CN112906389A - Fault trip discrimination method based on multi-dimensional data analysis - Google Patents
Fault trip discrimination method based on multi-dimensional data analysis Download PDFInfo
- Publication number
- CN112906389A CN112906389A CN202110158829.4A CN202110158829A CN112906389A CN 112906389 A CN112906389 A CN 112906389A CN 202110158829 A CN202110158829 A CN 202110158829A CN 112906389 A CN112906389 A CN 112906389A
- Authority
- CN
- China
- Prior art keywords
- equipment
- analysis
- signal
- data
- 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.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000012850 discrimination method Methods 0.000 title description 4
- 238000012544 monitoring process Methods 0.000 claims abstract description 68
- 238000004458 analytical method Methods 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000004140 cleaning Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims description 15
- 238000012423 maintenance Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 11
- 230000011664 signaling Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 6
- 238000003058 natural language processing Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000000052 comparative effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 238000012916 structural analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to a fault trip judging method based on multi-dimensional data analysis, and belongs to the technical field of power grid regulation and control intellectualization. The method comprises the following steps: information clustering and data cleaning with equipment as a center; monitoring signal structural analysis; establishing a standard event model library; analyzing the running mode of the equipment; cross identification of multi-dimensional data; monitoring signal eventing analysis. The method can assist a regulator in quickly and accurately finding and timely processing the abnormity and the fault of the power grid, improve the analysis capability of monitoring information of the substation equipment, and improve the processing efficiency of monitoring alarm signals by the regulation center, thereby improving the monitoring management level of the power grid and being easy to popularize and apply.
Description
Technical Field
The invention belongs to the technical field of power grid regulation and control intellectualization, and particularly relates to a fault trip judging method based on multi-dimensional data analysis.
Background
The electric power is one of the main common energy sources of the contemporary society, and plays an important role in the rapid development of national economy and the daily life of people. The dependence on electric power is stronger and stronger, and simultaneously, higher requirements are put forward to the reliability and the stability of electric supply. Along with the reformation of large operation, regulation and control integration and unattended operation of a transformer substation of a power grid, the number and the day of the transformer substation are monitored and controlled by a regulation and control center in a centralized manner, the operation state of the power grid is monitored and controlled in the centralized manner by remote measurement, remote signaling, remote control, remote regulation and the like, more and more kinds of primary and secondary equipment monitoring signals of various types and numbers are uploaded to the regulation and control center in real time, the single-day uploading data volume of the monitoring signals is large, the monitoring signals are influenced by the real environment, and the content of the monitoring signals is not standard. In the face of mass signals, a regulation and control person judges mass fragment monitoring alarm data by means of manual experience or according to a rule base maintained in advance, and the problem that effective monitoring and intelligent analysis cannot be achieved exists.
Disclosure of Invention
The invention aims to solve the defects of the prior art and provides a fault trip judging method based on multi-dimensional data analysis, the method comprises the steps of intelligently fusing cross-department and cross-professional massive multi-dimensional data in a power system, and performing multiple filtering, screening, verification and evidence-making on the signal quality by using multiple data sources to realize the identification and confirmation of the signal quality such as remote measurement and remote signaling and ensure the correctness of the signal; and (3) carrying out incident modeling by combining a power grid operation mode and a primary and secondary equipment operation rule and utilizing various incident rules of power grid operation, thereby realizing classification, packaging and combination of signals and abstracting the essence and outline of an incident. The regulation and control operation personnel are liberated from complicated daily repetitive work, the treatment of special key events and abnormal conditions is concentrated, the work efficiency is greatly improved, and the work load and the work pressure are reduced. The intelligent level of the regulation and control operation is improved, and meanwhile, the systematic and complete inheritance of the regulation and control operation experience is realized.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a fault trip judging method based on multi-dimensional data analysis comprises the following steps:
step (1), information clustering and data cleaning with equipment as a center;
step (2), monitoring signal structured analysis;
step (3), establishing a standard event model library;
step (4), analyzing the running mode of the equipment;
step (5), cross identification of multi-dimensional data;
and (6) monitoring signal eventing analysis.
Further, it is preferable that the specific method of step (1) is: the method comprises the steps of utilizing a natural language analysis technology to perform word segmentation extraction on alarm information, a remote signaling point table, an overhaul application, an operation ticket and remote control operation contents, obtaining key effective information of a station, a voltage grade, an equipment type, an equipment number and an interval name, comparing the station, a switch, a disconnecting link, a bus, a transformer and primary equipment of a capacitive reactance device in a D5000 model library to obtain associated equipment information, establishing data set grouping based on different equipment, putting various data into corresponding data sets according to the associated equipment, and achieving information classifying and clustering of various data centering on the equipment.
Further, it is preferable that the specific method of the step (2) is: and performing grammar inference and syntactic analysis on each monitoring signal based on a natural language processing technology, and screening and filtering invalid contents through segmentation and reconstruction to obtain accurate monitoring signal meanings.
Further, it is preferable that the step (2) of performing structured analysis on the monitoring signal includes identifying the signal correlation device and identifying the meaning of the signal;
the signal association device is specifically identified as follows: performing word segmentation extraction on the plant station to which the equipment belongs, the voltage grade and the equipment description content by using a natural language analysis technology, and performing association processing on the equipment description and a power grid model after standardizing the equipment description so as to obtain signal association equipment;
the signal meaning identification is specifically: and performing word segmentation extraction on the signal content by utilizing a natural language analysis technology, sequencing and matching the existing standard signal library and a signal list to be matched according to the similarity under the condition that key feature points of a plant station, the voltage level and the equipment type are the same, and taking the content with the maximum similarity as the signal meaning identification content.
Further, it is preferable that the specific method of step (3) is: different evenized matching models are established according to different voltage grades, wiring modes and operation modes, the existing standard event models are preferentially matched when monitoring information is analyzed, and an evenized analysis result is given at the first time when conditions are met.
Further, preferably, in step (3), the specific establishment method of the eventing matching model is as follows: analyzing the reason for sending the monitoring signal by combining the alarm signal, the load information, the operation condition and the environmental factors; by analyzing the generation reasons of the monitoring signals, key information of actions of protecting an outlet, switch deflection and reclosing is extracted, and a standard event model library is established according to different voltage grades, wiring modes and operation modes.
Further, it is preferable that the specific method of step (4) is: identifying the current operation mode of the equipment by combining a power grid topological structure according to the on-off state of the switch, the disconnecting link and the grounding disconnecting link equipment; the operation mode comprises operation, hot standby, cold standby or overhaul.
Further, it is preferable that the specific method of step (5) is: carrying out comparative fusion analysis on the maintenance application, remote control and equipment card placing data and the monitoring signal which are subjected to data cleaning in the step (1) on the basis of equipment and by taking a time period as a caliper, and identifying whether the time period of the signal sent by the equipment is in a maintenance range, whether the signal is in remote control operation and whether relevant card placing information exists, wherein the maintenance, remote control operation and card placing relevant equipment do not participate in event analysis; and meanwhile, cross identification is carried out by using the effective measurement value of the equipment in the telemetering data and the monitoring signal, so that the extraction of the remote signaling abnormal data is realized. For example: in the monitoring signal analysis process, performing data check of active power or reactive power in remote measurement data of a switch which is opened or closed for a long time, and if the switch is closed, the remote measurement value is 0 for a long time; or the switch is in a disconnected state, but the telemetering value in the time period is normal and has no change, the data in the time period can be extracted as abnormal data, and the abnormal state of the power grid can be reflected while the auxiliary event judgment is carried out.
Further, it is preferable that the specific method of step (6) is: carrying out data cleaning on monitoring signals, overhaul applications, remote control operations, operation tickets, card placing information and telemetering data which are uploaded in real time through the step (1) to realize the set clustering taking equipment as the center; performing structured analysis on the monitoring signal through the step (2) to realize equipment and meaning identification of the monitoring signal; analyzing the operation mode of the equipment by combining the power grid topology in the step (4); through the step (5), multi-dimensional data fusion analysis and cross identification are carried out, and filtering of overhaul equipment, remote control operation equipment and brand placing equipment and information extraction of remote signaling and telemetering data which do not correspond to the equipment are realized; and (4) combining the standard event model base established in the step (3) to give a complete trip event analysis result. The trip event analysis results may be: "X minute X second (XX change) XX protection action at X month X day X year, resulting in the XX switch tripping, coincidence success (or misregistration), belonging to instantaneous fault (or permanent fault)"
In order to solve the problem that the massive monitoring information cannot be effectively identified and timely processed at present by a power grid, the invention provides an event discrimination method based on multi-dimensional data fusion analysis, and massive fragment monitoring information is collected and abstracted by taking an event as a center by using an intelligent means. The following defects of the power grid can be effectively overcome:
1. massive monitoring information cannot be effectively identified and timely processed.
2. A large amount of labor is invested, and the dependence on personal factors such as responsibility, work experience and the like of workers is stronger and stronger. Too much manual intervention not only easily causes information overlooking, and regulators are difficult to quickly and accurately identify the power grid abnormity.
3. The signal difference is large, certain difficulty is added to signal meaning identification, the judgment of a regulation and control worker on the operation state of a field power grid is seriously influenced, and great potential safety hazards are buried in power grid monitoring signal analysis work.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a fault trip judging method based on multi-dimensional data analysis, which realizes integrated clustering with equipment and events as centers by performing structured analysis and cleaning on monitoring related data such as monitoring signals, maintenance applications, operation tickets, remote measurement, remote control and the like. The method has the advantages that massive monitoring signals are abstracted into simple events, and meanwhile, the accuracy of event judgment is improved by means of cross identification among multi-dimensional data. The method helps regulators quickly and accurately find and timely process the power grid abnormity and faults, and improves the monitoring information analysis capability of the substation equipment; the processing efficiency of monitoring alarm signals by the regulation and control center is improved; and the monitoring and management level of the power grid is improved.
Drawings
FIG. 1 is a flow chart of fault trip discrimination based on multi-dimensional data analysis in the present invention;
FIG. 2 is a diagram of wiring in a station with XX in normal operation mode in an application example;
FIG. 3 is an architecture diagram of a multi-data device-centric data integration;
fig. 4 is an analysis diagram of the operation ticket associating apparatus.
Detailed Description
The present invention will be described in further detail with reference to examples.
It will be appreciated by those skilled in the art that the following examples are illustrative of the invention only and should not be taken as limiting the scope of the invention. The examples do not specify particular techniques or conditions, and are performed according to the techniques or conditions described in the literature in the art or according to the product specifications. The materials or equipment used are not indicated by manufacturers, and all are conventional products available by purchase.
Referring to fig. 1, a fault trip discrimination method based on multidimensional data analysis includes the following steps:
step (1), information clustering and data cleaning with equipment as a center;
step (2), monitoring signal structured analysis;
step (3), establishing a standard event model library;
step (4), analyzing the running mode of the equipment;
step (5), cross identification of multi-dimensional data;
and (6) monitoring signal eventing analysis.
The specific implementation method of the step (1) comprises the following steps: the method comprises the steps of performing word segmentation extraction on structured and unstructured data contents in the power system, obtaining key effective information of a station, a voltage grade, an equipment type, an equipment number and an interval name, and realizing standardized data cleaning based on natural language analysis. And completing text and data connotation recognition and automatically analyzing to the equipment. The method is characterized in that the association relation between D5000 remote measurement, remote signaling, remote control and alarm information and circuit breaker, disconnecting link, bus, transformer and capacitive reactance device is established by taking the device as a center and adopting a mode of positioning the main device at intervals. And establishing data set groups on the basis of equipment, and putting various data into corresponding data sets according to associated equipment to realize the grouping and clustering of the various data by taking the equipment as the center.
FIG. 3 is an architecture diagram of a multi-data device-centric data integration; and carrying out data cleaning on the overhaul application content, the operation ticket, the operation command and the fault of the OMS by using a Natural Language Processing (NLP) technology and then associating the data with the D5000 model equipment. Fig. 4 is an analysis diagram of the operation ticket associating apparatus; similarly, the process can associate the overhaul ticket, the fault information and the operation command to the equipment for checking the operation mode of the power grid.
In the process of data standardization cleaning, characteristic point word segmentation and compatible processing of different description modes with the same meaning are required to be carried out on information, the accuracy of equipment is improved by unifying standardization rules, and the following standardization rules are exemplified as follows:
the numbers are not consistent
And carrying out unified standardized processing on the non-standard data such as Roman numerals, English letters, Chinese characters and the like in the equipment information.
② the equipment numbering is not uniform
For equipment such as transformers and buses, numbering often has different writing methods such as '1 #, and # 1', and standardization processing is required.
The specific implementation method of the step (2) is as follows: and establishing a standard electric power corpus model according to the characteristics of the power grid equipment and the monitoring signal. Based on various equipment typical information specifications issued by power companies, a complete standard signal library is formed by combining characteristic signal management specifications of various regions. And performing word segmentation, filtering and reconstruction on the monitoring signal content by utilizing a natural language analysis technology. And effectively identifying signal-related equipment and signal meanings by combining an optimal credibility occupation theory with a power grid model and a standard signal library. Table 1 is an example of the standard signal library section data.
TABLE 1
And performing grammar inference and syntactic analysis on each monitoring signal based on a natural language processing technology, and screening and filtering invalid contents through segmentation and reconstruction to obtain accurate monitoring signal meanings.
Wherein, the structured analysis of the monitoring signal comprises the identification of signal correlation equipment and the identification of signal meaning;
the signal association device is specifically identified as follows: performing word segmentation extraction on the plant station to which the equipment belongs, the voltage grade and the equipment description content by using a natural language analysis technology, and performing association processing on the equipment description and a power grid model after standardizing the equipment description so as to obtain signal association equipment;
the signal meaning identification is specifically: and performing word segmentation extraction on the signal content by utilizing a natural language analysis technology, sequencing and matching the existing standard signal library and a signal list to be matched according to the similarity under the condition that key feature points of a plant station, the voltage level and the equipment type are the same, and taking the content with the maximum similarity as the signal meaning identification content.
The specific implementation method of the step (3) is as follows: different evenized matching models are established according to different voltage grades, wiring modes and operation modes, the existing standard event models are preferentially matched when monitoring information is analyzed, and an evenized analysis result is given at the first time when conditions are met. Table 2 is an example of a trip event section standard model:
TABLE 2
The specific implementation method of the step (4) is as follows: the current operation mode of the equipment can be effectively identified by analyzing the on-off states of the switch, the disconnecting link and the grounding disconnecting link equipment and combining a power grid topological structure; the operation mode comprises operation, hot standby, cold standby or overhaul.
The specific implementation method of the step (5) is as follows: and performing multi-dimensional data fusion analysis and cross identification, completing screening and filtering of data, and realizing correlation verification between the data.
Carrying out comparative fusion analysis on the maintenance application, remote control and equipment card placing data and the monitoring signal which are subjected to data cleaning in the step (1) on the basis of equipment and by taking a time period as a caliper, and identifying whether the time period of the signal sent by the equipment is in a maintenance range, whether the signal is in remote control operation and whether relevant card placing information exists, wherein the maintenance, remote control operation and card placing relevant equipment do not participate in event analysis; and meanwhile, cross identification is carried out by using the effective measurement value of the equipment in the telemetering data and the monitoring signal, so that the extraction of the remote signaling abnormal data is realized. For example: in the monitoring signal analysis process, performing data check of active power or reactive power in remote measurement data of a switch which is opened or closed for a long time, and if the switch is closed, the remote measurement value is 0 for a long time; or the switch is in a disconnected state, but the telemetering value in the time period is normal and has no change, the data in the time period can be extracted as abnormal data, and the abnormal state of the power grid can be reflected while the auxiliary event judgment is carried out.
The following are examples of some of the data:
1) section of state
And D5000 state sections are docked regularly, and the equipment operation mode analyzed according to the monitoring signals is checked by utilizing the equipment state in the state sections, so that errors in the equipment operation state analysis caused by false sending, missed sending and frequent sending of the monitoring signals are effectively processed.
2) Telemetry data
The D5000 telemetry ID may be mapped to the primary device model with special binary translation. And measuring value conditions in a certain time period corresponding to the equipment are obtained, suspicious data can be identified by comparing the states of the monitoring signal analysis equipment, and the event judgment accuracy is checked.
3) Maintenance application, operation ticket, operation command, remote control operation and card placing information
The operation mode of the power grid can be effectively checked by using the standard cleaning results of maintenance application, operation tickets, operation commands, remote control operation and card information data and taking time as a mark. And a powerful judgment basis is provided for a signal which accords with the rule of the trip event and a brake separating signal during operation during equipment overhaul and debugging.
The specific implementation method of the step (6) is as follows: acquiring a monitoring signal which is uploaded in real time and related maintenance application, remote control operation and card placing information;
and (3) cleaning data by using the step (1), and realizing information integration with equipment as a center on the multi-dimensional data.
And (3) carrying out structural analysis on the monitoring signal by utilizing the step (2), and effectively identifying signal associated equipment and signal meaning.
And (5) analyzing the states of the switch, the disconnecting link and the grounding switch by utilizing the step (4), and acquiring the current operation mode of the equipment by combining a power grid topological structure.
And (5) performing multi-dimensional data fusion analysis and cross identification to realize filtering of the overhaul equipment, the remote control operation equipment and the brand placing equipment and extraction of abnormal data which is not corresponding to remote signaling and remote measuring.
And (3) performing standard event model matching by using the data results analyzed in the steps (1), (2), (4) and (5) and combining the standard event model library established in the step (3), and defining a trip event analysis result: "X minute X second [ XX changes ] XX protection action at X month X day X time X year, which causes the XX switch to trip, the reclosing is successful (or the reclosing is bad), and belongs to instantaneous failure (or permanent failure)".
The trip event analysis of the monitoring signals can be completed through the steps, the discrete monitoring signals are abstracted into concrete events, meanwhile, abnormal data captured during mutual checking among the multidimensional data are collected, workers are assisted to find power grid data risks, the monitoring information analysis capability of the substation equipment is improved, and the processing efficiency of monitoring alarm signals by a regulation and control center is improved.
Examples of the applications
FIG. 2 is a wiring diagram in the station with the XX changed to the normal operation mode; the list of monitor signals is sent up as in table 3 (reply signals not shown).
TABLE 3
The following results were obtained by analysis:
1. the associated equipment:
(1) the serial number 1, 2, 4, 5, 6, 7 associated devices are: XX variable 110kVA line 1151 switch
(2) Sequence number 3 associated device: is free of
2. Signal meaning:
(1) sequence number 1 is overcurrent protection action
(2) The serial numbers 2, 5 and 7 are switch-on and switch-off position signals
(3) Number 3 is accident total signal
(4) Number 4 is reclosing exit signal
(5) Number 6 is the signal that the switch spring does not store energy
3. In conjunction with the grid topology analysis, the 1151 switch is in an active state.
4. Cross identification of the state section and the telemetering data, checking the analysis result, and keeping 1151 in the running state currently; checking and analyzing the maintenance application and the operation ticket data, wherein the equipment does not have maintenance and operation information in the current time period; and (4) card placing and remote control operation data analysis, wherein the equipment does not carry out remote control operation in the time period and has no related card hanging information.
5. After signal cleaning, meaning identification and equipment operation mode checking, an analysis result is finally obtained: and 2020-01-2510: 57:28[ XX change ]1151 switch overcurrent II section protection action, which causes the 1151 switch to trip, the outlet of the reclosing switch, the 1151 switch to close and the 1151 switch to trip again, belongs to permanent fault and the reclosing is unsuccessful (on-off).
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A fault trip judging method based on multi-dimensional data analysis is characterized by comprising the following steps:
step (1), information clustering and data cleaning with equipment as a center;
step (2), monitoring signal structured analysis;
step (3), establishing a standard event model library;
step (4), analyzing the running mode of the equipment;
step (5), cross identification of multi-dimensional data;
and (6) monitoring signal eventing analysis.
2. The method for judging fault tripping based on multi-dimensional data analysis according to claim 1, wherein the specific method of the step (1) is as follows: the method comprises the steps of utilizing a natural language analysis technology to perform word segmentation extraction on alarm information, a remote signaling point table, an overhaul application, an operation ticket and remote control operation contents, obtaining key effective information of a station, a voltage grade, an equipment type, an equipment number and an interval name, comparing the station, a switch, a disconnecting link, a bus, a transformer and primary equipment of a capacitive reactance device in a D5000 model library to obtain associated equipment information, establishing data set grouping based on different equipment, putting various data into corresponding data sets according to the associated equipment, and achieving information classifying and clustering of various data centering on the equipment.
3. The method for judging fault tripping based on multi-dimensional data analysis according to claim 1, wherein the specific method of the step (2) is as follows: and performing grammar inference and syntactic analysis on each monitoring signal based on a natural language processing technology, and screening and filtering invalid contents through segmentation and reconstruction to obtain accurate monitoring signal meanings.
4. The method for discriminating fault trip based on multi-dimensional data analysis of claim 3 wherein the step (2) of structured analysis of the monitoring signal comprises identification of signal association equipment and identification of signal meaning;
the signal association device is specifically identified as follows: performing word segmentation extraction on the plant station to which the equipment belongs, the voltage grade and the equipment description content by using a natural language analysis technology, and performing association processing on the equipment description and a power grid model after standardizing the equipment description so as to obtain signal association equipment;
the signal meaning identification is specifically: and performing word segmentation extraction on the signal content by utilizing a natural language analysis technology, sequencing and matching the existing standard signal library and a signal list to be matched according to the similarity under the condition that key feature points of a plant station, the voltage level and the equipment type are the same, and taking the content with the maximum similarity as the signal meaning identification content.
5. The method for judging fault tripping based on multi-dimensional data analysis according to claim 1, wherein the specific method of the step (3) is as follows: different evenized matching models are established according to different voltage grades, wiring modes and operation modes, the existing standard event models are preferentially matched when monitoring information is analyzed, and an evenized analysis result is given at the first time when conditions are met.
6. The method for judging fault tripping based on multi-dimensional data analysis according to claim 5, wherein in the step (3), the concrete establishment method of the eventing matching model is as follows: analyzing the reason for sending the monitoring signal by combining the alarm signal, the load information, the operation condition and the environmental factors; by analyzing the generation reasons of the monitoring signals, key information of actions of protecting an outlet, switch deflection and reclosing is extracted, and a standard event model library is established according to different voltage grades, wiring modes and operation modes.
7. The method for judging fault tripping based on multi-dimensional data analysis according to claim 1, wherein the specific method of the step (4) is as follows: identifying the current operation mode of the equipment by combining a power grid topological structure according to the on-off state of the switch, the disconnecting link and the grounding disconnecting link equipment; the operation mode comprises operation, hot standby, cold standby or overhaul.
8. The method for judging fault tripping based on multi-dimensional data analysis according to claim 1, wherein the specific method of the step (5) is as follows: carrying out comparative fusion analysis on the maintenance application, remote control and equipment card placing data and the monitoring signal which are subjected to data cleaning in the step (1) on the basis of equipment and by taking a time period as a caliper, and identifying whether the time period of the signal sent by the equipment is in a maintenance range, whether the signal is in remote control operation and whether relevant card placing information exists, wherein the maintenance, remote control operation and card placing relevant equipment do not participate in event analysis; and meanwhile, cross identification is carried out by using the effective measurement value of the equipment in the telemetering data and the monitoring signal, so that the extraction of the remote signaling abnormal data is realized.
9. The method for judging fault tripping based on multi-dimensional data analysis according to claim 1, wherein the specific method of the step (6) is as follows: carrying out data cleaning on monitoring signals, overhaul applications, remote control operations, operation tickets, card placing information and telemetering data which are uploaded in real time through the step (1) to realize the set clustering taking equipment as the center; performing structured analysis on the monitoring signal through the step (2) to realize equipment and meaning identification of the monitoring signal; analyzing the operation mode of the equipment by combining the power grid topology in the step (4); through the step (5), multi-dimensional data fusion analysis and cross identification are carried out, and filtering of overhaul equipment, remote control operation equipment and brand placing equipment and information extraction of remote signaling and telemetering data which do not correspond to the equipment are realized; and (4) combining the standard event model base established in the step (3) to give a complete trip event analysis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110158829.4A CN112906389B (en) | 2021-02-04 | 2021-02-04 | Fault trip discrimination method based on multi-dimensional data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110158829.4A CN112906389B (en) | 2021-02-04 | 2021-02-04 | Fault trip discrimination method based on multi-dimensional data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112906389A true CN112906389A (en) | 2021-06-04 |
CN112906389B CN112906389B (en) | 2022-08-26 |
Family
ID=76122584
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110158829.4A Active CN112906389B (en) | 2021-02-04 | 2021-02-04 | Fault trip discrimination method based on multi-dimensional data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112906389B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115085139A (en) * | 2022-06-15 | 2022-09-20 | 国网山东省电力公司莘县供电公司 | Power grid accident trip analysis method and system based on data processing |
CN115549315A (en) * | 2022-11-30 | 2022-12-30 | 广东电网有限责任公司中山供电局 | Method for monitoring switching-on and switching-off of reclosure controlled by microcomputer |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4447673A (en) * | 1977-12-27 | 1984-05-08 | Stromberg-Carlson Corporation | Ring trip apparatus for a line circuit connected to DCO switch |
CA2102997A1 (en) * | 1992-11-18 | 1994-05-19 | John Peterson | Intrusion Alarm with Independent Trouble Evaluation |
CN101789626A (en) * | 2010-01-05 | 2010-07-28 | 国电南瑞科技股份有限公司 | Protected object-oriented automatic modeling and real-time information joint processing method |
CN102255380A (en) * | 2011-08-02 | 2011-11-23 | 上海思源弘瑞自动化有限公司 | Intelligent self-adaptive automatic throw-in equipment and method thereof of emergency power supplies in substation |
CN102684141A (en) * | 2012-04-28 | 2012-09-19 | 中国农业大学 | Shock current identifying method and aftercurrent protecting device |
WO2018090662A1 (en) * | 2016-11-15 | 2018-05-24 | 国电南瑞科技股份有限公司 | Displacement reason recognition method and apparatus for switchgear in power grid, and storage medium |
CN108537344A (en) * | 2018-02-01 | 2018-09-14 | 贵州电网有限责任公司 | Secondary device intelligence O&M method based on closed loop information management |
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 |
CN109347202A (en) * | 2018-09-06 | 2019-02-15 | 国网浙江省电力有限公司 | The identification of monitoring device typical operation and multidimensional analysis method |
CN109740770A (en) * | 2018-12-29 | 2019-05-10 | 广州供电局有限公司 | Unit exception processing method, device, computer equipment and storage medium |
CN110046782A (en) * | 2018-12-05 | 2019-07-23 | 国网江西省电力有限公司 | A kind of automatic identifying method of power grid accident tripping monitoring information problem |
CN110954782A (en) * | 2019-12-17 | 2020-04-03 | 国网山东省电力公司济宁供电公司 | Distribution network instantaneous fault identification method and system based on density peak clustering |
CN111047464A (en) * | 2019-12-04 | 2020-04-21 | 国网湖南省电力有限公司 | Automatic short message sending method and system for fault tripping of power system |
CN111090730A (en) * | 2019-12-05 | 2020-05-01 | 中科数智(北京)科技有限公司 | Intelligent voice scheduling system and method |
CN111509839A (en) * | 2020-03-04 | 2020-08-07 | 国网浙江省电力有限公司温州供电公司 | Trip event model analysis method based on alarm signal |
CN111753528A (en) * | 2020-07-27 | 2020-10-09 | 广东电网有限责任公司 | Method and system for checking four-remote information table of transformer substation in unified and standard manner |
CN111768077A (en) * | 2020-05-28 | 2020-10-13 | 国网浙江省电力有限公司绍兴供电公司 | Intelligent power grid trip event identification method based on knowledge graph |
CN111768076A (en) * | 2020-05-28 | 2020-10-13 | 国网浙江省电力有限公司绍兴供电公司 | Monitoring alarm signal clustering method taking power grid event as center |
CN111934291A (en) * | 2020-07-21 | 2020-11-13 | 广东电网有限责任公司 | Method for judging circuit breaker tripping due to stealing and electrical tripping |
CN112307003A (en) * | 2020-11-02 | 2021-02-02 | 合肥优尔电子科技有限公司 | Power grid data multidimensional auxiliary analysis method, system, terminal and readable storage medium |
-
2021
- 2021-02-04 CN CN202110158829.4A patent/CN112906389B/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4447673A (en) * | 1977-12-27 | 1984-05-08 | Stromberg-Carlson Corporation | Ring trip apparatus for a line circuit connected to DCO switch |
CA2102997A1 (en) * | 1992-11-18 | 1994-05-19 | John Peterson | Intrusion Alarm with Independent Trouble Evaluation |
CN101789626A (en) * | 2010-01-05 | 2010-07-28 | 国电南瑞科技股份有限公司 | Protected object-oriented automatic modeling and real-time information joint processing method |
CN102255380A (en) * | 2011-08-02 | 2011-11-23 | 上海思源弘瑞自动化有限公司 | Intelligent self-adaptive automatic throw-in equipment and method thereof of emergency power supplies in substation |
CN102684141A (en) * | 2012-04-28 | 2012-09-19 | 中国农业大学 | Shock current identifying method and aftercurrent protecting device |
WO2018090662A1 (en) * | 2016-11-15 | 2018-05-24 | 国电南瑞科技股份有限公司 | Displacement reason recognition method and apparatus for switchgear in power grid, and storage medium |
CN108537344A (en) * | 2018-02-01 | 2018-09-14 | 贵州电网有限责任公司 | Secondary device intelligence O&M method based on closed loop information management |
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 |
CN109347202A (en) * | 2018-09-06 | 2019-02-15 | 国网浙江省电力有限公司 | The identification of monitoring device typical operation and multidimensional analysis method |
CN110046782A (en) * | 2018-12-05 | 2019-07-23 | 国网江西省电力有限公司 | A kind of automatic identifying method of power grid accident tripping monitoring information problem |
CN109740770A (en) * | 2018-12-29 | 2019-05-10 | 广州供电局有限公司 | Unit exception processing method, device, computer equipment and storage medium |
CN111047464A (en) * | 2019-12-04 | 2020-04-21 | 国网湖南省电力有限公司 | Automatic short message sending method and system for fault tripping of power system |
CN111090730A (en) * | 2019-12-05 | 2020-05-01 | 中科数智(北京)科技有限公司 | Intelligent voice scheduling system and method |
CN110954782A (en) * | 2019-12-17 | 2020-04-03 | 国网山东省电力公司济宁供电公司 | Distribution network instantaneous fault identification method and system based on density peak clustering |
CN111509839A (en) * | 2020-03-04 | 2020-08-07 | 国网浙江省电力有限公司温州供电公司 | Trip event model analysis method based on alarm signal |
CN111768077A (en) * | 2020-05-28 | 2020-10-13 | 国网浙江省电力有限公司绍兴供电公司 | Intelligent power grid trip event identification method based on knowledge graph |
CN111768076A (en) * | 2020-05-28 | 2020-10-13 | 国网浙江省电力有限公司绍兴供电公司 | Monitoring alarm signal clustering method taking power grid event as center |
CN111934291A (en) * | 2020-07-21 | 2020-11-13 | 广东电网有限责任公司 | Method for judging circuit breaker tripping due to stealing and electrical tripping |
CN111753528A (en) * | 2020-07-27 | 2020-10-09 | 广东电网有限责任公司 | Method and system for checking four-remote information table of transformer substation in unified and standard manner |
CN112307003A (en) * | 2020-11-02 | 2021-02-02 | 合肥优尔电子科技有限公司 | Power grid data multidimensional auxiliary analysis method, system, terminal and readable storage medium |
Non-Patent Citations (2)
Title |
---|
张家玮等: "基于事故模型的监控信号智能分析算法", 《山西电力》 * |
段翔兮等: "基于告警信息的保护跳闸识别方法研究", 《四川电力技术》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115085139A (en) * | 2022-06-15 | 2022-09-20 | 国网山东省电力公司莘县供电公司 | Power grid accident trip analysis method and system based on data processing |
CN115085139B (en) * | 2022-06-15 | 2023-02-28 | 国网山东省电力公司莘县供电公司 | Power grid accident trip analysis method and system based on data processing |
CN115549315A (en) * | 2022-11-30 | 2022-12-30 | 广东电网有限责任公司中山供电局 | Method for monitoring switching-on and switching-off of reclosure controlled by microcomputer |
CN115549315B (en) * | 2022-11-30 | 2023-03-24 | 广东电网有限责任公司中山供电局 | Method for monitoring switching-on and switching-off of reclosure controlled by microcomputer |
Also Published As
Publication number | Publication date |
---|---|
CN112906389B (en) | 2022-08-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108847968B (en) | Monitoring accident and abnormal event identification and multidimensional analysis method | |
CN111768077B (en) | Intelligent identification method for power grid tripping event based on knowledge graph | |
CN107045663B (en) | Visual online checking system and method for secondary safety measure operation ticket | |
CN104020754B (en) | Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system | |
CN109347202B (en) | Typical operation identification and multidimensional analysis method for monitoring equipment | |
CN112906389B (en) | Fault trip discrimination method based on multi-dimensional data analysis | |
CN110674282B (en) | Expert knowledge rule base-based one-key sequential control operation order intelligent simulation method | |
CN109962443B (en) | SCD-based protection, overhaul and safety measure automatic generation system and method | |
CN108988487B (en) | Power grid power failure event identification method based on multidimensional data | |
CN106357002A (en) | Intelligent signal processing system of power grid equipment | |
CN113268590A (en) | Power grid equipment running state evaluation method based on equipment portrait and integrated learning | |
CN109145166A (en) | A kind of fault data fusion method based on fault message identification | |
CN111832977A (en) | Maintenance application automatic ticketing method based on natural language parsing | |
CN110704700B (en) | One-key sequence control equipment state intelligent simulation method based on expert knowledge rule base | |
CN112270555B (en) | Distribution network dispatching instruction ticket safety checking system and method | |
CN111708817A (en) | Intelligent disposal method for transformer substation monitoring information | |
CN104657814A (en) | Extraction definition method based on EMS system for relay protection device signal template | |
CN112182303A (en) | Transformer substation safety measure ticket one-key generation method based on maintenance safety measure general rule base | |
CN111753528A (en) | Method and system for checking four-remote information table of transformer substation in unified and standard manner | |
CN114089067B (en) | Electrical secondary circuit visualization system of transformer substation | |
CN114221436B (en) | Intelligent alarm method and system based on distribution network operation management system | |
CN115587635A (en) | Transformer area line loss analysis method and system based on neutral point deviation judgment | |
CN110245846A (en) | Current break reason method of discrimination based on XGBoost algorithm | |
CN109726214A (en) | A kind of equipment fault disposition aid decision-making method and system | |
CN114626440A (en) | Monitoring signal objectification analysis method and device |
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 |