CN113420162B - Equipment operation chain state monitoring method based on knowledge graph - Google Patents
Equipment operation chain state monitoring method based on knowledge graph Download PDFInfo
- Publication number
- CN113420162B CN113420162B CN202110705816.4A CN202110705816A CN113420162B CN 113420162 B CN113420162 B CN 113420162B CN 202110705816 A CN202110705816 A CN 202110705816A CN 113420162 B CN113420162 B CN 113420162B
- Authority
- CN
- China
- Prior art keywords
- equipment
- state
- information
- target
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 34
- 238000000605 extraction Methods 0.000 claims description 39
- 230000007547 defect Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 14
- 230000003068 static effect Effects 0.000 claims description 8
- 230000036541 health Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011158 quantitative evaluation Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 238000012502 risk assessment Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000008649 adaptation response Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a knowledge graph-based equipment operation chain state monitoring method, which comprises the following specific working steps of: collecting device information directly and indirectly associated with a target device in an electrical grid; data preprocessing and evaluation are carried out on the collected equipment information; constructing an operation state knowledge graph of the target equipment according to the preprocessing and evaluation results; further establishing a state running chain of the target equipment, comprehensively analyzing the state running chain of the target equipment, determining the weight of the data index and obtaining a state evaluation result of the state running chain of the equipment; ranking the attention degrees of a plurality of target devices in the device state operation chain according to the evaluation result of the device operation chain state, and actively recommending device information according to the ranking of the attention degrees; according to the invention, a dynamically updated knowledge map library is established in the power system, so that a real-time target equipment operation chain is established, and the requirements of a user for timely acquiring the equipment operation state trend and guiding the user to regulate and control to carry out real-time auxiliary decision making are met.
Description
Technical Field
The invention belongs to the field of monitoring of power system operation scheduling equipment, and particularly relates to an equipment operation chain state monitoring method based on a knowledge graph.
Background
With the comprehensive implementation of the gradual promotion of power grid intellectualization and the integration of regulation and control, the characteristics of multiple sources, high dimension, prior and isomerism of large electric power data are increasingly prominent, the decision and operation pressure of regulation and control operators is gradually increased, and the real-time state detection of the power grid regulation and control is extremely urgent.
The traditional equipment running state monitoring mainly depends on static information such as manual maintenance equipment management parameters and the like, multi-source service data such as power grid equipment running information, external environment information, video monitoring information, micro-terrain information, power transmission and transformation on-line monitoring information, equipment three-dimensional model information and the like are not fully fused, and completeness coverage of data sources cannot be achieved. And the evaluation of the running state of the equipment is mainly based on regular evaluation, and the requirements of timely acquiring the running state trend of the equipment and guiding regulation and control to carry out real-time auxiliary decision making cannot be met, so that the decision making of the power grid regulation and control mostly depends on a disposal plan and an expected fault set which are made offline by manual experience, and the existing auxiliary decision making system is lack of adaptive response capability.
Disclosure of Invention
The invention aims to: aiming at multi-source data such as maintenance, operation, defects, operation, measurement, topology and the like, the method establishes a dynamically updated knowledge map library and constructs a real-time mapping target equipment operation chain, meets the requirements of timely acquiring equipment operation state trends and guiding regulation and control to carry out real-time auxiliary decision making, and accordingly promotes priority scheduling among equipment in a power grid and processing of accuracy and availability of target equipment data.
The technical scheme is as follows: the method for monitoring the equipment operation chain state based on the knowledge graph comprises the following steps:
collecting device information associated with target devices by taking the target devices to be monitored as a center;
constructing a knowledge graph of the running state of the target equipment according to the equipment information;
constructing an equipment operation chain based on the knowledge graph, monitoring the operation state of target equipment, and comprehensively analyzing the equipment operation chain to obtain a state evaluation result of the target equipment and the equipment operation chain;
ordering attention degrees of the target equipment and the equipment operation chain according to the evaluation result, and pushing equipment and the equipment operation chain which need to be focused according to the attention degrees;
the equipment operation chain refers to equipment which takes target equipment as a center and has direct and indirect relation with the equipment, and comprises operation topology of the equipment, secondary devices (such as measurement and protection devices) and equipment which influences the operation state of the target equipment according to experience judgment of field workers.
In a further embodiment, the device information comprises:
static parameters: the static parameter is not changed after self-recording and is used as a reference quantity for judging the equipment state index;
dynamic parameters: the method comprises the steps of synchronously updating monitoring parameters reflecting the health state and risk of equipment during running;
quasi-dynamic parameters: including periodically updated overhaul, defect and fault parameters;
external parameters: including meteorological parameters, environmental parameters, and economic parameters.
In a further embodiment, a method for building a knowledge-graph of the operational status of a target device from device information includes:
extracting knowledge of entities, attributes and relationships from the equipment information;
and carrying out reasoning and constructing a knowledge graph through a data mining algorithm according to the knowledge extraction result.
In a further embodiment, prior to the extraction of knowledge of device information entities, attributes and relationships, the textual data and non-textual data of the device information are processed as follows:
arranging the non-text data in the equipment information to form text data;
and processing the missing value, the abnormal value, the repeated value and the dirty data of the text data in the equipment information and the text data formed after the arrangement according to the non-text data to standardize the text data.
In a further embodiment, the method of knowledge extraction comprises:
carrying out knowledge extraction on equipment information with different sources and different structures to form structured data;
through recognition, understanding, screening and formatting, all knowledge points in the structured data are extracted and stored, so that semantic annotation of the existing unstructured information is realized.
In further embodiments, the knowledge extraction includes an entity extraction, a relationship extraction, and an event extraction;
the entity extraction includes detection and classification of entities;
the relation extraction is four-tuple extraction, and further is used for extracting various relations among entities and/or between the entities and attributes in a time axis mode, namely semantic relations among associated entities and/or between the entities and the attributes are obtained in real time; the basic units of the knowledge graph are as follows: an "entity-relationship-entity" and/or an "entity-relationship-attribute" triple; according to the invention, a time axis attribute is added on the basis of the triple group to form a quadruple group, the progressive sequence of the time axis is used as the dimension of extraction and update, and real-time dynamic update is carried out on each state data of the equipment in the power grid.
In a further embodiment, the event extraction is extraction of a multi-element relation, and the unstructured text data containing the event information is presented in the form of structured text data; in a further embodiment, the method for building a knowledge graph of the operating state of the target device further comprises: and introducing updated equipment information periodically, comparing the equipment information with the stored equipment information, and updating the knowledge graph according to the comparison result.
In a further embodiment, the equipment information which is periodically imported and updated comprises data information of a D5000 system, a regulation cloud system, an OMS system and the station and equipment change conditions which are obtained by comparison.
In a further embodiment, the plant operation chain is created by mapping according to the grid topology relation stored in the target plant operation state knowledge graph. In a further embodiment, the state evaluation result is obtained by measuring the fluctuation of indexes by using an entropy method and analyzing the overhaul and defect conditions of an equipment operation chain for three months by combining a knowledge graph, so that the qualitative and quantitative evaluation of the equipment state is realized, and the attention degree is increased according to the overhaul and defect times;
when the fluctuation of the index is measured by using an entropy method, the larger the value is, the larger the dispersion of the index is, and the larger the corresponding weight is;
firstly, acquiring original data of equipment state indexes to form an original data matrix with m groups of data and n evaluation indexes, carrying out column-based normalization processing on the matrix, and solving the proportion of each item to the same type of indexes, wherein the calculation formula is as follows:
wherein x is ij A value representing the jth index in the ith set of sample samples;
further, an entropy k of a j index is calculated j The formula is as follows:
wherein p =1/ln (m) is constant, y ij Denotes x ij For the specific gravity of the similar indexes, the weight formula for calculating the jth index is as follows:
all index weights of the equipment can be obtained through formulas (1), (2) and (3), and an evaluation result is determined by combining the current equipment operation chain state and the weights.
In a further embodiment, pushing the devices and device operation chains with important attention comprises the following steps:
and (3) comprehensively evaluating the result and the attention degree of the target equipment in the operation chain, and automatically pushing the target equipment needing important attention and the operation chain of the target equipment for the user by combining the specialty, the post and the responsibility of the user, and pushing the state evaluation result and the defect repairing times of the operation chain for the assistant decision of a dispatcher.
Has the beneficial effects that: compared with the prior art, the invention has the following advantages:
(1) According to the method, a dynamically updated knowledge map library is established and a real-time mapping target equipment operation chain is established according to multi-source data such as overhaul, operation, defects, operation, measurement, topology and the like, so that the requirements of timely acquiring equipment operation state trends and guiding regulation and control to carry out real-time auxiliary decision making are met, and therefore priority scheduling among equipment in a power grid and processing on the accuracy and the availability of target equipment data are improved.
(2) The method has the advantages that the equipment state change is displayed by using a visualization technology, the equipment states and the mutual relation among the equipment states are excavated, analyzed, constructed and drawn, the real-time monitoring of the operation states of the target equipment is realized by constructing the state monitoring of the operation chain of the target equipment based on the knowledge graph, the more comprehensive system display and analysis of the power grid operation equipment are facilitated, powerful basis is provided for the equipment health state evaluation, risk assessment and fault research and judgment and early warning of a dispatcher, and the potential operation risk of key equipment, namely the target equipment is reduced.
(3) For the running states of faults, defects, alarms and the like of target equipment stored at regular time, samples of the target equipment in power grid dispatching are added, effective support is provided for state risk assessment and fault analysis of the target equipment, training of an artificial intelligence model is supported, and the requirement for monitoring the running state of the equipment is met.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a schematic flow chart of an embodiment of the method of the present invention.
Fig. 3 is a flowchart of a work flow of constructing a knowledge graph according to an operation chain state of a target device in a power grid.
Detailed Description
In order to more fully understand the technical content of the present invention, the technical solution of the present invention will be further described and illustrated with reference to the following specific embodiments, but not limited thereto.
The method for monitoring the chain state of the equipment based on the knowledge graph is further explained by combining with the figure 1:
collecting equipment information directly and indirectly associated with target equipment to be monitored in a power grid by taking the target equipment as a center, and performing data preprocessing and quality evaluation;
constructing a knowledge graph of the running state of the target equipment according to the equipment information;
constructing an equipment operation chain based on the knowledge graph, monitoring the operation state of the target equipment and comprehensively analyzing the equipment operation chain to obtain the state evaluation results of the target equipment and the equipment operation chain;
ordering attention degrees of the target equipment and the equipment operation chain according to the evaluation result, and pushing equipment and the equipment operation chain which need to be focused according to the attention degrees;
the equipment operation chain refers to equipment which takes target equipment as a center and has direct and indirect relation with the equipment, and comprises operation topology of the equipment, secondary devices (such as measurement and protection devices) and equipment which influences the operation state of the target equipment according to experience judgment of field workers.
The method provided by the invention has the advantages that the equipment operation chain is constructed by utilizing the knowledge map technology, the state of the equipment operation chain is monitored, the more comprehensive system display and analysis of the power grid operation equipment are facilitated, and a powerful basis is provided for the equipment health state evaluation, the risk evaluation and the fault study and judgment and early warning of a dispatcher.
The multivariate multidimensional data source is a basic condition for carrying out equipment state monitoring analysis; the equipment information comprises various data, records and the like suitable for equipment health state and risk assessment in the whole life cycle range of the equipment, and all data can be divided into four major parameters according to the updating frequency and the data source. The specific device information classification includes: static parameters, dynamic parameters, quasi-dynamic parameters and external parameters;
the static parameters include: the method comprises the steps of (1) machine account parameters of target equipment and test parameters before the target equipment is put into operation; the static parameters are not changed after being recorded, and are used as reference values and judgment bases for evaluating certain state parameters, and are used as initial values, limiting threshold values and the like.
The dynamic parameters include: running recorded data, inspection recorded parameters, live detection parameters and online monitoring parameters; all the dynamic parameters are periodically acquired according to the running state of the target equipment and then updated; the dynamic parameter data updating period is short, the timeliness is good, the most main and key equipment state evaluation data source is provided, and the health state and the risk of the equipment can be reflected most timely.
The quasi-dynamic parameters include: examining and repairing test parameters, defects and fault parameters; the quasi-dynamic parameters are usually acquired and updated periodically or aperiodically, and the period is usually in the unit of months; compared with dynamic parameters, the time efficiency of the dynamic parameters is relatively poor, but the dynamic parameters play a key role in the accuracy of equipment state evaluation; the quasi-dynamic parameter is particularly important when a multi-dimensional device state evaluation method is adopted to analyze potential specific defects/faults of the device.
The external parameters include: meteorological factors, environmental factors, and socioeconomic factors; the meteorological factors mainly comprise temperature, wind power, precipitation and the like; the environmental factors mainly include: earthquakes, floods, and the like; the socioeconomic factors mainly include: electricity consumption, economic situation, etc.
The state evaluation result of the further target equipment operation chain is characterized in that the qualitative and quantitative evaluation of the equipment state is realized by measuring the index fluctuation by using an entropy method and analyzing the overhaul and defect conditions of the equipment operation chain for three months by combining a knowledge graph, and the attention degree is increased according to the overhaul and defect times;
when the fluctuation of the index is measured by using an entropy method, the larger the value is, the larger the dispersion of the index is, and the larger the corresponding weight is;
firstly, acquiring original data of equipment state indexes to form an original data matrix with m groups of data and n evaluation indexes, carrying out column-based normalization processing on the matrix, and solving the proportion of each item to the same type of indexes, wherein the calculation formula is as follows:
wherein x is ij A value representing the jth index in the ith set of sample samples;
further, an entropy k of a j index is calculated j The formula is as follows:
wherein p =1/ln (m) is constant, y ij Denotes x ij For the specific gravity of the similar indexes, the weight formula for calculating the jth index is as follows:
all index weights of the equipment can be obtained through formulas (1), (2) and (3), and an evaluation result is determined by combining the current equipment operation chain state and the weights.
Pushing the equipment and the equipment operation chain needing important attention comprises the following steps:
and (3) comprehensively evaluating the result and the attention degree of the target equipment in the operation chain, and automatically pushing the target equipment needing important attention and the operation chain of the target equipment for the user by combining the specialty, the post and the responsibility of the user, and pushing the state evaluation result and the defect repairing times of the operation chain for the assistant decision of a dispatcher.
An embodiment of a method for monitoring the chain state of equipment operation based on a knowledge graph is described with reference to fig. 2, which comprises the following working steps:
collecting equipment information associated with target equipment by taking the target equipment to be monitored as a center;
preprocessing and evaluating the collected equipment information; key data information of system influence equipment operation such as EMS, OMS, big data monitoring, incident monitoring, cloud regulation and control, power grid topology, fault recording and the like is combed;
the method comprises the steps of constructing an operation state knowledge graph of target equipment for collected equipment information after multi-dimensional research by carrying out data processing, knowledge extraction, knowledge fusion and knowledge updating on the collected equipment data information;
in this embodiment, taking a transformer as an example, the key data information affecting the operation of the transformer includes:
taking a transformer as a center, combing the topological structure relationship of the equipment in the power grid, and storing the data of the transformer equipment information after data preprocessing and the topological structure relationship of the equipment in the power grid into an operation state knowledge graph of the transformer; creating a state operating chain for mapping the target equipment of the equipment based on the operating state knowledge graph of the equipment;
comprehensively analyzing an operation chain taking the transformer as a center, determining equipment information index weight and obtaining a state evaluation result of the operation chain of the transformer or equipment associated with the transformer;
and sequencing the attention degrees of a plurality of associated devices in the state operation chain with the transformer as the center according to the obtained evaluation result of the state of the operation chain, and actively recommending the device information according to the sequencing of the attention degrees.
In the present invention, the state operation chain of the target device is created and mapped according to a power grid topological relation stored in an operation state knowledge graph of the target device, for example, the target device in the present invention may include: the target device body, the target device accessory, a switch connected with the target device, a knife switch, a protection device, a signal channel and other related devices.
A method for constructing a knowledge graph of the operation state of the target device according to the device information is described with reference to fig. 3:
processing text data and non-text data of the data pair equipment information before entity extraction and relation extraction; the method comprises the following steps of (1) realizing the inspection and verification of text data and non-text data in the power grid;
arranging the non-text data in the equipment information to form text data;
processing the missing value, the abnormal value, the repeated value and the dirty data of the text data in the equipment information and the text data formed after the arrangement according to the non-text data to standardize the text data;
the non-textual data is equipment troubleshooting, equipment defects, and reports, tables, and pictures generated during operation of the equipment.
And finally, data processing such as redundant data cleaning, abnormal data processing and the like is realized, and the period and time for constructing data marks are reduced.
The knowledge extraction specifically comprises the steps of carrying out entity extraction, relation extraction and event extraction on data subjected to data preprocessing;
the entity extraction includes detection and classification of entities;
the relation extraction is four-tuple extraction, and further extracts various relations among the entities in a time axis mode, namely semantic relations among the associated entities and/or semantic relations among the entities and the attributes are obtained in real time; the basic units of the knowledge graph are as follows: an "entity-relationship-entity" and/or an "entity-relationship-attribute" triple; according to the invention, a time axis attribute is added on the basis of the triple to form a quadruple, the progressive sequence of the time axis is taken as the dimension of extraction and update, and the dynamic update is carried out on each state data of the equipment in the power grid in real time.
The event extraction is the extraction of a multivariate relation, and the unstructured text data containing event information is presented in the form of structured text data;
the knowledge extraction specifically comprises the following steps:
carrying out knowledge extraction on equipment information with different sources and different structures to form structured data;
extracting each knowledge point in the structured data for storage through identification, understanding, screening and formatting to realize semantic annotation of the existing unstructured information and further complete knowledge fusion;
the knowledge fusion in the invention means that the events such as defects, maintenance and the like are taken as storage targets, multi-source knowledge is fused, a knowledge system is constructed, and a knowledge graph of the running state of target equipment is constructed.
According to the method, a dynamically updated knowledge map library is established and a real-time mapping target equipment operation chain is established according to multi-source data such as overhaul, operation, defects, operation, measurement, topology and the like, so that the requirements of timely acquiring equipment operation state trends and guiding regulation and control to carry out real-time auxiliary decision making are met, and therefore priority scheduling among equipment in a power grid and processing on the accuracy and the availability of target equipment data are improved.
Secondly, the change of the equipment state is displayed by using a visualization technology, the equipment state and the mutual relation of the equipment state are mined, analyzed, constructed and drawn, the real-time monitoring of the operation state of the target equipment is realized by constructing the state monitoring of the operation chain of the target equipment based on the knowledge graph, the more comprehensive system display and analysis of the power grid operation equipment are facilitated, powerful basis is provided for the equipment health state evaluation, risk evaluation and fault research and judgment and early warning of a dispatcher, and the potential operation risk of key equipment, namely the target equipment is reduced.
Finally, for the running states of faults, defects, alarms and the like of the target equipment stored at regular time, samples of the target equipment in power grid dispatching are added, effective support is provided for state risk assessment and fault analysis of the target equipment, training of an artificial intelligence model is supported, and the requirement for monitoring the running state of the equipment is met.
The present invention has been described above by way of illustration in the drawings, and it will be understood by those skilled in the art that the present disclosure is not limited to the embodiments described above, and various changes, modifications and substitutions may be made without departing from the scope of the present invention.
Claims (9)
1. A method for monitoring the running state of power grid dispatching equipment is characterized by comprising the following steps:
collecting device information associated with target devices by taking the target devices to be monitored as a center;
constructing a knowledge graph of the running state of the target equipment according to the equipment information;
constructing an equipment operation chain based on the knowledge graph, monitoring the operation state of target equipment, and comprehensively analyzing the equipment operation chain to obtain a state evaluation result of the target equipment and the equipment operation chain;
ordering attention degrees of the target equipment and the equipment operation chain according to the evaluation result, and pushing equipment and the equipment operation chain which need to be focused according to the attention degrees;
the equipment operation chain is equipment which takes target equipment as a center and has direct and indirect relation with the equipment, and comprises operation topology of the equipment, a secondary device and equipment which influences the operation state of the target equipment;
the state evaluation result is used for measuring index fluctuation by using an entropy method and analyzing the overhaul and defect conditions of the equipment operation chain for three months by combining a knowledge graph, so that the qualitative and quantitative evaluation of the equipment state is realized, and the attention degree is increased according to the overhaul and defect times;
the method for determining the state evaluation result comprises the following steps:
acquiring original data of equipment state indexes to form an original data matrix with m groups of data and n evaluation indexes, carrying out column-based normalization processing on the matrix, and solving the proportion of each item to the similar indexes, wherein the calculation formula is as follows:
wherein the content of the first and second substances,x ij is shown asiGroup of sample samplesjThe numerical value of the item index;
calculate the firstjEntropy of each indexk j The formula is as follows:
wherein p =1/ln (m) is constant,y ij to representx ij For the specific gravity of the same kind index, the first one is calculatedjThe weight of each index is publicThe formula is as follows:
and (3) solving all index weights of the equipment through formulas (1), (2) and (3), and determining an evaluation result by combining the current equipment operation chain state and the weight.
2. The method for monitoring the operation state of the power grid dispatching equipment according to claim 1, wherein the equipment information comprises:
static parameters: the static parameter is not changed after self-recording and is used as a reference quantity for judging the equipment state index;
dynamic parameters: the method comprises the steps of synchronously updating monitoring parameters reflecting the health state and risk of equipment during running;
quasi-dynamic parameters: including periodically updated overhaul, defect and fault parameters;
external parameters: including meteorological parameters, environmental parameters, and economic parameters.
3. The method for monitoring the running state of the power grid dispatching equipment as claimed in claim 1, wherein the method for constructing the knowledge graph of the running state of the target equipment according to the equipment information comprises the following steps:
extracting knowledge of entities, attributes and relationships from the equipment information;
and carrying out reasoning and constructing a knowledge graph through a data mining algorithm according to the knowledge extraction result.
4. The method for monitoring the operating state of the power grid dispatching equipment as claimed in claim 3, wherein before the knowledge of the equipment information entities, attributes and relationships is extracted, the following processing is performed on the text data and the non-text data of the equipment information:
arranging the non-text data in the equipment information to form text data;
and processing the text data in the equipment information and the text data formed after the arrangement according to the non-text data by using a missing value, an abnormal value, a repeated value and dirty data so as to standardize the text data.
5. The method for monitoring the operation state of the power grid dispatching equipment according to claim 3, wherein the knowledge extraction method comprises the following steps:
carrying out knowledge extraction on equipment information with different sources and different structures to form structured data;
through recognition, understanding, screening and formatting, all knowledge points in the structured data are extracted and stored, so that semantic annotation of the existing unstructured information is realized.
6. The method for monitoring the operation state of the power grid dispatching equipment as claimed in claim 5, wherein the knowledge extraction comprises entity extraction, relation extraction and event extraction;
the entity extraction includes detection and classification of entities;
the relation extraction is to acquire semantic relations among the associated entities and/or between the entities and the attributes in real time;
the event extraction is to present the unstructured text data containing the event information in the form of structured text data.
7. The method for monitoring the operation state of the power grid dispatching equipment as claimed in claim 3, wherein the method further comprises:
and introducing updated equipment information periodically, comparing the equipment information with the stored equipment information, and updating the knowledge graph according to the comparison result.
8. The method for monitoring the running state of the power grid scheduling device according to claim 7, wherein the periodically imported updated device information includes D5000, regulation cloud, and OMS system data information, and plant station and device change conditions obtained by comparison.
9. The method for monitoring the operation state of the power grid dispatching equipment according to any one of claims 1 to 8, wherein the equipment operation chain is formed by creating and mapping according to the topological relation of the power grid stored in the operation state knowledge graph of the target equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705816.4A CN113420162B (en) | 2021-06-24 | 2021-06-24 | Equipment operation chain state monitoring method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705816.4A CN113420162B (en) | 2021-06-24 | 2021-06-24 | Equipment operation chain state monitoring method based on knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113420162A CN113420162A (en) | 2021-09-21 |
| CN113420162B true CN113420162B (en) | 2023-04-18 |
Family
ID=77717674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110705816.4A Active CN113420162B (en) | 2021-06-24 | 2021-06-24 | Equipment operation chain state monitoring method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113420162B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947320B (en) * | 2021-10-25 | 2024-05-28 | 国网天津市电力公司电力科学研究院 | Multi-mode reinforcement learning-based power grid regulation and control method |
| CN116207739B (en) * | 2023-05-04 | 2023-09-15 | 南方电网数字电网研究院有限公司 | Optimal scheduling method and device for power distribution network, computer equipment and storage medium |
| CN117197281B (en) * | 2023-11-08 | 2024-02-23 | 国网浙江省电力有限公司 | Asset data full life chain dynamic portrait construction method based on business scene |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859409A (en) * | 2010-05-25 | 2010-10-13 | 广西电网公司电力科学研究院 | Power transmission and transformation equipment state overhauling system based on risk evaluation |
| WO2020147349A1 (en) * | 2019-01-14 | 2020-07-23 | 中国电力科学研究院有限公司 | Power distribution network operation aided decision-making analysis system and method |
| CN112269901A (en) * | 2020-09-14 | 2021-01-26 | 合肥中科类脑智能技术有限公司 | Fault distinguishing and reasoning method based on knowledge graph |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840270A (en) * | 2018-12-23 | 2019-06-04 | 国网浙江省电力有限公司 | A kind of grid equipment approaches to IM based on Neo4j |
| CN112491636B (en) * | 2019-09-11 | 2023-04-18 | 华为技术有限公司 | Data processing method and device and computer storage medium |
| CN111191851B (en) * | 2020-01-03 | 2023-06-23 | 中国科学院信息工程研究所 | Knowledge graph-based data center energy efficiency optimization method |
| CN112596495B (en) * | 2020-12-07 | 2022-03-25 | 中科蓝智(武汉)科技有限公司 | Industrial equipment fault diagnosis method and system based on knowledge graph |
| CN112541600A (en) * | 2020-12-07 | 2021-03-23 | 上海电科智能系统股份有限公司 | Knowledge graph-based auxiliary maintenance decision method |
| CN112800212B (en) * | 2021-01-14 | 2022-06-03 | 国网山东省电力公司枣庄供电公司 | Power distribution station health assessment method based on knowledge graph and FAHP |
| CN112836972A (en) * | 2021-02-05 | 2021-05-25 | 南方电网调峰调频发电有限公司信息通信分公司 | IT equipment fault defect processing system and fault defect processing method |
-
2021
- 2021-06-24 CN CN202110705816.4A patent/CN113420162B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859409A (en) * | 2010-05-25 | 2010-10-13 | 广西电网公司电力科学研究院 | Power transmission and transformation equipment state overhauling system based on risk evaluation |
| WO2020147349A1 (en) * | 2019-01-14 | 2020-07-23 | 中国电力科学研究院有限公司 | Power distribution network operation aided decision-making analysis system and method |
| CN112269901A (en) * | 2020-09-14 | 2021-01-26 | 合肥中科类脑智能技术有限公司 | Fault distinguishing and reasoning method based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113420162A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113420162B (en) | Equipment operation chain state monitoring method based on knowledge graph | |
| CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
| CN108564254B (en) | Power distribution equipment state visualization platform based on big data | |
| CN108320040B (en) | Acquisition terminal fault prediction method and system based on Bayesian network optimization algorithm | |
| CN106600447B (en) | Big data cloud analysis method for transformer substation inspection robot centralized monitoring system | |
| CN110009208B (en) | Method and device for evaluating health state of pole-mounted switch complete equipment based on hybrid intelligent algorithm | |
| CN107069960B (en) | Online defect diagnosis method for secondary operation and maintenance management system | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| Bhuiyan et al. | Big data analysis of the electric power PMU data from smart grid | |
| CN116742799A (en) | Auxiliary power distribution monitoring and early warning system based on Internet of things technology | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN111582338A (en) | Method and system for evaluating running state of electric vehicle charging facility | |
| CN113902241A (en) | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation | |
| CN116432123A (en) | Electric energy meter fault early warning method based on CART decision tree algorithm | |
| CN110728381A (en) | Intelligent power plant inspection method and system based on RFID and data processing | |
| CN107862459B (en) | Metering equipment state evaluation method and system based on big data | |
| CN117390944A (en) | Substation operation condition simulation system | |
| CN117574624A (en) | Transformer state monitoring and early warning method based on digital twin technology | |
| CN116433218A (en) | Self-organizing mapping clustering-based mine mechanical equipment online health assessment method | |
| Liangzhi et al. | Research on fault prediction and diagnosis of power equipment based on big data | |
| Zhang et al. | Research on intelligent operation and maintenance technology of primary equipment in substation | |
| CN116300661B (en) | On-site data acquisition system based on Internet of things | |
| CN116910681B (en) | Electric power data analysis method and system based on Internet of things | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN117197770B (en) | Inspection complete flow data supervision system and method based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |