A digital twin modeling method and system of super-dimensional dynamic topology
By constructing a multi-dimensional category hyperdimensional dynamic topology and dependency mapping table, the problems of incomplete mapping and high computational resource consumption in existing digital twin modeling methods are solved, realizing real-time adaptive mapping and efficient synchronization between digital twins and physical entities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING EASY TIMES DIGITAL TECH
- Filing Date
- 2026-02-12
- Publication Date
- 2026-07-07
AI Technical Summary
Existing digital twin modeling methods cannot effectively represent high-dimensional features, and the topological structure cannot be adaptively adjusted in real time, resulting in distortion of the virtual-real mapping, high consumption of computing resources, and difficulty in achieving dynamic synchronization between the digital twin and the physical entity.
We construct a hyperdimensional dynamic topology structure with multiple categories, and achieve real-time adaptive adjustment and incremental topology reconstruction of the model by relying on mapping tables and periodically monitoring state data. We also combine parallel topology and incremental synchronization models for dynamic synchronization.
It achieves efficient and real-time mapping of digital twins to physical entities, adapts to structural and functional changes of complex objects, reduces computing resource consumption, and meets the real-time modeling requirements of large-scale complex systems.
Smart Images
Figure CN122345978A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of digital twin modeling technology, and in particular to a digital twin modeling method and system for hyperdimensional dynamic topology. Background Technology
[0002] Existing digital twin modeling methods are mainly limited to three-dimensional geometric space representation, which cannot effectively represent the high-dimensional features of physical entities (including time evolution dimension, state transition dimension, multi-physics coupling dimension, behavioral rule dimension, etc.), resulting in incomplete mapping of digital twins to physical entities.
[0003] Traditional digital twin models have a static and fixed topology. When the structure, function, or operating environment of the physical entity changes dynamically, existing modeling methods cannot achieve real-time adaptive adjustment of the topology, resulting in distortion of the virtual-real mapping and a significant decrease in mapping accuracy over time.
[0004] Existing modeling techniques struggle to fully integrate multi-dimensional information such as geometric, physical, behavioral, and rule elements within the same framework. The lack of effective coupling mechanisms between these elements prevents digital twins from comprehensively reflecting the complex behavior and evolutionary patterns of physical entities.
[0005] Driven by multi-source heterogeneous data (including real-time sensor data, historical operation and maintenance data, environmental parameters, etc.), existing methods are difficult to achieve efficient dynamic synchronization between digital twins and physical entities, resulting in poor real-time performance, high computational resource consumption, and inability to meet the real-time modeling needs of large-scale complex systems. Summary of the Invention
[0006] The purpose of this application is to provide a digital twin modeling method and system for hyperdimensional dynamic topology in order to solve the above-mentioned technical problems. The aim is to efficiently build a digital twin model and provide strong support for the digital management of complex objects throughout their entire lifecycle.
[0007] In some embodiments of this application, by constructing multi-dimensional categories, it is convenient to decompose and integrate complex objects. By constructing a dependency mapping table, the extension logic of each dimension category is built, enabling the model to adapt to changes in object structure or function and possessing good scalability.
[0008] In some embodiments of this application, by periodically monitoring the state data of the modeling object, the changed areas are automatically identified when the physical entity structure changes, the change trend is predicted, and incremental topology reconstruction is performed to achieve real-time adaptive adjustment of the internal topology of the model.
[0009] In some embodiments of this application, a digital twin modeling method for hyperdimensional dynamic topology is provided, including:
[0010] Obtain the initial entity data of the modeling object, and build a model and establish a hyperdimensional topology based on the preset topology and the initial entity data; Obtain the state data of the modeling object, and determine whether to generate a reconstruction instruction for the hyperdimensional topology based on the state data; Establish a superdimensional topological structure element mapping model and dynamic synchronization model, and generate a twin digital model of the modeling object.
[0011] In some embodiments of this application, the preset topology building model includes: Multiple preset dimension categories; Establish a dimensional category sequence , ,in, For the first Each dimension category; The number of dimension categories; According to the dimension category sequence Set in sequence For the target dimension; Establish a target dimension recognition sub-model; Construct recognition sub-models for each dimension category in sequence, and build a data recognition model based on all recognition sub-models; Generate dependency mapping tables for each dimension category, and build an extended evaluation model based on all dependency mapping tables; A topology construction model is established based on the data identification model and the extended evaluation model.
[0012] In some embodiments of this application, the establishment of the hyperdimensional topology includes: Generate the expansion sequence based on the expanded evaluation model and initial entity data; The first dimension to be built is selected based on the expansion order; The first dimension to be built is designated as the target recognition model; Based on the target recognition model and initial entity data, set the substructure parameters of the first dimension to be built of the modeling object; The second dimension to be built is selected based on the expansion order, and the iteration is repeated; Obtain the substructure parameters of the modeling object in each dimension category, and build the hyperdimensional topology of the modeling object based on all substructure parameters.
[0013] In some embodiments of this application, the step of determining whether to generate a reconstruction instruction for a hyperdimensional topology includes: Multiple monitoring time points can be preset; Obtain the status data of the modeling object at the current monitoring time point; Generate the status change data for the current monitoring time point based on the status data. ; ; in, It is a state vector generated based on the state data at the current monitoring time point; It is a state vector generated based on the state data of the previous monitoring time node; Represents the L2 norm; Set state change threshold ; like > At that time, a partial reconstruction instruction is generated at the current monitoring time node.
[0014] In some embodiments of this application, the local reconstruction instructions include: Identify regions of change in hyperdimensional topologies; Based on the topology model and the current time point's state data, set the update structure parameters for the changed region; Generate verification evaluation values for updated structural parameters; Preset verification evaluation value threshold ; If f> Generate update instructions; If f < Generate global refactoring instructions.
[0015] In some embodiments of this application, a dynamic synchronization model for a hyperdimensional topology is established, including: Multiple data partitions are set based on the initial entity data and the preset partition optimization model; Create a data partitioning series , ,in, Let i be the i-th partition; k is the number of data partitions; Based on data partitioning series Construct a dynamic synchronization model; The dynamic synchronization model includes: a parallel topology model and an incremental synchronization model.
[0016] In some embodiments of this application, a digital twin modeling system for hyperdimensional dynamic topology is provided, comprising: The sensing unit is used to acquire the initial entity data of the modeling object; The central control unit includes: The management module is used to build a hyperdimensional topology structure based on the preset topology model and initial entity data; The reconstruction module is used to obtain the state data of the modeling object and determine whether to generate a reconstruction instruction for the hyperdimensional topology based on the state data. The coupling module is used to establish the element mapping model and dynamic synchronization model of the hyperdimensional topology, and generate twin digital models of the modeling objects.
[0017] In some embodiments of this application, the management module is further configured to: Multiple preset dimension categories; Establish a dimensional category sequence , ,in, For the first Each dimension category; The number of dimension categories; According to the dimension category sequence Set in sequence For the target dimension; Establish a target dimension recognition sub-model; Construct recognition sub-models for each dimension category in sequence, and build a data recognition model based on all recognition sub-models; Generate dependency mapping tables for each dimension category, and build an extended evaluation model based on all dependency mapping tables; A topology construction model is established based on the data identification model and the extended evaluation model; The management module is also used to generate an expansion sequence based on the expanded evaluation model and the initial entity data; The first dimension to be built is selected based on the expansion order; The first dimension to be built is designated as the target recognition model; Based on the target recognition model and initial entity data, set the substructure parameters of the first dimension to be built of the modeling object; The second dimension to be built is selected based on the expansion order, and the iteration is repeated; Obtain the substructure parameters of the modeling object in each dimension category, and build the hyperdimensional topology of the modeling object based on all substructure parameters.
[0018] In some embodiments of this application, the reconstruction module is further configured to: Multiple monitoring time points can be preset; Obtain the status data of the modeling object at the current monitoring time point; Generate the status change data for the current monitoring time point based on the status data. ; ; in, It is a state vector generated based on the state data at the current monitoring time point; It is a state vector generated based on the state data of the previous monitoring time node; Represents the L2 norm; Set state change threshold ; like > At that time, a partial reconstruction instruction is generated at the current monitoring time node; The local reconstruction instructions include: Identify regions of change in hyperdimensional topologies; Based on the topology model and the current time point's state data, set the update structure parameters for the changed region; Generate verification evaluation values for updated structural parameters; Preset verification evaluation value threshold ; If f> Generate update instructions; If f < Generate global refactoring instructions.
[0019] In some embodiments of this application, the coupling module is further configured to: Multiple data partitions are set based on the initial entity data and the preset partition optimization model; Create a data partitioning series , ,in, Let i be the i-th partition; k is the number of data partitions; Based on data partitioning series Construct a dynamic synchronization model; The dynamic synchronization model includes: a parallel topology model and an incremental synchronization model.
[0020] Compared with existing technologies, the digital twin modeling method and system for hyperdimensional dynamic topology proposed in this application have the following advantages: By constructing multi-dimensional categories, it is easy to decompose and integrate complex objects. By building dependency mapping tables, the extension logic of each dimension category can be built, enabling the model to adapt to changes in object structure or function and possessing good scalability.
[0021] By periodically monitoring the state data of the modeled object, the system automatically identifies the changed areas when the physical entity structure changes, predicts the change trend, and performs incremental topology reconstruction to achieve real-time adaptive adjustment of the model's internal topology. Attached Figure Description
[0022] Figure 1 This is a flowchart illustrating a preferred embodiment of a digital twin modeling method for hyperdimensional dynamic topology in this application. Detailed Implementation
[0023] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.
[0024] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.
[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0026] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0027] like Figure 1 As shown in the preferred embodiment of this application, a digital twin modeling method for hyperdimensional dynamic topology includes: Obtain the initial entity data of the modeling object, and build a model and establish a hyperdimensional topology based on the preset topology and the initial entity data; Obtain the state data of the modeling object, and determine whether to generate a reconstruction instruction for the hyperdimensional topology based on the state data; Establish a superdimensional topological structure element mapping model and dynamic synchronization model, and generate a twin digital model of the modeling object.
[0028] Specifically, a multi-source data acquisition layer is set up for the modeling object, which is responsible for collecting multi-dimensional data (i.e., initial entity data and state data) from the physical entity (modeling object).
[0029] Specifically, the initial entity data includes, but is not limited to: geometric features extracted from the BIM / CAD model of the physical entity, physical properties (material properties such as density, thermal conductivity, Poisson's ratio, etc., state properties such as temperature, pressure, stress, etc., dynamic properties such as velocity, acceleration, angular velocity, etc.), historical time series data, behavioral rule data, etc.
[0030] Specifically, the preset topology building model includes: Multiple preset dimension categories; Establish a dimensional category sequence , ,in, For the first Each dimension category; The number of dimension categories; According to the dimension category sequence Set in sequence For the target dimension; Establish a target dimension recognition sub-model; Construct recognition sub-models for each dimension category in sequence, and build a data recognition model based on all recognition sub-models; Generate dependency mapping tables for each dimension category, and build an extended evaluation model based on all dependency mapping tables; A topology construction model is established based on the data identification model and the extended evaluation model.
[0031] Specifically, multiple dimensional categories are generated based on historical construction parameters. These dimensional categories include, but are not limited to, various extended dimensions required for building a digital twin model, such as basic geometric topology dimension, physical attribute dimension, time evolution dimension, behavioral rule dimension, and interaction relationship dimension.
[0032] Specifically, the target dimension recognition sub-model is used to filter relevant data of the target dimension in the initial entity data and generate corresponding extended data (for example, if the target dimension is the basic geometric topology dimension, the recognition sub-model can extract geometric features from the initial entity data and generate the number of geometric nodes, the number of geometric edges, and geometric connection parameters required to build the model; if the target dimension is the object attribute dimension, the corresponding recognition sub-model can generate the physical attributes required for each node, such as temperature, pressure, speed, etc. of each node).
[0033] Specifically, the process generates the dependencies between the target dimension and each dimension category. If the target dimension needs to be extended based on the current dimension category, it means that the target dimension has a dependency on the current dimension category (for example, the physical attribute dimension needs to be extended based on the basic geometric topology dimension). The process generates all the dependencies of the target dimension, generates the dependency sub-table of the target dimension based on all the dependencies, and constructs the mapping dependency table based on all the dependency sub-tables.
[0034] Specifically, establishing a hyperdimensional topology includes: Generate the expansion sequence based on the expanded evaluation model and initial entity data; The first dimension to be built is selected based on the expansion order; The first dimension to be built is designated as the target recognition model; Based on the target recognition model and initial entity data, set the substructure parameters of the first dimension to be built of the modeling object; The second dimension to be built is selected based on the expansion order, and the iteration is repeated; Obtain the substructure parameters of the modeling object in each dimension category, and build the hyperdimensional topology of the modeling object based on all substructure parameters.
[0035] Specifically, the extended evaluation model generates extended evaluation values for each dimension category by traversing the initial entity data. The more related data a current dimension category has in the initial entity data and the fewer its own dependencies, the greater its corresponding extended evaluation value.
[0036] Specifically, the larger the expansion evaluation value, the higher the position of the corresponding dimension category in the expansion order. The first dimension category in the expansion order is set as the first dimension to be built (normally the basic geometric topology dimension).
[0037] Specifically, the corresponding substructure parameters (i.e., the corresponding extended data) are generated based on the identification sub-model of the first dimension to be built, and the current substructure parameters are extended sequentially according to the extension order. Finally, the various dimensions are integrated to generate a hyperdimensional topology.
[0038] It is understandable that, in the above embodiments, by constructing multi-dimensional categories, it is convenient to decompose and integrate complex objects. By constructing a dependency mapping table, the extension logic of each dimension category is built, enabling the model to adapt to changes in object structure or function and possessing good scalability.
[0039] In a preferred embodiment of this application, determining whether to generate a reconstruction instruction for a hyperdimensional topology includes: Multiple monitoring time points can be preset; Obtain the status data of the modeling object at the current monitoring time point; Generate the status change data for the current monitoring time point based on the status data. ; ; in, It is a state vector generated based on the state data at the current monitoring time point; It is a state vector generated based on the state data of the previous monitoring time node; Represents the L2 norm; Set state change threshold ; like > At that time, a partial reconstruction instruction is generated at the current monitoring time node.
[0040] Specifically, the time interval between monitoring time nodes can be set according to the structural fluctuation frequency of the modeled object; the higher the fluctuation frequency, the shorter the corresponding time interval.
[0041] Specifically, based on the collected state data of the modeling object (i.e., the current entity data), the corresponding state change quantity is generated.
[0042] Specifically, the threshold for state change ,in, The standard deviation of the historical state. This represents the average of historical states. and These are weighting coefficients, which can be adjusted based on the object being modeled.
[0043] Specifically, local refactoring instructions include: Identify regions of change in hyperdimensional topologies; Based on the topology model and the current time point's state data, set the update structure parameters for the changed region; Generate verification evaluation values for updated structural parameters; Preset verification evaluation value threshold ; If f> Generate update instructions; If f < Generate global refactoring instructions.
[0044] Specifically, the change region is determined based on the gradient recognition method, and the state gradient of each node in the hyperdimensional topology is judged in turn. If it is greater than the gradient threshold, the current node is the node to be updated. The change region is identified based on all the judgment results, which is composed of all the nodes to be updated.
[0045] Specifically, the update structure parameters are set according to the entity data of the current monitoring time node corresponding to the changed area, and the topology consistency of the update structure parameters is checked. A first verification value is set according to the check result. The higher the topology consistency, the higher the corresponding first verification value. The attribute consistency of the update structure parameters is checked, and a second verification value is generated according to the check result. The higher the attribute consistency, the larger the corresponding second verification value. When both the first verification value and the second verification value are within the preset value range, the verification evaluation value is set to 1; otherwise, the verification evaluation value is set to 0.
[0046] Specifically, the value range of the verification evaluation threshold is (0,1), and it is preferably 0.5 in this application.
[0047] It is understood that in the above embodiments, by periodically monitoring the state data of the modeling object, the changed area is automatically identified when the physical entity structure changes, the change trend is predicted, and incremental topology reconstruction is performed to achieve real-time adaptive adjustment of the internal topology structure of the model.
[0048] In a preferred embodiment of this application, establishing a dynamic synchronization model for a hyperdimensional topology includes: Multiple data partitions are set based on the initial entity data and the preset partition optimization model; Create a data partitioning series , ,in, Let i be the i-th partition; k is the number of data partitions; Based on data partitioning series Construct a dynamic synchronization model; Dynamic synchronization models include: parallel topology model and incremental synchronization model.
[0049] Specifically, the partition optimization goal is to ,in The number of edges at the partition boundary. For partition load balancing, the optimal number of data partitions is generated by solving the partition optimization model.
[0050] Specifically, the parallel topology structure adopts the Map-Reduce framework: Map phase: Each partition independently processes local topology updates; Reduce phase: Merges local updates and processes boundary nodes; Parallelism optimization: ,in Where k is the number of CPU cores, and k is the number of partitions. These are the parallel coefficients.
[0051] Specifically, establishing a hyperdimensional topological element mapping model includes: geometric element mapping (establishing geometric mapping functions and evaluating geometric accuracy), physical element mapping (multiphysics coupling modeling and setting physical attribute mapping functions), behavioral element mapping (individual behavior modeling, group behavior modeling, and behavioral rule mapping), rule element mapping (defining rule hierarchy and establishing rule mapping functions), spatiotemporal evolution mapping (establishing spatiotemporal evolution models and spatiotemporal mapping functions), element coupling calculation (defining coupling matrices and calculating coupling strength), and establishing an adaptive weight adjustment mechanism.
[0052] In another preferred embodiment of the digital twin modeling method for hyperdimensional dynamic topology based on any of the above preferred embodiments, a digital twin modeling system for hyperdimensional dynamic topology is provided, comprising: The sensing unit is used to acquire the initial entity data of the modeling object; The central control unit includes: The management module is used to build a hyperdimensional topology structure based on the preset topology model and initial entity data; The reconstruction module is used to obtain the state data of the modeling object and determine whether to generate a reconstruction instruction for the hyperdimensional topology based on the state data. The coupling module is used to establish the element mapping model and dynamic synchronization model of the hyperdimensional topology, and generate twin digital models of the modeling objects.
[0053] In a preferred embodiment of this application, the management module is further configured to: Multiple preset dimension categories; Establish a dimensional category sequence , ,in, For the first Each dimension category; The number of dimension categories; According to the dimension category sequence Set in sequence For the target dimension; Establish a target dimension recognition sub-model; Construct recognition sub-models for each dimension category in sequence, and build a data recognition model based on all recognition sub-models; Generate dependency mapping tables for each dimension category, and build an extended evaluation model based on all dependency mapping tables; A topology construction model is established based on the data identification model and the extended evaluation model; The management module is also used to generate an expansion sequence based on the expanded evaluation model and the initial entity data; The first dimension to be built is selected based on the expansion order; The first dimension to be built is designated as the target recognition model; Based on the target recognition model and initial entity data, set the substructure parameters of the first dimension to be built of the modeling object; The second dimension to be built is selected based on the expansion order, and the iteration is repeated; Obtain the substructure parameters of the modeling object in each dimension category, and build the hyperdimensional topology of the modeling object based on all substructure parameters.
[0054] In a preferred embodiment of this application, the reconstruction module is further configured to: Multiple monitoring time points can be preset; Obtain the status data of the modeling object at the current monitoring time point; Generate the status change data for the current monitoring time point based on the status data. ; ; in, It is a state vector generated based on the state data at the current monitoring time point; It is a state vector generated based on the state data of the previous monitoring time node; Represents the L2 norm; Set state change threshold ; like > At that time, a partial reconstruction instruction is generated at the current monitoring time node; Local refactoring instructions include: Identify regions of change in hyperdimensional topologies; Based on the topology model and the current time point's state data, set the update structure parameters for the changed region; Generate verification evaluation values for updated structural parameters; Preset verification evaluation value threshold ; If f> Generate update instructions; If f < Generate global refactoring instructions.
[0055] In a preferred embodiment of this application, the coupling module is further used for: Multiple data partitions are set based on the initial entity data and the preset partition optimization model; Create a data partitioning series , ,in, Let i be the i-th partition; k is the number of data partitions; Based on data partitioning series Construct a dynamic synchronization model; Dynamic synchronization models include: parallel topology model and incremental synchronization model.
[0056] Based on the first concept of this application, by constructing multi-dimensional categories, it is easy to decompose and integrate complex objects. By constructing a dependency mapping table, the extension logic of each dimension category is built, enabling the model to adapt to changes in object structure or function and possessing good scalability.
[0057] According to the second concept of the application, by periodically monitoring the state data of the modeling object, the changed areas are automatically identified when the physical entity structure changes, the change trend is predicted, and incremental topology reconstruction is performed to achieve real-time adaptive adjustment of the internal topology of the model.
[0058] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.
Claims
1. A digital twin modeling method for hyperdimensional dynamic topology, characterized in that, include: Obtain the initial entity data of the modeling object, and build a model and establish a hyperdimensional topology based on the preset topology and the initial entity data; Obtain the state data of the modeling object, and determine whether to generate a reconstruction instruction for the hyperdimensional topology based on the state data; Establish a superdimensional topological structure element mapping model and dynamic synchronization model, and generate a twin digital model of the modeling object.
2. The digital twin modeling method for hyperdimensional dynamic topology as described in claim 1, characterized in that, The preset topology construction model includes: Multiple preset dimension categories; Establish a dimensional category sequence , ,in, For the first Each dimension category; The number of dimension categories; According to the dimension category sequence Set in sequence For the target dimension; Establish a target dimension recognition sub-model; Construct recognition sub-models for each dimension category in sequence, and build a data recognition model based on all recognition sub-models; Generate dependency mapping tables for each dimension category, and build an extended evaluation model based on all dependency mapping tables; A topology construction model is established based on the data identification model and the extended evaluation model.
3. The digital twin modeling method for hyperdimensional dynamic topology as described in claim 2, characterized in that, The establishment of the hyperdimensional topology includes: Generate the expansion sequence based on the expanded evaluation model and initial entity data; The first dimension to be built is selected based on the expansion order; The first dimension to be built is designated as the target recognition model; Based on the target recognition model and initial entity data, set the substructure parameters of the first dimension to be built of the modeling object; The second dimension to be built is selected based on the expansion order, and the iteration is repeated; Obtain the substructure parameters of the modeling object in each dimension category, and build the hyperdimensional topology of the modeling object based on all substructure parameters.
4. The digital twin modeling method for hyperdimensional dynamic topology as described in claim 3, characterized in that, The determination of whether to generate a reconstruction instruction for a hyperdimensional topology includes: Multiple monitoring time points can be preset; Obtain the status data of the modeling object at the current monitoring time point; Generate the status change data for the current monitoring time point based on the status data. ; ; in, It is a state vector generated based on the state data at the current monitoring time point; It is a state vector generated based on the state data of the previous monitoring time node; Represents the L2 norm; Set state change threshold ; like > At that time, a partial reconstruction instruction is generated at the current monitoring time node.
5. The digital twin modeling method for hyperdimensional dynamic topology as described in claim 4, characterized in that, The local reconstruction instructions include: Identify regions of change in hyperdimensional topologies; Based on the topology model and the current time point's state data, set the update structure parameters for the changed region; Generate verification evaluation values for updated structural parameters; Preset verification evaluation value threshold ; If f> Generate update instructions; If f < Generate global refactoring instructions.
6. The digital twin modeling method for hyperdimensional dynamic topology as described in claim 4, characterized in that, Establish a dynamic synchronization model for a hyperdimensional topology, including: Multiple data partitions are set based on the initial entity data and the preset partition optimization model; Create a data partitioning series , ,in, Let i be the i-th partition; k is the number of data partitions; Based on data partitioning series Construct a dynamic synchronization model; The dynamic synchronization model includes: a parallel topology model and an incremental synchronization model.
7. A digital twin modeling system for hyperdimensional dynamic topology, employing the digital twin modeling method for hyperdimensional dynamic topology as described in any one of claims 1-6, characterized in that, include: The sensing unit is used to acquire the initial entity data of the modeling object; The central control unit includes: The management module is used to build a hyperdimensional topology structure based on the preset topology model and initial entity data; The reconstruction module is used to obtain the state data of the modeling object and determine whether to generate a reconstruction instruction for the hyperdimensional topology based on the state data. The coupling module is used to establish the element mapping model and dynamic synchronization model of the hyperdimensional topology, and generate twin digital models of the modeling objects.
8. The digital twin modeling system for hyperdimensional dynamic topology as described in claim 7, characterized in that, The management module is also used for: Multiple preset dimension categories; Establish a dimensional category sequence , ,in, For the first Each dimension category; The number of dimension categories; According to the dimension category sequence Set in sequence For the target dimension; Establish a target dimension recognition sub-model; Construct recognition sub-models for each dimension category in sequence, and build a data recognition model based on all recognition sub-models; Generate dependency mapping tables for each dimension category, and build an extended evaluation model based on all dependency mapping tables; A topology construction model is established based on the data identification model and the extended evaluation model; The management module is also used to generate an expansion sequence based on the expanded evaluation model and the initial entity data; The first dimension to be built is selected based on the expansion order; The first dimension to be built is designated as the target recognition model; Based on the target recognition model and initial entity data, set the substructure parameters of the first dimension to be built of the modeling object; The second dimension to be built is selected based on the expansion order, and the iteration is repeated; Obtain the substructure parameters of the modeling object in each dimension category, and build the hyperdimensional topology of the modeling object based on all substructure parameters.
9. The digital twin modeling system for hyperdimensional dynamic topology as described in claim 8, characterized in that, The reconstruction module is also used for: Multiple monitoring time points can be preset; Obtain the status data of the modeling object at the current monitoring time point; Generate the status change data for the current monitoring time point based on the status data. ; ； in, It is a state vector generated based on the state data at the current monitoring time point; It is a state vector generated based on the state data of the previous monitoring time node; Represents the L2 norm; Set state change threshold ; like > At that time, a partial reconstruction instruction is generated at the current monitoring time node; The local reconstruction instructions include: Identify regions of change in hyperdimensional topologies; Based on the topology model and the current time point's state data, set the update structure parameters for the changed region; Generate verification evaluation values for updated structural parameters; Preset verification evaluation value threshold ; If f> Generate update instructions; If f < Generate global refactoring instructions.
10. The digital twin modeling system for hyperdimensional dynamic topology as described in claim 9, characterized in that, The coupling module is also used for: Multiple data partitions are set based on the initial entity data and the preset partition optimization model; Create a data partitioning series , ,in, Let i be the i-th partition; k is the number of data partitions; Based on data partitioning series Construct a dynamic synchronization model; The dynamic synchronization model includes: a parallel topology model and an incremental synchronization model.