Digital Twin Model of Electronic Equipment and Its Construction Method and Application

Abstract

The present invention provides a digital twin model of an electronic equipment, a construction method thereof and an application, relating to the field of digital twins. In the digital twin model of the electronic equipment, the digital twin meta-model includes a data-driven model and a data analysis model; the data-driven model is used to describe the geometric information, physical properties and assembly constraint relationships of the physical equipment; the data analysis model is used to express the functional characteristics of the physical equipment, including a structural system model, a control system model, an electrical system model, and an artificial intelligence algorithm model for the digital twin derivative model; the digital twin derivative model is used to reflect the physical connection, control, maintenance and management during the application process of the physical equipment. A digital twin model of the physical equipment is constructed, and a real-time mapping between the physical equipment and the digital twin equipment is carried out by using a data communication module, so as to realize the visual display, analysis and management of the status information, fault diagnosis information, predictive maintenance information and health management information of the physical equipment, and improve the remote operation and maintenance level of the electronic equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and particularly to a digital twin model of an electronic device, a construction method thereof, and an application thereof. Background Art

[0002] Electronic devices are one of the core devices for the intelligent perception of the national physical space. They are rich in variety, diverse in function, and widely used. Electronic devices involve multiple disciplines such as mechanics, electricity, optics, magnetism, and heat. With the development of electronic information technology and advanced manufacturing technology, the development trend of electronic device research and development shows system polarization, structural function integration, and multi-function integration. This development trend brings higher requirements for the assembly and maintenance of electronic devices. Facing the complex international environment and the needs of national defense construction, it also brings new challenges to the operation and maintenance of electronic devices. Digital twin is a technical means that constructs a virtual model of a physical entity in a digital way, maps the actual state of the physical entity by means of real-time data acquisition, and then realizes the state monitoring, fault diagnosis, predictive maintenance, and health management of the physical entity, and improves the operation and maintenance level of the physical entity.

[0003] As an important part of digital twins, the model is an important prerequisite for realizing digital twin applications. How to quickly construct a digital twin model and improve the generalization and real-time performance of the application platform has become an urgent problem to be solved. However, there are the following deficiencies in the actual modeling and application process: ① The model is the basis for the application of digital twin technology. At present, there is a lack of relevant research on digital twin models, and the application is mainly the state visualization of physical objects in the digital space, without considering fault diagnosis, predictive maintenance, and health management based on data analysis models, making it difficult to meet the real-time interaction and remote operation and maintenance requirements of complex electronic devices; ② At present, digital twin technology is in the initial exploration stage. Different enterprises and researchers have different definitions and interpretations of digital twin models. Some even think that digital twin technology is digital prototype technology, resulting in the blurred boundary between digital twin models and digital prototype models, and thus generating ambiguity.

[0004] In view of this, it is necessary to improve the remote operation and maintenance level of electronic devices. Summary of the Invention

[0005] (1) Technical Problems to be Solved

[0006] Aiming at the deficiencies of the prior art, the present invention provides a digital twin model of an electronic device, a construction method thereof, and an application thereof, and solves the technical problem of low remote operation and maintenance level.

[0007] (2) Technical Solutions

[0008] To achieve the above object, the present invention is realized through the following technical solutions:

[0009] An electronic equipment digital twin model, including a digital twin meta-model and a digital twin derivative model;

[0010] The digital twin meta-model includes a data-driven model and a data analysis model;

[0011] The data-driven model is used to describe the geometric information, physical properties, and assembly constraint relationships of physical equipment;

[0012] The data analysis model is used to express the functional characteristics of physical equipment, including a structural system model, a control system model, an electrical system model, and an artificial intelligence algorithm model of the digital twin derivative model for application services;

[0013] The digital twin derivative model is used to reflect the physical connection, control, management, and maintenance during the application process of physical equipment.

[0014] Preferably, it further includes an environment model, which is used to reflect the operating environment of physical equipment.

[0015] Preferably, the digital twin derivative model is used to identify and evaluate the fault modes of physical equipment by mathematical methods, and the mathematical methods include knowledge-based neural network method, expert system method, fault tree method, and data-driven multivariate statistical analysis method, clustering analysis method.

[0016] A construction method for the electronic equipment digital twin model as described above, including:

[0017] S300. Requirement analysis: According to the application requirements of physical equipment in different scenarios, sort out the geometric features, physical properties, constraint conditions, and behavior rule information of the model, and determine the relationship content between the construction and application of the digital twin model;

[0018] S301. Model construction: According to the characteristics of physical equipment and the application requirements in different scenarios, construct a data-driven model and a data analysis model through 3D design software, simulation software, and artificial intelligence algorithms respectively. The digital twin model supports the marking, loading, and display of equipment fault points on the model;

[0019] S302. Model fusion: On a unified coordinate system, fuse the data-driven model and the data analysis model, and perform coordinate matching and position calibration according to actual operation requirements and specifications;

[0020] S303. Model inspection and modification: Drive the model through the historical data of physical equipment, check the robustness and rationality of the model, and modify the geometric, physical, constraint, or functional characteristics that do not meet the requirements during model inspection;

[0021] S304. Model management: Manage the model in terms of levels, categories, and versions.

[0022] Preferably, in S301, a data-driven model of the physical equipment is established through 3D design software to map the geometric features of the equipment. The material should be the same as that of the physical equipment, and the color, texture, and texture map should be close to the actual appearance of the physical equipment. A data analysis model of the physical equipment is established using simulation software and artificial intelligence algorithms to describe the behavior mechanism of the equipment.

[0023] Preferably, the construction process of the data-driven model in S301 includes:

[0024] S400. Interface design: Perform data input / output according to predefined data types and adapt the software interface for accessing the data analysis model.

[0025] S401. Data-driven model design: Simplify, lightweight, and texture the existing data-driven model through a 3D design platform or tool, perform reverse modeling on the data-driven model of the equipment that cannot be directly obtained, and dynamically update the model according to the twin data.

[0026] S402. Model simplification and lightweighting: Delete geometric features, components, and information that do not affect the model application requirements, perform patch processing on the remaining geometric features to make the data volume of the simplified and lightweighted model small, and try to ensure that the lightweighted model is consistent with the physical equipment in terms of geometry and shape.

[0027] S403. Model physical properties and constraint conditions: Set according to the physical properties of the physical equipment, and set material properties according to different application requirements. The material properties include mechanical, electrical, magnetic, and optical properties.

[0028] S404. Model inspection and modification: Inspect the model according to the model application requirements and the consistency inspection rules of the geometric features, assembly constraints between the physical equipment and the model, and modify the constituent elements such as geometry, set materials, and assembly constraints that do not meet the requirements according to the results of the model inspection.

[0029] Preferably, the construction process of the data analysis model in S301 includes:

[0030] S500. Interface design: Perform data input / output according to predefined data types and adapt the software interface for accessing the data analysis model.

[0031] S501. Data analysis model design: Construct a digital model describing the behavior mechanism of the equipment through corresponding simulation software and artificial intelligence algorithms, including kinematic models, dynamic analysis models, thermal simulation analysis models, reliability simulation analysis models, static analysis models, electrical performance simulation models, servo control system simulation models, and other multi-disciplinary and multi-physical quantity analysis models.

[0032] S502, Functional characteristic setting: Describe and set the functional attribute characteristics of the model according to the respective characteristics and application requirements of each system of the physical equipment. The functional attributes include stress, strain, communication, and electromagnetic interference.

[0033] S503, Model inspection and modification: Inspect the model according to the model application requirements and the inspection rules for the consistency of the state attributes and behavior rules between the physical equipment and the model, and modify the state elements that do not meet the requirements.

[0034] Preferably, the interface of the S400 or S500 should provide functions of real-time data synchronization, data compression, and data quality assessment.

[0035] An application of the digital twin model of the electronic equipment as described above includes: collecting data through sensors or using existing data systems, visually monitoring the state of the physical equipment, and using edge computing at the data collection stage and big data analysis to perform fault monitoring, fault diagnosis, predictive maintenance, and health management on the physical equipment.

[0036] Preferably, the state monitoring is based on real-time collected data to monitor the operating state of the physical equipment in the digital space and alarm or perform corresponding automatic control on abnormal data.

[0037] The fault diagnosis is to construct a fault diagnosis model based on the operating historical data of the physical equipment, monitor the key fault parameters in real time, and identify the equipment fault mode by combining the operating state characteristics of the equipment.

[0038] The predictive maintenance is to analyze the damage and degradation mechanism of the key components of the physical equipment based on real-time operating data, analyze the internal damage state of the key components in real time, and achieve predictive maintenance of the equipment. The predictive maintenance includes state trend prediction and remaining life prediction. The state trend prediction can predict the state time series of the physical equipment according to the monitoring data and historical time series data, and combine the fault diagnosis model to describe the generation and transmission process of faults and predict possible fault modes. The remaining life prediction analyzes the failure reasons by real-time monitoring the damage state data of key components and vulnerable components and dynamically updates the predictive model.

[0039] The health management provides a series of maintenance and support measures according to the results of fault diagnosis and predictive maintenance.

[0040] (III) Beneficial effects

[0041] The present invention provides a digital twin model of an electronic equipment, its construction method, and application. Compared with the prior art, it has the following beneficial effects:

[0042] The present invention defines the composition types of a multi-dimensional digital twin model and the relationships between various models. Specifically, a digital twin model of a physical equipment is constructed, and a data communication module is used for real-time mapping between the physical equipment and the digital twin equipment, realizing the visual display, analysis, and management of the state information, fault diagnosis information, predictive maintenance information, and health management information of the physical equipment, and improving the remote operation and maintenance level of electronic equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0044] Figure 1 FIG. is a schematic structural diagram of a digital twin model of an electronic equipment provided by an embodiment of the present invention;

[0045] Figure 2 FIG. is a schematic flow diagram of a method for constructing a digital twin model of an electronic equipment provided by an embodiment of the present invention;

[0046] Figure 3 FIG. is a schematic flow diagram of a method for constructing a data-driven model provided by an embodiment of the present invention;

[0047] Figure 4 FIG. is a schematic flow diagram of a method for constructing a data analysis model provided by an embodiment of the present invention;

[0048] Figure 5 FIG. is a schematic interface diagram provided by an embodiment of the present invention;

[0049] Figure 6 FIG. is a schematic diagram of the application of a digital twin model provided by an embodiment of the present invention;

[0050] Figure 7 FIG. is a schematic diagram of the application of a digital twin system framework diagram provided by an embodiment of the present invention;

[0051] Figure 8(a) to Figure 8(b) FIG. is a digital twin model diagram of a certain tethered balloon equipment provided by an embodiment of the present invention;

[0052] Figure 9(a) to Figure 9(b) FIG. is a data analysis model diagram of a certain tethered balloon equipment provided by an embodiment of the present invention;

[0053] Figure 10 FIG. is a schematic diagram of a digital twin remote platform for a balloon-borne floating platform provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] By providing a digital twin model of an electronic device, a construction method thereof and an application, the embodiments of the present application solve the technical problem of low remote operation and maintenance level.

[0056] The overall idea of the technical solutions in the embodiments of the present application to solve the above technical problems is as follows:

[0057] The embodiments of the present invention clarify the composition types of the multi-dimensional digital twin model and the relationships between the models. Specifically, a digital twin model of a physical device is constructed, and a data communication module is used for real-time mapping between the physical device and the digital twin device, so as to realize the visual display, analysis and management of the state information, fault diagnosis information, predictive maintenance information, and health management information of the physical device, and improve the remote operation and maintenance level of the electronic device.

[0058] To better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0059] Embodiment:

[0060] In a first aspect, as Figure 1 shown, the embodiments of the present invention provide a digital twin model of an electronic device, including a digital twin meta-model and a digital twin derivative model.

[0061] The digital twin meta-model includes a data-driven model and a data analysis model;

[0062] The data-driven model is used to describe the geometric information, physical properties and assembly constraint relationships of the physical device.

[0063] The geometric information includes the shape, size, etc. of the physical device; the physical properties include the color, mass, material characteristics, etc. of the physical device.

[0064] The data analysis model is a model constructed to support functions such as mechanism motion simulation and servo control simulation; it is used to express the functional characteristics of the physical device, including a structural system model, a control system model, an electrical system model, and an artificial intelligence algorithm model of the digital twin derivative model for application services;

[0065] The digital twin derivative model is used to reflect the Internet of Things control, management, and maintenance in the application process of physical equipment; it is also used to identify and evaluate the failure modes of physical equipment using mathematical methods, including knowledge-based neural network methods, expert system methods, fault tree methods, and data-driven multivariate statistical analysis methods, clustering analysis methods.

[0066] The above-mentioned multi-dimensional digital twin model of electronic equipment consists of a digital twin meta-model and a digital twin derivative model. The meta-model reflects information dimensions such as geometric elements, physical elements, constraint elements, and state elements of electronic equipment, the object scale dimension of data analysis models and data-driven models, and functional dimensions such as structural system models, control system models, and electrical system models; the derivative model reflects the Internet of Things control, management, and maintenance dimensions in the application process of electronic equipment.

[0067] A certain coupling and mutual association should be established between the data-driven model and the data analysis model. The analysis results of the data analysis model can act on the data-driven model and support synchronous updates to ensure that data does not get confused during the application process.

[0068] In one embodiment, the digital twin model of the electronic equipment further includes an environment model, which is used to reflect the operating environment of the physical equipment.

[0069] In the second aspect, as Figure 2 shown, an embodiment of the present invention provides a construction method for a digital twin model of electronic equipment, including:

[0070] S300. Requirement analysis: According to the application requirements of physical equipment in different scenarios, sort out the geometric features, physical properties, constraint conditions, and behavior rule information of the model, and determine the relationship content between the construction and application of the digital twin model.

[0071] S301. Model construction: According to the characteristics of physical equipment and the application requirements in different scenarios, construct a data-driven model and a data analysis model respectively through 3D design software, simulation software, and artificial intelligence algorithms to meet the application requirements of the equipment, and be able to mark, load, display, and correct fault points and fault causes, and at the same time support remote maintenance of the equipment (that is, the digital twin model supports the marking, loading, and display of equipment fault points on the model).

[0072] Among them, a data-driven model of physical equipment is established through 3D design software to map the geometric features of the equipment, and the material should be the same as that of the physical equipment, and the color, texture, and texture map should be close to the actual appearance of the physical equipment; a data analysis model of physical equipment is established using simulation software and artificial intelligence algorithms to describe the behavior mechanism of the equipment.

[0073] S302. Model Fusion: On a unified coordinate system, such as the zero coordinate (0, 0, 0) of the world coordinate system, fuse the data-driven model and the data analysis model, and perform coordinate matching and position calibration according to the actual operation requirements and specifications to ensure the uniqueness, real-time nature, and reliability of model and data information updates. At the same time, set institutional motion constraints and establish a motion drive module and a virtual trigger signal management unit for the digital twin model.

[0074] S303. Model Inspection and Modification: Drive the model through the historical data of the physical equipment to check the robustness and rationality of the model, so that there is no mutual interference between the models; and modify the geometric, physical, constraint, or functional characteristics that do not meet the requirements in the model inspection. Drive the model through the real-time data of the physical equipment to check the consistency of the actions of the virtual and real equipment.

[0075] S304. Model Management: Manage the models hierarchically, by category, and by version for model sharing and exchange, and support the logical association between the models and the twin data to facilitate applications such as quick historical reproduction.

[0076] In one embodiment, as Figure 3 shown, the construction process of the data-driven model in S301 includes:

[0077] S400. Interface Design: Perform data input / output according to predefined data types (such as JSON, XML, etc.) and adapt to the software interfaces for accessing the data analysis model to ensure the connectivity of data loading and display;

[0078] S401. Data-Driven Model Design: Generally, two modes of forward modeling and reverse modeling are adopted. In the embodiment of the present invention, through a three-dimensional design platform or tool (such as 3DMAX, PiXYZ, etc.), simplify, lightweight, and texture the existing data-driven model, perform reverse modeling on the equipment data-driven model that cannot be directly obtained, and dynamically update the model according to the twin data;

[0079] S402. Model Simplification and Lightweighting: Delete geometric features, components, and information that do not affect the model application requirements, and perform patch processing on the remaining geometric features to make the data volume of the simplified and lightweight model small, and try to ensure that the lightweight model is consistent with the physical equipment in terms of geometry and appearance;

[0080] S403. Model Physical Attributes and Constraint Conditions: Set according to the actual physical attributes of the physical equipment as much as possible, such as actual color, texture, etc., for the visualization of model application, and set material attributes according to different application requirements. The material attributes include mechanical (elastic modulus, Poisson's ratio, etc.), electrical (conductivity, resistivity, etc.), magnetic (magnetic permeability, magnetic susceptibility, etc.), and optical (reflectivity, absorptivity, etc.) attributes;

[0081] S404, Model Inspection and Modification: Inspect the model according to the model application requirements and the consistency inspection rules of the geometric features, assembly constraints between the physical equipment and the model, so as to ensure the effectiveness and accuracy of the model; and modify the component elements such as geometry, set materials, and assembly constraints that do not meet the requirements according to the results of the model inspection.

[0082] In one embodiment, as Figure 4 shown, the construction process of the data analysis model in S301 includes:

[0083] S500, Interface Design: Perform data input / output according to predefined data types (such as JSON, XML, etc.) and adapt the software interface accessing the data analysis model to ensure the connectivity of data loading and display;

[0084] S501, Data Analysis Model Design: Build a digital model describing the behavior mechanism of the equipment through corresponding simulation software (such as ANSYS, Modelica, Matlab, etc.) and artificial intelligence algorithms (such as statistical analysis, machine learning, etc.), including kinematic models, dynamic analysis models, thermal simulation analysis models, reliability simulation analysis models, static analysis models, electrical performance simulation models, servo control system simulation models, etc., which are multi-disciplinary and multi-physical quantity analysis models;

[0085] S502, Functional Characteristic Setting: Describe and set the functional attribute characteristics of the model according to the respective characteristics and application requirements of each system of the physical equipment, and the functional attributes include stress, strain, communication, and electromagnetic interference;

[0086] S503, Model Inspection and Modification: Inspect the model according to the model application requirements and the inspection rules of the consistency of the state attributes and behavior rules between the physical equipment and the model, and modify the state elements that do not meet the requirements.

[0087] The interface of S400 or S500 is the bridge for information interaction between the physical equipment and the digital twin model. By agreeing on the interface relationship, the information interaction between the model and the equipment is realized, which facilitates the inspection, modification, and application process of the model, and also facilitates the reuse of digital twin models between different equipment; it should provide functions of data real-time synchronization, data compression, and data quality assessment to meet the virtual-real mapping between the physical equipment and the digital twin model.

[0088] It should be noted that the design of the interface in the embodiments of the present invention is as Figure 5As shown, the twin data of physical equipment is collected by sensors, and after parsing and processing, it drives the operation of the digital twin model, realizing the virtual-real mapping between the physical equipment and the digital twin model. At the same time, through preset thresholds or big data analysis, decision-making information is output to the physical equipment, thereby completing the status monitoring, fault diagnosis, predictive maintenance, and health management of the physical equipment, such as Figure 6 shown.

[0089] Thirdly, as Figure 6 to 7 shown, the embodiments of the present invention provide an application of a sub-equipment digital twin model, including: collecting data of physical equipment by using sensors or existing data systems, performing visual status monitoring on the physical equipment, and using edge-side computing and big data analysis in the data collection stage to perform fault status monitoring, fault diagnosis, predictive maintenance, and health management on the physical equipment.

[0090] Among them, the status monitoring is based on real-time collected data, monitors the operating status of the physical equipment in the digital space, and alarms abnormal data or performs corresponding automatic control;

[0091] The fault diagnosis is to construct a fault diagnosis model based on the operating historical data of the physical equipment, monitor key fault parameters in real time, and identify equipment fault modes by combining the operating status characteristics of the equipment;

[0092] The predictive maintenance is based on real-time operating data, analyzes the damage and degradation mechanisms of key components of the physical equipment, and analyzes the internal damage status of key components in real time to achieve predictive maintenance of the equipment. The predictive maintenance includes status trend prediction and remaining life prediction. The status trend prediction can predict the status time series of the physical equipment according to the monitoring data and historical time series data, and describe the fault generation and transmission process in combination with the fault diagnosis model to predict possible fault modes. The remaining life prediction analyzes the failure causes by real-time monitoring the damage status data of key components and vulnerable components, and dynamically updates the predictive model;

[0093] The health management provides a series of maintenance and guarantee measures according to the results of fault diagnosis and predictive maintenance.

[0094] To further illustrate the method of the embodiments of the present invention, taking a certain tethered balloon as an example, the specific process of the present invention is introduced in detail:

[0095] A moored balloon is an aerostat that is filled with gas inside to generate buoyancy and is suspended in the high altitude by a cable restraint. By carrying a certain payload, it can perform tasks such as early warning detection, reconnaissance and surveillance, and communication in the high altitude. Since the moored balloon works in the air for a long time and it is impossible to visually monitor the working state of the moored balloon in real time, by using the method in the embodiments of the present invention, a high-fidelity digital twin equipment of the moored balloon and the working environment of the equipment can be constructed in the digital space. The sensor data is collected by the data communication module, and the digital twin model is driven to move through processing, so as to complete the state monitoring of the moored balloon in the processes such as on the ground, taking off, and staying in the air. And according to the real-time state data of the moored balloon, an instruction can be sent to the actuator (such as the mooring cable retracting and releasing control switch) through the digital twin operation and maintenance system of the moored balloon. After receiving the instruction, the actuator completes the corresponding operation, so as to realize the remote automatic control of the moored balloon.

[0096] Step 1: The moored balloon is composed of a complex rigid and flexible body structure, including a spherical body, a mooring cable, a ground mooring facility, and functional subsystems, etc. Therefore, it is necessary to construct data-driven models such as a digital twin model of the spherical body, a digital twin model of the mooring cable, and a digital twin model of the ground mooring facility, as well as data analysis models such as an electrical subsystem model, a measurement and control subsystem model, a communication subsystem model, a pressure regulation subsystem model, a dynamics calculation model, an aerodynamic calculation model, and a thermodynamics calculation model in the functional subsystems.

[0097] In addition, the working environment of the moored balloon has a serious impact on the moored balloon, such as Figure 8(a) to Figure 8(b) shown, so it is also necessary to construct a digital twin environment model.

[0098] Step 2: Construct a digital twin meta-model and a digital twin derivative model respectively according to the steps shown in Figure 3 and Figure 4 shown.

[0099] Among them, the spherical body is composed of a bladder, a payload, and other components. Taking the central coordinate system of the spherical body as the local coordinate system SLCS (S s -o s x s y s z s ) to create a digital twin model of the spherical body. The bladder is a flexible body model. It is necessary to make the spherical body have texture and bumpy features through texturing, and use the obi-fluid in unity to simulate the inflation and deflation process. At the same time, the speed and time of the inflation and deflation process of the spherical body are controlled by code to realize the configurability of this process; the payload and other components can be simplified according to the visualization content and confidentiality requirements. The model is simplified by 3D Max, geometric features and components that do not affect performance expression and application are deleted, and the model volume is reduced through patch processing by Pixyz, and the position accuracy of the model is ensured to ensure that the modeling and assembly of each model of the spherical body are consistent with the physical assembly.

[0100] The mooring cable is used to connect the sphere and the ground mooring facility. During the process of releasing and mooring the mooring balloon in the air, due to the action of internal tension, gravity and wind force, the created cable model interferes with the sphere. Therefore, the cable is designed in segments through the obi module in unity and flexible feature processing is carried out to facilitate the retraction and extension of the cable and the mapping of bending changes at different heights.

[0101] The ground mooring facility takes the rotation support center coordinate system of the mooring equipment as the local coordinate system ELCS(S e -o e x e y e z e ), and digital twin models of ground mooring facilities such as mooring vehicles, servo control equipment, and retraction and extension equipment are created according to the three-dimensional model or actual size. At the same time, the ELCS is set as the original coordinate (0, 0, 0) of the world coordinate system for environmental model creation, assembly of each model, and coordinate system conversion. And through S s and S e the attitude angles of the sphere (α - pitch angle, β - yaw angle, θ - roll angle) can be calculated. The transformation matrix from ELCS to SLCS is:

[0102]

[0103] The functional subsystem mainly establishes a data analysis model through mathematical models and intelligent algorithms, and transmits the data collected and processed by the mooring balloon sensors to the digital twin model according to the corresponding interfaces to realize the virtual-real mapping of the mooring balloon and the control of the actuator.

[0104] As Figure 9(a) to Figure 9(b) shown, build the control circuit of the cable winch drive motor and set the reference value of the mooring balloon retraction and extension speed. Through the UDP protocol, the external ext transmission component reads the tension value of the mooring cable tension sensor and converts it into torque to be applied to the drive motor to control the retraction and extension of the mooring cable. Part of the historical data of the tension value can also be intercepted for simulation and training.

[0105] Step 3: Model fusion, model inspection and modification: As Figure 8(a) to Figure 8(b) shown, use the rotation support center coordinate system ELCS(S e -o e x e y e z e ) of the mooring equipment to assemble the data-driven model, data analysis model and environmental model of the mooring balloon. And use the data communication module to drive the movement of the mooring balloon digital twin model through the historical data or real-time data of the mooring balloon, and check and modify the digital twin model and digital twin system.

[0106] Final implementation Figure 10 The balloon-borne floating platform digital twin remotely shown.

[0107] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0108] The embodiment of the present invention clarifies the composition types of multi-dimensional digital twin models and the relationship between each model. Specifically, a digital twin model of physical equipment is constructed, and a data communication module is used to perform real-time mapping between physical equipment and digital twin equipment, so as to realize the visualization, analysis and management of physical equipment status information, fault diagnosis information, predictive maintenance information and health management information, and improve the remote operation and maintenance level of electronic equipment.

[0109] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0110] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a digital twin model of an electronic equipment, characterized in that The digital twin model of the electronic equipment includes a digital twin meta-model and a digital twin derivative model; the digital twin meta-model includes a data-driven model and a data analysis model; The data-driven model is used to describe the geometric information, physical properties, and assembly constraint relationships of the physical equipment; The data analysis model is used to express the functional characteristics of the physical equipment, including a structural system model, a control system model, an electrical system model, and an artificial intelligence algorithm model of the digital twin derivative model for application services; The digital twin derivative model is used to reflect the IoT management, control, and maintenance during the application process of the physical equipment; The construction method of the digital twin model of the electronic equipment includes: S300. Requirement analysis: According to the application requirements of the physical equipment in different scenarios, sort out the geometric features, physical properties, constraint conditions, and behavior rule information of the model, and determine the relationship content between the construction and application of the digital twin model; S301. Model construction: According to the characteristics of the physical equipment and the application requirements in different scenarios, construct a data-driven model and a data analysis model through 3D design software, simulation software, and artificial intelligence algorithms respectively. The digital twin model supports the marking, loading, and display of equipment fault points on the model; S302. Model fusion: On a unified coordinate system, fuse the data-driven model and the data analysis model, and perform coordinate matching and position calibration according to the actual operation requirements and specifications; S303. Model inspection and modification: Drive the model to work through the historical data of the physical equipment, check the robustness and rationality of the model, and modify the geometric, physical, constraint, or functional characteristics that do not meet the requirements during model inspection; S304. Model management: Manage the model hierarchically, by category, and by version.

2. A method for constructing a digital twin model of an electronic device as described in claim 1, characterized in that, The digital twin model of the electronic equipment further includes an environment model, and the environment model is used to reflect the operation environment of the physical equipment.

3. A method for constructing a digital twin model of an electronic device as claimed in claim 1 or 2, characterized in that, The digital twin derivative model is used to identify and evaluate the fault modes of physical devices using mathematical methods, and the mathematical methods include a knowledge-based neural network method, an expert system method, a fault tree method, a data-driven multivariate statistical analysis method, and a clustering analysis method.

4. The method for constructing a digital twin model of an electronic device according to claim 1, wherein In S301, a data-driven model of the physical equipment is established through 3D design software to map the geometric features of the equipment, and the material should be consistent with that of the physical equipment, and the color, texture, and texture map should be close to the actual appearance of the physical equipment; a data analysis model of the physical equipment is established using simulation software and artificial intelligence algorithms to describe the behavior mechanism of the equipment.

5. The method for constructing a digital twin model of an electronic device according to claim 3, wherein, The construction process of the data-driven model in S301 includes: S400. Interface design: Perform data input / output according to predefined data types and adapt to the software interface for accessing the data analysis model; S401. Data-driven model design: Through a 3D design platform or tool, simplify, lightweight, and texture the existing data-driven model, perform reverse modeling on the equipment data-driven model that cannot be directly obtained, and dynamically update the model according to the twin data; S402. Model Simplification and Lightweighting: Delete geometric features, components, and information that do not affect the requirements of model applications. Perform patch processing on the remaining geometric features to make the data volume of the simplified and lightweighted model small, and try to ensure that the lightweighted model is consistent with the physical equipment in terms of geometry and appearance. S403. Model Physical Properties and Constraint Conditions: Set according to the physical properties of the physical equipment, and set material properties according to different application requirements. The material properties include mechanical, electrical, magnetic, and optical properties. S404. Model Inspection and Modification: Check the model according to the model application requirements and the consistency inspection rules of the geometric features, assembly constraints between the physical equipment and the model, and modify the constituent elements such as geometry, set materials, and assembly constraints that do not meet the requirements according to the results of the model inspection.

6. The method for constructing a digital twin model of an electronic device according to claim 3, characterized in that, The construction process of the data analysis model in S301 includes: S500. Interface Design: Perform data input / output according to predefined data types and adapt to the software interfaces connected to the data analysis model. S501. Data Analysis Model Design: Build a digital model describing the behavior mechanism of the equipment through corresponding simulation software and artificial intelligence algorithms, including multi-disciplinary and multi-physical quantity analysis models such as kinematic models, dynamic analysis models, thermal simulation analysis models, reliability simulation analysis models, static analysis models, electrical performance simulation models, servo control system simulation models, etc. S502. Functional Characteristic Settings: Describe and set the functional attribute characteristics of the model according to the respective characteristics and application requirements of each system of the physical equipment. The functional attributes include stress, strain, communication, and electromagnetic interference. S503. Model Inspection and Modification: Check the model according to the model application requirements and the inspection rules of the consistency of the state attributes and behavior rules between the physical equipment and the model, and modify the state elements that do not meet the requirements.

7. The method for constructing a digital twin model of an electronic device according to claim 5, characterized in that, The interface of S400 should provide functions of data real-time synchronization, data compression, and data quality assessment.

8. The method for constructing a digital twin model of an electronic device according to claim 6, wherein The interface of S500 should provide functions of data real-time synchronization, data compression, and data quality assessment.

9. Application of a digital twin model of an electronic device constructed by using the construction method of the digital twin model of an electronic device described in any one of claims 1 to 3, characterized in that, Including: Collect data using sensors or data from existing data systems, perform visual status monitoring on the physical equipment, and use edge computing and big data analysis during the data collection stage to perform fault detection on the physical equipment, including status monitoring, fault diagnosis, predictive maintenance, and health management.

10. The application of the digital twin model of the electronic equipment according to claim 9, characterized in that, Including: The status monitoring is based on real-time collected data to monitor the operating status of the physical equipment in the digital space and alarm abnormal data or perform corresponding automatic control. The fault diagnosis is to build a fault diagnosis model based on the operating historical data of the physical equipment, monitor key fault parameters in real time, and combine with the equipment operating status characteristics to identify the equipment fault mode. The predictive maintenance is based on real-time operation data, analyzes the damage and degradation mechanisms of key components of physical equipment, and analyzes the internal damage state of key components in real time to achieve predictive maintenance of the equipment. The predictive maintenance includes state trend prediction and remaining life prediction. The state trend prediction can predict the state time series of physical equipment according to monitoring data and historical time series data, and describe the fault generation and transmission process in combination with the fault diagnosis model to predict possible fault modes. The remaining life prediction analyzes the failure causes by real-time monitoring of the damage state data of key components and vulnerable components, and dynamically updates the predictive model. The health management provides a series of maintenance and support measures according to the results of fault diagnosis and predictive maintenance.

Images