CN115329145A - Physical relationship-based power transformation simulation information knowledge graph construction and retrieval method - Google Patents
Physical relationship-based power transformation simulation information knowledge graph construction and retrieval method Download PDFInfo
- Publication number
- CN115329145A CN115329145A CN202210954229.3A CN202210954229A CN115329145A CN 115329145 A CN115329145 A CN 115329145A CN 202210954229 A CN202210954229 A CN 202210954229A CN 115329145 A CN115329145 A CN 115329145A
- Authority
- CN
- China
- Prior art keywords
- ontology
- equipment
- power transformation
- simulation information
- knowledge graph
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 155
- 230000009466 transformation Effects 0.000 title claims abstract description 124
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 230000006870 function Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000007547 defect Effects 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000001364 causal effect Effects 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 claims 2
- 230000002596 correlated effect Effects 0.000 claims 1
- 238000004804 winding Methods 0.000 description 59
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000009413 insulation Methods 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- WABPQHHGFIMREM-UHFFFAOYSA-N lead(0) Chemical compound [Pb] WABPQHHGFIMREM-UHFFFAOYSA-N 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000003000 inclusion body Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 125000006850 spacer group Chemical group 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power transformation simulation information knowledge graph construction and retrieval method based on physical relation in the technical field of power transformation equipment simulation, which comprises the following steps: acquiring simulation information of the power transformation equipment; constructing a power transformation equipment simulation information knowledge graph based on physical equipment, a system or a group of components thereof; building a power transformation equipment simulation information knowledge graph body based on physical equipment or a system on the basis of the power transformation equipment simulation information knowledge graph; establishing the body attribute of the simulation information knowledge map of the power transformation equipment on the basis of the body of the simulation information knowledge map, and establishing the body relation of the simulation information knowledge map of the power transformation equipment on the basis of the physical entity relation; performing extension reasoning on the ontology relationship and the ontology attribute of the knowledge graph; the power transformation equipment simulation information knowledge graph is used for external retrieval of the power transformation equipment simulation information by utilizing the query key words and graph structures corresponding to the combination of the query key words. The invention realizes the quick matching of the simulation information of the power transformation equipment with different sources and the knowledge graph.
Description
Technical Field
The invention relates to a power transformation simulation information knowledge graph construction and retrieval method based on physical relations, and belongs to the technical field of power transformation equipment simulation.
Background
In a transformer substation simulation system, in order to facilitate the realization of autonomous learning and knowledge assistance and the transmission of information among different simulation systems, a retrieval and query function of simulation information of the transformer equipment needs to be configured for various information generated in the simulation process of the transformer equipment. The simulated power transformation equipment simulates actual equipment, has the characteristics of various types and different models, but has more commonalities of item setting, data attribute and the like of information such as measurement, monitoring, regulation, control, running state and the like among the same type of power transformation equipment and different equipment. The information reflects physical phenomena, but for the same information of the same physical equipment, due to differences of manufacturers, development time, design schemes and the like of subsystems, data information names, key words, types, attributes and the like also often have differences. In order to realize the inquiry of the simulation information knowledge of the power transformation equipment, the simulation information of the power transformation equipment can be organized and managed by constructing a knowledge graph, and the simulation information of the power transformation equipment of different simulation systems or the same simulation system is associated with the knowledge graph and is used for realizing the comparison and knowledge retrieval of the simulation information of the power transformation equipment and avoiding the influence on the accuracy and the efficiency of the information retrieval due to the different expression forms of system data.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a power transformation simulation information knowledge graph construction and retrieval method based on physical relationship, constructs a power transformation equipment simulation information knowledge graph by taking a physical entity as a basis, and can realize the quick matching of power transformation equipment simulation information with different sources and a power transformation equipment simulation information knowledge graph by means of the mapping relationship between an information system and a physical system.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the invention provides a power transformation simulation information knowledge graph construction and retrieval method based on physical relationship, which comprises the following steps:
acquiring simulation information of the power transformation equipment;
constructing a power transformation equipment simulation information knowledge graph on the basis of physical equipment, a physical system or a component thereof;
building a power transformation equipment simulation information knowledge graph body based on physical equipment or a system on the basis of the power transformation equipment simulation information knowledge graph;
establishing the body attribute of the simulation information knowledge map of the power transformation equipment on the basis of the body of the simulation information knowledge map, and establishing the body relation of the simulation information knowledge map of the power transformation equipment on the basis of the physical entity relation;
performing extension reasoning on the ontology relationship and the ontology attribute of the knowledge graph;
the power transformation equipment simulation information knowledge graph is used for external power transformation equipment simulation information retrieval by utilizing the query key words and the graph structures corresponding to the combination of the query key words.
Further, the transformer equipment simulation information knowledge graph structure comprises a plurality of attributes and a plurality of incidence relations, and the structure is as follows: { ontology, ontology attribute set, ontology incidence relation set }, where the ontology attribute set includes multiple attributes of an ontology, the ontology incidence relation set includes a plurality of relations between the ontology and other ontologies, the incidence relation between ontologies is a physical relation between ontologies, and the ontology attributes correspond to applications of physical entities.
Further, a substation equipment simulation information knowledge map ontology is established based on the physical equipment or the system, and the method comprises the following steps: the knowledge graph body is constructed in a layered mode according to a transformer substation, intervals, equipment and component assemblies, wherein the transformer substation level body is a device or a system with functions facing a whole station or multiple intervals, the interval level body is arranged according to actual physical intervals, one or more transformer equipment including primary equipment, secondary equipment and auxiliary equipment is arranged in each interval, and the transformer equipment level body is constructed according to actual transformer equipment and internally contains the equipment and the component assemblies thereof.
Furthermore, the knowledge graph ontology attribute describes the information content of the physical entity in various applications, and is divided into the following types: parameter data, commissioning and decommissioning states, operational data, abnormal phenomena, operational control, defects, evaluation, operation and maintenance inspection and overhaul, wherein the physical entity comprises physical equipment or components thereof.
Further, the transformer equipment simulation information knowledge graph ontology relationship includes:
the inclusion relationship: physical equipment and physical equipment component parts, systems and component equipment thereof;
electrical and communication connection relation: a wire and communication connection to the physical device and the physical device component;
the magnetic field and the thermal force field are related: the magnetic field connection between the physical equipment and the physical equipment component, or the physical connection of the equipment group components on heat conduction;
spatial proximity relationship: the physical equipment is close to and in contact with the physical equipment component in space;
applying the incidence relation: the application functions of the physical equipment and the component parts of the physical equipment are consistent or have a causal relationship and an interactive relationship.
Further, performing extended reasoning on the ontology relationship of the knowledge graph, including: configuring the attribute of the association coefficient to describe the association relationship, wherein the association coefficient can calculate the association relationship degree between the bodies indirectly associated by inference, and the method comprises the following steps:
0≤a≤1
wherein a is a correlation coefficient and is used for describing the closeness degree of the relationship between the ontologies, and when the value is 0, no correlation exists between the ontologies; when the value is 1, the strong association between the ontologies is represented;
for an extended association relation acquired through inheritance among indirectly associated ontologies, assigning values of the indirectly associated ontologies as association coefficients according to the proportion of part of ontologies contained in the 'inclusion relation' in the inclusion ontology;
for the extended association relationship obtained by the association between indirectly associated ontologies, the association coefficient of the A ontology and the B ontology is assumed as a AB The correlation coefficient of B and C is assumed to be a BC The degree of association a between the A and C ontologies AC Comprises the following steps:
a AC ＝a AB ×a BC
further, performing extended reasoning on the ontology attributes of the knowledge graph, including: and relating the contained partial ontology attribute and the ontology name into an ontology attribute-containing name by extension, and when the A ontology and the B ontology are in an inclusion relationship and the A ontology contains the B ontology, relating the attribute of the B ontology into the attribute of the A ontology by extension, wherein the attribute name of the A ontology is obtained by inference by the extension method and is as follows:
a ontology attribute name = B ontology name + B attribute
Further, the retrieval target of the power transformation equipment simulation information is that the simulation information is associated with the power transformation equipment simulation information knowledge graph through keyword fields, the associated target comprises a body, attributes and a body relation of the power transformation equipment simulation information knowledge graph, for the power transformation equipment simulation information needing to be associated with the power transformation equipment simulation information knowledge graph, fields related to physical equipment and components are extracted to serve as body key words to be queried, attribute words related to the physical equipment and the components are extracted to serve as body attribute key words to be queried, predicate words are extracted, the direction of the extracted predicate words is determined, a combination of alternative key words to be queried is constructed, and graph search is carried out, namely sub-graphs of structures comprising the alternative key words are searched from the knowledge graph of the hidden graph structure.
Further, the power transformation equipment simulation information knowledge graph is used for external power transformation equipment simulation information retrieval by utilizing the query key words and graph structures corresponding to the combination of the query key words, and specifically comprises the following steps:
traversing bodies and attributes of the transformer equipment simulation information knowledge graph, performing semantic measurement calculation on matching values of each body, attribute and the like with the alternative keywords, extracting a plurality of knowledge graph bodies and attributes with the matching values ranked in the front, and screening out a target body and attribute set of a target knowledge graph similar to the alternative keywords;
calculating the relation and the correlation coefficient of a plurality of ontologies in a target ontology attribute set of the target knowledge graph to form a target ontology graph structure with the correlation relation, and simplifying the structural characteristics;
confirming a graph structure of the relation between the alternative keywords in the alternative keyword combination, simplifying structural features, and then establishing an alternative graph structure according to the effective features;
searching the characteristics of the alternative graph in the target graph through the graph structure, and returning a subgraph with the characteristics of the target graph as an alternative graph set;
calculating matching values of the alternative graph and the target graph, sequencing calculation results of the matching values, and giving a query evaluation result;
and according to the retrieval result of the target keyword in the knowledge graph, establishing index labels of the power transformation equipment simulation information and the knowledge graph according to the conformity degree, and establishing a mapping relation between the power transformation equipment simulation information and the power transformation equipment simulation information knowledge graph body, attribute and body relation.
Compared with the prior art, the invention has the following beneficial effects:
the method and the device construct the power transformation equipment simulation information knowledge graph by taking the physical entity of the power transformation equipment as a basis, can realize the quick matching of the power transformation equipment simulation information with different sources and the power transformation equipment simulation information knowledge graph by means of the mapping relation between the information system and the physical system, and construct the index labels of the power transformation equipment simulation information and the power transformation equipment simulation information knowledge graph in different application systems, so that the position of the retrieved information content in the knowledge graph can be quickly positioned in application, and the quick and accurate comparison of the power transformation equipment simulation information and the knowledge graph can be realized.
Drawings
FIG. 1 is a schematic diagram of an example transformer simulation information knowledge graph ontology according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the body relationship and the correlation coefficient of the high-voltage winding of the transformer according to the first embodiment of the invention;
FIG. 3 is an exemplary prescreened target knowledge graph as provided in accordance with an embodiment of the invention;
fig. 4 is an exemplary alternative keyword combination and graph structure thereof according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
in order to realize the rapid and accurate retrieval of the simulation information of the power transformation equipment of the simulation system, the embodiment provides a power transformation simulation information knowledge graph construction and retrieval method based on physical relationship. The method comprises the steps that a power transformation equipment simulation information knowledge map body is constructed on the basis of physical equipment and components of the physical equipment; describing the body attribute of the transformer equipment simulation information knowledge map; and constructing a transformer equipment simulation information knowledge map ontology relation based on the physical entity relation. When the simulation information of the power transformation equipment is retrieved, the simulation information query key words of the power transformation equipment can be extracted, and the simulation information query key words and the graph structures corresponding to the simulation information query key words and the combination of the simulation information query key words are utilized to realize the rapid retrieval of the simulation information of the power transformation equipment of the simulation system in the knowledge spectrogram.
In order to achieve the purpose, the invention adopts the following technical scheme:
the method for constructing and retrieving the power transformation equipment simulation information knowledge graph based on the physical entity relationship comprises the following steps:
(1) Construction of substation equipment simulation information knowledge graph based on physical equipment and component thereof
The simulation information of the power transformation equipment is associated with the actual physical equipment, so that the knowledge graph of the simulation information of the power transformation equipment is constructed on the basis of the physical equipment or the system, and the association of the information system and the physical system can be realized.
The method comprises the steps of constructing a power transformation equipment simulation information body on the basis of physical equipment, a system or a group of components thereof, wherein the association relationship among bodies is the physical relationship among the bodies, and the body attribute corresponds to each application of a physical entity. Most of single power transformation equipment or components thereof contain a plurality of attributes and are associated with a plurality of equipment or components, so that the power transformation equipment simulation information knowledge graph structure contains a plurality of association relations, and the structure is as follows: { ontology, ontology attribute set, ontology incidence relation set }, where the ontology attribute set contains multiple attributes of an ontology, and the ontology incidence relation set contains a plurality of relations between the ontology and other ontologies.
(2) Construction of substation equipment simulation information knowledge graph body based on physical equipment and components thereof
The contents of the simulation information of the power transformation equipment comprise physical equipment and parameter data thereof, switching states, monitoring data, monitoring phenomena, operation control behaviors, defect information, evaluation information, operation and maintenance inspection information, maintenance information and the like. Such information is directed to the physical device, system, or group of components thereof. The equipment related to the simulation information of the power transformation equipment comprises primary equipment, secondary equipment, substation auxiliary equipment and the like, a clear knowledge graph structure of the simulation information of the power transformation equipment is constructed to meet the power production operation habit, a knowledge graph body constructed based on physical equipment or a system is constructed in a layered mode according to substation, interval, equipment and component parts, and a substation level body is equipment or a system with functions oriented to a whole station or multiple intervals; the interval level bodies are arranged at actual physical intervals, and each interval comprises one or more power transformation devices such as primary devices, secondary devices, auxiliary devices and the like; the transformation equipment level body is constructed according to actual transformation equipment and internally contains equipment and components thereof.
The body hierarchy of the simulation information knowledge graph of the power transformation equipment is shown in a table 1:
table 1 substation equipment simulation information knowledge map ontology hierarchy
| Serial number | Ontology classification | Description of the |
| 1 | Substation level | Station level equipment or |
| 2 | Spacer stage | Interval equipment |
| 3 | Power transformation equipment stage | Power transformation equipment |
(3) Establishing transformer equipment simulation information knowledge graph body attributes
The ontology attribute describes the information content of physical entities such as physical devices or group components thereof in various applications. The classification is as follows: the specific attribute items are shown in table 2, wherein the specific attribute items include parameter data, switching states, running data, abnormal phenomena, operation control, defects, evaluation, operation and maintenance inspection, maintenance and the like.
TABLE 2 substation equipment simulation information knowledge graph ontology attributes
(4) Construction of transformer equipment simulation information knowledge graph ontology relation based on physical entity relation
The relationship among the ontologies is based on the physical relationship, and part of the physical association relationship has the expansion extensibility. And constructing a knowledge map spectrogram structure for the power transformation equipment and the components thereof according to the ontology relationship of the knowledge map. According to the information content of the power transformation equipment simulation system, the physical relationship of the power transformation equipment comprises the following steps:
1) The containment relationship. Such as physical devices and physical device components, systems and their component devices;
2) Electrical, communication, etc. Such as lines connected to the transformer and the connected transformer; means for communicating optical fiber connections;
3) Magnetic field, thermal field, etc. Such as two windings of a transformer, which are in magnetic communication, a device group component which is in physical communication in thermal conduction, etc.
4) A spatial proximity relationship. Such as a protection screen cabinet and a protection device arranged on the cabinet;
5) And applying the incidence relation. Such as the primary and standby devices of a system or device, the application functions are consistent.
(5) Extended reasoning for knowledge graph ontology relationships
The physical relation of the power transformation equipment has extension extensibility, and the extension relation between the ontologies which do not directly describe the association relation can be obtained through knowledge reasoning. The following:
1) Inheritance property. If the A body comprises a B body and the B body comprises a C body, the A body comprises the C body, and the A body and the C body can be inferred to be an inclusion relation through the B;
2) And (5) relevance. If the A body is electrically connected with the B body and the B body is electrically connected with the C body in the electrical connection, the relationship of 'electrical connection' can be inferred between the A body and the C body through the B body; the relationships of magnetic field, thermal force field, spatial proximity and the like are all related.
For the extension incidence relation obtained by inheritance and relevance among indirectly associated ontologies, the incidence degree among ontologies cannot be identified when the extension relation among knowledge reasoning ontologies is adopted, so the description of the incidence relation can configure the attribute of the incidence coefficient, and the incidence relation degree among indirectly associated ontologies can be calculated and deduced by adopting the incidence coefficient. If the correlation coefficient is assumed to be a, then:
0≤a≤1
the relevance coefficients describe the closeness of the relationships between the ontologies. When the value is 0, the ontology is unrelated. When the value is 1, it represents a strong association between ontologies.
The ontology relationship can obtain the quantitative index of the association degree through the association coefficient, and the association degree between the ontologies is inferred.
For the extended association relation acquired by inheritance among the indirectly associated ontologies, the indirectly associated ontologies can be assigned according to the proportion of part of ontologies contained in the 'containing relation' in the containing ontology. If two component bodies are included in the inclusion body, each component body may be set to have a correlation coefficient of 0.5.
For the extended association relationship obtained by the association between indirectly associated ontologies, the association coefficient of the A ontology and the B ontology is assumed as a AB The association coefficient of B and C is assumed as a BC The degree of association a between the A and C ontologies AC The following method can be adopted for reasoning:
a AC ＝a AB ×a BC
(6) Extended reasoning for knowledge graph ontology attributes
The attribute information of the partial ontology has a property of an extension relationship, and an attribute of a certain physical equipment group component can be extended as an attribute of an ontology having an inclusion relationship with the physical equipment group component by the following structure. When the A ontology and the B ontology are in inclusion relationship and the A ontology contains the B ontology, the attribute of the B ontology can be related to the attribute of the A ontology by extension. The A ontology attribute names obtained by inference of the extension method are as follows:
a ontology attribute name = B ontology name + B attribute
(7) Substation equipment simulation information knowledge graph retrieval based on graph structure
The simulation information retrieval of the power transformation equipment aims at establishing association between simulation information and a knowledge graph of the simulation information of the power transformation equipment through a keyword field. The associated targets comprise ontologies, attributes, ontologies relations and the like of the power transformation equipment simulation information knowledge graph.
For the power transformation equipment simulation information needing to be constructed in association with the power transformation equipment simulation information knowledge graph, extracting fields related to physical equipment and components as body key words to be queried, extracting attribute words related to the physical equipment and the components as body attribute key words to be queried, extracting predicate words, determining the direction of the extracted predicate words, and constructing alternative key word combinations to be queried.
The application of graph search is a process of searching out a subgraph of a structure consisting of alternative keywords from a knowledge graph containing a hidden graph structure.
The method for retrieving the power transformation equipment simulation information knowledge graph based on the graph structure comprises the following steps:
1) Traversing bodies and attributes of the transformer equipment simulation information knowledge graph, performing semantic measurement calculation on matching values of each body, attribute and the like with the alternative keywords, extracting a plurality of knowledge graph bodies and attributes with the matching values ranked in the front, and screening out a target body and attribute set of a target knowledge graph similar to the alternative keywords;
2) Calculating the relationship and the association coefficient of a plurality of ontologies in a target ontology attribute set of the target knowledge graph to form a target ontology graph structure with association relationship, and simplifying structural features, such as feature substructures of paths, rings, subgraphs, trees and the like;
3) Confirming a graph structure of the relation between the alternative keywords in the alternative keyword combination, simplifying the structural characteristics, and then establishing an alternative graph structure according to the effective characteristics;
4) Searching the characteristics of the alternative graph in the target graph through the graph structure, and returning a subgraph with the characteristics of the target graph as an alternative graph set;
5) And calculating the matching values of the alternative graph and the target graph, sequencing the calculation results of the matching values, and giving a query evaluation result.
6) And according to the retrieval result of the target keyword in the knowledge graph, establishing index labels of the power transformation equipment simulation information and the knowledge graph according to the conformity degree, and establishing a mapping relation between the power transformation equipment simulation information and the power transformation equipment simulation information knowledge graph body, attribute and body relation.
In this embodiment, a 110kV substation is taken as an example to illustrate the body hierarchy of the simulation information knowledge graph of the substation equipment, as shown in table 3:
meter 3110kV transformer substation equipment simulation information knowledge graph body level
The construction method of the structure and the body of the simulation information knowledge graph of the power transformation equipment is described by taking simulation information of the double-winding oil-immersed transformer as an example:
(1) Construction of transformer simulation information knowledge graph
The transformer simulation information knowledge map structure is as follows: { ontology, ontology attribute set, ontology incidence relation set }, where the ontology attribute set contains multiple attributes of an ontology, and the ontology incidence relation set contains a plurality of relations between the ontology and other ontologies.
(2) Establishing transformer simulation information knowledge graph body
A transformer simulation information knowledge graph body is constructed on the basis of physical equipment, a system or a group of components of the physical equipment, the system or the group of components of the system, the transformer simulation information knowledge graph body comprises transformer equipment and a group of components of the transformer equipment, and the body is shown in figure 1.
The method for constructing the body attribute by the simulation information knowledge graph of the double-winding oil-immersed transformer comprises the following steps:
the attributes of the transformer body are divided into the following categories: the specific attribute items are shown in table 4, wherein the specific attribute items include parameter data, switching states, running data, abnormal phenomena, operation control, defects, evaluation, operation and maintenance inspection, maintenance and the like.
TABLE 4 Transformer simulation information knowledge graph ontology Attribute
The method for constructing the body relation explained by the high-voltage winding body of the simulation information knowledge graph of the double-winding oil-immersed transformer comprises the following steps:
the transformer components associated with the transformer "high voltage winding" are as follows:
1) The containment relationship. The winding part comprises: "high voltage winding" and "low voltage winding.
2) Electrical, communication, etc. If the winding and the lead are in direct electrical connection relation; the winding is indirectly and electrically connected with a tap switch, a wire outlet device (sleeve), a lifting seat (sleeve type current transformer) and the like through a lead wire;
3) Magnetic field, thermal field, etc. For example, the high-voltage winding and the low-voltage winding of the transformer are connected through a magnetic field generated by an iron core and the like, and the high-voltage winding of the transformer dissipates heat through oil in heat conduction.
4) A spatial proximity relationship. For example, the winding is wrapped by insulation and is connected with a lead wire;
5) And applying the incidence relation. If "high voltage current" flows in the "high voltage winding", there is a correlation with the "operation data" property of the "transformer".
The body relationship and the correlation coefficient related to the high-voltage winding are shown in fig. 2, a part of the extended correlation relationship is shown in fig. 2, and the correlation coefficient is given according to the body correlation degree. The correlation coefficient assignments are illustrated below:
1) The containment relationship. The "winding" and the "high-voltage winding" are in a "containing relationship". The winding comprises a high-voltage winding and a low-voltage winding, and the correlation coefficients of the high-voltage winding and the low-voltage winding and the winding are both 0.5;
2) And (4) electrical connection relation. The high-voltage winding is electrically and directly connected with the high-voltage lead, and the correlation coefficient of the electrical connection relation of the high-voltage winding and the high-voltage lead is set to be 1;
3) And (4) magnetic field association relation. The high-voltage winding and the low-voltage winding generate magnetic field connection through the iron core, and the correlation coefficients of the high-voltage winding and the low-voltage winding and the iron core are set to be 0.5;
4) And (4) correlation of thermal force fields. The high-voltage winding is soaked in oil, the oil plays a role in insulation and heat conduction, the transformer oil is soaked in equipment such as the high-voltage winding, the low-voltage winding, the iron core and the clamping piece, heat generated by the components is transmitted by the oil, and the correlation coefficient of the high-voltage winding and the oil is set to be 0.5;
5) A spatial proximity relationship. The high-voltage winding is wrapped by insulation and is connected with a high-voltage lead, the insulation covers the winding, the lead and the like, the correlation coefficient of the high-voltage winding and the insulation is set to be 0.8, and the correlation coefficient of the space proximity relation of the high-voltage winding and the high-voltage lead is set to be 1;
6) And applying the incidence relation. High-voltage current flows through the high-voltage winding and is strongly associated with the high-voltage current, and the association coefficient of the high-voltage winding and the high-voltage current is set to be 1; the high-voltage power is calculated by high-voltage and high-voltage current, and the correlation coefficient of the high-voltage winding and the high-voltage is set to be 0.5; the high-voltage electricity degree is calculated by high-voltage and high-voltage current, and the correlation coefficient of the high-voltage winding and the high-voltage electricity degree is set to be 0.5.
Taking the information of' overhigh temperature of the #1 main transformer winding in the simulation information of the power transformation equipment as an example, an index tag of the information and the simulation information knowledge graph of the power transformation equipment is constructed, and the method for retrieving the simulation information knowledge graph of the power transformation equipment based on the graph structure is explained.
(1) Extracting query target key words and combinations thereof:
the simulation information of the power transformation equipment can be decomposed into: "#1", "main transformer", "winding", "temperature", "high". The keywords used as the query candidates are "main transformer", "winding temperature", "high" or "main transformer", "winding", "temperature", "high".
(2) The method for retrieving the power transformation equipment simulation information knowledge graph based on the graph structure comprises the following steps:
1) Traversing the ontology, attributes and ontology relations of the power transformation equipment simulation information knowledge graph, performing semantic metric calculation on matching values of each ontology, attribute and the like and the alternative keywords, extracting a plurality of knowledge graph ontologies and attributes with the matching values ranked in the front, and preliminarily screening an ontology and attribute set of a target knowledge graph similar to the alternative keywords;
the transformer equipment information knowledge map who tentatively screens out the target body in includes: "transformer", "station transformer", "winding", "thermometer";
the preliminarily screened target ontology and attributes in the transformer equipment information knowledge graph are shown in table 5:
TABLE 5 target ontology and attributes obtained by prescreening
Associated ontologies and attributes are outlined in FIG. 3, which identifies a number of ontologies and graph structures between ontologies obtained after a preliminary search.
2) Calculating the relation and the association coefficient of a plurality of ontologies in a target ontology set of the knowledge graph, forming a target keyword graph structure of a target keyword combination, simplifying structural features, such as feature substructures of paths, rings, subgraphs, trees and the like, and then establishing a target graph index according to the effective features; the graph structure of the obtained target ontology and attributes is shown as a 'primarily screened target knowledge graph' in fig. 3.
3) Confirming a graph structure of the relation among the alternative keywords in the alternative keyword combination, simplifying the structural characteristics, and obtaining an alternative keyword combination graph structure by applying a main transformer, a winding, a temperature and a height, wherein the alternative keyword combination graph structure is a 4-level chain structure as shown in an alternative keyword combination and structure in fig. 4; the alternative keyword combination obtained by applying the main transformer, the winding temperature and the high is in a 3-level chain structure;
4) And (3) using alternative keyword combinations obtained by the main transformer, the winding, the temperature and the height, searching the characteristics of the 4-level chain structure of the alternative graph in the primarily screened target knowledge graph, and returning a subgraph with the characteristics of the target graph as an alternative graph set. Only 1 alternative figure is shown as a structure (1), as shown in figure 3;
5) And (3) using alternative keyword combinations obtained by the main transformer, the winding temperature and the height, searching the characteristics of the 3-level chain structure of the alternative graph in the primarily screened target knowledge graph, and returning a subgraph with the characteristics of the target graph as an alternative graph set. Only 1 alternative figure is shown as structure (2), as shown in figure 3;
6) According to the method provided by the invention, the structure 1 and the structure 2 are both used as retrieval results meeting requirements in the knowledge graph;
7) According to the extended reasoning method of the knowledge graph ontology attribute, in the transformer ontology, the winding is a transformer equipment group component, so that the temperature attribute of the winding ontology of the transformer ontology can be further inferred as the transformer attribute, as shown in the following:
"transformer" attribute name = "winding" + "temperature" = "winding temperature"
Therefore, in the power transformation equipment simulation information knowledge graph, the alternative graph structure (1) and the alternative graph structure (2) both comprise all elements of alternative keywords;
8) The search results given by way of example are alternative structure 1 and alternative structure 2. Therefore, two groups of comparison labels, namely a knowledge graph body corresponding to ' #1 main transformer winding temperature is high ' and attributes of the knowledge graph body are ' transformer ' -winding ' -temperature ' -high ' and ' transformer ' -winding-temperature ' -high ', can be quickly established.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, it is possible to make various improvements and modifications without departing from the technical principle of the present invention, and those improvements and modifications should be considered as the protection scope of the present invention.
Claims (9)
1. A power transformation simulation information knowledge graph construction and retrieval method based on physical relation is characterized by comprising the following steps:
acquiring simulation information of the power transformation equipment;
constructing a power transformation equipment simulation information knowledge graph based on physical equipment, a system or a group of components thereof;
building a power transformation equipment simulation information knowledge map body based on physical equipment or a system on the basis of the power transformation equipment simulation information knowledge map;
establishing the body attribute of the simulation information knowledge map of the power transformation equipment on the basis of the body of the simulation information knowledge map, and establishing the body relation of the simulation information knowledge map of the power transformation equipment on the basis of the physical entity relation;
carrying out extension reasoning on the relation and the attribute of the knowledge graph ontology;
the power transformation equipment simulation information knowledge graph is used for external power transformation equipment simulation information retrieval by utilizing the query key words and the graph structures corresponding to the combination of the query key words.
2. The physical relationship-based power transformation simulation information knowledge graph construction and retrieval method according to claim 1, wherein the structure of the power transformation equipment simulation information knowledge graph comprises a plurality of attributes and a plurality of incidence relationships, and the structure is as follows: { ontology, ontology attribute set, ontology incidence relation set }, where the ontology attribute set includes multiple attributes of an ontology, the ontology incidence relation set includes a plurality of relations between the ontology and other ontologies, the incidence relation between ontologies is a physical relation between ontologies, and the ontology attributes correspond to applications of physical entities.
3. The method for constructing and retrieving the power transformation simulation information knowledge graph based on the physical relationship as claimed in claim 1, wherein the step of constructing the power transformation device simulation information knowledge graph ontology based on the physical device or the system comprises: the knowledge graph body is constructed according to a transformer substation, intervals, equipment and component parts in a layered mode, wherein the transformer substation level body is a function-oriented total station or multi-interval equipment or system, the interval level body is arranged according to actual physical intervals, one or more transformer equipment are arranged in each interval and comprise primary equipment, secondary equipment and auxiliary equipment, and the transformer equipment level body is constructed according to actual transformer equipment and internally contains the equipment and the component parts thereof.
4. The power transformation simulation information knowledge graph construction and retrieval method based on the physical relationship as claimed in claim 1, wherein the knowledge graph ontology attribute describes information content of a physical entity in various applications, and is divided into the following categories: parameter data, commissioning and decommissioning states, operational data, abnormal phenomena, operational control, defects, evaluation, operation and maintenance inspection and overhaul, wherein the physical entity comprises physical equipment or components thereof.
5. The physical relationship-based power transformation simulation information knowledge graph construction and retrieval method according to claim 1, wherein the power transformation equipment simulation information knowledge graph ontology relationship comprises:
the inclusion relationship: physical equipment and physical equipment component parts, systems and component equipment thereof;
electrical and communication connection relation: a wire and communication connection to the physical device and the physical device component;
the magnetic field and the thermal force field are related: magnetic field connection between the physical equipment and the component parts of the physical equipment, or physical connection exists between the component parts of the equipment group in heat conduction;
spatial proximity relations: the physical equipment and the physical equipment component parts are close to and contact with each other in space;
applying the incidence relation: the application functions of the physical equipment and the component parts of the physical equipment are consistent or have a causal relationship and an interactive relationship.
6. The power transformation simulation information knowledge graph construction and retrieval method based on the physical relationship as claimed in claim 1, wherein the expanding extension reasoning is carried out on the ontology relationship of the knowledge graph, and comprises the following steps: configuring the attribute of the association coefficient to describe the association relationship, wherein the association coefficient can calculate the association relationship degree between the bodies indirectly associated by inference, and the method comprises the following steps:
0≤a≤1
wherein, a is a correlation coefficient used for describing the degree of closeness of the relationship between the ontologies, and when the value is 0, the ontology is not correlated; when the value is 1, the strong association between the ontologies is represented;
for an extended association relation acquired through inheritance among indirectly associated ontologies, assigning values of the indirectly associated ontologies as association coefficients according to the proportion of part of ontologies contained in the 'inclusion relation' in the inclusion ontology;
for the extended association relationship obtained by the association between indirectly associated ontologies, the association coefficient of the A ontology and the B ontology is assumed as a AB The correlation coefficient of B and C is assumed to be a BC The degree of association a between the A and C ontologies AC Comprises the following steps:
a AC ＝a AB ×a BC
7. the power transformation simulation information knowledge graph construction and retrieval method based on the physical relationship as claimed in claim 1, wherein the expanding extension reasoning is carried out on the body attribute of the knowledge graph, and the method comprises the following steps: and when the A ontology and the B ontology are in an inclusion relationship and the A ontology contains the B ontology, the attribute of the B ontology is related to the attribute of the A ontology by the extension, and the attribute name of the A ontology obtained by inference of the extension method is as follows:
a ontology attribute name = B ontology name + B attribute
8. The power transformation simulation information knowledge graph construction and retrieval method based on physical relation as claimed in claim 1, wherein the retrieval target of the power transformation equipment simulation information is to establish the relation between the simulation information and the power transformation equipment simulation information knowledge graph through keyword fields, the relation target comprises the ontology, attributes and ontology relation of the power transformation equipment simulation information knowledge graph, for the power transformation equipment simulation information needing to establish the relation with the power transformation equipment simulation information knowledge graph, fields related to physical equipment and components are extracted as ontology keywords to be queried, attribute words related to the physical equipment and the components are extracted as ontology attribute keywords to be queried, and the predicate words are extracted, the direction of the extracted predicate words is determined, the combination of the queried alternative keywords is constructed, and graph search is applied, namely, a sub graph containing a structure consisting of the alternative keywords is searched from the knowledge graph with a hidden graph structure.
9. The physical relationship-based power transformation simulation information knowledge graph construction and retrieval method as claimed in claim 1, wherein the power transformation equipment simulation information knowledge graph is used for external power transformation equipment simulation information retrieval by using query keywords and graph structures corresponding to combinations thereof, and specifically comprises:
traversing the ontology and the attribute of the simulation information knowledge graph of the power transformation equipment, performing semantic measurement calculation on the matching value of each ontology, attribute and the like and the alternative keyword, extracting a plurality of knowledge graph ontologies and attributes with the matching values ranked in the front, and screening out a target ontology and an attribute set of a target knowledge graph similar to the alternative keyword;
calculating the relation and the correlation coefficient of a plurality of ontologies in a target ontology attribute set of the target knowledge graph to form a target ontology graph structure with the correlation relation, and simplifying the structural characteristics;
confirming a graph structure of the relation between the alternative keywords in the alternative keyword combination, simplifying structural features, and then establishing an alternative graph structure according to the effective features;
searching the characteristics of the alternative graph in the target graph through the graph structure, and returning a subgraph with the characteristics of the target graph as an alternative graph set;
calculating matching values of the alternative graph and the target graph, sequencing calculation results of the matching values, and giving a query evaluation result;
and according to the retrieval result of the target keyword in the knowledge graph, establishing index labels of the power transformation equipment simulation information and the knowledge graph according to the conformity degree, and establishing a mapping relation between the power transformation equipment simulation information and the power transformation equipment simulation information knowledge graph body, attribute and body relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210954229.3A CN115329145A (en) | 2022-08-10 | 2022-08-10 | Physical relationship-based power transformation simulation information knowledge graph construction and retrieval method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210954229.3A CN115329145A (en) | 2022-08-10 | 2022-08-10 | Physical relationship-based power transformation simulation information knowledge graph construction and retrieval method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115329145A true CN115329145A (en) | 2022-11-11 |
Family
ID=83921407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210954229.3A Pending CN115329145A (en) | 2022-08-10 | 2022-08-10 | Physical relationship-based power transformation simulation information knowledge graph construction and retrieval method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115329145A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115828622A (en) * | 2022-12-21 | 2023-03-21 | 中国电子科技集团公司信息科学研究院 | Radio frequency transceiving component model management method and device, electronic equipment and medium |
-
2022
- 2022-08-10 CN CN202210954229.3A patent/CN115329145A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115828622A (en) * | 2022-12-21 | 2023-03-21 | 中国电子科技集团公司信息科学研究院 | Radio frequency transceiving component model management method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tang et al. | Enhancement of power equipment management using knowledge graph | |
| CN113553420B (en) | Power grid fault processing rule recommendation method and system based on knowledge graph | |
| CN101930481B (en) | Method used for generating CIM model describing power grid change in designated time slot and system thereof | |
| Perçuku et al. | Modeling and processing big data of power transmission grid substation using Neo4j | |
| CN102403718B (en) | Generating method for power grid topological relationship based on Arcgis | |
| CN114138982B (en) | Knowledge graph construction method for fault diagnosis of dry-type transformer | |
| CN117273133A (en) | Construction method of multi-source heterogeneous data knowledge graph of power distribution network | |
| CN111931318B (en) | Power supply path analysis method and system based on graph calculation | |
| Yun et al. | Research on intelligent fault diagnosis of power acquisition based on knowledge graph | |
| Liu et al. | CNC machine tool fault diagnosis integrated rescheduling approach supported by digital twin-driven interaction and cooperation framework | |
| CN112383044B (en) | Power grid model comparison method and device based on hierarchical topological structure | |
| CN112685570A (en) | Multi-label graph-based power grid network frame knowledge graph construction method | |
| CN115329145A (en) | Physical relationship-based power transformation simulation information knowledge graph construction and retrieval method | |
| Heluany et al. | A review on digital twins for power generation and distribution | |
| Wu et al. | An intelligent search engine based on knowledge graph for power equipment management | |
| CN117194501B (en) | DCS trend measurement point jump logic configuration method, system, equipment and medium | |
| CN112115207B (en) | Ontology design method of knowledge graph of power equipment | |
| Jiang et al. | Construction of substation engineering design knowledge graph based on “ontology seven-step method” | |
| Nemirovski et al. | Ontological representation of knowledge related to building energy-efficiency | |
| WO2019140553A1 (en) | Method and device for determining health index of power distribution system and computer storage medium | |
| CN117573673A (en) | Regional power grid data management method, system, equipment and medium | |
| CN112529217A (en) | Power equipment information query method, system, device, equipment and storage medium | |
| Guo et al. | Big data processing and analysis platform for condition monitoring of electric power system | |
| Rocha et al. | Fast and flexible design of optimal metering systems for power systems monitoring | |
| Casagrande et al. | Semiautomatic system domain data analysis: A smart grid feasibility case study |
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 |