CN116521898A - Construction method of power plant power generation equipment fault knowledge graph - Google Patents
Construction method of power plant power generation equipment fault knowledge graph Download PDFInfo
- Publication number
- CN116521898A CN116521898A CN202310509481.8A CN202310509481A CN116521898A CN 116521898 A CN116521898 A CN 116521898A CN 202310509481 A CN202310509481 A CN 202310509481A CN 116521898 A CN116521898 A CN 116521898A
- Authority
- CN
- China
- Prior art keywords
- information
- fault
- knowledge graph
- power plant
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 23
- 238000010276 construction Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000005065 mining Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
Abstract
The invention relates to a construction method of a power plant power generation equipment fault knowledge graph, which comprises the following steps: acquiring fault knowledge information; preprocessing and structuring the fault knowledge information; constructing a 'unit-device-part' device tree according to the actual condition of the power plant; adopting a pattern matching method facing a relational database to mount the triplet vector information on the equipment tree to form a knowledge graph; based on fault information input by a user, searching the knowledge graph to obtain a reference of a fault cause positioning or reasonable disposal scheme. The beneficial effects of the invention are as follows: the invention utilizes the text meaning analysis and information association capability of the knowledge graph to aim at carrying out efficient and visual expression and intelligent processing on massive, heterogeneous and dynamic large data related to power plant equipment. The unstructured knowledge and the knowledge graph of the power plant are organically fused, the intelligent mining and application of the power plant equipment data are driven, and the safety management of power production and the efficient improvement of the power production efficiency are realized.
Description
Technical Field
The invention relates to the technical field of power generation information, in particular to a construction method of a power plant power generation equipment fault knowledge graph.
Background
At present, along with the rapid development of economy in China, the scale of the thermal power plant is also enlarged, and the power equipment becomes increasingly large in scale and complex in structure. The thermal power plant equipment is used as the main force army of the power supply of the user terminal, the equipment faults are rapidly processed, and the maintenance of the efficient operation of the thermal power plant equipment is the key of stable and high-quality power supply. In the actual fault processing process, a maintainer is often required to quickly position fault equipment and analyze fault reasons based on an experience and expertise mode by taking a fault phenomenon as a node according to a fault relation provided in a maintenance rule and a working manual, so that the equipment is ensured to be quickly put into production. However, the above maintenance strategies are largely associated with the expertise of the inspector, whose expertise reserves, logic processing power, and information analysis power will directly determine the effectiveness of equipment maintenance. The maintainer centrally processes and manages the multi-mode fault data and the procedure log, packages the data into a fault-equipment relation database of the intelligent fault searching application, assists the maintainer in fault positioning, and needs to provide possible fault reasons and processing schemes. The fault data generated by the equipment in the production process and the existing maintenance procedure data have the characteristics of complex types and redundant quantity, so that the centralized management and the rapid search of the multi-source heterogeneous fault data become two difficult problems.
The knowledge graph is taken as a powerful tool, has obvious advantages for the arrangement and induction of mass data, and can establish a knowledge base which is perfected than a system for the professional power equipment fault diagnosis field based on the powerful semantic processing and open interconnection capability, so that the searching capability of fault data is better improved; in the face of demands of knowledge management, semantic retrieval, data analysis, decision support and the like, unstructured data such as power generation equipment knowledge, a maintenance procedure, a workbook and the like can be organically fused with a knowledge graph through a text language analysis related technology of the power generation equipment, and the application of fault intelligent search in the power equipment maintenance scene is promoted.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a construction method of a fault knowledge graph of power generation equipment of a power plant.
In a first aspect, a method for constructing a power plant power generation equipment fault knowledge graph is provided, including:
step 1, obtaining fault knowledge information; the fault knowledge information comprises text format information and non-text format information;
step 2, preprocessing the fault knowledge information;
step 3, carrying out structural processing on the fault knowledge text information to obtain 'fault-cause-solution' triplet vector information;
step 4, constructing a 'unit-equipment-component' equipment tree according to the actual condition of the power plant;
step 5, adopting a pattern matching method facing a relational database to mount the triplet vector information on the equipment tree to form a knowledge graph;
and 6, searching the knowledge graph based on fault information input by a user to obtain a reference of a fault cause positioning or reasonable disposal scheme.
Preferably, in step 1, the text format information includes Excel format information and TXT format information; the non-text format information includes PDF format information and picture format information.
Preferably, in step 2, the text format information is imported into the system database by means of program reading, and the non-text format information is imported into the system database after OCR text recognition and manual verification.
Preferably, step 3 includes:
step 3.1, calculating semantic similarity of all text information by adopting a Doc2Vec algorithm in deep learning, projecting the imported text information into a vector space and visualizing, and marking manual information;
step 3.2, clustering according to the similarity of the text information by adopting a K-means algorithm to form a training set;
step 3.3, performing BIO labeling on the training set information;
step 3.4, receiving and processing the labeling information by using a bidirectional LIST circulating neural network;
step 3.5, outputting a predicted annotation sequence which accords with the annotation transfer constraint condition and is most possible through the CRF;
step 3.6, inputting training results into a corpus after finishing one training iteration, and performing accuracy matching;
step 3.7, continuously performing loop iteration to train a model with accuracy meeting the requirement;
and 3.8, predicting labels of the corpus data to be marked based on the trained model, and detecting the manual corpus marks by the sampling part to obtain the entity naming marks after ensuring the accuracy.
Preferably, step 6 includes:
step 6.1, analyzing a user search target by utilizing a Chinese natural language question-answering technology;
step 6.2, constructing target search based on the graph database query language;
step 6.3, obtaining a final search result after matching the fault knowledge nodes;
and 6.4, traversing the knowledge network output associated nodes in a depth-first or breadth-first mode to complete the mining of the knowledge graph.
In a second aspect, a device for constructing a power plant power generation equipment fault knowledge graph is provided, and the method for constructing the power plant power generation equipment fault knowledge graph in the first aspect is implemented, and includes:
the acquisition module is used for acquiring fault knowledge information; the fault knowledge information comprises text format information and non-text format information;
the preprocessing module is used for preprocessing the fault knowledge text information, the text format information is imported into the system database in a program reading mode, and the non-text format information is imported into the system database after OCR text recognition and manual verification;
the structuring module is used for carrying out structuring treatment on the fault knowledge text information to obtain 'fault-cause-solution' triplet vector information;
the construction module is used for constructing a 'unit-equipment-component' equipment tree according to the actual situation of the power plant;
the mounting module is used for mounting the triplet vector information on the equipment tree by adopting a pattern matching method facing to a relational database to form a knowledge graph;
and the searching module is used for searching the knowledge graph based on the fault information input by the user to obtain the reference of the fault cause positioning or reasonable disposal scheme.
In a third aspect, a computer storage medium having a computer program stored therein is provided; when the computer program runs on a computer, the computer is caused to execute the construction method of the power plant power generation equipment fault knowledge graph in the first aspect.
The beneficial effects of the invention are as follows: the invention utilizes the text meaning analysis and information association capability with superior knowledge patterns to aim at carrying out efficient and visual expression and intelligent processing on massive, heterogeneous and dynamic large data related to power plant equipment. The unstructured knowledge and the knowledge graph of the power plant are organically fused, the intelligent mining and application of the power plant equipment data are driven, and the safety management of power production and the efficient improvement of the power production efficiency are realized. The method can effectively solve the dilemma of difficult utilization of fault data, provides a new organization form for fault knowledge of the power equipment, is beneficial to collection and accumulation of the fault knowledge and excavation and application of fault rules, and can further drive operation and maintenance of the power equipment to be in an informatization and intelligent direction.
Drawings
FIG. 1 is a flow chart of a construction method of a power plant power generation equipment fault knowledge graph provided by the invention;
FIG. 2 is a diagram of a preprocessing process for text;
FIG. 3 is a flow chart of a text message structuring process;
FIG. 4 is a schematic diagram of a hierarchical structure of a device tree;
FIG. 5 is a schematic diagram of a knowledge graph structure;
FIG. 6 is a fault intelligent search flow chart;
fig. 7 is a schematic structural diagram of a device for constructing a fault knowledge graph of a power plant power generation device.
Detailed Description
The invention is further described below with reference to examples. The following examples are presented only to aid in the understanding of the invention. It should be noted that it will be apparent to those skilled in the art that modifications can be made to the present invention without departing from the principles of the invention, and such modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Example 1:
a construction method of a power plant power generation equipment fault knowledge graph comprises the following steps:
step 1, obtaining fault knowledge information; the fault knowledge information includes text format information and non-text format information.
The fault knowledge information comprises fault phenomena, fault reasons and corresponding solutions, and can be text format information, such as Excel format information and TXT format information; non-text format information such as PDF format information and picture format information is also possible.
And 2, preprocessing fault knowledge information.
In step 2, preprocessing refers to importing fault knowledge information into a system database. As shown in fig. 2, the text format information and the non-text format information are preprocessed in different manners, for example, the text format information is imported into a system database in a program reading manner, and the non-text format information is imported into the system database after OCR text recognition and manual verification. Therefore, the scope of fault information objects that can be handled by the present application is broad.
And step 3, carrying out structural processing on the fault knowledge text information to obtain 'fault-cause-solution' triplet vector information.
In step 3, the marked data is used as a training set to be input into a BiLSTM-CRF deep learning model for training. The BiLSTM algorithm can capture contextual information from both directions and can also mine hidden features from text, so that it has excellent effect feedback for knowledge extraction.
As shown in fig. 3, step 3 includes:
step 3.1, calculating semantic similarity of all text information by adopting a Doc2Vec algorithm in deep learning, projecting the imported text information into a vector space and visualizing, and marking manual information;
step 3.2, clustering according to the similarity of the text information by adopting a K-means algorithm to form a training set;
step 3.3, performing BIO labeling on the training set information;
step 3.4, receiving and processing the labeling information by using a bidirectional LIST circulating neural network;
step 3.5, outputting a predicted annotation sequence which accords with the annotation transfer constraint condition and is most possible through the CRF;
step 3.6, inputting training results into a corpus after finishing one training iteration, and performing accuracy matching;
step 3.7, continuously performing loop iteration to train a model with accuracy meeting the requirement;
and 3.8, predicting labels of corpus data to be marked based on the trained model, and detecting artificial corpus marks by a sampling part to obtain entity naming marks (namely 'failure-cause-solution' triplet vector information) after ensuring accuracy.
And 4, constructing a unit-equipment-component equipment tree according to the actual condition of the power plant. As shown in fig. 4, DA02 represents a unit number, DA0201, DA0202, and DA0202 are numbers of different devices belonging to the unit, and DA020101 is a number of a certain component of the device DA 0201.
And 5, mounting the triplet vector information on the equipment tree by adopting a pattern matching method facing the relational database to form a knowledge graph. As shown in fig. 5, a certain component in the equipment tree is matched with a certain fault of the triplet vector information, so as to form a knowledge graph.
And 6, searching the knowledge graph based on fault information input by a user to obtain a reference of a fault cause positioning or reasonable disposal scheme.
As shown in fig. 6, step 6 includes:
step 6.1, analyzing a user search target by utilizing a Chinese natural language question-answer technology (such as Template-Attention);
step 6.2, constructing target search based on a graph database query language (such as Cypher);
step 6.3, obtaining a final search result after matching the fault knowledge nodes;
and 6.4, traversing the knowledge network output associated nodes in a depth-first or breadth-first mode to complete the mining of the knowledge graph.
Example 2:
the utility model relates to a construction device of a power plant power generation equipment fault knowledge graph, as shown in fig. 7, comprising:
the acquisition module is used for acquiring fault knowledge information; the fault knowledge information comprises text format information and non-text format information;
the preprocessing module is used for preprocessing the fault knowledge text information, the text format information is imported into the system database in a program reading mode, and the non-text format information is imported into the system database after OCR text recognition and manual verification;
the structuring module is used for carrying out structuring treatment on the fault knowledge text information to obtain 'fault-cause-solution' triplet vector information;
the construction module is used for constructing a 'unit-equipment-component' equipment tree according to the actual situation of the power plant;
the mounting module is used for mounting the triplet vector information on the equipment tree by adopting a pattern matching method facing to a relational database to form a knowledge graph;
and the searching module is used for searching the knowledge graph based on the fault information input by the user to obtain the reference of the fault cause positioning or reasonable disposal scheme.
Claims (7)
1. The construction method of the power plant power generation equipment fault knowledge graph is characterized by comprising the following steps of:
step 1, obtaining fault knowledge information; the fault knowledge information comprises text format information and non-text format information;
step 2, preprocessing the fault knowledge information;
step 3, carrying out structural processing on the fault knowledge text information to obtain 'fault-cause-solution' triplet vector information;
step 4, constructing a 'unit-equipment-component' equipment tree according to the actual condition of the power plant;
step 5, adopting a pattern matching method facing a relational database to mount the triplet vector information on the equipment tree to form a knowledge graph;
and 6, searching the knowledge graph based on fault information input by a user to obtain a reference of a fault cause positioning or reasonable disposal scheme.
2. The method for constructing a fault knowledge graph of power plant power generation equipment according to claim 1, wherein in step 1, the text format information includes Excel format information and TXT format information; the non-text format information includes PDF format information and picture format information.
3. The method for constructing a fault knowledge graph of power plant power generation equipment according to claim 2, wherein in step 2, the text format information is imported into a system database in a program reading mode, and the non-text format information is imported into the system database after OCR text recognition and manual verification.
4. The method for constructing a power plant power generation equipment fault knowledge graph according to claim 3, wherein the step 3 comprises:
step 3.1, calculating semantic similarity of all text information by adopting a Doc2Vec algorithm in deep learning, projecting the imported text information into a vector space and visualizing, and marking manual information;
step 3.2, clustering according to the similarity of the text information by adopting a K-means algorithm to form a training set;
step 3.3, performing BIO labeling on the training set information;
step 3.4, receiving and processing the labeling information by using a bidirectional LIST circulating neural network;
step 3.5, outputting a predicted annotation sequence which accords with the annotation transfer constraint condition and is most possible through the CRF;
step 3.6, inputting training results into a corpus after finishing one training iteration, and performing accuracy matching;
step 3.7, continuously performing loop iteration to train a model with accuracy meeting the requirement;
and 3.8, predicting labels of the corpus data to be marked based on the trained model, and detecting the manual corpus marks by the sampling part to obtain the entity naming marks after ensuring the accuracy.
5. A method of constructing a power plant fault knowledge graph as claimed in claim 3, wherein step 6 comprises:
step 6.1, analyzing a user search target by utilizing a Chinese natural language question-answering technology;
step 6.2, constructing target search based on the graph database query language;
step 6.3, obtaining a final search result after matching the fault knowledge nodes;
and 6.4, traversing the knowledge network output associated nodes in a depth-first or breadth-first mode to complete the mining of the knowledge graph.
6. A device for constructing a power plant power generation equipment fault knowledge graph, which is used for executing the method for constructing the power plant power generation equipment fault knowledge graph according to any one of claims 1 to 5, and comprises the following steps:
the acquisition module is used for acquiring fault knowledge information; the fault knowledge information comprises text format information and non-text format information;
the preprocessing module is used for preprocessing the fault knowledge text information, the text format information is imported into the system database in a program reading mode, and the non-text format information is imported into the system database after OCR text recognition and manual verification;
the structuring module is used for carrying out structuring treatment on the fault knowledge text information to obtain 'fault-cause-solution' triplet vector information;
the construction module is used for constructing a 'unit-equipment-component' equipment tree according to the actual situation of the power plant;
the mounting module is used for mounting the triplet vector information on the equipment tree by adopting a pattern matching method facing to a relational database to form a knowledge graph;
and the searching module is used for searching the knowledge graph based on the fault information input by the user to obtain the reference of the fault cause positioning or reasonable disposal scheme.
7. A computer storage medium, wherein a computer program is stored in the computer storage medium; the computer program, when run on a computer, causes the computer to execute the method for constructing a power plant power generation equipment fault knowledge graph according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310509481.8A CN116521898A (en) | 2023-05-06 | 2023-05-06 | Construction method of power plant power generation equipment fault knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310509481.8A CN116521898A (en) | 2023-05-06 | 2023-05-06 | Construction method of power plant power generation equipment fault knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116521898A true CN116521898A (en) | 2023-08-01 |
Family
ID=87407940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310509481.8A Pending CN116521898A (en) | 2023-05-06 | 2023-05-06 | Construction method of power plant power generation equipment fault knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116521898A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117744775A (en) * | 2023-11-10 | 2024-03-22 | 天地科技股份有限公司北京技术研究分公司 | Method and system for constructing knowledge base of coal mining equipment |
| CN117973519A (en) * | 2024-03-29 | 2024-05-03 | 南京中医药大学 | Knowledge graph-based data processing method |
-
2023
- 2023-05-06 CN CN202310509481.8A patent/CN116521898A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117744775A (en) * | 2023-11-10 | 2024-03-22 | 天地科技股份有限公司北京技术研究分公司 | Method and system for constructing knowledge base of coal mining equipment |
| CN117973519A (en) * | 2024-03-29 | 2024-05-03 | 南京中医药大学 | Knowledge graph-based data processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110054B (en) | Method for acquiring question-answer pairs from unstructured text based on deep learning | |
| CN111709235B (en) | Text data statistical analysis system and method based on natural language processing | |
| CN116521898A (en) | Construction method of power plant power generation equipment fault knowledge graph | |
| CN113191148B (en) | Rail transit entity identification method based on semi-supervised learning and clustering | |
| CN108804529A (en) | A kind of question answering system implementation method based on Web | |
| CN113656805B (en) | Event map automatic construction method and system for multi-source vulnerability information | |
| CN111274817A (en) | Intelligent software cost measurement method based on natural language processing technology | |
| CN110377690B (en) | Information acquisition method and system based on remote relationship extraction | |
| Li et al. | Automatic identification of decisions from the hibernate developer mailing list | |
| CN106339455A (en) | Webpage text extracting method based on text tag feature mining | |
| Qin et al. | Agriculture knowledge graph construction and application | |
| CN113378024B (en) | Deep learning-oriented public inspection method field-based related event identification method | |
| CN113449508B (en) | Internet public opinion correlation deduction prediction analysis method based on event chain | |
| CN117592563A (en) | Power large model training and adjusting method with field knowledge enhancement | |
| CN117094390A (en) | Knowledge graph construction and intelligent search method oriented to ocean engineering field | |
| CN116974799A (en) | Fault diagnosis method and system of lighting system based on knowledge graph | |
| CN114238735B (en) | Intelligent internet data acquisition method | |
| Hu et al. | A classification model of power operation inspection defect texts based on graph convolutional network | |
| CN113326371B (en) | Event extraction method integrating pre-training language model and anti-noise interference remote supervision information | |
| CN116245108B (en) | Verification matching guide method, verification matching guide, device, and storage medium | |
| Xia et al. | Construction Method and Practical Application of Oil and Gas Field Surface Engineering Case Database Based on Knowledge Graph | |
| CN118132738B (en) | Extraction type question-answering method for bridge evaluation text | |
| CN118069853A (en) | Intelligent auxiliary system for writing text and construction method | |
| Meng et al. | A Text Mining based Entity Extraction Model for Power Plant Fault | |
| Yin et al. | Extraction method of general attributes of electronic components based on BiLSTM-CRF |
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 |