A Method and System for Retrieving Mechanical Fault Domain Knowledge Based on Dynamic Knowledge Graphs

Abstract

This invention discloses a method and system for querying mechanical fault domain knowledge based on a dynamic knowledge graph. The method includes: constructing a dynamic knowledge graph for rolling bearings; obtaining a query question; performing a query operation on the dynamic knowledge graph for rolling bearings based on the query question; and outputting the rolling bearing knowledge query results. This invention, on the one hand, constructs an ontology model to manage knowledge, and then incorporates time information as an attribute of relevant entities into the knowledge graph during the construction of the data layer to build a dynamic knowledge graph; on the other hand, based on the SPARQL language, it performs a series of query operations on the constructed dynamic knowledge graph, providing a solution to solve problems from a relational perspective.

Description

Technical Field

[0001] This invention relates to the field of knowledge domain visualization and application technology, and in particular to a method and system for querying mechanical fault knowledge based on dynamic knowledge graphs. Background Technology

[0002] The statements in this section merely refer to the background art related to this invention and do not necessarily constitute prior art.

[0003] As various types of machinery and equipment continue to evolve towards artificial intelligence, the demand for operational stability in industrial activities is constantly increasing. Given the high intensity of use, complex structures, and high failure rates of some machinery, workers need to react more promptly to the operational status of the machinery, timely replacement of parts, and maintenance. This necessitates the construction of a unified knowledge system to express this knowledge in a consistent manner, enabling workers to quickly access the necessary information. The emergence of knowledge graphs provides an effective way to solve this problem. Knowledge graph technology can connect different types of knowledge to form a relational network, efficiently representing the complex relationships between numerous things, providing a function for analyzing and solving problems from the perspective of "relationships" between things. With its unique semantic processing and open interconnection capabilities, knowledge graphs make it easier for people to compute, understand, and evaluate various information resources.

[0004] In the process of realizing this invention, the inventors discovered the following technical problems in the prior art:

[0005] Existing knowledge graphs in the field of mechanical failure do not consider temporal information and cannot reflect how the machine's operating status changes over time. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a method and system for querying mechanical fault domain knowledge based on dynamic knowledge graphs. On one hand, it constructs an ontology model to manage knowledge, and then incorporates time information as an attribute of relevant entities into the knowledge graph during the construction of the data layer to build a dynamic knowledge graph. On the other hand, based on the SPARQL language, it performs a series of query operations on the constructed dynamic knowledge graph, providing a solution to the problem from a relational perspective.

[0007] In a first aspect, the present invention provides a method for querying mechanical fault domain knowledge based on dynamic knowledge graphs;

[0008] A method for querying mechanical fault domain knowledge based on dynamic knowledge graphs includes:

[0009] Constructing a dynamic knowledge graph for rolling bearings;

[0010] Obtain the query question, perform a query operation on the dynamic knowledge graph of rolling bearings based on the query question, and output the rolling bearing knowledge query results.

[0011] Secondly, this invention provides a mechanical fault domain knowledge query system based on dynamic knowledge graphs;

[0012] A knowledge query system for mechanical faults based on dynamic knowledge graphs, including:

[0013] The module is configured to: build a dynamic knowledge graph of rolling bearings;

[0014] The query module is configured to: obtain the question to be queried, perform a query operation on the dynamic knowledge graph of rolling bearings based on the question to be queried, and output the knowledge query results of rolling bearings.

[0015] Thirdly, the present invention also provides an electronic device, comprising:

[0016] Memory, used for non-transitory storage of computer-readable instructions; and

[0017] Processor, for executing the computer-readable instructions,

[0018] When the computer-readable instructions are executed by the processor, they perform the method described in the first aspect above.

[0019] Fourthly, the present invention also provides a storage medium for non-transitory storage of computer-readable instructions, wherein, when the non-transitory computer-readable instructions are executed by a computer, the instructions for the method described in the first aspect are executed.

[0020] Fifthly, the present invention also provides a computer program product, including a computer program that, when run on one or more processors, is used to implement the method described in the first aspect above.

[0021] Compared with the prior art, the beneficial effects of the present invention are:

[0022] By combining relevant knowledge of rolling bearings, an ontology model of rolling bearings is constructed. Based on this, data is imported to build a data layer. During the construction process, a method is used to create time information attribute values ​​for entities containing time information, integrating time information into the knowledge graph to complete the construction of a dynamic knowledge graph. Then, based on the SPARQL language, query operations are performed on the constructed dynamic knowledge graph to quickly organize and present knowledge to staff.

[0023] This invention takes rolling bearings, a crucial component of mechanical equipment, as an example. Based on practical application needs, it constructs an ontology model using a combination of bottom-up and top-down approaches, establishing a dynamic knowledge graph model layer. The dataset is based on the SJTU-S rolling bearing operation dataset published by the Joint Laboratory for Mechanical Equipment Health Monitoring. This dataset is modified through random generation and manual setting to fill in the mechanical states and fault types corresponding to the machine's operating time, adapting to the model's data layer requirements. The modified dataset is then populated into the dynamic knowledge graph, completing the construction of the knowledge graph data layer. This successfully integrates rolling bearing-related knowledge into a unified knowledge system. Furthermore, the knowledge graph incorporates the time dimension of mechanical operation, refines entity attributes, and implements common query functions with time information. This provides assistance to staff in setting mechanical operating conditions and monitoring mechanical operating status. Attached Figure Description

[0024] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0025] Figure 1 This is an ontology construction flowchart;

[0026] Figure 2 It is a knowledge graph in the field of engineering machinery maintenance and support that was referenced when constructing the ontology;

[0027] Figure 3 and Figure 4 It is a hierarchical diagram of classes and the relationships between them. Detailed Implementation

[0028] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0029] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments of the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. Furthermore, it should be understood that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0031] All data acquisition in this embodiment is carried out in accordance with laws and regulations and with user consent, and the data is used legally.

[0032] The operating status and fault information of mechanical equipment are mostly time-related; therefore, the constructed knowledge graph must incorporate temporal information, i.e., a dynamic knowledge graph. A dynamic knowledge graph incorporating temporal information not only clearly represents the validity of things and the relationships between them, but also allows for further analysis of the temporal trends of the knowledge graph structure using temporal analysis and graph similarity techniques, enabling a series of predictive analyses and helping people grasp key information. In the field of mechanical faults, dynamic knowledge graphs can clearly and effectively reflect the changes in machine operating status over time.

[0033] Dynamic knowledge graphs primarily utilize two data models: RDF graphs and attribute graphs. In RDF graphs, storage is done in triples such as "entity-relationship-entity" or "entity-attribute-attribute value." Several query languages ​​exist for these models: SPARQL for RDF graphs and Cypher for attribute graphs. SPARQL, short for SPARQL Protocol and RDF Query Language, is similar to SQL and is a language for manipulating databases. It's a language for querying RDF datasets, defined by the RDF data model developed by the World Wide Web Consortium, but applicable to all information resources represented using RDF. A standard SPARQL query is based on graph matching, consisting of triple combinations, AND logic, OR logic, and option combinations. SPARQL allows for querying constructed dynamic knowledge graphs, quickly retrieving needed knowledge combinations to aid decision-making.

[0034] In summary, in order to unify the expression of knowledge and provide application value, this study takes rolling bearings, an important component in the field of mechanical failure, as an example. It adopts a method for constructing and applying dynamic knowledge graphs in the field of mechanical failure based on the Protege development tool and the SPARQL language. On the one hand, Protege is used to construct dynamic knowledge graphs, and on the other hand, the SPARQL language is used to query the constructed dynamic knowledge graphs to obtain relevant knowledge in a timely manner.

[0035] Example 1

[0036] This embodiment provides a method for querying mechanical fault domain knowledge based on dynamic knowledge graphs;

[0037] like Figure 1 As shown, the mechanical fault domain knowledge query method based on dynamic knowledge graph includes:

[0038] S101: Constructing a dynamic knowledge graph for rolling bearings;

[0039] S102: Obtain the question to be queried, perform a query operation on the dynamic knowledge graph of rolling bearings based on the question to be queried, and output the knowledge query results of rolling bearings.

[0040] Furthermore, S101: Constructing a dynamic knowledge graph for rolling bearings specifically includes:

[0041] S101-1: Define the class for rolling bearings and the class hierarchy;

[0042] S101-2: Create entities of the class; wherein, entities include: entities of non-time-series information and entities of time-series information;

[0043] S101-3: Define the attributes of an entity; where the attributes of an entity include data attributes and relational attributes;

[0044] S101-4: Define constraints for data attributes and constraints for relation attributes;

[0045] S101-5: Derive the dynamic knowledge graph of rolling bearings.

[0046] Furthermore, S101-1: defines the class of rolling bearings and the class structure hierarchy, specifically including:

[0047] S101-11: Starting from the upper-level concept, based on the conceptual terminology of rolling bearings, the class of the rolling bearing body is obtained; the class of the rolling bearing body includes: bearing components, bearing fault types, bearing maintenance methods, bearing operating conditions, bearing operating time, and bearing operating status; the bearing operating status includes: rotational speed and radial force during operation;

[0048] S101-12: Starting from the underlying data, the underlying data includes the horizontal and vertical vibration signals at each moment under normal operating conditions; and the horizontal and vertical vibration signals at each moment under abnormal operating conditions;

[0049] S101-13: Combine the conceptual terms of S101-11 and S101-12 to obtain the class of rolling bearings and the class structure hierarchy.

[0050] Further, S101-11: Starting from the higher-level concept, based on the conceptual terminology of rolling bearings, the class of rolling bearing body is obtained, wherein the conceptual terminology in the field of rolling bearings includes:

[0051] The components of a rolling bearing include: an outer ring, an inner ring, and a cage;

[0052] The four types of rolling bearing failures and their corresponding solutions are: outer ring wear, inner ring wear, cage breakage, and outer ring breakage. The corresponding solutions are: replace the outer ring, replace the inner ring, and replace the cage, respectively.

[0053] The two operating conditions of a rolling bearing are the bearing speed and the radial force it bears. The operating parameters include the operating time and the corresponding horizontal and vertical vibration signals. The operating states are normal operation and abnormal operation.

[0054] Rolling bearing maintenance methods include daily maintenance and periodic maintenance.

[0055] Further, S101-13: Combining the conceptual terms of S101-11 and S101-12 to obtain the class of rolling bearings and the class structure hierarchy, specifically including:

[0056] The categories of rolling bearing bodies include: bearing components, bearing operating conditions, bearing operating status, bearing operating time span, bearing fault types, bearing fault solutions, and maintenance methods.

[0057] Bearing operating conditions include two subcategories: radial force and rotational speed;

[0058] Bearing operating status includes two subclasses: normal status and abnormal status;

[0059] The normal state subclass includes: horizontal vibration signals and vertical vibration signals during normal operation;

[0060] The abnormal state subclass includes: horizontal and vertical vibration signals under abnormal operating conditions, as well as the specific fault type that occurs at the time of the fault.

[0061] The final defined classes and their hierarchical structure are visible. Figure 3 and Figure 4 As shown.

[0062] It should be understood that S101-1 defines the classes of rolling bearings and the hierarchical structure of the classes. This is a step in building a knowledge system during the construction of a knowledge graph, and it is also the most important step in the construction process. It adopts a combination of top-down and bottom-up methods, starting from the upper-level concepts and the lower-level data, to summarize the classes of the dynamic knowledge graph of rolling bearings and the hierarchical structure of the classes.

[0063] Further, in S101-2: creating entities of a class; wherein, the entities include: entities of non-time-series information and entities of time-series information; wherein, the entities of non-time-series information include:

[0064] The Component_parts class of bearings includes: the cage entity of rolling bearings, the inner ring entity of rolling bearings, and the outer ring entity of rolling bearings.

[0065] Rolling bearing failure types include: cage fracture, inner ring wear, outer ring wear, and outer ring fracture.

[0066] Trouble solutions include: replacing the cage, replacing the inner ring, and replacing the outer ring.

[0067] Since the dataset used in this invention was collected under a radial force of 12kN and a rotational speed of 35HZ, the entity of the radial force subclass under the operating_conditions class is 12kN, and the entity of the rotating speed subclass is 35HZ.

[0068] Furthermore, the entity relationships of the non-time-series information include: the relationship between the fault type entity and the component entity and the solution entity.

[0069] For example, in the event of a cage fracture failure, a relationship is established between the cage fracture entity `Cage_fracture` and the corresponding `Cage` entity of the rolling bearing component class by setting a fault type and a corresponding `trouble_unit` attribute. Similarly, a relationship is established between the cage fracture entity `Cage_fracture` and the replacement cage entity `Replace_cage` under the fault solution class by setting a fault type and a solution attribute, thus establishing a connection between two entities of different classes. Likewise, a maintenance method relationship is established between entities under the rolling bearing component class and their corresponding entities under the maintenance solution class.

[0070] Further, in S101-2: create an entity of the class; wherein, the entity includes: an entity of non-time-series information and an entity of time-series information; wherein, the entity of time-series information includes: horizontal vibration signal and vertical vibration signal and the time information contained therein under normal operating conditions, horizontal vibration signal and vertical vibration signal and the time information contained therein under operating fault conditions, and the time of operating fault and the type of fault that occurred.

[0071] It should be understood that S101-2: Create entities of a class; wherein, entities include: entities with non-time-series information and entities with time-series information; attributes are an indispensable part of describing an entity. This invention divides the attributes of an entity into two categories: attributes that do not contain time information and time attributes. Non-time attributes are information that is not related to time, such as the components of mechanical parts and maintenance methods, while defining time attributes is to import time information into a knowledge graph.

[0072] Further, S101-3: Define the attributes of the entity; wherein, the attributes of the entity include data attributes and relational attributes, wherein the data attributes include:

[0073] The bearing movement time attribute is Time (of type string, for easy character matching), the fault type attribute is SpecificFailure, the bearing movement status attribute is status, the bearing movement time attribute is t (of type integer, for easy sorting of search results), and the fault name attribute is faultname.

[0074] Among them, the Time and t attributes are used to represent the running time information of the rolling bearing; the time and t attributes are attributes possessed by entities containing time information under the time_span class, Specific_failure class, Horizontal_vibration_signals_a(b) class, and Vertical_vibration_signals_a(b) class.

[0075] The status attribute is used to mark the current running status of the entity;

[0076] The SpecificFailure attribute is used to mark the failure type of an entity;

[0077] The faultname attribute is used to identify entities under the fault type class Type_of_failure.

[0078] Further, S101-3: Define the attributes of the entity; wherein, the attributes of the entity include data attributes and relational attributes, wherein the relational attributes include:

[0079] The `solution` attribute, which represents the correspondence between entities under a fault type and entities under a fault solution, is used to link different fault types and their corresponding solutions.

[0080] The `trouble_unit` attribute, which establishes the correspondence between fault types and bearing components, is used to link different fault types with the components where the fault occurred.

[0081] The `maintenance` attribute, which establishes the relationship between the components of a rolling bearing and their corresponding maintenance methods, is used to link the components of a rolling bearing with their respective maintenance methods.

[0082] It should be understood that S101-3: Define the attributes of an entity; where the attributes of an entity include data attributes and relational attributes; different types of entities have different attributes. This step is to match the entity categories and attributes defined earlier, and to specify the attribute types.

[0083] Further, S101-4: Define constraints on data attributes and constraints on relation attributes, wherein the constraints on data attributes include:

[0084] The Time attribute has a string value and is used to query for a match at the given time.

[0085] The 't' attribute value is set to integer type to sort the query results by time information;

[0086] The values ​​of the SpecificFailure, status, and faultname properties are all of type string.

[0087] It should be understood that the purpose of defining constraints on data attributes is to facilitate matching during queries and the display of query results.

[0088] Further, S101-4: Define constraints on data attributes and constraints on relation attributes, wherein the constraints on relation attributes include:

[0089] The relationship between fault types and solutions is defined by the entity under the Type_of_failure class pointing to the entity under the trouble_solution class.

[0090] The component attribute trouble_unit corresponding to the fault is an entity in the Type_of_failure class that points to an entity in the Component_parts class, which is the bearing component class.

[0091] The maintenance attribute of a bearing component is an entity in the Component_parts class that points to an entity in the Maintenance_method class of the bearing component.

[0092] It should be understood that S101-4: Define the constraints of data attributes and the constraints of relation attributes; modify the dataset according to the schema layer, import the dataset in an appropriate form, create the relationships between corresponding attribute values ​​and entities during the data import process, and complete the creation of the data layer.

[0093] Furthermore, S101-5: deriving the dynamic knowledge graph of rolling bearings specifically includes:

[0094] Use the Protége knowledge graph to export it as an RDF file for storage.

[0095] It should be understood that S101-5: Export the dynamic knowledge graph of rolling bearings. For the convenience of subsequent query operations, the constructed dynamic knowledge graph is stored as RDF data.

[0096] It should be understood that S102: Obtain the query question, perform a query operation on the rolling bearing dynamic knowledge graph based on the query question, output the rolling bearing knowledge query results, and perform the query based on the SPARQL query statement. The query method of the SPARQL query statement is "entity-relationship-entity" or "entity-attribute-attribute value". This invention realizes the common query operations on the rolling bearing dynamic knowledge graph according to its query method, reflecting the construction value of the dynamic knowledge graph.

[0097] The ontology constructed belongs to the field of mechanical faults. The application goal of this invention is to represent knowledge more systematically and clearly on top of existing data, making it easier to query.

[0098] like Figure 2 As shown, an ontology model is designed with reference to existing knowledge graphs in the field of mechanical faults (such as knowledge graphs in the field of engineering machinery maintenance and support). Based on the ontology model, improvements are made to highlight the temporal characteristics of dynamic knowledge graphs, that is, to add temporal information of rolling bearing operation to make it suitable for the establishment of rolling bearing operation ontology in the field of mechanical faults.

[0099] Further, S102: Obtain the query question, perform a query operation on the rolling bearing dynamic knowledge graph based on the query question, and output the rolling bearing knowledge query results, specifically including:

[0100] S102-1: Query the operating time span of rolling bearings;

[0101] S102-2: Query the operating status and operating parameters of a rolling bearing at a certain moment;

[0102] S102-3: Query the set of times when a certain type of fault occurred;

[0103] S102-4: Query the time, type, and component of all failures that occurred during the operation of a rolling bearing; or,

[0104] S102-5: Query the fault types, corresponding faulty components, solutions, and maintenance methods during the operation of rolling bearings.

[0105] Further, S102-1: Querying the operating time span of the rolling bearing, the specific query process is as follows:

[0106] Use the `timespan` (a variable in the SPARQL statement, hereinafter the same) as the subject, `type` as the predicate, and `time_span` as the object. The query will return all entities of type `(time span) time_span`.

[0107] Further, S102-2: Querying the operating status and parameters of the rolling bearing at a certain moment, the specific query process is as follows:

[0108] Based on the given time information, query the horizontal vibration signal, vertical vibration signal under normal operating conditions, and horizontal vibration signal and vertical vibration signal under fault conditions.

[0109] Because the time information is unique, only one result can be retrieved. The time information is matched using the Filter statement, and the string type is matched based on the Time attribute of the entity.

[0110] If the query result is found during normal operation, the fault at that specific moment will not be displayed. Therefore, the OPTIONAL statement will not show the fault type. If the query result is found during a faulty state, it will be displayed normally, and the fault type will be shown based on the node's fault attributes. In summary, the UNION statement combines these two scenarios to display the query results.

[0111] Furthermore, S102-3: Query the set of times when a certain type of fault occurs, specifically including:

[0112] The Filter statement matches the fault attributes of entities in the Specific_failure class at a given time with the given fault type, retrieves the set of times that meet the conditions, and finally sorts the results in ascending order based on the time.

[0113] Furthermore, S102-4: Query the time, type, and component of all failures that occurred during the operation of the rolling bearing, specifically including:

[0114] By querying all entities of the `Specific_failure` class for a specific fault type at a given time, we can obtain all times when the bearing failed. For each time point, the fault type can be obtained based on the entity's fault attribute value. Since each fault type corresponds to a unique entity under the `Type_of_failure` class, the fault type entity can be retrieved. The faulty component can then be obtained by querying the "fault unit" relationship between the fault type entity and the bearing component.

[0115] Furthermore, S102-5: Querying the fault type, corresponding faulty component, solution method, and maintenance method during the operation of the rolling bearing, specifically including:

[0116] The bearing's fault type is obtained by querying the `Type_of_failure` class; the faulty component is obtained by querying the `trouble_unit` relationship between the fault type and the faulty component; and the solution is obtained by querying the `solution` relationship between the fault type and the solution entity. This helps engineers quickly understand the basic condition of the bearing.

[0117] Example 2

[0118] This embodiment provides a mechanical fault domain knowledge query system based on dynamic knowledge graph;

[0119] A knowledge query system for mechanical faults based on dynamic knowledge graphs, including:

[0120] The module is configured to: build a dynamic knowledge graph of rolling bearings;

[0121] The query module is configured to: obtain the question to be queried, perform a query operation on the dynamic knowledge graph of rolling bearings based on the question to be queried, and output the knowledge query results of rolling bearings.

[0122] It should be noted that the above-mentioned construction module and query module correspond to steps S101 to S102 in Embodiment 1. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0123] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0124] The proposed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and the division of modules described above is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0125] Example 3

[0126] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are stored in the memory. When the electronic device is running, the processor executes the one or more computer programs stored in the memory to cause the electronic device to perform the method described in Embodiment 1.

[0127] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0128] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0129] In the implementation process, each step of the above method can be completed by the integrated logic circuits in the processor hardware or by software instructions.

[0130] The method in Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0131] Those skilled in the art will recognize that the units and algorithm steps described in connection with the various examples of this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0132] Example 4

[0133] This embodiment also provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the method described in Embodiment 1.

[0134] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for querying mechanical fault domain knowledge based on dynamic knowledge graphs, characterized by: include: Constructing a dynamic knowledge graph for rolling bearings; Obtain the question to be queried, perform a query operation on the dynamic knowledge graph of rolling bearings based on the question to be queried, and output the knowledge query results of rolling bearings. Constructing a dynamic knowledge graph for rolling bearings, specifically including: Define the class for rolling bearings and its class hierarchy, specifically including: Starting from the upper-level concept and based on the conceptual terminology of rolling bearings, we obtain the class of rolling bearing body; the class of rolling bearing body includes: bearing components, bearing fault types, bearing maintenance methods, bearing operating conditions, bearing operating time, and bearing operating status; the bearing operating status includes: rotational speed and radial force during operation; Starting from the underlying data, the underlying data includes the horizontal and vertical vibration signals at each moment under normal operating conditions; and the horizontal and vertical vibration signals at each moment under abnormal operating conditions. Create entities of the class; wherein, the entities include: entities of non-time-series information and entities of time-series information; wherein, entities of non-time-series information include: The Component_parts class of a bearing includes: the cage entity of a rolling bearing, the inner ring entity of a rolling bearing, and the outer ring entity of a rolling bearing. Rolling bearing failure types include: cage fracture, inner ring wear, outer ring wear, and outer ring fracture. Trouble solutions include: replacing the cage, replacing the inner ring, and replacing the outer ring. The entities of the timing information include: horizontal vibration signals and vertical vibration signals under normal operating conditions and the time information contained therein, horizontal vibration signals and vertical vibration signals under operating fault conditions and the time information contained therein, as well as the time of the operating fault and the type of fault that occurred. Define the attributes of an entity; where entity attributes include data attributes and relational attributes; Define constraints on data attributes and constraints on relation attributes; Export the dynamic knowledge graph of rolling bearings.

2. The mechanical fault domain knowledge query method based on dynamic knowledge graph as described in claim 1, characterized in that, The definition of rolling bearing classes and their hierarchical structure also includes: By combining conceptual terms, we obtain the class of rolling bearings and the class structure hierarchy; By combining conceptual terms, we obtain the class of rolling bearings and its hierarchical structure, specifically including: The categories of rolling bearing bodies include: bearing components, bearing operating conditions, bearing operating status, bearing operating time span, bearing fault types, bearing fault solutions, and maintenance methods. Bearing operating conditions include two subcategories: radial force and rotational speed; Bearing operating status includes two subclasses: normal status and abnormal status; The normal state subclass includes: horizontal vibration signals and vertical vibration signals during normal operation; The abnormal state subclass includes: horizontal and vertical vibration signals under abnormal operating conditions, as well as the specific fault type that occurs at the time of the fault.

3. The mechanical fault domain knowledge query method based on dynamic knowledge graph as described in claim 2, characterized in that, Starting from the higher-level concepts and based on the conceptual terminology of rolling bearings, we obtain the class of rolling bearings themselves. The conceptual terminology in the field of rolling bearings includes: The components of a rolling bearing include: an outer ring, an inner ring, and a cage; The four types of rolling bearing failures and their corresponding solutions are: outer ring wear, inner ring wear, cage breakage, and outer ring breakage. The corresponding solutions are: replace the outer ring, replace the inner ring, and replace the cage, respectively. The two operating conditions of a rolling bearing are the bearing speed and the radial force it bears. The operating parameters include the operating time and the corresponding horizontal and vertical vibration signals. The operating states are normal operation and abnormal operation. Rolling bearing maintenance methods include daily maintenance and periodic maintenance.

4. The mechanical fault domain knowledge query method based on dynamic knowledge graph as described in claim 1, characterized in that, Define the attributes of an entity; where entity attributes include data attributes and relational attributes, where data attributes include: The bearing movement time attribute is Time, the fault type attribute is SpecificFailure, the bearing movement status attribute is status, the bearing movement time attribute is t, and the fault name attribute is faultname. The Time and t attributes are used to represent the running time information of the rolling bearing; the status attribute is used to mark the running status of the entity at any given time; and the SpecificFailure attribute is used to mark the failure type of the entity. The faultname attribute is used to identify entities under the fault type class Type_of_failure; Define the attributes of an entity; where entity attributes include data attributes and relational attributes, where relational attributes include: The `solution` attribute, which represents the correspondence between entities under a fault type and entities under a fault solution, is used to link different fault types and their corresponding solutions. The `trouble_unit` attribute, which establishes the correspondence between fault types and bearing components, is used to link different fault types with the components where the fault occurred. The `maintenance` attribute, which establishes the relationship between the components of a rolling bearing and their corresponding maintenance methods, is used to link the components of a rolling bearing with their respective maintenance methods.

5. The mechanical fault domain knowledge query method based on dynamic knowledge graph as described in claim 1, characterized in that, Define constraints for data attributes and constraints for relation attributes. Constraints for data attributes include: The Time attribute has a string value and is used to query for a match at the given time. The 't' attribute value is set to integer type to sort the query results by time information; The values ​​of the SpecificFailure, status, and faultname properties are all of type string; Define constraints for data attributes and constraints for relation attributes. Constraints for relation attributes include: The relationship between fault types and solutions is defined by the entity under the Type_of_failure class pointing to the entity under the trouble_solution class. The component attribute trouble_unit corresponding to the fault is an entity in the Type_of_failure class that points to an entity in the Component_parts class, which is the bearing component class. The maintenance attribute of a bearing component is an entity in the Component_parts class that points to an entity in the Maintenance_method class of the bearing component.

6. A mechanical fault domain knowledge query system based on dynamic knowledge graphs, characterized by including: The module is configured to: build a dynamic knowledge graph of rolling bearings; The query module is configured to: obtain the question to be queried, perform a query operation on the dynamic knowledge graph of rolling bearings based on the question to be queried, and output the knowledge query results of rolling bearings. Constructing a dynamic knowledge graph for rolling bearings, specifically including: Define the class for rolling bearings and its class hierarchy, specifically including: Starting from the upper-level concept and based on the conceptual terminology of rolling bearings, we obtain the class of rolling bearing body; the class of rolling bearing body includes: bearing components, bearing fault types, bearing maintenance methods, bearing operating conditions, bearing operating time, and bearing operating status; the bearing operating status includes: rotational speed and radial force during operation; Starting from the underlying data, the underlying data includes the horizontal and vertical vibration signals at each moment under normal operating conditions; and the horizontal and vertical vibration signals at each moment under abnormal operating conditions. Create entities of the class; wherein, the entities include: entities of non-time-series information and entities of time-series information; wherein, entities of non-time-series information include: The Component_parts class of a bearing includes: the cage entity of a rolling bearing, the inner ring entity of a rolling bearing, and the outer ring entity of a rolling bearing. Rolling bearing failure types include: cage fracture, inner ring wear, outer ring wear, and outer ring fracture. Trouble solutions include: replacing the cage, replacing the inner ring, and replacing the outer ring. The entities of the timing information include: horizontal vibration signals and vertical vibration signals under normal operating conditions and the time information contained therein, horizontal vibration signals and vertical vibration signals under operating fault conditions and the time information contained therein, as well as the time of the operating fault and the type of fault that occurred. Define the attributes of an entity; where entity attributes include data attributes and relational attributes; Define constraints on data attributes and constraints on relation attributes; Export the dynamic knowledge graph of rolling bearings.

7. An electronic device, characterized in that it comprises: Memory is used to store computer-readable instructions in a non-transitory manner. as well as Processor, for executing the computer-readable instructions, When the computer-readable instructions are executed by the processor, they perform the method described in any one of claims 1-5.

8. A storage medium, characterized in that, The computer-readable instructions are stored non-transitory, wherein when the non-transitory computer-readable instructions are executed by a computer, the instructions of the method according to any one of claims 1-5 are executed.

Images