Method and system for constructing and verifying digital twinborn model of major equipment in urban rail field section

Abstract

The invention discloses a construction and verification method and system for a digital twinborn model of major equipment in an urban rail field section, which adopts an advanced data fusion algorithm to fuse data from different sensors, improves the accuracy and comprehensiveness of the data and provides a more reliable basis for construction of the digital twinborn model. Machine learning and deep learning algorithms are utilized to construct a data-driven digital twinborn model, so that the future state and performance of the equipment can be accurately predicted, and powerful support is provided for intelligent management and maintenance of the urban rail field equipment; and a set of complete virtual-real consistency verification index system and verification method is designed, so that the accuracy and reliability of the digital twin model can be effectively ensured, and a guarantee is provided for the application of the digital twin technology in the urban rail field.

Description

Technical Field

[0001] The present invention relates to the technical field of urban rail transit, and particularly to a method and system for constructing and verifying a digital twin model of major equipment in urban rail transit yards and sections. Background Art

[0002] The equipment in urban rail transit yards and sections is a key infrastructure to ensure the safe and efficient operation of the entire rail transit system. These equipment include, but are not limited to, train maintenance equipment, signal control systems, power supply equipment, etc. However, the current management and maintenance of these equipment mainly rely on traditional methods such as regular inspections and post-failure repairs, which have problems such as low efficiency, low accuracy, and difficulty in predicting failures in advance. The traditional management and maintenance methods cannot understand the operating status of the equipment in real time and comprehensively, resulting in frequent equipment failures and affecting the normal operation of the urban rail system. For example, during the train maintenance process, due to the inability to accurately grasp the real-time status of the key components of the maintenance equipment, it may lead to abnormal maintenance, increasing the maintenance cost and equipment downtime.

[0003] As an emerging digital solution, digital twin technology has achieved remarkable development in the industrial field in recent years. By constructing a virtual model of a physical entity and realizing data interaction and synchronization between the virtual model and the physical entity, it can reflect the status and performance of the physical entity in real time. In the field of urban rail transit, the application of digital twin technology is still in its infancy, but it has great potential. By constructing a digital twin model of urban rail transit yard and section equipment, goals such as real-time monitoring of equipment, fault prediction, and optimized operation can be achieved. For example, using the digital twin model, the operating status of the train can be monitored in real time, and possible faults can be predicted in advance, so as to take corresponding measures for prevention and repair, improving the reliability and safety of the equipment.

[0004] In the application of digital twin models, ensuring the consistency between the virtual model and the physical entity is crucial. If there are large differences between the virtual and the real, then the decision-making and analysis based on the digital twin model will lose accuracy and reliability. Currently, in the field of urban rail transit yard and section equipment, there is a lack of effective virtual-real consistency verification methods, which has become a key bottleneck restricting the wide application of digital twin technology. For example, in some existing digital twin applications, due to the inability to accurately verify the consistency between the virtual model and the actual equipment, the results based on the model deviate greatly from the actual situation, affecting the correctness and effectiveness of decision-making. Summary of the Invention

[0005] This application provides a method and system for constructing and verifying a digital twin model of major equipment in urban rail transit yards and sections to solve the problems of constructing a digital twin model of major equipment in urban rail transit yards and sections and verifying the virtual-real consistency.

[0006] According to a first aspect, in one embodiment, a method for constructing and validating a digital twin model of major equipment in an urban rail yard section is provided, and the method includes:

[0007] Collect multi-source data of the urban rail yard section equipment and preprocess the collected data;

[0008] Perform data fusion and feature extraction on the preprocessed data, and construct a data-driven equipment digital twin model;

[0009] Based on the established verification index system, perform virtual-real consistency verification on the digital twin model, and analyze and process the verification results.

[0010] Further, collecting multi-source data of the urban rail yard section equipment and preprocessing the collected data specifically includes:

[0011] Construct a distributed data acquisition system, including sensor nodes, a transmission network, and a storage server;

[0012] Select appropriate sensors according to the different types and characteristics of the urban rail yard section equipment, and the layout of the sensor nodes follows the principles of comprehensive coverage and key part focused monitoring;

[0013] The data acquisition frequency is dynamically adjusted according to the equipment operation characteristics and monitoring requirements, and the data collected by the sensors is transmitted to the storage server in real time through the transmission network for storage and processing;

[0014] Clean, denoise, and normalize the collected raw data to improve the data quality and unify it into a standard format for subsequent processing and analysis.

[0015] Further, performing data fusion and feature extraction on the preprocessed data specifically includes:

[0016] Adopt a data fusion algorithm including Kalman filtering to fuse data from different sensors to obtain more comprehensive and accurate equipment state information;

[0017] Apply a feature extraction algorithm including principal component analysis to reduce the dimension of the fused high-dimensional data, and extract key features as input parameters of the digital twin model;

[0018] By analyzing the feature data, mine the potential laws and patterns of equipment operation, and provide a basis for the construction and optimization of the digital twin model.

[0019] Further, constructing a data-driven equipment digital twin model specifically includes:

[0020] Using 3D modeling technology, construct a high-precision 3D geometric model of urban rail yard equipment, including: adopting a combination of CAD software and 3D scanning technology to accurately restore the external structure and detailed features of the equipment; for complex equipment structures, adopt a method of modeling and assembling by components to ensure the accuracy and editability of the model; control the accuracy of the 3D geometric model within the millimeter level, and be able to highly realistically present the actual appearance and dimensions of the equipment;

[0021] Based on the physical characteristics and operating principles of the equipment, construct a physical model of the equipment, including a geometric model, a behavior model, and a rule model; the geometric model is constructed using 3D measurement technology, reflecting the geometric shape of the equipment and providing a spatial framework for the physical model; the behavior model analyzes the behavior performance under different working conditions based on the operating principles and physical characteristics of the equipment, and models and predicts the output response through physical laws and dynamic equations; the rule model is formulated based on operating specifications and safety restrictions to ensure the safe operation of the equipment and be able to detect abnormal situations and issue alarms;

[0022] Using machine learning and deep learning algorithms, construct a data-driven digital twin model; through learning a large amount of historical data, enable the model to predict the future state and performance of the equipment.

[0023] Furthermore, establish a verification index system, specifically including:

[0024] The verification index system includes:

[0025] Model accuracy index: including the geometric accuracy, physical accuracy, and data accuracy of the model; the geometric accuracy is measured by comparing the difference in external dimensions between the virtual model and the actual equipment; the physical accuracy is measured by comparing the difference in physical characteristics between the virtual model and the actual equipment; the data accuracy is measured by comparing the difference in operating data between the virtual model and the actual equipment;

[0026] Response time index: measure the response speed of the virtual model to the change in the state of the actual equipment, and require the virtual model to be able to respond to the change in the state of the actual equipment in real time, and the response time is within the preset range;

[0027] Data synchronization index: measure the data synchronization between the virtual model and the actual equipment, and require the data synchronization error between the virtual model and the actual equipment to be within the preset range.

[0028] Furthermore, conduct a virtual-real consistency verification on the digital twin model, specifically including:

[0029] Static verification: Verify the geometric accuracy and physical accuracy of the digital twin model when the equipment is in a stationary state; calculate the error value by measuring the key dimensions and physical parameters of the actual equipment and comparing them with the virtual model; verify the physical accuracy by setting specific physical conditions on the actual equipment and comparing with the simulation results in the virtual model.

[0030] Dynamic verification: Verify the response time and data synchronization of the digital twin model when the equipment is in operation; record the response time by setting specific operating conditions on the actual equipment and observing the response of the virtual model; calculate the data synchronization error by comparing the data changes between the actual equipment and the virtual model in real time.

[0031] Regular verification: Regularly conduct a comprehensive virtual-real consistency verification of the digital twin model to ensure the accuracy and reliability of the model; determine the verification cycle according to the importance and operating characteristics of the equipment; regular verification includes a comprehensive inspection and evaluation of model accuracy, response time, and data synchronization indicators.

[0032] Furthermore, analyze and process the verification results, specifically including:

[0033] Result analysis: Conduct a detailed analysis of the verification results to find out the reasons for the virtual-real inconsistency.

[0034] Error correction: Take corresponding measures to correct the error according to the analysis results.

[0035] Model update: Update and optimize the digital twin model according to the verification results and error correction situation.

[0036] According to the second aspect, an embodiment provides a construction and verification system for a digital twin model of major equipment in an urban rail yard section, and the system includes:

[0037] A data acquisition module, configured to perform multi-source data acquisition on the urban rail yard section equipment and preprocess the acquired data.

[0038] A digital twin model construction module, configured to perform data fusion and feature extraction on the preprocessed data and construct a data-driven equipment digital twin model.

[0039] A verification module, configured to perform virtual-real consistency verification on the digital twin model based on the established verification index system, and analyze and process the verification results.

[0040] According to the third aspect, an embodiment provides an electronic device, and the device includes: a processor and a memory;

[0041] The memory is used to store one or more program instructions;

[0042] The processor is used to run one or more program instructions to execute the steps of the method for constructing and verifying a digital twin model of major equipment in an urban rail yard section as described in any one of the above.

[0043] According to a fourth aspect, in one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for constructing and verifying a digital twin model of major equipment in an urban rail yard section as described in any one of the above are implemented.

[0044] This application provides a method and system for constructing and verifying a digital twin model of major equipment in an urban rail yard section. By using an advanced data fusion algorithm, data from different sensors are fused, improving the accuracy and comprehensiveness of the data and providing a more reliable basis for the construction of the digital twin model. Machine learning and deep learning algorithms are used to construct a data-driven digital twin model, which can accurately predict the future state and performance of the equipment, providing strong support for the intelligent management and maintenance of urban rail yard section equipment. A complete set of virtual-real consistency verification index systems and verification methods are designed, which can effectively ensure the accuracy and reliability of the digital twin model, providing a guarantee for the application of digital twin technology in the urban rail field. It has the following beneficial effects:

[0045] (1) Improve management efficiency: Through the real-time monitoring and analysis functions of the digital twin model, potential problems and faults of the equipment can be discovered in a timely manner, and measures can be taken in advance for prevention and repair, improving the management efficiency of urban rail yard section equipment.

[0046] (2) Reduce maintenance costs: Based on the predictive maintenance function of the digital twin model, unnecessary regular inspections and repairs can be reduced, lowering the maintenance costs.

[0047] (3) Enhance safety: Through the real-time monitoring and early warning of the equipment status, potential safety hazards can be discovered and handled in a timely manner, enhancing the operation safety of urban rail yard section equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flowchart of a method for constructing and verifying a digital twin model of major equipment in an urban rail yard section provided by an embodiment of the present invention;

[0049] Figure 2 It is a schematic structural diagram of a fixed car lifter in a method for constructing and verifying a digital twin model of major equipment in an urban rail yard section provided by an embodiment of the present invention;

[0050] Figure 3 It is a schematic 3D model diagram of a fixed car lifter in a method for constructing and verifying a digital twin model of major equipment in an urban rail yard section provided by an embodiment of the present invention;

[0051] Figure 4 The physical model and behavior model of the car body lifting machine bearing in the construction and verification method of the digital twin model of major equipment in urban rail yard sections provided by an embodiment of the present invention;

[0052] Figure 5 The virtual-real synchronization effect and interface of the fixed car body lifting machine in the construction and verification method of the digital twin model of major equipment in urban rail yard sections provided by an embodiment of the present invention;

[0053] Figure 6 The flow chart for verifying the consistency of the full-element digital twin entity model in the construction and verification method of the digital twin model of major equipment in urban rail yard sections provided by an embodiment of the present invention;

[0054] Figure 7 The CAD modeling drawing of the pit-type fixed car body lifting machine in the construction and verification method of the digital twin model of major equipment in urban rail yard sections provided by an embodiment of the present invention;

[0055] Figure 8 The model drawing of the pit-type fixed car body lifting machine in the construction and verification method of the digital twin model of major equipment in urban rail yard sections provided by an embodiment of the present invention;

[0056] Figure 9 The schematic diagram of the logical structure of the construction and verification system of the digital twin model of major equipment in urban rail yard sections provided by an embodiment of the present invention.

[0057] In the figure: pit cover 1, steel structure 2, maintenance platform 3, steel structure bogie lifting unit 4, car body lifting unit 5. Specific embodiments

[0058] The present invention will be further described in detail below in conjunction with the accompanying drawings through specific embodiments. Similar elements in different embodiments are labeled with related similar element numbers. In the following embodiments, many detailed descriptions are provided to enable a better understanding of the present application. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present application are not shown or described in the specification to avoid overwhelming the core part of the present application with excessive descriptions. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the descriptions in the specification and general technical knowledge in the art.

[0059] In addition, the features, operations, or characteristics described in the specification can be combined in any appropriate manner to form various embodiments. Meanwhile, the steps or actions in the method description can also be reordered or adjusted in a manner obvious to those skilled in the art. Therefore, the various sequences in the specification and drawings are only for clearly describing a certain embodiment and do not mean a necessary sequence, unless it is stated that a certain sequence must be followed.

[0060] The first embodiment of the present invention provides a method for constructing and verifying a digital twin model of major equipment in urban rail yards to achieve efficient management and maintenance of urban rail yard equipment. The specific ideas include the following key steps: First, obtain various data of urban rail yard equipment through multi-source data acquisition technology; then, construct a digital twin model using advanced data processing and modeling algorithms; finally, design an effective virtual-real consistency verification method to ensure the accuracy and reliability of the digital twin model. The following will be described in detail in combination with Figure 1 for detailed description.

[0061] As Figure 1 shown, in step S100, multi-source data is collected for urban rail yard equipment, and the collected data is preprocessed.

[0062] Multi-source data acquisition technology: For urban rail yard equipment, appropriate sensors need to be selected according to different types and characteristics, such as temperature, pressure, vibration sensors, etc. The layout follows the principles of comprehensive coverage and key part focused monitoring. A distributed data acquisition system is constructed, which consists of sensor nodes, a transmission network, and a storage server. The data acquisition frequency is dynamically adjusted according to the operating characteristics of the equipment and the monitoring requirements. The collected raw data is cleaned, denoised, and normalized to improve the data quality and unify it into a standard format for subsequent processing and analysis.

[0063] As Figure 1 shown, in step S200, the data obtained from preprocessing is subjected to data fusion and feature extraction, and a data-driven equipment digital twin model is constructed.

[0064] Data fusion and processing technology:

[0065] (1) Adopt advanced data fusion algorithms, such as Kalman filtering, to fuse data from different sensors to obtain more comprehensive and accurate equipment status information. It fuses different sensor data as observation values by establishing state and observation equations to obtain a more accurate system state estimate.

[0066] The data fusion steps through Kalman filtering are as follows:

[0067] a. Initialization

[0068] Determine the initial state estimate Usually set according to prior knowledge or initial measurement values.

[0069] Determine the initial estimated covariance P0, which reflects the uncertainty of the initial state estimate.

[0070] b. Prediction step

[0071] A priori state estimate: Predict according to the state transition equation of the system. The formula is where, is the a priori state estimate at time k, is the posterior state estimate at the previous time, A is the state transition matrix, B is the control input matrix, and uk-1 is the control input.

[0072] A priori estimated covariance: Update the covariance according to the state transition equation as well. The formula is Pk = A * P k-1 A T + Q. Where, is the a priori estimated covariance, P k-1 is the posterior estimated covariance at the previous time, and Q is the process noise covariance matrix, representing the uncertainty of the system model.

[0073] c. Update step

[0074] Calculate the Kalman gain: The Kalman gain is used to weigh the importance of the predicted value and the observed value. The formula is where, K k is the Kalman gain, H is the observation matrix that relates the state variables to the observed values, and R is the observation noise covariance matrix, representing the uncertainty of the observed values.

[0075] Posterior state estimate: Combine the predicted value and the observed value to obtain a more accurate state estimate. The formula is where, is the posterior state estimate at time k, z k is the observed value.

[0076] Posterior estimated covariance: Update the estimated covariance to reflect the uncertainty of the new state estimate. The formula is where, P k is the posterior estimated covariance, and I is the identity matrix.

[0077] d. Repeat step

[0078] Continuously repeat the prediction and update steps. As new observed values arrive, continuously update the state estimate and covariance to achieve real-time tracking of the device state and fusion of data from different sensors.

[0079] Kalman filtering obtains a more accurate estimation of the device state by continuously iterating the prediction and update steps and fusing multi-sensor data. In this process, the accurate setting of the state transition matrix A, control input matrix B, observation matrix H, process noise covariance matrix Q, and observation noise covariance matrix R is crucial for the filtering effect. These parameters usually need to be adjusted and optimized according to the specific system model and sensor characteristics.

[0080] (2) Apply feature extraction algorithms, such as principal component analysis, to reduce the dimensionality of the fused high-dimensional data and extract key features as input parameters for the digital twin model. By analyzing the feature data, potential laws and patterns of equipment operation are mined, providing a basis for the construction and optimization of the digital twin model.

[0081] Digital twin model construction technology:

[0082] (1) Three-dimensional geometric model construction

[0083] Use three-dimensional modeling technology to construct a high-precision three-dimensional geometric model of urban rail yard equipment. Adopt a combination of CAD software and three-dimensional scanning technology to accurately restore the external structure and detailed features of the equipment. For complex equipment structures, use the method of component modeling and assembly to ensure the accuracy and editability of the model. For example, for the structure of a pit-type fixed car-lifting machine, first construct the three-dimensional models of the car body lifting unit, bogie unit, and maintenance platform separately, and then combine these components into a complete car-lifting machine model through assembly technology.

[0084] The accuracy requirement of the three-dimensional geometric model is controlled within millimeters, and it can highly realistically present the actual appearance and size of the equipment. For example, for a large train maintenance equipment, the size error of its three-dimensional geometric model is controlled within ±2mm.

[0085] (2) Physical model construction

[0086] Based on the physical characteristics and operating principles of the equipment, construct the physical model of the equipment. The physical model includes geometric models, behavior models, rule models, etc.

[0087] The geometric model is constructed using three-dimensional measurement technology, reflecting the geometric shape of the equipment and providing a spatial framework for the physical model. The behavior model analyzes the behavior performance under different working conditions based on the operating principles and physical characteristics of the equipment, and models and predicts the output response through physical laws and dynamic equations. The rule model is formulated based on operation specifications and safety restrictions to ensure the safe operation of the equipment, and can also detect abnormal situations and issue alarms.

[0088] (3) Data-driven model construction

[0089] Using machine learning and deep learning algorithms, a data-driven digital twin model is constructed. Through learning a large amount of historical data, the model can predict the future state and performance of the equipment. For example, by using neural network algorithms to learn sensor data, a fault prediction model of the equipment is constructed, which can predict the fault time and type of the equipment in advance and provide decision support for equipment maintenance.

[0090] As Figure 1 shown, in step S300, based on the established verification index system, the virtual-real consistency of the digital twin model is verified, and the verification results are analyzed and processed.

[0091] Virtual-real consistency verification method:

[0092] 1. Verification index system design

[0093] (1) Model accuracy index: It includes the geometric accuracy, physical accuracy and data accuracy of the model. The geometric accuracy is measured by comparing the difference in the shape and size between the virtual model and the actual equipment, and the error is required to be within a certain range. For example, for train maintenance equipment, the geometric dimension error is required to be controlled within ±2mm. The physical accuracy is measured by comparing the difference in the physical characteristics between the virtual model and the actual equipment. For example, the temperature simulation error is controlled within ±1℃, and the pressure simulation error is controlled within ±0.5%. The data accuracy is measured by comparing the difference in the operation data between the virtual model and the actual equipment, and the data error rate is required to be controlled within a certain range. For example, for sensor data, the data error rate is required to be controlled within 5%.

[0094] (2) Response time index: It measures the response speed of the virtual model to the state change of the actual equipment. It is required that the virtual model can respond to the state change of the actual equipment in real time, and the response time is within a certain range. For example, for the state change of the running bogie unit, the response time of the virtual model is required to be no more than 1 second.

[0095] (3) Data synchronization index: It measures the data synchronization between the virtual model and the actual equipment. It is required that the data synchronization error between the virtual model and the actual equipment is within a certain range. For example, for the synchronization of sensor data, the data synchronization error is required to be controlled within ±0.5s.

[0096] 2. Verification method and process

[0097] (1) Static verification: Verify the geometric accuracy and physical accuracy of the digital twin model when the equipment is in a stationary state. By measuring the key dimensions and physical parameters of the actual equipment and comparing them with the virtual model, calculate the error value. For example, for the measurement of the key component dimensions of train maintenance equipment, if the error between the actual measurement value and the value shown in the virtual model is within the allowable range, it is considered that the geometric accuracy meets the requirements. At the same time, by setting specific physical conditions, such as temperature, pressure, etc. on the actual equipment and comparing with the simulation results in the virtual model, verify the physical accuracy.

[0098] (2) Dynamic verification: Verify the response time and data synchronization of the digital twin model when the fixed car lift is in operation. By setting specific operating conditions, such as rapid lifting, slow lowering, sudden increase in load, etc. on the actual fixed car lift and observing the response of the virtual model, record the response time. At the same time, compare the data change situations between the actual fixed car lift and the virtual model in real time, and calculate the data synchronization error. For example, during the lifting process of the fixed car lift, if the synchronization error between the height change of the actual car lift and the height change in the virtual model is within the allowable range, it is considered that the data synchronization meets the requirements.

[0099] (3) Periodic verification: Periodically conduct a comprehensive virtual-real consistency verification on the digital twin model to ensure the accuracy and reliability of the model. The verification period is determined according to the importance and operating characteristics of the equipment. For example, for key equipment, conduct verification once a week; for general equipment, conduct verification once a month. Periodic verification includes a comprehensive inspection and evaluation of indicators such as model accuracy, response time, and data synchronization, and adjust and optimize the digital twin model according to the verification results.

[0100] 3. Analysis and Processing of Verification Results

[0101] (1) Result analysis: Conduct a detailed analysis of the verification results to find out the reasons for virtual-real inconsistency. Possible reasons include sensor failures, data transmission errors, model algorithm errors, etc. For example, if it is found that the data synchronization error is large, it may be that there is a problem with the data transmission link, and it is necessary to check the network equipment and transmission protocol; if it is found that the model accuracy does not meet the requirements, it may be that the model algorithm needs to be optimized, and it is necessary to re-adjust the model parameters or improve the algorithm.

[0102] (2) Error correction: According to the analysis results, take corresponding measures to correct the errors. For example, if it is a sensor failure, replace the faulty sensor in time; if it is a data transmission error, optimize the data transmission link and protocol; if it is a model algorithm error, re-train the model or improve the algorithm. At the same time, verify the corrected results again to ensure that the errors are effectively resolved.

[0103] (3) Model Update: Update and optimize the digital twin model based on the verification results and error correction. As the equipment operates and is used, its performance and status may change. Therefore, it is necessary to regularly update the digital twin model to ensure that the model can accurately reflect the actual situation of the equipment. For example, when the equipment undergoes maintenance or upgrades, relevant parameters and model structures in the digital twin model need to be updated in a timely manner.

[0104] The digital twin models of three important pieces of equipment in the urban rail yard section are constructed, but their construction processes are highly similar. In this embodiment, the fixed car body jacking machine will be used as an example to introduce the specific implementation methods for constructing the digital twin model. The mechanical system of the fixed car body jacking machine mainly includes a pit cover plate 1, a steel structure 2, a maintenance platform 3, a steel structure bogie lifting unit 4, a car body lifting unit 5, etc., as Figure 2 shown.

[0105] Usually, this equipment is fixed in a pit. To facilitate the assembly and integration of this equipment with the entire workshop model, the BIM modeling method is adopted. The REVIT modeling software is used to model each part of the fixed car body jacking machine equipment, and a structure tree is established, and constraints are added to the parts. All parts are assembled in sequence to achieve the assembly of multi-level models at the part level - component level - equipment level, and a complete 3D model of the car body jacking machine is obtained, as Figure 3 shown.

[0106] During the process of component grouping, it is necessary to set the basic physical properties of the main components in Abaqus. Since there are many components of the car body jacking machine, taking the bearings of the car body jacking machine as an example, the construction of the physical model is illustrated. After completing the modeling of the parts, the model is exported and converted into the STEP format, imported into Abaqus, and parameters such as material properties, boundary conditions, and external loads are added to the model to complete the construction of the physical model. Mesh division is performed on it to solve parameters such as the stress field and displacement of the components, as Figure 4 shown.

[0107] Taking the fixed car lifter as an example, the real-time operation data of the fixed car lifter is synchronously transmitted to the digital twin system of the fixed car lifter. The virtual fixed car lifter updates its state according to the data and always remains consistent with the physical fixed car lifter, highly realistically restoring any state changes occurring to the physical fixed car lifter in a three-dimensional visualization manner. At the same time, the virtual fixed car lifter will also perform simulation optimization analysis on the operation state of the physical fixed car lifter based on the real-time data and conduct real-time regulation on the physical fixed car lifter. The two can timely grasp each other's dynamic changes and make real-time responses. The information of the perceived and synchronized fixed car lifter includes: bogie height, car body height, bogie lifting speed, car body lifting speed, nut temperature, nut wear amount, lifting asynchrony fault, upper limit fault, lower limit fault, nut wear fault, nut detachment fault, sensor fault, overload fault, etc. The real-time operation synchronization effect and interface of the fixed car lifter are as Figure 5 shown.

[0108] The flow chart of the virtual-real consistency verification method is as Figure 6 : It details the determination of verification indicators, the implementation of the verification process, and the analysis and processing flow of verification results. Through this figure, it is possible to comprehensively understand how to evaluate and verify the accuracy and reliability of the digital twin model to ensure a high degree of consistency between the virtual model and the actual equipment.

[0109] Taking the fixed car lifter in a certain urban rail transit yard section as an example, the specific implementation manner of the present invention is introduced in detail. This equipment is one of the key equipments in the urban rail transit yard section, and its operation state directly affects the maintenance quality and efficiency of the train. At present, there are problems such as untimely fault detection, long maintenance cycle, and inability to accurately predict equipment performance changes under the traditional management mode for this equipment, and there is an urgent need to introduce advanced digital twin technology to improve the management and maintenance level.

[0110] (I) Implementation steps and processes

[0111] 1. Multi-source data collection

[0112] (1) Install various sensors on the fixed car lifter, including temperature sensors, pressure sensors, vibration sensors, current sensors, etc. The installation positions of the sensors are reasonably selected according to the structure and operation characteristics of the equipment to ensure that key data can be accurately collected.

[0113] For key mechanical transmission components, such as motors, reducers, etc., install vibration sensors and temperature sensors. The vibration sensors are installed at the bearing seats, housings, etc. of the equipment to monitor the vibration of the equipment and judge whether there are mechanical faults. The temperature sensors are installed at the motor windings, bearings and other parts prone to heat generation to monitor the temperature change of the equipment in real time and prevent overheating faults. For example, the temperature sensor installed on the motor winding has a measurement accuracy of ±0.5°C and can accurately monitor the working temperature of the motor.

[0114] For the hydraulic system, install pressure sensors and flow sensors. The pressure sensors are installed at key positions in the hydraulic pipeline to monitor the working pressure of the hydraulic system and ensure the normal operation of the system. The flow sensors are installed at the outlet of the hydraulic pump and the inlet of the actuator to monitor the flow rate of the hydraulic oil and determine whether there are problems such as leakage or blockage in the system. For example, the measurement range of the pressure sensor is 0 - 20 MPa, and the accuracy is ±0.2% FS, which can meet the pressure monitoring requirements of the hydraulic system.

[0115] (2) Establish a data acquisition and transmission system to transmit the data collected by the sensors to the data center for storage and processing in real time.

[0116] Adopt wireless communication technologies (such as Wi-Fi or Bluetooth) to build a communication link between the data acquisition terminal and the data center. After the data acquisition terminal preliminarily processes and encapsulates the data collected by the sensors, it sends the data to the data center through wireless communication. The data center adopts high-performance servers and storage devices, which can receive and store a large amount of data in real time. For example, the servers in the data center are configured with multi-core processors, large-capacity memory, and high-speed hard disks, which can meet the requirements of rapid data processing and storage.

[0117] The data acquisition frequency is adjusted according to the operating status of the equipment and the monitoring requirements, generally between milliseconds and seconds. For the monitoring of key parameters, such as the temperature and vibration of the motor, the acquisition frequency is set to more than 10 times per second to ensure that abnormal changes can be detected in a timely manner. For the monitoring of general parameters, such as the ambient temperature and humidity of the equipment, the acquisition frequency can be appropriately reduced and set to 1 time per minute.

[0118] 2. Digital twin model construction

[0119] (1) Use 3D modeling technology to construct the geometric model of the train maintenance equipment.

[0120] Adopt a combination of CAD software and 3D scanning technology to accurately restore the shape and structure of the equipment. First, use a 3D scanning device to scan the fixed car lift in all directions to obtain the point cloud data of the equipment. Then, import the point cloud data into CAD software for data processing and model construction. In CAD software, through the fitting and editing of the point cloud data, a 3D geometric model of the equipment is constructed, as Figure 7 shown. For example, for a complex train maintenance equipment, through 3D scanning and CAD modeling, the shape and positional relationship of each component of the equipment can be accurately constructed, and the accuracy error of the model is controlled within ±1 mm.

[0121] Optimize and render the geometric model to make it more realistically represent the appearance of the device. Use texture mapping technology to map the actual appearance texture of the device onto the geometric model, making the model look more realistic. At the same time, use rendering techniques for lighting and shadow effects to enhance the three-dimensional sense and realism of the model. As Figure 8 shown. For example, during the model rendering process, set appropriate lighting parameters and material properties according to the environment and lighting conditions in which the device is located, so that the appearance effect of the model is consistent with the actual device.

[0122] (2) Construct a physical model of the device based on its physical characteristics and operating principles.

[0123] For the mechanical transmission system of the fixed car lift, establish a dynamic model. Analyze the mechanical relationships between various components according to the structure and movement mode of the device, and establish a motion equation. For example, for a motor-driven transmission system, consider factors such as the output torque of the motor, transmission ratio, and load, and establish a relationship model between the rotational speed and torque of the motor and the movement speed and acceleration of the device. Through dynamic simulation software, simulate and analyze the model to predict the motion performance and mechanical characteristics of the device under different working conditions. For example, during the simulation process, the rotational speed and load of the motor can be adjusted to observe the motion state and force conditions of the device to verify the accuracy of the model.

[0124] For the hydraulic system, establish a thermodynamic model. Analyze the heat transfer and temperature change laws during the operation of the hydraulic system, and establish heat conduction equations and fluid dynamics equations. Consider factors such as the physical properties of the hydraulic oil, the resistance of the pipeline, and the heat dissipation conditions, and simulate the temperature distribution and change of the hydraulic system during operation. For example, through thermodynamic simulation software, perform a thermal analysis of the hydraulic system to predict the temperature rise of the system during long-term operation, providing a basis for the heat dissipation design and fault diagnosis of the device.

[0125] (3) Use machine learning and deep learning algorithms to construct a data-driven digital twin model.

[0126] Collect a large amount of historical operation data of the fixed car lift, including data such as temperature, pressure, and vibration collected by sensors, as well as information such as the maintenance records and operation logs of the device. Clean and preprocess this data, remove noise and abnormal data, and extract key features. Use a data smoothing algorithm to process the sensor data to remove high-frequency noise in the data; use the principal component analysis (PCA) algorithm to perform dimensionality reduction on high-dimensional data and extract the main feature vectors.

[0127] Select appropriate machine learning algorithms, such as neural networks, support vector machines, etc., to build a digital twin model. Use the preprocessed historical data as training data and input it into the machine learning algorithm for model training. By continuously adjusting the parameters and structure of the model, the model can accurately predict the future state and performance of the device. Build a fault prediction model for train maintenance equipment using a neural network. Through learning a large amount of fault data and normal operation data, the model can predict whether the device is likely to fail and the type and location of the fault based on the current device operation status data.

[0128] 3. Verification of virtual-real consistency

[0129] (1) Design a verification index system, including model accuracy index, response time index, data synchronization index, etc.

[0130] The model accuracy index includes geometric accuracy, physical accuracy, and data accuracy. Geometric accuracy is measured by comparing the shape and size differences between the virtual model and the actual device, and the error is required to be controlled within ±2 mm. For example, use a three-dimensional measuring instrument to measure the key dimensions of the actual device, and then compare them with the corresponding dimensions in the virtual model to calculate the error value. Physical accuracy is measured by comparing the physical property differences between the virtual model and the actual device. For example, the temperature simulation error is controlled within ±1 °C, and the pressure simulation error is controlled within ±0.5% FS. During the operation of the device, monitor the temperature and pressure data of the actual device and the virtual model simultaneously and calculate the error value. Data accuracy is measured by comparing the operation data differences between the virtual model and the actual device, and the data error rate is required to be controlled within 5%. For example, compare the operation data such as the motor speed and current of the actual device with the corresponding data in the virtual model to calculate the error rate.

[0131] The response time index measures the response speed of the virtual model to the state changes of the actual device. It is required that the virtual model can respond to the state changes of the actual device in real time, and the response time does not exceed 1 second. For example, set a state change event on the actual device, such as suddenly increasing the load or changing the running speed, and observe the response time of the virtual model to this event.

[0132] The data synchronization index measures the data synchronization between the virtual model and the actual device. The data synchronization error is required to be controlled within ±0.5 s. For example, during the operation of the device, record the occurrence time of a key event of the actual device, and at the same time check the time record of the corresponding event in the virtual model, and calculate the time difference as the data synchronization error.

[0133] (2) Conduct static verification. When the device is in a static state, verify the geometric accuracy and physical accuracy of the digital twin model.

[0134] Use high-precision measuring instruments, such as laser rangefinders, thermometers, pressure gauges, etc., to measure the key dimensions and physical parameters of the actual equipment. Then, compare the measurement results with the corresponding data in the virtual model and calculate the error value. For example, for the external dimensions of the equipment, use a laser rangefinder for measurement with a measurement accuracy of ±0.1 mm. For the temperature and pressure parameters of the equipment, use high-precision thermometers and pressure gauges for measurement with measurement accuracies of ±0.2 °C and ±0.1% FS respectively.

[0135] During the static verification process, the visualization effect of the virtual model can also be evaluated. Check whether the appearance of the virtual model is consistent with the actual equipment, including details such as color, texture, and markings. For example, compare the appearance photos of the virtual model and the actual equipment to check for obvious differences.

[0136] (3) Conduct dynamic verification. When the equipment is in operation, verify the response time and data synchronization of the digital twin model.

[0137] Set a series of dynamic test conditions on the actual equipment, such as start, stop, acceleration, deceleration, etc. At the same time, observe the response of the virtual model to these conditions and record the response time. For example, during the acceleration process of the equipment, record the time required for the actual equipment to increase from one speed to another, and at the same time observe the corresponding speed change time in the virtual model to calculate the response time error.

[0138] During the dynamic verification process, monitor the data change situations in the actual equipment and the virtual model in real time and compare the data synchronization between the two. For example, use a data acquisition system to collect data such as temperature, pressure, and rotational speed in the actual equipment and the virtual model at the same time, and calculate the data synchronization error. If a large data synchronization error is found, it is necessary to check the data transmission link and the data processing algorithm of the model and perform optimization and adjustment.

[0139] (4) Regularly conduct a comprehensive virtual-real consistency verification on the digital twin model to ensure the accuracy and reliability of the model.

[0140] The verification cycle is determined according to the importance and operating characteristics of the equipment. For example, for key equipment, conduct verification once a week; for general equipment, conduct verification once a month. Regular verification includes a comprehensive inspection and evaluation of indicators such as model accuracy, response time, and data synchronization, and adjust and optimize the digital twin model according to the verification results.

[0141] 4. Application and Effect Evaluation

[0142] (1) Apply the constructed digital twin model to the management and maintenance of train maintenance equipment. By real-time monitoring the operating status and performance parameters of the equipment, potential problems and faults can be detected in a timely manner, and corresponding measures can be taken for handling. For example, when the digital twin model predicts that the equipment may have a fault, an early warning is sent in advance to notify the maintenance personnel for inspection and repair to avoid the occurrence of equipment failures.

[0143] (2) Evaluate the application effect of the digital twin model. The evaluation indicators include the reduction rate of equipment failure rate, the reduction rate of maintenance cost, the improvement rate of inspection efficiency, etc. By comparing the equipment operation data and maintenance records before and after applying the digital twin model, the actual application effect of the model is analyzed. For example, after a period of application, the equipment failure rate has been reduced by 30%, the maintenance cost has been reduced by 20%, and the inspection efficiency has been improved by 40%, which proves the effectiveness and practicality of the digital twin model.

[0144] (3) Precautions and technical key points during the implementation process

[0145] (1) Selection and installation of sensors: The selection of sensors should be reasonably made according to the monitoring requirements and operating environment of the equipment to ensure the performance and reliability of the sensors. The installation positions of the sensors should be carefully designed to ensure that key data can be accurately collected without affecting the normal operation of the equipment.

[0146] (2) Stability of data collection and transmission: The data collection and transmission system should have high stability and reliability to ensure the real-time and accuracy of data. Redundant design and backup mechanisms are adopted to prevent data loss and system failures.

[0147] (3) Accuracy and reliability of the digital twin model: The construction of the digital twin model should be based on accurate physical principles and actual data, and advanced modeling algorithms and technologies should be adopted to ensure the accuracy and reliability of the model. The verification and optimization of the model should be carried out regularly to adapt to the operation changes of the equipment and environmental impacts.

[0148] (4) Comprehensiveness and accuracy of virtual-real consistency verification: The virtual-real consistency verification should cover all aspects of the model, including geometric accuracy, physical accuracy, response time, data synchronization, etc. The verification methods and indicators should be scientific and reasonable, and can accurately reflect the differences between the virtual and the real.

[0149] (5) Security and privacy protection: During the implementation process, attention should be paid to protecting the security of the equipment and data to prevent data leakage and system attacks. Encryption technologies and access control mechanisms are adopted to ensure the security and privacy of the data.

[0150] The present invention provides a method for constructing a digital twin model of urban rail yard equipment and virtual-real consistency verification, having the following technical contributions and innovation values:

[0151] 1. It solves the problems in the management and maintenance of urban rail yard equipment, improves the operation efficiency and safety of equipment, and reduces the maintenance cost.

[0152] 2. It promotes the application and development of digital twin technology in the urban rail field and provides strong support for the intelligent construction of urban rail transit.

[0153] 3. It innovates key technologies such as multi-source data fusion, data-driven model construction, and virtual-real consistency verification, providing reference for technical research and application in related fields.

[0154] In summary, the construction method and virtual-real consistency verification method of the digital twin model of urban rail yard equipment have broad application prospects and development potential, and will bring positive impacts to the development of urban rail transit.

[0155] Corresponding to the above-disclosed method for constructing and verifying a digital twin model of major equipment in urban rail yards, an embodiment of the present invention also discloses a system for constructing and verifying a digital twin model of major equipment in urban rail yards, as Figure 9 shown, which specifically includes:

[0156] A data acquisition module, configured to perform multi-source data acquisition on urban rail yard equipment and preprocess the acquired data;

[0157] A digital twin model construction module, configured to perform data fusion and feature extraction on the preprocessed data and construct a data-driven equipment digital twin model;

[0158] A verification module, configured to perform virtual-real consistency verification on the digital twin model based on the established verification index system, and analyze and process the verification results.

[0159] It should be noted that for the detailed description of a system for constructing and verifying a digital twin model of major equipment in urban rail yards provided in an embodiment of the present invention, reference can be made to the related description of a method for constructing and verifying a digital twin model of major equipment in urban rail yards provided in an embodiment of the present application, which will not be elaborated here.

[0160] In addition, an embodiment of the present invention also provides an electronic device, where the device includes: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to execute the steps of a method for constructing and verifying a digital twin model of major equipment in urban rail yards as described in any one of the above.

[0161] It should be noted that for the detailed description of an electronic device provided in an embodiment of the present invention, reference can be made to the relevant description of a method for constructing and verifying a digital twin model of major equipment in an urban rail yard section provided in an embodiment of the present application, which will not be elaborated here.

[0162] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for constructing and verifying a digital twin model of major equipment in an urban rail yard section as described in any one of the above are implemented.

[0163] It should be noted that for the detailed description of a computer-readable storage medium provided in an embodiment of the present invention, reference can be made to the relevant description of a method for constructing and verifying a digital twin model of major equipment in an urban rail yard section provided in an embodiment of the present application, which will not be elaborated here.

[0164] Those skilled in the art can understand that all or part of the functions of the above methods can be implemented in a hardware manner or in a computer program manner. When all or part of the functions in the above embodiments are implemented in a computer program manner, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, magnetic disk, optical disk, hard disk, etc. The above functions are implemented by a computer executing the program. For example, the program is stored in the memory of the device, and when the processor executes the program in the memory, the above all or part of the functions can be implemented. In addition, when all or part of the functions in the above embodiments are implemented in a computer program manner, the program can also be stored in a storage medium such as a server, another computer, magnetic disk, optical disk, flash drive or mobile hard disk, downloaded or copied and saved to the memory of the local device, or the system of the local device is updated in version. When the processor executes the program in the memory, the above all or part of the functions in the above embodiments can be implemented.

[0165] The above uses specific examples to elaborate on the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the technical field to which the present invention belongs, based on the idea of the present invention, several simple deductions, deformations or substitutions can also be made.

Claims

1. A method for constructing and verifying a digital twin model of major equipment in an urban rail station, characterized in that: The method comprises: Collect multi-source data from urban rail yard equipment and pre-process the collected data; Perform data fusion and feature extraction on the preprocessed data, and build a data-driven equipment digital twin model; Based on the established verification index system, the virtual-reality consistency of the digital twin model is verified, and the verification results are analyzed and processed.

2. The method for constructing and verifying a digital twin model of major equipment in an urban rail yard as claimed in claim 1, characterized in that: Collect multi-source data from urban rail yard equipment and pre-process the collected data, including: Build a distributed data acquisition system, including sensor nodes, transmission networks, and storage servers; Select appropriate sensors according to the different types and characteristics of urban rail equipment, and the layout of sensor nodes follows the principle of comprehensive coverage and key monitoring of key parts; The frequency of data collection is dynamically adjusted according to the equipment operation characteristics and monitoring requirements. The data collected by the sensor is transmitted to the storage server in real time through the transmission network for storage and processing; The collected raw data is cleaned, denoised and normalized to improve data quality and unify it into a standard format for subsequent processing and analysis.

3. The method for constructing and verifying a digital twin model of major equipment in an urban rail yard as claimed in claim 1, characterized in that: Data fusion and feature extraction are performed on the preprocessed data, including: Use data fusion algorithms including Kalman filtering to fuse different sensor data to obtain more comprehensive and accurate equipment status information; Use feature extraction algorithms including principal component analysis to reduce the dimensionality of the fused high-dimensional data and extract key features as input parameters for the digital twin model; By analyzing feature data and mining the potential laws and patterns of equipment operation, a basis is provided for the construction and optimization of digital twin models.

4. The method for constructing and verifying a digital twin model of major equipment in an urban rail yard as claimed in claim 1, characterized in that: Construct a data-driven equipment digital twin model, including: Use 3D modeling technology to build high-precision 3D geometric models of urban rail equipment, including: using a combination of CAD software and 3D scanning technology to accurately restore the appearance structure and detailed features of the equipment; for complex equipment structures, use sub-component modeling and assembly to ensure the accuracy and editability of the model; control the accuracy of the 3D geometric model within the millimeter level, and be able to present the actual appearance and size of the equipment with high fidelity; Based on the physical characteristics and operating principles of the equipment, a physical model of the equipment is constructed, including a geometric model, a behavioral model, and a rule model; the geometric model is constructed using three-dimensional measurement technology to reflect the geometric shape of the equipment and provide a spatial framework for the physical model; the behavioral model analyzes the behavioral performance under different working conditions based on the operating principles and physical characteristics of the equipment, and predicts the output response through modeling using physical laws and dynamic equations; the rule model is formulated based on operating specifications and safety restrictions to ensure the safe operation of the equipment, and can detect abnormal conditions and issue alarms; Use machine learning and deep learning algorithms to build a data-driven digital twin model; by learning from large amounts of historical data, the model can predict the future status and performance of the equipment.

5. The method for constructing and verifying a digital twin model of major equipment in an urban rail yard as claimed in claim 1, characterized in that: Establish a verification indicator system, including: The verification indicator system includes: Model accuracy indicators: including geometric accuracy, physical accuracy and data accuracy of the model; geometric accuracy is measured by comparing the difference in external dimensions between the virtual model and the actual equipment; physical accuracy is measured by comparing the difference in physical characteristics between the virtual model and the actual equipment; data accuracy is measured by comparing the difference in operating data between the virtual model and the actual equipment; Response time indicator: measures the response speed of the virtual model to the status changes of the actual equipment. It requires that the virtual model can respond to the status changes of the actual equipment in real time and the response time is within the preset range. Data synchronization index: measures the data synchronization between the virtual model and the actual equipment, requiring that the data synchronization error between the virtual model and the actual equipment is within a preset range.

6. The method for constructing and verifying a digital twin model of major equipment in an urban rail yard as claimed in claim 5, characterized in that: The virtual-real consistency verification of the digital twin model specifically includes: Static verification: Verify the geometric accuracy and physical accuracy of the digital twin model when the equipment is stationary; calculate the error value by measuring the key dimensions and physical parameters of the actual equipment and comparing them with the virtual model; verify the physical accuracy by setting specific physical conditions on the actual equipment and comparing them with the simulation results in the virtual model; Dynamic verification: Verify the response time and data synchronization of the digital twin model when the equipment is in operation; set specific operating conditions on the actual equipment, observe the response of the virtual model, and record the response time; compare the data changes between the actual equipment and the virtual model in real time, and calculate the data synchronization error; Regular verification: Regularly conduct comprehensive virtual-reality consistency verification on the digital twin model to ensure the accuracy and reliability of the model; the verification cycle is determined based on the importance of the equipment and operating characteristics; regular verification includes comprehensive testing and evaluation of model accuracy, response time and data synchronization indicators.

7. The method for constructing and verifying a digital twin model of major equipment in an urban rail yard as claimed in claim 6, characterized in that: Analyze and process the verification results, including: Result analysis: Analyze the verification results in detail to find out the reasons for the inconsistency between the virtual and the real; Error correction: Take appropriate measures to correct the error based on the analysis results; Model update: Update and optimize the digital twin model based on the verification results and error correction.

8. A system for constructing and verifying a digital twin model of major equipment in an urban rail yard, characterized in that: The system comprises: The data acquisition module is used to collect multi-source data from urban rail equipment and pre-process the collected data; The digital twin model building module is used to perform data fusion and feature extraction on the preprocessed data and build a data-driven digital twin model of the equipment; The verification module is used to verify the virtual-reality consistency of the digital twin model based on the established verification indicator system, and to analyze and process the verification results.

9. An electronic device, characterized in that: The device comprises: a processor and a memory; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute the steps of a method for constructing and verifying a digital twin model of major equipment in an urban rail yard as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for constructing and verifying a digital twin model of major equipment in an urban rail yard as described in any one of claims 1 to 7.

Images