key components are detected for abnormalities according to the key component monitoring data and the internal parameter information detection results; if a key component abnormality is detected, a warning signal is generated, and the warning signal is sent to the smart cloud platform layer.

[0057] At the same time, based on historical data and system operation mechanism, the ground server adopts a data-mechanism dual-driven approach to complete the construction of a complex offline digital twin model of the ground-level traction transmission system. The model iterates and updates parameters based on the data information obtained by the on-board virtual body layer and the interactive perception layer. Since the offline model does not require real-time performance, the complexity and accuracy of the modeling are improved. Compared with the on-board real-time digital twin model, the influence of electromechanical, electromagnetic and thermal multi-physical field coupling is comprehensively considered in the electrical main circuit. The model can use the actual data after downloading as the model input to drive the model to complete the system fault inversion offline; it can also input simulation data to complete performance prediction and other functions offline.

[0058] Specifically, the ground virtual body layer is also used to construct an offline digital twin model through offline iterative calculations based on the acquired historical data, multi-physical field coupling parameters, actual external characteristic quantities, internal parameter information and key component monitoring data through the particle swarm algorithm; through the offline digital twin model, offline simulation prediction is performed according to the input simulation instruction data to generate simulation prediction results.

[0059] like Figure 1As shown in the figure, the smart cloud platform layer is the last layer of the digital twin framework, which stores and manages the data output by the vehicle virtual body layer and the ground virtual body layer model, and realizes the information exchange and sharing between the digital twins of each traction drive system through cloud computing technology, as well as the information exchange and sharing between the digital twins of other systems such as braking and power supply. It is specifically used to realize real-time operation and maintenance data sharing, historical operation and test data sharing, real-time state perception and interaction, health management and performance prediction functions. In this way, when a traction drive system fails or is abnormal, the current problems, alarm information, fault root detection, diagnosis and maintenance information, solutions, etc. can be notified to each traction drive system digital twin that may have similar hidden dangers in a timely manner for early prevention. At the same time, it can also communicate with other digital twins and provide timely information feedback to ensure the safe and reliable operation of the traction drive system, and ultimately help improve the reliability, data mining and information fusion of the key systems of the entire vehicle.

[0060] Specifically, the smart cloud platform layer is used to generate a warning message based on the warning signal sent by the vehicle-mounted virtual body layer, and send the warning message to each stored digital twin of the traction drive system.

[0061] like Figure 1 As shown, the physical entity layer of the system architecture is the physical body of the traction transmission system, the interactive perception layer and the vehicle-mounted virtual body layer are the vehicle-mounted traction control system and sensors, and data collection and control are carried out between the physical body of the traction transmission system and the vehicle-mounted traction control system and sensors through hard lines; the ground virtual body layer and the intelligent sharing layer are built on the ground server, and real-time transmission of vehicle-to-ground data is carried out between the ground server and the vehicle-mounted traction control system and sensors.

[0062] This application is aimed at the traction drive system of rail transit vehicles, and provides a multi-time scale digital twin architecture including a physical entity layer, an interactive perception layer, an on-board virtual body layer, a ground virtual body layer, and a smart cloud platform layer. By adding an on-board virtual body layer and using the on-board digital twin board to realize the characterization of on-board small time scale real-time digital twins, it can meet the requirements of the electrical model in the traction drive system of rail transit vehicles for the high demand for discrete frequency and real-time solution. At the same time, in the ground virtual body layer, the server is used in the cloud to realize the characterization of the ground-level large time scale real-time digital twin.

[0063] This application uses a dual-driven approach based on data and mechanism at the ground virtual body layer based on historical data and system operation mechanism, comprehensively considers the influence of electromechanical, electromagnetic and thermal multi-physical field coupling, and completes the characterization of a complex offline digital twin model of the traction transmission system. Although this model is an offline model, it can iteratively update the model parameters based on the real-time data information uploaded by the on-board virtual body layer and the interactive perception layer through the vehicle-to-ground wireless communication. When a system failure occurs, the high-sampling precision actual data downloaded automatically or manually is used as the model input to drive the model to complete the system fault inversion offline; at the same time, the simulation data can also be manually input to complete the system performance prediction offline. The offline simulation model constructed by the present invention at the ground virtual body layer can realize automatic parameter updates according to the real-time data of the system, ensuring the consistency of the offline model with the actual system; and fully utilizes the computing power of the ground server, comprehensively considers the influence of electromechanical, electromagnetic and thermal multi-physical field coupling, and makes the model more accurate.

[0064] Figure 2 A schematic diagram of the structure of a physical entity of a rail transit vehicle traction drive system provided by an embodiment of the present invention, such as Figure 2 As shown, the physical entities include traction transformer, traction converter, traction motor and traction control system. Among them, the traction converter includes rectifier and traction inverter. The traction control system is used to control the operation of traction converter and traction motor. The traction control system is used to collect the secondary voltage output by the traction transformer and control the rectifier to perform AC / DC conversion to provide a stable DC voltage for the traction inverter; the traction control system is also used to control the traction inverter to perform DC / AC conversion and output variable frequency and voltage three-phase AC voltage to drive the traction motor to exert the command torque.

[0065] Figure 3 A signal flow diagram of a digital twin architecture of a rail transit vehicle traction drive system provided by an embodiment of the present invention, such as Figure 3 As shown, an intermediate DC circuit is set between the rectifier and the traction inverter. The secondary voltage of the 25kV grid after passing through the traction transformer is used as the system input. The traction control system outputs PWM drive pulses to control the rectifier for AC / DC conversion, providing a stable DC voltage for the traction inverter; then the traction control system outputs PWM drive pulses to control the traction inverter for DC / AC conversion, and outputs a variable frequency and voltage three-phase AC voltage to drive the traction motor to exert the command torque.

[0066] like Figure 3As shown, the traction control system includes a rectifier control board, an analog quantity acquisition board, a traction inverter control board, an on-board digital twin board, and a digital quantity acquisition board. In the digital twin architecture of the traction drive system of rail transit vehicles, various types of sensors are installed at different locations, including but not limited to current sensors, voltage sensors, temperature sensors, and speed sensors to detect various types of sensor signal data at different locations. As an optional solution, a current sensor is installed at the input end of the rectifier to collect the grid-side input current signal; a voltage sensor is installed in the intermediate DC side circuit to collect the intermediate DC voltage and ground voltage signals; a current sensor is installed at the output end of the traction inverter to collect the traction inverter output current signal; temperature sensors are installed on the heat dissipation substrates of the rectifier and traction inverter power modules respectively to collect temperature signals at different positions of the power module; speed and temperature sensors are installed on the traction motor to collect motor speed and stator temperature signals respectively.

[0067] In an embodiment of the present invention, the sensor signal data is conditioned by an analog quantity acquisition board, and the sensor signal data is converted into a voltage signal recognizable by a chip to generate an actual external characteristic quantity; the actual external characteristic quantity is transmitted to the rectifier control board and the traction inverter control board through a hard line as a necessary input for controlling the rectifier and the traction inverter. At the same time, the rectifier control board and the traction inverter control board combine the received control instructions and their own control parameters, such as: traction instructions, braking instructions, direction instructions, power module drive pulse PWM and other information, to perform edge computing in each board of the traction control system, enhance the perception capability, and obtain the calculation status data of the sensorless part of the physical entity layer in real time, such as: the current of the intermediate DC circuit support capacitor, the stator voltage of the traction motor, the rotor resistance of the traction motor, the actual torque value output by the traction motor, etc. The collected data and calculated data are pre-processed by noise reduction, alignment, screening, etc., and sent to the field programmable gate array (FPGA) component in the on-board digital twin board of the on-board virtual body layer using low voltage differential signaling (LVDS), thereby realizing real-time digital twin model characterization and updating.

[0068] like Figure 3As shown in the figure, the vehicle-level digital twin board adopts the architecture of the main central processing unit (CPU) plus the coprocessor FPGA. The coprocessor FPGA uses low voltage differential signaling (LVDS) communication to obtain the control signals and edge computing output information of the rectifier control board and the traction inverter control board in the traction control system, as well as the analog quantity output by the analog quantity acquisition board and the digital quantity information output by the digital quantity acquisition board at a communication rate of 50MHz. It is sent to the main CPU processor through the PCIE (Peripheral Component Interconnect Express) bus as the input for the simplified real-time digital twin model characterization of the traction drive system. The model discretization frequency is as high as 4kHz. Due to the use of vehicle-level digital twin boards, the high requirements of the real-time digital twin model of electrical components and electrical systems for data acquisition accuracy, discretization frequency and real-time solution can be met. At the same time, the output data of the digital twin model of the vehicle-mounted virtual body layer will also be uploaded to the ground server through the network system for use by the ground virtual body layer and the smart cloud platform layer.

[0069] It is worth mentioning that PCIE is a high-speed serial computer expansion bus standard, which is mainly used to connect high-speed devices to computer motherboards.

[0070] This application integrates a high-performance on-board digital twin board in the traction control system. The board uses the architecture of the main CPU processor plus the coprocessor FPGA. The coprocessor FPGA uses LVDS communication at a communication rate of 50MHz to synchronously obtain all control signals and edge computing output information of the traction control system, as well as analog and digital information obtained by the sensor, and sends them to the main CPU processor through PCIE as the input for the simplified real-time digital twin model of the traction drive system. The main CPU processor serves as the carrier of the simplified real-time digital twin model.

[0071] In the technical solution provided by the embodiment of the present invention, through the multi-time scale digital twin architecture composed of the physical entity layer, the interactive perception layer, the vehicle-mounted virtual body layer, the ground virtual body layer and the smart cloud platform layer, the vehicle-mounted digital twin board is used to realize the characterization of the vehicle-level small time scale real-time digital twin, which meets the high requirements of the electrical model in the traction drive system of the rail transit vehicle for the discrete frequency and the real-time performance of the solution, ensures the sampling precision, accuracy and real-time performance of the data, and provides a good platform foundation for the application of digital twin technology in the traction drive system of the rail transit vehicle; at the same time, in the ground virtual body layer, the server is used to realize the characterization of the ground-level large time scale real-time digital twin in the cloud, which meets the real-time perception of the current state of the actual system, and when the actual traction system is abnormal, it can be warned and adjusted in time to ensure the consistency between the model solution result and the actual system state, and can also communicate with other digital twins to provide timely information feedback to ensure the safe and reliable operation of the traction drive system, and ultimately help improve the reliability, data mining and information fusion of various key systems of the entire vehicle.

[0072] It is worth mentioning that Figure 1 The digital twin system of the rail transit vehicle traction drive system shown is also applicable to Figure 4 The digital twin method of the rail transit vehicle traction drive system will not be elaborated here.

[0073] The following takes the digital twin device of the traction drive system of a rail transit vehicle as an example of the execution subject to illustrate the implementation process of the digital twin method of the traction drive system of a rail transit vehicle provided by the embodiment of the present invention. It can be understood that the execution subject of the digital twin method of the traction drive system of a rail transit vehicle provided by the embodiment of the present invention includes but is not limited to the digital twin device of the traction drive system of a rail transit vehicle.

[0074] Figure 4 A flow chart of a digital twin method for a rail transit vehicle traction drive system provided by an embodiment of the present invention, such as Figure 4 As shown, the method includes:

[0075] Step 101: Detect the operation status data of the physical entity layer.

[0076] In the embodiment of the present invention, the physical entity layer includes a traction converter, a traction motor and a traction control system, and the traction control system is used to control the operation of the traction converter and the traction motor. As an optional solution, the secondary voltage of the 25kV grid after passing through the transformer is used as the system input; the traction control system outputs PWM drive pulses to control the rectifier to perform AC / DC conversion, providing a stable DC voltage for the traction inverter; then the traction control system outputs PWM drive pulses to control the traction inverter to perform DC / AC conversion, and outputs a variable frequency and variable voltage three-phase AC voltage to drive the traction motor to exert the command torque.

[0077] In the embodiment of the present invention, step 101 specifically includes:

[0078] Step 1011: Perform various types of signal detection on the traction inverter, traction motor and traction control system through various types of sensors to generate sensor signal data.

[0079] In the embodiment of the present invention, the multiple types of sensors include but are not limited to current sensors, voltage sensors, temperature sensors and speed sensors; the sensor signal data includes current signals, voltage signals, temperature signals and speed signals.

[0080] In the embodiment of the present invention, different types of sensor signal data at different locations are acquired by installing different types of sensors at different locations.

[0081] Specifically, a current sensor is installed at the input end of the rectifier to collect the grid-side input current signal; a voltage sensor is installed in the intermediate DC side loop to collect the intermediate DC voltage and ground voltage signals; a current sensor is installed at the output end of the traction inverter to collect the inverter output current signal; temperature sensors are respectively installed on the heat dissipation substrates of the rectifier and traction inverter power modules to collect temperature signals at different positions of the power modules; speed and temperature sensors are installed on the traction motor to collect the motor speed and stator temperature signals respectively.

[0082] Step 1012: Perform data conversion based on the sensor signal data through the analog quantity acquisition board to generate actual external characteristic quantities.

[0083] In the embodiment of the present invention, the sensor signal data is conditioned by an analog quantity acquisition board, and the sensor signal data is converted into a voltage signal recognizable by a chip to generate an actual external characteristic quantity.

[0084] Furthermore, the actual external characteristic quantity is transmitted to the rectifier control board and the traction inverter control board through hard wires as necessary inputs for controlling the rectifier and the traction inverter.

[0085] Step 1013: Perform edge computing based on actual external feature quantities, received control instructions, and preset self-control parameters to generate computing status data.

[0086] In the embodiment of the present invention, the control instructions include but are not limited to traction instructions, braking instructions, and direction instructions; the self-control parameters include but are not limited to power module drive pulse PWM.

[0087] Specifically, according to the operating mechanism of each component state, edge computing is performed in each board of the traction control system according to the actual external characteristic quantity, the received control command and the preset self-control parameters to generate the computing state data. The computing state data includes but is not limited to the current of the intermediate DC circuit support capacitor, the stator voltage of the traction motor, the resistance value of the rotor resistance of the traction motor, and the actual torque value output by the traction motor.

[0088] Furthermore, the running status data is preprocessed to generate preprocessed running status data, and the preprocessing includes noise reduction, alignment and screening. The preprocessed running status data is sent to the FPGA component in the on-board digital twin board of the on-board virtual body layer by using LVDS, thereby realizing real-time digital twin model characterization and updating.

[0089] Step 102: Using the pre-built real-time digital twin model of the traction drive system, a time-scale real-time simulation calculation is performed according to the operating status data and the acquired digital quantity information to generate simulation external characteristic quantities and internal parameter information.

[0090] Specifically, the operation status data and digital quantity information are input into the real-time digital twin model of the traction drive system for real-time simulation calculation on a small time scale to generate simulation external characteristic quantities and internal parameter information. The simulation external characteristic quantities include but are not limited to the grid-side current, the intermediate DC voltage, the inverter output current, and the traction motor speed; the internal parameter information includes but is not limited to the rectifier grid-side equivalent inductance value, the DC-side support capacitance value, the DC-side capacitance equivalent resistance value, the insulated gate bipolar transistor (IGBT) saturation voltage drop, the IGBT body diode conduction voltage drop, the traction motor stator and rotor resistance value, and the traction motor excitation inductance; the digital quantity information includes but is not limited to the vehicle control signal and the converter internal control / feedback signal.

[0091] In the embodiment of the present invention, according to the operation and control mechanism of the rectifier, traction inverter, and traction motor, a digital model is built in the high-performance vehicle-mounted digital twin board CPU component in the traction control system, and various instruction information obtained by the FPGA from the digital quantity acquisition board, the rectifier control board, and the traction inverter control board through LVDS communication is received as the input of the model through the PCIE bus. At the same time, the grid-side current, intermediate DC voltage, inverter output current, and traction motor speed information obtained by the FPGA from the analog quantity acquisition board through LVDS communication through the PCIE bus are used as the model external feature quantity and the objective function is set. In view of the fact that there are more than one external feature quantity that needs to be approximated to the actual system, the construction of the digital twin model of the traction drive system is essentially a multi-parameter multi-objective optimization process, which has high requirements on the optimization algorithm. The present invention adopts a particle swarm algorithm to iteratively update the internal parameters of the twin model, so that the model output simulation external feature quantity gradually approaches the actual external feature quantity of the actual physical entity. Finally, when the objective function meets the threshold or the number of iterations reaches the upper limit, the real-time digital twin model of the traction drive system can be obtained.

[0092] Specifically, through the particle swarm algorithm and the preset objective function, the internal parameter information of the model is iteratively updated according to the digital quantity information, the actual external characteristic quantity and the calculated state data to construct a real-time digital twin model of the traction drive system.

[0093] Furthermore, the initial value and updated value of the internal parameter information of the real-time digital twin model of the traction drive system are obtained; anomaly detection is performed based on the initial value and the updated value; if an abnormality in the internal parameter information is detected, a warning signal is generated and sent to the smart cloud platform layer.

[0094] Specifically, if the difference between the initial value and the updated value is greater than the preset difference threshold, it indicates that the internal parameter information is abnormal, and an early warning message is generated and the early warning signal is sent to the smart cloud platform layer; if the difference between the initial value and the updated value is less than or equal to the preset difference threshold, it indicates that the internal parameter information is normal, and real-time detection continues.

[0095] It is worth noting that the difference threshold can be set according to actual needs, and the embodiment of the present invention does not limit this.

[0096] Step 103 : Generate key component monitoring data based on the preset visualized geometric real-time digital twin model of the key components of the traction drive system and the operating status data and internal parameter information.

[0097] Specifically, the operating status data and internal parameter information are input into the visualized geometric real-time digital twin model for calculation to generate key component monitoring data. Key components include but are not limited to support capacitors, resonant reactance, power modules, various contactors, and traction motors; key component monitoring data include but are not limited to the real-time temperature, insulation, and deformation of each key component.

[0098] In an embodiment of the present invention, the ground virtual body layer receives information measured by the interactive perception layer and edge computing through wireless data communication between the vehicle and the ground, as well as internal parameter information output by the simplified real-time digital twin model of the vehicle-mounted virtual body layer, and combines three-dimensional (3D) lightweight technology to construct a 3D visualized physical and geometric real-time digital twin model of key components of the traction drive system.

[0099] Specifically, based on 3D lightweight technology, a visual geometric real-time digital twin model of the key components of the traction drive system is constructed according to the internal parameter information and operating status data output by the real-time digital twin model of the traction drive system.

[0100] Furthermore, when the monitoring data of key components reaches a certain threshold, combined with the abnormal warning signal of internal parameter changes of the real-time model sent by the on-board virtual body layer, the ground virtual body layer sends adjustment instructions to the on-board virtual body layer through the vehicle-ground wireless data communication. The adjustment instructions are then sent to the rectifier control board or the traction inverter control board through the on-board digital twin board FPGA component using LVDS communication, and finally act on the physical entity layer.

[0101] In an embodiment of the present invention, abnormality detection is performed on key components based on preset key component indicator thresholds and key component monitoring data and internal parameter information detection results; if a key component abnormality is detected, a warning signal is generated and sent to the smart cloud platform layer.

[0102] Specifically, if the key component monitoring data is greater than or equal to the corresponding key component indicator threshold, it indicates that the key component is abnormal, and an early warning signal is generated and sent to the smart cloud platform layer; if the key component monitoring data is less than the corresponding key component indicator threshold, it indicates that the key component is normal and real-time detection continues.

[0103] It is worth noting that the key component indicator threshold can be set according to actual needs, and the embodiment of the present invention does not limit this.

[0104] Step 104: Using a particle swarm algorithm, offline iterative calculations are performed based on the acquired historical data, multi-physics field coupling parameters, actual external characteristic quantities, internal parameter information, and key component monitoring data to construct an offline digital twin model.

[0105] In the embodiment of the present invention, historical data includes but is not limited to historical test and driving data; multi-physics field coupling parameters include but are not limited to electric field strength, magnetic field strength, thermal conductivity, heat capacity, geometric shape and size. Specifically, based on historical test and driving data, traction system operation and control mechanism, a data and mechanism dual-driven approach is adopted, and the influence of electromechanical, electromagnetic and thermal multi-physics field coupling is comprehensively considered. A complex offline digital twin model of the traction drive system is built on the ground server, and the internal parameter information output by the vehicle-mounted virtual body layer simplified real-time digital twin model received by the vehicle-ground wireless data communication, as well as the 3D visualized physical and geometric real-time digital twin model output information of the key components of the traction drive system, is updated in real time. The parameter values ​​of the offline model are ensured to ensure the consistency between the routine model and the actual system.

[0106] Furthermore, when a system failure occurs, the actual system output data with high sampling accuracy downloaded automatically or manually is used as the offline model input, and the particle swarm algorithm is used to drive the model to perform offline iterative calculations to complete the system fault inversion and locate the fault factor, which can greatly improve the fault analysis efficiency of maintenance personnel.

[0107] Furthermore, through the offline digital twin model, offline simulation prediction is performed according to the input simulation instruction data, simulation prediction results are generated, and the performance and health prediction of the system is completed offline, which assists in the formulation of system maintenance and repair plans.

[0108] Step 105 : Generate a warning message according to the warning signal sent by the vehicle-mounted virtual body layer, and send the warning message to each stored digital twin of the traction drive system.

[0109] In the embodiment of the present invention, the smart cloud platform layer stores and manages all data and information output by the vehicle virtual body layer and the ground virtual body layer model, and realizes information exchange and sharing between the digital twins of each traction drive system through cloud computing technology, so that when a traction drive system fails or is abnormal, the current problem, alarm information, fault root cause detection, diagnosis and repair information, solutions, etc. can be promptly notified to each digital twin of the traction drive system that may have similar hidden dangers for early prevention. In addition, the smart cloud platform layer can also exchange and share information with the digital twins of other systems such as vehicle braking and ground traction power supply to ensure the safe and reliable operation of the traction drive system, and ultimately help improve the reliability, data mining and information fusion of the key systems of the entire vehicle.

[0110] In the technical solution provided by the embodiment of the present invention, through the multi-time scale digital twin architecture composed of the physical entity layer, the interactive perception layer, the vehicle-mounted virtual body layer, the ground virtual body layer and the smart cloud platform layer, the vehicle-mounted digital twin board is used to realize the characterization of the vehicle-level small time scale real-time digital twin, which meets the high requirements of the electrical model in the traction drive system of the rail transit vehicle for the discrete frequency and the real-time performance of the solution, ensures the sampling precision, accuracy and real-time performance of the data, and provides a good platform foundation for the application of digital twin technology in the traction drive system of the rail transit vehicle; at the same time, in the ground virtual body layer, the server is used to realize the characterization of the ground-level large time scale real-time digital twin in the cloud, which meets the real-time perception of the current state of the actual system, and when the actual traction system is abnormal, it can be warned and adjusted in time to ensure the consistency between the model solution result and the actual system state, and can also communicate with other digital twins to provide timely information feedback to ensure the safe and reliable operation of the traction drive system, and ultimately help improve the reliability, data mining and information fusion of various key systems of the entire vehicle.

[0111] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.

[0112] It is worth noting that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0113] It is worth noting that the technical solution provided in this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0114] In the technical solution of the digital twin method of the traction drive system of a rail transit vehicle provided by the embodiment of the present invention, a multi-time scale digital twin architecture composed of a physical entity layer, an interactive perception layer, an on-board virtual body layer, a ground virtual body layer and a smart cloud platform layer is used, and the on-board digital twin board is used to realize the characterization of the on-board small time scale real-time digital twin, so as to meet the high requirements of the electrical model in the traction drive system of the rail transit vehicle for the discrete frequency and the real-time performance of the solution, and ensure the sampling precision, accuracy and real-time performance of the data, so as to provide a good platform foundation for the application of digital twin technology in the traction drive system of the rail transit vehicle; at the same time, in the ground virtual body layer, the server is used to realize the characterization of the ground-level large time scale real-time digital twin in the cloud, so as to meet the real-time perception of the current state of the actual system, and when the actual traction system is abnormal, it can timely warn and adjust, so as to ensure the consistency between the model solution result and the actual system state, and can also communicate with other digital twins, and timely feedback information, so as to ensure the safe and reliable operation of the traction drive system, and finally help improve the reliability, data mining and information fusion of various key systems of the entire vehicle.

[0115] Figure 5 A schematic diagram of the structure of a digital twin device of a rail transit vehicle traction drive system provided by an embodiment of the present invention, wherein the device is used to execute the digital twin method of the rail transit vehicle traction drive system, such as Figure 5 As shown, the device includes: a detection unit 11, a real-time simulation unit 12, a key component monitoring unit 13 and an early warning unit 14.

[0116] The detection unit 11 is used to detect the operation status data of the physical entity layer. The physical entity layer includes a traction converter, a traction motor and a traction control system. The traction control system is used to control the operation of the traction converter and the traction motor.

[0117] The real-time simulation unit 12 is used to perform time-scale real-time simulation calculations based on the operating status data and the acquired digital quantity information through a pre-built real-time digital twin model of the traction drive system, and generate simulation external characteristic quantities and internal parameter information.

[0118] The key component monitoring unit 13 is used to generate key component monitoring data according to the operating status data and internal parameter information through a preset visualized geometric real-time digital twin model of the key components of the traction drive system.

[0119] The warning unit 14 is used to generate a warning message according to the warning signal sent by the vehicle-mounted virtual body layer, and send the warning message to each stored digital twin of the traction drive system.

[0120] In the scheme of the embodiment of the present invention, through the multi-time scale digital twin architecture composed of the physical entity layer, the interactive perception layer, the vehicle-mounted virtual body layer, the ground virtual body layer and the smart cloud platform layer, the vehicle-mounted digital twin board is used to realize the characterization of the vehicle-level small time scale real-time digital twin, which meets the high requirements of the electrical model in the traction drive system of the rail transit vehicle for the discrete frequency and the real-time performance of the solution, ensures the sampling precision, accuracy and real-time performance of the data, and provides a good platform foundation for the application of digital twin technology in the traction drive system of the rail transit vehicle; at the same time, in the ground virtual body layer, the server is used to realize the characterization of the ground-level large time scale real-time digital twin in the cloud, which meets the real-time perception of the current state of the actual system, and when the actual traction system is abnormal, it can be warned and adjusted in time to ensure the consistency between the model solution result and the actual system state, and can also communicate with other digital twins to provide information feedback in time to ensure the safe and reliable operation of the traction drive system, and ultimately help improve the reliability, data mining and information fusion of various key systems of the entire vehicle.

[0121] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0122] An embodiment of the present invention provides a computer device, including a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, and when the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned rail transit vehicle traction drive system digital twin method are implemented. For a specific description, please refer to the embodiment of the above-mentioned rail transit vehicle traction drive system digital twin method.

[0123] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.

[0124] like Figure 6As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer device 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0125] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.

[0126] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the removable medium 611.

[0127] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0128] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0129] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0132] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0133] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0134] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0135] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0136] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0137] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0138] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A digital twin system of a rail transit vehicle traction drive system, characterized in that: The system includes: a physical entity layer, an interactive perception layer, a vehicle-mounted virtual body layer, a ground virtual body layer and a smart cloud platform layer; The physical entity layer includes a traction converter, a traction motor and a traction control system, wherein the traction control system is used to control the operation of the traction converter and the traction motor; The interactive perception layer is used to detect the operating status data of the physical entity layer; The vehicle-mounted virtual body layer is used to perform time-scale real-time simulation calculation according to the operating state data and the acquired digital quantity information through a pre-built real-time digital twin model of the traction drive system, and generate simulation external feature quantities and internal parameter information; The ground virtual volume layer is used to generate key component monitoring data according to the operating status data and internal parameter information through a preset visualized geometric real-time digital twin model of key components of the traction drive system; The smart cloud platform layer is used to generate a warning message according to the warning signal sent by the vehicle-mounted virtual body layer, and send the warning message to each stored digital twin of the traction drive system.

2. The digital twin system of the rail transit vehicle traction drive system according to claim 1, characterized in that: The running status data includes actual external characteristic quantities and calculation status data, and the traction control system also includes an analog quantity acquisition board; The interactive sensing layer is used to perform various types of signal detection on the traction converter, traction motor and traction control system through various types of sensors to generate sensor signal data; The interactive perception layer is used to perform data conversion according to the sensor signal data through the analog quantity acquisition board to generate actual external feature quantities; Edge computing is performed according to the actual external characteristic quantity, the received control instruction and the preset self-control parameters to generate the computing status data.

3. The digital twin system of the rail transit vehicle traction drive system according to claim 1, characterized in that: The interactive perception layer is also used to preprocess the running status data to generate preprocessed running status data, wherein the preprocessing includes noise reduction, alignment and screening.

4. The digital twin system of the rail transit vehicle traction drive system according to claim 2, characterized in that: The vehicle-mounted virtual body layer is used to iteratively update the model's internal parameter information according to the digital quantity information, actual external feature quantity and calculated state data through a particle swarm algorithm and a preset objective function, so as to construct a real-time digital twin model of the traction drive system.

5. The digital twin system of the rail transit vehicle traction drive system according to claim 1, characterized in that: The vehicle-mounted virtual body layer is also used to obtain the initial value and update value of the internal parameter information of the real-time digital twin model of the traction drive system; perform anomaly detection based on the initial value and update value; if an abnormality in the internal parameter information is detected, generate a warning signal, and send the warning signal to the smart cloud platform layer.

6. The digital twin system of the rail transit vehicle traction drive system according to claim 1, characterized in that: The ground virtual body layer is used to construct a visualized geometric real-time digital twin model of key components of the traction drive system based on three-dimensional lightweight technology and according to internal parameter information and operating status data output by the real-time digital twin model of the traction drive system.

7. The digital twin system of the rail transit vehicle traction drive system according to claim 1, characterized in that: The ground virtual body layer is used to perform abnormality detection on the key components through preset key component indicator thresholds, based on the key component monitoring data and internal parameter information detection results; if a key component abnormality is detected, a warning signal is generated and sent to the smart cloud platform layer.

8. The digital twin system of the rail transit vehicle traction drive system according to claim 1, characterized in that: The ground virtual body layer is also used to construct an offline digital twin model by performing offline iterative calculations based on acquired historical data, multi-physical field coupling parameters, actual external characteristic quantities, internal parameter information and key component monitoring data through a particle swarm algorithm.

9. The digital twin system of the rail transit vehicle traction drive system according to claim 8, characterized in that: The ground virtual volume layer is also used to perform offline simulation prediction according to the input simulation instruction data through the offline digital twin model to generate simulation prediction results.

10. A digital twin method for a rail transit vehicle traction drive system, characterized in that: The method applied to the digital twin system of the rail transit vehicle traction drive system according to any one of claims 1 to 9 comprises: Detecting operation status data of a physical entity layer, wherein the physical entity layer includes a traction converter, a traction motor and a traction control system, wherein the traction control system is used to control the operation of the traction converter and the traction motor; By using a pre-built real-time digital twin model of the traction drive system, a time-scale real-time simulation calculation is performed according to the operating status data and the acquired digital quantity information to generate simulation external characteristic quantities and internal parameter information; Generate key component monitoring data based on the operating status data and internal parameter information by using a preset visualized geometric real-time digital twin model of key components of the traction drive system; A warning message is generated according to the warning signal sent by the vehicle-mounted virtual body layer, and the warning message is sent to each stored digital twin of the traction drive system.

11. A digital twin device for a rail transit vehicle traction drive system, characterized in that: The device comprises: A detection unit, used to detect operating status data of a physical entity layer, wherein the physical entity layer includes a traction converter, a traction motor and a traction control system, wherein the traction control system is used to control the operation of the traction converter and the traction motor; A real-time simulation unit, configured to perform time-scale real-time simulation calculations according to the operating state data and the acquired digital quantity information through a pre-built real-time digital twin model of the traction drive system, and generate simulation external characteristic quantities and internal parameter information; A key component monitoring unit, used to generate key component monitoring data according to the operating status data and internal parameter information through a preset visualized geometric real-time digital twin model of the key components of the traction drive system; The early warning unit is used to generate an early warning message according to the early warning signal sent by the vehicle-mounted virtual body layer, and send the early warning message to each stored digital twin of the traction drive system.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the digital twin method of the rail transit vehicle traction drive system described in claim 10 is implemented.

13. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by the processor, the digital twin method of the rail transit vehicle traction drive system described in claim 10 is implemented.

14. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by the processor, the digital twin method of the rail transit vehicle traction drive system described in claim 10 is implemented.

Images