CN113283704A - Intelligent power grid fault handling system and method based on knowledge graph - Google Patents
Intelligent power grid fault handling system and method based on knowledge graph Download PDFInfo
- Publication number
- CN113283704A CN113283704A CN202110441766.3A CN202110441766A CN113283704A CN 113283704 A CN113283704 A CN 113283704A CN 202110441766 A CN202110441766 A CN 202110441766A CN 113283704 A CN113283704 A CN 113283704A
- Authority
- CN
- China
- Prior art keywords
- fault
- power grid
- handling
- knowledge
- disposal
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000008447 perception Effects 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 8
- 238000012502 risk assessment Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000003058 natural language processing Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000007726 management method Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 230000014509 gene expression Effects 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 4
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/08—Learning methods
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/40—Display of information, e.g. of data or controls
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Power Engineering (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Game Theory and Decision Science (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power grid fault intelligent disposal system based on a knowledge graph, wherein a fault disposal plan analysis module of the system is used for acquiring fault disposal entities and relation knowledge; the map generation module is used for storing the identified entity and the entity relation in a triple form to obtain an equipment entity knowledge map, an accident plan knowledge map and a disposal process knowledge map; the fault perception module intelligently perceives and collects information related to the power grid fault in the power grid system; the fault risk evaluation module is used for carrying out risk identification; the intelligent fault handling module is used for reasoning out handling measures suitable for the current fault based on the accident plan knowledge graph and the handling process knowledge graph and by combining topological changes before and after the power grid fault, the power flow and the alternating current power supply frequency after the power grid has the line fault. The comprehensive intelligent alarm system can sense comprehensive intelligent alarm information in an all-round way, and guides dispatching personnel to perform intelligent treatment on power grid risks and power restoration based on the established knowledge graph.
Description
Technical Field
The invention relates to the technical field of crossing artificial intelligence and power grid regulation, in particular to a power grid fault intelligent treatment system and method based on a knowledge graph.
Background
With the formation of large alternating-current and direct-current hybrid power grids in China, the structures of the power grids are increasingly complex, the operation modes are flexible and changeable, the regulation and control business is increasingly complex, single grid faults are not timely treated, cascading failure reactions are caused among alternating-current and direct-current systems, and the safety and stability of the power grids are seriously threatened. The power grid fault disposal is mainly implemented by receiving fault disposal signals by scheduling personnel, analyzing the operation condition of a power grid according to fault text description and a fault disposal plan, evaluating the safety risk of the power grid, disposing line faults and recording fault disposal information.
The existing line fault handling scheme judges and analyzes faults by depending on a dispatcher, reports the faults by adopting manual records, communicates information by manual telephones, and counts the average time of tens of minutes for the existing manual handling of the line faults, so that the risk of the line faults causing cascading faults between alternating current and direct current systems is increased, and the requirement of timely handling the grid faults in an alternating current and direct current parallel-serial complex grid cannot be met. Therefore, a method and a system for handling a line fault of a smart grid are needed to realize intelligent sensing of fault information, assistance of a dispatcher in fault handling decision making and automatic recording of fault handling information.
Disclosure of Invention
The invention aims to provide a power grid fault intelligent disposal system and a power grid fault intelligent disposal method based on a knowledge graph.
In order to achieve the purpose, the power grid fault intelligent handling system based on the knowledge graph comprises a fault handling plan analyzing module, a graph generating module, a fault sensing module, a fault risk evaluating module and a fault intelligent handling module, wherein the fault handling plan analyzing module is used for acquiring an unstructured power grid fault handling text from a scheduling rule, a fault handling plan and an operation instruction book, and sequentially performing data preprocessing, text marking, knowledge extraction and knowledge fusion on the power grid fault handling text based on natural language processing and artificial intelligence technology to form a fault handling entity and relationship knowledge;
the map generation module is used for storing the identified entity and entity relation in a triple form to obtain an equipment entity knowledge map, an accident plan knowledge map and a disposal flow knowledge map, establishing the equipment entity knowledge map based on power grid model data to inquire fault equipment information, establishing the accident plan knowledge map based on a fault disposal plan to push the accident plan, establishing the disposal flow knowledge map based on a scheduling procedure, fault disposal detailed rules, fault disposal experience and the fault disposal plan to guide a dispatcher to dispose faults, and mutually connecting the equipment entity knowledge map, the accident plan knowledge map and the disposal flow knowledge map to support line fault disposal;
the fault sensing module is used for sensing the power grid fault through comprehensive intelligent alarm, and intelligently sensing and collecting information related to the power grid fault in the power grid system by taking a power grid fault equipment model and occurrence time as an equipment label and a time label;
the fault risk assessment module is used for carrying out risk identification on the power grid risk by combining the intelligent sensing and collecting result with the equipment entity knowledge graph;
the intelligent fault handling module is used for reasoning out handling measures suitable for the current fault based on the accident plan knowledge graph and the handling process knowledge graph and by combining topological changes before and after the power grid fault, the power flow and the alternating current power supply frequency after the power grid has the line fault.
According to the invention, based on the requirements of the power grid line fault disposal application scene, the real-time sensing of power grid line fault information can be realized, the power grid risk can be effectively evaluated, the corresponding fault disposal plan is matched, and the fault disposal knowledge graph formed by the equipment entity knowledge graph, the accident plan knowledge graph and the fault disposal process knowledge graph can rapidly guide a dispatcher to eliminate the fault risk, dispose the line fault and realize the automatic recording of the fault disposal information, so that the fault disposal time is greatly shortened, the fault disposal efficiency is improved, the line fault disposal experience can be multiplexed, and the method has high application value.
The invention solves the problem that the power grid line fault needs to be quickly treated, reduces the experience dependence on a dispatcher, avoids the problem of long time consumption of manual treatment, reduces the risk of cascading faults caused by the line fault between an alternating current system and a direct current system, and can meet the requirement of timely treating the power grid fault in an alternating current-direct current hybrid complex power grid. The device entity knowledge graph can be used for rapidly positioning the position of the fault device and returning parameter information of the fault device aiming at alarm information, rapidly positioning and monitoring the device connected with the fault device, accurately mastering the real-time dynamic state of a power grid, and giving a disposal mode of part of fault devices, so that the time from the occurrence of the fault to the failure is greatly shortened, the risk of causing cascading failures is favorably reduced, the disposal flow when the failure occurs can be guided by the disposal flow knowledge graph, and the problem that a dispatcher spends a long time according to personal experience or manual inquiry of the disposal mode is avoided. According to the power grid fault intelligent disposal method and system based on the knowledge graph, comprehensive intelligent alarm information can be sensed in an all-around mode, risk assessment can be conducted on a power grid section after equipment faults, a fault solving mode is pushed, a dispatcher is guided to conduct line fault disposal according to the knowledge graph of a disposal flow, and fault related information in the disposal process is automatically recorded.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a diagram of a line fault handling knowledge graph logic model;
FIG. 3 is a power grid equipment knowledge graph;
FIG. 4 is a chart of an accident prediction knowledge map;
FIG. 5 is a grid line fault handling flow diagram;
fig. 6 is a line fault handling flow knowledge graph.
The system comprises a fault handling plan analyzing module 1, a map generating module 2, a fault sensing module 3, a fault risk evaluating module 4, a fault intelligent handling module 5 and a fault information recording module 6.
Detailed Description
The invention is described in further detail below with reference to the following figures and specific examples:
the power grid fault intelligent handling system based on the knowledge graph as shown in fig. 1 comprises a fault handling plan parsing module 1, a graph generating module 2, a fault sensing module 3, a fault risk evaluating module 4 and a fault intelligent handling module 5, wherein the fault handling plan parsing module 1 is used for obtaining an unstructured power grid fault handling text (the power grid fault handling text is an unstructured text which cannot be directly stored in a database and directly used, and a corresponding fault handling entity is an nonstandard equipment name, so that the entity and the relationship need to be extracted, and the entity and the relationship need to be fused and mapped into a standard equipment name to construct the knowledge graph from a scheduling rule, fault handling rules, a fault handling plan (the plan refers to a fault form which is expected to occur in the power grid, and a handling measure when the fault occurs), for pushing subsequent plans), sequentially performing data preprocessing, text marking, knowledge extraction and knowledge fusion on the power grid fault handling text to form fault handling entity and relationship knowledge based on natural language processing and artificial intelligence technology (including entity identification technology during text marking, used deep learning model extraction entity and relationship, and constructed knowledge map);
the map generation module 2 is configured to store the identified entity and entity relationship in a triple form to obtain an equipment entity knowledge map, an accident plan knowledge map, and a disposal process knowledge map, establish an equipment entity knowledge map based on the grid model data to query fault equipment information (for example, to query a voltage class, a wiring diagram, an equipment limit value, a power curve, and the like of the equipment, and monitor other equipment connected to the fault equipment), establish a plan knowledge map based on the fault disposal plan to push the accident plan, establish a disposal process knowledge map based on a scheduling procedure, a fault disposal rule, a fault disposal experience, and a fault disposal plan to guide a dispatcher to dispose a fault, associate the equipment entity knowledge map, the accident plan knowledge map, and the disposal process knowledge map with each other to support circuit fault disposal, and a fault disposal knowledge map logic model is shown in fig. 2, when a certain device fails and returns alarm information, the device entity knowledge graph can be quickly positioned to the device in the graph and return attribute information of the device, so that detailed information of the device can be conveniently known, other devices connected with the failed device can be timely positioned, monitoring operation is carried out on the devices, and chain faults of other devices caused by single device faults are prevented. The equipment entity knowledge map is connected with the failure plan knowledge map, when a failure point is located, the failure entity is pushed into the failure plan knowledge map, the failure plan knowledge map is inquired, whether the failure has a disposal scheme in the plan knowledge map is judged, the disposal scheme is inquired and pushed, the process disposal knowledge map is responsible for the whole process guidance from fault alarm receiving to failure solving, when the failure sensing module receives the alarm information, the disposal process knowledge map acquires the attribute information of the failure equipment from the entity knowledge map, carries out failure risk assessment according to the attribute information, identifies the failure category, then detects whether the failure plan knowledge map carries out plan pushing, if the plan pushing of the plan knowledge map is received, executes corresponding failure elimination operation according to the plan pushing result, if the plan push of the fault plan map is not received, corresponding handling measures are given according to the power grid topology change, the tide change, the frequency change and the like before and after the power grid fault, fault elimination is carried out, so that the normal operation of the power grid is recovered, fault information and a solution are automatically recorded, and the whole process from the fault occurrence to the recovery of the normal operation of the power grid is realized and recorded on the plan;
the fault perception module 3 is used for perceiving the power grid fault through comprehensive intelligent warning, and intelligently perceiving and collecting the information related to the power grid fault in the power grid system from two dimensions of time and space by taking a power grid fault equipment model and occurrence time as an equipment label and a time label, so as to provide a decision basis for power grid fault disposal;
the fault risk assessment module 4 is used for carrying out risk identification on the power grid risk (including equipment limit value, section stability limit, power grid wiring diagram and the like) by combining the intelligent sensing collected result with the relevant information fed back by the equipment entity knowledge graph;
the fault intelligent handling module 5 is configured to infer a handling measure suitable for a current fault based on an accident plan knowledge graph and a handling flow knowledge graph after the line fault occurs in a power grid, and by combining topology changes before and after the power grid fault (abstracting each device in the power grid into corresponding nodes, abstracting power lines of the nodes into lines, and further representing a relationship between the nodes in a topology graph form.
In the technical scheme, the triple group knowledge unit 'entity-relation-entity' of the equipment entity knowledge graph is derived from equipment table information in an intelligent dispatching control system relation library, and the related equipment tables comprise information such as a power grid information table, an alternating current line segment table, a transformer table, a bus bar table, a breaker table, a disconnecting link table and a station table. The attributes of each transformer substation in the substation table comprise a wiring diagram, a region to which the transformer substation belongs, voltage equivalence, a power curve, an operation state, a manufacturer, a substation type, a unique identifier and the like, slave equipment of the transformer substation comprises a bus, a switch, a main transformer, a line, a disconnecting link and the like, and the transformer substation is managed by a power grid. The method for establishing the equipment entity knowledge graph is that each power equipment in each equipment list is connected with a corresponding transformer substation through a station unique identifier existing in each equipment list to form a uniform equipment entity knowledge network, each power equipment in the network represents an entity, a power grid and the transformer substation are in a management relationship, the transformer substation is managed by the power grid, and other equipment are in a subordinate relationship. The equipment entity part knowledge graph is shown in figure 3. And storing the equipment entity knowledge networks into a Neo4j database in a form of triples to form an equipment entity knowledge graph.
The accident plan knowledge graph is established according to 'entity-relation-entity' by taking the fault handling entities as entity elements in the accident plan knowledge graph and taking the relationships among the entities as relationship elements in the accident plan knowledge graph. Wherein the extracted part of the fault handling entities is shown in table 1.
Table 1 part accident plan fault handling entity
The contents extracted from the table form an entity-relationship-entity, and the entity-relationship-entity is stored in the Neo4j database, and the established accident prediction knowledge graph is shown in the following fig. 4.
A disposal process knowledge graph, which is established according to a line fault disposal process, wherein the line fault disposal process is shown in fig. 5, and the flow chart describes detailed node information for guiding line fault disposal, and mainly includes: fault sensing, risk assessment, fault handling, fault operation recovery, information recording and the like. The treatment flow knowledge graph takes the flow steps in fig. 6 as a conceptual model, combines each position point according to an "entity-relationship-entity" form to form a treatment flow represented in a triple form, and the treatment flow partially represented in the triple form is shown in table 2.
Table 2 treatment flow partially represented in triplet form
Serial number | Entity-relationship-entity |
1 | Line fault sensing-next-risk assessment |
2 | Risk assessment-next step-plan intelligent push |
3 | Power grid risk judgment-yes-adjustment unit output |
4 | Power grid risk judgment-no-forced delivery condition judgment |
5 | Forced delivery condition judgment-yes-generation operation ticket |
The flow handling knowledge in the table is stored in the Neo4j database in the form of triples, and a flow guidance knowledge graph is established as shown in fig. 6.
In the above technical solution, the data preprocessing specifically includes filtering and cleaning selected special symbols and selected special numbers in the text related to fault handling through a regular expression. Here, the preprocessing process is performed before the marking, and in each fault handling text, the filtered symbols include tab characters, carriage returns, line breaks, page breaks, and the sequence numbers of the beginning part, such as "1", "2", "punctuation mark of the ending part, of each sentence are filtered.
In the above technical solution, the text marking is to mark the power grid fault handling text after data preprocessing according to natural language syntax by using a BIO (B-begin represents the beginning of an entity, I-ide represents the middle or end of the entity, and O-outside represents that the entity does not belong to) text marking specification, and mark syntax relations among fault handling noun entities, fault handling verb entities, and entities in the text, where the relations mainly include: subject, object, guest supplement, prepended, postended, conditional relationship (when the condition is satisfied, perform a specified action, e.g., perform XX decentration to notify XX of provincial control XX cross section not exceeding 1800MW when grid frequency is higher than 50 Hz).
In the above technical solution, the knowledge extraction specifically includes marking a part of texts (a part of texts is a part of all texts, since the amount of fault handling texts is huge, and the amount of fault handling texts is completely excessive through manual marking tasks, selecting a part of texts in all texts to be manually marked, then training corresponding models by using the part of marked texts, then automatically extracting all texts based on the trained models, extracting grammatical relations among fault handling noun entities, fault handling entities and entities in all power grid fault handling texts by using a deep neural network, and using the extracted entities and relations to construct a plan knowledge graph, wherein a fault handling entity recognition model is established based on a bidirectional long-short term memory network and a conditional random field (BiLSTM-CRF) (establishing a model is a process of training a model, the marked part of text is referred to as a training set used for training the model, based on the training set, the model represents that the model training is completed, namely the model construction is completed, when the automatic extraction of the fault handling entity in the unmarked fault handling text can be realized through the continuous self-learning process, the fault handling noun entity and the fault handling verb entity are extracted (the extracted entity mainly acts as an entity element in the plan knowledge graph), the grammatical relation between the entities is extracted based on the text convolutional neural network (TextCNN), and the extracted relation is used as the relation between the entities in the plan knowledge graph.
The fault handling entities comprise electric equipment category entities (areas, stations, buses, units, alternating current line sections, transformers, sections, direct current line sections and the like), and the fault handling verb entities comprise orders, common jumps, holding, guaranteeing, full opening, full stopping and the like.
In the above technical solution, the knowledge fusion specifically is to fuse entities (in the fault handling entity, the part of the entities corresponding to the electrical equipment) with the same semantics by using a text similarity calculation technique, and map the extracted fault handling entity with the electrical equipment in the standard equipment table, so as to obtain a standard electrical equipment name. The fusion is used for corresponding the extracted fault handling entities with the equipment in the standard equipment table, and the fused result is that each extracted power equipment entity corresponds to the standard equipment in the standard equipment table.
In the above technical solution, the system further includes a fault information recording module 6, where the fault information recording module 6 is configured to generate a fault panoramic information record, a scheduling log, and a fault report after the power grid fault disposal is finished. The method comprises the steps of comprehensively analyzing signals related to the power grid faults through multiple dimensions such as equipment labels, time labels and topology analysis, aggregating to form a set and electronically recording the content of the set. The panoramic information belongs to a certain power grid fault, and the power grid fault reason can be analyzed through panoramic information recording. And scheduling logs, namely collecting information such as accident reasons, occurrence time, fault equipment and the like according to the power grid accidents and forming related fault logs. Meanwhile, in the whole fault handling process, information such as fault handling time, key links, handling personnel and the like is automatically recorded, and a fault handling flow recording log is formed for post analysis. For the convenience of subsequent analysis and retrieval, the storage of the scheduling log information needs an OMS (Operations Management System) to provide a relevant data interface, and data solidification and information display of the scheduling log are completed.
And after the fault disposal is finished, generating a fault disposal report of the fault according to various information related to the fault, the time stamp of the fault key point, the fault analysis result, the fault response measure and the like when the fault occurs.
The grammatical relations among the entities comprise subject, object, guest, preposition, postition and conditional relations.
In the above technical solution, the information sensed and collected by the fault sensing module 3 includes a comprehensive intelligent alarm signal, a steady state monitoring signal, OMS system information, and weather information. The comprehensive intelligent alarm signal comprises the description of trip equipment, a station or line to which the fault belongs, the fault category, the reclosing action condition, the fault occurrence time and the like. The steady-state monitoring signals comprise remote signaling deflection conditions of the fault equipment, remote measuring information of equipment related to the fault equipment, heavy-load equipment information caused by power grid faults and critical section out-of-limit information caused by the power grid faults. The OMS system information comprises overhaul information, live working information and equipment abnormity information related to fault equipment. The weather information comprises weather condition information of areas where fault stations, fault lines and the like are located after faults occur.
In the above technical solution, the risk identification range of the fault risk assessment module 4 includes equipment overload, section out-of-limit, and power grid weak link. The equipment overload is the out-of-limit caused by the comparison of the tidal current values of the equipment such as lines, transformers and the like with the equipment limit values. The cross section limit exceeding is the cross section real-time tidal current value and the cross section stable limit comparison occurrence limit exceeding. The power grid weak link analysis is to analyze the single-line grid connection condition of a power grid and the single-line grid connection condition of a local power grid (isolated island operation), and the judgment is carried out through the static safety analysis N-1 of the power grid analysis.
In the above technical solution, the disposal measures of the intelligent fault disposal module 5 include intelligent pushing of a fault disposal plan, unit output adjustment, emergency power drawing and limiting, rapid load transfer, operation mode adjustment, emergency shutdown of the unit, forced power transmission and the like. And pushing the disposal mode when the fault occurs according to the disposal mode in the accident plan knowledge graph, so as to realize the rapid solution of the fault. The unit output adjustment is an effective means for eliminating the power grid risk, the sensitivity value of the line and the section to the unit is calculated through power grid analysis, the calculated sensitivity represents and adjusts the influence of the unit output on the line and the section, the unit which is influenced by the risk equipment and the section can be adjusted, the power grid risk can be eliminated or reduced, and the unit output adjustment range is within the range of ensuring the power grid safety. And the accident power drawing and limiting is to cut off the load capable of eliminating the risk of the power grid so as to ensure the stable operation of the power grid. Sensitivity values of the lines and the sections to the loads are calculated through power grid analysis, the sensitivity represents the influence of load switching on the lines and the sections, and the risk of the power grid can be eliminated or reduced by cutting off the corresponding loads. The method for processing the line fault further comprises measures of operation mode adjustment, emergency stop of the unit, strong power transmission and the like, wherein the operation mode adjustment is to change the topological relation of the operation of the power grid to reduce or eliminate risks. The emergency stop unit is forced to quit the operation. And the strong power transmission is to recover the line power supply after the power grid state and the field condition are judged.
A power grid fault intelligent treatment method based on a knowledge graph comprises the following steps:
step 1: the fault handling plan analysis module 1 acquires an unstructured power grid fault handling text from a scheduling rule, a fault handling plan and an operation instruction book, and sequentially performs data preprocessing, text marking, knowledge extraction and knowledge fusion on the power grid fault handling text based on natural language processing and artificial intelligence technology to form a fault handling entity and relationship knowledge;
step 2: the map generation module 2 stores the identified entity and entity relation in a triple form to obtain an equipment entity knowledge map, an accident plan knowledge map and a disposal process knowledge map, establishes the equipment entity knowledge map based on power grid model data to inquire fault equipment information, establishes the plan knowledge map based on the accident plan to push the accident plan, establishes the disposal process knowledge map based on a scheduling procedure, fault disposal rules, fault disposal experience and the fault disposal plan to guide a dispatcher to dispose faults, and the equipment entity knowledge map, the accident plan knowledge map and the disposal process knowledge map are mutually linked to support line fault disposal;
and step 3: the fault perception module 3 perceives the power grid fault through comprehensive intelligent warning, and intelligently perceives and collects information related to the power grid fault in the power grid system by taking a power grid fault equipment model and occurrence time as an equipment label and a time label;
and 4, step 4: the fault risk evaluation module 4 carries out risk identification on the power grid risk by combining the intelligent sensing and collecting result with the equipment entity knowledge graph;
and 5: after a line fault occurs in the power grid, the fault intelligent handling module 5 infers a handling measure suitable for the current fault based on the accident plan knowledge graph and the handling process knowledge graph and by combining topological changes before and after the power grid fault, the power flow and the alternating current power supply frequency.
Details not described in this specification are within the skill of the art that are well known to those skilled in the art.
Claims (10)
1. A power grid fault intelligent handling system based on a knowledge graph is characterized by comprising a fault handling plan analyzing module (1), a graph generating module (2), a fault sensing module (3), a fault risk evaluating module (4) and a fault intelligent handling module (5), wherein the fault handling plan analyzing module (1) is used for acquiring unstructured power grid fault handling texts from scheduling rules, fault handling plans and operation guide books, and sequentially performing data preprocessing, text marking, knowledge extraction and knowledge fusion on the power grid fault handling texts based on natural language processing and artificial intelligence technology to form fault handling entities and relationship knowledge;
the map generation module (2) is used for storing the identified entity and entity relation in a triple form to obtain an equipment entity knowledge map, an accident plan knowledge map and a disposal process knowledge map, establishing the equipment entity knowledge map based on power grid model data to inquire fault equipment information, establishing the plan knowledge map based on a fault disposal plan to push the accident plan, establishing the disposal process knowledge map based on a scheduling procedure, a fault disposal rule, a fault disposal experience and the fault disposal plan to guide a dispatcher to dispose faults, and mutually connecting the equipment entity knowledge map, the accident plan knowledge map and the disposal process knowledge map to support line fault disposal;
the fault perception module (3) is used for perceiving the power grid fault through comprehensive intelligent warning, and intelligently perceiving and collecting information related to the power grid fault in the power grid system by taking a power grid fault equipment model and occurrence time as an equipment label and a time label;
the fault risk assessment module (4) is used for carrying out risk identification on the power grid risk by combining the intelligent perception collected result with the equipment entity knowledge graph;
the intelligent fault handling module (5) is used for reasoning out handling measures suitable for the current fault based on the accident plan knowledge graph and the handling process knowledge graph and by combining topology change, tide and alternating current power supply frequency before and after the fault of the power grid after the line fault of the power grid occurs.
2. The intellectual graph based power grid fault intelligent handling system according to claim 1, wherein: the data preprocessing specifically includes that selected special symbols and selected special numbers in the text related to fault handling are filtered and cleaned through regular expressions.
3. The intellectual graph based power grid fault intelligent handling system according to claim 2, wherein: the text marking is specifically to mark the power grid fault handling text after data preprocessing by adopting a BIO text marking specification according to natural language grammar, and mark a fault handling noun entity, a fault handling verb entity and a grammatical relation among the entities in the text.
4. The intellectual property graph based grid fault intelligent handling system according to claim 3, wherein: the knowledge extraction specifically comprises the steps of marking partial texts, extracting grammatical relations among fault handling noun entities, fault handling verb entities and entities in all power grid fault handling texts by using a deep neural network, wherein a fault handling entity recognition model is established based on a bidirectional long-short term memory network and a conditional random field, extracting the fault handling noun entities and the fault handling verb entities, and extracting the grammatical relations among the entities based on a text convolutional neural network.
5. The intellectual graph based power grid fault intelligent handling system according to claim 4, wherein: the knowledge fusion specifically is to fuse entities with the same semantics by adopting a text similarity calculation technology, and map the extracted fault handling entity with the power equipment in the standard equipment table to obtain the name of the standard power equipment.
6. The intellectual graph based power grid fault intelligent handling system according to claim 1, wherein: the power grid fault management system further comprises a fault information recording module (6), wherein the fault information recording module (6) is used for generating a fault panoramic information record, a scheduling log and a fault report after the power grid fault is handled.
7. The intellectual graph based power grid fault intelligent handling system according to claim 1, wherein: the fault sensing module (3) senses the collected information including comprehensive intelligent alarm signals, steady state monitoring signals, OMS system information and meteorological information.
8. The intellectual graph based power grid fault intelligent handling system according to claim 1, wherein: and the risk identification range of the fault risk evaluation module (4) comprises equipment overload, section out-of-limit and power grid weak links.
9. The intellectual graph based power grid fault intelligent handling system according to claim 1, wherein: the disposal measures of the intelligent fault disposal module (5) comprise intelligent pushing of a fault disposal plan, unit output adjustment, accident power drawing and limiting, rapid load transfer, operation mode adjustment, emergency shutdown of the unit, forced power transmission and the like.
10. A power grid fault intelligent handling method based on a knowledge graph is characterized by comprising the following steps:
step 1: the fault handling scheme analysis module (1) acquires an unstructured power grid fault handling text from a scheduling rule, a fault handling plan and an operation instruction book, and sequentially performs data preprocessing, text marking, knowledge extraction and knowledge fusion on the power grid fault handling text based on natural language processing and artificial intelligence technology to form a fault handling entity and relationship knowledge;
step 2: the map generation module (2) stores the identified entity and entity relation in a triple form to obtain an equipment entity knowledge map, an accident plan knowledge map and a disposal flow knowledge map, establishes the equipment entity knowledge map based on power grid model data to inquire fault equipment information, establishes the plan knowledge map based on the accident plan to push the accident plan, establishes the disposal flow knowledge map based on a scheduling procedure, fault disposal rules, fault disposal experience and the fault disposal plan to guide a dispatcher to dispose faults, and the equipment entity knowledge map, the accident plan knowledge map and the disposal flow knowledge map are mutually connected to support line fault disposal;
and step 3: the fault perception module (3) perceives the power grid fault through comprehensive intelligent warning, and intelligently perceives and collects information related to the power grid fault in the power grid system by taking a power grid fault equipment model and occurrence time as an equipment label and a time label;
and 4, step 4: the fault risk evaluation module (4) performs risk identification on the power grid risk by combining the intelligent perception collected result with the equipment entity knowledge graph;
and 5: and after the line fault occurs in the power grid, the fault intelligent treatment module (5) infers treatment measures suitable for the current fault based on the accident plan knowledge graph and the treatment process knowledge graph and by combining topology change, tide and alternating current power supply frequency before and after the power grid fault.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110441766.3A CN113283704B (en) | 2021-04-23 | 2021-04-23 | Intelligent power grid fault handling system and method based on knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110441766.3A CN113283704B (en) | 2021-04-23 | 2021-04-23 | Intelligent power grid fault handling system and method based on knowledge graph |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113283704A true CN113283704A (en) | 2021-08-20 |
CN113283704B CN113283704B (en) | 2024-05-14 |
Family
ID=77277155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110441766.3A Active CN113283704B (en) | 2021-04-23 | 2021-04-23 | Intelligent power grid fault handling system and method based on knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113283704B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111474444A (en) * | 2020-04-14 | 2020-07-31 | 国网山东省电力公司电力科学研究院 | Line fault power restoration decision method based on knowledge graph |
CN113765100A (en) * | 2021-09-10 | 2021-12-07 | 国网上海市电力公司 | Power grid fault processing system and method |
CN113779254A (en) * | 2021-09-13 | 2021-12-10 | 广州汇通国信科技有限公司 | Power grid fault handling plan recommendation method and device based on knowledge graph |
CN113821408A (en) * | 2021-09-23 | 2021-12-21 | 中国建设银行股份有限公司 | Server alarm processing method and related equipment |
CN113837625A (en) * | 2021-09-27 | 2021-12-24 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Method, device and equipment for quantitatively evaluating risks of cascading failures of power grid |
CN113850481A (en) * | 2021-09-07 | 2021-12-28 | 华南理工大学 | Power system scheduling service assistant decision method, system, device and storage medium |
CN113919171A (en) * | 2021-10-22 | 2022-01-11 | 国家电网有限公司华东分部 | Method for generating online power grid fault plan considering steady-state power flow state |
CN113947320A (en) * | 2021-10-25 | 2022-01-18 | 国网天津市电力公司电力科学研究院 | Power grid regulation and control method based on multi-mode reinforcement learning |
CN113987183A (en) * | 2021-10-29 | 2022-01-28 | 广西电网有限责任公司南宁供电局 | Power grid fault handling plan auxiliary decision-making method based on data driving |
CN114138759A (en) * | 2021-11-08 | 2022-03-04 | 国家电网公司华中分部 | Secondary equipment fault processing and pushing method and system based on knowledge graph reasoning |
CN114157021A (en) * | 2021-10-28 | 2022-03-08 | 国网江苏省电力有限公司 | Multi-user cooperative disposal system and method for power grid faults |
CN114912637A (en) * | 2022-05-21 | 2022-08-16 | 重庆大学 | Operation and maintenance decision method and system for man-machine knowledge map manufacturing production line and storage medium |
CN115276003A (en) * | 2022-09-19 | 2022-11-01 | 国网江西省电力有限公司电力科学研究院 | Power distribution station area topological relation identification method based on multi-source data fusion knowledge graph |
CN115508672A (en) * | 2022-11-22 | 2022-12-23 | 中国电力科学研究院有限公司 | Power grid main equipment fault tracing reasoning method, system, equipment and medium |
CN116415002A (en) * | 2023-04-17 | 2023-07-11 | 合肥工业大学 | Power grid fault recovery error-proof checking method based on graph matching |
CN116561588A (en) * | 2023-07-07 | 2023-08-08 | 北京国电通网络技术有限公司 | Power text recognition model construction method, power equipment maintenance method and device |
CN116629604A (en) * | 2023-05-15 | 2023-08-22 | 国网冀北电力有限公司信息通信分公司 | Method and device for processing and analyzing power grid operation risk |
CN116860989A (en) * | 2023-06-19 | 2023-10-10 | 国网江苏省电力有限公司南京供电分公司 | Power distribution fault processing scheme recommendation method, device, equipment and storage medium |
CN117373487A (en) * | 2023-12-04 | 2024-01-09 | 浙江恒逸石化有限公司 | Audio-based equipment fault detection method and device and related equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109840270A (en) * | 2018-12-23 | 2019-06-04 | 国网浙江省电力有限公司 | A kind of grid equipment approaches to IM based on Neo4j |
CN110008288A (en) * | 2019-02-19 | 2019-07-12 | 武汉烽火技术服务有限公司 | The construction method in the knowledge mapping library for Analysis of Network Malfunction and its application |
CN110378585A (en) * | 2019-07-08 | 2019-10-25 | 国电南瑞科技股份有限公司 | Electric network fault disposes calculating task layout call method, system and storage medium |
WO2020063092A1 (en) * | 2018-09-30 | 2020-04-02 | 北京国双科技有限公司 | Knowledge graph processing method and apparatus |
CN111414491A (en) * | 2020-04-14 | 2020-07-14 | 广州劲源科技发展股份有限公司 | Power grid industry knowledge graph construction method, device and equipment |
CN111474444A (en) * | 2020-04-14 | 2020-07-31 | 国网山东省电力公司电力科学研究院 | Line fault power restoration decision method based on knowledge graph |
CN111552804A (en) * | 2020-04-08 | 2020-08-18 | 国电南瑞科技股份有限公司 | Knowledge graph construction method of power grid fault handling plan |
CN111737496A (en) * | 2020-06-29 | 2020-10-02 | 东北电力大学 | Power equipment fault knowledge map construction method |
CN112100397A (en) * | 2020-09-07 | 2020-12-18 | 南京航空航天大学 | Electric power plan knowledge graph construction method and system based on bidirectional gating circulation unit |
-
2021
- 2021-04-23 CN CN202110441766.3A patent/CN113283704B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020063092A1 (en) * | 2018-09-30 | 2020-04-02 | 北京国双科技有限公司 | Knowledge graph processing method and apparatus |
CN109840270A (en) * | 2018-12-23 | 2019-06-04 | 国网浙江省电力有限公司 | A kind of grid equipment approaches to IM based on Neo4j |
CN110008288A (en) * | 2019-02-19 | 2019-07-12 | 武汉烽火技术服务有限公司 | The construction method in the knowledge mapping library for Analysis of Network Malfunction and its application |
CN110378585A (en) * | 2019-07-08 | 2019-10-25 | 国电南瑞科技股份有限公司 | Electric network fault disposes calculating task layout call method, system and storage medium |
CN111552804A (en) * | 2020-04-08 | 2020-08-18 | 国电南瑞科技股份有限公司 | Knowledge graph construction method of power grid fault handling plan |
CN111414491A (en) * | 2020-04-14 | 2020-07-14 | 广州劲源科技发展股份有限公司 | Power grid industry knowledge graph construction method, device and equipment |
CN111474444A (en) * | 2020-04-14 | 2020-07-31 | 国网山东省电力公司电力科学研究院 | Line fault power restoration decision method based on knowledge graph |
CN111737496A (en) * | 2020-06-29 | 2020-10-02 | 东北电力大学 | Power equipment fault knowledge map construction method |
CN112100397A (en) * | 2020-09-07 | 2020-12-18 | 南京航空航天大学 | Electric power plan knowledge graph construction method and system based on bidirectional gating circulation unit |
Non-Patent Citations (3)
Title |
---|
乔骥等: "面向电网调度故障处理的知识图谱框架与关键技术初探", 《中国电机工程学报》, vol. 40, no. 18, pages 3 - 4 * |
余建明等: "面向智能调控领域的知识图谱构建与应用", 《电力***保护与控制》, vol. 48, no. 3, pages 2 * |
唐建兴等: "考虑自动装置控制策略的故障后潮流快速计算方法", 《南方电网技术》, vol. 14, no. 5, pages 51 - 58 * |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111474444A (en) * | 2020-04-14 | 2020-07-31 | 国网山东省电力公司电力科学研究院 | Line fault power restoration decision method based on knowledge graph |
CN113850481A (en) * | 2021-09-07 | 2021-12-28 | 华南理工大学 | Power system scheduling service assistant decision method, system, device and storage medium |
CN113765100A (en) * | 2021-09-10 | 2021-12-07 | 国网上海市电力公司 | Power grid fault processing system and method |
CN113779254A (en) * | 2021-09-13 | 2021-12-10 | 广州汇通国信科技有限公司 | Power grid fault handling plan recommendation method and device based on knowledge graph |
CN113821408A (en) * | 2021-09-23 | 2021-12-21 | 中国建设银行股份有限公司 | Server alarm processing method and related equipment |
CN113837625A (en) * | 2021-09-27 | 2021-12-24 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Method, device and equipment for quantitatively evaluating risks of cascading failures of power grid |
CN113837625B (en) * | 2021-09-27 | 2024-04-02 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Risk quantitative assessment method, device and equipment for grid cascading failure |
CN113919171B (en) * | 2021-10-22 | 2024-04-19 | 国家电网有限公司华东分部 | Online power grid fault plan generation method considering steady-state power flow state |
CN113919171A (en) * | 2021-10-22 | 2022-01-11 | 国家电网有限公司华东分部 | Method for generating online power grid fault plan considering steady-state power flow state |
CN113947320B (en) * | 2021-10-25 | 2024-05-28 | 国网天津市电力公司电力科学研究院 | Multi-mode reinforcement learning-based power grid regulation and control method |
CN113947320A (en) * | 2021-10-25 | 2022-01-18 | 国网天津市电力公司电力科学研究院 | Power grid regulation and control method based on multi-mode reinforcement learning |
CN114157021A (en) * | 2021-10-28 | 2022-03-08 | 国网江苏省电力有限公司 | Multi-user cooperative disposal system and method for power grid faults |
CN114157021B (en) * | 2021-10-28 | 2024-01-09 | 国网江苏省电力有限公司 | Multi-person co-processing system and method for power grid faults |
CN113987183A (en) * | 2021-10-29 | 2022-01-28 | 广西电网有限责任公司南宁供电局 | Power grid fault handling plan auxiliary decision-making method based on data driving |
CN114138759A (en) * | 2021-11-08 | 2022-03-04 | 国家电网公司华中分部 | Secondary equipment fault processing and pushing method and system based on knowledge graph reasoning |
CN114912637A (en) * | 2022-05-21 | 2022-08-16 | 重庆大学 | Operation and maintenance decision method and system for man-machine knowledge map manufacturing production line and storage medium |
CN114912637B (en) * | 2022-05-21 | 2023-08-29 | 重庆大学 | Human-computer object knowledge graph manufacturing production line operation and maintenance decision method and system and storage medium |
CN115276003B (en) * | 2022-09-19 | 2023-02-10 | 国网江西省电力有限公司电力科学研究院 | Power distribution station area topological relation identification method based on multi-source data fusion knowledge graph |
CN115276003A (en) * | 2022-09-19 | 2022-11-01 | 国网江西省电力有限公司电力科学研究院 | Power distribution station area topological relation identification method based on multi-source data fusion knowledge graph |
CN115508672A (en) * | 2022-11-22 | 2022-12-23 | 中国电力科学研究院有限公司 | Power grid main equipment fault tracing reasoning method, system, equipment and medium |
CN116415002B (en) * | 2023-04-17 | 2023-11-14 | 合肥工业大学 | Power grid fault recovery error-proof checking method based on graph matching |
CN116415002A (en) * | 2023-04-17 | 2023-07-11 | 合肥工业大学 | Power grid fault recovery error-proof checking method based on graph matching |
CN116629604A (en) * | 2023-05-15 | 2023-08-22 | 国网冀北电力有限公司信息通信分公司 | Method and device for processing and analyzing power grid operation risk |
CN116860989A (en) * | 2023-06-19 | 2023-10-10 | 国网江苏省电力有限公司南京供电分公司 | Power distribution fault processing scheme recommendation method, device, equipment and storage medium |
CN116561588B (en) * | 2023-07-07 | 2023-10-20 | 北京国电通网络技术有限公司 | Power text recognition model construction method, power equipment maintenance method and device |
CN116561588A (en) * | 2023-07-07 | 2023-08-08 | 北京国电通网络技术有限公司 | Power text recognition model construction method, power equipment maintenance method and device |
CN117373487A (en) * | 2023-12-04 | 2024-01-09 | 浙江恒逸石化有限公司 | Audio-based equipment fault detection method and device and related equipment |
CN117373487B (en) * | 2023-12-04 | 2024-02-09 | 浙江恒逸石化有限公司 | Audio-based equipment fault detection method and device and related equipment |
Also Published As
Publication number | Publication date |
---|---|
CN113283704B (en) | 2024-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113283704B (en) | Intelligent power grid fault handling system and method based on knowledge graph | |
CN111768077B (en) | Intelligent identification method for power grid tripping event based on knowledge graph | |
CN110717665B (en) | System and method for fault identification and trend analysis based on scheduling control system | |
CN102236841B (en) | Method for handling accidents of electric power system | |
CN106908690A (en) | Distributed intelligence warning system and its method for diagnosing faults between boss station | |
CN112910089A (en) | Transformer substation secondary equipment fault logic visualization method and system | |
CN103618297B (en) | Efficient high reliability fault handling method towards Complicated Distribution Network | |
CN106532940A (en) | Alarm signal action and time sequence logic relationship analysis method of intelligent substation | |
CN110888973B (en) | Method for automatically structuring and carding monitoring information table | |
CN103326467A (en) | Protection action report implementation method based on information protection main station device recorded information | |
CN109062993A (en) | Method and device for generating offline power grid fault handling plan | |
CN106651198B (en) | Power grid accident auxiliary processing method and system | |
CN111667143A (en) | Method for realizing fusion of real-time monitoring data and service management data in power grid dispatching | |
CN111049266A (en) | Intelligent second-level power restoration method and system for regulation and control service | |
CN116094174A (en) | Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium | |
CN114781662A (en) | Fault line power restoration knowledge reasoning method based on deep learning | |
CN110837027A (en) | Auxiliary decision method and system based on scheduling end key information extraction under power grid fault condition | |
CN110739770A (en) | relay protection tube control system based on information fusion | |
CN113659712A (en) | Power equipment big data label operation platform and method | |
CN104467174A (en) | Transformer station monitoring alarm information auxiliary processing system | |
CN104483595A (en) | Transmission line malfunction online analytic method of self-adaptive power system | |
CN107977774A (en) | A kind of method of electrical network weak link automatic identification after failure | |
CN112101422B (en) | Typical case self-learning method for power system fault case | |
CN107958505A (en) | A kind of stable intelligent inspection system for operating condition and its control method | |
CN114895115B (en) | Fault prediction method based on heuristic search analysis in extra-high voltage direct current protection system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |