CN115238099A - Industrial Internet data middle platform construction method for energy industry equipment - Google Patents
Industrial Internet data middle platform construction method for energy industry equipment Download PDFInfo
- Publication number
- CN115238099A CN115238099A CN202211021985.7A CN202211021985A CN115238099A CN 115238099 A CN115238099 A CN 115238099A CN 202211021985 A CN202211021985 A CN 202211021985A CN 115238099 A CN115238099 A CN 115238099A
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- knowledge
- graph
- core
- 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
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- 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
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses an energy industry equipment-oriented industrial internet data center platform construction method, which integrates structured data, semi-structured data, unstructured data and time sequence data by taking energy industry equipment as a core, builds an equipment object by relying on KKS/BCS equipment coding and a knowledge graph, realizes data center platform construction from acquisition, storage, administration to service, and supports business center platform and SaaS application. The data center station takes KKS/BCS coded process equipment as a center, and is composed of four types of data of structuring, semi-structuring, non-structuring and time sequence to form a data pasting source layer, a data management layer and a data service layer. The core of the construction method is to construct a data middle platform by taking equipment data as a main line, and realize a data middle platform construction target through design purchase, installation and debugging to operation overhaul and retired scrapped equipment full life cycle data management by taking entity data storage and mapping/indexing data storage as a graph database storage system of the core.
Description
Technical Field
The invention relates to the technical field of data middlings in the energy industry, in particular to an industrial internet data middling construction method for energy industry equipment.
Background
KKS/BCS coding system description of the device:
(1) KKS coding system: also known as a power plant identification System, and is derived from germany, and is short for a kraft-Kennzeichen System, and mainly comprises three types including process-related codes, installation point codes and position codes.
(2) BCS coding system: the method is a unified modeling of the measurement data according to the IEC 61850 Basic Communication Structure, so that all parties have common and unified knowledge on the definition of the data.
Knowledge graph technology:
a knowledge graph is a technical method for describing the association between knowledge and modeling world everything by using a graph model. The knowledge graph is a data structure based on a graph and consists of nodes (points) and edges (edges), each node represents an entity, each Edge is a relation between the entities, and the knowledge graph is a semantic network in nature. An entity refers to something in the real world, such as a person, company, device, etc.; relationships are used to express some kind of linkage between different entities.
Graph database technology:
graph databases, which are derived from Euler and graph theory (graph thesaurus), may also be referred to as graph-oriented/graph-based databases, have the basic meaning of storing and querying data in a data structure such as a "graph". The data model is mainly embodied by nodes and relations (edges), and can also process key value pairs, and the advantage is that the complex relation problem is rapidly solved. The graph database is a non-relational database and supports operations such as query, addition, deletion, update and the like on graph structures. Compared with the traditional relational database, the query speed is high, the operation is simple, more abundant relation showing modes can be provided, and the Neo4J database is a representative native database.
The conventional data middle platform is based on structured, semi-structured, unstructured and time sequence data, is oriented to construct a data asset directory, is targeted to provide data service, is mostly managed and constructed according to data sources or industry classification and other modes, most services and applications in the energy industry are carried out around equipment, and the construction of the conventional middle platform is inconvenient to use, has strong IT (information technology) attributes, and does not accord with the use habits of production service personnel such as operation and maintenance, so a new data middle platform construction method facing the equipment in the energy industry is needed.
Disclosure of Invention
The invention aims to provide a method for constructing a data center station of an industrial internet by taking equipment as a center and utilizing a knowledge map technology and a graph database technology through the whole life cycle of the equipment in the energy industry;
the invention is realized by the following steps:
the industrial internet data middle platform construction process for the energy industry equipment comprises the whole process from acquisition, storage, management to service, and is composed of a data pasting layer, a data management layer and a data service layer which are sequentially built on a bottom layer.
The data of the data pasting layer is composed of structured data, semi-structured data, unstructured data and time sequence data, wherein the structured data is composed of core basic information and other non-core structured data from various stations and energy equipment. The core structure information of the equipment is from organization units of different levels and different energy industry categories, the core information of the equipment is not uniform in structure and inconsistent in description, a globally unique equipment identifier cannot be formed, the equipment is inconvenient to use and manage, at the stage, a data coding tool needs to be used, the equipment is uniformly coded according to a KKS/BCS coding standard, a uniform structure of the core information of the equipment is formed and used as a core for building a data middle station, and data governance is carried out by taking the uniform structure as a center to form an equipment data/knowledge system.
The data management layer is mainly formed by a knowledge graph construction process based on equipment, and comprises information extraction, knowledge fusion and knowledge processing, wherein entity data penetrating through a data management stage are mainly core basic data of the equipment, and other data surround the core basic data to be managed and constructed according to a knowledge graph principle. The information extraction is to extract entities, attributes and the mutual relations among the entities from various types of data sources, and form an ontology knowledge expression taking equipment as a main line on the basis of the entity knowledge expression; the knowledge fusion is a process of standardized governance, wherein new data and knowledge are acquired and need to be integrated to eliminate ambiguity and inconsistency; the knowledge processing is to add qualified parts to a data center station after quality evaluation on new fused data knowledge so as to ensure the quality of the data and knowledge, and to store the qualified data or knowledge in a database in the form of entity data or mapping data/index data for use in a data service manner.
And the data service layer is used for uniformly providing the treated equipment full-life cycle data to service middleboxes and SaaS applications in a data object or data view technical mode, so that the requirements of various services and applications on the data are met.
Further, the core function of the data center station construction method provided by the invention is executed according to the following steps:
(1) And KKS/BCS coding is carried out on the equipment by relying on a data coding tool to form the global unique code of the equipment.
Firstly, using a data coding tool to manage a data dictionary and creating a basic data dictionary and a complex data dictionary; secondly, coding rule management is carried out, coding rules and value ranges of KKS and BCS are created, the coding rules are created, code segments are created, coding topology is checked, and the like, the created coding rules need to be checked, the value threshold is created and modified, and the rules and the value ranges can be used only after the rules and the value ranges pass the checking; and finally, model management, including the import, browsing and online maintenance of a CIM public information model and a BCS basic communication structure standard, wherein a BCS global unique code of the equipment can be constructed through the BCS model standard.
(2) And constructing a network knowledge system of the equipment information based on the knowledge graph technology.
Firstly, establishing a knowledge graph Schema, wherein the knowledge graph Schema is used for defining a knowledge graph data model and expressing vocabulary system normalized data for describing a physical world. A Schema of a knowledge graph is a data model in a field, and comprises meaningful concept types in the field and attributes of the concept types, and the Schema design comprises entity definitions and entity relation definitions. And the creation of the device knowledge graph Schema comprises the definition and creation of an ontology and classification, a relation and classification, an attribute and classification and a data type and classification.
And secondly, modeling an equipment knowledge graph model, wherein knowledge modeling is a process of establishing a conceptual model of the knowledge graph so as to reasonably organize knowledge, better organize ontology, relation and attribute and form a graph data knowledge model. A net atlas general graph is formed by constructing an equipment main graph model, a fault subgraph, an application subgraph, a time sequence data subgraph, an organization subgraph and a user subgraph. The network relation comprises various ontologies and relation classes such as an ontology-relation-ontology, an ontology-attribute value and a virtual category-ontology, and is different from a traditional tree structure data organization mode, the organization mode of knowledge mapping equipment data is a complex grid, and the relation between node data has a direction and is unidirectional or bidirectional.
And finally, performing knowledge extraction and association, then hanging the knowledge graph model to the equipment knowledge graph model, instantiating the model to form a knowledge graph of entity data, and then storing the knowledge graph into a graph database.
(3) Entity data and mapping data/index data for device knowledge graph based on graph database storage
The basic meaning of graph databases is to store and query data in a data structure such as a "graph". The equipment knowledge data storage is to design a bottom storage mode aiming at the knowledge representation mode of the equipment knowledge map, complete the storage of various kinds of knowledge and data, and support the effective management and calculation of large-scale map data. The objects of the knowledge storage comprise basic attribute knowledge, associated knowledge, event knowledge, time sequence knowledge, resource knowledge and the like. The quality of the knowledge storage mode directly influences the efficiency of knowledge query, knowledge calculation and knowledge update in the knowledge map.
The device body in the knowledge map is corresponding to the device field in the relational database table by adopting a 'direct extraction method of structured data', so that a large amount of redundant information may exist, and the storage space waste and the cost are increased. Aiming at the core basic data of the equipment, the method of storing entity data in a graph database is adopted, so that the efficiency of query analysis is ensured, and the heterogeneous situation of the equipment body data is solved by adopting a body mapping and body integration method, so that the heterogeneous body is eliminated, the body alignment is realized, the body structure is standardized, and the interoperation among heterogeneous bodies is achieved.
By mapping the body and the relation of other non-core data of the equipment and storing the mapping relation in the graph database instead of all entity data, the occupied space of the graph database is reduced, the supporting capability of the graph database on knowledge map data is utilized, the balance between efficiency and storage is realized, the access speed and efficiency are improved by establishing a path diagram index mode, and sustainable supporting capability is provided for incremental updating iteration and management of future equipment data.
(4) The data management of the whole life cycle of the equipment from design, purchase, installation, operation, maintenance to scrapping is realized by adding the time attribute.
Conventional equipment data management, heavy operation, maintenance, light design scrap, large middle, small two ends and heavy current shortage of the whole body exist, the defect of improving quality management through PDCA circulation exists, data support can be well provided for PDCA circulation of quality management through management of equipment full life cycle data, and the falling support is provided for business application such as future design type selection, process improvement, purchase support and the like.
By adding time attributes or time labels for design, purchase, installation, operation, maintenance and scrapping in the process of constructing the equipment knowledge graph and establishing a full life cycle relationship subgraph of similar equipment through the time attributes and the labels, the data of the full life cycle of iterative equipment can be effectively managed and updated.
Compared with the prior art, the invention has the beneficial effects that:
1. the data center platform with equipment as the center is constructed, so that the data center platform is more in line with the business characteristics of the energy industry, the construction and calling of data services are facilitated, the service center platform and SaaS application are facilitated, and the use habits of production business personnel are more in line with.
2. By using the knowledge map technology and the graph database technology, a new method is provided for the construction of a conventional data center, a data management mode and a data management method with higher efficiency and speed are provided on the basis of not carrying out subversive change on the conventional data center, the traditional tree-shaped data relation is changed into a net-shaped relation for representation, the storage capacity is not increased too much, the organization and the use efficiency of the data are greatly improved, the logic between the data is clearer, and the possibility is provided for future knowledge calculation based on semantics, NLP (non line learning), deep learning and the like.
3. The data management of the full life cycle of the equipment is established through a knowledge graph technology, the integrity of the equipment data is ensured, a data cycle of the equipment PDCA is formed, and sustainable development and iterative support are provided for business application and data management.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings which are needed to be used in the implementation process will be briefly described below, and it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope.
FIG. 1 is a system diagram of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions will be described in detail and completely with reference to the accompanying drawings, wherein the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, a data pasting layer is raw data collected from a data source, structured data is stored in a greenplus data warehouse, semi-structured data is stored in an HDFS, unstructured data is stored in an HDFS and a MongoDB, and a time sequence library is stored using a special library.
The data management layer is used for carrying out data coding by using a special data coding tool, taking wind power equipment as an example, global unique codes of the equipment can be established through BCS coding, an equipment knowledge graph is established by taking core information of the equipment as a center, and static information (equipment models, equipment manufacturers, fixed assets, equipment drawings and the like) and dynamic information (including equipment operation accounts, equipment maintenance records, work tickets, operation tickets, fire tickets, overhaul records, equipment inventory and the like) of the equipment, and primary data and secondary processing data such as main data, metadata, time sequence data and the like of each equipment are all extracted, fused and processed and associated to form equipment panoramic graph data which are stored in a Neo4j graph database to provide support for unified data services.
Data services such as data views and data objects taking the equipment as a main key are constructed through a data service tool, and all the middle tools and business applications can use BCS equipment coding to inquire and analyze the panoramic data of the equipment.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A construction method of industrial Internet data middlings for equipment in the energy industry is characterized in that a data/knowledge system with equipment as a core and a net-shaped complex relation is constructed by means of a knowledge map technology, equipment data are stored in a graph database in the form of entity data and mapping/indexing data, and construction of data middlings for full-life-cycle equipment data management is supported.
2. The method for constructing the industrial internet data middlebox for the energy industry equipment as claimed in claim 1, wherein the relationships between the coded equipment and the equipment in each hierarchy are formed by taking a tree-shaped vertical structure of KKS/BCS as a core and combining equipment horizontal relationships of process flow and business logic, and the cross-correlation is formed to have a one-way and two-way meshed complex data/knowledge system.
3. The method for constructing the industrial internet data middlebox facing the energy industry equipment as claimed in claim 1, wherein not all the source layer data are stored in one part of the graph data, but core equipment basic data are stored in a graph database in a solid data form, and non-core data are mainly stored in a mapping relation or index data of the data, so that repeated storage of the data is reduced, and support of the graph database on the equipment knowledge graph is realized.
4. The method for constructing the industrial internet data center platform for the energy industry equipment as claimed in claim 1, wherein under the condition that other dimensions are the same, relationships and attributes among equipment data are organized according to a full life cycle mode of equipment which is designed, purchased, installed, debugged, operated, overhauled and retired, and support is provided for data governance and data center platform construction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211021985.7A CN115238099A (en) | 2022-08-24 | 2022-08-24 | Industrial Internet data middle platform construction method for energy industry equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211021985.7A CN115238099A (en) | 2022-08-24 | 2022-08-24 | Industrial Internet data middle platform construction method for energy industry equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115238099A true CN115238099A (en) | 2022-10-25 |
Family
ID=83680916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211021985.7A Pending CN115238099A (en) | 2022-08-24 | 2022-08-24 | Industrial Internet data middle platform construction method for energy industry equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115238099A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910130A (en) * | 2023-09-08 | 2023-10-20 | 中国长江电力股份有限公司 | Construction method of industrial data middle platform frame for hydropower equipment |
-
2022
- 2022-08-24 CN CN202211021985.7A patent/CN115238099A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910130A (en) * | 2023-09-08 | 2023-10-20 | 中国长江电力股份有限公司 | Construction method of industrial data middle platform frame for hydropower equipment |
| CN116910130B (en) * | 2023-09-08 | 2023-12-26 | 中国长江电力股份有限公司 | Construction method of industrial data middle platform frame for hydropower equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | KnowIME: a system to construct a knowledge graph for intelligent manufacturing equipment | |
| CN105139281A (en) | Method and system for processing big data of electric power marketing | |
| CN103778304A (en) | Motor vehicle drive axle design method | |
| CN105183834A (en) | Ontology library based transportation big data semantic application service method | |
| CN112182077B (en) | Intelligent operation and maintenance system based on data middling platform technology | |
| CN114077674A (en) | Power grid dispatching knowledge graph data optimization method and system | |
| CN115858513A (en) | Data governance method, data governance device, computer equipment and storage medium | |
| CN106503811A (en) | A kind of infrastructure full life cycle management method based on big data | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| CN115757810A (en) | Method for constructing standard ontology of knowledge graph | |
| CN115238099A (en) | Industrial Internet data middle platform construction method for energy industry equipment | |
| Tang et al. | Automatic schema construction of electrical graph data platform based on multi-source relational data models | |
| CN113722564A (en) | Visualization method and device for energy and material supply chain based on space map convolution | |
| CN113254517A (en) | Service providing method based on internet big data | |
| CN115937881A (en) | Method for automatically identifying content of knowledge graph construction standard form | |
| CN116011564A (en) | Entity relationship completion method, system and application for power equipment | |
| CN115858498A (en) | Five-dimensional space-time distributed database construction method and device | |
| CN115618007A (en) | Monitoring data analysis system based on knowledge graph | |
| Tang et al. | Ontology based Knowledge Modeling and Extraction of Power Equipment Supply Chain | |
| Shouaib et al. | Survey on iot-based big data analytics | |
| CN112784129A (en) | Pump station equipment operation and maintenance data supervision platform | |
| Wang | RETRACTED: Research on Big Data Integration Method for Investment Statistics Based on Artificial Intelligence Technology | |
| CN114090790B (en) | Man-machine friendly data logic fusion power knowledge graph and construction method thereof | |
| Luo et al. | Ontology modeling method applied in simulation modeling of distribution network time series operation | |
| CN102609777A (en) | Method for controlling emergency decision knowledge base system for disaster reduction |
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 |