CN115953146B - Auxiliary decision-making system for fault treatment of power distribution network - Google Patents
Auxiliary decision-making system for fault treatment of power distribution network Download PDFInfo
- Publication number
- CN115953146B CN115953146B CN202211579008.9A CN202211579008A CN115953146B CN 115953146 B CN115953146 B CN 115953146B CN 202211579008 A CN202211579008 A CN 202211579008A CN 115953146 B CN115953146 B CN 115953146B
- Authority
- CN
- China
- Prior art keywords
- fault
- module
- processing
- decision
- knowledge graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 claims abstract description 164
- 230000003993 interaction Effects 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 230000002452 interceptive effect Effects 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 18
- 230000004048 modification Effects 0.000 claims description 10
- 238000012986 modification Methods 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 abstract description 8
- 239000000284 extract Substances 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 5
- 230000008676 import Effects 0.000 description 5
- 238000010998 test method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 208000025274 Lightning injury Diseases 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution network fault processing auxiliary decision-making system, which comprises an interface interaction module, a fault processing knowledge graph, a file analysis module, an entity relation extraction module and a fault decision-making processing module, wherein an importing interaction interface module in the interface interaction module is used for receiving related files uploaded by a dispatcher, the file analysis module analyzes contents, and the entity relation extraction module extracts power distribution network entities and relations and stores the power distribution network entities and relations in the fault processing knowledge graph; the fault processing decision-making interaction interface module is connected with the fault decision-making processing module, and a fault processing decision-making suggestion module in the fault decision-making processing module obtains an inference conclusion after reasoning; the similar historical fault recommending module calculates a historical fault similar to k before the current accident and outputs the historical fault; the rule management interactive interface module is used for displaying fault processing rules and power distribution network fault regulations to a dispatcher. The invention realizes the advantages of recommending fault treatment suggestions, reducing response time and having maintainability and stability.
Description
Technical Field
The invention relates to the technical field of power distribution networks, in particular to a power distribution network fault processing auxiliary decision-making system.
Background
The fault handling decision service can be generally divided into two major problems of immediate fault handling and how to handle faults. Wherein the fault handling can be immediately related to the forward factor and the reverse factor of the fault handling. The forward factor refers to the urgency of the current line fault handling requirements. The urgency of immediate fault handling is also different for different faults due to the different line itself and site conditions. When a line for supplying power to an organization such as a hospital or a railway is tripped, the emergency degree of fault handling is higher than that of a normal line. The reverse factor is the risk that the fault handling may be performed. For example, live working plans currently exist for faulty lines, and the handling of a trade fault may pose a significant threat to the personnel safety of the operators. Generally for fault handling decisions, there are three basic principles:
(1) If there are any reverse factors of the fault handling, the fault handling cannot be immediately performed, and it is necessary to wait for the reverse factors to completely disappear.
(2) If there is no fault handling reversing factor and there is a fault handling forward factor, the fault handling should be immediate.
(3) If the forward factor and the reverse factor are not present, the line station needs to be inspected and the fault processing is tried again.
How fault handling refers to what operations the dispatcher should perform in what order under the current fault condition. For example, the dispatcher needs to consider the mode of carrying out the forced power transmission, whether the remote control or the personnel operation in the command station are carried out, and whether the fault processing is carried out from the transmitting end or the receiving end of the line. These problems are in principle dependent on the content of the distribution network line fault handling procedure, but the content of the procedure is that the distribution network scheduling expert composes based on his own knowledge and cannot correspond to all field fault conditions. Therefore, currently, when handling how to deal with the fault handling problem, a dispatcher generally comprehensively makes a dispatching decision under the framework of a power distribution network fault handling rule and combining own fault handling experience.
The following problems are common in the current fault handling decision process:
(1) Repeated confirmation of the protocol. Because the distribution network fault handling procedure items are numerous, complex and changeable, a dispatcher needs to read through the procedure to review a large number of terms, and repeatedly confirms to ensure that no omission exists when fault handling decisions are made, and reliability and timeliness cannot be considered.
(2) The efficiency of obtaining the line information is low. The number of the entities of the distribution network is large, when a dispatcher refers to different information of the same line, the dispatcher needs to call a plurality of documents of different types to inquire respectively, and the efficiency is low.
(3) Personal treatment experience is limited. The processing experience of a single dispatcher often has limitation, when faults which are not explicitly described in a procedure and are not processed by the dispatcher are encountered, the dispatcher needs to inform an upper level, give feedback after being discussed by a plurality of dispatching expert systems, and delay the processing time of the faults.
Disclosure of Invention
Aiming at the problems of repeated confirmation of rules, low efficiency of obtaining line information and delay of fault processing time due to limited personal processing experience in the conventional fault processing decision process, the invention provides an auxiliary decision system for power distribution network fault processing, which can realize recommendation of fault processing suggestions, reduce response time and has the advantages of maintainability and stability.
The technical scheme adopted is as follows:
the auxiliary decision-making system for power distribution network fault processing comprises a computer, an interface interaction module, a fault processing knowledge graph, a file analysis module, an entity relation extraction module and a fault decision-making processing module, wherein the interface interaction module is operated in the computer and comprises a file importing interaction interface module, a fault processing decision-making interaction interface module and a rule management interaction interface module;
the system comprises a file analysis module, a file type analysis module, a fault processing knowledge graph, a power distribution network entity and a power distribution network entity relation extraction module, wherein the file analysis module is used for confirming the file type and analyzing the content of the file type through the file name and suffix name modes of various power related files;
the fault processing decision-making interaction interface module is used for receiving the field accident situation uploaded by a dispatcher and is connected with the fault decision-making processing module, the fault decision-making processing module comprises a fault processing decision-making suggestion module and a similar historical fault recommendation module, and after the fault processing decision-making suggestion module utilizes a fault processing rule in the fault processing knowledge graph to carry out related reasoning on a line, whether immediate fault processing, fault processing emergency degree and all non-fault processing reasons are given for the received field situation; the similarity history fault recommendation module calculates a history fault similar to k before the current accident in the fault processing knowledge graph by using a similarity algorithm, and gives out a fault situation, a fault result and a processing mode of the similar fault in a text form;
the rule management interactive interface module is used for graphically displaying fault processing rules and power distribution network fault regulations in the fault processing knowledge graph to a dispatcher.
Further, the fault processing knowledge graph is respectively connected with the entity relation extraction module, the fault decision processing module and the rule management interaction interface module through a knowledge graph access interface module, and the knowledge graph access interface module is used for providing an access interface for storing a knowledge graph database.
Further, a follow-up processing suggestion module is further arranged in the fault decision processing module, receives the scene accident situation transmitted by the dispatcher, and gives out the relevant handling actions in the power distribution network procedure processing and instantiates after reasoning the procedure in the fault processing knowledge graph and the line relevant data, so as to guide the follow-up processing scheme of the dispatcher.
Further, the rule management interactive interface module is also connected with a rule management module, and the rule management module performs data transmission with the fault processing knowledge graph through the knowledge graph access interface module.
Further, a rule display module is arranged in the rule management module, and the relationship among all the current rules in the fault processing knowledge graph and the rules is intuitively displayed in a Neo4j browsing graph mode.
Further, a rule modification module and a rule updating module are further arranged in the rule management module, and a dispatcher directly adds and deletes rules in the fault processing knowledge graph through a Cypher statement in the rule modification module and directly modifies conditional statements, action statements and the like; and the rule updating module converts the modified fault processing rules in the fault processing knowledge graph into DRL rule files, and stores the DRL rule files in the KieContainer1 and KieContainer2 objects for the fault processing decision suggestion module and the subsequent processing suggestion module.
Preferably, the fault handling decision suggestion module performs fault handling decision making by: the DRL rules stored in the KieContainer1 object, the related entity information in the fault processing knowledge graph and the real-time fault information stored in the dfact object are externally transmitted through the rule management module, and all the DRL rules and the related entity information are imported into the kSession; performing fault handling reasoning by adopting a fireAllRules () method of a Drools engine; and (3) after reasoning, obtaining whether the current line fault should be processed immediately, the emergency degree of the current line fault demand fault processing and the conclusion of all the current reasons which cause the fault processing incapability.
Preferably, fault handling reasoning is performed by adopting a fireallroles () method of a Drools engine, and the fault handling reasoning algorithm is as follows:
further preferably, the similarity history fault recommending module calculates the similarity between the current fault and the history faults obtained by inquiring all knowledge maps through fault lines and fault information input by a dispatcher, and outputs the first 3-5 history faults with the highest similarity to the fault processing decision-making interaction interface module.
The similarity history fault recommending module obtains the first k history faults through a similarity algorithm, and the similarity algorithm is:
the technical scheme of the invention has the following advantages:
A. the invention has the automatic importing function: the system receives and automatically analyzes various types of documents such as excel forms, word documents and the like uploaded by a dispatcher, and extracts related entities of power distribution network fault processing, including stations, lines, historical faults and the like. And then automatically updating the attributes and the relations of the nodes in the map.
B. The invention has the rule management function: the system allows a dispatcher to check related fault handling rules in the existing map, allows a map administrator to delete and check the fault handling rules, and the modified fault handling rules can be directly reflected to the results of fault handling reasoning.
C. The invention has the fault processing reasoning function: the system receives real-time fault information and line overall information input by a dispatcher, automatically infers by using fault processing rules, and then gives out whether immediate fault processing is recommended in a text form, and the dispatcher is assisted in decision making by using information such as follow-up processing flow recommended to be performed due to reasons of incapability of fault processing in the current line fault processing requirement.
D. The invention has similar history fault recommending function: the system receives real-time fault information transmitted by a dispatcher or other system interfaces, and gives k historical faults with highest similarity in a text form for reference of the dispatcher after calculation by a similarity algorithm.
In conclusion, the system provided by the invention greatly improves the fault processing efficiency of the power distribution network and greatly reduces the loss.
Drawings
In order to more clearly illustrate the embodiments of the present invention, the drawings that are required for the embodiments will be briefly described, and it will be apparent that the drawings in the following description are some embodiments of the present invention and that other drawings may be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a diagram of a power distribution network fault handling auxiliary decision making system provided by the invention;
FIG. 2 is a timing diagram of an automatic import function provided by the document import interface module of FIG. 1;
FIG. 3 is a functional timing diagram provided by the rule management module of FIG. 1;
FIG. 4 is a timing diagram of the inference function provided by the fault decision processing module of FIG. 1;
FIG. 5 is a functional timing diagram provided by the similar history fault recommendation module of FIG. 1.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention provides a power distribution network fault processing auxiliary decision-making system, which comprises a computer, an interface interaction module and a fault processing knowledge graph, a file analysis module, an entity relation extraction module and a fault decision-making processing module, wherein the interface interaction module is operated in the computer and comprises a file importing interaction interface module, a fault processing decision-making interaction interface module and a rule management interaction interface module, and a knowledge graph database is stored in the fault processing knowledge graph; the system comprises a dispatcher, a file analysis module, a file relation extraction module, a file type analysis module, a power distribution network management module and a fault processing knowledge graph, wherein the dispatcher uploads various power related files to the dispatcher; the fault processing decision-making interaction interface module is used for receiving the field accident situation uploaded by a dispatcher and is connected with the fault decision-making processing module, the fault decision-making processing module comprises a fault processing decision-making suggestion module and a similar history fault recommendation module, and the fault processing decision-making suggestion module gives immediate fault processing, fault processing emergency degree and all non-fault processing reasons for the received field situation after utilizing the fault processing rules in the fault processing knowledge graph to carry out related reasoning on the lines; the similar historical fault recommendation module calculates a historical fault similar to k before the current accident in the fault treatment knowledge graph by using a similarity algorithm, and gives out a fault situation, a fault result and a treatment mode of the similar fault in a text form; the rule management interactive interface module is used for graphically displaying fault processing rules and power distribution network fault regulations in the fault processing knowledge graph to a dispatcher.
The fault processing knowledge graph is respectively connected with the entity relation extraction module, the fault decision processing module and the rule management interaction interface module through the knowledge graph access interface module, and the knowledge graph access interface module is used for providing an access interface for storing a knowledge graph database.
The interface interaction module provided by the invention is used for interaction between a dispatcher and the system. The method is preferably realized by a WEB page, comprises three different sub-interface functions, comprises a file import interactive interface module with a file import function, a fault processing decision interactive interface module with a fault processing decision function and a rule management interactive interface module with a rule management function, and realizes different functions according to the requirements of a dispatcher.
As shown in fig. 2, the file is automatically imported into an interface through a file importing interactive interface module, a power file is uploaded, a file analyzing module receives various power related files uploaded by a dispatcher, the types of the power related files are confirmed through file names, suffix names and the like, the content of the files is analyzed through the corresponding interface, then character strings of specific areas are selected and transmitted to an entity relation extracting module, the entity relation extracting module extracts power distribution network entities and relations which need to be stored into a fault processing knowledge graph from the received character strings of specific types in a template matching mode, after an equivalent entity is obtained through a power dictionary, the original entities and relations are changed through a knowledge graph accessing interface module, and meanwhile, the result display can be presented through the file importing interactive interface module, so that the modification of the entities and the relations is completed.
As shown in fig. 1 and fig. 4, a subsequent processing suggestion module is further provided in the fault decision processing module, and the fault decision processing suggestion module performs a fault decision making method by: the method comprises the steps that DRL rules stored in a KieContainer1 object, related entity information in a fault processing knowledge graph and real-time fault information stored in a dfact object are externally transmitted through a rule management module, and all the DRL rules and the related entity information are imported into a kSession; performing fault handling reasoning by adopting a fireAllRules () method of a Drools engine; and (3) after reasoning, obtaining whether the current line fault should be processed immediately, the emergency degree of the current line fault demand fault processing and the conclusion of all the current reasons which cause the fault processing incapability.
When the functions are used, a dispatcher enters a fault processing decision-making interaction interface module, receives the scene accident situation transmitted by the dispatcher, namely, inputs the current fault situation, and clicks a start button; and after reasoning the related data of the rules and the lines in the fault processing knowledge graph by using the fault processing decision suggestion module, related treatment actions in the power distribution network rule processing are given and instantiated, so as to guide a dispatcher to follow-up processing schemes.
As shown in fig. 1 and fig. 3, the rule management interactive interface module is further connected to a rule management module, and the rule management module performs data transmission with the fault processing knowledge graph through the knowledge graph access interface module. The rule management module is also provided with a rule modification module and a rule updating module, and a dispatcher directly adds and deletes rules in the fault processing knowledge graph through a Cypher statement in the rule modification module and directly modifies a conditional statement action statement and the like; the rule updating module converts the fault processing rules in the modified fault processing knowledge graph into DRL rule files, stores the DRL rule files in the KieContainer1 and KieContainer2 objects for the fault processing decision suggesting module and the subsequent processing suggesting module, wherein the subsequent processing suggesting module uses the subsequent processing related fault processing rules in the KieContainer2, and when the power distribution network fault rules are screened according to the existing fault conditions, the DRL rule files are embodied through information in the graph, and finally each operation prompt of the subsequent suggestion is given.
When the function is used, a dispatcher enters a rule management interface to check fault processing rules and power distribution network processing rules in a graph mode. Through inputting corresponding instructions, operations such as adding, deleting and the like can be performed on the rules. After modification, the click update may generate a generational rule update in the system to support subsequent failure handling reasoning. The rule management module is provided with a rule display module which intuitively displays all the current rules and the relations among the rules in the fault processing knowledge graph in a Neo4j browsing graph mode.
As shown in FIG. 5, the similarity history fault recommendation module calculates the similarity between the current fault and the history faults obtained by inquiring all knowledge maps through the fault line and the fault information input by the dispatcher at the interactive interface module, and outputs the first 3-5 history faults with the highest similarity to the fault processing decision interactive interface module.
The system mainly comprises map construction, fault processing rule conversion, fault processing reasoning and similarity calculation:
(1) And (3) constructing a map: the core of the map construction is the identification of the entity and the addition of the relation, the system extracts the entity firstly by directly carrying out different operations on the attribute judgment of each line record in the document, then carries out comparison, finally adds the relation, and takes the line entity and the station entity in the line information table as an example, and the analysis and extraction algorithm of the core entity is shown in the table 1:
table 1 line and station entity resolution extraction algorithm
(2) Fault handling rule conversion: and converting the fault processing rules in the fault processing knowledge graph into DRL files directly used by a Drools rule engine.
(3) Fault handling reasoning: the converted DRL file is used as a rule base, the external real-time fault information and the fault processing related entity in the fault processing knowledge graph are used as a fact base, the results are obtained by utilizing the Drools rule engine reasoning, and the core fault processing reasoning algorithm is shown in the table 2:
table 2 Fault handling inference correlation Algorithm
(4) Similar historical fault recommendations: the converted DRL file is used as a rule base, the real-time fault information transmitted from the outside and the related entity of fault processing in the fault processing knowledge graph are used as a fact base, and the results are obtained by utilizing the Drools rule engine reasoning, and the algorithm is shown in the table 3:
table 3 similar historical Fault recommendation correlation Algorithm
The nonfunctional requirements of the system of the present invention include accuracy, response time, maintainability and stability, and nonfunctional testing and verification of the system from these aspects.
A. Extraction accuracy rate of related entities of power distribution network
The system adopts a template regular expression mode to extract the required related entity information of the distribution network from each unstructured document, and the accuracy of the related entity information is required to be tested. The test data are documents used in a real distribution network system, and the source is the national distribution network Nanrui group. The test method is that after the document is automatically transmitted into the system, the correctness of the extracted entity category is manually compared, and the experimental result is shown in the table 4:
table 4 system automatically extracts test results of correctness of related entities of power distribution network
B. Failure handling business reasoning correct rate
The result of the system fault handling reasoning has an influence on the decision of the dispatcher, and the correctness of the result must be verified. The test data are modified from the power grid fault processing and checking questions, and the total number of the test data is 8. The test method is that related entity documents of the power distribution network are automatically transmitted into the system, after a fault processing rule of the power distribution network is manually input into a map, fault real-time information is input, whether immediate fault processing suggestions given by the system are consistent with answers or not is compared and checked, and experimental results are shown in a table 5:
TABLE 5 failure handling inference accuracy test results
As can be seen from Table 5, the system gives 8-topic results with 100% accuracy. The test result proves that the system can give out correct and reliable fault processing conclusion after giving the fault processing rule and the related entity information of the power distribution network, and meets the requirement of an auxiliary dispatcher for carrying out fault processing decision.
C. Recommending historical failure accuracy
The similar historical faults recommended by the system of the invention need to verify the reliability according to the relation between the cosine similarity and the line. The test data are 500 pieces of real power distribution network historical fault data, and the source is the national power grid Nanrui group. The test method is to take out 5 historical faults as a test set, input the fault line, fault phase, fault category and other information into the system, and compare the fault cause with the system recommended historical faults, wherein the test result is shown in table 6:
table 6 recommended historical failure accuracy test results
As can be seen from table 6, 77 of the 150 recommended historical faults were consistent with the test faults, and 140 of the treatment results were consistent with the test faults. Part of fault reasons are obviously positively correlated with fault information reported by a dispatcher, and if 26 final reasons among 32 faults with site weather being thunderstorms are caused by lightning strokes. Others cannot be inferred from existing fault conditions, such as line breaks due to vehicle bumps or line shorts due to improper crane operation, and general fault recommendations are presented. The treatment result is excellent, and the final treatment mode is highly relevant to the fault phenomenon reported by the dispatcher.
The overall hit rate of the recommended history fault is (77+129)/300=68.7%. The experimental result proves that the first 3 high similarity recommended historical faults given by the system have higher referential property and have certain help to the fault handling decision of the dispatcher.
D. Multi-tier relationship query time
In order to verify the advantages of the knowledge graph compared with the traditional relational database in the aspect of multi-relational query, test verification is carried out on the knowledge graph and the traditional relational database. The test data are a real 2500 power distribution network lines and 700 station information tables in Liaoning province. The test method is that all the stations and lines are first led into fault processing knowledge graph, and then the line and station line list, station list and line station connection list are stored in Mysql database. Finally, all non-repeated lines contained in a certain line as a starting point, namely a starting point line- > (intermediate station- > -line) n and n epsilon (1-5) are inquired, the respective required time is recorded, and the test results are shown in table 7:
TABLE 7 time consuming comparison data for multi-layer relationship line query Neo4j and Mysql
It can be found that when the number of relationship layers increases, the map query time based on Neo4j is significantly shortened compared to the presentation of the conventional relational database Mysql.
In order to verify the response time of the system and the time shortening of the fault handling decision of the dispatcher, the response time of the file and the fault handling decision is imported by the test system. The test data are a real 2500 power distribution network line and 700 station information tables in a certain province and 10 real historical faults. The test method is that firstly, the line and the station table are imported into the fault processing knowledge graph, and the importing time is recorded. Then, 10 fault conditions of actual historical faults are input into the system, and the decision time of the system is recorded. The results are shown in Table 8:
table 8 system response time test results
From the results of table 8, it can be found that both the import response time and the decision response time of the system meet the non-functional requirements of the system. Meanwhile, compared with the time required by 15 minutes for the real fault decision, the time required by the fault processing decision can be greatly reduced by a dispatcher under the help of a system, so that various losses caused by power failure are reduced.
The invention is applicable to the prior art where nothing is mentioned.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While obvious variations or modifications are contemplated as falling within the scope of the present invention.
Claims (4)
1. The auxiliary decision-making system for the power distribution network fault processing is characterized by comprising a computer, an interface interaction module, a fault processing knowledge graph, a file analysis module, an entity relation extraction module and a fault decision-making processing module, wherein the interface interaction module is operated in the computer and comprises a file importing interaction interface module, a fault processing decision-making interaction interface module and a rule management interaction interface module;
the file importing interactive interface module is used for receiving various power related files uploaded by a dispatcher, is connected with the file analysis module and the entity relation extraction module, the file analysis module confirms file types and analyzes the content of the file types in a mode of file names and suffix names of the various power related files, and the entity relation extraction module is used for extracting power distribution network entities and relations in the file analysis module and storing the power distribution network entities and relations in the fault processing knowledge graph;
the fault processing decision-making interaction interface module is used for receiving the field accident situation uploaded by a dispatcher and is connected with the fault decision-making processing module, the fault decision-making processing module comprises a fault processing decision-making suggestion module and a similar historical fault recommendation module, and after the fault processing decision-making suggestion module utilizes a fault processing rule in the fault processing knowledge graph to carry out related reasoning on a line, whether immediate fault processing, fault processing emergency degree and all non-fault processing reasons are given for the received field situation; the similarity history fault recommendation module calculates a history fault similar to k before the current accident in the fault processing knowledge graph by using a similarity algorithm, and gives out a fault situation, a fault result and a processing mode of the similar fault in a text form;
the rule management interaction interface module is used for graphically displaying fault processing rules in the fault processing knowledge graph and power distribution network fault regulations to a dispatcher;
the fault processing knowledge graph is respectively connected with the entity relation extraction module, the fault decision processing module and the rule management interaction interface module through a knowledge graph access interface module, and the knowledge graph access interface module is used for providing an access interface for storing a knowledge graph database;
the fault decision processing module is also provided with a follow-up processing suggestion module which receives the scene accident situation transmitted by a dispatcher, gives out the relevant treatment actions in the power distribution network procedure processing and instantiates the relevant treatment actions after the procedure in the fault processing knowledge graph is utilized to infer the relevant data of the line, and guides the follow-up processing scheme of the dispatcher;
the rule management interactive interface module is also connected with a rule management module, a rule modification module and a rule updating module are also arranged in the rule management module, and a dispatcher directly adds and deletes the rules in the fault processing knowledge graph in the rule modification module through a Cypher statement and directly modifies a conditional statement and an action statement; the rule updating module converts the modified fault processing rules in the fault processing knowledge graph into DRL rule files, and stores the DRL rule files in the KieContainer1 and KieContainer2 objects for the fault processing decision suggestion module and the subsequent processing suggestion module to use;
the fault handling decision suggestion module performs the fault handling decision by the following steps: the DRL rules stored in the KieContainer1 object, the related entity information in the fault processing knowledge graph and the real-time fault information stored in the dfact object are externally transmitted through the rule management module, and all the DRL rules and the related entity information are imported into the kSession; performing fault handling reasoning by adopting a fireAllRules () method of a Drools engine; and (3) after reasoning, obtaining whether the current line fault should be processed immediately, the emergency degree of the current line fault demand fault processing and the conclusion of all the current reasons which cause the fault processing incapability.
2. The power distribution network fault handling aid decision making system according to claim 1, wherein the rule management module performs data transmission with the fault handling knowledge graph through the knowledge graph access interface module.
3. The power distribution network fault handling auxiliary decision making system according to claim 2, wherein the rule management module is provided with a rule display module, and the relationship between all the current rules in the fault handling knowledge graph is intuitively displayed in a browsing graph mode of Neo4 j.
4. A power distribution network fault handling auxiliary decision making system according to any one of claims 1-3, wherein the similarity history fault recommending module calculates the similarity between the current fault and the historical faults obtained by inquiring in all knowledge maps through fault lines and fault information input by a dispatcher, and outputs the first 3-5 historical faults with the highest similarity to the fault handling decision making interaction interface module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211579008.9A CN115953146B (en) | 2022-12-07 | 2022-12-07 | Auxiliary decision-making system for fault treatment of power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211579008.9A CN115953146B (en) | 2022-12-07 | 2022-12-07 | Auxiliary decision-making system for fault treatment of power distribution network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115953146A CN115953146A (en) | 2023-04-11 |
| CN115953146B true CN115953146B (en) | 2024-02-13 |
Family
ID=87288669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211579008.9A Active CN115953146B (en) | 2022-12-07 | 2022-12-07 | Auxiliary decision-making system for fault treatment of power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115953146B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009294837A (en) * | 2008-06-04 | 2009-12-17 | Hitachi Ltd | Failure monitoring system and device, monitoring apparatus, and failure monitoring method |
| CN111985653A (en) * | 2020-06-24 | 2020-11-24 | 国网江苏省电力有限公司 | Power grid fault knowledge recommendation and knowledge management system and method based on knowledge graph |
| CN113553420A (en) * | 2020-04-22 | 2021-10-26 | 国网电力科学研究院有限公司 | Power grid fault handling regulation recommendation method and system based on knowledge graph |
| CN114781662A (en) * | 2022-03-30 | 2022-07-22 | 国网浙江省电力有限公司绍兴供电公司 | Fault line power restoration knowledge reasoning method based on deep learning |
| CN114841797A (en) * | 2022-05-16 | 2022-08-02 | 中国邮政储蓄银行股份有限公司 | Method and device for determining business processing rule based on Drools rule engine |
| CN115357726A (en) * | 2022-08-15 | 2022-11-18 | 云南电网有限责任公司玉溪供电局 | Fault disposal plan digital model establishing method based on knowledge graph |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100976443B1 (en) * | 2008-09-04 | 2010-08-18 | 한국전자통신연구원 | Home-network error prediction system and home-network fault estimation method |
| US10536294B2 (en) * | 2017-07-17 | 2020-01-14 | Midea America Corp. | Computer-based platform for quality management of home devices |
| 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 |
-
2022
- 2022-12-07 CN CN202211579008.9A patent/CN115953146B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009294837A (en) * | 2008-06-04 | 2009-12-17 | Hitachi Ltd | Failure monitoring system and device, monitoring apparatus, and failure monitoring method |
| CN113553420A (en) * | 2020-04-22 | 2021-10-26 | 国网电力科学研究院有限公司 | Power grid fault handling regulation recommendation method and system based on knowledge graph |
| CN111985653A (en) * | 2020-06-24 | 2020-11-24 | 国网江苏省电力有限公司 | Power grid fault knowledge recommendation and knowledge management system and method based on knowledge graph |
| CN114781662A (en) * | 2022-03-30 | 2022-07-22 | 国网浙江省电力有限公司绍兴供电公司 | Fault line power restoration knowledge reasoning method based on deep learning |
| CN114841797A (en) * | 2022-05-16 | 2022-08-02 | 中国邮政储蓄银行股份有限公司 | Method and device for determining business processing rule based on Drools rule engine |
| CN115357726A (en) * | 2022-08-15 | 2022-11-18 | 云南电网有限责任公司玉溪供电局 | Fault disposal plan digital model establishing method based on knowledge graph |
Non-Patent Citations (2)
| Title |
|---|
| 基于规则引擎的综合网管告警管理系统的设计与实现;符永涛;杨芳南;;铁路计算机应用(10);全文 * |
| 智慧管廊实时监测与异常预警系统设计与实现;程一梁;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;第四章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115953146A (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111985653B (en) | Power grid fault knowledge recommendation and knowledge management system and method based on knowledge graph | |
| US7739138B2 (en) | Automated utility supply management system integrating data sources including geographic information systems (GIS) data | |
| WO2021073409A1 (en) | Data processing method, apparatus and device and storage medium | |
| CN108491378B (en) | Intelligent response system for operation and maintenance of electric power information | |
| CN103744919B (en) | Power grid knowledge base self learning method and system | |
| CN109767081A (en) | Electric power work order table generating method and device | |
| KR101917038B1 (en) | Device of reference document integration management and procedure display for making nuclear power plant commissioning procedures | |
| CN102902689A (en) | Application of matching method and system based on traveling line geometrical characteristics to social network | |
| CN111949779A (en) | Intelligent rail transit response method and system based on knowledge graph | |
| CN117273133A (en) | Construction method of multi-source heterogeneous data knowledge graph of power distribution network | |
| CN114841128B (en) | Business interaction method, device, equipment, medium and product based on artificial intelligence | |
| JP2020123371A (en) | Question answering system, question reception answering system, primary answering system, and question answering method using them | |
| CN115953146B (en) | Auxiliary decision-making system for fault treatment of power distribution network | |
| CN118245614A (en) | Mine hoist fault diagnosis and prevention method based on knowledge graph | |
| CN117911039A (en) | Control method, equipment and storage medium for after-sales service system | |
| CN117764774A (en) | Knowledge graph-based power grid dispatching risk analysis method, system and storage medium | |
| CN117668250A (en) | Knowledge graph construction method, device and equipment for lightning arrester faults and storage medium | |
| CN111950875A (en) | Intelligent contract reviewing method | |
| CN116501845A (en) | Human-computer interaction method and system based on LLM model | |
| CN114971218A (en) | Locomotive repair digital management system | |
| CN114069836A (en) | Artificial intelligence-based docking method for operation and maintenance operation of distribution automation system | |
| US20220342743A1 (en) | Recommendation system, configuration method therefor, and recommendation method | |
| CN115345407A (en) | Virtual assistant system for emergency dispatcher and operation method thereof | |
| CN109064362B (en) | AI technology-based power grid material management and training system | |
| CN106484888A (en) | A kind of traffic communication record readjustment and prompt system and its method |
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 |