CN113807007B - Power grid short circuit fault judging method and system - Google Patents
Power grid short circuit fault judging method and system Download PDFInfo
- Publication number
- CN113807007B CN113807007B CN202110984963.XA CN202110984963A CN113807007B CN 113807007 B CN113807007 B CN 113807007B CN 202110984963 A CN202110984963 A CN 202110984963A CN 113807007 B CN113807007 B CN 113807007B
- Authority
- CN
- China
- Prior art keywords
- power equipment
- fault
- power
- short
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000000835 fiber Substances 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000004088 simulation Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 6
- 238000012850 discrimination method Methods 0.000 claims 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 6
- 229910002804 graphite Inorganic materials 0.000 description 6
- 239000010439 graphite Substances 0.000 description 6
- 239000004020 conductor Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method and a system for judging a power grid short-circuit fault, wherein the method comprises the steps of screening a power equipment set to be maintained, which accords with the condition of conducting fiber induced short-circuit fault, from a whole-network power equipment database; classifying the power equipment as alternating current equipment or direct current equipment into a fault type power equipment set; traversing all faults in a fault type power equipment set according to the power equipment and the running condition section data at the typical running time, and recording bus current, bus voltage and bus frequency change data of m fault observation points; training a classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time; after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, judging the fault type of the wave recording result through the trained classification learners corresponding to the m fault observation points respectively to obtain m judging results, and judging the fault type of the power grid after suffering from the short-circuit fault caused by the conductive fiber.
Description
Technical Field
The invention relates to the technical field of power system analysis, in particular to a method and a system for judging a power grid short circuit fault.
Background
The rapid development of national economy drives the continuous increase of the power demand of society, and the traditional transmission and distribution network is difficult to meet the requirement of system capacity. Meanwhile, the requirements of large cities, industrial centers, residential buildings and the like on the electric energy quality are more severe. In order to solve the above problems, the power system needs to be continuously upgraded and modified. The voltage class of the power system is higher and higher, the power capacity is larger and the interconnection among the power systems in each region is stronger, so that the short circuit level in each stage of power grid is continuously improved, and the damage of the short circuit fault to the power system and the electric equipment connected with the power system is larger.
The short circuit caused by the conductive fiber is one of the reasons for causing the short circuit fault, such as a graphite bomb made of specially treated conductive fiber yarn, the main attack object is the electric facilities of the urban electric network, the attack object is to destroy the normal power supply of the electric network, the graphite bomb releases a large number of conductive fibers after being exploded in the air, a plurality of conductive fibers can form a conductive fiber network in the air, and the conductive fibers fall on the conductive part of the electric equipment to cause the short circuit fault to cause power failure, and the electric network is paralyzed when serious. Graphite bombs were first used by the army in the gulf war in 1992 and later applied in the kewow war in 1999, and it was anticipated that there will be still a field of use for graphite bombs in future wars. Because the short-circuit fault caused by the conductive fiber generally cannot disappear by itself, the short-circuit fault generated after the power grid is attacked by the graphite bomb is generally a permanent fault, and the attacked equipment trips under the protection action after the fault occurs until the power grid staff clarifies the fault type and takes corresponding measures to clean the conductive fiber on the exposed conductor of the equipment, the equipment can be put into use again, and the power supply of the power grid can be recovered.
Therefore, when the power grid suffers from a large-range short-circuit fault caused by the conductive fiber, the fault type of the power grid is rapidly distinguished, and the method has important significance for cleaning the fault and recovering the power supply of the power grid at the first time, but related researches are lacking at home and abroad at present.
Disclosure of Invention
The invention provides a method and a system for judging the type of a power grid short-circuit fault, which are used for solving the problem that the conventional power grid is subjected to conductive fibers to cause the type of fault to be judged after a large-scale short-circuit fault.
In order to solve the above technical problems, an embodiment of the present invention provides a method for discriminating a short-circuit fault of a power grid, including:
acquiring all power equipment data in a power grid, constructing a whole-network power equipment set, and screening the power equipment set to be maintained, which accords with the condition that the conductive fiber causes a short-circuit fault, from the whole-network power equipment database;
traversing all the power equipment in the power equipment set to be maintained, and classifying the power equipment serving as alternating current equipment or direct current equipment into a fault type power equipment set;
simulating and calculating power equipment and running condition section data of a power grid in a typical running time of M continuous days, selecting M power grid bus nodes as fault observation points, traversing all faults in the fault type power equipment set according to the power equipment and running condition section data in the typical running time, and recording bus current, bus voltage and bus frequency change data of M fault observation points; wherein M is an integer greater than or equal to 3, and M is an integer greater than 1;
selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time;
after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, carrying out fault wave recording on the change data of the bus current, the bus voltage and the bus frequency of m fault observation points, carrying out fault type judgment on the wave recording results through the trained classification learners corresponding to the m fault observation points respectively to obtain m judgment results, and carrying out fault type judgment on the power grid after suffering from the short-circuit fault caused by the conductive fiber based on the m judgment results.
As a further improvement, the method includes the steps of obtaining all the power equipment data in the power grid and constructing a whole-network power equipment set, and screening the power equipment set to be maintained, which accords with the condition that the conductive fiber causes the short-circuit fault, from the whole-network power equipment database, specifically including:
acquiring all power equipment data in a power grid, and constructing a whole-network power equipment set according to the all power equipment data, wherein the power equipment set at least comprises power equipment and attributes, arrangement environments and distribution arrangement forms thereof;
when traversing the whole network power equipment set to obtain power equipment serving as power grid primary equipment, judging whether the arrangement environment of the power equipment is outdoor or not;
after the arrangement environment of the power equipment is judged to be outdoor, judging whether the distribution arrangement form of the power equipment is non-GIS equipment or not;
and after judging that the power distribution of the power equipment is non-GIS equipment, classifying the power equipment into the fault type power equipment set.
As a further improvement, the traversing all the power devices in the power device set to be maintained classifies the power devices as ac devices or dc devices into the fault type power device set, specifically including:
when traversing the fault type power equipment set to obtain power equipment serving as alternating current equipment, classifying the power equipment meeting preset alternating current fault conditions into a short circuit fault power equipment database; the preset fault conditions comprise single-phase grounding short-circuit faults, two-phase grounding short-circuit faults, three-phase grounding short-circuit faults, two-phase ungrounded short-circuit faults and three-phase ungrounded short-circuit faults.
As a further improvement, the traversing all the power devices in the power device set to be maintained classifies the power devices as ac devices or dc devices into the fault type power device set, specifically including:
when traversing the fault type power equipment set to obtain power equipment serving as direct current equipment, classifying the power equipment meeting the preset direct current fault condition into the short circuit fault power equipment database; the preset direct current fault conditions comprise a single-pole grounding short-circuit fault, a double-pole grounding short-circuit fault and a double-pole non-grounding short-circuit fault.
As a further improvement, the simulation calculation is performed on the power equipment and the running condition section data of the power grid at the typical running time in M consecutive days, M power grid bus nodes are selected as fault observation points, all faults in the fault type power equipment set are traversed according to the power equipment and the running condition section data at the typical running time, and bus current, bus voltage and bus frequency change data of M fault observation points are recorded, and the method specifically comprises the following steps:
acquiring n pieces of power equipment and running condition section data of typical running time of continuous M days from a power grid running management system; wherein n is an integer of 1 or more;
traversing all faults in the fault type power equipment set for n pieces of power equipment and running condition section data through an electromechanical-electromagnetic hybrid simulation software platform and performing electromechanical-electromagnetic hybrid simulation;
and selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change data of the m fault observation points when each simulation is carried out.
As a further improvement, the selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner for each fault observation point according to the power equipment and the running condition section data at the typical running time specifically includes:
randomly selecting a classification learner for each fault observation node;
and taking the fault type power equipment set as a sample set of each fault observation point, carrying out simulation calculation on n pieces of power equipment and running condition section data to obtain n groups of busbar current, busbar voltage and busbar frequency change curves of the observation nodes as n attribute sets, and respectively forming n training sets by the fault type power equipment set and the n attribute sets so as to train a classification learner corresponding to each observation node.
The embodiment of the invention also provides a system for judging the short-circuit fault of the power grid, which comprises the following steps:
the collection construction module is used for acquiring all power equipment data in the power grid, constructing a whole-network power equipment collection, and screening the power equipment collection to be maintained, which accords with the condition that the conductive fiber causes the short-circuit fault, from the whole-network power equipment database;
the collection classification module is used for traversing all the power equipment in the power equipment collection to be maintained and classifying the power equipment serving as alternating current equipment or direct current equipment into a fault type power equipment collection;
the simulation calculation module is used for carrying out simulation calculation on the power equipment and the running condition section data of the power grid in the typical running time for M continuous days, selecting M power grid bus nodes as fault observation points, traversing all faults in the fault type power equipment set according to the power equipment and the running condition section data in the typical running time, and recording bus current, bus voltage and bus frequency change data of M fault observation points; wherein M is an integer greater than or equal to 3, and M is an integer greater than 1;
the learning training module is used for selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time;
the fault type judging module is used for carrying out fault wave recording on the change data of the bus current, the bus voltage and the bus frequency of m fault observation points after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, carrying out fault type judgment on the wave recording results through the trained classification learners corresponding to the m fault observation points respectively to obtain m judging results, and carrying out fault type judgment on the power grid after suffering from the short-circuit fault caused by the conductive fiber based on the m judging results.
As a further improvement, the set construction module is further configured to:
acquiring all power equipment data in a power grid, and constructing a whole-network power equipment set according to the all power equipment data, wherein the power equipment set at least comprises power equipment and attributes, arrangement environments and distribution arrangement forms thereof;
judging whether the arrangement environment of the power equipment is outdoor or not when the power equipment serving as the primary power grid equipment is obtained through traversal in the whole power grid power equipment set;
after the arrangement environment of the power equipment is judged to be outdoor, judging whether the distribution arrangement form of the power equipment is non-GIS equipment or not;
and after judging that the power distribution of the power equipment is non-GIS equipment, classifying the power equipment into the fault type power equipment set.
As a further improvement, the set categorizing module is further configured to:
when traversing the fault type power equipment set to obtain power equipment serving as alternating current equipment, classifying the power equipment meeting preset alternating current fault conditions into a short circuit fault power equipment database; the preset fault conditions comprise single-phase grounding short-circuit faults, two-phase grounding short-circuit faults, three-phase grounding short-circuit faults and two-phase ungrounded short-circuit faults, wherein the three-phase ungrounded short-circuit faults are included;
when traversing the fault type power equipment set to obtain power equipment serving as direct current equipment, classifying the power equipment meeting the preset direct current fault condition into the short circuit fault power equipment database; the preset direct current fault conditions comprise a single-pole grounding short-circuit fault, a double-pole grounding short-circuit fault and a double-pole non-grounding short-circuit fault.
As a further improvement, the simulation calculation module is further configured to:
acquiring n pieces of power equipment and running condition section data of typical running time of continuous M days from a power grid running management system; wherein n is an integer of 1 or more;
traversing all faults in the fault type power equipment set for n pieces of power equipment and running condition section data through an electromechanical-electromagnetic hybrid simulation software platform and performing electromechanical-electromagnetic hybrid simulation;
and selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change data of the m fault observation points when each simulation is carried out.
As a further improvement, the learning training module is further configured to:
randomly selecting a classification learner for each fault observation node;
and taking the fault type power equipment set as a sample set of each fault observation point, carrying out simulation calculation on n pieces of power equipment and running condition section data to obtain n groups of busbar current, busbar voltage and busbar frequency change curves of the observation nodes as n attribute sets, and respectively forming n training sets by the fault type power equipment set and the n attribute sets so as to train a classification learner corresponding to each observation node.
Compared with the prior art, the embodiment of the invention provides a method and a system for judging the type of the short-circuit fault of the power grid, which are characterized in that the power grid simulation data are used as basic training samples, different types of classification learners are randomly selected for different fault observation points, different training attribute samples are used for different classification learners, the final judging result of the type of the fault synthesizes the judging results of a plurality of multi-type classification learners, and the accuracy of the judging result is obviously improved compared with that of a single classification learner.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for discriminating a type of a short-circuit fault of a power grid in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the present invention provides a method for discriminating a short-circuit fault of a power grid, including:
step S1, acquiring all power equipment data in a power grid, constructing a whole-network power equipment set, and screening the power equipment set to be maintained, which accords with the condition that the conductive fiber causes a short-circuit fault, from the whole-network power equipment database;
step S2, traversing all the power equipment in the power equipment set to be maintained, and classifying the power equipment serving as alternating current equipment or direct current equipment into a fault type power equipment set;
step S3, simulation calculation is carried out on power equipment and running condition section data of a power grid in a typical running time for M continuous days, M power grid bus nodes are selected to serve as fault observation points, all faults in the fault type power equipment set are traversed according to the power equipment and running condition section data in the typical running time, and bus current, bus voltage and bus frequency change data of the M fault observation points are recorded; wherein M is an integer greater than or equal to 3, and M is an integer greater than 1;
step S4, selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time;
and S5, after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, performing fault wave recording on the change data of the bus current, the bus voltage and the bus frequency of m fault observation points, and performing fault type judgment on the wave recording results through trained classification learners corresponding to the m fault observation points respectively to obtain m judgment results, and performing fault type judgment on the power grid after suffering from the short-circuit fault caused by the conductive fiber based on the m judgment results.
In the embodiment of the present invention, the step S1 is to acquire all power equipment data in a power grid and construct a whole-grid power equipment set, and screen the power equipment set to be maintained, which meets the condition that the conductive fiber causes a short-circuit fault, from the whole-grid power equipment database, and specifically includes:
step S11, acquiring all power equipment data in a power grid, and constructing a whole-network power equipment set according to all the power equipment data, wherein the power equipment set at least comprises power equipment and attributes, arrangement environments and distribution arrangement forms thereof;
step S12, judging whether the arrangement environment of the power equipment is outdoor or not when the power equipment serving as the primary power grid equipment is obtained through traversal in the whole power grid power equipment set;
step S13, after judging that the arrangement environment of the power equipment is outdoor, judging whether the distribution arrangement form of the power equipment is non-GIS equipment or not;
and step S14, after judging that the power distribution of the power equipment is non-GIS equipment, classifying the power equipment into the fault type power equipment set.
In this embodiment, it should be noted that, according to the characteristics of the conductive fibers for the exposed conductors of the primary power equipment, the primary power equipment set E, in which all the power grids to be analyzed meet the condition of short-circuit fault caused by the conductive fibers, is obtained by searching and distinguishing, and the specific method is implemented as follows:
1) A set of all force devices of the grid is generated, defined as a set D of power devices.
2) And (3) starting to traverse all the power equipment in the power equipment set D, if the power equipment belongs to primary equipment, turning to the next step (3), and if not, starting to judge the next power equipment.
3) If the arrangement environment of the power equipment is outdoor, the next step 4) is carried out, and if not, the next power equipment is judged.
4) If the distribution device arrangement form of the power equipment is non-GIS equipment, the power equipment is added into the set E, otherwise, the next equipment is judged.
5) And traversing all the power equipment in the power equipment set D to obtain a set E, wherein the set E is a primary power equipment set of which the power grid possibly suffers from short-circuit faults caused by conductive fibers.
In the embodiment of the present invention, the step S2 traverses all the power devices in the power device set to be maintained, classifies the power devices as ac devices or dc devices into the fault type power device set, and specifically includes:
step S21, when traversing the fault type power equipment set to obtain power equipment serving as alternating current equipment, classifying the power equipment meeting preset alternating current fault conditions into a short circuit fault power equipment database; the preset fault conditions comprise single-phase grounding short-circuit faults, two-phase grounding short-circuit faults, three-phase grounding short-circuit faults, two-phase ungrounded short-circuit faults and three-phase ungrounded short-circuit faults.
Step S22, when traversing the fault type power equipment set to obtain power equipment serving as direct current equipment, classifying the power equipment meeting the preset direct current fault condition into the short circuit fault power equipment database; the preset direct current fault conditions comprise a single-pole grounding short-circuit fault, a double-pole grounding short-circuit fault and a double-pole non-grounding short-circuit fault.
In the embodiment of the present invention, the step S3 performs simulation calculation on power equipment and operation condition section data of a power grid at a typical operation time for M consecutive days, selects M power grid bus nodes as fault observation points, traverses all faults in the fault type power equipment set according to the power equipment and operation condition section data at the typical operation time, and records bus current, bus voltage and bus frequency change data of M fault observation points, including:
step S31, acquiring n pieces of power equipment and running condition section data of typical running time of continuous M days from a power grid running management system (OMS); wherein n is an integer of 1 or more;
step S32, traversing all faults in the fault type power equipment set through the electromechanical-electromagnetic hybrid simulation software platform for the n pieces of power equipment and the running condition section data and performing electromechanical-electromagnetic hybrid simulation;
step S33, selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change data (which can be bus frequency change curves) of the m fault observation points when each simulation is performed.
As an example, the specific implementation method of the simulation calculation is as follows:
1) In the extreme case that the power grid may be attacked by a graphite bomb, n pieces of equipment and running condition section data of the power grid at a typical running time of approximately 3 days are obtained from an Operation Management System (OMS) of the power grid;
2) And applying an electromechanical-electromagnetic hybrid simulation software platform (such as DSP-EMTDC or ADPSS) to perform electromechanical-electromagnetic hybrid simulation on all faults in the n-section data traversing fault set F. If the number of faults in the fault type power equipment set is t, the total number of electromechanical-electromagnetic hybrid simulation is n multiplied by t;
3) And selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change curves of the m fault observation points in each simulation.
In the embodiment of the present invention, the step S4 is to select a classification learner for each fault observation point, use the fault type power equipment set as a sample set of each fault observation point, and train the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time, and specifically includes:
step S41, randomly selecting a classification learner for each fault observation node; the optional classification learners comprise decision trees, BP neural networks and the like;
and S42, taking the fault type power equipment set as a sample set of each fault observation point, carrying out simulation calculation on n pieces of power equipment and running condition section data to obtain n groups of bus current, bus voltage and bus frequency change curves of the observation nodes as n attribute sets, and respectively forming n training sets by the fault type power equipment set and the n attribute sets so as to train a classification learner corresponding to each observation node.
The embodiment of the invention also provides a system for judging the short-circuit fault of the power grid, which comprises the following steps:
the collection construction module is used for acquiring all power equipment data in the power grid, constructing a whole-network power equipment collection, and screening the power equipment collection to be maintained, which accords with the condition that the conductive fiber causes the short-circuit fault, from the whole-network power equipment database;
the collection classification module is used for traversing all the power equipment in the power equipment collection to be maintained and classifying the power equipment serving as alternating current equipment or direct current equipment into a fault type power equipment collection;
the simulation calculation module is used for carrying out simulation calculation on the power equipment and the running condition section data of the power grid in the typical running time for M continuous days, selecting M power grid bus nodes as fault observation points, traversing all faults in the fault type power equipment set according to the power equipment and the running condition section data in the typical running time, and recording bus current, bus voltage and bus frequency change data of M fault observation points; wherein M is an integer greater than or equal to 3, and M is an integer greater than 1;
the learning training module is used for selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time;
the fault type judging module is used for carrying out fault wave recording on the change data of the bus current, the bus voltage and the bus frequency of m fault observation points after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, carrying out fault type judgment on the wave recording results through the trained classification learners corresponding to the m fault observation points respectively to obtain m judging results, and carrying out fault type judgment on the power grid after suffering from the short-circuit fault caused by the conductive fiber based on the m judging results.
As a further improvement, the set construction module is further configured to:
acquiring all power equipment data in a power grid, and constructing a whole-network power equipment set according to the all power equipment data, wherein the power equipment set at least comprises power equipment and attributes, arrangement environments and distribution arrangement forms thereof;
judging whether the arrangement environment of the power equipment is outdoor or not when the power equipment serving as the primary power grid equipment is obtained through traversal in the whole power grid power equipment set;
after the arrangement environment of the power equipment is judged to be outdoor, judging whether the distribution arrangement form of the power equipment is non-GIS equipment or not;
and after judging that the power distribution of the power equipment is non-GIS equipment, classifying the power equipment into the fault type power equipment set.
As a further improvement, the set categorizing module is further configured to:
when traversing the fault type power equipment set to obtain power equipment serving as alternating current equipment, classifying the power equipment meeting preset alternating current fault conditions into a short circuit fault power equipment database; the preset fault conditions comprise single-phase grounding short-circuit faults, two-phase grounding short-circuit faults, three-phase grounding short-circuit faults and two-phase ungrounded short-circuit faults, wherein the three-phase ungrounded short-circuit faults are included;
when traversing the fault type power equipment set to obtain power equipment serving as direct current equipment, classifying the power equipment meeting the preset direct current fault condition into the short circuit fault power equipment database; the preset direct current fault conditions comprise a single-pole grounding short-circuit fault, a double-pole grounding short-circuit fault and a double-pole non-grounding short-circuit fault.
As a further improvement, the simulation calculation module is further configured to:
acquiring n pieces of power equipment and running condition section data of typical running time of continuous M days from a power grid running management system; wherein n is an integer of 1 or more;
traversing all faults in the fault type power equipment set for n pieces of power equipment and running condition section data through an electromechanical-electromagnetic hybrid simulation software platform and performing electromechanical-electromagnetic hybrid simulation;
and selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change data of the m fault observation points when each simulation is carried out.
As a further improvement, the learning training module is further configured to:
randomly selecting a classification learner for each fault observation node;
and taking the fault type power equipment set as a sample set of each fault observation point, carrying out simulation calculation on n pieces of power equipment and running condition section data to obtain n groups of busbar current, busbar voltage and busbar frequency change curves of the observation nodes as n attribute sets, and respectively forming n training sets by the fault type power equipment set and the n attribute sets so as to train a classification learner corresponding to each observation node.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (10)
1. The utility model provides a power grid short circuit fault distinguishing method which is characterized by comprising the following steps:
acquiring all power equipment data in a power grid, constructing a whole-network power equipment set, and screening the power equipment set to be maintained, which accords with the condition that the conductive fiber causes a short-circuit fault, from a whole-network power equipment database;
traversing all the power equipment in the power equipment set to be maintained, and classifying the power equipment serving as alternating current equipment or direct current equipment into a fault type power equipment set;
simulating and calculating power equipment and running condition section data of a power grid in a typical running time of M continuous days, selecting M power grid bus nodes as fault observation points, traversing all faults in the fault type power equipment set according to the power equipment and running condition section data in the typical running time, and recording bus current, bus voltage and bus frequency change data of M fault observation points; wherein M is an integer greater than or equal to 3, and M is an integer greater than 1;
selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time;
after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, carrying out fault wave recording on the change data of the bus current, the bus voltage and the bus frequency of m fault observation points, and carrying out fault type judgment on wave recording results through trained classification learners corresponding to the m fault observation points respectively to obtain m judging results, and carrying out fault type judgment on the power grid after suffering from the short-circuit fault caused by the conductive fiber based on the m judging results.
2. The method for discriminating a short-circuit fault of a power grid according to claim 1, wherein the steps of obtaining all the power equipment data in the power grid and constructing a whole-network power equipment set, and screening the whole-network power equipment database for the power equipment set to be maintained, which meets the condition that the short-circuit fault is caused by the conductive fiber, specifically comprise the steps of:
acquiring all power equipment data in a power grid, and constructing a whole-network power equipment set according to the all power equipment data, wherein the power equipment set at least comprises power equipment and attributes, arrangement environments and distribution arrangement forms thereof;
when traversing the whole network power equipment set to obtain power equipment serving as power grid primary equipment, judging whether the arrangement environment of the power equipment is outdoor or not;
after the arrangement environment of the power equipment is judged to be outdoor, judging whether the distribution arrangement form of the power equipment is non-GIS equipment or not;
and after judging that the power distribution of the power equipment is non-GIS equipment, classifying the power equipment into the fault type power equipment set.
3. The method for discriminating a short-circuit fault of a power grid according to claim 1 or 2, wherein the traversing all the power devices in the set of power devices to be maintained classifies the power devices as ac devices or dc devices into the set of fault type power devices, specifically includes:
when traversing the fault type power equipment set to obtain power equipment serving as alternating current equipment, classifying the power equipment meeting preset alternating current fault conditions into a short circuit fault power equipment database; the preset fault conditions comprise single-phase grounding short-circuit faults, two-phase grounding short-circuit faults, three-phase grounding short-circuit faults, two-phase ungrounded short-circuit faults and three-phase ungrounded short-circuit faults.
4. The grid short-circuit fault discrimination method according to claim 1 or 2, characterized in that the method further comprises:
when traversing the fault type power equipment set to obtain power equipment serving as direct current equipment, classifying the power equipment meeting the preset direct current fault condition into a short circuit fault power equipment database; the preset direct current fault conditions comprise a single-pole grounding short-circuit fault, a double-pole grounding short-circuit fault and a double-pole non-grounding short-circuit fault.
5. The method for determining a short-circuit fault of a power grid according to claim 1, wherein the simulation calculation is performed on power equipment and operation condition section data of the power grid at typical operation time for M consecutive days, M power grid bus nodes are selected as fault observation points, all faults in the fault type power equipment set are traversed according to the power equipment and operation condition section data at typical operation time, and bus current, bus voltage and bus frequency change data of M fault observation points are recorded, and the method specifically comprises the steps of:
acquiring n pieces of power equipment and running condition section data of typical running time of continuous M days from a power grid running management system; wherein n is an integer of 1 or more;
traversing all faults in the fault type power equipment set for n pieces of power equipment and running condition section data through an electromechanical-electromagnetic hybrid simulation software platform and performing electromechanical-electromagnetic hybrid simulation;
and selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change data of the m fault observation points when each simulation is carried out.
6. The method for determining a short-circuit fault of a power grid according to claim 1, wherein the selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner for each fault observation point according to the power equipment and the running condition section data at the typical running time specifically comprises:
randomly selecting a classification learner for each fault observation node;
and taking the fault type power equipment set as a sample set of each fault observation point, carrying out simulation calculation on n pieces of power equipment and running condition section data to obtain n groups of busbar current, busbar voltage and busbar frequency change curves of the observation nodes as n attribute sets, and respectively forming n training sets by the fault type power equipment set and the n attribute sets so as to train a classification learner corresponding to each observation node.
7. A power grid short-circuit fault discrimination system, comprising:
the collection construction module is used for acquiring all power equipment data in the power grid, constructing a whole-network power equipment collection, and screening the power equipment collection to be maintained, which accords with the condition that the conductive fiber causes a short-circuit fault, from the whole-network power equipment database;
the collection classification module is used for traversing all the power equipment in the power equipment collection to be maintained and classifying the power equipment serving as alternating current equipment or direct current equipment into a fault type power equipment collection;
the simulation calculation module is used for carrying out simulation calculation on the power equipment and the running condition section data of the power grid in the typical running time for M continuous days, selecting M power grid bus nodes as fault observation points, traversing all faults in the fault type power equipment set according to the power equipment and the running condition section data in the typical running time, and recording bus current, bus voltage and bus frequency change data of M fault observation points; wherein M is an integer greater than or equal to 3, and M is an integer greater than 1;
the learning training module is used for selecting a classification learner for each fault observation point, taking the fault type power equipment set as a sample set of each fault observation point, and training the classification learner of each fault observation point according to the power equipment and the running condition section data at the typical running time;
the fault type judging module is used for carrying out fault wave recording on the change data of the bus current, the bus voltage and the bus frequency of m fault observation points after judging that the power grid suffers from the short-circuit fault caused by the conductive fiber, carrying out fault type judgment on wave recording results through trained classification learners corresponding to the m fault observation points respectively to obtain m judging results, and carrying out fault type judgment on the power grid after suffering from the short-circuit fault caused by the conductive fiber based on the m judging results.
8. The grid short circuit fault discrimination system according to claim 7, wherein said set construction module is further configured to:
acquiring all power equipment data in a power grid, and constructing a whole-network power equipment set according to the all power equipment data, wherein the power equipment set at least comprises power equipment and attributes, arrangement environments and distribution arrangement forms thereof;
when traversing the whole network power equipment set to obtain power equipment serving as power grid primary equipment, judging whether the arrangement environment of the power equipment is outdoor or not;
after the arrangement environment of the power equipment is judged to be outdoor, judging whether the distribution arrangement form of the power equipment is non-GIS equipment or not;
and after judging that the power distribution of the power equipment is non-GIS equipment, classifying the power equipment into the fault type power equipment set.
9. The grid short circuit fault discrimination system according to claim 7, wherein said simulation calculation module is further configured to:
acquiring n pieces of power equipment and running condition section data of typical running time of continuous M days from a power grid running management system; wherein n is an integer of 1 or more;
traversing all faults in the fault type power equipment set for n pieces of power equipment and running condition section data through an electromechanical-electromagnetic hybrid simulation software platform and performing electromechanical-electromagnetic hybrid simulation;
and selecting m power grid bus nodes as fault observation points, and recording bus current, bus voltage and bus frequency change data of the m fault observation points when each simulation is carried out.
10. The grid short circuit fault discrimination system according to claim 7, wherein the learning training module is further configured to:
randomly selecting a classification learner for each fault observation node;
and taking the fault type power equipment set as a sample set of each fault observation point, carrying out simulation calculation on n pieces of power equipment and running condition section data to obtain n groups of busbar current, busbar voltage and busbar frequency change curves of the observation nodes as n attribute sets, and respectively forming n training sets by the fault type power equipment set and the n attribute sets so as to train a classification learner corresponding to each observation node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110984963.XA CN113807007B (en) | 2021-08-25 | 2021-08-25 | Power grid short circuit fault judging method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110984963.XA CN113807007B (en) | 2021-08-25 | 2021-08-25 | Power grid short circuit fault judging method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807007A CN113807007A (en) | 2021-12-17 |
| CN113807007B true CN113807007B (en) | 2023-05-23 |
Family
ID=78894171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110984963.XA Active CN113807007B (en) | 2021-08-25 | 2021-08-25 | Power grid short circuit fault judging method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807007B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108448566B (en) * | 2018-02-12 | 2022-08-09 | 中国电力科学研究院有限公司 | Online hybrid simulation method and system for power system |
| AU2020326795A1 (en) * | 2019-08-06 | 2022-03-10 | Glxt Holdings, Llc | Systems and methods for electrical earthing systems |
| CN110766137A (en) * | 2019-10-18 | 2020-02-07 | 武汉大学 | Power electronic circuit fault diagnosis method based on longicorn whisker optimized deep confidence network algorithm |
| CN111160241B (en) * | 2019-12-27 | 2022-08-12 | 华中科技大学 | Power distribution network fault classification method, system and medium based on deep learning |
| CN111598166B (en) * | 2020-05-18 | 2023-10-17 | 国网山东省电力公司电力科学研究院 | Single-phase earth fault classification method and system based on principal component analysis and Softmax function |
-
2021
- 2021-08-25 CN CN202110984963.XA patent/CN113807007B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807007A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106019084A (en) | Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method | |
| CN109655712A (en) | A kind of distribution network line fault analysis of causes method and system | |
| CN112307435A (en) | Method for judging and screening abnormal electricity consumption based on fuzzy clustering and trend | |
| CN103871003A (en) | Power distribution network fault diagnosis method utilizing historical fault data | |
| CN109444667A (en) | Power distribution network initial failure classification method and device based on convolutional neural networks | |
| CN110045207A (en) | A kind of complex fault diagnostic method based on power grid architecture and multisource data fusion | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN113807007B (en) | Power grid short circuit fault judging method and system | |
| CN113572771B (en) | Power grid CPS network attack identification method and system | |
| Forsberg et al. | Power grid vulnerability analysis using complex network theory: A topological study of the Nordic transmission grid | |
| CN117669361A (en) | Power distribution area topology identification function verification method and system | |
| CN111369388B (en) | Anti-vulnerability assessment method and system for urban power grid | |
| CN113240005B (en) | Power system complex network false data detection method based on static network representation | |
| CN116432077A (en) | Intelligent station secondary system fault positioning method based on optimized BP neural network | |
| CN115549040A (en) | Automatic fault diagnosis method and system for flexible direct current converter station | |
| Kezunovic | Automated analysis of voltage sags, their causes and impacts | |
| CN114064622A (en) | Big data-based power failure study and judgment processing method and system | |
| CN113902346A (en) | Intelligent allocation method for electric power rush-repair team | |
| CN113850422A (en) | Method for quickly searching transformer area line loss point based on multiple nonlinear regression or/and parallel vector | |
| Pylarinos et al. | Discharges classification using genetic algorithms and feature selection algorithms on time and frequency domain data extracted from leakage current measurements | |
| CN115809761B (en) | Voltage quality analysis method and system based on low-voltage transformer area | |
| Kezunovic et al. | Automated Fault Analysis Using Advanced Information Technology for Data Integration and Information Exchange | |
| Liang | High impedance fault detection in power distribution systems with impedance-based methods in frequency domain | |
| CN114021395B (en) | Method and device for analyzing fragile correlation of power information physical system line | |
| Maurya et al. | A Short Review on Fault Detection and Fault Classification in Transmission Lines |
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 |