Multi-domain digital twin integration method and electronic device based on cognitive clues

Abstract

The present invention provides a multi-domain digital twin integration method and electronic device based on cognitive clues, the method comprising: extracting digital twin model information of each field of equipment; determining the description specification of the cognitive ability of the multi-domain digital twin; establishing a unified knowledge expression model capable of expressing the cognitive information of the digital twin based on the description specification of the cognitive ability of the multi-domain digital twin; instantiating the unified knowledge expression model; generating a unified resource identifier for the data information of digital twins in different fields, integrating the data of the whole life cycle involved in heterogeneous digital twins, and forming cognitive clues based on the instantiation description in the unified knowledge expression model to realize the integration of multi-domain digital twins. The present invention effectively solves the technical problem that it is difficult to effectively integrate multi-domain digital twins of complex equipment in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of multi-domain digital twin integration technology for complex equipment, and in particular to the field of multi-domain digital twin integration technology based on cognitive clues. Background Art

[0002] Nowadays, as complex equipment develops in the direction of multi-disciplinary and multi-field, it involves multiple fields such as mechanics, electronics, hydraulics, and control. In design and development, models in various fields of complex equipment are often modeled using different simulation tools. Their digital twin models have problems such as high complexity, large number, difficult management, and poor integration capabilities. Each twin is independent of each other and contains a large amount of heterogeneous model data. The heterogeneous digital twins in various fields lack effective integration and management methods throughout the entire operation cycle of the equipment, making it difficult to achieve joint simulation and integration of system-level models of complex equipment.

[0003] At present, the integration of multi-domain digital twins adopts the interface-based or high-level architecture (HLA)-based methods. The former is realized through the open interfaces between commercial simulation software in different fields. However, when the number of commercial simulation software increases, the maximum number of interfaces required in theory will become very large, and the complexity will increase accordingly. The latter is to develop HLA interfaces of various commercial simulation software based on the HLA framework, and to interact with data through the bus of the run-time support system (RTI). However, it requires modelers to be familiar with various services of HLA / RTI, and it is necessary to artificially separate the coupling relationship between subsystems in different fields. The digital twins in each field of the above two methods lack cognitive ability, cannot effectively describe the iterative information of the digital twin model and the relationship between models, and it is difficult to achieve effective integration of multi-domain digital twins of complex equipment. Summary of the invention

[0004] In view of the shortcomings of the prior art mentioned above, the object of the present invention is to provide a multi-domain digital twin integration method and electronic device based on cognitive clues, to achieve the integration of heterogeneous data information of twins in various fields, and to support the joint simulation and integration of multi-domain digital twins of complex systems.

[0005] To achieve the above-mentioned objectives and other related objectives, the present invention provides a multi-domain digital twin integration method based on cognitive clues, the method comprising: extracting digital twin model information of equipment in various fields; determining the description specifications of the cognitive capabilities of multi-domain digital twins; establishing a unified knowledge expression model that can express the cognitive information of digital twins based on the description specifications of the cognitive capabilities of multi-domain digital twins; instantiating the unified knowledge expression model; generating a unified resource identifier for the data information of digital twins in different fields, integrating the data of the entire life cycle involved in heterogeneous digital twins, and forming cognitive clues based on the instantiated descriptions in the unified knowledge expression model to achieve the integration of multi-domain digital twins.

[0006] In one embodiment of the present invention, the extraction of digital twin model information of equipment in various fields includes: determining the cross-domain correlation relationship, intra-domain correlation relationship, model attributes and parameter information of each digital twin; based on the composition of multi-domain digital twins, according to the system division of different fields, determining the cross-domain hierarchical relationship between each heterogeneous data twin; analyzing the attributes of each digital twin, and determining the model structure and data relationship of the twin in each field; extracting the digital twin model information of equipment in various fields based on the cross-domain correlation relationship, intra-domain correlation relationship, model attributes and parameter information of each digital twin, the cross-domain hierarchical relationship between each heterogeneous data twin, and the model structure and data relationship of the twin in each field.

[0007] In one embodiment of the present invention, the description specifications for determining the cognitive capabilities of multi-domain digital twins include: determining a digital twin cognitive capability description architecture based on a meta-metamodel system; based on the digital twin cognitive capability description architecture, determining the information elements at each level within the architecture and the corresponding description specifications.

[0008] In one embodiment of the present invention, the information elements at each level in the architecture include: meta-metamodel, meta-model, model, association rules between meta-metamodels, connection relationships between models, system properties of meta-model, system properties of model and custom properties.

[0009] In one embodiment of the present invention, the meta-metamodel layer is described by the classes of the first level in the architecture, the metamodel layer is described by the subclasses of the first level, and the model layer is described by the entities after the classes are instantiated.

[0010] In one embodiment of the present invention, the establishment of a unified knowledge expression model capable of expressing the cognitive information of digital twins based on the description specifications of the cognitive capabilities of the multi-domain digital twins includes: constructing the classes required for the meta-meta model based on the digital twin cognitive capability description architecture; establishing subclasses of digital twins in each field based on the extracted digital twin model information in each field and the classes required by the meta-meta model; defining corresponding object attributes and data attributes in each class and subclass, and establishing a unified knowledge expression model for describing the cognitive information of digital twins.

[0011] In one embodiment of the present invention, the classes include graphs, objects, nodes, attributes, roles, and relationships.

[0012] In one embodiment of the present invention, the instantiation of the unified knowledge expression model includes: constructing a multi-domain digital twin entity in the ontology model by instantiating the classes in the ontology model; and establishing an association relationship between the multi-domain digital twin entities based on the corresponding object attributes defined by each class and subclass.

[0013] In one embodiment of the present invention, a unified resource identifier is generated for the data information of digital twins in different fields, the data of the entire life cycle involved in heterogeneous digital twins are integrated, and cognitive clues are formed based on the instantiated description in the unified knowledge expression model to achieve the integration of multi-domain digital twins, including: using an open full life cycle service architecture to generate a unified resource identifier for the data information in multi-domain digital twins, and accessing the data information of multi-domain digital twins through the unified resource identifier; filling the generated unified resource identifier into the model as a data attribute in the cognitive ontology model, so that the cognitive ontology model has the ability to access the digital twin information in each field, form cognitive clues, and achieve the integration of multi-domain digital twins.

[0014] To achieve the above-mentioned purpose and other related purposes, the present invention also provides an electronic device, including a memory for storing a computer program; and a processor for running the computer program to implement the steps of the multi-domain digital twin integration method based on cognitive clues as described above.

[0015] As described above, the multi-domain digital twin integration method and electronic device based on cognitive clues of the present invention have the following beneficial effects:

[0016] 1. The present invention applies the conceptual theory of ontology and builds a cognitive ontology model with high scalability to characterize the multi-domain digital twin framework through a modeling method based on the meta-meta model. It serves the data in the multi-domain digital twin based on the data bonding technology, generates a unified identifier that can access the digital twin data resources, and assigns it to the data attributes in the ontology model, so that the ontology model can access multi-domain data on the basis of describing the multi-domain digital twin framework, thereby constructing cognitive clues, giving the digital twin cognitive ability, and realizing the integration of multi-domain digital twins, effectively solving the technical problem that the existing technology is difficult to effectively integrate multi-domain digital twins of complex equipment.

[0017] 2. Compared with other methods, the present invention can use cognitive clue technology for complex multi-domain digital twins to form a model integration framework with high openness and scalability, and support heterogeneous data interaction between different fields, thereby achieving high integration of multi-domain digital twins. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 Shown is a schematic diagram of the overall process of a multi-domain digital twin integration method based on cognitive clues in an embodiment of the present application;

[0020] Figure 2 Shown is a cognitive clue architecture diagram of a multi-domain digital twin integration method based on cognitive clues in one embodiment of the present application;

[0021] Figure 3 Shown is a multi-domain digital twin concept class extracted from a multi-domain digital twin integration method based on cognitive clues in an embodiment of the present application;

[0022] Figure 4 Displayed are the multi-domain digital twin object attributes extracted from the multi-domain digital twin integration method based on cognitive clues in one embodiment of the present application;

[0023] Figure 5 Displayed are multi-domain digital twin data attributes extracted by a multi-domain digital twin integration method based on cognitive clues in an embodiment of the present application;

[0024] Figure 6 Shown is a principle block diagram of an electronic device in an embodiment of the present application.

[0025] Component number description

[0026] 101 Electronic Equipment

[0027] 1001 Processor

[0028] 1002 Memory

[0029] S100~S500 Steps DETAILED DESCRIPTION

[0030] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0031] The existing multi-domain digital twin integration mainly adopts interface-based and high-level architecture-based modeling methods. The former will cause the number of interfaces to become very large and the complexity will increase accordingly when the number of simulation software increases. The latter requires artificial severing of the coupling relationship between subsystems in different fields. Both of them make it difficult to achieve effective digital twin management and integration of the entire system throughout the life cycle.

[0032] The purpose of this embodiment is to provide a multi-domain digital twin integration method and electronic device based on cognitive clues, to achieve the integration of heterogeneous data information of twins in various fields, to support the joint simulation and integration of multi-domain digital twins of complex systems, and to solve the problem that it is difficult for existing technologies to effectively integrate multi-domain digital twins of complex equipment.

[0033] The principles and implementation methods of the multi-domain digital twin integration method and electronic device based on cognitive clues of the present invention will be explained in detail below, so that those skilled in the art can understand the multi-domain digital twin integration method and electronic device based on cognitive clues of the present invention without creative work.

[0034] Example 1

[0035] This embodiment provides a multi-domain digital twin integration method based on cognitive clues. To address the problem that the existing multi-domain digital twins of complex equipment lack cognitive capabilities and are difficult to effectively organize, manage and integrate throughout their life cycle, a structured and regularized ontology model is used to describe the iterative information of the digital twins of complex equipment and the topological structure of the relationship between the digital twins. Cognitive clues are constructed to give the digital twins cognitive capabilities, and the integration of heterogeneous data information of twins in various fields is achieved based on the data bonding method, supporting the joint simulation and integration of multi-domain digital twins of complex systems.

[0036] Specifically, Figure 1 As shown, the multi-domain digital twin integration method based on cognitive clues described in this embodiment includes:

[0037] Step S100, extracting digital twin model information of each field of equipment;

[0038] Step S200, determining the description specification of the cognitive capabilities of multi-domain digital twins;

[0039] Step S300, establishing a unified knowledge expression model capable of expressing digital twin cognitive information based on the description specification of the multi-domain digital twin cognitive capabilities;

[0040] Step S400, instantiating the unified knowledge expression model;

[0041] Step S500, generates a unified resource identifier for the data information of digital twins in different fields, integrates the data of the entire life cycle involved in heterogeneous digital twins, and forms cognitive clues based on the instantiation description in the unified knowledge expression model to achieve the integration of multi-domain digital twins.

[0042] The following combination Figures 2 to 5 Steps S100 to 5300 of the multi-domain digital twin integration method based on cognitive clues of this embodiment are described in detail.

[0043] Step S100: extract digital twin model information of each field of equipment.

[0044] In this embodiment, all class hierarchical relationships, object attributes, and data attributes contained in the complex system joint simulation scenario are analyzed. Based on the relevant theoretical knowledge of the system to be simulated and the division of subsystems in different fields, the hierarchical relationship of the classes to be modeled, that is, the association relationship between classes, is clarified; the object attributes of each class are analyzed, and the data attributes of each class are defined, that is, the information type and value type of the class itself are defined.

[0045] That is, in this embodiment, the model information required to define the cognitive ability of the digital twin is determined based on the cross-domain associations of the digital twins, the intra-domain associations, the model attributes of each digital twin, and the parameter information.

[0046] In this embodiment, first, the association relationship between the digital twins at each stage of the entire life cycle and the relevant design information during the iterative development process are determined to fully describe the evolution and mutual relationship of each digital twin during the research and development process; then, based on the composition of the multi-domain digital twins and the system division of different fields, the cross-domain hierarchical relationship between the heterogeneous data twins is clarified; finally, the properties of each digital twin are analyzed to clarify the model structure and data relationship of the twins in each field.

[0047] Specifically, in this embodiment, the extraction of digital twin model information of each field of equipment includes:

[0048] 1) Determine the cross-domain relationships among digital twins, the intra-domain relationships, the model attributes of each digital twin, and the parameter information;

[0049] 2) Based on the composition of multi-domain digital twins and the system division of different fields, determine the cross-domain hierarchical relationship between heterogeneous data twins;

[0050] 3) Analyze the properties of each digital twin and determine the model structure and data relationship of the twin in each field;

[0051] 4) Based on the cross-domain correlation relationships among digital twins, the intra-domain correlation relationships, the model attributes and parameter information of each digital twin, the cross-domain hierarchical relationship between the heterogeneous data twins, and the model structure and data relationship of the twins in each domain, the digital twin model information of each domain of equipment is extracted.

[0052] Step S200, determine the description specifications of the multi-domain digital twin cognitive capabilities.

[0053] In this embodiment, the expression specifications of the cognitive capabilities of multi-domain digital twins are determined, specifically including building a unified ontology modeling technology for the entire life cycle, multi-domain, and cross-level of the complex equipment R&D process based on the meta-meta model system. Through the ontology modeling technology based on the meta-meta model system, a unified and standardized description standard is determined for the extracted digital twin model information, so that it can standardize the description of the model information required to construct the cognitive capabilities of the digital twins, thereby standardizing the expression of the cognitive capabilities of the digital twins.

[0054] Specifically, in this embodiment, the description specification for determining the cognitive capabilities of multi-domain digital twins includes:

[0055] 1) Determine the description architecture of the digital twin’s cognitive capabilities based on the meta-metamodel system.

[0056] Determine the description architecture of digital twin cognitive capabilities based on the meta-metamodel system. Introduce a meta-metamodel layer that is more abstract than the metamodel layer to realize the cognitive ontology model description architecture from the meta-metamodel-metamodel-model layer, and maintain a unified description of data information in multi-domain digital twins.

[0057] 2) Based on the digital twin cognitive capability description architecture, determine the information elements at each level within the architecture and the corresponding description specifications.

[0058] Among them, in this embodiment, the information elements at each level in the architecture include: meta-metamodel, meta-model, model, association rules between meta-metamodels, connection relationships between models, system properties of meta-model, system properties of model and custom properties.

[0059] Among them, in this embodiment, the meta-metamodel layer is described by the class of the first level in the architecture, the metamodel layer is described by the subclass of the first level, and the model layer is described by the entity after the class is instantiated.

[0060] Step S300: Establish a unified knowledge expression model that can express the cognitive information of the digital twin based on the description specification of the multi-domain digital twin cognitive capabilities.

[0061] In this embodiment, an ontology model that characterizes the relationship between various simulation models of a complex system is constructed based on the meta-meta modeling method, and a complex system joint simulation framework is built; based on the determined multi-domain digital twin cognitive ability expression specification, a unified knowledge expression model that can express the cognitive information of digital twins is established, specifically including expressing the cognitive information of twins in various fields by establishing classes, object attributes, and data attribute data in the model. The composition of each digital twin is expressed by the class in the ontology, the cross-domain and intra-domain relationships of each digital twin are expressed by the object attribute, and the parameter attribute value of each digital twin is defined by the data attribute, so as to obtain a cognitive model for describing the domain information of multi-domain digital twins.

[0062] Specifically, in this embodiment, the unified knowledge expression model capable of expressing the cognitive information of the digital twin based on the description specification of the cognitive capabilities of the multi-domain digital twins is established, including:

[0063] The classes required for constructing the meta-meta model are based on the digital twin cognitive capability description architecture; wherein, in this embodiment, the classes specifically include six classes: graph, object, point, property, role, and relationship.

[0064] 2) Establish subclasses of digital twins in each field based on the extracted digital twin model information in each field and the classes required by the meta-meta model; that is, based on the concept classes describing the digital twins in each field extracted in step S100 and the hierarchical relationships, object attributes and data attributes between the concept classes, establish subclasses of digital twins in each field based on the meta-meta model classes.

[0065] 3) Define the corresponding object attributes and data attributes in each class and subclass, and establish a unified knowledge expression model for describing the cognitive information of digital twins.

[0066] Step S400: instantiate the unified knowledge expression model.

[0067] In this embodiment, the class is instantiated according to the actual complex system joint simulation scenario to form an architectural model under a specific joint simulation scenario; that is, the unified knowledge expression model in the instantiation step S300, specifically including instantiating the class in the ontology to obtain the digital twin entity, and accurately establishing the association relationship between different digital twin entities through the defined object attributes, and the instantiated ontology establishes the correct relationship between the data production digital twin and the data consumption digital twin to ensure the correct link between the twins in each field.

[0068] Specifically, in this embodiment, instantiating the unified knowledge expression model includes:

[0069] 1) Construct multi-domain digital twin entities in the ontology model by instantiating the classes in the ontology model;

[0070] 2) Based on the corresponding object attributes defined by each class and subclass, establish the association relationship between multi-domain digital twin entities.

[0071] Step S500, generates a unified resource identifier for the data information of digital twins in different fields, integrates the data of the entire life cycle involved in heterogeneous digital twins, and forms cognitive clues based on the instantiation description in the unified knowledge expression model to achieve the integration of multi-domain digital twins.

[0072] In this embodiment, data bonding technology is used to service the data information of each subsystem simulation model, and a unified resource identifier is generated, which is assigned as a data attribute value in the ontology model, and finally a cognitive clue is generated. That is, the heterogeneous data of each subsystem simulation model is serviced through data bonding technology, and cognitive clues are formed in combination with the cognitive ontology model that describes the multi-domain digital twin joint simulation framework, so as to achieve a high degree of integration of joint simulation. A unified resource identifier is generated for the data information of digital twins in different fields through data bonding technology, and the data of the entire life cycle involved in the heterogeneous digital twins is integrated, and cognitive clues are formed in combination with the instantiation description in the constructed cognitive ontology model, such as Figure 2 As shown in the figure, the integration of multi-domain digital twins is realized. Specifically, it includes generating a unified resource identifier from the heterogeneous data of multi-domain digital twins based on the open full life cycle specification, obtaining the data in the digital twins through the HTTP protocol, and then filling the unified identifier into the data attributes in the entity of the ontology model, giving the ontology model the ability to access the digital twin data resources, completing the construction of cognitive clues, and realizing the integration of digital twins between different fields.

[0073] Specifically, in this embodiment, the unified resource identifier is generated for the data information of digital twins in different fields, the data of the whole life cycle involved in the heterogeneous digital twins are integrated, and cognitive clues are formed based on the instantiation description in the unified knowledge expression model to realize the integration of multi-domain digital twins, including:

[0074] 1) Generate a unified resource identifier for the data information in the multi-domain digital twins using an open full life cycle service architecture, and access the multi-domain digital twins data information through the unified resource identifier;

[0075] 2) Fill the generated uniform resource identifier into the model as a data attribute in the cognitive ontology model, so that the cognitive ontology model has the ability to access the digital twin information in various fields, form cognitive clues, and realize the integration of multi-domain digital twins.

[0076] A certain type of gas turbine is used as an example below to explain in detail a multi-domain digital twin integration method based on cognitive clues involved in this example, but this is not intended to limit the scope of protection of the present invention.

[0077] 1) Extract the digital twin model information of gas turbines in various fields, including concept classes, object attributes, and data attributes. In order to facilitate the unified description of entities in the multi-domain digital twin of gas turbines, the concept classes that should be included in the multi-domain digital twin of gas turbines are as follows: Figure 3 shown.

[0078] Among them, the Thing class is the parent class of all concept classes in the ontology and is the most basic concept class. The graph class Graph is used to describe the digital twin integration scenario. It is a collection of Object, Property, and Point. The object class Object is used to describe the system in the digital twin. The property class Property is used to describe the properties of the digital twin. The point class Point is used to describe the ports on the digital twin object. The relationship class Relationship is used to describe the association between multi-domain digital twins. The role class Role is used to describe the direction of the digital twin association. The Cosimulation class is a subclass of Graph and is used to define specific simulation scenarios. Subsystem is a subclass of Object and is used to describe the digital twins of each subdomain system. The Inpoint class and the Outpoint class are both subclasses of the Point class, which define the input and output ports of the digital twins in each domain respectively. The ModelVariables class is a subclass of the Property class and defines the model variables of the digital twins in each domain. The StartValue class, the valueReference class, and the variableName class are all subclasses of the ModelVaribles class and are used to describe the model variables in detail. The startTime class, the stopTime class, the generationTool class, the author class, the modelName class, and the stepSize class are all subclasses of the Property class and are used to describe the design information and parameter information of the digital twins. The Rela1 class and the Rela2 class are both subclasses of the Relationship class and are used to describe different types of connection relationships respectively. The To class and the From class are both subclasses of the Role class and are used to describe the beginning and end of the relationship.

[0079] The connection between different concept classes is defined by object attributes. In this case, the object attributes of the multi-domain digital twin of the gas turbine are as follows: Figure 4 shown.

[0080] The object property hasName is used to connect Subsystem and modelName, hasPoint is used to connect Object and Point classes, hasProperty is used to connect Object and Property classes, hasReference is used to connect Point and valueReference classes, and hasStartvalue is used to connect Point and StartValue classes.

[0081] Then extract the data attributes of each entity class to describe the relationship between the instances of the concept class and the data type, such as Figure 5 shown.

[0082] ArchitectureInfo is used to describe the digital twin architecture information, DesignInfo is used to describe the digital twin design information, and ParameterInfo is used to describe the digital twin parameter information.

[0083] 2) Determine the expression specifications of the cognitive capabilities of multi-domain digital twins, use the meta-metamodel system to construct the ontology model, and determine the unified and standardized description standards for the extracted gas turbine digital twin model information.

[0084] 3) Based on the defined multi-domain digital twin cognitive ability expression specification, the ontology model representing the joint simulation framework is built in the protégé software using the meta-metamodel modeling method. First, the meta-metamodel modeling method is used to construct six classes: graph, object, point, property, role, and relationship. Then, based on the information of the gas turbine digital twin concept class, object attribute, and data attribute extracted in step 1, subclasses are established for the six classes in the meta-metamodel layer.

[0085] 4) According to the actual gas turbine digital twin integration scenario, the class is instantiated to form the gas turbine digital twin entity, and the association relationship between the digital twin entities is constructed through object attributes.

[0086] 5) Through data linkage technology, the heterogeneous data of each subsystem simulation model is service-oriented, combined with the cognitive ontology model that describes the multi-domain digital twin joint simulation framework to form cognitive clues, build a highly integrated joint simulation model, and finally obtain a digital twin integration scenario.

[0087] Example 2

[0088] like Figure 6 As shown, this embodiment provides an electronic device 101, and the electronic device 101 includes: a processor 1001 and a memory 1002; the memory 1002 is used to store a computer program; the processor 1001 is used to execute the computer program stored in the memory 1002, so that the electronic device 101 performs the steps of the multi-domain digital twin integration method based on cognitive clues in Example 1. Since the specific implementation process of the steps of the multi-domain digital twin integration method based on cognitive clues has been described in detail in Example 1, it will not be repeated here.

[0089] The processor 1001 is a (Central Processing Unit). The memory 1002 is connected to the processor 1001 through a system bus and completes communication with each other. The memory 1002 is used to store computer programs, and the processor 1001 is used to run computer programs so that the processor 1001 executes the multi-domain digital twin integration method based on cognitive clues. The memory 1002 may include a random access memory (Random Access Memory, referred to as RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0090] In addition, this embodiment further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by the processor 1001, the steps in the multi-domain digital twin integration method based on cognitive clues described in Example 1 are implemented. Example 1 has already described the multi-domain digital twin integration method based on cognitive clues in detail, which will not be repeated here.

[0091] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0092] In summary, the present invention uses the conceptual theory of ontology, through a modeling method based on the meta-meta model, to build a cognitive ontology model with high scalability to characterize the multi-domain digital twin framework, based on the data keying technology, to serve the data in the multi-domain digital twin, to generate a unified identifier that can access the digital twin data resources, and to assign it to the data attributes in the ontology model, so that the ontology model can also access the multi-domain data on the basis of describing the multi-domain digital twin framework, thereby constructing cognitive clues, giving the digital twin cognitive ability, and realizing the integration of multi-domain digital twins, effectively solving the technical problem that the prior art is difficult to effectively integrate the multi-domain digital twins of complex equipment; compared with other methods, the present invention can adopt cognitive clues technology for complex multi-domain digital twins, form a model integration framework with high openness and scalability, and support heterogeneous data interaction between different fields, thereby realizing the high integration of multi-domain digital twins. Therefore, the present invention effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0093] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A multi-domain digital twin integration method based on cognitive clues, characterized by: The method comprises: Extract digital twin model information of equipment in various fields; Determine the description specification of the cognitive ability of multi-domain digital twins; the description specification of determining the cognitive ability of multi-domain digital twins includes: determining the digital twin cognitive ability description architecture based on the meta-metamodel system; based on the digital twin cognitive ability description architecture, determine the information elements and corresponding description specifications at each level in the architecture; the information elements at each level in the architecture include: meta-metamodel, metamodel, model, association rules between meta-metamodels, connection relationships between models, system properties of metamodels, system properties of models and custom properties; the meta-metamodel layer is described by the class of the first level in the architecture, the metamodel layer is described by the subclass of the first level, and the model layer is described by the entity after the class is instantiated; A unified knowledge expression model capable of expressing the cognitive information of digital twins is established based on the description specification of the cognitive capabilities of the multi-domain digital twins; the unified knowledge expression model capable of expressing the cognitive information of digital twins is established based on the description specification of the cognitive capabilities of the multi-domain digital twins, including: constructing the classes required by the meta-meta model based on the digital twin cognitive capability description architecture; establishing subclasses of digital twins in various fields based on the extracted digital twin model information in various fields and the classes required by the meta-meta model; defining corresponding object attributes and data attributes in each class and subclass, and establishing a unified knowledge expression model for describing the cognitive information of digital twins; Instantiating the unified knowledge representation model; Through data linking technology, a unified resource identifier is generated for the data information of digital twins in different fields, the data of the entire life cycle involved in heterogeneous digital twins are integrated, and cognitive clues are formed based on the instantiated description in the unified knowledge expression model to achieve the integration of multi-domain digital twins.

2. The multi-domain digital twin integration method based on cognitive clues according to claim 1 is characterized by: The extraction of digital twin model information in various fields of equipment includes: Determine the cross-domain relationships among digital twins, the intra-domain relationships, the model attributes of each digital twin, and parameter information; Based on the composition of multi-domain digital twins and the system division of different fields, the cross-domain hierarchical relationship between heterogeneous data twins is determined; Analyze the properties of each digital twin and determine the model structure and data relationship of the twin in each field; Based on the cross-domain correlation relationships among digital twins, the intra-domain correlation relationships, the model attributes and parameter information of each digital twin, the cross-domain hierarchical relationship between the heterogeneous data twins, and the model structure and data relationship of the twins within each field, the digital twin model information of each field of equipment is extracted.

3. The multi-domain digital twin integration method based on cognitive clues according to claim 1 is characterized in that: The classes include graphs, objects, nodes, attributes, roles, and relationships.

4. The multi-domain digital twin integration method based on cognitive clues according to claim 1 is characterized in that: The instantiating the unified knowledge expression model comprises: By instantiating the classes in the ontology model, the multi-domain digital twin entities in the ontology model are constructed; Based on the corresponding object attributes defined by each class and subclass, an association relationship between multi-domain digital twin entities is established.

5. The multi-domain digital twin integration method based on cognitive clues according to claim 1 is characterized in that: The generation of unified resource identifiers for data information of digital twins in different fields, integration of data of the entire life cycle involved in heterogeneous digital twins, and formation of cognitive clues based on the instantiation description in the unified knowledge expression model to achieve the integration of digital twins in multiple fields include: An open full lifecycle service architecture is used to generate a uniform resource identifier for data information in multi-domain digital twins, and access to multi-domain digital twin data information is achieved through the uniform resource identifier; The generated uniform resource identifier is filled into the model as a data attribute in the cognitive ontology model, so that the cognitive ontology model has the ability to access the digital twin information in various fields, form cognitive clues, and realize the integration of multi-domain digital twins.

6. An electronic device, characterized in that: It includes a memory for storing a computer program; and a processor for running the computer program to implement the steps of the multi-domain digital twin integration method based on cognitive clues as described in any one of claims 1 to 5.

Images