CN111768076B - Monitoring alarm signal clustering method taking power grid event as center - Google Patents
Monitoring alarm signal clustering method taking power grid event as center Download PDFInfo
- Publication number
- CN111768076B CN111768076B CN202010465852.3A CN202010465852A CN111768076B CN 111768076 B CN111768076 B CN 111768076B CN 202010465852 A CN202010465852 A CN 202010465852A CN 111768076 B CN111768076 B CN 111768076B
- Authority
- CN
- China
- Prior art keywords
- event
- power grid
- information
- signals
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000012790 confirmation Methods 0.000 claims abstract description 9
- 238000012916 structural analysis Methods 0.000 claims abstract description 8
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 230000011664 signaling Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000003032 molecular docking Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06Q10/06—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
- H02J13/00006—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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- 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
-
- 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
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
Abstract
The invention discloses a monitoring alarm signal clustering method taking a power grid event as a center, which comprises the following steps: step 1: extracting characteristic information to form a standard signal characteristic point mapping model based on a standard signal in the monitoring information specification; step 2: based on the expert experience of the power system, constructing a power grid eventing model according to logic of manually analyzing power grid events; step 3: based on the historical power grid event analysis report, the historical monitoring data and the measurement data, carrying out event model deduction and perfection; step 4: carrying out structural analysis on the monitoring alarm information and matching the monitoring alarm information with a standard signal; step 5: carrying out event analysis by combining the topology and the operation mode of the power grid, and carrying out multi-dimensional cross confirmation by combining telemetry information; step 6: based on the event analysis result, clustering the monitoring alarm signals related to the event. The invention effectively reduces the treatment confirmation time of the monitoring alarm signal, lightens the working pressure of operators and improves the monitoring management level of the power grid.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to an intelligent monitoring and analyzing technology for power grid events.
Background
With the popularization of the rapid development and regulation integrated mode of the power grid in China, the gradual integration of large operation and large maintenance systems is realized, the dispatching mechanism increases the centralized monitoring function of equipment, the production command center function of the power grid dispatching center is more outstanding, and higher requirements are also provided for the quality of the power grid monitoring related data. The quantity of the centralized monitoring substations of the regulation and control center is increased dramatically, the monitoring signals of the primary equipment and the secondary equipment are monitored in the centralized monitoring master station, the quantity of the monitoring alarm signals generated in a single day reaches ten thousand levels, and the signals are nonstandard and nonstandard due to different professional levels of maintenance personnel and different localization experience differences. In the face of massive signals, the judgment is carried out completely by means of manual experience, the problem that the alarm information cannot be effectively monitored exists, and the perception key information of the power grid event can be missed. In recent years, artificial intelligence theory and technology such as expert systems in the artificial intelligence field, natural language processing and the like are mature increasingly, and technical feasibility is provided for constructing intelligent perception power grid running states and autonomously analyzing power grid events.
Disclosure of Invention
In order to overcome the defects of the prior art, the technical problem to be solved by the invention is to provide a monitoring alarm signal clustering method taking a power grid event as a center, so that the treatment and confirmation time of the monitoring alarm signal is reduced, the working pressure of operators is lightened, and the monitoring management level of a power grid is improved.
In order to solve the technical problems, the invention adopts the following technical scheme: a monitoring alarm signal clustering method taking a power grid event as a center comprises the following steps:
step 1: extracting characteristic information to form a standard signal characteristic point mapping model based on a standard signal in the monitoring information specification;
step 2: based on the expert experience of the power system, constructing a power grid eventing model according to logic of manually analyzing power grid events;
step 3: based on the historical power grid event analysis report, the historical monitoring data and the measurement data, carrying out event model deduction and perfection;
step 4: carrying out structural analysis on the monitoring alarm information and matching the monitoring alarm information with a standard signal;
step 5: carrying out event analysis by combining the topology and the operation mode of the power grid, and carrying out multi-dimensional cross confirmation by combining telemetry information;
step 6: based on the event analysis result, clustering the monitoring alarm signals related to the event.
Preferably, the implementation method of the step 1 includes the following steps:
(1) According to standard signals in the centralized monitoring information specification, extracting different characteristic points to make a mapping table, and establishing an alarm signal matching model;
(2) And adjusting the weight of the characteristic points, and defining the priority occupation logic based on the signal confidence.
Preferably, the implementation method of the step 2 includes the following steps:
(1) Based on a scheduling rule and manual experience, analyzing the reason for sending the monitoring signal by combining the power grid operation data and various factors affecting the power grid;
(2) Analyzing the generation source of the monitoring signal, establishing an event model of various events, distinguishing different wiring modes and operation modes, and establishing a standard event model library matched with different characteristic point modes;
(3) Aiming at an overhaul debugging event, extracting deflection information in remote signaling information, analyzing an operation mode by combining with a power grid topology, identifying equipment in an overhaul window, and extracting and filtering overhaul debugging signals;
(4) Aiming at a fault tripping event, searching for switching-off information of related equipment in an effective time interval by taking tripping outlet class signals of all equipment as an analysis starting point; after confirming the effective tripping event, further searching tripping related signals, and analyzing and deducting a fault tripping process;
(5) Extracting opening and closing information of a switch, a disconnecting link and a ground knife aiming at power grid operation associated signals, identifying associated signals related to each operation by utilizing an associated signal rule base, merging operation events according to main equipment related to each operation small event, and checking information by utilizing an operation ticket and an overhaul application;
(6) And aiming at an AVC control event, combining the switching on-off operation related to the voltage regulating equipment, and integrally judging according to the power grid topology and combining remote control operation information and an AVC operation record.
Preferably, the implementation method of the step 3 includes the following steps:
(1) Carrying out big data calculation on a scene event set of each factor and result which possibly occur in a power grid by utilizing an equivalent modeling technology, and screening combinations with strong relevance and high confidence coefficient to form a knowledge base;
(2) Based on the monitoring scene model library, the standard event model library is generalized, verified and promoted, and rules and characteristic points of the power grid event under various voltage grades, wiring modes and operation modes are perfected.
Preferably, the implementation method of the step 4 includes the following steps:
(1) Carrying out structural analysis on the monitoring alarm signal, identifying the alarm signal and carrying out information stripping, wherein the stripped information comprises a factory station, a voltage grade, a main equipment name, an interval number, a sleeve and a protection model;
(2) And reserving the alarm signals after the description of the structured power grid model is removed, and acquiring standard signals corresponding to the alarm signals based on the standard signal feature point mapping model.
Preferably, the implementation method of the step 5 includes the following steps:
(1) Based on the analysis result of the monitoring alarm signal, the operation state of the associated equipment is judged by combining the operation mode analysis of the power grid topology;
(2) Carrying out state superposition of deflection information of remote signaling warning signal equipment on a history state section of periodical docking synchronization;
(3) Cross identification confirmation is carried out on the running state of the equipment by combining with telemetry information;
(4) And carrying out eventuality analysis and identification on the power grid events by using a standard event model library according to the sequence of overhaul debugging, accident tripping, operation accompaniment and AVC control events.
Preferably, the implementation method of the step 6 includes the following steps:
(1) For each power grid event, clustering event-related signals by taking key signals of the event as a clustering starting point and combining judgment standard factors in cluster analysis, wherein the judgment standard factors comprise signal occurrence time, topological relation of equipment to which the signals belong, and association degree of the signals and an initial signal;
(2) And aiming at the monitoring alarm signals clustered to a certain power grid event, the analysis or classification is not repeated, and the monitoring alarm signals are removed from the original alarm information record.
Based on expert system and natural language processing technology in the artificial intelligence field, the invention carries out structural analysis and cross identification cleaning on the monitoring related data, presents massive and disordered monitoring signals in an event form, and is more concise and organized, the display form of the event is convenient for the operation management of operators, so that the operators concentrate attention on a small amount of effective alarms of real feedback equipment problems, the treatment and confirmation time of monitoring alarm signals is effectively reduced, the working pressure of the operators is reduced, and the monitoring management level of a power grid is improved.
The specific technical scheme and the beneficial effects of the invention are described in detail in the following detailed description with reference to the accompanying drawings.
Drawings
The invention is further described with reference to the drawings and detailed description which follow:
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a method for clustering monitoring alarm signals centered on a grid event includes the following steps:
step 1: extracting characteristic information to form a standard signal characteristic point mapping model based on a standard signal in the monitoring information specification;
step 2: based on the expert experience of the power system, constructing a power grid eventing model according to logic of manually analyzing power grid events;
step 3: based on the historical power grid event analysis report, the historical monitoring data and the measurement data, carrying out event model deduction and perfection;
step 4: carrying out structural analysis on the monitoring alarm information and matching the monitoring alarm information with a standard signal;
step 5: carrying out event analysis by combining the topology and the operation mode of the power grid, and carrying out multi-dimensional cross confirmation by combining telemetry information;
step 6: based on the event analysis result, clustering the monitoring alarm signals related to the event.
The specific implementation method of the step 1 is as follows:
according to standard signals in the enterprise standard Q/GDW 11398-2015 of the national network company, the type of equipment, the number of the equipment, the voltage level, the interval type, the action of the equipment and the like are extracted as characteristic points, and the characteristic points mainly select the equipment information of the equipment which sends out the signal and the operation content corresponding to the alarm, wherein the equipment information and the operation content are necessary for understanding the definition of the signal. For the standard signal of 'switching oil pressure low switching-on and switching-off total locking', the classification equipment type is a switch or a hydraulic mechanism, and the characteristic points are oil pressure, locking, switching-on/switching-off and total locking. The subsequent matching standard signals are classified according to intervals and equipment, characteristic points are used as matching core contents, a matching rule is predefined to be made into a mapping table, and an alarm signal matching model is established, wherein the alarm signal matching model is mapped to the main transformer high-voltage side, such as the main transformer high-voltage side, the main transformer high-voltage side and the main transformer high-voltage side.
According to the signal priority preemption site with high information reliability, the actual monitoring information point table and the standard signal point table are mapped, the characteristic point weight is adjusted by combining with the experience of expert personnel, and the priority preemption logic based on the signal confidence is defined.
The specific implementation method of the step 2 is as follows:
based on scheduling rules and manual experience, the reasons for sending the monitoring signals are analyzed by combining power grid operation data such as alarm signals, load information, operation conditions, environmental factors and the like and various factors affecting the power grid.
Analyzing the generation source of the monitoring signal, establishing an event model of various events such as overhaul debugging, fault tripping, operation accompaniment and the like, distinguishing different wiring modes and operation modes, and establishing a standard event model library matched with different characteristic point modes.
Aiming at maintenance and debugging events, the deflection information in the remote signaling information is extracted, the operation mode analysis is carried out by combining the power grid topology, equipment in a maintenance window is identified, and maintenance and debugging signals are extracted and filtered.
Aiming at a fault tripping event, searching for switching-off information of related equipment in an effective time interval by taking tripping outlet class signals of all equipment as an analysis starting point; after confirming the effective tripping event, further searching signals such as reclosing outlet, interval accident total, total station accident total, closing and the like, and analyzing and deducting the fault tripping process.
Aiming at the power grid operation associated signals, an associated device, a device topology, a power grid operation mode and signal meanings of the monitoring signals are based, an associated signal rule base is established by combining action time and reset time of the signals, opening and closing information of a switch, a disconnecting link and a ground knife is extracted, the associated signal rule base is utilized to identify associated signals related to each operation, and the combination of operation events is carried out according to main devices associated with each operation small event.
For AVC control events, the switching operation related to voltage regulating equipment such as a capacitor and a reactor is combined, and the judgment is integrally carried out according to the power grid topology and the remote control operation information and the AVC operation record.
The specific implementation method of the step 3 is as follows:
and by utilizing an equivalent modeling correlation technique, historical monitoring alarm data and a historical log in a past period of time are selected for testing, such as historical data of a certain area in the past year, big data calculation is carried out on a scene event set of various factors and results which possibly occur in a power grid, event discrimination is carried out according to a predefined event model which possibly generates alarm signal combinations when the event occurs, comparison is carried out by combining the historical log, whether the discriminated events such as tripping, overhauling, AVC action and the like occur or not is determined, the reliability is calculated according to the actual occurrence rate/the total number of discrimination events, the combination with the accurate event model, strong relevance and high confidence degree is screened, the judgment basis is a knowledge base, and a standard event model base is perfected.
Based on the events such as tripping of a power grid, abnormal defects of the power grid, overhaul and debugging of the equipment, automatic voltage regulation of AVC and the like which are usually focused by equipment monitoring service, a monitoring scene model library is formed by combining service focus points, and the standard event model library is induced, verified and promoted to perfect rules and characteristic points of the power grid events under various voltage levels, wiring modes and operation modes.
The specific implementation method of the step 4 is as follows:
the monitoring alarm signal is subjected to structural analysis, information such as a station, a voltage grade, a main equipment name, an interval number, a set, a protection model and the like in the alarm signal are identified and stripped, for example, a 'XX substation 1# phase-change A body air-cooled control loop fault alarm' is carried out, certain station information and certain equipment information which are specifically sourced by the signal are removed through stripping interference information, core information of a 'body air-cooled control loop fault alarm' which represents the true interpretation of the signal is left, and the core information is irrelevant to specific body equipment and can represent the meaning of the signal.
And reserving the alarm signal after the description of the structured power grid model is removed, and acquiring a standard signal corresponding to the alarm signal, for example, the main transformer body air-cooling control loop fault corresponding to the standard signal based on the standard signal feature point mapping model.
The specific implementation method of the step 5 is as follows:
the same alarm signal has different meanings under different running states, so that based on the analysis result of the monitoring alarm signal, the running state of the related equipment (such as the isolating switches on two sides of the circuit breaker can be known according to a primary wiring diagram) is judged by combining the running mode analysis of the power grid topology, and the state superposition of the deflection information of the remote signaling alarm signal equipment is carried out on the section of the history state in the butt joint synchronization, so that the initial section needs to be synchronized regularly due to the possible problems of missed transmission and false transmission of the remote signaling.
For the equipment state in the power grid production management system, there is also possibility of error, the operation state of the equipment needs to be cross-identified and confirmed by combining the telemetry information, for example, a switch in an off state is required to be turned off, the current, the active power and the reactive power of the switch are 0, and the reliability of equipment state judgment can be greatly increased by checking the telemetry information.
And carrying out eventuality analysis and identification on the power grid event by using a standard event model library according to the sequence of overhaul debugging, accident tripping, operation accompaniment and AVC control event, removing the identified and confirmed alarm signal from an analysis table, and avoiding affecting the subsequent statistical analysis.
The specific implementation method of the step 6 is as follows:
for each power grid event, the key signals analyzed by the event are used as clustering starting points, for example, for a tripping event, a signal with a 'control loop disconnection' can be often used as a judging starting point for the occurrence of a suspected tripping event, and the event model is different for different types of events, so that the starting signals are different, the starting signals are selected according to the event model, and the comprehensive factors such as the signal occurrence time, the topological relation of equipment to which the signals belong, the association degree of the signals and the starting signals are used as judging standards in the clustering analysis, so that the clustering of the monitoring alarm signals related to the event is completed.
While the invention has been described in terms of specific embodiments, it will be appreciated by those skilled in the art that the invention is not limited to the specific embodiments described above. Any modifications which do not depart from the functional and structural principles of the present invention are intended to be included within the scope of the appended claims.
Claims (1)
1. A method for clustering monitoring alarm signals by taking a power grid event as a center is characterized by comprising the following steps: step 1: extracting characteristic information to form a standard signal characteristic point mapping model based on a standard signal in the monitoring information specification;
step 2: based on the expert experience of the power system, constructing a power grid eventing model according to logic of manually analyzing power grid events;
step 3: based on the historical power grid event analysis report, the historical monitoring data and the measurement data, carrying out event model deduction and perfection;
step 4: carrying out structural analysis on the monitoring alarm information and matching the monitoring alarm information with a standard signal;
step 5: carrying out event analysis by combining the topology and the operation mode of the power grid, and carrying out multi-dimensional cross confirmation by combining telemetry information;
step 6: clustering the monitoring alarm signals related to the event based on the event analysis result;
the implementation method of the step 1 comprises the following steps:
(1) According to standard signals in the centralized monitoring information specification, extracting different characteristic points to make a mapping table, and establishing an alarm signal matching model;
(2) Adjusting the weight of the feature points, and defining a priority occupation logic based on signal confidence;
the implementation method of the step 2 comprises the following steps:
(1) Based on a scheduling rule and manual experience, analyzing the reason for sending the monitoring signal by combining the power grid operation data and various factors affecting the power grid;
(2) Analyzing the generation source of the monitoring signal, establishing an event model of various events, distinguishing different wiring modes and operation modes, and establishing a standard event model library matched with different characteristic point modes;
(3) Aiming at an overhaul debugging event, extracting deflection information in remote signaling information, analyzing an operation mode by combining with a power grid topology, identifying equipment in an overhaul window, and extracting and filtering overhaul debugging signals;
(4) Aiming at a fault tripping event, searching for switching-off information of related equipment in an effective time interval by taking tripping outlet class signals of all equipment as an analysis starting point; after confirming the effective tripping event, further searching tripping related signals, and analyzing and deducting a fault tripping process;
(5) Extracting opening and closing information of a switch, a disconnecting link and a ground knife aiming at power grid operation associated signals, identifying associated signals related to each operation by utilizing an associated signal rule base, merging operation events according to main equipment related to each operation small event, and checking information by utilizing an operation ticket and an overhaul application;
(6) Aiming at an AVC control event, combining the switching on-off operation related to the voltage regulating equipment, and integrally judging according to the power grid topology and combining remote control operation information and an AVC operation record;
the implementation method of the step 3 comprises the following steps:
(1) Carrying out big data calculation on a scene event set of each factor and result which possibly occur in a power grid by utilizing an equivalent modeling technology, and screening combinations with strong relevance and high confidence coefficient to form a knowledge base;
(2) Based on the monitoring scene model library, the standard event model library is generalized, verified and promoted, and rules and characteristic points of the power grid event under various voltage grades, wiring modes and operation modes are perfected;
the implementation method of the step 4 comprises the following steps:
(1) Carrying out structural analysis on the monitoring alarm signal, identifying the alarm signal and carrying out information stripping, wherein the stripped information comprises a factory station, a voltage grade, a main equipment name, an interval number, a sleeve and a protection model;
(2) The alarm signals after the description of the structured power grid model are reserved and removed, and standard signals corresponding to the alarm signals are obtained based on the standard signal feature point mapping model;
the implementation method of the step 5 comprises the following steps:
(1) Based on the analysis result of the monitoring alarm signal, the operation state of the associated equipment is judged by combining the operation mode analysis of the power grid topology;
(2) Carrying out state superposition of deflection information of remote signaling warning signal equipment on a history state section of periodical docking synchronization;
(3) Cross identification confirmation is carried out on the running state of the equipment by combining with telemetry information;
(4) Carrying out event analysis and identification on the power grid events in a layering manner according to the sequence of overhaul debugging, accident tripping, operation accompaniment and AVC control events by utilizing a standard event model library;
the implementation method of the step 6 comprises the following steps:
(1) For each power grid event, clustering event-related signals by taking key signals of the event as a clustering starting point and combining judgment standard factors in cluster analysis, wherein the judgment standard factors comprise signal occurrence time, topological relation of equipment to which the signals belong, and association degree of the signals and an initial signal;
(2) And aiming at the monitoring alarm signals clustered to a certain power grid event, the analysis or classification is not repeated, and the monitoring alarm signals are removed from the original alarm information record.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010465852.3A CN111768076B (en) | 2020-05-28 | 2020-05-28 | Monitoring alarm signal clustering method taking power grid event as center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010465852.3A CN111768076B (en) | 2020-05-28 | 2020-05-28 | Monitoring alarm signal clustering method taking power grid event as center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111768076A CN111768076A (en) | 2020-10-13 |
| CN111768076B true CN111768076B (en) | 2023-12-01 |
Family
ID=72719799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010465852.3A Active CN111768076B (en) | 2020-05-28 | 2020-05-28 | Monitoring alarm signal clustering method taking power grid event as center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111768076B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580993B (en) * | 2020-12-23 | 2022-08-26 | 云南电网有限责任公司昆明供电局 | Power grid equipment fault probability analysis method |
| CN112906389B (en) * | 2021-02-04 | 2022-08-26 | 云南电网有限责任公司昆明供电局 | Fault trip discrimination method based on multi-dimensional data analysis |
| CN113065978A (en) * | 2021-03-15 | 2021-07-02 | 国网江苏省电力有限公司南通供电分公司 | Analysis method for monitoring information defect event |
| CN113097981B (en) * | 2021-03-15 | 2022-03-25 | 国网江苏省电力有限公司南通供电分公司 | Method for judging missing of monitoring alarm signal of transformer substation |
| CN113268590A (en) * | 2021-04-06 | 2021-08-17 | 云南电网有限责任公司昆明供电局 | Power grid equipment running state evaluation method based on equipment portrait and integrated learning |
| CN113743717A (en) * | 2021-07-26 | 2021-12-03 | 南方电网深圳数字电网研究院有限公司 | Reminding method, equipment and storage medium based on classification technology |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108847968A (en) * | 2018-06-04 | 2018-11-20 | 国网浙江省电力有限公司 | Monitoring accident, anomalous event identification and multidimensional analysis method |
| CN109657912A (en) * | 2018-11-15 | 2019-04-19 | 国网浙江省电力有限公司金华供电公司 | A kind of visual power grid risk management and control method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9009002B2 (en) * | 2011-05-19 | 2015-04-14 | Accenture Global Services Limited | Intelligent grid communication network management system and methods |
-
2020
- 2020-05-28 CN CN202010465852.3A patent/CN111768076B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108847968A (en) * | 2018-06-04 | 2018-11-20 | 国网浙江省电力有限公司 | Monitoring accident, anomalous event identification and multidimensional analysis method |
| CN109657912A (en) * | 2018-11-15 | 2019-04-19 | 国网浙江省电力有限公司金华供电公司 | A kind of visual power grid risk management and control method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于辅助决策专家库的设备健康水平预测研究;耿艳;崔慧军;于洋;张奇;;华北电力技术(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111768076A (en) | 2020-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111768076B (en) | Monitoring alarm signal clustering method taking power grid event as center | |
| CN102638100B (en) | District power network equipment abnormal alarm signal association analysis and diagnosis method | |
| WO2015043441A1 (en) | Smart alarm inference method based on multi-scenario analysis | |
| CN110336375B (en) | Processing method and system for power grid monitoring alarm information | |
| CN106908690A (en) | Distributed intelligence warning system and its method for diagnosing faults between boss station | |
| CN108268706B (en) | Closed loop test system and method for intelligent alarm application of integrated monitoring system | |
| CN110738330B (en) | Intelligent report generation method based on scheduling prefecture-county integrated control system | |
| CN110493031A (en) | A kind of substation control system network device state on-line monitoring method | |
| CN110867958A (en) | Automatic fault identification and alarm method for electric power system | |
| CN108876197B (en) | Power equipment cluster and group analysis system | |
| CN110954782B (en) | Distribution network instantaneous fault identification method and system based on density peak clustering | |
| CN111509839A (en) | Trip event model analysis method based on alarm signal | |
| CN116169778A (en) | Processing method and system based on power distribution network anomaly analysis | |
| CN114626440A (en) | Monitoring signal objectification analysis method and device | |
| CN115378127A (en) | Fault depth diagnosis method based on multi-dimensional data real-time analysis of power grid equipment | |
| CN106022950B (en) | Power distribution network secondary equipment type identification method and system | |
| CN111444164B (en) | Method for establishing substation equipment monitoring information base based on equipment monitoring information standard | |
| CN114693186A (en) | Method and system for analyzing and processing multiple fault events of differentiated combined type transformer substation | |
| CN113570474A (en) | Monitoring system for power grid event response | |
| CN106709158B (en) | Performance improvement method of power grid feeder automation system | |
| CN113097981B (en) | Method for judging missing of monitoring alarm signal of transformer substation | |
| CN112564033B (en) | Circuit breaker protection device abnormity identification method and system based on main and auxiliary data fusion | |
| CN115907014A (en) | Fault reasoning method based on composite characteristic points of power grid equipment | |
| CN112671106B (en) | Control method and system for secondary equipment based on graph theory | |
| CN116578577A (en) | Method for realizing active safety of accident handling through event application |
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 |