CN115759258A - Relation adjusting method of power grid equipment entity based on knowledge graph - Google Patents
Relation adjusting method of power grid equipment entity based on knowledge graph Download PDFInfo
- Publication number
- CN115759258A CN115759258A CN202211432005.2A CN202211432005A CN115759258A CN 115759258 A CN115759258 A CN 115759258A CN 202211432005 A CN202211432005 A CN 202211432005A CN 115759258 A CN115759258 A CN 115759258A
- Authority
- CN
- China
- Prior art keywords
- power grid
- grid equipment
- relation
- knowledge
- component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a relation adjusting method of power grid equipment entities based on a knowledge graph, which can automatically distinguish equipment types to adjust the relation between the entities when a new knowledge graph is constructed without manual marking, thereby reducing the workload of constructing the knowledge graph. The method comprises the following steps: A. acquiring an initialization model of a power grid equipment updating engineering knowledge map; B. loading a data instance and reading attributes; C. searching different components of the equipment in different types in the entity attributes of the power grid equipment as components to be adjusted, and acquiring the relation of the components to be adjusted; D. c, a plurality of power grid equipment models with the components to be adjusted are called, and whether the components to be adjusted have the same relation with the power grid equipment entity in the step C and other entities to which the relation points are respectively searched in the models; E. and D, if the relation is not retrieved in the step D, deleting the relation of the power grid equipment entity in the initialization model of the currently loaded data instance.
Description
Technical Field
The invention relates to the technical field of knowledge graphs, in particular to a relation adjusting method of a power grid equipment entity based on a knowledge graph.
Background
The power industry is used as the center of energy production and consumption, mass data assets are accumulated, and the power industry enters the big power data era along with the rapid development of new technologies such as artificial intelligence, cloud computing and the Internet of things. Knowledge maps (Knowledge graphs) are used as innovation and development power of the emerging technologies, and can correlate Knowledge of multiple dimensions such as power grid equipment Knowledge, department service functions, industry experience and the like to analyze problems from multiple angles, so that the power industry also applies Knowledge maps to improve the utilization rate of power data. The data of the power industry is numerous and complex, and it is difficult to completely construct a knowledge graph covering the whole industry, so that the existing knowledge graph is mainly constructed by a small knowledge graph in a detailed field, such as a power grid organization architecture graph, a power grid equipment graph, an equipment operation graph, a power grid topology graph and the like.
The power grid equipment updating project is an important link of a power grid transformation upgrading project, so that a power grid equipment updating project knowledge graph is also one of important concerns in power grid services, the knowledge extraction of equipment entities in the power grid equipment updating project knowledge graph mainly comes from equipment own knowledge, such as an equipment guide, a manual and a basic concept, and the relationship among the entities mainly comes from a topological structure of a power grid example, such as a power grid wiring diagram in a certain area. However, in the grid example, there may be cases where the data example only describes the equipment, key components, and equipment attributes, but not the equipment type. For example, the transformer is divided into a dry type transformer and an oil immersed type transformer according to the cooling mode, and the device attributes of the dry type transformer and the oil immersed type transformer both have performance parameters related to functions: the device structure of the transformer and the device structure of the transformer are related to the key component iron core and the winding (winding), so that the transformer knowledge/relationship extracted from the existing knowledge graph is not only a dry type transformer but also an oil immersed transformer, but other parts of the transformer and the oil immersed transformer are greatly different, for example, the oil immersed transformer is provided with an oil tank and a cooling device, but the dry type transformer is not provided, so that the related relationship of the oil immersed transformer cannot be completely and directly multiplexed to the dry type transformer, otherwise, an invalid relationship is easily generated. The existing method is to manually label the equipment types to be distinguished in the knowledge graph, and the equipment types are distinguished when the knowledge graph is used, but the manual labeling is carried out on all the various power grid equipment, so that the operation difficulty is too high.
Disclosure of Invention
The invention aims to solve the technical problem of providing a relation adjusting method of power grid equipment entities based on a knowledge graph, which can automatically distinguish equipment types to adjust the relation between the entities without manual marking and reduce the workload of constructing the knowledge graph.
In order to solve the technical problem, the invention provides a relation adjustment method of a power grid equipment entity based on a knowledge graph, which comprises the following steps:
a, acquiring an initialization model of a power grid equipment updating engineering knowledge map;
b, loading a data instance of the initialization model, and reading the attribute of the power grid equipment entity in the data instance;
c, searching whether preset components to be adjusted exist in the attributes of each power grid equipment entity of the initialization model, wherein the preset components to be adjusted are different components of the power grid equipment entity in different types, and acquiring the relation of the power grid equipment entity to which the searched components to be adjusted belong;
d, a plurality of power grid equipment models with the components to be adjusted are called, and whether the components to be adjusted have the same relation with the power grid equipment entity in the step C and the entity to which the relation points is searched in the models respectively;
and E, if the relation is not retrieved in the retrieval result in the step D, deleting the relation of the power grid equipment entity in the initialization model of the current loaded data instance.
Further, in the step a, the initialization model is constructed by extracting entities and relationships from updated engineering knowledge of the power grid equipment selected by the user.
Further, the power grid equipment update engineering knowledge selected by the user comprises one or more of a power grid equipment map, a power grid topology map and a power grid maintenance record map.
Further, the component to be adjusted preset in the step C is obtained by calculation through the following steps:
c1, calling a plurality of power grid equipment models with component knowledge and performance parameter knowledge of power grid equipment entities, and respectively loading data of the power grid equipment models to obtain a plurality of model examples;
and C2, calculating the influence degree of each component of the power grid equipment entity on the performance parameters in the model example, and marking the component influencing the power grid equipment to the preset degree as a component to be adjusted.
Further, in the step C2, the influence degree of the component on the performance parameter is: closeness of association of the component with a performance parameter of the user-selected device.
Further, in the step C2, the influence degree of the component on the performance parameter is: the closeness of association of the components with faults that result in the device failing to function properly.
Further, the closeness of association is calculated based on its distance to the component in the plurality of grid equipment models.
Further, the distance calculation is implemented by one or more of the following distance metric algorithms: a path search algorithm Dijkstra, a centrality algorithm PageRank and a community discovery algorithm LPA.
Further, in the step C2: the core component for directly realizing the function of the equipment has high influence degree on the performance parameters of the equipment; auxiliary components providing performance optimization and/or safety protection functions have a low degree of influence on the performance parameters of the device.
Further, in the step E, the deleting is performed according to a selection operation of a user.
The invention provides a relation adjustment method of a power grid equipment entity based on a knowledge graph, which comprises the steps of finding out parts with differences in different types of the power grid equipment entity as parts to be adjusted through automatic analysis of the equipment entity, then obtaining an example of an initialization model of an updated engineering knowledge graph of power grid equipment, retrieving the parts to be adjusted from the example, then calling some power grid equipment models with the parts to be adjusted for comparison, judging whether the equipment entity has the same relation with the initialization model and other entities pointed by the relation in the power grid equipment models under the condition that the parts to be adjusted are represented by the equipment entity, and if the relation is not found, indicating that the relation which does not belong to the parts to be adjusted exists in the updated engineering knowledge graph of the power grid equipment, wherein the relation may be from other types of the equipment part, so that the equipment types are automatically distinguished to adjust the relation between the entities, if the relation is automatically deleted in the knowledge graph, the workload for constructing the knowledge graph is reduced.
Drawings
Fig. 1 is a schematic flow chart of a method for adjusting the relationship of power grid equipment entities based on a knowledge graph according to the present invention;
FIG. 2 is an example of an initialization model for updating an engineering knowledge graph of a power grid device provided by the present invention;
FIG. 3 is a schematic representation of attributes of the grid equipment entity of FIG. 2 provided by the present invention;
FIG. 4 is a schematic diagram of a tightness model for association between components and faults causing equipment to fail to operate normally in other power grid models provided by the present invention;
fig. 5 is a schematic diagram of an initialization model adjusted by the relation adjustment method of the knowledge-graph-based power grid equipment entity of the invention.
Detailed Description
The invention will be described in further detail with reference to specific embodiments.
The invention excavates different components with difference in different types of an equipment entity from a data example through correlation algorithm analysis, and then automatically correlates a plurality of knowledge map model examples of the equipment to find out which type of equipment the different components belong to. When the knowledge-graph is newly created/expanded, the components that find the differences of the devices from the knowledge of the data instances can know which type of device the devices of the knowledge-graph should be, and thus remove the relationships in the knowledge-graph that do not belong to that type of device and preserve the relationships of that type of device.
As shown in fig. 1, the method for adjusting the relationship of the power grid equipment entity based on the knowledge-graph includes the following steps.
And A, acquiring an initialization model of the power grid equipment updating engineering knowledge map.
The embodiment describes a process for constructing an update project knowledge graph of power grid equipment in a certain county by taking the example of constructing the update project knowledge graph of the power grid equipment: the power grid staff updates the engineering knowledge source of the power grid equipment selected from the knowledge map system, such as the power grid equipment map, the power grid topology map and the power grid maintenance record map of the local county, and the knowledge map system extracts entities and relations related to the power grid equipment from the power grid equipment updating engineering knowledge selected by the user to construct an initialization model, which is shown in fig. 2.
And B, loading the data instance of the initialization model, and reading the attribute of the power grid equipment entity in the data instance.
The power grid staff loads the data instance of the initialization model in the knowledge graph system, and the system highlights the power grid equipment entity in the data instance and displays the attribute characteristics of the power grid equipment entity to the power grid staff, as shown in fig. 3.
And C, searching whether a preset component to be adjusted exists in the attribute of the transformer of each power grid equipment entity power transformation equipment of the initialization model, wherein the preset component to be adjusted is a component with difference in different types of the power grid equipment entity, and acquiring the relation of the power grid equipment entity to which the searched component to be adjusted belongs.
The preset component to be adjusted is obtained through calculation according to the following steps.
And C1, calling a plurality of power grid equipment models with component knowledge and performance parameter knowledge of the power grid equipment entity, and respectively loading data of the power grid equipment models to obtain a plurality of model examples. The power grid equipment models are a large number of established service models related to power grid equipment in the system, such as a power grid equipment classification model, a power transmission/transformation equipment body model and a regional power grid system maintenance model, and data examples are loaded.
And C2, calculating the influence degree of each component of the power grid equipment entity on the performance parameters in the model example, and marking the component which has the preset influence degree on the power grid equipment as the component to be adjusted.
The core component directly realizing the equipment function has high influence degree on the equipment performance parameters; auxiliary components providing performance optimization and/or safety protection functions have a low degree of influence on the performance parameters of the device. The importance of each component to the device can be obtained from the existing device evaluation report, such as (1) a core component that implements the main function of the device, and (2) an auxiliary component that provides functions such as performance optimization/security protection. In the oil immersed transformer, (1) there are iron core, winding, oil tank, cooling device \8230; (2) 8230, oil purifier; the dry type transformer (1) has high voltage winding, low voltage winding, concentric winding 8230; (2) its advantages are high adhesion to substrate, low cost and high adhesion to substrate.
In the embodiment, through performing relevance algorithm analysis of components and performance parameters on a large number of data examples, one or more components with difference, such as a cooling device of an oil-immersed transformer and a concentric winding of the dry-type transformer, which have the greatest influence on the performance parameters of the self-equipment, are found, except core components such as an iron core and a winding (winding), of the dry-type transformer and the oil-immersed transformer.
In addition, the influence degree of the component on the performance parameter can be obtained through the relationship reasoning of the component in the existing mass knowledge graph models: such as closeness of association of a component to a user-selected performance parameter of the device or closeness of association of a component to a failure that results in the device failing to function properly, as shown in fig. 4. The closeness of association is calculated from its distance to the component in the plurality of grid equipment models by one or more of the following distance metric algorithms: the path search algorithm Dijkstra, the centrality algorithm PageRank and the community discovery algorithm LPA are implemented by the prior art, and are not described herein.
And D, calling a plurality of power grid equipment models with the components to be adjusted, and respectively searching whether the components to be adjusted have the same relation with the power grid equipment entity in the step C and the entity pointed by the relation. Searching out the components with difference in the data example in the modes of model/name of the component to be adjusted and the like, if finding out the cooling device of the dry-type transformer, calling out all the components: and if the power grid equipment updates a relation of the power grid equipment entity transformer in the engineering knowledge graph and other entity objects pointed by the relation, and the relation is not found in all the called power grid equipment service models, the retrieval result is that the relation is not retrieved.
And E, if the relation is not retrieved in the retrieval result in the step D, deleting the relation of the power grid equipment entity in the initialization model of the current loaded data instance. Further, the system displays the relationships to be deleted for the user to select, as shown by the dotted line in fig. 5, and the system deletes the relationships between the entities according to the user's selection operation.
The relation adjusting method of the power grid equipment entity based on the knowledge graph comprises the steps of finding out parts with differences in different types of the power grid equipment entity as parts to be adjusted through automatic analysis of the equipment entity, then obtaining an example of an initialization model of an updating engineering knowledge graph of the power grid equipment, searching the parts to be adjusted from the example, then calling some power grid equipment models with the parts to be adjusted for comparison, judging whether the equipment entity has the same relation with the initialization model and other entities to which the relation points in the power grid equipment models under the condition that the parts to be adjusted are represented by the equipment entity, and if the relation is not found, indicating that the power grid equipment updates the relation which does not belong to the parts to be adjusted and possibly comes from other types of the equipment part, so that the equipment type is automatically distinguished to adjust the relation between the entities, and if the relation is automatically deleted in the knowledge graph, the workload of constructing the knowledge graph is reduced.
The above description is only the embodiments of the present invention, and the scope of protection is not limited thereto. The insubstantial changes or substitutions will now be made by those skilled in the art based on the teachings of the present invention, which fall within the scope of the claims.
Claims (10)
1. A relation adjustment method of a power grid equipment entity based on a knowledge graph is characterized by comprising the following steps:
a, acquiring an initialization model of a power grid equipment updating engineering knowledge map;
b, loading a data instance of the initialization model, and reading the attribute of the power grid equipment entity in the data instance;
c, searching whether a preset component to be adjusted exists in the attribute of each power grid equipment entity of the initialization model, wherein the preset component to be adjusted is a component with difference in different types of the power grid equipment entity, and acquiring the relation of the power grid equipment entity to which the searched component to be adjusted belongs;
d, a plurality of power grid equipment models with the components to be adjusted are called, and whether the components to be adjusted have the same relation with the power grid equipment entity in the step C and an entity pointed by the relation is searched in the models respectively;
and E, if the relation is not retrieved in the retrieval result in the step D, deleting the relation of the power grid equipment entity in the initialization model of the current loaded data instance.
2. The method according to claim 1, wherein in step a, the initialization model is constructed by extracting entities and relationships from updated engineering knowledge of the grid devices selected by the user.
3. The method of adjusting relationship of a knowledge-graph-based grid equipment entity as claimed in claim 2, wherein the user-selected grid equipment update engineering knowledge comprises one or more of a grid equipment graph, a grid topology graph, and a grid maintenance record graph.
4. The relation adjustment method of the power grid equipment entity based on the knowledge graph as claimed in claim 1, wherein the preset component to be adjusted in the step C is obtained by calculating through the following steps:
c1, calling a plurality of power grid equipment models with component knowledge and performance parameter knowledge of power grid equipment entities, and respectively loading data of the power grid equipment models to obtain a plurality of model examples;
and C2, calculating the influence degree of each component of the power grid equipment entity on the performance parameters in the model example, and marking the component influencing the power grid equipment to the preset degree as a component to be adjusted.
5. The relation adjustment method for the power grid equipment entity based on the knowledge-graph as claimed in claim 4, wherein in the step C2, the influence degree of the component on the performance parameter is: closeness of association of the component with a performance parameter of the user-selected device.
6. The relation adjustment method for the power grid equipment entity based on the knowledge-graph as claimed in claim 4, wherein in the step C2, the influence degree of the component on the performance parameter is: the closeness of association of the components with faults that result in the device failing to function properly.
7. A method for relation adjustment of a knowledge-graph based grid equipment entity according to claim 5 or 6, characterized in that said closeness of association is calculated based on its distance to the component in a plurality of grid equipment models.
8. The method of relation adjustment of a knowledge-graph-based power grid equipment entity of claim 7, wherein the distance calculation is performed by one or more of the following distance metric algorithms: a path search algorithm Dijkstra, a centrality algorithm PageRank and a community discovery algorithm LPA.
9. The relation adjustment method for the power grid equipment entity based on the knowledge-graph as claimed in claim 4, wherein in the step C2: the core component for directly realizing the function of the equipment has high influence degree on the performance parameters of the equipment; auxiliary components providing performance optimization and/or safety protection functions have a low degree of influence on the performance parameters of the device.
10. The relation adjustment method of the power grid equipment entity based on the knowledge-graph as claimed in claim 1, wherein in the step E, the deletion is performed according to a selection operation of a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211432005.2A CN115759258A (en) | 2022-11-16 | 2022-11-16 | Relation adjusting method of power grid equipment entity based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211432005.2A CN115759258A (en) | 2022-11-16 | 2022-11-16 | Relation adjusting method of power grid equipment entity based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115759258A true CN115759258A (en) | 2023-03-07 |
Family
ID=85371717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211432005.2A Pending CN115759258A (en) | 2022-11-16 | 2022-11-16 | Relation adjusting method of power grid equipment entity based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759258A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117726322A (en) * | 2023-12-25 | 2024-03-19 | 深圳市正源翔工业智能有限公司 | Intelligent management method and system for probe test equipment |
-
2022
- 2022-11-16 CN CN202211432005.2A patent/CN115759258A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117726322A (en) * | 2023-12-25 | 2024-03-19 | 深圳市正源翔工业智能有限公司 | Intelligent management method and system for probe test equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113553420B (en) | Power grid fault processing rule recommendation method and system based on knowledge graph | |
| WO2018082364A1 (en) | Method and device for analyzing power-off range of power distribution network, and computer storage medium | |
| CN107657019B (en) | Network topology structure obtaining method and system of power grid system | |
| CN111159165B (en) | Cloud platform-based electric power underground low-power consumption edge computing system and method thereof | |
| CN106815409B (en) | Analysis method of power grid topological relation | |
| US20210390422A1 (en) | Knowledge-Base Information Sensing Method And System For Operations And Maintenance Of Data Center | |
| CN108206522B (en) | Power equipment state monitoring method and system | |
| CN115759258A (en) | Relation adjusting method of power grid equipment entity based on knowledge graph | |
| CN113723810A (en) | Graph database-based power grid modeling method | |
| CN115033657A (en) | Inquiry method, device and equipment based on knowledge graph and storage medium | |
| CN115392704A (en) | Material detection key parameter correlation analysis method | |
| CN117273133A (en) | Construction method of multi-source heterogeneous data knowledge graph of power distribution network | |
| CN115774915A (en) | Method and device for quickly constructing real-time topology of power grid | |
| CN105653419B (en) | Realization method and system of tracing to the source based on monitoring point | |
| CN112886574A (en) | Power grid operation control method and system based on graphic database | |
| US20160078129A1 (en) | Data processing apparatus and method | |
| CN109271350A (en) | A kind of database and information point table automatic comparison and synchronous method based on telemechanical communication | |
| CN112686468B (en) | Public facility stability optimization method | |
| KR101927689B1 (en) | Method for processing of cim network diagram | |
| CN115705364A (en) | Power grid monitoring knowledge graph construction method based on equipment operation characteristics | |
| CN112101798A (en) | Power equipment service life management method based on big data technology | |
| CN112101422A (en) | Typical case self-learning method for power system fault case | |
| CN114124717B (en) | Distribution network line topology visual monitoring method based on Internet of things technology | |
| CN105302921B (en) | Map class date storage method and system | |
| CN112287495B (en) | Method, device and system for judging subsection rationality of grid frame of power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |