CN115271116A - Power grid secondary equipment fault tracing, operation and maintenance service method and system - Google Patents

Power grid secondary equipment fault tracing, operation and maintenance service method and system Download PDF

Info

Publication number
CN115271116A
CN115271116A CN202210873057.7A CN202210873057A CN115271116A CN 115271116 A CN115271116 A CN 115271116A CN 202210873057 A CN202210873057 A CN 202210873057A CN 115271116 A CN115271116 A CN 115271116A
Authority
CN
China
Prior art keywords
data
service
fault
knowledge
tracing
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
Application number
CN202210873057.7A
Other languages
Chinese (zh)
Inventor
刘军
任祥伟
郭瑞瑞
裴辉东
戴宏伟
张金鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongfang Electronics Co Ltd
Original Assignee
Dongfang Electronics Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dongfang Electronics Co Ltd filed Critical Dongfang Electronics Co Ltd
Priority to CN202210873057.7A priority Critical patent/CN115271116A/en
Publication of CN115271116A publication Critical patent/CN115271116A/en
Pending legal-status Critical Current

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
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • 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
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
    • 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

Abstract

The invention discloses a method and a system for tracing faults of secondary equipment of a power grid and an operation and maintenance service, which relate to the technical field of fault processing of the secondary equipment of the power grid and comprise the following steps: establishing an enterprise data gene library; extracting fault knowledge, cleaning data and storing knowledge; establishing a service middle station, and acquiring data transmitted by a channel; building a fault tracing platform; constructing a product fault tracing and operation and maintenance service knowledge map database, and designing and developing a knowledge map search engine; carrying out fault tracing; updating a knowledge graph database; and constructing a fault tracing domain knowledge graph of the new product through a rule-based reasoning algorithm. According to the invention, by integrating research and development, purchasing and production link data and quickly building a fault tracing platform, the problem of enterprise data isolated island is solved, the fault reason is quickly positioned, and the fault tracing efficiency is improved; and updating the domain knowledge map database according to the service operation, equipment failure and solution conditions.

Description

Power grid secondary equipment fault tracing, operation and maintenance service method and system
Technical Field
The invention relates to the technical field of fault processing of secondary equipment of a power grid, in particular to a fault tracing, operation and maintenance service method and system for the secondary equipment of the power grid.
Background
At present, the research and development of secondary equipment of a power grid and manufacturing enterprises complete the management of products from sales to after-sales services according to the processes of sales, design, purchase, production, service and the like of the manufacturing enterprises, and generated business data are dispersed in corresponding business systems: ERP, MES, PLM, engineering service and other systems, the data exchange among the systems is completed through an interface, and the information utilization rate is low.
When the secondary equipment has problems on the site, the secondary equipment basically waits for after-sales service personnel to arrive at the site for phenomenon analysis and fault location, then communicates with technical support personnel of a company to clarify the problems, the company posts the repaired spare parts to the site, the after-sales service personnel replaces and tests the spare parts, and finally the problems are eliminated, so that the technical level and experience of the after-sales service personnel are relatively dependent. The existing power equipment informatization system focuses on a service process, the service data is not sufficiently applied, and the data island problem is serious. In a conventional power equipment information system, only the failure of equipment is registered. The fault tracing of the power equipment needs to be connected with an ERP system, an MES system and a PLM system, the formats of data storage of a plurality of systems are different, the data need to be subjected to format conversion, the statistical analysis cannot be directly carried out, and the efficiency is low.
Chinese patent document CN113360555A discloses a fault diagnosis and analysis method and system based on big data of secondary devices in a power grid, which extracts historical data of a fault station from a unified data platform of the power grid, extracts instantaneous value information of current and voltage when a fault occurs, and performs fault analysis to form a fault analysis report and a solution. The technical scheme only focuses on the business process, only registers the fault condition of the equipment, and has insufficient application to other business system data and serious data island problem. The fault tracing of the power equipment needs to be connected with an ERP system, an MES system and a PLM system, and the data storage formats of a plurality of systems are different, so that a power grid secondary equipment fault tracing, operation and maintenance service method and a system which can comprehensively read real-time fault data of a multi-service system and directly perform statistical analysis are urgently needed.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the system for the fault tracing of the power grid secondary equipment overcome the defects in the prior art, and based on a full life cycle management mode of the power grid secondary equipment product, a knowledge base is formed by utilizing data accumulated by various informatization systems, technologies such as a knowledge map and the like are applied to the fault tracing of the power grid secondary equipment, the intelligent level of the fault tracing is improved, and the method and the system for the fault tracing and operation and maintenance service of the power grid secondary equipment are provided.
The technical scheme for solving the technical problems is as follows:
a power grid secondary equipment fault tracing and operation and maintenance service method is characterized by comprising the following steps:
s1, combing the service and data, and establishing an enterprise data gene library;
s2, fault knowledge extraction, data cleaning and knowledge storage, namely extracting existing defect records and corresponding processing schemes in an information system in a rule-based mode, carrying out data analysis and cleaning on the extracted defect records and the corresponding processing schemes, storing and establishing a knowledge base;
s3, establishing a service middle platform, connecting a connector with a data channel configured in a data gene library based on a virtualization technology and a container technology, acquiring data transmitted by the channel, and storing the data by using a data model, wherein the data model is bound with a specific service model;
s4, building a fault tracing platform, and building the fault tracing platform on the basis of the built database and the built business middle platform;
s5, constructing a knowledge map database, extracting generated data based on the fault knowledge, constructing a product fault tracing and operation and maintenance service knowledge map database, storing object relations of the knowledge map by using a map database, and displaying the knowledge map through a visual interface;
s6, tracing the faults;
s7, updating the knowledge map database, continuously updating the domain knowledge map database according to service operation, equipment faults and solution conditions, and realizing closed-loop management of fault tracing;
and S8, knowledge graph reasoning, namely constructing the knowledge graph of the fault tracing field of the new product through a rule-based reasoning algorithm for the product of the deformed design based on the knowledge graph of the original product.
Further, the establishment of the enterprise database comprises the following steps: s1.1, combing the enterprise metadata, sorting the enterprise data asset catalogue, and compiling a data sharing open catalogue, wherein the data sharing open catalogue comprises the following steps: structured data and related semi-structured data of suppliers, products and engineering service knowledge bases; s1.2, based on data search, providing information such as table use description, data categories, data consanguinity, field consanguinity and the like, and establishing an enterprise data gene library; s1.3, a connection bridge between data is built, and all elements such as business data, product design, department responsibility and the like are organically related to form a data standard.
Further, the fault knowledge extraction, data cleaning and knowledge storage method comprises the following steps: s2.1, performing semantic processing on the defect recording and processing scheme; s2.2, extracting stems from the data after the semantic processing by using a natural language processing method; s2.3, performing data cleaning on the extracted data, wherein the data cleaning comprises missing data judgment, missing data processing, noise data detection and noise data processing; s2.4, establishing a knowledge base corresponding to the defect-scheme by the entity, the attribute and the relationship according to the entity-relationship-entity triple and the entity-attribute value pair.
Further, the missing data judgment comprises the steps of rapidly searching for missing of data by using thermodynamic diagrams, finding out attribute missing values by means of an info method, and counting missing rates by means of an application method. And the missing data processing comprises the steps of directly deleting missing row data and column attributes, filling the mean value, determining the filling of the nearest distance and filling missing values by hot cards. The noise data detection comprises a mean standard deviation method and an upper and lower four median and median method, wherein numerical values are not in a range (mean-2 x standard deviation, mean +2x standard deviation) and a range (lower four median-1.5 x median and upper four median +1.5x median) to be judged as noise data. The noise data processing comprises noise data deletion and noise data rewriting; deleting the noise data, including deleting the whole row data and deleting the whole column data; and the noise data rewriting comprises average value replacement, median replacement and adjacent maximum and minimum boundary value replacement.
Further, the knowledge store comprises: the relational database is used for storing structured data, and the document, drawing and video data are stored in a file form.
Further, the fault tracing platform is built, and the method comprises the following steps: s4.1, based on the built data gene library and the built business middle platform, extracting data to a cloud computing platform through data acquisition and existing multi-source data access, and establishing a unified standard data modeling system; s4.2, constructing a big data platform by taking service layering as a framework, completing system construction related to enterprise data value, such as a system framework, a data map, data quality, an organization framework, a standard flow and the like, and realizing rapid fusion of data, service and intelligence; s4.3, unifying service outlets, providing a characteristic data service, realizing code-free development and intelligent performance optimization of the data service, and providing data intelligent capability for upper-layer business application; s4.4, combing production problems and management problems to be solved and main business functions to be realized by the system around the links of enterprise purchasing, planning, product detailed lists, raw material inventory, workshop order batch information, arranged production plans, supply demands and the like; s4.5, a micro-service development mode is adopted, based on the big data platform and the high-multiplexing software development platform, the function development of the system is completed, and data, service and functions of the model are imported into the fault tracing platform by dragging and dropping various UI components through UI building; and S4.6, the built fault tracing platform is issued to an application platform through an issuing function for a user to use.
Further, the characteristic data services comprise data intelligent query services, complex data query services and real-time data push services.
Further, the fault tracing implementation comprises the following steps: s6.1, sending a fault tracing form to a first-level user, wherein the first-level user inquires fault reasons based on a knowledge graph search engine and feeds back the fault reasons to a second-level user; s6.2 the second-level user inquires the corresponding logic relation classification of the fault product in the fault tracing platform and inquires the products in the same batch. S6.3, tracing the finished products and semi-finished products with problems and other user sites; s6.4, tracing the used materials and software, and judging whether the materials can affect other products to form a tracing system.
Further, the corresponding logical relation classification of the fault products comprises storage, preparation and delivery.
The invention also provides a power grid secondary equipment fault tracing and operation and maintenance service system, which comprises: the database module provides information such as table use description, data categories, data blood relationship, field blood relationship and the like; the knowledge base module is used for storing the defect records and the corresponding processing schemes; the business middle station module is connected with a data channel of the data gene library through a connector, acquires data transmitted by the channel and stores the data by using a data model; the fault tracing platform module realizes the rapid fusion of data, business and intelligence and provides a characteristic data service; and the knowledge map library module is used for storing the object relation of the knowledge map by adopting a map database and displaying the knowledge map through a visual interface.
The invention has the beneficial effects that:
1. the usability of the fault tracing knowledge base is improved, the display is visual, the understanding is easy, the training and using cost of staff is reduced, and the after-sale service cost of enterprises is reduced; by utilizing the fault tracing and operation and maintenance service system, the reason of the fault can be quickly positioned, the problem of low tracing efficiency is solved, the customer service level is improved, and the satisfaction degree of a user on a product is improved.
2. Aiming at the problems of multi-source and heterogeneous data and the like in the digital transformation process, the data and the business related to the links of research and development, purchase, production and the like of an enterprise are combed, a data space and a business space are established, and the data and the business space are applied to the rapid development of intelligent service software of enterprise products, so that the problem of enterprise data isolated island is solved.
3. The intelligent service of enterprise products is delivered to the field application of a power grid company as a novel service mode and is put into practical use; a private cloud platform of enterprise product intelligent service is built, remote operation and maintenance housekeeping service is provided for medium and small enterprises, and the labor operation and maintenance cost of the enterprises is reduced.
4. The fault tracing platform can be rapidly built based on a data center platform of an enterprise data gene library and a service platform for one-cloud multi-terminal intelligent high-multiplexing software development, and the problem of low building efficiency of the fault tracing platform is solved.
5. The intelligent level of fault tracing is improved, and the knowledge map of a new product is formed through knowledge reasoning.
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 flow chart of a power grid secondary device fault tracing and operation and maintenance service method in an embodiment of the present invention.
Fig. 2 is a schematic structural component diagram of a power grid secondary equipment fault tracing, operation and maintenance service system in the embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the following description is merely exemplary and exemplary in nature and is in no way intended to limit the invention, its application, or uses, and the relative positions of components and steps, numerical expressions, and numerical values set forth in the embodiments do not limit the scope of the invention unless it is specifically stated otherwise. Additionally, techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail but are intended to be part of the specification where appropriate.
In the embodiment of the invention, based on the whole life cycle management mode of the power grid secondary equipment product of the enterprise, a knowledge base is formed by utilizing data accumulated by each informatization system of the enterprise, the technologies such as a knowledge map and the like are applied to the aspect of fault tracing of the power grid secondary equipment, and the intelligent level of fault tracing is improved. Based on the built data space and the built service space, the method adopts a cloud-oriented multi-terminal intelligent high-multiplexing software development and operation platform to complete industrial management software development, and moves an offline fault tracing mode to an online mode, so that the informatization and the intellectualization of fault tracing and the machine account information management, the fault tracing and the early warning of management products are realized.
Fig. 1 illustrates a general flowchart of a power grid secondary equipment fault tracing and operation and maintenance service method according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
s1, combing the service and the data, and establishing an enterprise data gene library.
S2, fault knowledge extraction, data cleaning and knowledge storage, wherein existing defect records and corresponding processing schemes in an information system are extracted in a rule-based mode, data analysis and cleaning are carried out on the extracted defect records and the corresponding processing schemes, and a knowledge base is stored and established.
S3, establishing a service central station, designing the service central station of the industrial management software based on a virtualization technology and a container technology, connecting the service central station with a data channel of a data gene library through a connector, acquiring data transmitted by the channel, and storing the data by using a data model; and binding the data model with the specific service model to provide data support for the service model, thereby forming a group of high-multiplexing components for rapidly building a fault tracing platform.
S4, building a fault tracing platform, and building the fault tracing platform on the basis of the built database and the built business middle platform; the fault tracing platform comprises a plurality of groups of data models and high-multiplexing components bound with the service models, and provides data support for the service models.
S5, constructing a knowledge map database, extracting generated data based on the fault knowledge, constructing a product fault tracing and operation and maintenance service knowledge map database, storing object relations of the knowledge map by using a map database, displaying the knowledge map through a visual interface, designing and developing a knowledge map search engine, and supporting quick search of the knowledge base. The knowledge graph search engine is internally provided with a fault keyword matching index matrix, can automatically match industry synonyms, fixed phrases and Chinese and English abbreviations according to fault keywords, sets keyword matching value parameters, sorts knowledge base search results according to the matching values and feeds the results back to a user, and completes quick and accurate search of a knowledge base.
And S6, carrying out fault tracing.
And S7, updating the knowledge map database, continuously updating the field knowledge map database according to service operation, equipment faults and solution conditions, and realizing closed-loop management of fault tracing.
And S8, knowledge graph reasoning, namely constructing the knowledge graph of the fault tracing field of the new product through a rule-based reasoning algorithm for the product of the deformed design based on the knowledge graph of the original product. Specifically, a Neural network-based knowledge graph inference NTN model (Neural temporal Networks) is adopted, and two actually-occurring power grid secondary equipment fault entities (e) are extracted from a knowledge base1，e2)(e1，e2∈RdIs a vector representation of the entity) summarizing the relationship between the voltage, current, power factor, phase and frequency transients and equipment parameters, service modules for each fault entity. The reasoning calculation formula is as follows:
g(e1，R，e2)＝uT Rf(eT 1WR [1:k]e2+VR[e1e2]+bR
compared with a traditional standard linear neural network fault tracing mode, the knowledge graph reasoning model uses a bilinear tensor layer (bilinear tensor layer) to associate two entity vectors, an entity vector in the graph reasoning model measures the average value of all word vectors, the number of words in the entity is far less than the number of the entity, and the word vectors can be fully and repeatedly utilized to construct entity representation; and (3) corresponding the semantic relation between different slices of the relation tensor and the vectors of different entities to enhance the semantic relation between different entities. The probability score of a certain relation between two entities is calculated through the model, and the probability score can be applied to the products of deformation design to construct relation prediction and knowledge base completion of the knowledge map in the fault tracing field of a new product.
In a preferred embodiment, the service and data combing in step S1 includes combing the current service situation of an enterprise, including the research and development and manufacturing process, the production process, the supplier and customer information, the product information, the current operation situation of the equipment, the historical fault and maintenance situation, the intelligentization level, the data acquisition mode and capability, and the equipment monitoring application level of the company in the smart grid secondary equipment industry. The establishment of the enterprise database in the step S1 comprises the following steps: the method for carding the enterprise metadata, sorting the enterprise data asset catalogue and compiling the data sharing open catalogue comprises the following steps: structured data and related semi-structured data of suppliers, products, engineering service knowledge bases and the like; on the basis of data search, providing information such as table use description, data categories, data consanguinity, field consanguinity and the like, and establishing an enterprise data gene library; and (3) constructing a connection bridge between data, organically associating various elements such as business data, product design, department responsibility and the like, and forming an industrial enterprise data standard. Aiming at the problems of multi-source and heterogeneous data and the like in the digital transformation process, the data and business related to the links of research and development, purchase, production and the like of enterprises are combed, a data space and a business space are established, and the problem of enterprise data isolated island is solved.
In a preferred embodiment, the fault knowledge extraction, data cleaning and knowledge storage in step S2 include extracting existing fault records and corresponding processing schemes in various existing information systems such as an ERP system, an MES system, a PLM system and an engineering service system. And performing semantic processing on the defect recording and processing scheme, and extracting stems from the data subjected to the semantic processing by using a natural language processing method. And (4) performing data cleaning on the extracted data, wherein the data cleaning comprises missing data judgment, missing data processing, noise data detection and noise data processing. And establishing a knowledge base corresponding to the defect-scheme by the entity, the attribute and the relationship according to the entity-relationship-entity triple and the entity-attribute value pair.
The fault knowledge extraction in the step S2 is specifically that a language Cloud platform (LTP-Cloud) of Harbin university of industry is adopted, a Chinese word segmentation calling interface of the latest version is combined with a conditional Random Fields (CFRs) algorithm, a method based on dictionary matching and a method based on statistical machine learning are fused, word segmentation is carried out on a defect recording and processing scheme, a natural language processing technology based on deep learning is used for extracting stems, and the platform is high in operation speed, high in stem extraction accuracy and good in overall application effect.
And the data cleaning in the step S2 comprises 4 steps of judging missing values, processing the missing values, detecting abnormal values and processing the abnormal values, so that the abnormal values of noise are eliminated, the missing values are reasonably filled, the repeated values are accurately removed, and the data accuracy is improved. The missing data determination includes: the method comprises the following steps of (1) quickly searching missing of data by using thermodynamic diagrams, wherein the missing position and the missing degree are clear at a glance; the attribute missing value is found by means of an info method, the operation is simple and convenient, the speed is high, and the attribute missing value can be quickly positioned; the deletion rate is counted by an application method, and the result is displayed in a percentage mode, so that the method is convenient and quick. And the missing data processing comprises the steps of directly deleting missing row data and column attributes, filling the mean value, determining the filling of the nearest distance and filling missing values by hot cards. The noise data detection comprises a mean standard deviation method and an upper and lower four median and median method, wherein numerical values are not in a range (mean-2 x standard deviation, mean +2x standard deviation) and a range (lower four median-1.5 x median and upper four median +1.5x median) to be judged as noise data. The noise data processing comprises noise data deleting and rewriting; deleting the noise data, namely deleting the whole row data and the whole column data; and the noise data rewriting comprises average value replacement, median value replacement and adjacent maximum and minimum boundary value replacement. The data cleaning process has the advantages of small error, high efficiency, low cost and the like, and can effectively ensure the stability and the safety of data.
And step 2, storing the fault knowledge, wherein the stored system data with different formats can be directly subjected to statistical analysis after being extracted and cleaned according to the rules. The relational database is used for storing structured data, and the file form is used for storing data such as documents, drawings, videos and the like.
In a preferred implementation, the step S3 includes designing and developing a service center platform of the industrial management software, where the service center platform is connected to a data channel configured in the data gene library through a connector, and obtains data transmitted by the channel, and the data transmitted by the channel is stored by using a data model; and binding the data model with the specific service model to provide data support for the service model, so that the data model becomes a group of high-multiplexing components for rapidly building a fault tracing platform.
In a preferred embodiment, the building of the fault tracing platform in step S4 includes: and constructing a fault tracing platform on the basis of the constructed data gene library and the constructed service platform, extracting data to a cloud computing platform through data acquisition and the existing multi-source data access, and establishing a unified standard data modeling system. And a big data middle platform is constructed by taking the service hierarchy as a framework, system construction related to enterprise data value such as a system framework, a data map, data quality, an organization framework, a standard flow and the like is completed, and rapid fusion of data, service and intelligence is realized. The unified service outlet provides three special data services of intelligent data query service, complex data query service and real-time data push service, realizes code-free development and intelligent performance optimization of the data service, and provides data intelligent capability for upper-layer business application. The production problems and the management problems to be solved and the main business functions to be realized by the system are combed around the links of enterprise purchasing, planning, product detailed lists, raw material inventory, workshop order batch information, arranged production plans, supply demands and the like. The method comprises the following steps of completing the function development of a system by adopting a micro-service development mode in the prior art and based on a big data middle platform and a high multiplexing software development platform, and importing data, services and functions of a model into a fault tracing platform by building a UI and dragging and dropping various UI components; and releasing the built application to an application platform through a releasing function for all users to use.
In a preferred embodiment, the tracing of the fault in step S6 includes: and sending the fault tracing form to quality department personnel, and inquiring fault reasons and feeding back the operation and maintenance personnel by the quality department personnel based on a knowledge map search engine of the fault tracing and operation and maintenance service system. The operation and maintenance personnel inquire the corresponding logic relation classification of the fault product in the fault tracing, operation and maintenance service system: and inquiring the products in the same batch in the states of library, preparation, delivery and the like. Tracing the product products, semi-finished products and other user sites with problems, and tracing the materials and software to judge whether the materials affect other products to form a tracing system. When a field product breaks down, the fault tracing platform can be used for rapidly tracing the defective finished product, semi-finished product and other user fields, all the time, the used materials are traced, whether the materials influence other products or not is judged, and a tracing standardized system is formed.
The power grid secondary equipment fault tracing and operation and maintenance service system shown in FIG. 2 is delivered to a power grid company as a novel service mode, is applied and put into practical use on site, builds a private cloud platform of enterprise product intelligent service, provides remote operation and maintenance manager service for small and medium-sized enterprises, and reduces the manpower operation and maintenance cost of the enterprises. By utilizing the fault tracing and operation and maintenance service system (including defects and solutions), the reason of the fault can be quickly positioned, the customer service level is improved, and the satisfaction degree of the user on the product is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. A power grid secondary equipment fault tracing and operation and maintenance service method is characterized by comprising the following steps:
s1, combing the service and data, and establishing an enterprise data gene library;
s2, fault knowledge extraction, data cleaning and knowledge storage, wherein existing defect records and corresponding processing schemes in an information system are extracted in a rule-based mode, the extracted defect records and the corresponding processing schemes are subjected to data analysis and cleaning, and a knowledge base is stored and established;
s3, establishing a service middle platform, connecting a connector with a data channel configured in a data gene library based on a virtualization technology and a container technology, acquiring data transmitted by the channel, and storing the data by using a data model, wherein the data model is bound with a specific service model;
s4, building a fault tracing platform, and building the fault tracing platform on the basis of the built data gene library, knowledge base and business middle platform;
s5, constructing a knowledge map database, extracting generated data based on the fault knowledge, constructing a product fault tracing and operation and maintenance service knowledge map database, and designing and developing a knowledge map search engine;
s6, tracing the faults;
s7, updating the knowledge map database, continuously updating the domain knowledge map database according to service operation, equipment faults and solution conditions, and realizing closed-loop management of fault tracing;
and S8, knowledge graph reasoning, namely constructing the knowledge graph of the fault tracing field of the new product through a rule-based reasoning algorithm for the product of the deformed design based on the knowledge graph of the original product.
2. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 1, wherein the establishing of the enterprise database comprises the following steps:
s1.1, combing the enterprise metadata, sorting the enterprise data asset catalog, and compiling a data sharing open catalog, comprising: structured data and related semi-structured data of suppliers, products and engineering service knowledge bases;
s1.2, based on data search, providing information such as table use description, data category, data consanguinity, field consanguinity and the like, and establishing an enterprise data gene library;
s1.3, a connection bridge among data is built, and all elements such as business data, product design, department responsibility and the like are organically related to form a data standard.
3. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 1, wherein the fault knowledge extraction, data cleaning and knowledge storage comprises the following steps:
s2.1, performing semantic processing on the defect recording and processing scheme;
s2.2, extracting a stem from the semantically processed data by using a natural language processing method;
s2.3, performing data cleaning on the extracted data, wherein the data cleaning comprises missing data judgment, missing data processing, noise data detection and noise data processing;
s2.4, establishing a knowledge base corresponding to the defect-scheme by the entity, the attribute and the relationship according to the entity-relationship-entity triple and the entity-attribute value pair.
4. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 3, characterized in that:
the missing data determination includes: rapidly searching for data missing by using a thermodynamic diagram, finding an attribute missing value by using an info method, and counting the missing rate by using an application method;
the missing data processing comprises the following steps: directly deleting missing row data and column attributes, filling the mean value, determining the nearest distance, and filling missing values by hot cards;
the noise data detection includes: judging that the numerical value is not in a section (the mean value is-2 x of the standard deviation, the mean value is +2x of the standard deviation) and a section (the lower four median is-1.5 x of the median, and the upper four median is +1.5x of the median) as noise data by adopting a mean value standard deviation method and an upper four median and median method;
the noise data processing comprises: noise data deletion and noise data rewriting; deleting the noise data, including deleting the whole row data and deleting the whole column data; and the noise data rewriting comprises average value replacement, median value replacement and adjacent maximum and minimum boundary value replacement.
5. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 3, wherein the knowledge storage comprises: the relational database is used for storing structured data, and the document, drawing and video data are stored in a file form.
6. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 1, wherein the fault tracing platform is built, and the method comprises the following steps:
s4.1, based on the built data gene library and the built business middle platform, extracting data to a cloud computing platform through data acquisition and existing multi-source data access, and establishing a unified standard data modeling system;
s4.2, constructing a big data platform by taking service layering as a framework, completing system construction related to enterprise data value, such as a system framework, a data map, data quality, an organization framework, a standard flow and the like, and realizing rapid fusion of data, service and intelligence;
s4.3, unifying service outlets, providing a characteristic data service, realizing code-free development and intelligent performance optimization of the data service, and providing data intelligent capability for upper-layer business application;
s4.4, combing production problems and management problems to be solved and main business functions to be realized by the system around the links of enterprise purchasing, planning, product detailed lists, raw material inventory, workshop order batch information, arranged production plans, supply demands and the like;
s4.5, a micro-service development mode is adopted, based on the big data platform and the high-multiplexing software development platform, the function development of the system is completed, and data, service and functions of the model are imported into the fault tracing platform by dragging and dropping various UI components through UI building;
and S4.6, the built fault tracing platform is issued to an application platform through an issuing function for a user to use.
7. The power grid secondary equipment fault tracing and operation and maintenance service method as claimed in claim 6, wherein the characteristic data service comprises: the system comprises a data intelligent query service, a complex data query service and a real-time data push service.
8. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 1, wherein the fault tracing implementation comprises the following steps:
s6.1, sending a fault tracing form to a first-level user, wherein the first-level user inquires fault reasons and feeds back the fault reasons to a second-level user on the basis of a knowledge graph search engine;
s6.2, the second-level user inquires corresponding logic relation classification of fault products in the fault tracing platform and inquires products in the same batch;
s6.3, tracing the finished products and semi-finished products with problems and other user sites;
s6.4, tracing the used materials and software, and judging whether the materials can affect other products to form a tracing system.
9. The power grid secondary equipment fault tracing and operation and maintenance service method according to claim 8, wherein the fault products are classified according to logical relations, including being in a warehouse, being in process and being delivered.
10. The utility model provides a power grid secondary equipment trouble is traceed back, operation and maintenance service system which characterized in that: comprises that
The database module provides information such as table use description, data categories, data blood relationship, field blood relationship and the like;
the knowledge base module is used for storing the defect records and the corresponding processing schemes;
the business middle station module is connected with a data channel of the data gene library through a connector, acquires data transmitted by the channel and stores the data by using a data model;
the fault tracing platform module realizes the rapid fusion of data, business and intelligence and provides a characteristic data service;
and the knowledge map library module is used for storing the object relation of the knowledge map by adopting a map database and displaying the knowledge map through a visual interface.
CN202210873057.7A 2022-07-22 2022-07-22 Power grid secondary equipment fault tracing, operation and maintenance service method and system Pending CN115271116A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210873057.7A CN115271116A (en) 2022-07-22 2022-07-22 Power grid secondary equipment fault tracing, operation and maintenance service method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210873057.7A CN115271116A (en) 2022-07-22 2022-07-22 Power grid secondary equipment fault tracing, operation and maintenance service method and system

Publications (1)

Publication Number Publication Date
CN115271116A true CN115271116A (en) 2022-11-01

Family

ID=83769299

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210873057.7A Pending CN115271116A (en) 2022-07-22 2022-07-22 Power grid secondary equipment fault tracing, operation and maintenance service method and system

Country Status (1)

Country Link
CN (1) CN115271116A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115508672A (en) * 2022-11-22 2022-12-23 中国电力科学研究院有限公司 Power grid main equipment fault tracing reasoning method, system, equipment and medium
CN116955648A (en) * 2023-07-19 2023-10-27 上海企卓元科技合伙企业(有限合伙) Knowledge graph analysis method based on non-privacy data association
CN117131425A (en) * 2023-10-25 2023-11-28 广东德力宏展智能装备有限公司 Numerical control machine tool processing state monitoring method and system based on feedback data

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115508672A (en) * 2022-11-22 2022-12-23 中国电力科学研究院有限公司 Power grid main equipment fault tracing reasoning method, system, equipment and medium
CN116955648A (en) * 2023-07-19 2023-10-27 上海企卓元科技合伙企业(有限合伙) Knowledge graph analysis method based on non-privacy data association
CN116955648B (en) * 2023-07-19 2024-01-26 上海企卓元科技合伙企业(有限合伙) Knowledge graph analysis method based on non-privacy data association
CN117131425A (en) * 2023-10-25 2023-11-28 广东德力宏展智能装备有限公司 Numerical control machine tool processing state monitoring method and system based on feedback data
CN117131425B (en) * 2023-10-25 2024-02-27 广东德力宏展智能装备有限公司 Numerical control machine tool processing state monitoring method and system based on feedback data

Similar Documents

Publication Publication Date Title
US20220137612A1 (en) Transformer fault diagnosis and positioning system based on digital twin
CN115271116A (en) Power grid secondary equipment fault tracing, operation and maintenance service method and system
CA3042926A1 (en) Technology incident management platform
CN105868373B (en) Method and device for processing key data of power business information system
CN111552813A (en) Power knowledge graph construction method based on power grid full-service data
KR20210001243A (en) Online and offline information analysis service system by lifecycle according to product life cycle
CN105759784A (en) Fault diagnosis method based on data envelopment analysis
CN104750496A (en) Automatic checking method for change influence degree of model
CN108664509A (en) A kind of method, apparatus and server of extemporaneous inquiry
CN115423429A (en) Multimode integrated distribution network operation system based on image and sound information
CN112241424A (en) Air traffic control equipment application system and method based on knowledge graph
CN115564071A (en) Method and system for generating data labels of power Internet of things equipment
CN113590607A (en) Electric power marketing report realization method and system based on report factor
CN113592378A (en) BOM construction method and management system of large complex equipment
CN113435721A (en) Method for constructing secondary data center of intelligent substation
Márquez Digital maintenance manage ́ ment
Yu et al. Research on situational perception of power grid business based on user portrait
CN116308494A (en) Supply chain demand prediction method
CN115309724A (en) Data warehouse design and data analysis acceleration system for industrial analysis
CN112784129A (en) Pump station equipment operation and maintenance data supervision platform
CN115330404A (en) System and method for electric power marketing inspection
CN114862233A (en) Intelligent decision method and intelligent decision system
Tang et al. Ontology based Knowledge Modeling and Extraction of Power Equipment Supply Chain
CN113342987A (en) Composite network construction method of special corpus for power distribution DTU acceptance
Meng et al. Design and Implementation of Knowledge Graph Platform of Power Marketing

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