CN113761927B - Power grid fault handling real-time auxiliary decision-making method, system, equipment and storage medium - Google Patents
Power grid fault handling real-time auxiliary decision-making method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN113761927B CN113761927B CN202111015300.3A CN202111015300A CN113761927B CN 113761927 B CN113761927 B CN 113761927B CN 202111015300 A CN202111015300 A CN 202111015300A CN 113761927 B CN113761927 B CN 113761927B
- Authority
- CN
- China
- Prior art keywords
- data
- power grid
- fault
- information
- real
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012360 testing method Methods 0.000 claims description 33
- 230000005540 biological transmission Effects 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a system, equipment and a storage medium for real-time auxiliary decision making of power grid fault treatment, wherein the method comprises the following steps: acquiring fault information; and searching and reasoning fault information based on the power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment. By constructing a power grid fault disposal knowledge graph and combining power grid dispatching priori knowledge, the power grid fault real-time auxiliary decision-making method is designed, decision-making can be effectively realized for power grid fault disposal, and power grid dispatching work is supported. Based on knowledge reasoning of the power grid fault handling knowledge graph and real-time power flow data of the power grid, the actual situation of the dispatching service is combined, the power grid fault handling efficiency is improved, the power grid protection work is supported, and the intelligent development of the power service is promoted.
Description
Technical Field
The invention belongs to the field of electric artificial intelligence, and relates to application of an artificial intelligence technology in the field of power grid dispatching. In particular to a method, a system, equipment and a storage medium for real-time auxiliary decision making of power grid fault treatment.
Background
Named entity recognition (Named Entity Recognition, NER) is a fundamental, important technology of natural language processing, aiming at identifying important information from text, typically including various types of information such as time, people, places, etc. The traditional named entity recognition is a scheme based on rules, dictionaries and an online knowledge base, and with the continuous development of machine learning and deep learning, various new algorithms are developed, and the work of manually completing steps such as feature engineering and the like can be relieved by using powerful computing power and learning power of a computer. The BiLSTM-CRF algorithm takes the advantages of the BiLSTM that the BiLSTM has bidirectional long-distance semantic dependence and the CRF considers the label constraint relation on the sequence labeling task into consideration, and the BiLSTM-CRF algorithm becomes a named entity recognition model which is most commonly used in the NER field at present.
The Chinese knowledge graph (Chinese Knowledge Graph) originated at Google Knowledge Graph at the earliest. Is essentially a semantic network. The nodes represent entities (entities) or concepts (concepts), and the edges represent various semantic relationships between entities/concepts. Knowledge graph is good at fusing multi-source heterogeneous information together, and different entities are connected together in a relation mode, so that information is converted into knowledge, and the knowledge graph is an important means in field data research. The knowledge graph construction process involves knowledge extraction, knowledge representation, knowledge fusion and other theories, and at present, the corresponding technologies of the theories are gradually maturing. The knowledge graph is mainly applied to aspects of intelligent search, deep question and answer, network social contact and the like, and is widely applied to many vertical fields such as finance, medical treatment, electronic commerce and the like in recent years.
Aiming at the low power grid fault handling efficiency, the problem of daily power conservation work cannot be met. The prior art does not give an effective solution, how to provide an auxiliary decision in combination with a knowledge graph is a problem to be solved.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a real-time auxiliary decision-making method, a system, equipment and a storage medium for power grid fault treatment.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a real-time auxiliary decision-making method for power grid fault handling, comprising the following steps:
acquiring fault information;
searching and reasoning fault information based on a preset power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of real-time power flow data by combining the real-time power flow data of power grid equipment.
As a further improvement of the invention, the preset power grid fault handling knowledge graph is constructed by adopting the following method:
dividing the power grid field data into structured data, semi-structured data and unstructured data according to the power grid field data analysis;
respectively carrying out data entity identification on the structured data, the semi-structured data and the unstructured data, and extracting to obtain a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table;
respectively constructing an ontology model for the structured data, the semi-structured data and the unstructured data, and combining the three types of ontology models to finish the construction of the fault handling ontology model; and connecting the data graph base and automatically eliminating repeated nodes and relations based on the power grid fault entity base to construct a power grid fault handling knowledge graph.
As a further improvement of the invention, the structured data comprise power grid operation section data, and the topological structure of the power grid equipment and the operation state of the power grid equipment can be obtained through analysis of the power grid operation section data;
the semi-structured data includes a grid fault handling plan;
the unstructured data includes grid dispatch control management procedures.
As a further improvement of the present invention, the data entity identification of the structured data specifically includes:
matching connected topological nodes in the running section data of the power grid by using topological attributes among the devices, indirectly supplementing missing relations by combining the names of the devices and the intervals of the devices, and automatically constructing a summary table of the topological relations of the devices; and after one-time wiring diagram verification with the power grid equipment, obtaining the equipment topology information data summary table.
As a further improvement of the present invention, the data entity identification of the semi-structured data specifically includes:
locking the normalized information according to the corresponding transformer substation or fault case name, and extracting the normalized information into a plan data table;
identifying key fields before and after target information, locking the target information, removing invalid characters and matching the key information by using a regularization expression method, and extracting the key information into a plan data table;
and the fault treatment plan information is automatically extracted to obtain a fault plan information summary table by means of locking the target information.
As a further improvement of the present invention, the data entity identification of the unstructured data specifically includes:
and extracting text features by using a language model to obtain a word granularity vector matrix, extracting context information by using a bidirectional long-short-term memory neural network, and extracting a global optimal sequence by combining a conditional random field model to obtain a scheduling naming entity and further scheduling procedure information summary.
As a further improvement of the present invention, the searching and reasoning of fault information based on the power grid fault handling knowledge graph, and the real-time auxiliary decision of the real-time power flow data in combination with the real-time power flow data of the power grid equipment, specifically include:
searching in the knowledge graph by using the fault information to obtain a fault point and a fault type, and pushing a power grid fault treatment plan of corresponding fault information after confirming the fault information and a corresponding touch finger strategy;
judging whether the equipment has the test conditions or not based on the real-time tide data of the equipment and the test conditions in the knowledge graph; after judging the conditions, confirming the pushing test operation and calculating whether the test is successful or not by combining the tide data:
if the test is successful, the fault handling is finished;
if the trial transmission fails, judging whether switching operation is carried out or not by combining the knowledge graph, confirming switching operation deduced by the knowledge graph, judging whether equipment resumes power transmission after the switching operation is finished, and if the equipment resumes power transmission and confirms that fault treatment is finished after the power transmission operation.
A grid fault handling real-time auxiliary decision system, comprising:
the acquisition module is used for acquiring fault information;
and the auxiliary decision-making module is used for searching and reasoning fault information based on the power grid fault handling knowledge graph and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment.
As a further improvement of the invention, the power grid fault handling knowledge graph in the auxiliary decision module is constructed by adopting the following method:
dividing the power grid field data into structured data, semi-structured data and unstructured data according to the power grid field data analysis;
respectively carrying out data entity identification on the structured data, the semi-structured data and the unstructured data, and extracting to obtain a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table;
respectively constructing an ontology model for the structured data, the semi-structured data and the unstructured data, and combining the three types of ontology models to finish the construction of the fault handling ontology model; and connecting the data graph base and automatically eliminating repeated nodes and relations based on the power grid fault entity base to construct a power grid fault handling knowledge graph.
As a further development of the invention, the auxiliary decision module is specifically configured to: searching in the knowledge graph by using the fault information to obtain a fault point and a fault type, and pushing a power grid fault treatment plan of corresponding fault information after confirming the fault information and a corresponding touch finger strategy;
judging whether the equipment has the test conditions or not based on the real-time tide data of the equipment and the test conditions in the knowledge graph; after judging the conditions, confirming the pushing test operation and calculating whether the test is successful or not by combining the tide data:
if the test is successful, the fault handling is finished;
if the trial transmission fails, judging whether switching operation is carried out or not by combining the knowledge graph, confirming switching operation deduced by the knowledge graph, judging whether equipment resumes power transmission after the switching operation is finished, and if the equipment resumes power transmission and confirms that fault treatment is finished after the power transmission operation.
An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the grid fault handling real-time auxiliary decision method when the computer program is executed.
A computer readable storage medium storing a computer program which when executed by a processor implements the steps of the grid fault handling real-time auxiliary decision method.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, a real-time auxiliary decision-making method for power grid faults is designed by combining a preset power grid fault treatment knowledge graph with power grid dispatching priori knowledge, so that decision-making for power grid fault treatment can be effectively realized, and power grid dispatching work is supported. Based on knowledge reasoning of a preset power grid fault handling knowledge graph and real-time power flow data of the power grid, the actual condition of dispatching business is combined, the power grid fault handling efficiency is improved, the power grid protection work is supported, and the intelligent development of the power business is promoted.
Drawings
FIG. 1 is a flow chart of a method for real-time auxiliary decision-making for grid fault handling;
FIG. 2 is a flow chart of a grid fault handling real-time auxiliary decision method of the preferred embodiment;
FIG. 3 is a schematic diagram of a data feature analysis flow;
FIG. 4 is a schematic diagram of a knowledge graph ontology model;
FIG. 5 is a schematic diagram of a real-time decision-assist business process;
FIG. 6 is an example of an auxiliary decision;
FIG. 7 is a schematic diagram of a system for real-time auxiliary decision-making for grid fault handling according to the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings in connection with embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
The following detailed description is exemplary and is intended to provide further details of the invention. Unless defined otherwise, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the invention.
As shown in fig. 1, the method for assisting in deciding power grid fault handling in real time comprises the following steps: acquiring fault information;
and searching and reasoning fault information based on the power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment.
Based on knowledge reasoning of a power grid fault handling knowledge graph and real-time power flow data of a power grid, the method combines actual conditions of dispatching business, achieves improvement of power grid fault handling efficiency, supports power-preserving work of a national grid company, and promotes intelligent development of power business.
The power grid fault handling knowledge graph is constructed by the following method:
dividing the power grid field data into structured data, semi-structured data and unstructured data according to the power grid field data analysis;
respectively carrying out data entity identification on the structured data, the semi-structured data and the unstructured data, and extracting to obtain a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table;
respectively constructing an ontology model for the structured data, the semi-structured data and the unstructured data, and combining the three types of ontology models to finish the construction of the fault handling ontology model; and connecting the data graph base and automatically eliminating repeated nodes and relations based on the power grid fault entity base to construct a power grid fault handling knowledge graph.
As a preferred embodiment, the searching and reasoning of fault information based on the power grid fault handling knowledge graph, and the real-time auxiliary decision of the real-time power flow data in combination with the real-time power flow data of the power grid equipment, specifically include:
searching in the knowledge graph by using the fault information to obtain a fault point and a fault type, and pushing a power grid fault treatment plan of corresponding fault information after confirming the fault information and a corresponding touch finger strategy;
judging whether the equipment has the test conditions or not based on the real-time tide data of the equipment and the test conditions in the knowledge graph; after judging the conditions, confirming the pushing test operation and calculating whether the test is successful or not by combining the tide data:
if the test is successful, the fault handling is finished;
if the trial transmission fails, judging whether switching operation is carried out or not by combining the knowledge graph, confirming switching operation deduced by the knowledge graph, judging whether equipment resumes power transmission after the switching operation is finished, and if the equipment resumes power transmission and confirms that fault treatment is finished after the power transmission operation.
The following describes the present invention in detail, and specifically includes the following steps with reference to fig. 2:
step one: power grid domain data analysis
In combination with the data profiling shown in fig. 3, the data assisting in grid fault handling is diverse. The structural division can be divided into structured data, semi-structured data and unstructured data.
a) The power grid operation section data are structured data reflecting the information of the power grid real-time operation equipment, and the topological structure of the power grid equipment and the operation state of the power grid equipment can be obtained through analysis of the power grid operation section data. The processing mode is direct extraction.
b) Grid fault handling plans are necessary reference texts in the fault handling process, including important data such as substation profiles, fault phenomena and emergency handling measures. The treatment plan has good compiling habit, relatively uniform content and consistent editing format, and belongs to semi-structured data. The processing mode is keyword extraction.
c) The power grid dispatching control management regulation is regulation and provision according to the power grid dispatching control management work, and is important auxiliary decision reference data in power grid fault handling work. The scheduling procedure data are unstructured data and have smaller data volume, and the traditional entity recognition algorithm cannot meet the recognition requirement, so that the entity recognition technology based on transfer learning is adopted for entity recognition. The processing mode is deep learning.
And the original data is extracted to obtain a power grid fault finger entity library.
Step two: data entity identification
Described in connection with fig. 4, includes:
step 2.1: structured and semi-structured data entity identification
The power grid operation section data reflects the power grid operation state through the power grid equipment operation parameters and simultaneously contains equipment names and topological relations among the equipment. The topological properties of 7 types of equipment such as transformers, buses, switches, disconnecting links, capacitors and the like are utilized to match and connect topological nodes in the running section data of the power grid, and missing relations are indirectly supplemented by combining equipment names and the intervals, so that the total table of the topological relations of the equipment is automatically built. The equipment topological relation obtained by the method is proved to be accurate through one-time wiring diagram verification with power grid equipment. Obtaining a device topology information data summary table.
The fault handling plan has larger information quantity, and comprises standardized contents such as substation and line guard personnel information, dispatcher information, switching operation, power transmission recovery operation and the like, and differentiated contents such as basic information of the substation and typical fault handling information and the like. Firstly, locking normalized information according to the corresponding transformer substation or fault case name, and extracting the normalized information into a plan data table. And identifying key fields before and after target information, locking the target information, removing invalid characters and matching the key information by using a regularization expression method, and extracting the invalid characters and the key information into a plan data table. And the automatic extraction of the fault handling plan information is realized by locking the target information. And obtaining a fault plan information summary table.
Step 2.2: unstructured data entity identification
And performing entity identification on the scheduling procedure data by adopting a BERT-BiLSMT-CRF model. Firstly, text feature extraction is carried out by using a BERT language model of Google open source to obtain a word granularity vector matrix, biLSTM is used for extracting context information, meanwhile, a global optimal sequence is extracted by combining a CRF model (conditional random field model), and finally, a scheduling naming entity and further a scheduling procedure information summary table are obtained.
Among them, long and short memory neural networks (LSTM) are popular recurrent neural networks, which are not only sensitive to short-term inputs, but also preserve long-term states.
(1) Forgetting the decision of keeping the cell state ct-1 to the current time ct, wherein the calculation formula is as shown in formula (1):
f t ＝σ(w fh ·h t-1 +w fx ·x t +b f ) (1)
wherein w is fh Corresponding to input item h t-1 ；w fx Corresponding input item x t ；w fh And w fx Weight matrix w for forming forgetting gate f ，b f For offset top, σ is the activation function.
(2) Input gate current input x t Save to c t The calculation formula is shown as formula (2):
i t ＝σ(w i ·[h t-1 ,x t ]+b i ) (2)
wherein w is i As a weight matrix, b i Is an offset roof.
By usingRepresenting the state of the cell currently being input, as determined by the last output and the current input, e.g. formula(3)：
Current time cell state c t As formula (4):
wherein, c t-1 Representing the state of the previous cell, f t Is a forgetful door. Sign symbolRepresenting multiplication by element.
(3) Output gate, calculating as formula (5):
the input gate and cell states determine the output of the long and short term memory neural network as in equation (6):
the neural network can automatically extract features according to the distributed expression of words in the text, and a BiLSTM-CRF model of word vectors finds a globally optimal labeling sequence by using labels which are predicted by the CRF layer by utilizing the context after the BiLSTM (two-way long and short memory neural network) outputs a prediction.
Step three: knowledge graph construction
An ER model (Entity-relationship model) may be employed for the structured data for the ontology model design. For unstructured data and semi-structured data, a top-down construction mode is adopted, and a Prot ontology construction tool is utilized to construct an ontology model. And finally, combining the three types of ontology models to complete the construction of the fault handling ontology model. The ontology model is shown in figure 5.
Based on a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table, a Py2Neo (python drive of a Neo4j database) is utilized to connect a Neo4j (a high-performance NOSQL graphic database) graph database, and repeated nodes and relations are automatically removed through a Merge (functions in SQL sentences for merging) method, so that a power grid fault handling knowledge graph is constructed.
Of course, the present application is not limited to the above specific model and algorithm, but only gives a best implementation, and other models and algorithms can be used to achieve the above object.
Step four: real-time auxiliary decision making method
The real-time fault handling assistance is a fault assistance handling method for searching and reasoning fault handling knowledge based on a power grid fault handling knowledge graph and combining real-time power flow data of power grid equipment. When a fault occurs, searching in a knowledge graph according to fault information, deducing a fault point and a fault type, and pushing a disposal flow and notes of the corresponding fault for the fault after manual confirmation. And judging whether the equipment has the test-delivery condition or not based on the real-time power flow data of the equipment and the related knowledge of the test-delivery condition in the knowledge graph. After judging the condition, the pushing test operation is confirmed manually, and whether the test is successful is calculated by combining the tide data. If the test is successful, the fault handling is ended. If the trial delivery fails, judging whether switching operation is performed or not according to the knowledge graph. And (3) a switching operation flow deduced by a manual intervention confirmation knowledge graph is needed, judging whether the equipment recovers power transmission after switching is finished, and if the equipment recovers power transmission and manually confirms power transmission operation, finishing fault treatment. The real-time auxiliary decision-making business process is shown in figure 6.
Examples
And realizing the real-time auxiliary decision function module based on the real-time auxiliary decision service flow. The knowledge-graph-based real-time auxiliary decision function is taken as a core, and provincial and regional collaborative fault handling application can be provided. The application selects the django (python language frame) of the web application frame as a front-end page development frame, integrates the entity recognition model with the training completion and the power grid fault handling knowledge graph, and realizes the storage and visualization of various knowledge. Through a friendly man-machine interaction interface, two functions of intelligent diagnosis and auxiliary decision making are mainly realized.
Judging whether the faults reach the degree of the major event according to the fault phenomenon fed back on site and the major event category and basis obtained by knowledge reasoning, and if the faults need to be reported to an upper level, deducing the attribute of a dispatching unit of a transformer substation where the fault equipment is located and the information of a dispatching attendant of the transformer substation, the transformer substation and a line attendant through a knowledge graph.
In the fault handling process, the application can provide real-time operating parameters of equipment including bus voltage, transformer load rate and the like for a dispatcher. According to the power grid fault handling knowledge graph, an application can make an auxiliary fault handling decision for a dispatcher according to the equipment state and the handling progress, and when operations such as trial transmission, switching and power transmission recovery are required in the fault handling process, the application can automatically acquire response data to calculate whether the response data accords with the operation conditions. If the operation conditions are met, the application informs the dispatcher, and the treatment operation can be performed after the manual confirmation. In addition to the malfunctioning device, the application will also focus on and demonstrate the behavior of the neighboring devices in order for the dispatcher to conduct the load-shedding work. The fault handling steps are displayed in the form of nodes, so that the retrospective handling process in the process of scheduling work is convenient. Taking conventional line fault treatment as an example, the conventional treatment is often 30 minutes, and the application treatment time can be reduced to 12 minutes, so that the power grid fault treatment efficiency is improved. An example of an auxiliary decision is shown in fig. 5.
As shown in fig. 7, another object of the present invention is to propose a real-time auxiliary decision system for grid fault handling, comprising:
the acquisition module is used for acquiring fault information;
and the auxiliary decision-making module is used for searching and reasoning fault information based on the power grid fault handling knowledge graph and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment.
Preferably, the power grid fault handling knowledge graph in the auxiliary decision module is constructed by adopting the following method:
dividing the power grid field data into structured data, semi-structured data and unstructured data according to the power grid field data analysis;
respectively carrying out data entity identification on the structured data, the semi-structured data and the unstructured data, and extracting to obtain a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table;
respectively constructing an ontology model for the structured data, the semi-structured data and the unstructured data, and combining the three types of ontology models to finish the construction of the fault handling ontology model; and connecting the data graph base and automatically eliminating repeated nodes and relations based on the power grid fault entity base to construct a power grid fault handling knowledge graph.
Preferably, the auxiliary decision module is specifically configured to: searching in the knowledge graph by using the fault information to obtain a fault point and a fault type, and pushing a power grid fault treatment plan of corresponding fault information after confirming the fault information and a corresponding touch finger strategy;
judging whether the equipment has the test conditions or not based on the real-time tide data of the equipment and the test conditions in the knowledge graph; after judging the conditions, confirming the pushing test operation and calculating whether the test is successful or not by combining the tide data:
if the test is successful, the fault handling is finished;
if the trial transmission fails, judging whether switching operation is carried out or not by combining the knowledge graph, confirming switching operation deduced by the knowledge graph, judging whether equipment resumes power transmission after the switching operation is finished, and if the equipment resumes power transmission and confirms that fault treatment is finished after the power transmission operation.
As shown in fig. 8, a third object of the present invention is to provide an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, which when executed by the processor implements the steps of the grid fault handling real-time auxiliary decision method.
The power grid fault handling real-time auxiliary decision-making method comprises the following steps of:
acquiring fault information;
and searching and reasoning fault information based on the power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment.
A fourth object of the present invention is to provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the grid fault handling real-time auxiliary decision method.
The power grid fault handling real-time auxiliary decision-making method comprises the following steps of:
acquiring fault information;
and searching and reasoning fault information based on the power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (8)
1. The real-time auxiliary decision-making method for power grid fault treatment is characterized by comprising the following steps of:
acquiring fault information;
searching and reasoning fault information based on a preset power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of real-time power flow data by combining the real-time power flow data of power grid equipment;
the preset power grid fault handling knowledge graph is constructed by the following method:
dividing the power grid field data into structured data, semi-structured data and unstructured data according to the power grid field data analysis;
respectively carrying out data entity identification on the structured data, the semi-structured data and the unstructured data, and extracting to obtain a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table;
respectively constructing an ontology model for the structured data, the semi-structured data and the unstructured data, and combining the three types of ontology models to finish the construction of the fault handling ontology model; based on a power grid fault entity library, connecting a data graph library and automatically eliminating repeated nodes and relations to construct a power grid fault handling knowledge graph;
searching and reasoning fault information based on a preset power grid fault handling knowledge graph, and carrying out real-time auxiliary decision-making of real-time power flow data by combining the real-time power flow data of power grid equipment, wherein the method specifically comprises the following steps:
searching in the knowledge graph by using the fault information to obtain a fault point and a fault type, and pushing a power grid fault treatment plan of corresponding fault information after confirming the fault information and a corresponding touch finger strategy;
judging whether the equipment has the test conditions or not based on the real-time tide data of the equipment and the test conditions in the knowledge graph; after judging the conditions, confirming the pushing test operation and calculating whether the test is successful or not by combining the tide data:
if the test is successful, the fault handling is finished;
if the trial transmission fails, judging whether switching operation is carried out or not by combining the knowledge graph, confirming switching operation deduced by the knowledge graph, judging whether equipment resumes power transmission after the switching operation is finished, and if the equipment resumes power transmission and confirms that fault treatment is finished after the power transmission operation.
2. The method according to claim 1, characterized in that:
the structural data comprise power grid operation section data, and the topological structure of power grid equipment and the operation state of the power grid equipment can be obtained through analysis of the power grid operation section data;
the semi-structured data includes a grid fault handling plan;
the unstructured data includes grid dispatch control management procedures.
3. The method according to claim 1, characterized in that:
the data entity identification of the structured data specifically comprises the following steps:
matching connected topological nodes in the running section data of the power grid by using topological attributes among the devices, indirectly supplementing missing relations by combining the names of the devices and the intervals of the devices, and automatically constructing a summary table of the topological relations of the devices; and after one-time wiring diagram verification with the power grid equipment, obtaining the equipment topology information data summary table.
4. The method according to claim 1, characterized in that:
the data entity identification of the semi-structured data specifically comprises the following steps:
locking the normalized information according to the corresponding transformer substation or fault case name, and extracting the normalized information into a plan data table;
identifying key fields before and after target information, locking the target information, removing invalid characters and matching the key information by using a regularization expression method, and extracting the key information into a plan data table;
and the fault treatment plan information is automatically extracted to obtain a fault plan information summary table by means of locking the target information.
5. The method according to claim 1, characterized in that:
the method for identifying the data entity of the unstructured data specifically comprises the following steps:
and extracting text features by using a language model to obtain a word granularity vector matrix, extracting context information by using a bidirectional long-short-term memory neural network, and extracting a global optimal sequence by combining a conditional random field model to obtain a scheduling naming entity and further scheduling procedure information summary.
6. A grid fault handling real-time auxiliary decision system, comprising:
the acquisition module is used for acquiring fault information;
the auxiliary decision-making module is used for searching and reasoning fault information based on the power grid fault handling knowledge graph and carrying out real-time auxiliary decision-making of the real-time power flow data by combining the real-time power flow data of the power grid equipment;
the power grid fault handling knowledge graph in the auxiliary decision module is constructed by adopting the following method:
dividing the power grid field data into structured data, semi-structured data and unstructured data according to the power grid field data analysis;
respectively carrying out data entity identification on the structured data, the semi-structured data and the unstructured data, and extracting to obtain a power grid fault entity library consisting of a device topology information data summary table, a fault plan information summary table and a scheduling procedure information summary table;
respectively constructing an ontology model for the structured data, the semi-structured data and the unstructured data, and combining the three types of ontology models to finish the construction of the fault handling ontology model; based on a power grid fault entity library, connecting a data graph library and automatically eliminating repeated nodes and relations to construct a power grid fault handling knowledge graph;
the auxiliary decision module is specifically configured to: searching in the knowledge graph by using the fault information to obtain a fault point and a fault type, and pushing a power grid fault treatment plan of corresponding fault information after confirming the fault information and a corresponding touch finger strategy;
judging whether the equipment has the test conditions or not based on the real-time tide data of the equipment and the test conditions in the knowledge graph; after judging the conditions, confirming the pushing test operation and calculating whether the test is successful or not by combining the tide data:
if the test is successful, the fault handling is finished;
if the trial transmission fails, judging whether switching operation is carried out or not by combining the knowledge graph, confirming switching operation deduced by the knowledge graph, judging whether equipment resumes power transmission after the switching operation is finished, and if the equipment resumes power transmission and confirms that fault treatment is finished after the power transmission operation.
7. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the grid fault handling real-time auxiliary decision method of any of claims 1-5 when the computer program is executed.
8. A computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the grid fault handling real-time auxiliary decision method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015300.3A CN113761927B (en) | 2021-08-31 | 2021-08-31 | Power grid fault handling real-time auxiliary decision-making method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015300.3A CN113761927B (en) | 2021-08-31 | 2021-08-31 | Power grid fault handling real-time auxiliary decision-making method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113761927A CN113761927A (en) | 2021-12-07 |
| CN113761927B true CN113761927B (en) | 2024-02-06 |
Family
ID=78792262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111015300.3A Active CN113761927B (en) | 2021-08-31 | 2021-08-31 | Power grid fault handling real-time auxiliary decision-making method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761927B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN116644810B (en) * | 2023-05-06 | 2024-04-05 | 国网冀北电力有限公司信息通信分公司 | Power grid fault risk treatment method and device based on knowledge graph |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605771A (en) * | 2013-11-28 | 2014-02-26 | 东莞中国科学院云计算产业技术创新与育成中心 | Intelligent assistant decision and maintenance system and method for operating same |
| CN109816161A (en) * | 2019-01-14 | 2019-05-28 | 中国电力科学研究院有限公司 | A kind of power distribution network operation computer-aided decision support System and its application method |
| CN110795532A (en) * | 2019-10-18 | 2020-02-14 | 珠海格力电器股份有限公司 | Voice information processing method and device, intelligent terminal and storage medium |
| CN111428054A (en) * | 2020-04-14 | 2020-07-17 | 中国电子科技网络信息安全有限公司 | Construction and storage method of knowledge graph in network space security field |
| CN111444351A (en) * | 2020-03-24 | 2020-07-24 | 清华苏州环境创新研究院 | Method and device for constructing knowledge graph in industrial process field |
| CN111552820A (en) * | 2020-04-30 | 2020-08-18 | 江河瑞通（北京）技术有限公司 | Water engineering scheduling data processing method and device |
| CN112541600A (en) * | 2020-12-07 | 2021-03-23 | 上海电科智能系统股份有限公司 | Knowledge graph-based auxiliary maintenance decision method |
| CN112699681A (en) * | 2020-12-17 | 2021-04-23 | 国网冀北电力有限公司信息通信分公司 | Power communication system defect fault order dispatching method and device based on knowledge graph |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636131A (en) * | 2018-11-21 | 2019-04-16 | 北京域天科技有限公司 | A kind of emergency communication intelligent emergent DSS |
-
2021
- 2021-08-31 CN CN202111015300.3A patent/CN113761927B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605771A (en) * | 2013-11-28 | 2014-02-26 | 东莞中国科学院云计算产业技术创新与育成中心 | Intelligent assistant decision and maintenance system and method for operating same |
| CN109816161A (en) * | 2019-01-14 | 2019-05-28 | 中国电力科学研究院有限公司 | A kind of power distribution network operation computer-aided decision support System and its application method |
| CN110795532A (en) * | 2019-10-18 | 2020-02-14 | 珠海格力电器股份有限公司 | Voice information processing method and device, intelligent terminal and storage medium |
| CN111444351A (en) * | 2020-03-24 | 2020-07-24 | 清华苏州环境创新研究院 | Method and device for constructing knowledge graph in industrial process field |
| CN111428054A (en) * | 2020-04-14 | 2020-07-17 | 中国电子科技网络信息安全有限公司 | Construction and storage method of knowledge graph in network space security field |
| CN111552820A (en) * | 2020-04-30 | 2020-08-18 | 江河瑞通（北京）技术有限公司 | Water engineering scheduling data processing method and device |
| CN112541600A (en) * | 2020-12-07 | 2021-03-23 | 上海电科智能系统股份有限公司 | Knowledge graph-based auxiliary maintenance decision method |
| CN112699681A (en) * | 2020-12-17 | 2021-04-23 | 国网冀北电力有限公司信息通信分公司 | Power communication system defect fault order dispatching method and device based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113761927A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113761927B (en) | Power grid fault handling real-time auxiliary decision-making method, system, equipment and storage medium | |
| CN115357726A (en) | Fault disposal plan digital model establishing method based on knowledge graph | |
| CN115293507A (en) | Situation knowledge graph construction method and system for power grid dispatching operation management | |
| CN112100397A (en) | Electric power plan knowledge graph construction method and system based on bidirectional gating circulation unit | |
| CN112434532B (en) | Power grid environment model supporting man-machine bidirectional understanding and modeling method | |
| Fan et al. | How to construct a power knowledge graph with dispatching data? | |
| CN102243649A (en) | Semi-automatic information extraction processing device of ontology | |
| CN113946684A (en) | Electric power capital construction knowledge graph construction method | |
| CN113627797A (en) | Image generation method and device for employee enrollment, computer equipment and storage medium | |
| Pan et al. | A new regret theory-based risk decision-making method for renewable energy investment under uncertain environment | |
| CN112434129A (en) | Method and system for generating professional corpus in power grid dispatching field | |
| Qu et al. | Knowledge-driven recognition methodology for electricity safety hazard scenarios | |
| Jiang et al. | Construction of substation engineering design knowledge graph based on “ontology seven-step method” | |
| CN116523042A (en) | Combined extraction method and system for power grid dispatching entity relationship | |
| Chen et al. | Research review of the knowledge graph and its application in power system dispatching and operation | |
| CN114328959B (en) | Knowledge graph construction and use method, device, equipment and medium | |
| Zhu et al. | Review on knowledge graph and its application in power dispatching | |
| CN116304070A (en) | Automatic generation method of power grid emergency treatment scheme based on knowledge graph construction | |
| CN115203427A (en) | Power system regulation and control regulation knowledge graph management system, knowledge graph generation method and storage medium | |
| Tang et al. | On constructing semantic decision tables | |
| Gao et al. | Research on power entity recognition technology base on BiLSTM-CRF | |
| Wang et al. | Research and application of knowledge graph in distribution network dispatching and control aided decision making | |
| Yan et al. | Construction of Dynamic Knowledge Graph for Grid day-ahead Scheduling Optimization Decision | |
| Gao et al. | GridOnto: knowledge representation and extraction for fault events in power grid | |
| Ji et al. | Construction and application of knowledge graph for grid dispatch fault handling based on pre-trained model |
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 |