CN117250439B - Three-layer type studying and judging analysis system for multi-source ground fault - Google Patents
Three-layer type studying and judging analysis system for multi-source ground fault Download PDFInfo
- Publication number
- CN117250439B CN117250439B CN202311473340.1A CN202311473340A CN117250439B CN 117250439 B CN117250439 B CN 117250439B CN 202311473340 A CN202311473340 A CN 202311473340A CN 117250439 B CN117250439 B CN 117250439B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- waveform data
- module
- judging
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 57
- 238000009826 distribution Methods 0.000 claims abstract description 86
- 238000000034 method Methods 0.000 claims abstract description 67
- 238000011160 research Methods 0.000 claims abstract description 62
- 238000004088 simulation Methods 0.000 claims abstract description 45
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000006243 chemical reaction Methods 0.000 claims description 40
- 238000012549 training Methods 0.000 claims description 28
- 238000010586 diagram Methods 0.000 claims description 27
- 238000005070 sampling Methods 0.000 claims description 21
- 101100499229 Mus musculus Dhrsx gene Proteins 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 17
- 230000001052 transient effect Effects 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 8
- 230000007935 neutral effect Effects 0.000 claims description 7
- 230000011664 signaling Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 5
- 238000013500 data storage Methods 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
- G01R19/16533—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values characterised by the application
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/175—Indicating the instants of passage of current or voltage through a given value, e.g. passage through zero
-
- 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
Abstract
The invention belongs to the technical field of power distribution network fault detection and protection, and discloses a three-layer type studying and judging analysis system for multi-source ground faults, which comprises a data layer, an analysis layer and an application layer. The data layer collects fault waveform data from the GIS real test platform and the simulation platform, power distribution terminal equipment and self-defined fault waveform data, and a fault case waveform library is established according to the collected fault waveform data; the analysis layer extracts fault characteristics from the fault case waveform library by using a first half-wave method, a phase asymmetry method and a zero sequence power method and performs fault research and judgment to obtain a research and judgment result; and the application layer carries out self-healing fault research and judgment, consistency check of the research and judgment result and the SOE message, distribution statistics of fault characteristics and line fault distribution statistics according to the research and judgment result, and outputs an analysis result. The method can avoid the problem that the prior single-phase earth fault treatment technology has no field data support, and solves the problem that the prior art cannot perform centralized management and efficient utilization on a large amount of fault waveform data.
Description
Technical Field
The invention relates to the technical field of power distribution network fault detection and protection, in particular to a three-layer type studying and judging analysis system for multi-source ground faults.
Background
With the strategic advancement of the digital transformation of power distribution, the distribution network is changed from a traditional 'blind tuning' mode into a high-efficiency mode of considerable, measurable and controllable on-line sensing, monitoring and auxiliary decision-making automation and intellectualization. Under the background, in order to cope with the "worldwide" problem of single-phase earth fault, extensive theoretical research and practical devices are used as references in scientific and effective treatment of distribution network earth fault, but in order to adapt to 10kV distribution lines with huge quantity and scale, a secondary fusion complete-set switch breaker with tens of thousands of stages is installed and applied to the field. In addition, it is well known that in the distribution network fault class, the probability of occurrence of a single-phase earth fault is dominant, thousands of earth fault waveforms gradually appear to the field of view of users and are all stored in a secondary fusion complete switch on site, and the switching equipment of the class locally stores at most 64 records, but currently, for the precious and slightly-elapsed fault waveforms, a centralized management, effective and efficient intelligent analysis platform is lacking so as to assist the actual engineering application on site.
It is noted that the effective handling of the ground fault has extremely high requirements for the fault identification performance of the secondary switch set, so how to select excellent equipment is a major concern. The problem of effective treatment of ground faults around the whole country is solved, a plurality of distribution network true test platforms are established so as to be capable of performing special detection tests on network access equipment, but even so, the true test platforms are equivalent to simulation tests, the tests are theoretical fault waveforms, the distance between the actual complex working conditions of the site is far, and the equipment ground fault identification performance cannot be accurately and reliably achieved. If tens of thousands of field fault waveforms can be concentrated and collected, typical fault waveforms are extracted, and the ground fault identification performance of the equipment can be evaluated in a multi-dimensional, more objective, comprehensive and scientific manner by matching with a true test and a modeling simulation mode which can simulate various scenes. In the whole, a ground fault research and judgment analysis system oriented to various sources is established, and the method has very important guiding significance for guiding the scientific treatment of faults, the improvement supervision of manufacturer equipment and the mastering of the evolution characteristics of the faults in the production line.
In view of this, the present application is specifically proposed.
Disclosure of Invention
The invention aims to provide a three-layer type studying and judging analysis system for multi-source ground faults, which solves the problem that the prior art cannot perform centralized management and efficient utilization on a large amount of fault waveform data.
The invention is realized by the following technical scheme:
the three-layer type studying and judging analysis system for the multi-source grounding faults comprises a data layer, a fault case waveform library and a fault judging analysis layer, wherein the data layer is used for collecting fault waveform data from a GIS true test platform, fault waveform data from a plurality of simulation platforms, fault waveform data from a plurality of power distribution terminal equipment and self-defined fault waveform data, and the fault case waveform library is established according to the collected fault waveform data; the analysis layer is used for integrating a plurality of fault judging methods, extracting fault characteristics from the fault case waveform library by utilizing each fault judging method respectively, and carrying out fault judgment according to each fault judging method respectively by combining the extracted fault characteristics to obtain judging results; the multiple fault judging methods comprise a first half-wave method, a phase asymmetry method and a zero sequence power method; and the application layer is used for carrying out self-healing fault research and judgment according to the research and judgment result, checking the consistency of the research and judgment result and the SOE message, carrying out distributed statistics of fault characteristics and carrying out distributed statistics of line faults, and outputting an analysis result.
Further, the plurality of simulation platforms comprise a PSCAD electromagnetic transient simulation system and an RTDS real-time digital simulation system; the data layer comprises a data conversion module and a data storage module; the data conversion module is used for carrying out data conversion among fault waveform data output by the PSCAD electromagnetic transient simulation system, fault waveform data output by the RTDS real-time digital simulation system and fault waveform data output by the GIS true test platform according to a standard COMTRADE data format, and storing the fault waveform data in the standard COMRADE data format obtained after conversion; the data storage module is used for starting the wave recording starting function and directly storing fault waveform data from the GIS true test platform and fault waveform data from the plurality of power distribution terminal equipment in a standard COMTRADE data format.
Further, the data conversion module comprises a PSCAD-GIS data conversion sub-module; the PSCAD-GIS data conversion submodule comprises an electric quantity output set generating unit, a power supply module and a power supply module, wherein the electric quantity output set generating unit is used for generating an electric quantity output set corresponding to each 10kV distribution line in each transformer substation according to fault waveform data output by the PSCAD electromagnetic transient simulation system; the data in the electrical quantity output set comprises A-phase voltage B-phase voltage->C-phase voltage->Zero sequence voltage->Phase A current->B phase current->C phase current->And zero sequence current->The method comprises the steps of carrying out a first treatment on the surface of the The index set generation unit is used for summarizing a plurality of electric quantity output sets corresponding to the transformer substation according to the total number of 10kV distribution lines in the transformer substation to generate an index set +.>；/>Wherein N represents the total number of 10kV distribution lines in the substation, < >>Corresponding->Electrical quantity output set of 10kV distribution line, ">The method comprises the steps of carrying out a first treatment on the surface of the A text file generating unit for gathering the index +.>Is +.>Outputting the data to a text file, and recording the electrical channel data and the system parameters of the PSCAD electromagnetic transient simulation system; the electrical channel data includes +/each electrical quantity output set>The system parameters include simulation step size ∈>Simulation duration->And drawing step->The method comprises the steps of carrying out a first treatment on the surface of the CFG file converting unit for converting the CFG file according to the drawing step length +.>Acquisition of sampling frequency->And the data point number M, obtaining the scaling transformation ratio of the PSCAD electromagnetic transient simulation system when performing secondary transformation ratio conversion, and obtaining the sampling frequency +.>Outputting the data points M and the scaling transformation ratio to a designated position in the COMTRADE configuration file CFG; DAT file conversion unit for converting data in text file according to +. >Performing data conversion in an arrangement mode; wherein,nthe number of samples is indicated and,timerepresenting a time scale, wherein the sampling number and the time scale are 4 bytes of unsigned binary data;Aiin order to simulate the data of a channel,i=1,2,…,m，mthe total number of analog channel data is represented, and the analog channel data is 2-byte data in a two's complement format.
Further, the analysis layer comprises a fault feature extraction module and a fault research and judgment module; the fault feature extraction module is used for extracting corresponding fault features from the fault case waveform library by using a first half-wave method, a phase asymmetry method and a zero sequence power method respectively; the fault judging module is used for carrying out fault judgment by using a first half-wave method, a phase asymmetry method and a zero sequence power method according to the extracted fault characteristics and outputting a judging result; the determination result includes a flag indicating whether or not a ground fault has occurred.
Further, the analysis layer further comprises a data classification module for dividing the data in the fault case waveform library into a marked data set and a unmarked data set according to the extracted fault characteristics and the output research and judgment result; the marked data set comprises a plurality of fault waveform data with fault characteristics and fault labels, and the unmarked data set comprises a plurality of fault waveform data lacking at least one of the fault characteristics and the fault labels; the data set splitting module is used for splitting fault waveform data in the labeled data set into a training set and a testing set; the classifier training module is used for training the classifier by utilizing fault waveform data in the training set; the label-free data classification module is used for classifying fault waveform data in the label-free data set by using a trained classifier, calculating class labels corresponding to each fault waveform data, and taking the class label corresponding to the fault waveform data with the highest classification accuracy as a pseudo label; the data association module is used for associating the fault waveform data with the pseudo tag with the marked data set to obtain a new data set; the secondary training module is used for carrying out secondary training on the classifier by utilizing the data in the new data set; the marked data classification module is used for classifying fault waveform data in the marked data set by using a classifier obtained after secondary training.
Further, the application layer comprises a waveform splicing module, which is used for splicing a plurality of continuous fault waveform data of the same data source to obtain a file containing the continuous fault waveform data; the self-healing fault judging module is used for judging whether a ground fault occurs according to continuous fault waveform data to judge; the judging result checking module is used for checking whether the judging result output by the analysis layer is consistent with the SOE message of the secondary fusion switch; the fault line distribution statistics module is used for carrying out daily, monthly, quaternary and annual fault frequency statistics on each 10kV power distribution line according to the research and judgment result output by the analysis layer and the verification result output by the research and judgment result verification module to obtain fault frequency distribution results of each 10kV power distribution line under different time scales; the fault characteristic distribution statistics module is used for obtaining a zero-sequence voltage distribution result according to each fault waveform data, setting a wave recording starting fixed value according to the zero-sequence voltage distribution result, obtaining a zero-sequence current distribution result and a box diagram respectively according to each fault waveform data, and judging whether the transformer substation is a neutral point and is not grounded according to the zero-sequence current distribution result and the box diagram respectively.
Further, the waveform splicing module comprises a discrete waveform data extraction unit for extracting a plurality of discrete fault waveform data of the same data source; a plurality of discrete fault data are continuous in a time dimension; the CFG file parameter extraction unit is used for extracting channel definition fields and transformation ratio parameter fields of all simulation channels from the CFG configuration file where the fault waveform data are located according to each piece of discrete fault waveform data to obtain a parameter list, and checking the parameter list; the sampling point parameter configuration correcting unit is used for correcting the sampling point parameter configuration according to the CFG configuration file format according to the verified parameter list; and the fault waveform data writing unit is used for writing the rest fault waveform data in the parameter list in the DAT file of the first fault waveform data in the verified parameter list in a binary mode according to the DAT file format of the COMTRADE.
Further, the self-healing fault judging module comprises a first self-healing fault judging unit, a second self-healing fault judging unit and a third self-healing fault judging unit, wherein the first self-healing fault judging unit is used for extracting fault characteristics in the front period and the rear period of the corresponding moment of the wave recording point in a mode of combining a sliding time window with a first half-wave method, a phase asymmetry method and a zero sequence power method respectively according to continuous fault waveform data, and judging whether a self-healing ground fault occurs according to the extracted fault characteristics; the second self-healing fault research judging unit is used for extracting zero-sequence voltage fundamental wave effective values corresponding to the wave head, the wave middle and the wave tail respectively from fault waveform data, comparing the zero-sequence voltage fundamental wave effective values of the wave head with the zero-sequence voltage fundamental wave effective values of the wave tail, comparing the zero-sequence voltage fundamental wave effective values in the wave with the zero-sequence voltage fundamental wave effective values of the wave head or the zero-sequence voltage fundamental wave effective values of the wave tail, and judging whether the self-healing ground fault occurs according to the comparison result.
Further, the judging result checking module comprises an SOE message extracting unit, which is used for extracting an action SOE message of a secondary fusion complete switch from the power distribution automation master station and correlating the extracted SOE message with fault waveform data of corresponding time; the data comparison unit is used for extracting a ground fault signal and a switch remote signaling signal from the SOE message, comparing the research and judgment result output by the analysis layer with the ground fault signal and the switch remote signaling signal respectively, and judging whether the research and judgment result output by the analysis layer is consistent with the SOE message or not according to the comparison result.
Further, the fault characteristic distribution statistics module comprises a zero sequence voltage statistics unit, which is used for descending order of the zero sequence voltage distribution according to each fault waveform data to obtain a voltage descending order chart; the box diagram statistics unit is used for carrying out box diagram statistics according to the fault waveform data; the zero sequence voltage duty ratio statistics unit is used for acquiring corresponding zero sequence voltages according to the box diagram statistics result and acquiring duty ratios of the zero sequence voltages corresponding to the box diagram statistics result in the voltage descending order chart; the setting unit of the recording starting constant value is used for determining the recording starting constant value according to the duty ratio; the zero sequence current statistics unit is used for descending and arranging the distribution of the zero sequence current according to the waveform data of each fault to obtain a current descending and ordering diagram; the zero sequence current duty ratio statistics unit is used for acquiring the duty ratio of the zero sequence current larger than 10A; and the grounding mode judging unit is used for judging whether the transformer substation is in a neutral point ungrounded mode according to the duty ratio of the zero sequence current larger than 10A.
Compared with the prior art, the invention has the following advantages and beneficial effects: and a three-layer analysis architecture is adopted, and three-layer progressive modes of integrating data layers with different sources, an analysis layer for fault data analysis and an application layer for generating and scientific research pushing analysis results are established. Secondly, the simulation waveforms compatible with different simulation platforms and the simulation waveforms of true tests are considered in the data layer, and a specific implementation mode of various waveform data conversion by taking COMTRADE as a standard data format is provided; further, in an analysis layer, objective research and judgment results are provided by methods such as a first half-wave method and a phase asymmetry method which inherit the existing main stream, and a ground fault identification model which introduces semi-supervised learning is provided. Further, in an application layer, self-healing fault research and judgment, consistency verification of the research and judgment result and an SOE message, distribution statistics of fault characteristics and line fault distribution statistics are carried out according to the research and judgment result, and analysis results are output, so that the problems that an existing single-phase earth fault treatment technology is free of on-site data support, a line selection technology and on-site actions are disjoint and the like can be avoided, construction and deployment of a single-phase earth fault platform system of a power distribution network are promoted, single-phase earth faults can be better, faster and more conveniently treated in a production line, and the problem that the prior art cannot conduct centralized management and efficient utilization on a large number of fault waveform data can be effectively solved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an overall architecture of a three-layer analysis system for ground fault with multiple sources according to an embodiment of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Fig. 1 is a schematic diagram of an overall architecture of a three-layer analysis system for multi-source ground fault, which includes a data layer, an analysis layer and an application layer.
1. Data layer
The data layer is used for collecting fault waveform data from the GIS true test platform, fault waveform data from a plurality of simulation platforms, fault waveform data from a plurality of power distribution terminal devices and self-defined fault waveform data, and a fault case waveform library is established according to the collected fault waveform data.
Because the established fault case waveform library contains fault waveform data from a true test platform, a PSCAD electromagnetic transient simulation system and an RTDS real-time digital simulation system, the mutual conversion between the fault waveform data is required to be realized. Correspondingly, the data layer comprises a data conversion module, which is used for carrying out data conversion among fault waveform data output by the PSCAD electromagnetic transient simulation system, fault waveform data output by the RTDS real-time digital simulation system and fault waveform data output by the GIS true test platform according to the standard COMTRADE data format, and storing the fault waveform data of the standard COMTRADE data format obtained after conversion.
It should be noted that, in this embodiment, the bridge for implementing data conversion between the PSCAD data, the RTDS data, and the fault waveform data output by the GIS true test platform is in the standard COMTRADE data format. The format conversion principle between the fault waveform data output by PSCAD and the standard COMTRADE data is as follows:
first, in units of substations, sets of electrical outputs of faulty and non-faulty lines are defined, each set containing a-phase voltagesB-phase voltage->C-phase voltage->Zero sequence voltage->Phase A current- >B phase current->C phase current->And zero sequence current->And each set defines index sets according to the total number of 10kV distribution lines of the transformer substation>，/>Wherein N is the total number of 10kV lines, +.>Corresponding->Electrical quantity output set of 10kV distribution line, ">；
And then outputting the sets one by one to a text file according to the sequence, and recording system parameters and electric channel data. Wherein the system parameters include simulation step sizesDuration of simulation/>And drawing step->The electrical channel data comprises electrical signals of all lines in all substations; the electrical signals described herein are data in the electrical quantity output set.
Finally, according to the format of the standard COMTRADE data, the conversion between the PSCAD output file and the COMTRADE is established, mainly as two base files (CFG file and DAT file) surrounding the COMTRADE data. On the one hand, for CFG files, the basis is thatCalculate the sampling frequency +.>Sum data pointsMThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>，/>，/>. In addition, considering the simulation as an actual signal, the conversion between the secondary transformation ratios is required to adapt the waveform data to the secondary fused sleeve column breaker according to the addition of the secondary signal. The transformation rule of the transformation ratio signal is as follows: phase currents scale at 600:5 and 600:1, zero sequence currents scale at 20:1, line voltages scale at 10000:100, and zero sequence voltages scale at (10000:sqrt (3))/(100/3) and (10000:sqrt (3))/(6.5/3), respectively. Further, will- >、/>And scaling the configuration text of the transformation ratio output to the COMTRADEDesignated locations in the member CFG. On the other hand, according to the DAT file, the data in the electric quantity output set are subjected to sampling number and analog channel sampling data conversion according to the DAT format requirement. The conversion rule is as follows: sample numbers and time stamps, each stored in a 4 byte, unsigned binary format; the analog channel samples data, each data is stored in a 2 byte, two's complement format, e.g., data 0 is stored as hexadecimal 0000, -1 is stored as FFPF, the maximum positive value is 7FFF, the maximum negative value is stored as 8001, and hexadecimal 8000. On the basis of two, the data of each set are converted in such a way that +.>Wherein n is a sampling number, is an integer type, has a minimum length of 4 bytes and a maximum length of 4 bytes; time is a time scale in microseconds; />、/>The data are analog channel data, the data are continuously displayed by taking 2 bytes as a unit, the maximum length and the minimum length are 2 bytes, and if the conversion fails, the value range is assigned by 8000 according to the COMTRADE rule.
According to the above principle, to achieve conversion between the failure waveform data format of the PSCAD output and the standard COMTRADE data format, the PSCAD-GIS data conversion submodule of the present embodiment includes:
The electric quantity output set generating unit is used for generating an electric quantity output set corresponding to each 10kV distribution line in each transformer substation according to fault waveform data output by the PSCAD electromagnetic transient simulation system; the data in the electrical quantity output set comprises A-phase voltageB-phase voltage->C-phase voltage->Zero sequence voltage->Phase A current->B phase current->C phase current->And zero sequence current->。
The index set generation unit is used for summarizing a plurality of electric quantity output sets corresponding to the transformer substation according to the total number of the 10kV distribution lines in the transformer substation to generate an index set；/>Wherein N represents the total number of 10kV distribution lines in the substation, < >>Corresponding->Electrical quantity output set of 10kV distribution line, ">。
A text file generating unit for gathering the indexesIs +.>Outputting to text file, and recording electric channel data and PSCAD electricityMagnetic transient simulation system parameters; the electrical channel data includes +/each electrical quantity output set>The system parameters include simulation step size ∈>Simulation duration->And drawing step->。
CFG file conversion unit for drawing step lengthAcquisition of sampling frequency->And the data point number M, obtaining the scaling transformation ratio of the PSCAD electromagnetic transient simulation system when performing secondary transformation ratio conversion, and obtaining the sampling frequency +. >The number of data points M and the scaling ratio are output to specified locations in the COMTRADE profile CFG.
DAT file conversion unit for converting the data in the text file into a text file according to the dataPerforming data conversion in an arrangement mode; wherein,nthe number of samples is indicated and,timerepresenting a time scale, wherein the sampling number and the time scale are 4 bytes of unsigned binary data;Aiin order to simulate the data of a channel,i=1,2,…,m，mthe total number of analog channel data is represented, and the analog channel data is 2-byte data in a two's complement format.
In addition, for fault data of a massive secondary integrated complete switch and a true test, the recording starting function of the switch equipment can be directly adopted to directly store the fault data in a COMTRADE file, and the digital waveform and the COMTRADE conversion of a simulation platform are not required to be complicated.
Correspondingly, the data layer of the embodiment further comprises a data storage module, which is used for enabling the wave recording starting function, and storing the fault waveform data from the GIS true test platform and the fault waveform data from the plurality of power distribution terminal devices directly in a standard COMTRADE data format.
2. Analytical layer
The analysis layer is used for integrating a plurality of fault judging methods, extracting fault characteristics from the fault case waveform library by utilizing each fault judging method respectively, and carrying out fault judgment according to each fault judging method respectively by combining the extracted fault characteristics to obtain judging results. The fault judging method comprises a first half-wave method, a phase asymmetry method and a zero sequence power method.
The analysis layer comprises a fault feature extraction module. The fault feature extraction module is used for extracting corresponding fault features from the fault case waveform library by using a first half-wave method, a phase asymmetry method and a zero sequence power method respectively. Furthermore, the fault feature extraction module of the embodiment can also establish weights for the results of various algorithms by combining expert experience method, voting method and other methods, and finally, comprehensive research and judgment are performed by using a weighting method.
Besides the fault feature extraction module, the analysis layer further comprises a fault research and judgment module, a data classification module, a data set splitting module, a classifier training module, a label-free data classification module, a data association module, a secondary training module and a label data classification module.
The fault judging module is used for carrying out fault judgment by using a first half-wave method, a phase asymmetry method and a zero sequence power method according to the extracted fault characteristics, and outputting a judging result; the determination result includes a flag indicating whether or not a ground fault has occurred.
The data classification module is used for dividing the data in the fault case waveform library into a marked data set and a unmarked data set according to the extracted fault characteristics and the output research and judgment result; the marked dataset includes a plurality of fault waveform data having fault signatures and fault signatures, and the unmarked dataset includes a plurality of fault waveform data lacking at least one of the fault signatures and fault signatures.
The data set splitting module is used for splitting fault waveform data in the labeled data set into a training set and a testing set.
The classifier training module is used for training the classifier by using fault waveform data in the training set.
The unmarked data classification module is used for classifying fault waveform data in the unmarked data set by using a trained classifier, calculating class labels corresponding to each fault waveform data, and taking the class label corresponding to the fault waveform data with the highest classification accuracy as a pseudo label.
The data association module is used for associating the fault waveform data with the pseudo tag with the marked data set to obtain a new data set.
The secondary training module is used for carrying out secondary training on the classifier by utilizing the data in the new data set.
The marked data classification module is used for classifying fault waveform data in the marked data set by using a classifier obtained after secondary training.
For each functional module of the analysis layer, it should be noted that: the present embodiment considers the following cases:
first case: the difference of the research and judgment logics of different algorithms is large, and the production line is difficult to use. For this case, the present embodiment adopts the intelligent analysis mode.
Second case: the live real-recorded waveform is difficult to construct standard and complete ground fault data due to a plurality of possible anomalies such as abnormal file channels, incorrect configuration files, abnormal frequency sampling points, incomplete waveform data and the like.
Third case: the ground fault waveforms exist primarily in CFG files and DAT files.
For the second case and the third case, although the judging result can provide a fault or not label, if the label is correct or not, only the initial label can be provided for intelligent learning, if the label is unreliable, the intelligent algorithm is easy to lead dirty data to sink into learning low-lying. Therefore, in the intelligent learning stage, under the premise of considering the lack of part fault characteristics and fault labels, the semi-supervised learning is integrated, and the ground fault semi-supervised learning step adapting to the technical field of the invention comprises five links:
link 1: waveforms of various data sources related to various types of ground faults are divided into marked data (feature clear and tag clear) and unmarked data (feature clear or tag missing). Link 2: dividing the marked fault characteristic data instance into a training set and a testing set, and carrying out classified learning training on the marked training data by combining a classified learner. Link 3: and (3) classifying by combining the trained classifier in the second link, predicting all unlabeled data, calculating class labels, and recognizing the label with highest accuracy as a pseudo label. Link 4: the pseudo tag data and correctly labeled training data are concatenated and the training data is obtained at the combined pseudo tag and correct label to retrain the classifier. Link 5: and predicting class labels of marked test data examples by using the ground fault classifier trained in the link 4, and introducing a measurement index of classification evaluation performance to judge the learning performance of the current ground fault learning model.
3. Application layer
The application layer is mainly used for pushing the research and judgment result, carrying out self-healing fault research and judgment according to the research and judgment result, carrying out consistency check on the research and judgment result and the SOE message, carrying out distributed statistics on fault characteristics and carrying out line fault distributed statistics, and outputting an analysis result. On the one hand, the analysis result can serve a production line, guide production, set an optimal wave recording starting threshold, set an optimal judging algorithm and autonomously analyze the doubtful waveform, and can improve inspection efficiency, guide quick rush repair and enhance professional ability; on the other hand, the system can support scientific research, and can construct a rich fault case library and a fault characteristic engineering library, thereby establishing a ground fault research and judgment platform of the power distribution main station and constructing a sound and uniform comprehensive research and judgment system for the power distribution network faults according to the idea.
The application layer comprises a waveform splicing module, a self-healing fault studying and judging module, a studying and judging result checking module, a fault line distribution statistical module and a fault characteristic distribution statistical module.
The waveform splicing module is used for splicing a plurality of continuous fault waveform data of the same data source to obtain a file containing the continuous fault waveform data. Specifically, since the current ground fault waveform stores only 12 cycles of data in a mode of four front and eight back, the present embodiment adopts a waveform "splicing" mode, and connects a plurality of discrete waveform files on the same time scale through a waveform splicing module, and the main steps include S1: and automatically arranging a plurality of discrete wave recording files of the same equipment in continuous time. S2: and extracting two types of fields, namely a characterization channel definition and a transformation ratio parameter of each analog channel in the CFG configuration file of each discrete wave recording file, forming a list, carrying out repeatability verification, sequence and quantity consistency verification, and switching to S3 if the two types of fields meet the requirement. S3: and correcting the parameter configuration of the sampling points according to the CFG configuration file of the COMTRADE. S4: and writing the recording data of the other files in the DAT file of the first recording file step by step in a binary mode according to the DAT file format of the COMTRADE.
According to the principle related to the waveform splicing module, the corresponding waveform splicing module comprises a discrete waveform data extraction unit for extracting a plurality of discrete fault waveform data of the same data source; a plurality of discrete fault data are continuous in a time dimension; the CFG file parameter extraction unit is used for extracting channel definition fields and transformation ratio parameter fields of all simulation channels from the CFG configuration file where the fault waveform data are located according to each piece of discrete fault waveform data to obtain a parameter list, and checking the parameter list; the sampling point parameter configuration correcting unit is used for correcting the sampling point parameter configuration according to the CFG configuration file format according to the verified parameter list; and the fault waveform data writing unit is used for writing the rest fault waveform data in the parameter list in the DAT file of the first fault waveform data in the verified parameter list in a binary mode according to the DAT file format of the COMTRADE.
Further, the self-healing fault judging module is used for judging whether the ground fault occurs according to the continuous fault waveform data to judge. It should be noted that, according to the spliced long-time scale wave recording file, the method is combined with multiple types of methods in the analysis layer to perform group study and judgment, and different starting wave recording points are gradually shifted by introducing a sliding time window mode, fault characteristics are extracted by two cycles near the corresponding moment of the wave recording points, whether the grounding fault characteristics are presented is judged, if the grounding fault characteristics are different from front to back, the grounding fault is represented to be transient, namely, the grounding fault belongs to self-healing grounding fault, and the on-site investigation of an allocation and transportation group is not needed, so that the labor cost is reduced; in addition, the zero sequence voltage channels in the fault waveform can be combined, the effective values of the zero sequence voltage fundamental waves of the waveform wave head, the wave middle and the wave tail are respectively extracted, the difference between the wave head and the wave tail is judged, and if the difference is less than 5% of the initial value of the wave head or 0.05% of the effective value of the normal phase voltage; and the effective value of the zero sequence voltage fundamental wave in the wave is obviously different from one of the wave head or the wave tail, so that the fault is represented to be self-healing.
According to the principle related to the self-healing fault research and judgment module, the corresponding self-healing fault research and judgment module comprises a first self-healing fault research and judgment unit, which is used for extracting fault characteristics in the front and rear two periods of corresponding time of a wave recording point in a mode of combining a sliding time window with a first half-wave method, a phase asymmetry method and a zero sequence power method respectively according to continuous fault waveform data, and judging whether a self-healing ground fault occurs according to the extracted fault characteristics; the second self-healing fault research judging unit is used for extracting zero-sequence voltage fundamental wave effective values corresponding to the wave head, the wave middle and the wave tail respectively from fault waveform data, comparing the zero-sequence voltage fundamental wave effective values of the wave head with the zero-sequence voltage fundamental wave effective values of the wave tail, comparing the zero-sequence voltage fundamental wave effective values in the wave with the zero-sequence voltage fundamental wave effective values of the wave head or the zero-sequence voltage fundamental wave effective values of the wave tail, and judging whether the self-healing ground fault occurs according to the comparison result.
Further, the judging result checking module is used for checking whether the judging result output by the analysis layer is consistent with the SOE message of the secondary fusion switch. It should be noted that, a secondary integrated complete switch action SOE message is extracted from the distribution automation master station, and is associated with the fault waveform under the time section, according to the research and judgment results of various algorithms in step S3, the total grounding accident signal and the switch remote signaling signal in the SOE message are extracted and compared with the research and judgment results, whether the specific behavior associated with the research and judgment results is met is judged, if the specific behavior is met, the specific behavior is checked by the consistency outlet, and if the specific behavior is met, the specific behavior is correct. The check closed loop is introduced into the research and judgment system, so that the possibility of frequent false tripping or refusal of the on-site switch can be reduced.
According to the principle about the research and judgment result verification module, the corresponding research and judgment result verification module comprises an SOE message extraction unit, which is used for extracting an action SOE message of a secondary fusion complete switch from a power distribution automation main station and correlating the extracted SOE message with fault waveform data of corresponding time; the data comparison unit is used for extracting a ground fault signal and a switch remote signaling signal from the SOE message, comparing the research and judgment result output by the analysis layer with the ground fault signal and the switch remote signaling signal respectively, and judging whether the research and judgment result output by the analysis layer is consistent with the SOE message or not according to the comparison result.
Further, the fault line distribution statistics module is used for carrying out statistics on the fault frequency of each 10kV power distribution line day, month, season and year according to the research and judgment result output by the analysis layer and the verification result output by the research and judgment result verification module, so as to obtain the fault frequency distribution result of each 10kV power distribution line under different time scales. The fault characteristic distribution statistics module is used for obtaining a zero-sequence voltage distribution result according to each fault waveform data, setting a wave recording starting fixed value according to the zero-sequence voltage distribution result, obtaining a zero-sequence current distribution result and a box diagram respectively according to each fault waveform data, and judging whether the transformer substation is a neutral point and is not grounded according to the zero-sequence current distribution result and the box diagram respectively.
And converging fault waveforms of the secondary fused complete switch installed in different city companies, counting the research and judgment results of various methods through an analysis layer, and combining the verification results of the research and judgment result verification module to obtain a reliable ground fault research and judgment result. According to the result, the fault frequency statistics of the day, month, season and year is carried out on each 10kV distribution line of each local city company, the distribution of each line under each time scale is analyzed, and important patrol and important prevention are carried out on important transportation and inspection team personnel according to the concentrated time period with higher frequency; secondly, counting fault characteristic distribution, especially zero sequence voltage, of each ground-to-earth fault waveform, performing descending order according to the zero sequence voltage distribution, performing box diagram statistics, obtaining corresponding zero sequence voltage according to a box with higher occupation, calculating a specific proportion of the corresponding zero sequence voltage to the value in the descending order diagram, and if the value is greater than 90%, setting a wave recording starting fixed value according to the value; and finally, counting zero sequence current distribution of each ground fault waveform, carrying out box line diagram distribution, judging and obtaining the duty ratio larger than 10A, further judging whether the transformer substation corresponding to the line is in a neutral point ungrounded mode, if so, indicating that the distribution network operation rule is not satisfied, and guiding the transformer substation to carry out distribution network reconstruction closed loop.
Correspondingly, the fault characteristic distribution statistics module comprises a zero sequence voltage statistics unit, and is used for descending order of the zero sequence voltage distribution according to each fault waveform data to obtain a voltage descending order chart; the box diagram statistics unit is used for carrying out box diagram statistics according to the fault waveform data; the zero sequence voltage duty ratio statistics unit is used for acquiring corresponding zero sequence voltages according to the box diagram statistics result and acquiring duty ratios of the zero sequence voltages corresponding to the box diagram statistics result in the voltage descending order chart; the setting unit of the recording starting constant value is used for determining the recording starting constant value according to the duty ratio; the zero sequence current statistics unit is used for descending and arranging the distribution of the zero sequence current according to the waveform data of each fault to obtain a current descending and ordering diagram; the zero sequence current duty ratio statistics unit is used for acquiring the duty ratio of the zero sequence current larger than 10A; and the grounding mode judging unit is used for judging whether the transformer substation is in a neutral point ungrounded mode according to the duty ratio of the zero sequence current larger than 10A.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A three-layer type studying and judging analysis system for multi-source ground faults is characterized by comprising
The data layer is used for collecting fault waveform data from the GIS true test platform, fault waveform data from a plurality of simulation platforms, fault waveform data from a plurality of power distribution terminal devices and self-defined fault waveform data, and a fault case waveform library is established according to the collected fault waveform data;
the analysis layer is used for integrating a plurality of fault judging methods, extracting fault characteristics from the fault case waveform library by utilizing each fault judging method respectively, and carrying out fault judgment according to each fault judging method respectively by combining the extracted fault characteristics to obtain judging results; the multiple fault judging methods comprise a first half-wave method, a phase asymmetry method and a zero sequence power method;
the application layer is used for carrying out self-healing fault research and judgment according to the research and judgment result, checking the consistency of the research and judgment result and the SOE message, carrying out distributed statistics of fault characteristics and carrying out distributed statistics of line faults, and outputting an analysis result;
wherein, the application layer includes:
the waveform splicing module is used for splicing a plurality of continuous fault waveform data from the same data source to obtain a file containing the continuous fault waveform data;
The self-healing fault judging module is used for judging whether a ground fault occurs according to continuous fault waveform data to judge;
the judging result checking module is used for checking whether the judging result output by the analysis layer is consistent with the SOE message of the secondary fusion switch;
the self-healing fault research and judgment module comprises:
the first self-healing fault research judging unit is used for extracting fault characteristics in the front and rear two periods of the corresponding moment of the wave recording point in a mode of combining a sliding time window with a first half-wave method, a phase asymmetry method and a zero sequence power method respectively according to continuous fault waveform data, and judging whether a self-healing ground fault occurs according to the extracted fault characteristics;
the second self-healing fault research judging unit is used for extracting zero-sequence voltage fundamental wave effective values corresponding to the wave head, the wave middle and the wave tail respectively from fault waveform data, comparing the zero-sequence voltage fundamental wave effective value of the wave head with the zero-sequence voltage fundamental wave effective value of the wave tail, comparing the zero-sequence voltage fundamental wave effective value in the wave with the zero-sequence voltage fundamental wave effective value of the wave head or the zero-sequence voltage fundamental wave effective value of the wave tail, and judging whether a self-healing ground fault occurs according to a comparison result;
The judging result checking module comprises:
the SOE message extraction unit is used for extracting an action SOE message of a secondary fusion complete switch from the distribution automation master station and correlating the extracted SOE message with fault waveform data of corresponding time;
the data comparison unit is used for extracting a ground fault signal and a switch remote signaling signal from the SOE message, comparing the research and judgment result output by the analysis layer with the ground fault signal and the switch remote signaling signal respectively, and judging whether the research and judgment result output by the analysis layer is consistent with the SOE message or not according to the comparison result.
2. The three-layer analysis system for ground faults in multiple sources of claim 1 in which,
the simulation platforms comprise a PSCAD electromagnetic transient simulation system and an RTDS real-time digital simulation system;
the data layer comprises a data conversion module and a data storage module;
the data conversion module is used for carrying out data conversion among fault waveform data output by the PSCAD electromagnetic transient simulation system, fault waveform data output by the RTDS real-time digital simulation system and fault waveform data output by the GIS true test platform according to a standard COMTRADE data format, and storing the fault waveform data in the standard COMRADE data format obtained after conversion;
The data storage module is used for starting the wave recording starting function and directly storing fault waveform data from the GIS true test platform and fault waveform data from the plurality of power distribution terminal equipment in a standard COMTRADE data format.
3. The three-layer type ground fault oriented analysis system of claim 2, wherein the data conversion module comprises a PSCAD-GIS data conversion sub-module; the PSCAD-GIS data conversion submodule comprises:
the electric quantity output set generating unit is used for generating an electric quantity output set corresponding to each 10kV distribution line in each transformer substation according to fault waveform data output by the PSCAD electromagnetic transient simulation system; the data in the electrical quantity output set comprises A-phase voltageB-phase voltage->C-phase voltage->Zero sequence voltage->Phase A current->B phase current->C phase current->And zero sequence current->；
The index set generation unit is used for summarizing a plurality of electric quantity output sets corresponding to the transformer substation according to the total number of the 10kV distribution lines in the transformer substation to generate an index set；/>Wherein N represents the total number of 10kV distribution lines in the substation, < >>Corresponding->The electrical quantity output set of the 10kV distribution line, ；
A text file generating unit for gathering the indexesIs +.>Outputting the data to a text file, and recording the electrical channel data and the system parameters of the PSCAD electromagnetic transient simulation system; the electrical channel data includes +/each electrical quantity output set>The system parameters include simulation step size ∈>Simulation duration->And drawing step->；
CFG file conversion unit for drawing step lengthAcquisition of sampling frequency->And the data point number M, obtaining the scaling transformation ratio of the PSCAD electromagnetic transient simulation system when performing secondary transformation ratio conversion, and obtaining the sampling frequency +.>Outputting the data points M and the scaling transformation ratio to a designated position in the COMTRADE configuration file CFG;
DAT file conversion unit for converting the data in the text file into a text file according to the dataPerforming data conversion in an arrangement mode; wherein,nthe number of samples is indicated and,timerepresenting a time scale, wherein the sampling number and the time scale are 4 bytes of unsigned binary data;Aiin order to simulate the data of a channel,i=1,2,…,m，mthe total number of analog channel data is represented, and the analog channel data is 2-byte data in a two's complement format.
4. The three-layer analysis system for ground faults in multiple sources of claim 1 in which,
The analysis layer comprises a fault feature extraction module and a fault research and judgment module;
the fault feature extraction module is used for extracting corresponding fault features from the fault case waveform library by using a first half-wave method, a phase asymmetry method and a zero sequence power method respectively;
the fault judging module is used for carrying out fault judgment by using a first half-wave method, a phase asymmetry method and a zero sequence power method according to the extracted fault characteristics and outputting a judging result; the determination result includes a flag indicating whether or not a ground fault has occurred.
5. The multi-source ground fault oriented three-layer analysis system of claim 4, wherein the analysis layer further comprises:
the data classification module is used for dividing the data in the fault case waveform library into a marked data set and a unmarked data set according to the extracted fault characteristics and the output research and judgment result; the marked data set comprises a plurality of fault waveform data with fault characteristics and fault labels, and the unmarked data set comprises a plurality of fault waveform data lacking at least one of the fault characteristics and the fault labels;
the data set splitting module is used for splitting fault waveform data in the labeled data set into a training set and a testing set;
The classifier training module is used for training the classifier by utilizing fault waveform data in the training set;
the label-free data classification module is used for classifying fault waveform data in the label-free data set by using a trained classifier, calculating class labels corresponding to each fault waveform data, and taking the class label corresponding to the fault waveform data with the highest classification accuracy as a pseudo label;
the data association module is used for associating the fault waveform data with the pseudo tag with the marked data set to obtain a new data set;
the secondary training module is used for carrying out secondary training on the classifier by utilizing the data in the new data set;
the marked data classification module is used for classifying fault waveform data in the marked data set by using a classifier obtained after secondary training.
6. A multi-source ground fault oriented three-layer analysis system as claimed in claim 3 wherein the application layer further comprises:
the fault line distribution statistics module is used for carrying out statistics on the fault frequency of each 10kV power distribution line in days, months, seasons and years according to the research and judgment result output by the analysis layer and the verification result output by the research and judgment result verification module to obtain the fault frequency distribution result of each 10kV power distribution line in different time scales;
The fault characteristic distribution statistics module is used for obtaining a zero-sequence voltage distribution result according to each fault waveform data, setting a wave recording starting fixed value according to the zero-sequence voltage distribution result, obtaining a zero-sequence current distribution result and a box diagram respectively according to each fault waveform data, and judging whether the transformer substation is a neutral point and is not grounded according to the zero-sequence current distribution result and the box diagram respectively.
7. The three-layer analysis system for multi-source ground fault as claimed in claim 6, wherein the waveform stitching module comprises
A discrete waveform data extraction unit for extracting a plurality of discrete fault waveform data of the same data source; a plurality of discrete fault data are continuous in a time dimension;
the CFG file parameter extraction unit is used for extracting channel definition fields and transformation ratio parameter fields of all simulation channels from the CFG configuration file where the fault waveform data are located according to each piece of discrete fault waveform data to obtain a parameter list, and checking the parameter list;
the sampling point parameter configuration correcting unit is used for correcting the sampling point parameter configuration according to the CFG configuration file format according to the verified parameter list;
And the fault waveform data writing unit is used for writing the rest fault waveform data in the parameter list in the DAT file of the first fault waveform data in the verified parameter list in a binary mode according to the DAT file format of the COMTRADE.
8. The three-layer analysis system for ground fault of multiple sources as set forth in claim 6, wherein the fault signature distribution statistics module comprises
The zero sequence voltage statistics unit is used for descending and arranging the zero sequence voltage distribution according to the fault waveform data to obtain a voltage descending and ordering diagram;
the box diagram statistics unit is used for carrying out box diagram statistics according to the fault waveform data;
the zero sequence voltage duty ratio statistics unit is used for acquiring corresponding zero sequence voltages according to the box diagram statistics result and acquiring duty ratios of the zero sequence voltages corresponding to the box diagram statistics result in the voltage descending order chart;
the setting unit of the recording starting constant value is used for determining the recording starting constant value according to the duty ratio;
the zero sequence current statistics unit is used for descending and arranging the distribution of the zero sequence current according to the waveform data of each fault to obtain a current descending and ordering diagram;
the zero sequence current duty ratio statistics unit is used for acquiring the duty ratio of the zero sequence current larger than 10A;
And the grounding mode judging unit is used for judging whether the transformer substation is in a neutral point ungrounded mode according to the duty ratio of the zero sequence current larger than 10A.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473340.1A CN117250439B (en) | 2023-11-08 | 2023-11-08 | Three-layer type studying and judging analysis system for multi-source ground fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473340.1A CN117250439B (en) | 2023-11-08 | 2023-11-08 | Three-layer type studying and judging analysis system for multi-source ground fault |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117250439A CN117250439A (en) | 2023-12-19 |
| CN117250439B true CN117250439B (en) | 2024-01-30 |
Family
ID=89135294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311473340.1A Active CN117250439B (en) | 2023-11-08 | 2023-11-08 | Three-layer type studying and judging analysis system for multi-source ground fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117250439B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006025870A2 (en) * | 2004-08-26 | 2006-03-09 | Springbok Incorporated | Method of precisely determining the location, and validity of a fault on an electrical transmission system |
| EP2033316A2 (en) * | 2006-06-21 | 2009-03-11 | Element CXI, LLC | Fault tolerant integrated circuit architecture |
| JP2011196701A (en) * | 2010-03-17 | 2011-10-06 | Hitachi Ltd | Device and system for detecting minute ground fault |
| CN104123675A (en) * | 2013-04-27 | 2014-10-29 | 国家电网公司 | Power distribution network simulation research and analysis system and method based on network-wide data |
| CN108132425A (en) * | 2017-12-18 | 2018-06-08 | 云南电网有限责任公司电力科学研究院 | Power grid distribution line failure on-line monitoring method and system |
| CN109557423A (en) * | 2019-01-22 | 2019-04-02 | 山东大学 | A kind of Fault Diagnosis of Distribution Network system, method and application |
| CN109813999A (en) * | 2019-01-22 | 2019-05-28 | 山东大学 | A kind of Fault Diagnosis of Distribution Network algorithm automatically testing platform, method and application |
| CN110865997A (en) * | 2019-11-08 | 2020-03-06 | 国网四川省电力公司电力科学研究院 | Online identification method for hidden danger of power system equipment and application platform thereof |
| CN112054596A (en) * | 2020-09-09 | 2020-12-08 | 国网信通亿力科技有限责任公司 | System and method for acquiring running data of power distribution network in real time |
| CN112213592A (en) * | 2020-11-10 | 2021-01-12 | 珠海欧力配网自动化股份有限公司 | Distributed terminal double-loop network self-healing transfer detection system and method thereof |
| CN114028756A (en) * | 2021-11-04 | 2022-02-11 | 浙江泰和智谷科技有限公司 | Intelligent fire fighting system and method based on Internet of things technology |
| WO2022183698A1 (en) * | 2021-03-05 | 2022-09-09 | 国网电力科学研究院武汉南瑞有限责任公司 | Artificial intelligence fault identification system and method based on power transmission line transient waveform |
| CN116359668A (en) * | 2023-03-15 | 2023-06-30 | 国网宁夏电力有限公司银川供电公司 | Power distribution network single-phase earth fault positioning method based on multi-source information comprehensive judgment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10481195B2 (en) * | 2015-12-02 | 2019-11-19 | Machinesense, Llc | Distributed IoT based sensor analytics for power line diagnosis |
| CN106771870A (en) * | 2016-12-26 | 2017-05-31 | 北京国电通网络技术有限公司 | A kind of distribution net work earthing fault localization method and system |
| CN112668164A (en) * | 2020-12-18 | 2021-04-16 | 武汉大学 | Transformer fault diagnosis method and system for inducing ordered weighted evidence reasoning |
-
2023
- 2023-11-08 CN CN202311473340.1A patent/CN117250439B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006025870A2 (en) * | 2004-08-26 | 2006-03-09 | Springbok Incorporated | Method of precisely determining the location, and validity of a fault on an electrical transmission system |
| EP2033316A2 (en) * | 2006-06-21 | 2009-03-11 | Element CXI, LLC | Fault tolerant integrated circuit architecture |
| JP2011196701A (en) * | 2010-03-17 | 2011-10-06 | Hitachi Ltd | Device and system for detecting minute ground fault |
| CN104123675A (en) * | 2013-04-27 | 2014-10-29 | 国家电网公司 | Power distribution network simulation research and analysis system and method based on network-wide data |
| CN108132425A (en) * | 2017-12-18 | 2018-06-08 | 云南电网有限责任公司电力科学研究院 | Power grid distribution line failure on-line monitoring method and system |
| CN109813999A (en) * | 2019-01-22 | 2019-05-28 | 山东大学 | A kind of Fault Diagnosis of Distribution Network algorithm automatically testing platform, method and application |
| CN109557423A (en) * | 2019-01-22 | 2019-04-02 | 山东大学 | A kind of Fault Diagnosis of Distribution Network system, method and application |
| CN110865997A (en) * | 2019-11-08 | 2020-03-06 | 国网四川省电力公司电力科学研究院 | Online identification method for hidden danger of power system equipment and application platform thereof |
| CN112054596A (en) * | 2020-09-09 | 2020-12-08 | 国网信通亿力科技有限责任公司 | System and method for acquiring running data of power distribution network in real time |
| CN112213592A (en) * | 2020-11-10 | 2021-01-12 | 珠海欧力配网自动化股份有限公司 | Distributed terminal double-loop network self-healing transfer detection system and method thereof |
| WO2022183698A1 (en) * | 2021-03-05 | 2022-09-09 | 国网电力科学研究院武汉南瑞有限责任公司 | Artificial intelligence fault identification system and method based on power transmission line transient waveform |
| CN114028756A (en) * | 2021-11-04 | 2022-02-11 | 浙江泰和智谷科技有限公司 | Intelligent fire fighting system and method based on Internet of things technology |
| CN116359668A (en) * | 2023-03-15 | 2023-06-30 | 国网宁夏电力有限公司银川供电公司 | Power distribution network single-phase earth fault positioning method based on multi-source information comprehensive judgment |
Non-Patent Citations (3)
| Title |
|---|
| "基于多源数据的电网及设备状态在线感知与预警关键技术研究";南东亮;《科技成果》;全文 * |
| "基于多源暂稳态信息的电缆型配电网故障辨识与定位研究";彭楠;《中国优秀硕士学位论文全文数据库》;第14-104页 * |
| "省级配电自动化主站的停电信息资源池功能设计";冷华;《电力系统自动化》;第150-155页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117250439A (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cui et al. | Enhance high impedance fault detection and location accuracy via $\mu $-PMUs | |
| CN112147462A (en) | Power transmission line fault identification method based on deep learning | |
| CN115932484B (en) | Power transmission line fault identification and fault location method and device and electronic equipment | |
| CN114330097A (en) | Heterogeneous data and deep learning wind power cluster power prediction method and device | |
| CN107844466A (en) | A kind of failure wave-recording file analysis auto-building model system and method | |
| CN106843041A (en) | The anti-error logical formula automation generation system and method for electrical equipment | |
| Blakely et al. | Identifying errors in service transformer connections | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN115186974A (en) | Power distribution network power supply quality comprehensive evaluation method and system based on business middling station | |
| CN112182499B (en) | Low-voltage distribution network topological structure identification method based on time sequence electric quantity data | |
| CN114021425A (en) | Power system operation data modeling and feature selection method and device, electronic equipment and storage medium | |
| CN117250439B (en) | Three-layer type studying and judging analysis system for multi-source ground fault | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN116879672A (en) | Intelligent identification method for total fault of area based on time convolution network | |
| Lima et al. | Hardware and software architecture for power quality analysis | |
| CN116502149A (en) | Low-voltage power distribution network user-transformation relation identification method and system based on current characteristic conduction | |
| CN115587635A (en) | Transformer area line loss analysis method and system based on neutral point deviation judgment | |
| CN115455802A (en) | Low-voltage distribution network modeling based on data driving and visualization method thereof | |
| Yu et al. | Practical method for data-driven user phase identification in low-voltage distribution networks | |
| CN114626433A (en) | Fault prediction and classification method, device and system for intelligent electric energy meter | |
| CN207516464U (en) | A kind of Portable metering automatization terminal trouble-shooter | |
| Medeiros et al. | Network oriented approaches using smart metering data for non-technical losses detection | |
| Zhang et al. | Named Entity Recognition for Smart Grid Operation and Inspection Domain using Attention Mechanism | |
| CN117271375B (en) | Power grid graph modulus test sample generation, maintenance and management method and related device | |
| CN115935264B (en) | Power grid transient voltage stability evaluation method based on space-time information synchronous learning |
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 |