CN113269281A - Image-based scheduling master station three-remote change identification method and system - Google Patents

Image-based scheduling master station three-remote change identification method and system Download PDF

Info

Publication number
CN113269281A
CN113269281A CN202110822079.6A CN202110822079A CN113269281A CN 113269281 A CN113269281 A CN 113269281A CN 202110822079 A CN202110822079 A CN 202110822079A CN 113269281 A CN113269281 A CN 113269281A
Authority
CN
China
Prior art keywords
scheduling
master station
remote
scheduling master
cluster
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110822079.6A
Other languages
Chinese (zh)
Inventor
钟志明
汪杰
段孟雍
李波
郭志军
吴钟飞
李祺威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Original Assignee
Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd filed Critical Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority to CN202110822079.6A priority Critical patent/CN113269281A/en
Publication of CN113269281A publication Critical patent/CN113269281A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • 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
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—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 monitoring
    • 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
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
    • 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
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00036—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers
    • 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
    • Y04S10/40—Display of information, e.g. of data or controls

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Artificial Intelligence (AREA)
  • Water Supply & Treatment (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Public Health (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Human Computer Interaction (AREA)
  • Evolutionary Biology (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a method and a system for identifying three remote changes of a scheduling master station based on images, which comprises the following steps: s1, collecting an SVG operation graph of a background picture of the scheduling system in real time, and performing external similarity analysis and linkage on the SVG operation graph according to a time sequence to obtain a scheduling master station three-remote change key data chain containing the scheduling master station three-remote change characteristics; and step S2, extracting the target of the scheduling master station based on the three-remote-change key data chain of the scheduling master station, and clustering and dividing the scheduling master station into a plurality of groups of scheduling clusters according to the same scheduling attribute. According to the invention, an image similarity recognition technology is utilized to quickly acquire the SVG operation graph only containing the three-remote change characteristics of the scheduling master station from the SVG operation graph of the real-time acquired background picture of the scheduling system to form the three-remote change key data chain of the scheduling master station, so that useless SVG operation graphs can be effectively removed, redundant calculation is reduced, and the recognition efficiency is improved.

Description

Image-based scheduling master station three-remote change identification method and system
Technical Field
The invention relates to the technical field of mechanical scheduling, in particular to a method and a system for identifying three remote changes of a scheduling master station based on images.
Background
In the comprehensive automation transformation project of the transformer substation, the three remotes of the transformer substation need to be checked and accepted, in one example, the three remotes comprise remote signaling, remote measurement and remote control of the transformer substation, and the transformer substation can be put into use only if the three remotes are checked and accepted.
The remote signaling is a remote signal, and is a state quantity of primary equipment, the position division and the position combination of the primary equipment are transmitted to a monitoring background, once the actual position changes, the remote signaling is displayed on a primary graph of the monitoring background, or when the primary equipment is divided, the remote signaling of the monitoring background is prompted, specifically, the state quantity of the primary equipment comprises a switch state, a disconnecting link state, a dispatching master station tap signal, a primary equipment alarm signal, a protection trip signal, a forecast signal, various equipment signals (such as an SF6 low-air-pressure alarm signal and an oil-pressure low-oil-pressure alarm signal) and the like; remote measurement refers to remote measurement, which is collected operation parameters of the transformer substation, including various electrical quantities (voltage, current, power and other quantities on a line), load flow and the like; remote control refers to remote control, and refers to remote control commands received and executed by equipment in a substation, mainly including opening and closing operations, and remote control of remote switch control equipment.
The conventional method is to adopt a mode of manually selecting and making a table, but the traditional three-remote inspection acceptance efficiency is low in the implementation process.
Disclosure of Invention
The invention aims to provide a method and a system for identifying three-remote change of a scheduling main station based on an image, and the method and the system are used for solving the technical problem of low three-remote efficiency acceptance in the prior art.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
an image-based scheduling master station three-remote change identification method comprises the following steps:
s1, collecting an SVG operation graph of a background picture of the scheduling system in real time, and performing external similarity analysis and linkage on the SVG operation graph according to a time sequence to obtain a scheduling master station three-remote change key data chain 6 containing the scheduling master station three-remote change characteristics;
step S2, extracting the target of the scheduling master station based on the key data chain 6 of the three remote changes of the scheduling master station, and clustering and dividing the scheduling master station into a plurality of groups of scheduling clusters according to the same scheduling attribute;
and step S3, carrying out internal similarity analysis on each scheduling cluster to judge the three-remote-change running state of the scheduling master station contained in the scheduling cluster.
As a preferred embodiment of the present invention, in step S1, the specific method for scheduling the construction of the key data chain 6 for the master station three-remote change includes:
s101, performing pixel binarization on all SVG operation graphs in a time sequence to convert the SVG operation graphs into SVG operation binarization graphs 4, and performing external similarity analysis on the SVG operation binarization graphs 4 in adjacent time sequences;
and S102, only preserving the SVG operation diagrams which embody the three-remote change characteristics of the scheduling main station in all the SVG operation diagrams in the time sequence according to the external similarity analysis result in the step S101, and linking the SVG operation diagrams as the three-remote change key data chain 6 of the scheduling main station according to the time sequence.
As a preferable aspect of the present invention, in step S101, the specific method of the external similarity analysis includes:
and sequentially calculating the external similarity of the SVG operation binary image 4 of the adjacent time sequence to form an external similarity data chain 5, wherein the calculation formula of the external similarity is as follows:
Figure DEST_PATH_IMAGE001
wherein I is an external similarity value, X is a binarization graph 4 of all SVG operations,
Figure DEST_PATH_IMAGE002
，
Figure DEST_PATH_IMAGE003
is as followsi，i+Figure 4 is binarized for 1 SVG operation,
Figure DEST_PATH_IMAGE004
is that
Figure 438610DEST_PATH_IMAGE002
And
Figure 293434DEST_PATH_IMAGE003
is combined with the probability distribution function of
Figure DEST_PATH_IMAGE005
And
Figure DEST_PATH_IMAGE006
are respectively
Figure 10854DEST_PATH_IMAGE002
And
Figure DEST_PATH_IMAGE007
the edge probability distribution function of (1);
selecting all jumping nodes on the external similarity data chain 5, and selecting SVG operation binary images 4 at two ends of all jumping nodes to be summarized and linked according to time sequence to form a scheduling master station three-remote change key data chain 6;
the jump node is a data node of which the numerical value difference of adjacent nodes on the external similarity data chain 5 exceeds a similarity threshold.
As a preferred embodiment of the present invention, in step S2, the extracting the target of the scheduling master station based on the key data chain 6 for the change of the scheduling master station includes:
sequentially extracting all target pixel blocks in the SVG operation binary image 4 contained in a scheduling master station three-remote change key data chain 6;
and comparing the target pixel block with the scheduling master station pixel block, and determining that the scheduling master station corresponding to the target pixel block obtains all the scheduling master stations in the SVG operation binary image 4 contained in the scheduling master station three-remote change key data chain 6.
As a preferable scheme of the present invention, the step S2 further includes acquiring parameter data of the scheduling master station, so as to perform cluster aggregation and division on all scheduling master stations in the SVG operation binarization diagram 4 included in the scheduling master station three-remote-change key data chain 6 according to a same scheduling attribute to multiple groups of scheduling clusters.
As a preferred embodiment of the present invention, in step S2, the specific method for cluster aggregation and division of the scheduling master station into multiple groups of scheduling clusters according to the same scheduling attribute includes:
the method comprises the following steps: quantizing all scheduling master stations into a single scheduling cluster respectively based on the parameter data
Figure DEST_PATH_IMAGE008
Wherein
Figure DEST_PATH_IMAGE009
A set of parameter data representing the y-th scheduling master station,
Figure DEST_PATH_IMAGE010
indicating the y-th scheduling master station
Figure DEST_PATH_IMAGE011
The data of the parameters are stored in a memory,
Figure DEST_PATH_IMAGE012
，
Figure DEST_PATH_IMAGE013
m is the total category number of the parameter data, and n is the total number of the scheduling master stations;
step two: sequentially calculating the consistency of the two scheduling clusters, and performing cluster fusion and normalization based on the maximum consistency, wherein the consistency of the scheduling clusters is the consistency between a pair of scheduling master stations with the maximum consistency in the two scheduling clusters, and the consistency is measured by a levator coefficient:
Figure DEST_PATH_IMAGE014
；
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE015
for scheduling master stations
Figure DEST_PATH_IMAGE016
And a scheduling master station
Figure DEST_PATH_IMAGE017
The coefficient of the bearing capacity of the fruit,
Figure DEST_PATH_IMAGE018
for scheduling master stations
Figure 156796DEST_PATH_IMAGE016
And a scheduling master station
Figure 971168DEST_PATH_IMAGE017
In that
Figure DEST_PATH_IMAGE019
And
Figure DEST_PATH_IMAGE020
the value of (a) is selected from,
Figure 731314DEST_PATH_IMAGE019
and
Figure 936030DEST_PATH_IMAGE020
respectively represent the y1、y2Station dispatching master station
Figure DEST_PATH_IMAGE021
The data of the parameters are stored in a memory,
Figure DEST_PATH_IMAGE022
in order to weight the variables, the weight of the variables,
Figure DEST_PATH_IMAGE023
，
Figure DEST_PATH_IMAGE024
m is the total category number of the parameter data, and n is the total number of the scheduling master stations;
step three: and repeating the second step until the total number of the current scheduling clusters is 10% of the total number of the initial scheduling clusters to complete clustering, and taking the current scheduling clusters as a result of cluster aggregation division of the scheduling master station according to the scheduling attributes.
As a preferable aspect of the present invention, in step S3, the method for determining the three-remote-change operation state of the scheduling master station includes:
collecting three-remote operation data of the scheduling master station, and monitoring data of all scheduling master stations in each scheduling cluster on line
Figure DEST_PATH_IMAGE025
Respectively carrying out normalization processing to eliminate differences brought by different index dimensions, wherein the normalization formula is as follows:
Figure DEST_PATH_IMAGE026
；
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE027
is shown as
Figure DEST_PATH_IMAGE028
The station schedules the on-line monitoring data of the master station,
Figure DEST_PATH_IMAGE029
indicating the y-th scheduling master station
Figure DEST_PATH_IMAGE030
Class online monitoring data, n2 represents the number of scheduling masters in the cluster,
Figure DEST_PATH_IMAGE031
the second station of the y scheduling master station after normalization processing
Figure 885663DEST_PATH_IMAGE030
Class on-line monitoring data, p is the total number of the types of the on-line monitoring data,
Figure DEST_PATH_IMAGE032
；
quantifying the distance between every two scheduling master stations in the same cluster, wherein the distance is measured by Euclidean distance, and the calculation formula of the Euclidean distance is as follows:
Figure DEST_PATH_IMAGE033
；
Figure DEST_PATH_IMAGE034
for scheduling master stations
Figure 492224DEST_PATH_IMAGE016
And a scheduling master station
Figure 423271DEST_PATH_IMAGE017
The Euclidean distance of (a) is,
Figure DEST_PATH_IMAGE035
、
Figure DEST_PATH_IMAGE036
are respectively denoted as the y1、y2Station dispatching master station
Figure 177601DEST_PATH_IMAGE030
The data is monitored on-line in a similar way,
Figure DEST_PATH_IMAGE037
n2 denotes the total number of scheduling masters in the cluster,
Figure DEST_PATH_IMAGE038
p is the total number of the types of the online monitoring data;
and setting a distance threshold value, and judging the running condition of the scheduling master station in the cluster based on the distance threshold value.
As a preferred aspect of the present invention, the method for determining the operating condition of the scheduling master station in the scheduling cluster based on the distance threshold includes:
and if the number of the scheduling master stations in each scheduling cluster, which are more than the distance threshold value from the scheduling master station y, exceeds 80% of the total number n2 of the cluster scheduling master stations. And determining that the scheduling running condition of the scheduling master station y is abnormal, otherwise determining that the scheduling running condition of the scheduling master station y is normal.
As a preferred aspect of the present invention, the present invention provides an identification system according to the method for automatically identifying three remote changes of a scheduling master station based on an image identification technology, comprising:
the data acquisition unit is used for acquiring an SVG operation graph of a background picture of the scheduling system in real time, and performing external similarity analysis and linkage on the SVG operation graph according to a time sequence to obtain a scheduling master station three-remote change key data chain containing the scheduling master station three-remote change characteristics;
the cluster clustering unit is used for extracting targets of the scheduling master station based on the three remote change key data chains of the scheduling master station, and clustering and dividing the scheduling master station into a plurality of groups of scheduling clusters according to the same scheduling attribute;
and the three-remote judging unit is used for carrying out internal similarity analysis on each scheduling cluster to judge the three-remote changing running state of the scheduling master station contained in the scheduling cluster.
As a preferable scheme of the present invention, the three-remote determination unit is further integrated with an alarm device for giving an alarm when it is determined that the scheduling operation state of the scheduling master station is abnormal.
Compared with the prior art, the invention has the following beneficial effects:
the invention utilizes the image similarity recognition technology, can quickly acquire the SVG operation graph only containing the three-remote change characteristics of the dispatching master station from the SVG operation graph of the background picture of the dispatching system collected in real time, and form a key data chain of the three-remote change of the dispatching master station, thereby effectively removing useless SVG operation graphs and achieving the effects of reducing redundant calculation and improving the recognition efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flowchart of a method for identifying three remote changes of a scheduling master station according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a key data chain structure for scheduling three remote changes of a master station according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a scheduling cluster structure according to an embodiment of the present invention;
fig. 4 is a block diagram of an identification system according to an embodiment of the present invention.
The reference numerals in the drawings denote the following, respectively:
1-a data acquisition unit; 2-cluster clustering unit; 3-three remote discriminating unit; 4-SVG operation binarization graph; 5-outer similarity data chain; 6-scheduling the main station to change the key data chain, and 7-scheduling the main station.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1-4, the three-remote change feature of the scheduling master station usually includes an SVG operation diagram for monitoring the background picture of the scheduling system in real time, so that the SVG operation diagram for monitoring the background picture of the scheduling system in real time is required, what really has analytical value in the SVG operation chart of the background picture of the scheduling system is an image with three remote changing operations of the scheduling main station, if a large amount of redundant calculation is caused by analyzing all SVG operation graphs of the background picture of the real-time monitoring and scheduling system, the efficiency of identifying the three-remote change of the scheduling master station by using the image identification technology is reduced, therefore, the invention provides an image-based method for identifying the three-remote change of the dispatching master station, which can quickly extract the SVG operation graph with the three-remote change operation of the dispatching master station, avoid redundant calculation, meanwhile, the scheduling cluster is used for internal similarity analysis, and the scheduling master station 7 with abnormal change of the three remote locations is rapidly identified.
The embodiment of the invention provides an image-based scheduling master station three-remote change identification method, which comprises the following steps:
s1, collecting an SVG operation graph of a background picture of the scheduling system in real time, and performing external similarity analysis and linkage on the SVG operation graph according to a time sequence to obtain a scheduling master station three-remote change key data chain 6 containing the scheduling master station three-remote change characteristics;
SVG: is an image file format, its english language is called Scalable Vector Graphics, meaning Scalable Vector Graphics. It is realized based on XML (extensible Markup language) and is a standard open vector graphics language, which can be opened and read by any word processing tool.
As shown in fig. 2, in step S1, the specific method for scheduling the construction of the key data chain 6 for the change of the master station includes:
s101, performing pixel binarization on all SVG operation graphs in a time sequence to convert the SVG operation graphs into SVG operation binarization graphs 4, and performing external similarity analysis on the SVG operation binarization graphs 4 in adjacent time sequences;
and S102, only preserving the SVG operation diagrams which embody the three-remote change characteristics of the scheduling main station in all the SVG operation diagrams in the time sequence according to the external similarity analysis result in the step S101, and linking the SVG operation diagrams as the three-remote change key data chain 6 of the scheduling main station according to the time sequence.
In step S101, the specific method of the external similarity analysis includes:
and sequentially calculating the external similarity of the SVG operation binary image 4 of the adjacent time sequence to form an external similarity data chain 5, wherein the calculation formula of the external similarity is as follows:
Figure 852296DEST_PATH_IMAGE001
wherein I is an external similarity value, X is a binarization graph 4 of all SVG operations,
Figure 313364DEST_PATH_IMAGE002
，
Figure 743208DEST_PATH_IMAGE003
is as followsi，i+Figure 4 is binarized for 1 SVG operation,
Figure 984834DEST_PATH_IMAGE004
is that
Figure DEST_PATH_IMAGE039
And
Figure 197640DEST_PATH_IMAGE003
is combined with the probability distribution function of
Figure 841111DEST_PATH_IMAGE005
And
Figure 176278DEST_PATH_IMAGE006
are respectively
Figure 905199DEST_PATH_IMAGE002
And
Figure 921697DEST_PATH_IMAGE003
the edge probability distribution function of (1);
selecting all jumping nodes on the external similarity data chain 5, and selecting SVG operation binary images 4 at two ends of all jumping nodes to be summarized and linked according to time sequence to form a scheduling master station three-remote change key data chain 6;
the jump node is a data node of which the numerical value difference of adjacent nodes on the external similarity data chain 5 exceeds a similarity threshold.
The external similarity represents the similarity between the SVG operation binary images 4 in adjacent time sequences, the higher the numerical value is, the higher the similarity is, namely, the two adjacent SVG operation binary images 4 can be used for reducing the dimension to any one SVG operation binary image 4 for representation, therefore, the similarity between the adjacent SVG operation binary images 4 forms an external similarity data chain 5, the adjacent SVG operation binary images 4 corresponding to all data nodes on a gentle curve in the external similarity data chain 5 have consistent similarity, a certain SVG operation binary image 4 corresponding to all data nodes on the gentle curve can be randomly selected for representing the dimension reduction of the SVG operation binary image 4 which is changed by one change, the adjacent SVG operation binary images 4 corresponding to a jump node on the external similarity data chain 5 have inconsistent similarity, namely, the scheduling operation condition of the adjacent SVG operation binary image 4 changes violently, and the key feature of three changes is embodied, therefore, the adjacent SVG operation binary image 4 is reserved as a key SVG operation binary image 4, all key SVG operation binary images 4 are linked to form a scheduling main station three-remote-change key data chain 6, the scheduling main station three-remote-change key characteristics can be obtained through analysis, the SVG operation binary image 4 containing the scheduling main station three-remote-change key characteristics is reserved, the SVG operation binary image 4 where non-key characteristics are located is removed, and redundant calculation in subsequent steps is reduced.
Step S2, extracting the target of the scheduling master station 7 based on the key data chain 6 of the three remote changes of the scheduling master station, and clustering and dividing the scheduling master station 7 into a plurality of groups of scheduling clusters according to the same scheduling attribute;
in step S2, the extracting the target of the scheduling master station 7 based on the key data chain 6 for the three-remote change of the scheduling master station includes:
sequentially extracting all target pixel blocks in the SVG operation binary image 4 contained in a scheduling master station three-remote change key data chain 6;
and comparing the target pixel block with the scheduling master station pixel block and determining that the scheduling master station 7 corresponding to the target pixel block obtains all the scheduling master stations 7 in the SVG operation binary image 4 contained in the scheduling master station three-remote change key data chain 6.
The step S2 further includes acquiring parameter data of the scheduling master station 7, so as to perform cluster aggregation and division on all scheduling master stations 7 in the SVG operation binarization diagram 4 included in the scheduling master station three-remote-change key data chain 6 according to the same scheduling attribute to multiple groups of scheduling clusters.
In step S2, the specific method for cluster aggregation and division of the scheduling master station 7 into multiple groups of scheduling clusters according to the same scheduling attribute includes:
the parameter data include the standing book data of dispatch main website 7, and operating mode data adopts the KVM mode to snatch, KVM: is an abbreviation of Keyboard Video Mouse, and can access and control a computer by directly connecting a Keyboard, a Video and Mouse (KVM) port, and the technology directly transmits image and sound data through an HDMI interface. Plays an important role in remote scheduling monitoring. The KVM technology can send various data information in the scheduling information network to the remote terminal, provides convenience for the next-level scheduling mechanism, and realizes information sharing.
The method comprises the following steps: quantizing all scheduling master stations 7 into a single scheduling cluster respectively based on the parameter data
Figure 419674DEST_PATH_IMAGE008
Wherein
Figure 191321DEST_PATH_IMAGE009
A set of parameter data representing the y-th scheduling master station 7,
Figure 79643DEST_PATH_IMAGE010
indicating the y-th scheduling master station 7
Figure 962148DEST_PATH_IMAGE011
The data of the parameters are stored in a memory,
Figure 314632DEST_PATH_IMAGE012
，
Figure 257180DEST_PATH_IMAGE013
m is the total number of categories of parameter data, and n is the total number of the scheduling master station 7;
step two: the consistency of the two scheduling clusters is calculated in sequence, cluster fusion normalization is carried out on the basis of the maximum consistency, the consistency of the scheduling clusters is the consistency between a pair of scheduling master stations 7 with the maximum consistency in the two scheduling clusters, and the consistency is measured by a levator coefficient:
Figure 632798DEST_PATH_IMAGE014
；
wherein the content of the first and second substances,
Figure 53415DEST_PATH_IMAGE015
for scheduling master stations
Figure 525985DEST_PATH_IMAGE016
And a scheduling master station
Figure 577117DEST_PATH_IMAGE017
The coefficient of the bearing capacity of the fruit,
Figure 502348DEST_PATH_IMAGE018
for scheduling master stations
Figure 726656DEST_PATH_IMAGE016
And a scheduling master station
Figure 788153DEST_PATH_IMAGE017
In that
Figure 10187DEST_PATH_IMAGE019
And
Figure 422714DEST_PATH_IMAGE020
the value of (a) is selected from,
Figure 450712DEST_PATH_IMAGE019
and
Figure 569978DEST_PATH_IMAGE020
respectively represent the y1、y2The second of the station dispatching master station 7
Figure 697334DEST_PATH_IMAGE021
The data of the parameters are stored in a memory,
Figure 597157DEST_PATH_IMAGE022
in order to weight the variables, the weight of the variables,
Figure 163268DEST_PATH_IMAGE023
，
Figure 464936DEST_PATH_IMAGE024
m is the total number of categories of parameter data, and n is the total number of the scheduling master station 7;
step three: and repeating the second step until the total number of the current scheduling clusters is 10% of the total number of the initial scheduling clusters to complete clustering, and taking the current scheduling clusters as the result of cluster aggregation division of the scheduling master station 7 according to the scheduling attributes.
As shown in fig. 3, the scheduling cluster includes five clusters, for example, all scheduling master stations 7 in the cluster 1 have similar ledger parameters and similar condition data, all scheduling master stations 7 in the cluster 2 have similar ledger parameters and similar condition data, and the difference between the ledger parameters and the condition data of the scheduling master stations 7 between the clusters 1 and 2 is large, so that internal similarity comparison can be performed on online operation data of each scheduling master station 7 in the cluster 1, and the operation state of the scheduling master station 7 can be determined.
And step S3, carrying out internal similarity analysis on each scheduling cluster to judge the three-remote-change running state of the scheduling master station 7 contained in the scheduling cluster.
In step S3, the method for determining the three-remote-change operating state of the scheduling master station 7 includes:
collecting three-remote operation data of the scheduling master station 7, and monitoring the data of all the scheduling master stations in each scheduling cluster on line
Figure DEST_PATH_IMAGE040
Respectively carrying out normalization processing to eliminate differences brought by different index dimensions, wherein the normalization formula is as follows:
Figure 763193DEST_PATH_IMAGE026
；
wherein the content of the first and second substances,
Figure 150312DEST_PATH_IMAGE027
is shown as
Figure 457797DEST_PATH_IMAGE028
The station schedules the on-line monitoring data of the master station 7,
Figure 348392DEST_PATH_IMAGE029
indicating the y-th scheduling master station 7
Figure 145447DEST_PATH_IMAGE030
Class online monitoring data, n2 denotes the number of scheduling master stations 7 in the cluster,
Figure 754283DEST_PATH_IMAGE031
the second station 7 represents the y-th scheduling master station after normalization processing
Figure 927775DEST_PATH_IMAGE030
Class on-line monitoring data, p is the total number of the types of the on-line monitoring data,
Figure 876140DEST_PATH_IMAGE032
；
quantifying the distance between every two scheduling master stations 7 in the same cluster, wherein the distance is measured by Euclidean distance, and the calculation formula of the Euclidean distance is as follows:
Figure 844096DEST_PATH_IMAGE033
；
Figure 940228DEST_PATH_IMAGE034
for scheduling master stations
Figure 589515DEST_PATH_IMAGE016
And a scheduling master station
Figure 454703DEST_PATH_IMAGE017
The Euclidean distance of (a) is,
Figure DEST_PATH_IMAGE041
、
Figure 593560DEST_PATH_IMAGE036
are respectively denoted as the y1、y2Station dispatching master station
Figure DEST_PATH_IMAGE042
The data is monitored on-line in a similar way,
Figure DEST_PATH_IMAGE043
n2 denotes the total number of scheduling masters 7 in the cluster,
Figure DEST_PATH_IMAGE044
p is the total number of the types of the online monitoring data;
and setting a distance threshold value, and judging the running condition of the scheduling master station 7 in the cluster based on the distance threshold value.
The method for judging the operating condition of the scheduling master station 7 in the scheduling cluster based on the distance threshold value comprises the following steps:
and if the number of the scheduling master stations in each scheduling cluster, which are more than the distance threshold value from the scheduling master station y, exceeds 80% of the total number n2 of the cluster scheduling master stations. And determining that the scheduling running condition of the scheduling master station y is abnormal, otherwise determining that the scheduling running condition of the scheduling master station y is normal.
The dispatching master station abnormity detection method based on cluster management of the invention takes the dispatching master stations 7 in the same cluster as a reference, judges the states of the dispatching master stations 7 through mutual comparison, can identify the abnormity of the dispatching master stations 7 at the early stage of the fault occurrence of the dispatching master stations 7, and has great significance for ensuring the safe and stable operation of the dispatching master stations 7.
The scheduling master station anomaly detection method based on cluster management introduces the concept of cluster management into the scheduling master station anomaly detection, and combines similar scheduling master stations 7 together to form each scheduling master station cluster, thereby being beneficial to the long-term supervision of the scheduling master stations 7.
As shown in fig. 4, based on the automatic identification method for three remote changes of the scheduling master station, the invention provides an identification system, which includes:
the data acquisition unit 1 is used for acquiring an SVG operation graph of a background picture of the scheduling system in real time, and performing external similarity analysis and linkage on the SVG operation graph according to a time sequence to obtain a scheduling master station three-remote change key data chain 6 containing the scheduling master station three-remote change characteristics;
the cluster clustering unit 2 is used for extracting targets of the scheduling master station 7 based on the three-remote-change key data chain 6 of the scheduling master station, and clustering and dividing the scheduling master station 7 into a plurality of groups of scheduling clusters according to the scheduling attribute;
and the three-remote judging unit 3 is used for carrying out internal similarity analysis on each scheduling cluster to judge the three-remote changing running state of the scheduling main station 7 contained in the scheduling cluster.
The three-remote judging unit is also integrated with an alarm device for giving an alarm when the dispatching operation state of the dispatching master station 7 is judged to be abnormal.
The invention can rapidly acquire the SVG operation picture only containing the three-remote change characteristic of the dispatching master station from the SVG operation picture of the real-time acquired background picture of the dispatching system by utilizing the image similarity recognition technology to form a three-remote change key data link 6 of the dispatching master station, can effectively remove useless SVG operation graphs, reduce redundant calculation, improve recognition efficiency, and adopt a hierarchical clustering algorithm to divide the scheduling master station 7 with similar ledger parameters and working condition data into the same scheduling cluster, based on the fact that the dispatching master stations 7 of each dispatching cluster are in similar states, the differences of the devices in the clusters are identified through internal similarity analysis of the monitoring data of the states of the dispatching master stations 7 in the same dispatching cluster, which dispatching master station 7 is in an abnormal state can be rapidly judged, and the anomaly identification accuracy is high, the automatic identification of the three-remote change of the dispatching master station is finally realized, and the identification efficiency and the accuracy are high.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.

Claims (10)

1. An image-based scheduling main station three-remote change identification method is characterized by comprising the following steps:
s1, collecting an SVG operation graph of a background picture of the scheduling system in real time, carrying out external similarity analysis and linkage on the SVG operation graph according to a time sequence, and obtaining a scheduling master station three-remote change key data chain containing a scheduling master station three-remote change characteristic;
step S2, extracting the target of the scheduling master station based on the three-remote-change key data chain of the scheduling master station, and clustering and dividing the scheduling master station into a plurality of groups of scheduling clusters according to the same scheduling attribute;
and step S3, carrying out internal similarity analysis on each scheduling cluster to judge the three-remote-change running state of the scheduling master station contained in the scheduling cluster.
2. The method of claim 1, wherein the step S1 includes:
s101, performing pixel binarization on all SVG operation graphs in a time sequence to convert the SVG operation graphs into SVG operation binarization graphs, and performing external similarity analysis on the SVG operation binarization graphs in adjacent time sequences;
and S102, according to the external similarity analysis result of the step S101, only the SVG operation graphs which embody the three-remote change characteristics of the scheduling main station are reserved in all the SVG operation graphs in the time sequence, and the SVG operation graphs are linked into a three-remote change key data chain of the scheduling main station according to the time sequence.
3. The method for identifying three remote changes of the image-based scheduling master station according to claim 2, wherein in the step S101, the performing external similarity analysis on the SVG operation binary image of the adjacent time sequence comprises:
sequentially calculating the external similarity of the SVG operation binary images of adjacent time sequences based on a calculation formula of the external similarity, and forming an external similarity data chain;
selecting all jumping nodes on the external similarity data chain, selecting SVG operation binary graphs at two ends of all jumping nodes for summarizing, and linking according to time sequence to form a key data chain for scheduling the main station to change remotely; the jumping node is a data node with the numerical value difference of adjacent nodes on the external similarity data chain exceeding a similarity threshold;
the calculation formula of the external similarity is as follows:
Figure 15881DEST_PATH_IMAGE001
wherein I is an external similarity value, X is a binary image of all SVG operations,
Figure 933021DEST_PATH_IMAGE002
，
Figure 712758DEST_PATH_IMAGE003
operating a binary image for the ith, i +1 SVG,
Figure 107968DEST_PATH_IMAGE004
is that
Figure 860023DEST_PATH_IMAGE005
And
Figure 682485DEST_PATH_IMAGE006
is combined with the probability distribution function of
Figure 949519DEST_PATH_IMAGE007
And
Figure 148419DEST_PATH_IMAGE008
are respectively
Figure 754981DEST_PATH_IMAGE005
And
Figure 748345DEST_PATH_IMAGE006
the edge probability distribution function of (1).
4. The method according to claim 3, wherein in step S2, the extracting the target of the scheduling master station based on the key data chain for the three-remote change of the scheduling master station includes:
sequentially extracting target pixel blocks in all the SVG operation binary images contained in the key data chain of the three-remote change of the scheduling master station;
and comparing the target pixel blocks with the pixel blocks of the scheduling master station, determining the scheduling master station corresponding to the target pixel blocks, and acquiring all the scheduling master stations in all the SVG operation binary graphs contained in the three-remote change key data chain of the scheduling master station.
5. The method of claim 4, wherein the step S2 further comprises:
and acquiring parameter data of the scheduling master station, so that all the scheduling master stations in all the SVG operation binary graphs contained in the three-remote change key data chain of the scheduling master station are clustered and divided into a plurality of groups of scheduling clusters according to the same scheduling attribute.
6. The method of claim 5, wherein in step S2, the dividing cluster aggregation of the scheduling master station into multiple groups of scheduling clusters according to the same scheduling attribute comprises:
the method comprises the following steps: quantizing all scheduling master stations into a single scheduling cluster respectively based on the parameter data
Figure 502674DEST_PATH_IMAGE009
Wherein
Figure 177369DEST_PATH_IMAGE010
A set of parameter data representing the y-th scheduling master station,
Figure 700754DEST_PATH_IMAGE011
indicating the y-th scheduling master station
Figure 130598DEST_PATH_IMAGE012
The data of the parameters are stored in a memory,
Figure 309907DEST_PATH_IMAGE013
，
Figure 585031DEST_PATH_IMAGE014
m is the total category number of the parameter data, and n is the total number of the scheduling master stations;
step two: sequentially calculating the consistency of the two scheduling clusters, and performing cluster fusion and normalization based on the maximum consistency, wherein the consistency of the scheduling clusters is the consistency between a pair of scheduling master stations with the maximum consistency in the two scheduling clusters, and the consistency is measured by a levator coefficient:
Figure 228501DEST_PATH_IMAGE015
；
wherein the content of the first and second substances,
Figure 563668DEST_PATH_IMAGE016
for scheduling master stations
Figure 230273DEST_PATH_IMAGE017
And a scheduling master station
Figure 309087DEST_PATH_IMAGE018
The coefficient of the bearing capacity of the fruit,
Figure 807064DEST_PATH_IMAGE019
for scheduling master stations
Figure 516394DEST_PATH_IMAGE017
And a scheduling master station
Figure 467033DEST_PATH_IMAGE018
In that
Figure 287221DEST_PATH_IMAGE020
And
Figure 639705DEST_PATH_IMAGE021
the value of (a) is selected from,
Figure 582254DEST_PATH_IMAGE020
and
Figure 20188DEST_PATH_IMAGE021
respectively represent the y1、y2Station dispatching master station
Figure 378488DEST_PATH_IMAGE022
The data of the parameters are stored in a memory,
Figure 851058DEST_PATH_IMAGE023
in order to weight the variables, the weight of the variables,
Figure 964507DEST_PATH_IMAGE024
，
Figure 827421DEST_PATH_IMAGE025
m is the total category number of the parameter data, and n is the total number of the scheduling master stations;
step three: and repeating the second step until the total number of the current scheduling clusters is 10% of the total number of the initial scheduling clusters to complete clustering, and taking the current scheduling clusters as the result of cluster aggregation division of the scheduling master station according to the scheduling attributes.
7. The method as claimed in claim 6, wherein in step S3, the method for determining the three-remote operation status of the dispatch master station includes:
collecting three-remote operation data of the scheduling master station, and monitoring data of all scheduling master stations in each scheduling cluster on line
Figure 51729DEST_PATH_IMAGE026
Respectively carrying out normalization processing to eliminate differences brought by different index dimensions;
the normalization formula is:
Figure 113226DEST_PATH_IMAGE027
；
wherein the content of the first and second substances,
Figure 397577DEST_PATH_IMAGE028
is shown as
Figure 810104DEST_PATH_IMAGE029
The station schedules the on-line monitoring data of the master station,
Figure 775786DEST_PATH_IMAGE030
indicating the y-th scheduling master station
Figure 957368DEST_PATH_IMAGE031
Class online monitoring data, n2 represents the number of scheduling masters in the cluster,
Figure 147041DEST_PATH_IMAGE032
the second station of the y scheduling master station after normalization processing
Figure 46864DEST_PATH_IMAGE033
Class on-line monitoring data, p is the total number of the types of the on-line monitoring data,
Figure 550658DEST_PATH_IMAGE034
；
quantifying the distance between every two scheduling master stations in the same cluster, wherein the distance is measured by Euclidean distance, and the calculation formula of the Euclidean distance is as follows:
Figure 852326DEST_PATH_IMAGE035
；
Figure 212900DEST_PATH_IMAGE036
for scheduling master stations
Figure 600019DEST_PATH_IMAGE017
And a scheduling master station
Figure 907504DEST_PATH_IMAGE018
The Euclidean distance of (a) is,
Figure 798099DEST_PATH_IMAGE037
、
Figure 595154DEST_PATH_IMAGE038
are respectively denoted as the y1、y2Station dispatching master station
Figure 141673DEST_PATH_IMAGE033
The data is monitored on-line in a similar way,
Figure 315166DEST_PATH_IMAGE039
n2 denotes the total number of scheduling masters in the cluster,
Figure 325847DEST_PATH_IMAGE040
p is the total number of the types of the online monitoring data;
and setting a distance threshold value, and judging the running condition of the scheduling master station in the cluster based on the distance threshold value.
8. The method of claim 7, wherein the determining the operating condition of the dispatch master stations in the cluster based on the distance threshold comprises:
if the number of the scheduling master stations with the distance from the scheduling master station y to the scheduling master station y in each scheduling cluster is greater than 80% of the total number n2 of the cluster scheduling master stations, determining that the scheduling running condition of the scheduling master station y is abnormal; otherwise, determining that the scheduling running condition of the scheduling master station y is normal.
9. An image-based scheduling master station three-remote change identification system, which is used for realizing the image-based scheduling master station three-remote change identification method of any one of claims 1 to 8, and which comprises the following steps:
the data acquisition unit (1) is used for acquiring an SVG operation graph of a background picture of the scheduling system in real time, and performing external similarity analysis and linkage on the SVG operation graph according to a time sequence to obtain a scheduling master station three-remote change key data chain containing the scheduling master station three-remote change characteristics;
the cluster clustering unit (2) is used for extracting targets of the scheduling master station based on the three-remote-change key data chain of the scheduling master station, and clustering and dividing the scheduling master station into a plurality of groups of scheduling clusters according to the same scheduling attribute;
and the three-remote judging unit (3) is used for carrying out internal similarity analysis on each scheduling cluster to judge the three-remote changing running state of the scheduling master station contained in the scheduling cluster.
10. The image-based dispatch master station three-remote change identification system of claim 9, characterized in that the three-remote discrimination unit (3) is further integrated with an alarm device for alarming when it is discriminated that the dispatch operating state of the dispatch master station is abnormal.
CN202110822079.6A 2021-07-21 2021-07-21 Image-based scheduling master station three-remote change identification method and system Pending CN113269281A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110822079.6A CN113269281A (en) 2021-07-21 2021-07-21 Image-based scheduling master station three-remote change identification method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110822079.6A CN113269281A (en) 2021-07-21 2021-07-21 Image-based scheduling master station three-remote change identification method and system

Publications (1)

Publication Number Publication Date
CN113269281A true CN113269281A (en) 2021-08-17

Family

ID=77236966

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110822079.6A Pending CN113269281A (en) 2021-07-21 2021-07-21 Image-based scheduling master station three-remote change identification method and system

Country Status (1)

Country Link
CN (1) CN113269281A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112270373A (en) * 2020-11-06 2021-01-26 广东电网有限责任公司 Automatic three-remote change identification method for scheduling master station based on image identification technology
CN113077020A (en) * 2021-06-07 2021-07-06 广东电网有限责任公司湛江供电局 Transformer cluster management method and system
CN113099242A (en) * 2021-06-09 2021-07-09 广东电网有限责任公司湛江供电局 Power transmission line video monitoring data processing method and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112270373A (en) * 2020-11-06 2021-01-26 广东电网有限责任公司 Automatic three-remote change identification method for scheduling master station based on image identification technology
CN113077020A (en) * 2021-06-07 2021-07-06 广东电网有限责任公司湛江供电局 Transformer cluster management method and system
CN113099242A (en) * 2021-06-09 2021-07-09 广东电网有限责任公司湛江供电局 Power transmission line video monitoring data processing method and system

Similar Documents

Publication Publication Date Title
CN109633369B (en) Power grid fault diagnosis method based on multi-dimensional data similarity matching
CN108988487B (en) Power grid power failure event identification method based on multidimensional data
CN113268590A (en) Power grid equipment running state evaluation method based on equipment portrait and integrated learning
CN112381668B (en) Information extraction method for power grid faults
CN115358155A (en) Power big data abnormity early warning method, device, equipment and readable storage medium
CN103324128A (en) Primary equipment fault warning comprehensive compression method in power dispatching automation system
CN111044845B (en) Power distribution network accident identification method and system based on Apriori algorithm
CN115905959A (en) Method and device for analyzing relevance fault of power circuit breaker based on defect factor
CN115828145A (en) Online monitoring method, system and medium for electronic equipment
CN112270373A (en) Automatic three-remote change identification method for scheduling master station based on image identification technology
CN114676791A (en) Electric power system alarm information processing method based on fuzzy evidence reasoning
Andrade et al. Data-driven anomaly detection and event log profiling of SCADA alarms
CN109933450A (en) A kind of method of calibration and device of intelligent substation secondary void loop configuration file
CN113269281A (en) Image-based scheduling master station three-remote change identification method and system
Zhang et al. Research on power grid fault diagnosis based on a quantitative representation of alarm information
CN111313355B (en) Method for updating monitoring signal event rule under manual supervision
CN114118208A (en) Transformer fault judgment method and device based on multivariate information and electronic equipment
CN111899448A (en) Method and system for filtering intelligent inspection information of traction substation
Zhai et al. Improved Fault Classification Method in Transmission Line based on K-means Clustering
CN114625786B (en) Dynamic data mining method and system based on wind control technology
CN116630991B (en) Power transmission line state evaluation method and system
CN116796213B (en) Power distribution network line transformation relation identification method based on clustering algorithm
CN110398666B (en) Power distribution network fault diagnosis method based on relay protection time sequence information characteristics
CN118091003A (en) Transformer oil chromatographic anomaly identification method based on random matrix
CN115760732A (en) Method, equipment and medium for identifying oil level of transformer bushing

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210817

RJ01 Rejection of invention patent application after publication