CN114385782A - Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph - Google Patents
Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph Download PDFInfo
- Publication number
- CN114385782A CN114385782A CN202111490653.9A CN202111490653A CN114385782A CN 114385782 A CN114385782 A CN 114385782A CN 202111490653 A CN202111490653 A CN 202111490653A CN 114385782 A CN114385782 A CN 114385782A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- information
- knowledge
- nuclear power
- entity
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a nuclear power plant maintenance aid decision-making method based on a knowledge graph, which comprises the following steps: step S1: establishing an equipment fault library and an equipment maintenance information library; step S2: the entity, the relation and the attribute category contained in the equipment and the maintenance information thereof are summarized and sorted, and a maintenance knowledge map service model is established; step S3: further combing the collected equipment fault information and maintenance decision information according to the triple relation in the maintenance knowledge map service model, and storing the combed entity-relation-entity or entity-attribute value information into a map database to establish a maintenance assistant decision knowledge map model; step S4: and constructing a nuclear power plant maintenance aid decision-making system based on the knowledge graph. The knowledge graph-based nuclear power plant maintenance auxiliary decision-making method solves the problems of time consumption and inaccuracy of information search in the maintenance preparation process.
Description
Technical Field
The invention relates to the technical field of nuclear power plant maintenance, in particular to a knowledge graph-based nuclear power plant maintenance aid decision-making method.
Background
The preparation for maintenance of the vital equipment of a nuclear power plant is a complex and cumbersome process. Basic information and historical experience feedback information of fault equipment need to be collected, wherein the basic information and the historical experience feedback information comprise equipment function structure information, equipment drawings, design specifications, use specifications, historical work orders, state reports, maintenance rules, maintenance schemes and the like, but the information is often scattered in various systems such as a production management system, a document system, a state report database and the like and equipment maintenance experts, is time-consuming and troublesome to collect, and cannot accurately and quickly locate the information needed by maintenance preparers.
Based on the problems, the method establishes a nuclear power plant maintenance aid decision-making method based on the knowledge graph by combining the outstanding advantages and wide application of the current knowledge graph technology in the natural language processing field and the intelligent retrieval aspect. By using knowledge map technology, a triple relation between equipment fault information and maintenance information is established, a knowledge network system is established, maintenance decision information is pushed to a maintenance preparer in a precise retrieval and intelligent question and answer mode, and the maintenance decision information is helped to complete preparation of a maintenance work package and formulation of a maintenance scheme.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a nuclear power plant maintenance aid decision-making method based on a knowledge graph, which solves the problems of time consumption and inaccuracy in information search in the maintenance preparation process.
In order to achieve the above purpose, the invention provides the following technical scheme:
a nuclear power plant maintenance aid decision-making method based on knowledge graph includes the following steps:
step S1: establishing an equipment fault library and an equipment maintenance information library;
step S2: the entity, the relation and the attribute category contained in the equipment and the maintenance information thereof are summarized and sorted, and a maintenance knowledge map service model is established;
step S3: further combing the collected equipment fault information and maintenance decision information according to the triple relation in the maintenance knowledge map service model, and storing the combed entity-relation-entity or entity-attribute value information into a map database to establish a maintenance assistant decision knowledge map model;
step S4: and constructing a nuclear power plant maintenance aid decision-making system based on the knowledge graph.
Further, in step S1, an equipment maintenance information base is created by collecting equipment functional structure information, equipment drawings, instruction manuals, design specifications, related status reports, operational events, internal events, work order tasks, maintenance procedures, maintenance schemes, and treatise information.
Further, in the step S1, a device failure library is created by analyzing the failure modes and corresponding failure causes common to the summarized and carded devices.
Further, in step S1, the equipment failure library is used as a "problem set", and the maintenance information library is used as an "answer set", so as to implement matching between the failure phenomenon and the maintenance decision information.
Further, in the step S4, a knowledge graph-based nuclear power plant maintenance aid decision system is constructed by using graph database storage, nuclear power professional segmentation, semantic similarity, a search engine, and intelligent question answering.
Further, the step S4 specifically includes the following steps:
step S41: storing the maintenance aid decision knowledge map model in a map database;
step S42: constructing indexes for entities, relations and attributes in a graph database;
step S43: performing word segmentation processing by using a natural language processing technology, performing semantic similarity matching on a word segmentation result of input information and a word segmentation result of graph database information, and positioning matched entities, relations and attributes;
step S44: displaying the located entity value, relationship value and attribute value to realize accurate semantic retrieval function;
step S45: carrying out relation analysis on the located entities, relations and attributes, and analyzing another entity through the entities and relations in the located triple relations; or analyzing an attribute value by positioning an entity and an attribute in the triple relation; or analyzing the relationship between the entities by positioning the entities in the triple relationship;
step S46: and carrying out map visual display on the located entities, relations and attributes.
Further, in step S43, the service person input information and the map database entity name, entity value, relationship name, relationship value, attribute name, and attribute value are subjected to word segmentation.
Compared with the prior art, the knowledge graph-based nuclear power plant maintenance aid decision-making method provided by the invention has the following beneficial effects:
through the construction of the equipment maintenance knowledge map, the fault information and the maintenance information of important equipment of the nuclear power plant are combined and a relationship is established, so that the functions of retrieving the equipment fault information, asking for answers and pushing the maintenance information are realized, and maintenance personnel are assisted to complete the preparation of maintenance work.
The method is characterized in that important equipment of a nuclear power plant is used as a basis, a knowledge graph in the nuclear power maintenance field is constructed by using a knowledge graph technology, basic equipment information and equipment maintenance information are pushed to a maintenance preparer through a natural language processing and intelligent retrieval technology, the preparation of a maintenance work package and the formulation of a maintenance scheme are completed, and the problems of time consumption and inaccuracy of information search in the maintenance preparation process are solved.
And storing the collected equipment failure information and maintenance information into an equipment failure library and a maintenance information library. In the actual searching process, the equipment fault library is used as an input question set, the maintenance information library is used as an output answer set, the relation between the two libraries is established through a knowledge graph service model, the entity, relation and attribute triple sorting is completed, an equipment maintenance knowledge graph model is established, the precise matching of the question set and the answer set is realized, the searching accuracy and comprehensiveness are improved, and the pushing and intelligent question-answering functions of maintenance information are completed. Therefore, the system helps maintenance personnel to formulate equipment maintenance schemes and carry out preparation and other work of work packages, shortens the time for searching relevant information of the maintenance personnel, improves the working efficiency, and ensures timely and high-quality development of maintenance work.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a repair decision knowledge graph model according to an embodiment of the present invention;
FIG. 2 is a block diagram of an overall framework for support of maintenance aid decision-making provided by an embodiment of the present invention;
FIG. 3 is a maintenance decision knowledge graph business model framework diagram provided by an embodiment of the present invention;
fig. 4 is a schematic diagram of a part of a maintenance assistant decision knowledge graph model of an oil-immersed transformer bushing according to an embodiment of the present invention;
fig. 5 is another partial schematic view of a repair assistant decision knowledge map model of an oil-filled transformer bushing according to an embodiment of the present invention, where fig. 5 connects the contents of fig. 4.
Detailed Description
Although the knowledgegraph-based plant maintenance aid decision method of the present invention may be implemented in a number of different ways, the exemplary embodiments will be described in detail herein with reference to the accompanying drawings, without intending to limit the scope of the invention to the exemplary embodiments. Accordingly, the drawings and description of the specific embodiments are to be regarded as illustrative in nature, and not as restrictive.
The following is a more detailed description of the present invention by way of specific embodiments.
As shown in fig. 1 to 3, the invention provides a nuclear power plant maintenance aid decision method based on a knowledge graph, which mainly comprises the following three points:
(1) collecting relevant information of equipment maintenance, including equipment functional structure information, equipment drawings, failure modes and reasons, design specifications, instruction manuals, status reports, operation events, internal events, work order tasks, QDR (quality defect reports), NCR (production nonconformance items), maintenance rules, maintenance schemes, treatises and the like, and constructing an equipment failure library and a maintenance information library.
(2) And combing the information, and sorting out entities, relations and attribute categories in the equipment maintenance knowledge graph so as to establish a knowledge graph service model. And then, the extraction of knowledge is completed by combining a knowledge map service model through a mode of combining manual carding and machine extraction, and map data in the form of equipment entity-relation-entity or entity-attribute value triples is constructed to serve as a data base of the equipment maintenance knowledge map model.
(3) On the basis of the equipment maintenance knowledge graph, a maintenance knowledge graph prototype system with accurate retrieval and intelligent question answering is developed by combining technologies such as graph database storage, nuclear power professional word segmentation, semantic similarity, search engines and intelligent question answering, and the maintenance aid decision making function of important equipment of a nuclear power plant is realized.
The maintenance assistant decision method based on the knowledge graph has the core of the construction of a knowledge graph model, the construction process is shown in figure 1, an equipment fault base and a maintenance information base are firstly established, then the information is induced and refined, the entity, the relation and the attribute category related to the equipment maintenance knowledge graph are combed out, a knowledge graph service model is established, then the triple information of entity-relation-entity or entity-attribute value is combed by taking the service model as a frame, and a graph database is established. With knowledge graph data, a maintenance decision knowledge graph model can be constructed. On the basis of a maintenance decision knowledge map model, a maintenance knowledge map prototype system with accurate retrieval and intelligent question and answer is developed by combining nuclear power professional word segmentation, a search engine and an intelligent question and answer technology, so that a user can match corresponding maintenance information according to input fault phenomena to assist in completing maintenance decision support, and the overall design framework is shown in fig. 2.
The following is a detailed description of a knowledge graph-based nuclear power plant maintenance aid decision method:
step S1: on the basis of important equipment of a nuclear power plant, relevant information of the equipment, including equipment drawings, instruction manuals, design specifications, related status reports, operation events, internal events, work order tasks, maintenance rules, maintenance schemes, papers and the like, is collected, so that an equipment maintenance information base is established. Meanwhile, through analysis and summary, the common failure modes and corresponding failure reasons of the carding equipment are used for establishing an equipment failure library. In the searching process of a user, the equipment fault library is used as a question set, and the maintenance information library is used as an answer set, so that accurate matching of fault phenomena and maintenance decision information is realized.
Step S2: through the collection of the equipment fault information and the maintenance decision information in the step S1, the entities, relationships, and attribute categories included in the equipment and the maintenance information thereof are summarized and sorted, and a maintenance knowledge graph service model is established, as shown in fig. 3. Business models are the framework for building knowledge map databases, so business models are required to cover as much as possible all entities, relationships, and attribute classes required for equipment maintenance decision making processes.
Step S3: and after the knowledge graph service model is established, the collected equipment fault information and maintenance decision information can be further sorted according to the triple relation in the maintenance knowledge graph service model, and the sorted entity-relation-entity or entity-attribute value information is stored in a graph database so as to establish the maintenance decision auxiliary strategy graph model. Taking the oil-immersed transformer bushing as an example, the partial maintenance assistant decision knowledge graph model is shown in fig. 4 and fig. 5 (only partial knowledge graph is shown in space).
Step S4: through the equipment maintenance auxiliary decision-making knowledge graph model established in the step S3, a nuclear power plant maintenance auxiliary decision-making system based on the knowledge graph is established by utilizing the technologies of graph database storage, nuclear power professional word segmentation, semantic similarity, search engines, intelligent question answering and the like, so that the functions of accurate retrieval, intelligent question answering and auxiliary decision making are realized.
Step S4 specifically includes the following steps:
step S41: storing the equipment maintenance assistant decision knowledge map model established in the step S3 in a map database;
step S42: constructing indexes for entities, relations and attributes in a graph database;
step S43: and performing word segmentation processing on the information input by the maintenance personnel and the entity name, the entity value, the relation name, the relation value, the attribute name and the attribute value of the graph database by using a natural language processing technology, performing semantic similarity matching on the word segmentation result of the input information and the word segmentation result of the graph database information, and positioning the matched entity, relation and attribute.
Step S44: displaying the located entity value, relationship value and attribute value to realize accurate semantic retrieval function;
step S45: carrying out relation analysis on the located entities, relations and attributes, and analyzing another entity through the entities and relations in the located triple relations; or analyzing an attribute value by positioning an entity and an attribute in the triple relation; or the relation between the entities is analyzed by positioning the entities in the triple relation, and finally the intelligent question-answering function is realized.
Step S46: and performing map visual display on the located entities, relations and attributes to help maintenance personnel find out potential relations among various information through a relation network.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (7)
1. A nuclear power plant maintenance aid decision-making method based on knowledge graph is characterized by comprising the following steps:
step S1: establishing an equipment fault library and an equipment maintenance information library;
step S2: the entity, the relation and the attribute category contained in the equipment and the maintenance information thereof are summarized and sorted, and a maintenance knowledge map service model is established;
step S3: further combing the collected equipment fault information and maintenance decision information according to the triple relation in the maintenance knowledge map service model, and storing the combed entity-relation-entity or entity-attribute value information into a map database to establish a maintenance assistant decision knowledge map model;
step S4: and constructing a nuclear power plant maintenance aid decision-making system based on the knowledge graph.
2. The knowledge-graph-based nuclear power plant maintenance aid decision-making method according to claim 1, characterized in that in step S1, an equipment maintenance information base is established by collecting equipment functional structure information, equipment drawings, instruction manuals, design specifications, related status reports, operational events, internal events, work order tasks, maintenance procedures, maintenance schemes and thesis information.
3. The knowledge-graph-based nuclear power plant maintenance aid decision-making method according to claim 1, characterized in that in the step S1, an equipment fault library is established by analyzing common failure modes of summarized and carded equipment and corresponding fault reasons.
4. The knowledge-graph-based nuclear power plant maintenance aid decision-making method according to claim 1, wherein in the step S1, the equipment failure library is used as a question set, and the maintenance information library is used as an answer set, so as to realize matching of failure phenomena and maintenance decision-making information.
5. The knowledge-graph-based nuclear power plant maintenance aid decision method according to claim 1, wherein in the step S4, a knowledge-graph-based nuclear power plant maintenance aid decision system is constructed by using graph database storage, nuclear power professional segmentation, semantic similarity, a search engine and intelligent question and answer.
6. The knowledge-graph-based nuclear power plant maintenance aid decision-making method according to claim 1, wherein the step S4 specifically comprises the following steps:
step S41: storing the maintenance aid decision knowledge map model in a map database;
step S42: constructing indexes for entities, relations and attributes in a graph database;
step S43: performing word segmentation processing by using a natural language processing technology, performing semantic similarity matching on a word segmentation result of input information and a word segmentation result of graph database information, and positioning matched entities, relations and attributes;
step S44: displaying the located entity value, relationship value and attribute value to realize accurate semantic retrieval function;
step S45: carrying out relation analysis on the located entities, relations and attributes, and analyzing another entity through the entities and relations in the located triple relations; or analyzing an attribute value by positioning an entity and an attribute in the triple relation; or analyzing the relationship between the entities by positioning the entities in the triple relationship;
step S46: and carrying out map visual display on the located entities, relations and attributes.
7. The knowledge-graph-based nuclear power plant maintenance aid decision-making method according to claim 6, wherein in the step S43, the input information of maintenance personnel and database entity name, entity value, relationship name, relationship value, attribute name and attribute value are subjected to word segmentation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111490653.9A CN114385782A (en) | 2021-12-08 | 2021-12-08 | Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111490653.9A CN114385782A (en) | 2021-12-08 | 2021-12-08 | Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114385782A true CN114385782A (en) | 2022-04-22 |
Family
ID=81196236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111490653.9A Pending CN114385782A (en) | 2021-12-08 | 2021-12-08 | Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114385782A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912637A (en) * | 2022-05-21 | 2022-08-16 | 重庆大学 | Operation and maintenance decision method and system for man-machine knowledge map manufacturing production line and storage medium |
-
2021
- 2021-12-08 CN CN202111490653.9A patent/CN114385782A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912637A (en) * | 2022-05-21 | 2022-08-16 | 重庆大学 | Operation and maintenance decision method and system for man-machine knowledge map manufacturing production line and storage medium |
| CN114912637B (en) * | 2022-05-21 | 2023-08-29 | 重庆大学 | Human-computer object knowledge graph manufacturing production line operation and maintenance decision method and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hui et al. | Data mining for customer service support | |
| CN108491378B (en) | Intelligent response system for operation and maintenance of electric power information | |
| Lau et al. | Design and implementation of an integrated knowledge system | |
| CN111859969A (en) | Data analysis method and device, electronic equipment and storage medium | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| CN116128213A (en) | Industrial chain map construction and analysis method and system | |
| CN114385782A (en) | Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph | |
| CN114997624A (en) | Intelligent whole-person safety production responsibility management system | |
| CN114117065A (en) | Knowledge graph construction method and system based on power production statistical service | |
| CN111784192A (en) | Industrial park emergency plan executable system based on dynamic evolution | |
| CN115510214A (en) | A stock index knowledge graph construction processing system, method, device, processor and storage medium for intelligent question answering in financial field | |
| CN114049082A (en) | Power grid technical improvement overhaul cost data structuring method | |
| CN113792157A (en) | Domain mechanism-oriented knowledge base construction method | |
| JP2005044046A (en) | Engineering work request support system, method, and program | |
| KR20080112141A (en) | Construction project performance management method and system using bsc and the data warehouse | |
| CN118246895A (en) | Nuclear power plant maintenance auxiliary decision-making method based on knowledge graph | |
| Sinlae et al. | Application Of Business Intelligence In The Analysis And Visualization Of Xyz University Alumni Data Using The Tableau Platform | |
| Borchers et al. | DESIGNING AI-BASED SYSTEMS TO SUPPORT THE ANALYSIS OF CITIZENS’INPUTS FROM E-PARTICIPATION | |
| Coelho et al. | Online platform for case studies in smart cities | |
| JP2004326617A (en) | Customer information processing program and method | |
| Chen et al. | Development and evaluation of a character social network relationship map tool in an ancient book digital humanities research platform | |
| Li et al. | The framework of constructing university coMprehensive evaluation system based on online comments | |
| Wei | Design and Application of University Evaluation Performance Intelligent Analysis Based on Data Mining | |
| Wang et al. | Research on Construction and Application of Knowledge Mapping of Intelligent Transportation Inspection | |
| Stohr | Automated support for formulating linear programs |
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 |