CN116821423A - Intelligent analysis and knowledge type fault processing auxiliary system and method for power distribution network - Google Patents
Intelligent analysis and knowledge type fault processing auxiliary system and method for power distribution network Download PDFInfo
- Publication number
- CN116821423A CN116821423A CN202310663567.6A CN202310663567A CN116821423A CN 116821423 A CN116821423 A CN 116821423A CN 202310663567 A CN202310663567 A CN 202310663567A CN 116821423 A CN116821423 A CN 116821423A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- fault
- data
- layer
- distribution network
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 47
- 238000012545 processing Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 title claims abstract description 26
- 238000010276 construction Methods 0.000 claims abstract description 38
- 239000010410 layer Substances 0.000 claims description 128
- 238000004364 calculation method Methods 0.000 claims description 45
- 238000000605 extraction Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000004927 fusion Effects 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 13
- 238000005065 mining Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims description 10
- 238000002372 labelling Methods 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000007418 data mining Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 239000012792 core layer Substances 0.000 claims description 4
- 238000013499 data model Methods 0.000 claims description 4
- 238000011161 development Methods 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 12
- 230000008859 change Effects 0.000 abstract description 6
- 230000008901 benefit Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 7
- 238000001228 spectrum Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000000295 complement effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- 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
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- 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
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Probability & Statistics with Applications (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an intelligent analysis and knowledge type fault processing auxiliary system and method for a power distribution network, which have the advantage of auxiliary fault diagnosis. The fault diagnosis of the traditional power grid depends on the working experience and professional knowledge of a dispatcher, the dispatcher is required to analyze the state and parameter change information of the power grid after the fault in real time, the reason of the accident is inferred, the accident characteristics of various expected faults are recorded in detail by a map construction layer and a map application layer, the knowledge map is searched and inferred according to the change condition of the operation mode of the power grid after the accident, the knowledge-driven fault diagnosis auxiliary decision is realized, the experience dependence on the dispatcher is reduced, in addition, the result of each fault diagnosis is used as new knowledge to update and perfect the knowledge map, and the knowledge map can provide more accurate, comprehensive and dynamic decision auxiliary support.
Description
Technical Field
The application relates to the technical field of power distribution networks, in particular to an intelligent analysis and knowledge type fault processing auxiliary system and method for a power distribution network.
Background
With the continuous development of the electric power Internet of things, large electric power data meet new opportunities. The distribution network is used as a final link closely connected with the user terminal, and is a key for ensuring the power supply quality. The novel challenges of diversity, complexity and islanding of data and high task scene combination degree are faced, the cognitive intelligent level of the power distribution network data perception is improved, and the fault processing capability is standardized, so that the method has important significance for dispatching work.
The scheduling decision knowledge exists in text files, databases and expert experiences of scheduling regulations, and when a fault is processed, a dispatcher needs to rely on a great deal of expertise to support, history and real-time power grid situation awareness, and make an optimal decision in a short time according to situation changes. Aiming at the requirements of complex scheduling knowledge and high real-time scheduling decision, how to construct a knowledge graph containing scheduling knowledge, fault processing knowledge and business process knowledge by using power grid scheduling rules, fault plans and manual experience knowledge, construct a knowledge representation formed by a power grid topological structure, and associate the fault plans and fault processing cases in an event cluster form, thereby playing an important role in the decision of the power distribution network. Therefore, the application provides an intelligent analysis and knowledge type fault processing auxiliary system and method for a power distribution network.
Disclosure of Invention
The application aims to overcome the defects of complex scheduling knowledge and high scheduling decision instantaneity in the prior art and provide an intelligent analysis and knowledge type fault processing auxiliary system and method for a power distribution network.
In order to achieve the above purpose, the present application provides the following technical solutions: the intelligent analysis and knowledge type fault processing auxiliary system for the power distribution network comprises a data acquisition layer, a map construction layer, a knowledge calculation layer and a map application layer;
the data acquisition layer is used for structured data analysis, semi/unstructured data labeling and third party cooperative data analysis, the data acquisition layer comprises scheduling rules, safety rules and expert experience related data, the data acquisition layer is connected with a resource layer and is used for acquiring information collected by a monitoring terminal matched in the resource layer at the bottommost layer, and particularly acquiring an entity, an event and a knowledge graph, wherein the entity comprises related contents of operation professional terms, accident handling professional terms and a power grid topological graph structure, and the event comprises related contents of a fault handling general principle, fault handling expert experience and fault handling business logic;
the map construction layer comprises an entity identification model, the entity identification model is connected with the data acquisition layer, the entity identification model comprises a BERT layer, a Word2Vec Word embedding layer, a bidirectional long and short term memory network layer BiLSTM, a characteristic serial layer connection and a full connection layer Dense, the map construction layer provides data which accords with RDF data files based on CIM model rules or CIM-XML model data files, and is used for carrying out natural language processing, knowledge extraction, knowledge fusion and knowledge processing work on a core layer of a knowledge map application framework, and carrying out standardization processing on entity, concept, relation and event data stored in a map database, wherein the knowledge map construction comprises data cleaning, user load, knowledge extraction, knowledge fusion, knowledge processing, manual verification and knowledge updating;
the knowledge calculation layer comprises a processor, is connected with the entity identification model and is used for general algorithm model calculation of the entity identification model data integration, such as representation learning, relationship reasoning, attribute reasoning, event reasoning, path calculation and comparison sequencing, and the knowledge calculation layer comprises data storage, data processing, reasoning calculation, wherein the data storage comprises the requirements of a multi-layer multi-library principle, authority partition management, sub-graph access control and the like, and particularly, the data logic association mining is carried out by a basic data source, operation data and fault information through a knowledge graph, and then reasoning analysis and calculation are carried out;
the map application layer provides an interface for the knowledge calculation layer through a data form of CIS service, outputs calculation processing data of the knowledge calculation layer, is used for providing intelligent searching, intelligent question-answering, intelligent recommending, auxiliary decision making, knowledge management and third party application, is used as a final functional module produced by a power domain knowledge map application architecture to be in butt joint with an actual application scene, and is used for carrying out data logic association mining by combining with a service scene, and analyzing and calculating by key information matching, topology path searching and data mining statistical methods.
Preferably, the data layer construction of the map construction layer is that a label attribute map data model based on Neo4j is composed of two types of data of Entity Node and relation Relationship, wherein the Node stores Entity information, the relation links the Entity, and the Node and the attribute and label of the relation are stored in a key value pair mode.
Preferably, the general algorithm model constructed by the knowledge graph of the knowledge calculation layer is a TF-IDF algorithm, specifically, the power distribution network fault classification is taken as an entity, after forming a plurality of groups by fault occurrence reasons, fault attributes, fault phenomena, a fault processing method and related expert experiences, the TF-IDF algorithm is adopted to screen out the whole file in the local textWords with concentrated distribution and high frequencytf ij The formula is as follows;
；
wherein ,the representation being wordstf ij In File->The number of occurrences of>Then is file->The sum of the times of occurrence of all words in the list;
；
where D is the total number of documents in the knowledge-graph corpus,representing comprising words->I.e. ni, j not equal to 0;
the TF-IDF value formula for calculating the specified word is as follows:
；
each word in each sentenceTF-IDF values were calculated separately.
Preferably, the data acquisition layer comprises a knowledge extraction module, a knowledge fusion module and a knowledge updating module, wherein the knowledge extraction module acquires entities, relationships among the entities and structured knowledge of attributes from the semi/unstructured data through a knowledge extraction method under the guidance of a knowledge organization architecture of a mode layer; the knowledge fusion module is used for carrying out entity disambiguation and coreference resolution processing based on the entity information data obtained by the knowledge extraction module; the knowledge updating module evaluates the quality and timeliness of the corresponding knowledge in the process of applying the knowledge graph, and updates and corrects the knowledge by combining the development of the knowledge.
Preferably, the data in the data acquisition layer refers to importing, reading and structuralized storing of the excel, csv, json, xml file, and the data labeling refers to labeling of concepts, entities, relations and attribute semantic information of the text data.
Preferably, the map construction layer is created by combining top-down and bottom-up, and specifically, the self-oriented lower algorithm or the self-bottom-up algorithm correspondingly extracts corresponding keywords for fusion, screening, correction and classification, and classifies the keywords into operation terms, accident handling terms, operation terms and fault terms, and performs term complementation by adopting a screening method in combination with data materials, and content complementation for professional term interpretation and related scheduling regulations and safety regulations is completed through search matching.
The method for the intelligent analysis and knowledge type fault processing auxiliary system of the power distribution network comprises the following steps of:
step 1: counting the existing operation rules, treatment plans and regulation rules of the power grid, associating the operation rules, treatment plans and regulation rules required after the power grid fails, and respectively carrying out one-to-one correspondence on the existing operation rules, treatment plans and regulation rules of the power grid and the operation rules, treatment plans and regulation rules required after the power grid fails to form a structured network;
step 2: constructing a data acquisition layer and a map construction layer according to the power distribution network fault information knowledge, unifying a physical model and a knowledge model required in a power distribution network fault scheduling decision, and constructing a multi-source data relationship link through the map construction layer to finish the construction of the data layer and the knowledge map layer;
step 3: constructing a knowledge calculation layer according to a power distribution network fault information knowledge reasoning technology, carrying out data logic association mining by a basic data source, operation data and fault information through a knowledge graph, and finally carrying out reasoning analysis and calculation;
step 4: when the dispatching faults occur, the fault information is transmitted to a control personnel monitoring system in real time, the regional fault plan is automatically recommended according to the position of the faults, and relevant fault cases are matched;
step 5: fitting human thinking and working modes, matching real-time fault information comprising fault equipment, places, states and phenomena with fault phenomena and fault cases in a knowledge graph of a joint memory network, forming initial constraints according to the fault information from three aspects of the same equipment fault case cluster, the same equipment fault case cluster and the same equipment fault processing principle, establishing entity links, associating fault case clusters and fault processing knowledge based on subgraph retrieval and paths, counting historical fault information, and realizing knowledge searching, calculating and recommending through path recall;
step 6: and (3) performing network reconstruction on a non-fault power-losing area after fault location is finished, and performing man-machine interaction scene with small network loss, more non-fault load recovery and less switching times by referring to fault recommendation information under the condition that power balance, capacity and voltage constraint and power distribution network connectivity and radial constraint are met, so that the method is suitable for multi-objective optimization.
A computer-readable storage medium storing instructions, characterized in that: and when the instructions run on the computer, the instructions enable the computer to apply the intelligent analysis and knowledge-based fault handling auxiliary system of the power distribution network or a method for executing the intelligent analysis and knowledge-based fault handling auxiliary system of the power distribution network.
Compared with the prior art, the application has the beneficial effects that:
the application has the advantage of intelligent information retrieval, and the traditional fault handling information retrieval mode is completed by decomposing and matching the keywords, so that semantic information of the problem can not be deeply understood and processed. The knowledge graph represents fault handling knowledge in a graph form, accurately represents the association relation between the knowledge, analyzes keywords queried by a user by means of the knowledge graph, maps the keywords to specific concepts or entities, and can return comprehensive and accurate search results based on semantic networks rich in the knowledge graph; the application has the advantage of auxiliary fault diagnosis, the fault diagnosis of the traditional power grid depends on the working experience and professional knowledge of a dispatcher, the dispatcher needs to analyze the state and parameter change information of the power grid after the fault in real time, the reason of accident occurrence is inferred, the power grid knowledge graph records the accident characteristics of various expected faults in detail, the knowledge graph is searched and inferred according to the change condition of the power grid operation mode after the accident occurs, the knowledge driven fault diagnosis auxiliary decision is realized, the experience dependence on the dispatcher is reduced, in addition, the result of each fault diagnosis is used as new knowledge to update and perfect the knowledge graph, and the knowledge graph can provide more accurate, comprehensive and dynamic decision auxiliary support.
Drawings
FIG. 1 is a schematic diagram of an intelligent analysis and knowledge type fault handling auxiliary system for a power distribution network;
FIG. 2 is a construction flow chart of the map construction layer of the present application;
FIG. 3 is a data structure diagram of the intelligent analysis and knowledge type fault handling auxiliary system for the power distribution network of the present application;
FIG. 4 is a diagram of a decision-making framework of the intelligent analysis and knowledge type fault handling auxiliary system for the power distribution network;
FIG. 5 is a flow chart and exemplary diagram of a dispatch assisted question-answering process of the present application.
Reference numerals in the drawings: 10. a data acquisition layer; 20. a map construction layer; 30. a knowledge calculation layer; 40. and (5) a map application layer.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1 and 3, the present application provides a technical solution: the intelligent analysis and knowledge type fault processing auxiliary system for the power distribution network comprises a data acquisition layer 10, a map construction layer 20, a knowledge calculation layer 30 and a map application layer 40. The data acquisition layer 10 is responsible for structured data analysis, semi/unstructured data labeling and third party collaborative data analysis, and the data acquisition layer 10 comprises scheduling rules, security rules and expert experience related data, in particular, acquires entities, events and knowledge maps, wherein the entities comprise operation and operation terms, accident handling terms and related contents of a power grid topological graph structure, the events comprise related contents of a fault handling general principle, fault handling expert experience and fault handling business logic, the data in the data acquisition layer 10 generally refers to importing, reading and structurally storing excel, csv, json, xml files, and the data labeling refers to labeling work of concepts, entities, relations and attribute semantic information on text data;
the construction of the data acquisition layer 10 of the present embodiment includes the following three steps:
step (1): the knowledge extraction module is used for acquiring entity, relationship among entities, attribute and other structured knowledge from unstructured data through a series of knowledge extraction methods under the guidance of a mode layer knowledge organization architecture by the information collected by the monitoring terminals matched in the lowest resource layer, wherein the data acquisition layer 10 is connected with the resource layer;
step (2): the knowledge fusion module is used for carrying out entity disambiguation and coreference resolution processing on the entity obtained by the knowledge extraction module, wherein the map construction layer 20 comprises an entity identification model, the entity identification model is connected with the data acquisition layer 10, the entity identification model comprises a BERT layer, a Word2Vec Word embedding layer, a bidirectional long and short time memory network layer BiLSTM, a feature serial layer connection layer and a full connection layer Dense, and the map construction layer 20 is used for carrying out natural language processing, knowledge extraction, knowledge fusion and knowledge processing on a core layer of a knowledge map application framework and carrying out standardization processing on entity, concept, relationship and event data stored in a map database so as to realize many-to-many relationship management; the knowledge graph construction comprises data cleaning, user load, knowledge extraction, knowledge fusion, knowledge processing, manual verification and knowledge updating; the knowledge calculation layer 30 is connected with the entity recognition model through a processor of the knowledge calculation layer 30 and is used for general algorithm model calculation of expression learning, relation reasoning, attribute reasoning, event reasoning, path calculation and comparison sequencing of entity recognition model data integration, the knowledge calculation layer 30 comprises data storage and data processing and reasoning calculation, the data storage comprises the requirements of multi-layer multi-library principle, authority partition management, sub-graph access control and the like, and specifically, the data logic association mining is carried out through a knowledge graph by a basic data source, operation data and fault information, and then reasoning analysis and calculation are carried out; in addition, the spectrum application layer 40 provides an interface for the knowledge calculation layer 30 through a data form of CIS service, and is used for providing intelligent searching, intelligent question-answering, intelligent recommendation, auxiliary decision making, knowledge management and third party application, and the final function module produced by the knowledge spectrum application architecture is used for interfacing with an actual application scene, and the spectrum application layer 40 is combined with a service scene for carrying out data logic association mining, and key information matching, topology path searching and data mining statistical method analysis and calculation;
step (3): and the knowledge updating module is used for evaluating the quality and timeliness of the knowledge in the process of applying the knowledge graph and updating and correcting the knowledge by combining the development of the knowledge.
The graph construction layer 20 of the embodiment serves as a core layer of a knowledge graph application architecture, and carries natural language processing, knowledge extraction, knowledge fusion and knowledge processing capabilities, and meanwhile, the specification requires that a graph database is adopted to store entities, concepts, relations and events and realize many-to-many relation management, wherein the knowledge graph construction comprises data cleaning, user load, knowledge extraction, knowledge fusion, knowledge processing, manual verification and knowledge updating;
the knowledge calculation layer 30 of the present embodiment is responsible for integrating a general algorithm model for expression learning, relationship reasoning, attribute reasoning, event reasoning, path calculation, and comparison ordering, and the knowledge calculation layer 30 includes data storage and data processing and reasoning calculation, where the data storage includes requirements of multi-layer multi-library principle, authority partition management, sub-graph access control, and the like, specifically, the data logic association mining is performed by the basic data source, operation data and fault information through the knowledge graph, and then the reasoning analysis and calculation are performed.
Referring to fig. 2, further preferably, the map construction layer 20 is created by combining top-down and bottom-up, in which the corresponding keywords extracted by the self-oriented algorithm or the self-oriented algorithm are fused, screened, corrected and classified into operation terms, accident handling terms, operation terms and fault terms, and the data materials are combined to complete term complement by adopting a screening method, and the interpretation of the technical terms and the content complement of the relevant scheduling procedure and safety procedure are completed by searching and matching.
The data layer construction of the map construction layer 20 of this embodiment involves two major categories of a Neo4j attribute-map-oriented storage system or a gStore RDF map-oriented storage system, adopts relational databases to manage multimedia data such as files, videos, images, audios and the like and one-to-many relationships, and connects each other through id_name in HTML elements, is based on a Neo4j tag attribute map data model, and is composed of two types of data of nodes (nodes) and relationships (relationships), node storage entity (entity) information, relationship link entity, node and relationship attributes (properties) and tags (labels) are stored in a key-value pair (key-value) form;
Entity Node:Label{Property1, Property2•••}；
Relationship start node-[rel:Property3]-end node；
wherein: label, property1, property2 are entity labels and multiple attribute values, the entity labels are used for distinguishing different types of nodes, each entity can contain one or more labels, zero or more attributes; the start node, end node, rel, property3, and entity-entity relationship have directionality.
The general algorithm model constructed by the knowledge graph of the knowledge calculation layer 30 in this embodiment is a TF-IDF algorithm, specifically, the power distribution network fault classification is taken as an entity, after the multiple groups are formed by the fault occurrence cause, the fault attribute, the fault phenomenon, the fault processing method and the experience of the related expert, the TF-IDF algorithm is further adopted to screen out the whole file in the local textWords with concentrated distribution and high frequencytf ij The formula is as follows;
；
wherein ,the representation being wordstf ij In File->The number of occurrences of>Then is file->The sum of the times of occurrence of all words in the list;
；
where D is the total number of documents in the knowledge-graph corpus,representing comprising words->I.e. ni, j not equal to 0;
the formula for calculating the TF-IDF value of a certain word is as follows:
；
each word in each sentenceTF-IDF values were calculated separately.
Referring to fig. 3 and 4, the spectrum application layer 40 of the present embodiment is responsible for providing intelligent searching, intelligent question-answering, intelligent recommendation, auxiliary decision making, knowledge management and third party application, and is used as a final functional module generated by the power domain knowledge spectrum application architecture to interface with an actual application scene, and the spectrum application layer 40 performs data logic association mining in combination with a service scene, so as to analyze and calculate by using key information matching, topology path searching and data mining statistical methods.
Referring to fig. 5, the embodiment further provides a method for intelligent analysis and knowledge type fault processing auxiliary system of a power distribution network, which includes the following steps:
step 1: the method comprises the steps of counting the contents of the existing operation rules, treatment plans, regulation rules and the like of a power grid, associating the contents of the operation rules, the treatment plans, the regulation rules and the like required after the power grid fails to form a structured network in a one-to-one correspondence mode, wherein when the power grid fails, different faults correspond to different fault treatment schemes, and relate to different power equipment, transformers, connection points and the like, different terms, different fault plans and different fault records. Therefore, the fault condition is corresponding to the corresponding module according to the contents of the operation rules, the treatment plans, the regulation rules and the like regulated by the power grid;
the structure adopts a label attribute graph data model based on Neo4j, and macroscopically consists of two types of data, namely node and relation, namely node storage entity (entity), relation link entity, attribute (property) of the node and the relation and label (label) which are stored in a key-value pair form.
Entity Node:Label{Property1, Property2•••}；
Relationship start node-[rel:Property3]-end node；
Wherein: label, property1, property2 are entity labels and multiple attribute values, the labels are used for distinguishing different types of nodes, each entity can contain one or multiple labels, zero or multiple attributes; start node, end node, rel, property3, and entity-entity relationship, wherein the start node represents a head entity and a tail entity, rel represents a relationship name, property3 represents a relationship attribute, and the relationship has directivity;
step 2: the method comprises the steps of constructing a data acquisition layer 10 and a map construction layer 20 according to power distribution network fault information knowledge, unifying a physical model and a knowledge model required in power distribution network fault scheduling decisions by the data acquisition layer 10, establishing relation links among multi-source data through the map construction layer 20, wherein the data acquisition layer 10 comprises related data such as scheduling regulations, safety regulations, expert experiences and the like, and the knowledge map layer comprises construction of entities, events and knowledge maps, wherein the entities comprise related contents such as operation and running professional terms, accident handling professional terms, a power grid topological graph structure and the like. The event comprises related contents such as a general fault processing principle, a fault processing expert experience, a fault processing business logic and the like, and the knowledge graph construction comprises the contents such as data cleaning, user load, knowledge extraction, knowledge fusion, knowledge processing, manual verification, knowledge updating and the like;
step 3: constructing a knowledge calculation layer 30 according to a power distribution network fault information knowledge reasoning technology, carrying out data logic association mining by a basic data source, operation data and fault information through a knowledge graph, finally carrying out reasoning analysis and calculation, carrying out data logic association mining by the knowledge reasoning layer in combination with a service scene, carrying out analysis and calculation by methods of key information matching, topology path searching, data mining statistics and the like, and realizing power knowledge application exploration in a refined scene;
step 4: when the dispatching faults occur, the fault information is transmitted to a control personnel monitoring system in real time, and the regional fault plans can be automatically recommended according to the occurrence positions of the faults and related fault cases are matched;
step 5: fitting human thinking and working modes, matching real-time fault information including fault equipment, places, states, phenomena, fault cases and the like in a knowledge graph of a joint memory network, forming initial constraints according to the fault information from three aspects of a fault case cluster of the same equipment, a fault case cluster of the same equipment and a fault processing principle of the same equipment, establishing entity links, associating fault case clusters and fault processing knowledge based on subgraph retrieval and paths, counting historical fault information, and further realizing knowledge searching, calculating and recommending through path recall;
forming initial constraint according to fault information, establishing entity link, based on sub-graph search and path association fault case cluster and fault processing knowledge, counting historical fault information, further realizing knowledge search, calculation and recommendation through path recall, setting m types of faults in the same type of equipment E (E1, E2, the first-class, the second-class, the third-class, the fourth-class) coexist, setting all possible fault phenomenon sets as A, setting m types of faults to be corresponding to experienced fault phenomenon subsets Am { a1, a2, the first-class, the third-class, the fourth-class, the fifth-class and the fourth-class. When the equipment e1 fails, on the basis of constructing a failure case function module, the automatic generation, storage and display of a case event cluster can be realized, the Neo4j front end interface can provide visual display of the failure case cluster, more failure information is provided, and the discovery of weak points of a power grid is facilitated;
step 6: and when fault positioning is completed, network reconstruction is performed on a non-fault power-losing area after fault isolation is implemented, and under the condition that the constraints of power balance, capacity and voltage, power distribution network connectivity, radial and the like are met, fault recommendation information is referred to, so that man-machine interaction scenes including small network loss, more non-fault load recovery, less switching times and the like are completed, and the multi-objective optimization is adapted.
In summary, the application has the advantage of intelligent information retrieval, and the traditional fault handling information retrieval mode is completed by decomposing and matching keywords, so that semantic information of the problem cannot be deeply understood and processed. The knowledge graph represents fault handling knowledge in a graph form, accurately represents the association relation between the knowledge, analyzes keywords queried by a user by means of the knowledge graph, maps the keywords to specific concepts or entities, and can return comprehensive and accurate search results based on semantic networks rich in the knowledge graph; the application has the advantage of assisting fault diagnosis, the fault diagnosis of the traditional power grid depends on the working experience and professional knowledge of a dispatcher, the dispatcher is required to analyze the state and parameter change information of the power grid after the fault in real time, the reason of accident occurrence is inferred, the power grid fault disposal knowledge graph records the accident characteristics of various expected faults in detail, the knowledge graph is searched and inferred according to the change condition of the power grid operation mode after the accident occurs, the knowledge driven fault diagnosis assisting decision is realized, the experience dependence on the dispatcher is reduced, in addition, the result of each fault diagnosis is used as new knowledge to update and perfect the knowledge graph, and the knowledge graph can provide more accurate, comprehensive and dynamic decision assisting support.
The nonvolatile memory may include a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory, among others. Volatile memory can include random access memory (random access memory, RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic RAM (dynamic random access memory, DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (enhancedSDRAM, ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. Computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Any process or method description in a flowchart or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process. And the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed in a substantially simultaneous manner or in an opposite order from that shown or discussed, including in accordance with the functions that are involved.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the methods of the embodiments described above may be performed by a program that, when executed, comprises one or a combination of the steps of the method embodiments, instructs the associated hardware to perform the method.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules described above, if implemented in the form of software functional modules and sold or used as a stand-alone product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like. Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. Intelligent analysis and knowledge type fault processing auxiliary system for power distribution network, which is characterized in that: the system comprises a data acquisition layer (10), a map construction layer (20), a knowledge calculation layer (30) and a map application layer (40);
the data acquisition layer (10) is used for structured data analysis, semi/unstructured data labeling and third party cooperative data analysis, and the data acquisition layer (10) is connected with a resource layer to acquire information collected by a monitoring terminal matched in the resource layer at the bottommost layer;
the map construction layer (20) comprises an entity identification model, the entity identification model is connected with the data acquisition layer (10), the map construction layer (20) provides RDF data files or CIM-XML model data files conforming to CIM model rules, and the map construction layer (20) is used for carrying out natural language processing, knowledge extraction, knowledge fusion and knowledge processing work on a core layer of a knowledge map application architecture and carrying out standardization processing on entity, concept, relationship and event data stored in a map database;
the knowledge calculation layer (30) comprises a processor, is connected with the entity identification model and is used for general algorithm model calculation of representation learning, relationship reasoning, attribute reasoning, event reasoning, path calculation and comparison sequencing of the entity identification model data integration;
the map application layer (40) provides an interface for the knowledge calculation layer (30) through a data form of CIS service, outputs calculation processing data of the knowledge calculation layer (30), and is used for providing intelligent searching, intelligent question answering, intelligent recommending, auxiliary decision making, knowledge management and third party application, and the final functional module produced by the knowledge map application architecture is used for interfacing with an actual application scene.
2. The power distribution network intelligent resolution and knowledge fault handling auxiliary system according to claim 1, wherein: the data acquisition layer (10) comprises scheduling regulations, safety regulations and expert experience related data, and particularly acquires entities, events and knowledge maps, wherein the entities comprise operation and running special terms, accident handling special terms and related contents of a power grid topological graph structure, and the events comprise general principles of fault handling, expert experience of fault handling and contents of fault handling business logic;
the knowledge graph construction of the graph construction layer (20) comprises data cleaning, user load, knowledge extraction, knowledge fusion, knowledge processing, manual verification and knowledge updating; the entity recognition model comprises a BERT layer, a Word2Vec Word embedding layer, a bidirectional long and short time memory network layer BiLSTM, a characteristic serial layer connection and a full connection layer Dense;
the knowledge calculation layer (30) comprises data storage, data processing and reasoning calculation, wherein the data storage comprises a multi-layer multi-library principle, authority partition management and sub-graph access control, and particularly, the data logic association mining is carried out by a basic data source, operation data and fault information through a knowledge graph, and then the reasoning analysis and calculation are carried out;
the map application layer (40) performs data logic association mining in combination with the service scene, and performs key information matching, topology path searching and data mining statistical method analysis and calculation.
3. The power distribution network intelligent parsing and knowledge based fault handling assistance system according to claim 2, wherein: the data layer construction of the map construction layer (20) is a label attribute map data model based on Neo4j, and consists of two types of data, namely Entity Node and relation, wherein the Node stores Entity information, the relation links the Entity, and the Node and the attribute and label of the relation are stored in a key value pair mode.
4. The power distribution network intelligent resolution and knowledge fault handling auxiliary system according to claim 1, wherein: the general algorithm model constructed by the knowledge graph of the knowledge calculation layer (30) is TF-IDF algorithm, the distribution network fault classification is taken as an entity, after a plurality of groups are formed by fault occurrence reasons, fault attributes, fault phenomena, a fault processing method and related expert experiences, the TF-IDF algorithm is adopted to screen out the whole file in the local textWords with concentrated distribution and high frequencytf ij The formula is as follows;
；
wherein ,the representation being wordstf ij In File->The number of occurrences of>Then is file->The sum of the times of occurrence of all words in the list;
；
where D is the total number of documents in the knowledge-graph corpus,representing comprising words->I.e. ni, j not equal to 0;
the TF-IDF value formula for calculating the specified word is as follows:
；
each word in each sentenceTF-IDF values were calculated separately.
5. The power distribution network intelligent resolution and knowledge fault handling auxiliary system according to claim 1, wherein: the data acquisition layer (10) comprises a knowledge extraction module, a knowledge fusion module and a knowledge updating module, wherein the knowledge extraction module is used for acquiring entities, relationships among the entities and structured knowledge of attributes from semi/unstructured data through a knowledge extraction method under the guidance of a knowledge organization architecture; the knowledge fusion module is used for carrying out entity disambiguation and coreference resolution processing based on the entity information data obtained by the knowledge extraction module; the knowledge updating module evaluates the quality and timeliness of the corresponding knowledge in the process of applying the knowledge graph, and updates and corrects the knowledge by combining the development of the knowledge.
6. The power distribution network intelligent resolution and knowledge fault handling auxiliary system according to claim 1, wherein: the data in the data acquisition layer (10) refers to data obtained by importing, reading and structurally storing a excel, csv, json, xml file, and the data labeling refers to labeling of concept, entity, relationship and attribute semantic information on text data.
7. The power distribution network intelligent resolution and knowledge fault handling auxiliary system according to claim 1, wherein: the building mode of the map building layer (20) is established in a mode of combining top-down and bottom-up, corresponding keywords are extracted from top-down and bottom-up correspondingly to be fused, screened, corrected and classified into operation terms, accident handling terms, operation terms and fault terms, a screening method is adopted to carry out term complementation by combining data materials, and content complementation of professional term explanation and related scheduling regulations and safety regulations is completed through search matching.
8. The method of a power distribution network intelligent resolution and knowledge fault handling assistance system according to any one of claims 1-7, wherein: the method comprises the following steps:
step 1: counting the existing operation rules, treatment plans and regulation rules of the power grid, associating the operation rules, treatment plans and regulation rules required after the power grid fails, and respectively performing one-to-one correspondence on the existing operation rules, treatment plans and regulation rules of the power grid and the operation rules, treatment plans and regulation rules required after the power grid fails to form a structured network;
step 2: the method comprises the steps that a data acquisition layer (10) and a map construction layer (20) are constructed according to power distribution network fault information knowledge, the data acquisition layer (10) unifies a physical model and a knowledge model required in power distribution network fault scheduling decisions, a relation link among multi-source data is established through the map construction layer (20), and the data layer and the knowledge map layer are constructed;
step 3: constructing a knowledge calculation layer (30) according to a power distribution network fault information knowledge reasoning technology, carrying out data logic association mining by a basic data source, operation data and fault information through a knowledge graph, and finally carrying out reasoning analysis and calculation;
step 4: when the dispatching faults occur, the fault information is transmitted to a control personnel monitoring system in real time, the regional fault plan is automatically recommended according to the position of the faults, and relevant fault cases are matched;
step 5: fitting human thinking and working modes, matching real-time fault information comprising fault equipment, places, states and phenomena with fault phenomena and fault cases in a knowledge graph of a joint memory network, forming initial constraints according to the fault information from three aspects of the same equipment fault case cluster, the same equipment fault case cluster and the same equipment fault processing principle, establishing entity links, associating fault case clusters and fault processing knowledge based on subgraph retrieval and paths, counting historical fault information, and realizing knowledge searching, calculating and recommending through path recall;
step 6: and (3) performing network reconstruction on a non-fault power-losing area after fault location is finished, and performing man-machine interaction scene with small network loss, more non-fault load recovery and less switching times by referring to fault recommendation information under the condition that power balance, capacity and voltage constraint and power distribution network connectivity and radial constraint are met, so that the method is suitable for multi-objective optimization.
9. A computer-readable storage medium storing instructions, characterized in that: when the instructions are run on a computer, the instructions cause the computer to apply the power distribution network intelligent resolution and knowledge based fault handling assistance system according to any one of claims 1 to 7 or to perform the method of the power distribution network intelligent resolution and knowledge based fault handling assistance system according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310663567.6A CN116821423A (en) | 2023-06-06 | 2023-06-06 | Intelligent analysis and knowledge type fault processing auxiliary system and method for power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310663567.6A CN116821423A (en) | 2023-06-06 | 2023-06-06 | Intelligent analysis and knowledge type fault processing auxiliary system and method for power distribution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116821423A true CN116821423A (en) | 2023-09-29 |
Family
ID=88115946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310663567.6A Pending CN116821423A (en) | 2023-06-06 | 2023-06-06 | Intelligent analysis and knowledge type fault processing auxiliary system and method for power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116821423A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117521662A (en) * | 2023-10-19 | 2024-02-06 | 湖北华中电力科技开发有限责任公司 | Power dispatching semantic analysis method based on deep learning |
-
2023
- 2023-06-06 CN CN202310663567.6A patent/CN116821423A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117521662A (en) * | 2023-10-19 | 2024-02-06 | 湖北华中电力科技开发有限责任公司 | Power dispatching semantic analysis method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9798310B2 (en) | Method for searching cross-regional power supply area based on CIM model and system thereof | |
| WO2023045417A1 (en) | Fault knowledge graph construction method and apparatus | |
| CN114138759B (en) | Secondary equipment fault processing pushing method and system based on knowledge graph reasoning | |
| CN113434634A (en) | Knowledge graph construction method and device | |
| CN116821423A (en) | Intelligent analysis and knowledge type fault processing auxiliary system and method for power distribution network | |
| CN114138982A (en) | Construction method of knowledge graph for dry-type transformer fault diagnosis | |
| CN112613611A (en) | Tax knowledge base system based on knowledge graph | |
| CN113095524A (en) | Intelligent generation method, system and storage medium for maintenance work document of power equipment | |
| CN115221776A (en) | Training method and device for intelligent sensing diagnosis model of novel power distribution network | |
| Tang et al. | Automatic schema construction of electrical graph data platform based on multi-source relational data models | |
| Xiao et al. | Research on the construction and implementation of power grid fault handling knowledge graphs | |
| WO2019140553A1 (en) | Method and device for determining health index of power distribution system and computer storage medium | |
| CN115827885A (en) | Operation and maintenance knowledge graph construction method and device and electronic equipment | |
| Si et al. | Research on comprehensive evaluation of distribution network based on Knowledge Graphs | |
| Li et al. | Multi-source education knowledge graph construction and fusion for college curricula | |
| Meng et al. | Research on the typical application of knowledge graph in power marketing | |
| Yan et al. | Implementation of Intelligent Q&A System for Electric Power Knowledge Based on Knowledge Graph | |
| CN117934209B (en) | Regional power system carbon emission big data analysis method based on knowledge graph | |
| Gao et al. | GridOnto: knowledge representation and extraction for fault events in power grid | |
| Liu et al. | Application of Knowledge Graph Technology in the Field of Power Grid Infrastructure | |
| Gu et al. | Research on the Knowledge Graph Construction Technology and its Power Grid Applications | |
| Haibo et al. | Construction of Knowledge Graph of Power Communication Planning based on Deep Learning | |
| Yan et al. | Construction of Dynamic Knowledge Graph for Grid day-ahead Scheduling Optimization Decision | |
| CN116644950A (en) | Knowledge graph-based power failure influence range analysis method and device and electronic equipment | |
| Cao et al. | Intelligent substation virtual circuit verification method combining knowledge graph and deep learning |
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 |