Digital Twin Model Construction Method, Device and Computer Equipment for Power Equipment

Abstract

The present application provides a method, an apparatus, and a computer device for constructing a digital twin model of a power device. The method includes: determining components included in a target device at a component layer and parts included in the target device at a part layer; classifying the parts in the part layer to obtain a visual-level part list and a simulation calculation-level part list; establishing corresponding first part models for the parts in the visual-level part list according to a first modeling method, and establishing corresponding second part models for the parts in the simulation calculation-level part list according to a second modeling method; connecting the first part models and the second part models into component models corresponding to the respective components according to part connection relationships; and connecting the component models into a device model corresponding to the target device according to component connection relationships. This method enables the modeling of complex power devices, improves the modeling efficiency, and can also improve the applicability of the model in different usage scenarios.

Description

Technical Field

[0001] This application relates to the technical field of power equipment modeling, and particularly to a method, device, computer device, and storage medium for constructing a digital twin model of power equipment. Background Art

[0002] With the gradual development and application of power grid digital technology, the requirements for the visualization of scenarios and the refinement of device simulation modeling are getting higher and higher. By using three-dimensional visualization rendering technology, the model image can be made to approach the real spatial effect, enabling people to roam in the virtual world composed of three-dimensional models, being on the scene and quickly grasping key information. As the foundation of digital visualization software and the key input for finite element simulation calculation, the model plays a crucial role in the initial stage of constructing a digital twin body. In the digital twin models of traditional technologies, there is only a single-precision part model: if all parts are modeled 1:1 in line with the actual scenario, the model size will be huge, thus affecting the efficiency of model rendering and data simulation. Summary of the Invention

[0003] The purpose of this application aims to solve at least one of the above technical defects, especially the technical defect that the large model size in the prior art affects the efficiency of model rendering and data simulation.

[0004] From the above technical solutions, the embodiments of this application have the following advantages:

[0005] In the first aspect, this application provides a method for constructing a digital twin model of power equipment, including:

[0006] Determine the components included in the target device at the component layer and the parts included at the part layer;

[0007] Classify the parts in the part layer to obtain a visualization-level part list and a simulation calculation-level part list;

[0008] Build corresponding first part models for the parts in the visualization-level part list according to the first modeling method, and build corresponding second part models for the parts in the simulation calculation-level part list according to the second modeling method;

[0009] Connect the first part models and the second part models into component models corresponding to each component according to the part connection relationship;

[0010] Connect the component models into a device model corresponding to the target device according to the component connection relationship.

[0011] In one embodiment, parts in the visualization-level part list are used to create corresponding first part models according to a first modeling method, and parts in the simulation calculation-level part list are used to create corresponding second part models according to a second modeling method, including:

[0012] Construct three-dimensional model white models of the first part model and the second part model respectively according to the geometric information of the parts;

[0013] In the three-dimensional model white model of the second part model, elements with a scale smaller than the first size threshold are determined as target elements;

[0014] Simplify the target elements.

[0015] Perform texture rendering on the three-dimensional model white models to obtain the first part model and the second part model.

[0016] In one embodiment, parts in the visualization-level part list are used to create corresponding first part models according to a first modeling method, and parts in the simulation calculation-level part list are used to create corresponding second part models according to a second modeling method, further including:

[0017] Associate the first feature information of the parts with the first part model, and associate the second feature information of the parts with the second part model; wherein, the first feature information is information related to the visualization display of the parts, and the second feature information is feature information related to the simulation calculation of the parts.

[0018] In one embodiment, simplifying the target elements includes:

[0019] If the target element is a line, determine whether there are other lines collinear with the line within a first preset range;

[0020] If so, extend the line to merge it with the other collinear lines;

[0021] If not, remove the line and merge the two endpoints of the line.

[0022] In one embodiment, simplifying the target elements includes:

[0023] If the target element is a plane, determine the shape of the plane;

[0024] If the shape of the plane is a rectangle with an aspect ratio greater than a preset aspect ratio, determine whether there are other planes coplanar with the plane within a second preset range;

[0025] If so, extend the plane to merge it with the other coplanar planes;

[0026] If not, remove the two short sides of the plane and merge the two long sides of the plane;

[0027] If the shape of the plane is a square, then remove the plane and only retain and merge the four endpoints of the plane.

[0028] In one embodiment, after classifying the parts in the part layer to obtain a visual-level part list and a simulation calculation-level part list, it further includes:

[0029] For the parts in the visual-level part list, if the scale of the part is less than the second size threshold, then delete the part from the visual-level part list;

[0030] For the parts in the simulation calculation-level list, if the scale of the part is less than the third size threshold and the part is located in a preset ignored area, then delete the part from the simulation calculation-level list; the third size threshold is less than the second size threshold.

[0031] In one embodiment, the preset ignored area includes an electrostatic shielding area, a mechanical negligible area, and / or a temperature negligible area; wherein, the electrostatic shielding area is the area shielded by static electricity in the target device, the mechanical negligible area is the area where the force received during the operation of the target device is less than the preset force threshold, and the temperature negligible area is the area where the temperature is lower than the temperature threshold during the operation of the device.

[0032] In one embodiment, before classifying the parts in the part layer, it further includes:

[0033] Identify duplicate parts in the parts;

[0034] If there are duplicate parts in the parts and corresponding first part models or second part models have been established for the duplicate parts, then ignore the parts.

[0035] In one embodiment, identifying duplicate parts in the parts includes:

[0036] Obtain the third feature information of the parts;

[0037] Input the third feature information into a classifier to obtain the classification label of the parts;

[0038] If there are parts with the same classification label, then determine that there are duplicate parts in the parts.

[0039] In one embodiment, after connecting the component models into the device model corresponding to the target device according to the component connection relationship, it further includes:

[0040] Establish an association between the corresponding traceability information and the first part model, the second part model, the component module, and the device model.

[0041] In one embodiment, after connecting the component models into the device model corresponding to the target device according to the component connection relationship, it further includes:

[0042] Model and evaluate the device model;

[0043] Repair the device model whose modeling evaluation results do not meet the requirements.

[0044] In one embodiment, the process of modeling and evaluating the device model includes:

[0045] Obtain images of each first part model in the device model from multiple preset perspectives;

[0046] Compare the first part model with the corresponding part image under the same preset perspective according to the preset comparison items to obtain the scores of each preset comparison item;

[0047] According to each score, obtain the modeling evaluation result at the visualization level of the device model.

[0048] In one embodiment, the process of modeling and evaluating the device model includes:

[0049] Sample the marked dimensions in the design drawings of the parts in the simulation calculation level part list to obtain multiple sampled standard dimensions;

[0050] Obtain the sampled model dimensions at the positions marked by each sampled standard dimension in the device model;

[0051] According to the error between each sampled model dimension and the corresponding sampled standard dimension, obtain the modeling evaluation result at the simulation calculation level of the device model.

[0052] In a second aspect, the present application provides a digital twin model construction device for power equipment, including:

[0053] A hierarchical division module for determining the components included in the target device at the component layer and the parts included in the target device at the part layer;

[0054] A classification module for classifying the parts in the part layer to obtain a visualization level part list and a simulation calculation level part list;

[0055] A first modeling module for establishing corresponding first part models for the parts in the visualization level part list according to the first modeling method, and establishing corresponding second part models for the parts in the simulation calculation level part list according to the second modeling method;

[0056] A second modeling module for connecting the first part models and the second part models into component models corresponding to each component according to the part connection relationship;

[0057] A third modeling module for connecting the component models into a device model corresponding to the target device according to the component connection relationship.

[0058] In a third aspect, the present application provides a computer device, including one or more processors and a memory. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the one or more processors, the steps of the method for constructing a digital twin model of a power device in any of the above embodiments are executed.

[0059] In a fourth aspect, the present application provides a storage medium in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute the steps of the method for constructing a digital twin model of a power device in any of the above embodiments.

[0060] For the target device, according to the idea of hierarchical modeling, its model is divided into a part layer, a component layer, and a device layer according to the assembly level. First, determine the component composition and part composition of the target device. Then, classify each part according to the modeling needs, classify the parts only related to visual display into the visual-level part list, and classify the parts also related to simulation calculation into the simulation calculation-level part list. Establish first part models and second part models with different accuracy levels for the parts in these two lists respectively. Then, connect the part models according to the connection relationships between the parts to obtain component models. Finally, based on the connection relationships between the components, integrate the component models into a complete device model. This way of hierarchical modeling reflects the progressive integration idea from local to whole, enables the modeling of complex power devices to be realized, and improves the modeling efficiency. The way of hierarchical modeling of parts is to establish models with different resolutions according to the actual needs of modeling, which not only meets the requirements for fast visual display of some scenarios but also can be used for high-precision numerical simulation of complex multi-physical fields, ensuring both simulation accuracy and improving the rendering speed of the model. Description of the Drawings

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application 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 application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0062] Figure 1 It is a schematic flowchart of the method for constructing a digital twin model of a power device provided by an embodiment of the present application;

[0063] Figure 2 It is a schematic block diagram of the device for constructing a digital twin model of a power device provided by an embodiment of the present application;

[0064] Figure 3Internal structure diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0065] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0066] The present application provides a method for constructing a digital twin model of a power device. Please refer to Figure 1 , which includes steps S102 to S108.

[0067] S102. Determine the components included in the target device at the component layer and the parts included in the target device at the part layer.

[0068] It can be understood that the target device refers to the power device for which a digital twin model needs to be constructed. At present, there is a need for digital modeling of complex power transmission and transformation devices in the power system. Therefore, the power device can be a transformer, a reactor, etc. In the following, the power device will be taken as an example of a transformer for illustration. In this embodiment, the model of the target device is divided into multiple layers according to the assembly level, namely the part layer, the component layer, and the device layer. The part layer is the constituent unit of the component and is the smallest functional monomer in the target device. The component layer is the main functional unit that makes up the device, usually composed of multiple parts combined to achieve a complete function. Of course, some components can also be composed of integrally formed parts. The device layer is the complete model of the target device. In a transformer, the component layer includes windings, iron cores, and leads. In the part layer, the windings include high-voltage, medium-voltage, low-voltage, regulating windings, and coil leads. The iron core includes core columns, upper yokes, lower yokes, side yokes, core tie plates, core tie plates, and spacers. The leads include high-voltage, high-voltage neutral points, medium-voltage, medium-voltage neutral points, low-voltage, and regulating leads. In addition, the part layer also includes connectors, supports, etc. This step analyzes the structure of the target device in combination with various requirements during modeling, will clarify the level and granularity of digital modeling, lay a foundation for subsequent modeling, help manage the complexity of the model, and make the modeling more targeted.

[0069] This step can be that the modeler can understand its constituent structure by collecting design materials such as structure diagrams, assembly diagrams, and part diagrams of the target device. And according to the working principle of the device, analyze the composition of its different functional modules, determine the division of the component layer, and obtain a component list. Further decompose the internal structure of each component in the component list to determine the parts it contains, and obtain a part list. Input the part list and the component list into the computer for storage.

[0070] S104. Classify the parts in the part layer to obtain a visual-level part list and a simulation calculation-level part list.

[0071] It can be understood that during the use of the digital twin model, the part models for visual display and accurate simulation calculation have different levels of detail, resulting in different computing powers required for rendering and simulation. In traditional technologies, parts are only modeled according to a unified level of detail, resulting in low accuracy when the device model composed of visual-level parts is used for simulation calculation, and long rendering time when the device model composed of simulation-level parts is used for visual display. During the research process, it was found that not every part in the part layer is related to accurate simulation calculation. The parts in the part list can be classified into a visual-level part list and a simulation calculation-level part list based on the working principle of the target device, simulation requirements, etc. Among them, the parts included in the visual-level part list are only related to visual display and have little impact on simulation calculation. The parts included in the simulation calculation-level part list are related to both visual display and have a great impact on simulation calculation. Taking a transformer as an example, among the parts corresponding to the winding in the component layer, the high-voltage coil and the medium-voltage coil are of the simulation calculation level, and the low-voltage coil, the regulating coil, and the coil end are of the visual level. Among the parts corresponding to the iron core in the component layer, the core column, the upper yoke, the lower yoke, the side yoke, and the side column are of the accurate calculation level, and the iron core tie plate, the iron core tie plate, and the spacer are of the visual level. Among the parts corresponding to the leads in the component layer, the high-voltage lead, the high-voltage neutral point lead, the medium-voltage lead, and the medium-voltage neutral point lead are of the accurate calculation level, and the low-voltage lead and the regulating lead are of the visual level. In addition, the part layer also includes connecting parts and supporting parts, etc., which are also of the visual level.

[0072] S106. Establish corresponding first part models for the parts in the visual-level part list according to the first modeling method, and establish corresponding second part models for the parts in the simulation calculation-level part list according to the second modeling method.

[0073] It can be understood that the modeling of the parts in the visual-level part list needs to be able to intuitively display the external structure of the target device. In addition to visual display, the simulation calculation model also needs to perform multi-physical field simulations on the operating conditions of the target device, and in order to obtain better simulation accuracy, some display details can be corrected. The simulation calculation can specifically be to input the operating parameters of the target device into the simulation calculation model, and the simulation calculation model can obtain the simulation results of the target device under physical fields such as electric field, magnetic field, temperature, and force according to the operating parameters. Therefore, for the parts in different lists, it is necessary to establish first part models and second part models with different levels of detail respectively.

[0074] S108. Connect the first part model and the second part model into the component models corresponding to each component according to the part connection relationship.

[0075] It can be understood that the part connection relationship refers to the assembly connection between different parts within the same component, including positioning constraints, limit in all directions, assembly dimensions, etc. These connection relationships follow the actual assembly requirements to determine the spatial positions and limiting conditions between parts. The assembly and positioning requirements of each part within the same component can be determined based on the component design drawings of the target device, and its part connection relationship can be analyzed. In the digital modeling software, positioning constraints are added between different part models according to the determined part connection relationship, the assembly positions are adjusted, limiting conditions are applied, etc. to simulate physical assembly. In addition, some parts are independent parts, that is, a single part can be used as a complete component, such as integral connectors, fixing parts, etc. These first part models and second part models can be marked as independent parts during modeling and can be directly upgraded from the part layer to the component layer at step S108 to become the corresponding component models. The composition of the component models will include the first part model and / or the second part model.

[0076] This solution aims at the target device and, with the idea of hierarchical modeling, divides its model into a part layer, a component layer, and a device layer according to the assembly hierarchy. First, the component composition and part composition of the target device are determined. Then, each part is classified according to the modeling needs. The parts related only to visual display are classified into the visual-level part list, and the parts related to simulation calculation are classified into the simulation-calculation-level part list. First part models and second part models with different precision levels are established for the parts in these two lists respectively. Then, according to the connection relationship between the parts, the component models are connected. Finally, based on the connection relationship between the components, the component models are integrated into a complete device model. This way of hierarchical modeling reflects the progressive integration idea from the local to the whole, enables the modeling of complex power equipment, and improves the modeling efficiency. And the way of hierarchical modeling of parts is to establish models with different resolutions according to the actual requirements of modeling, which not only meets the need for rapid visual display of some scenarios but also can be used for high-precision numerical simulation of complex multi-physical fields, ensuring both the simulation accuracy and improving the rendering speed of the model.

[0077] In one of the embodiments, the parts in the visual-level part list are used to establish the corresponding first part models according to the first modeling method, and the parts in the simulation-calculation-level part list are used to establish the corresponding second part models according to the second modeling method, including:

[0078] (1) Three-dimensional model white models of the first part models and the second part models are respectively constructed according to the geometric information of the parts.

[0079] The reference data for constructing the part model is the geometric information of the part. Geometric information can describe spatial information such as the shape and size of the part. Generally speaking, it can be the point cloud data obtained by point cloud scanning of the part. When constructing the first part model and the second part model, although both are based on geometric information, different fidelity and simplification strategies will be adopted to meet the needs of visual display and accurate calculation respectively. The 3D model white model is a 3D model that only contains 3D geometric shape information and no rendering information such as materials and colors. That is, based on the geometric information of the same part, first depict the 3D model white model that reflects the outer contour of the target device. During the construction of the 3D model white model, since the appearance of both levels of models needs to be displayed, the constructed 3D model white models can be the same. Or, according to the computing power of the computer device, the 3D model white models can be selected for differentiation. For example, the 3D model white model corresponding to the first part model is appropriately surface-fitted and simplified while maintaining the main outer contour to reduce the complexity of the 3D surface. The 3D model white model corresponding to the second part model can try to maintain various details of the target device.

[0080] (2) In the 3D model white model of the second part model, determine the elements with a scale smaller than the first size threshold as target elements.

[0081] It can be understood that the scale is used to represent the size of the elements of the 3D model. The scale of the surface element can be represented by the side length of its smallest side. The scale of the line element can be directly represented by its side length. During the generation of the 3D model white model, there may be some elements with relatively small scales that will affect the finite element simulation analysis. These elements need to be simplified to eliminate the impact on the simulation accuracy. Therefore, before rendering, traverse and check the elements (lines and planes) in the 3D model white model according to the first size threshold, and determine the elements with a scale smaller than the first size threshold as the elements that need to be simplified. The first size threshold here can generally be set to 0.1 mm.

[0082] (3) Simplify the target elements.

[0083] After determining the target elements, corresponding simplification means can be adopted for processing according to the type, shape, etc. of the target elements.

[0084] (4) Perform texture rendering on the 3D model white model to obtain the first part model and the second part model.

[0085] It can be understood that after the construction of the 3D model white model is completed, materials, colors, etc. can be added to the surface of the 3D model white model to achieve the rendering of the 3D model white model. The texture data used for rendering can be selected and generated in the rendering software according to the materials of the target device.

[0086] In one embodiment, parts in the visualization-level part list are used to create corresponding first part models according to a first modeling method, and parts in the simulation calculation-level part list are used to create corresponding second part models according to a second modeling method. It further includes: associating the first feature information of the part with the first part model and associating the second feature information of the part with the second part model. Among them, the first feature information is information related to the visualization display of the part, and the second feature information is feature information related to the simulation calculation of the part.

[0087] It can be understood that establishing the association here means adding one-to-one corresponding information to the part model and storing it. After the first part model and the second part model are established, it is also necessary to add corresponding feature information to the models to meet the corresponding usage requirements. That is, the geometric information only describes the shape information of the part, and relying solely on geometric features is not sufficient to support the different uses of the model. Adding various types of feature information can enrich the semantic description of the model, enabling the model to support different functional applications. Therefore, it is necessary to add feature information specifically for the visualization-level model and the simulation calculation-level model. Specifically, the first feature information may include geometric information and material properties. The second feature information includes geometric information, spatial relationship, material properties, number of models, operating conditions, precise calculation drawings, test plans, insulation criteria, etc. Since the main purpose of the visualization model is to display the external shape and structural information of the product, its feature information only needs to include geometric information and material properties related to the appearance for real-scene rendering display. While the simulation calculation model needs to perform precise numerical analysis, so its feature information needs to be as complete and detailed as possible, including geometric information, spatial relationship, material properties, number of models, operating conditions, precise calculation drawings, test plans, insulation criteria, etc., all of which are important information affecting the simulation calculation. In some embodiments, the naming method for storing feature information can adopt a specific coding method. For example, X-Y.Y.Y-A-N, where X is the first letter of the English name of the part, Y is the first letter of the English name of the part connected to it, A is the first letter of the English name of the material of the part, and N is the number of the part model under the same type of model.

[0088] In one embodiment, simplifying the target element includes:

[0089] (1) If the target element is a line, determine whether there are other lines collinear with the line within a first preset range.

[0090] It can be understood that the first preset range is a search range set for determining whether there are collinear lines centered on the target element. This step is for the lines in the 3D model that need to be simplified. If there are other collinear lines near this line, it means that this line may be part of other lines, but is disconnected due to an error during rendering. Therefore, if other collinear lines can be found within the first preset range, the line is directly extended to merge it with the other collinear lines into a complete line. Otherwise, it means that this line is a redundant line and can be directly removed. The two endpoints left after the line is removed can be merged into one endpoint to prevent point loss.

[0091] (2) If so, extend the line to merge it with the other collinear lines.

[0092] (3) If not, remove the line and merge the two endpoints of the line.

[0093] In one embodiment, simplifying the target element includes:

[0094] (1) If the target element is a plane, determine the shape of the plane.

[0095] It can be understood that for plane elements, different shapes have different simplification strategies. Therefore, it is necessary to first determine the specific shape of the plane.

[0096] (2) If the shape of the plane is a rectangle with an aspect ratio greater than the preset aspect ratio, determine whether there are other planes coplanar with the plane within the second preset range.

[0097] It can be understood that a rectangle with an aspect ratio greater than the preset aspect ratio is a narrow small plane, and a narrow small plane means that this plane may be part of other planes, but is disconnected due to an error during rendering, or a redundant plane is formed after the lines are wrongly copied. Therefore, if other coplanar planes can be found within the second preset range, the plane is directly extended to merge it with the other coplanar planes into a complete plane. Otherwise, it means that this line is a redundant plane, the two short sides are removed, and the two long sides of the plane are merged.

[0098] (3) If so, extend the plane to merge it with the other coplanar planes.

[0099] (4) If not, remove the two short sides of the plane and merge the two long sides of the plane.

[0100] (5) If the shape of the plane is a square, remove the plane and only retain and merge the four endpoints of the plane.

[0101] It can be understood that the influence of the small face of the square on the simulation calculation can be ignored. For the sake of simplifying the modeling, it can be directly removed, and only the four endpoints of the plane are retained and merged.

[0102] In one embodiment, in order to simplify the modeling process and improve the modeling efficiency, some parts with less influence in the part layer can be ignored. After classifying the parts in the part layer to obtain the visual-level part list and the simulation calculation-level part list, it further includes:

[0103] (1) For the parts in the visual-level part list, if the scale of the part is less than the second size threshold, the part is deleted from the visual-level part list.

[0104] It can be understood that the first part model is a visual-level model. During the visualization process, parts with too small scales generally do not need to be concerned when being displayed, and simplifying them will not affect the display effect. Therefore, during the process of traversing and modeling the parts in the part layer, if it is found that the traversed part is smaller than the second size threshold, then this part does not need to be modeled. Generally speaking, the second size threshold can be set to 10 mm. By specifying the second size threshold, it can be automatically determined which parts with smaller sizes can be excluded from modeling, thereby simplifying the construction process of the visual model and improving the modeling efficiency of the visual model.

[0105] (2) For the parts in the simulation calculation-level list, if the scale of the part is less than the third size threshold and the part is located in the preset ignored area, the part is deleted from the simulation calculation-level list. The third size threshold is smaller than the second size threshold.

[0106] It can be understood that the second part model is a model at the precise simulation calculation level. In the simulation calculation, in addition to being small enough in scale, it is also necessary to ensure that the part is within a preset ignored area that has no impact on the finite element simulation calculation before the part can be not modeled. The preset ignorable area is related to the physical fields that need to be simulated according to the simulation calculation level model. Taking a transformer as an example, its working process involves multiple physical fields such as electric field, magnetic field, temperature, and mechanics. Then, the area that does not affect the distribution of the above physical fields can be set as the ignorable area. Specifically, the preset ignored area includes an electrostatic shielding area, a mechanical ignorable area, and / or a temperature ignorable area. Among them, the electrostatic shielding area is the area shielded by electrostatic shielding in the target device. Under the action of electrostatic shielding, the parts within the electrostatic shielding area have no impact on the electric field distribution, the insulation state of the device, etc., so they can be ignored. The mechanical ignorable area is the area where the force on the target device during operation is less than the preset force threshold. The area where the force is less than the preset force threshold will not produce stress concentration, or even if stress concentration occurs, there is still a large gap from the limit value of material damage. Therefore, simplifying the details will not affect the mechanical performance verification of the device. The temperature ignorable area is the area where the temperature of the device during operation is lower than the temperature threshold. The temperature in the temperature ignorable area is relatively low and has little impact on the temperature distribution. Simplifying it will not affect the verification calculation of the temperature field distribution of the device.

[0107] In one of the embodiments, for the parts in the part layer, before classifying the parts in the part layer, it further includes:

[0108] (1) Identify the duplicate parts in the parts.

[0109] It can be understood that duplicate parts refer to parts that are exactly the same as the current part.

[0110] (2) If there are duplicate parts in the parts and the corresponding first part model or second part model has been established for the duplicate parts, then ignore the parts.

[0111] That is, during the process of establishing the part model, there is a possibility of duplicate modeling for duplicate parts. First, check whether the part is duplicate with the historical parts. If so, further check whether the corresponding visualization and calculation models have been established for the duplicate parts. If they exist, there is no need to establish duplicate models. Directly reuse the established first part model and second part model. Skipping the modeling can avoid duplicate work and greatly improve efficiency.

[0112] In one of the embodiments, identifying the duplicate parts in the parts includes:

[0113] (1) Obtain the third feature information of the parts.

[0114] It can be understood that the third feature information is the feature information used for part classification and recognition, which may include images of multiple perspectives of the part, numbers and models during part procurement, etc.

[0115] (2) Input the third feature information into a classifier to obtain the classification label of the part.

[0116] It can be understood that a classifier is a machine learning model that maps feature information to class outputs.

[0117] (3) If there are parts with the same classification label, it is determined that there are duplicate parts. For the case where the third feature information includes images, the model can be based on a convolutional neural network. The entire network architecture consists of several convolutional layers, pooling layers, and fully connected layers. The input image passes through multiple convolutional layers and pooling layers and then outputs the final result through the fully connected layer. The multiple convolutional layers and pooling layers can extract the deep abstract features of the image layer by layer. Finally, all the abstract features are combined through the fully connected layer for calculation, establishing a complex non-linear mapping relationship between the abstract features and the target output to achieve the classification function. For numbers during part procurement, etc., the corresponding relationship can be directly established using semantics, which will not be elaborated here.

[0118] In one embodiment, after connecting the component models into the device model corresponding to the target device according to the component connection relationship, it further includes: associating the corresponding traceability information with the first part model, the second part model, the component module, and the device model.

[0119] It can be understood that the traceability information of a product reflects various historical data of the entire life cycle of the product from design, manufacturing to use. The traceability information is very important for ensuring product quality and process control. Digitalizing the traceability information of the target device and associating it with the first device model and the second device model can achieve the persistent storage and effective utilization of the traceability information. The traceability information may include digital two-dimensional codes, processing technologies, material sources, production batches, responsible persons, etc. Since the production of a device is carried out in units of parts, establishing the connection with the first device model and the second device model here also requires establishing an association between the traceability information and each part model. Injecting the traceability information after the device model is established is because there are some omissions and defaults of some components during the modeling process, and performing it after the final device layer modeling is completed can reduce the workload of traceability information statistics.

[0120] In one embodiment, after connecting the component models into the device model corresponding to the target device according to the component connection relationship, it further includes:

[0121] (1) Perform modeling evaluation on the device model.

[0122] It can be understood that the first device model and the second device model that have been constructed need to be specifically evaluated to determine whether the established models meet the usage requirements. For these two models with different precision levels, different evaluation methods can be used.

[0123] (2) Repair the device model whose modeling evaluation result does not meet the requirements.

[0124] According to the evaluation feedback, if it is found that there are problems with the model not meeting the requirements, then targeted model repair is required. The repair means can include model reconstruction, parameter adjustment, supplementary information, etc. The goal of the repair is to eliminate the problems found in the evaluation and meet the quality requirements of the model.

[0125] In one embodiment, the process of modeling evaluation of the device model includes:

[0126] (1) Obtain the images of each first part model in the device model from multiple preset perspectives.

[0127] It can be understood that for the visualization-level model, the quality of its model is determined by the visual correlation with the target device. By setting multiple perspectives to cover the main parts of the parts, taking pictures of the parts and the real-scene pictures respectively from the same preset perspectives and taking screenshots of the first part models, an image dataset for comparison is constructed.

[0128] (2) Compare the first part model with the images of the corresponding part from the same preset perspective according to the preset comparison items to obtain the scores of each preset comparison item.

[0129] It can be understood that the preset comparison items refer to the items that need to be compared between the screenshots of the visualization model and the corresponding real-scene pictures. In addition to the conventional visual similarity, inspection items such as perspective correctness, component interference relationship, integrity, etc. can also be added according to needs. For each preset comparison item, a quantitative index can be obtained to reflect the performance of the first part model in this item. Finally, by synthesizing the scores of each preset comparison item, the modeling evaluation result of the visualization-level model can be obtained.

[0130] (3) Obtain the modeling evaluation result of the visualization level of the device model according to each score.

[0131] In one embodiment, the process of modeling evaluation of the device model includes:

[0132] (1) Sample the marked dimensions in the design drawings of the parts in the simulation calculation-level part list to obtain multiple sampled standard dimensions.

[0133] The sampling standard dimensions refer to the partial standard dimensions selected according to the sampling method from the dimensions marked on the design drawings of each part of the target device. Latin hypercube sampling can be used for sampling.

[0134] (2) Obtain the sampling model dimensions at the positions marked by each sampling standard dimension in the device model.

[0135] It can be understood that in order to compare whether the dimensions on the device model are consistent with the dimensions required on the actual drawings, it is necessary to calculate the dimensions of these positions in the model at the corresponding positions in the device model to form data pairs with the standard dimensions.

[0136] (3) Obtain the modeling evaluation results at the simulation calculation level of the device model according to the errors between each sampling model dimension and the corresponding sampling standard dimension.

[0137] Finally, the geometric accuracy of the model can be judged according to the errors by calculating the errors of each pair of data and then analyzing the error distribution. The calculation of errors can be carried out in the form of residuals.

[0138] This application provides a digital twin model construction device for power equipment. Please refer to Figure 2 , including:

[0139] The hierarchical division module 210 is used to determine the components included in the target device at the component layer and the parts included in the target device at the part layer.

[0140] The classification module 220 is used to classify the parts in the part layer to obtain a visual-level part list and a simulation calculation-level part list.

[0141] The first modeling module 230 is used to establish corresponding first part models for the parts in the visual-level part list according to the first modeling method, and establish corresponding second part models for the parts in the simulation calculation-level part list according to the second modeling method.

[0142] The second modeling module 240 is used to connect the first part model and the second part model into component models corresponding to each component according to the part connection relationship.

[0143] The third modeling module 250 is used to connect the component models into a device model corresponding to the target device according to the component connection relationship.

[0144] For the specific limitations of the digital twin model construction device for power equipment, reference can be made to the limitations of the digital twin model construction method for power equipment in the foregoing text. Each module in the above digital twin model construction device for power equipment can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules. It should be noted that the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0145] The present application provides a computer device, including one or more processors and a memory. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the one or more processors, the steps of the digital twin model construction method for power equipment in any of the above embodiments are executed.

[0146] Schematically, as Figure 3 shown, Figure 3 is a schematic internal structure diagram of a computer device provided by an embodiment of the present application. Referring to Figure 3 , the computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by a memory 301 for storing instructions executable by the processing component 302, such as application programs. The application programs stored in the memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the steps of the digital twin model construction method for power equipment in any of the above embodiments.

[0147] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305.

[0148] Those skilled in the art can understand that Figure 3 the structure shown in

[0149] The present application provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to execute the steps of the method for constructing a digital twin model of a power device in any of the above embodiments.

[0150] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0151] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing a digital twin model of a power device, characterized in that Including: Determine the components included in the target device at the component layer and the parts included in the target device at the part layer; Classify the parts in the part layer according to the working principle and simulation requirements of the target device to obtain a visual-level part list and a simulation calculation-level part list; The modeling of the parts in the visual-level part list is used to display the external structure of the target device, and the modeling of the parts in the simulation calculation-level part list is used to display the external structure of the target device and perform multi-physics field simulation on the operating conditions of the target device; Establish corresponding first part models for the parts in the visual-level part list according to the first modeling method, and establish corresponding second part models for the parts in the simulation calculation-level part list according to the second modeling method; Connect the first part model and the second part model into a component model corresponding to each component according to the part connection relationship; Connect the component models into a device model corresponding to the target device according to the component connection relationship.

2. The method for constructing a digital twin model of an electrical device according to claim 1, wherein The step of establishing corresponding first part models for the parts in the visual-level part list according to the first modeling method and establishing corresponding second part models for the parts in the simulation calculation-level part list according to the second modeling method includes: Construct three-dimensional model white models of the first part model and the second part model respectively according to the geometric information of the parts; In the three-dimensional model white model of the second part model, determine the elements with a scale smaller than the first size threshold as target elements; Simplify the target elements; Perform texture rendering on the three-dimensional model white model to obtain the first part model and the second part model.

3. The method for constructing a digital twin model of a power device according to claim 2, wherein, The step of establishing corresponding first part models for the parts in the visual-level part list according to the first modeling method and establishing corresponding second part models for the parts in the simulation calculation-level part list according to the second modeling method further includes: Associate the first feature information of the part with the first part model, and associate the second feature information of the part with the second part model; wherein, the first feature information is information related to visual display of the part, and the second feature information is feature information related to simulation calculation of the part.

4. The method for constructing a digital twin model of a power device according to claim 2, wherein The step of simplifying the target elements includes: If the target element is a line, determine whether there are other lines collinear with the line within the first preset range; If so, extend the line to merge with other collinear lines; If not, remove the line and merge the two endpoints of the line.

5. The method for constructing a digital twin model of a power device according to claim 2, wherein The step of simplifying the target elements includes: If the target element is a plane, determine the shape of the plane; If the shape of the plane is a rectangle with an aspect ratio greater than the preset aspect ratio, determine whether there are other planes coplanar with the plane within the second preset range; If so, extend the plane to merge with other coplanar planes; If not, remove the two short sides of the plane and merge the two long sides of the plane. If the shape of the plane is square, then remove the plane and only retain and merge the four endpoints of the plane.

6. The method for constructing a digital twin model of a power device according to claim 1, characterized in that After classifying the parts in the part layer to obtain a visual-level part list and a simulation calculation-level part list, it further includes: For the parts in the visual-level part list, if the scale of the part is smaller than the second size threshold, then delete the part from the visual-level part list; For the parts in the simulation calculation-level list, if the scale of the part is smaller than the third size threshold and the part is located in a preset ignored area, then delete the part from the simulation calculation-level list; the third size threshold is smaller than the second size threshold.

7. The method for constructing a digital twin model of a power device according to claim 6, wherein The preset ignored area includes an electrostatic shielding area, a mechanically negligible area, and / or a temperature negligible area; wherein, the electrostatic shielding area is the area shielded by static electricity in the target device, the mechanically negligible area is the area where the force received by the target device during operation is less than the preset force threshold, and the temperature negligible area is the area where the temperature of the device is lower than the temperature threshold during operation.

8. The method for constructing a digital twin model of a power device according to claim 1, wherein Before classifying the parts in the part layer, it further includes: Identifying duplicate parts in the parts; If there are duplicate parts in the part and the corresponding first part model or second part model has been established for the duplicate parts, then ignore the part.

9. The method for constructing a digital twin model of a power device according to claim 8, wherein The identifying duplicate parts in the parts includes: Obtaining the third feature information of the parts; Inputting the third feature information into a classifier to obtain the classification label of the parts; If there are parts with the same classification label, then determine that there are duplicate parts in the parts.

10. The method for constructing a digital twin model of a power device according to claim 1, wherein, After connecting the component models into the device model corresponding to the target device according to the component connection relationship, it further includes: Establishing an association between the corresponding traceability information and the first part model, the second part model, the component model, and the device model.

11. The method for constructing a digital twin model of a power device according to claim 1, wherein After connecting the component models into the device model corresponding to the target device according to the component connection relationship, it further includes: Performing a modeling evaluation on the device model; Repairing the device model whose modeling evaluation result does not meet the requirements.

12. The method for constructing a digital twin model of a power device according to claim 11, characterized in that The process of performing a modeling evaluation on the device model includes: Obtaining images of each of the first part models in the device model from multiple preset perspectives; Comparing the first part model with the image of the corresponding part from the same preset perspective according to preset comparison items to obtain the scores of each of the preset comparison items; Obtaining the modeling evaluation result at the visual level of the device model according to each of the scores.

13. The method for constructing a digital twin model of the power equipment according to claim 11, characterized in that, The process of performing a modeling evaluation on the device model includes: Sampling the marked dimensions in the design drawings of the parts in the simulation calculation-level part list to obtain multiple sampled standard dimensions; Obtaining the sampled model dimensions at the positions marked by each of the sampled standard dimensions in the device model; Obtaining the modeling evaluation result at the simulation calculation level of the device model according to the error between each of the sampled model dimensions and the corresponding sampled standard dimension.

14. A digital twin model construction device for a power equipment, characterized in that, Includes: A hierarchical division module, configured to determine the components included in the target device at the component layer and the parts included in the target device at the part layer; A classification module, configured to classify the parts in the part layer according to the working principle and simulation requirements of the target device, so as to obtain a visual-level part list and a simulation calculation-level part list; The modeling of the parts in the visual-level part list is used to display the external structure of the target device, and the modeling of the parts in the simulation calculation-level part list is used to display the external structure of the target device and perform multi-physical field simulation on the operating conditions of the target device; A first modeling module, configured to establish corresponding first part models for the parts in the visual-level part list according to a first modeling method, and establish corresponding second part models for the parts in the simulation calculation-level part list according to a second modeling method; A second modeling module, configured to connect the first part models and the second part models into component models corresponding to the respective components according to the part connection relationship; A third modeling module, configured to connect the component models into a device model corresponding to the target device according to the component connection relationship.

15. A computer device, characterized in that, It includes one or more processors and a memory. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the one or more processors, the steps of the method for constructing a digital twin model of the power device according to any one of claims 1-13 are executed.

16. A storage medium, characterized in that, Computer-readable instructions are stored in the storage medium. When the computer-readable instructions are executed by one or more processors, one or more processors are caused to execute the steps of the method for constructing a digital twin model of the power device according to any one of claims 1-13.

Images