CN117368824A - Current transformer fault diagnosis method, electronic equipment and storage medium - Google Patents
Current transformer fault diagnosis method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117368824A CN117368824A CN202311309493.2A CN202311309493A CN117368824A CN 117368824 A CN117368824 A CN 117368824A CN 202311309493 A CN202311309493 A CN 202311309493A CN 117368824 A CN117368824 A CN 117368824A
- Authority
- CN
- China
- Prior art keywords
- current
- current transformer
- value
- time domain
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 230000009467 reduction Effects 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- 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
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
Abstract
The embodiment of the application provides a fault diagnosis method for a current transformer, electronic equipment and a storage medium, comprising the following steps: calculating each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer; calculating the correlation coefficient r of the current of the secondary side of the current transformer and corresponding time domain statistics of the current transformer under normal and different faults ij The method comprises the steps of carrying out a first treatment on the surface of the According toTime domain statistics and correlation coefficient r of current actual value and predicted value ij Calculating the total characteristic quantity of fault states of the actual value and the predicted value of the current transformer; judging whether the ratio of the current actual value to the total fault state characteristic quantity of the predicted value exceeds a threshold value, if so, the current transformer fails; according to the method, the time domain statistics are calculated after the current data of the current transformer are subjected to LSTM current prediction model and wavelet noise reduction treatment, the influence of special factors on the current transformer in the operation of a power grid is greatly reduced, and the fault diagnosis rate of the current transformer is improved.
Description
Technical Field
The application belongs to the technical field of current transformers, and particularly relates to a fault diagnosis method for a current transformer, electronic equipment and a storage medium.
Background
The current transformer is one of important equipment of a transformer substation, and converts high-voltage side large current into smaller secondary current through the transformer, so that measurement, metering and relay protection are realized. Because the current transformer runs for a long time under severe environments such as high temperature and strong electromagnetic interference, the performance of the element is easy to deteriorate, various faults are caused, the safety of a power grid is threatened, and therefore, the effective diagnosis of the faults of the current transformer is required to be realized.
The current common fault diagnosis methods include a threshold method, a time domain decomposition method, machine learning and the like; the threshold method is largely used because of simple model and clear physical meaning; the threshold method judges whether the equipment is faulty or not by comparing the selected fault state characteristic quantity with the critical value, but the power grid current is influenced by factors such as load change, faults and the like, the fluctuation range is large and is possibly several times of the rated current at maximum, so that the critical value is not easy to select when the threshold method is adopted to realize fault diagnosis of the current transformer; the current can be predicted by adopting a load prediction mode, the current is used as a critical value in a threshold method to realize fault diagnosis of the current transformer, the current prediction accuracy at individual time points can be reduced due to the influence of special factors such as weather mutation, special events, holidays, large user production faults and the like, and the current prediction value is used as the critical value to reduce the diagnosis accuracy. Based on the above, it is necessary to invent a new fault diagnosis method for the current transformer.
Disclosure of Invention
In order to solve one of the technical defects, the embodiment of the application provides a current transformer fault diagnosis method capable of improving the fault diagnosis rate of the current transformer, electronic equipment and a storage medium.
According to a first aspect of an embodiment of the present application, there is provided a fault diagnosis method for a current transformer, including:
calculating each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer;
calculating the correlation coefficient r of the current of the secondary side of the current transformer and corresponding time domain statistics of the current transformer under normal and different faults ij ;
Time domain statistics and correlation coefficient r according to current actual value and predicted value ij Calculating the total characteristic quantity of fault states of the actual value and the predicted value of the current transformer;
and judging whether the ratio of the current actual value to the total fault state characteristic quantity of the predicted value exceeds a threshold value, if so, the current transformer fails.
Preferably, the calculating each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer includes:
collecting outgoing line current data of a transformer substation, and dividing the outgoing line current data into a training set and a testing set;
constructing an LSTM current prediction model;
inputting the current data of the training set into an LSTM current prediction model for training, and obtaining an optimal LSTM current prediction model through a current data test model of the test set;
inputting the current value of the current transformer into an LSTM current prediction model to obtain a predicted value i p 。
Preferably, the calculating each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer includes:
setting faults by the equivalent fault transformation ratio K to obtainTo fault data, recorded as current actual value i r ;
Will predict the value i p And current actual value i r The actual value i of the current after filtering is obtained through wavelet noise reduction treatment rf And predictive value i pf ;
Calculating the actual value i of the current rf Is a time domain statistic of (1);
calculating a predicted value i pf Is a time domain statistic of the (c).
Preferably, the correlation coefficient r of the secondary side current of the current transformer under normal and different faults and corresponding time domain statistics thereof is calculated ij Comprising:
calculating each time domain statistic of the current transformer secondary side normal current history value;
calculating time domain statistics of secondary side currents of the current transformer under different faults;
calculating the correlation coefficient r of the secondary side current of the current transformer and corresponding time domain statistics thereof under normal and different faults according to the formula (1) ij :
In the formula (1), C ov Representing covariance, V ar Representing variance, x ij Each time domain statistic of the secondary side current of the current transformer is represented, wherein i is the number of fault degrees, and j is the number of time domain statistics;
according to the correlation coefficient r ij After the arrangement from high to low, the time domain statistics of the first ten of the phase relation numbers are taken.
Preferably, the calculating each time domain statistic of the secondary side current of the current transformer under different faults includes:
converting the current history value to a primary side according to a transformation ratio, substituting the current history value into the formula (2) to obtain secondary side current during faults, changing a deviation constant d to obtain secondary side current under different faults, and further obtaining time domain statistics of the secondary side current under different faults;
i 2 =ki 1 +v x ±d(t-t s ) (2);
in the formula (2), i 2 Representing the secondary side current of the current transformer; i.e 1 Representing primary side current of the current transformer; k represents the transformation ratio of the current transformer; v x Representing a measurement error; d represents the deviation constant t s Indicating the moment of occurrence of the fault; t represents any time of measurement after a fault.
Preferably, the calculating the fault state total feature quantity of the actual value and the predicted value of the current transformer includes:
calculating the current actual value and the predicted value of the current transformer according to the formula (3):
in the formula (3), y 0 Representing the total characteristic quantity of the fault state of the current actual value of the current transformer; x is x rf1 ,x rf2 ,…x rfL Representing the actual value i of the current rf Each time domain statistic obtained through calculation; y is 1 Representing the total characteristic quantity of the fault state of the predicted value of the current transformer; x is x pf1 ,x pf2 ,…x pfL Representing the predicted value i pf Each calculated time domain statistic.
Preferably, the time domain statistics include maximum, minimum, peak-to-peak, average, absolute average, root mean square, standard deviation, skewness, variance, kurtosis, coefficient of variation, peak factor, waveform factor, pulse factor, square root amplitude, margin index, and clearance factor.
Preferably, the LSTM current prediction model includes an input layer, a hidden layer, and an output layer.
According to a second aspect of embodiments of the present application, there is provided a computer device comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the current transformer fault diagnosis method as claimed in any one of the above.
According to a third aspect of embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the current transformer fault diagnosis method as set forth in any one of the above.
By adopting the current transformer fault diagnosis method, the electronic equipment and the storage medium provided by the embodiment of the application, according to each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer and the correlation coefficient r of the current transformer secondary side current under normal and different faults and each corresponding time domain statistic thereof, the current transformer secondary side current is calculated ij Calculating the current actual value and the predicted value of the current transformer and the total characteristic quantity of the fault state, and judging whether the current transformer has faults or not according to the threshold value of the total characteristic quantity difference value of the fault state; according to the method, the time domain statistics are calculated after the current data of the current transformer are subjected to LSTM current prediction model and wavelet noise reduction treatment, the influence of special factors on the current transformer in the operation of a power grid is greatly reduced, and the fault diagnosis rate of the current transformer is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
fig. 1 is a schematic flow chart of a fault diagnosis method for a current transformer according to an embodiment of the present application;
FIG. 2 is a flow chart of calculating time domain statistics of actual and predicted values of current according to an embodiment of the present application;
FIG. 3 is a schematic diagram of fault data provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of a fault accuracy curve provided in an embodiment of the present application;
fig. 5 is a schematic diagram of accuracy of different algorithms provided in the embodiments of the present application.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of exemplary embodiments of the present application is given with reference to the accompanying drawings, and it is apparent that the described embodiments are only some of the embodiments of the present application and not exhaustive of all the embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
In the process of realizing the current transformer, the inventor finds that the performance of the element is easy to deteriorate under severe environments such as high temperature, strong electromagnetic interference and the like due to long-term operation of the current transformer, so that various faults are caused, the safety of a power grid is threatened, and therefore, the effective diagnosis of the faults of the current transformer is required to be realized.
In view of the above problems, an embodiment of the present application provides a current transformer fault diagnosis method, as shown in fig. 1, including:
s10, calculating time domain statistics of an actual value and a predicted value of the current after wavelet noise reduction of the current transformer;
step S20, calculating the correlation coefficient r of the current transformer secondary side current and the corresponding time domain statistics of the current transformer secondary side current under normal and different faults ij ;
Step S30, based on each time domain statistic of current actual value and predicted value and correlation coefficient r ij Calculating the total characteristic quantity of fault states of the actual value and the predicted value of the current transformer;
and S40, judging whether the ratio of the actual value to the predicted value of the current exceeds a threshold value, and if so, judging that the current transformer fails.
In this embodiment, according to each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer and the correlation coefficient r of the current transformer secondary side current under normal and different faults and each corresponding time domain statistic ij Calculating the current actual value and the predicted value of the current transformer and the total characteristic quantity of the fault state, and judging whether the current transformer has faults or not according to the threshold value of the total characteristic quantity difference value of the fault state; current transformer of the applicationAfter the current data of the current transformer is processed by an LSTM current prediction model and wavelet noise reduction, each time domain statistic is calculated, so that the influence of special factors on the current transformer in the operation of the power grid is greatly reduced, and the fault diagnosis rate of the current transformer is improved.
Further, as shown in fig. 2, calculating each time domain statistic of the actual value and the predicted value of the current after wavelet noise reduction of the current transformer includes:
s101, collecting outgoing line current data of a transformer substation, and dividing the outgoing line current data into a training set and a testing set;
step S102, constructing an LSTM current prediction model; the LSTM current prediction model comprises an input layer, a hidden layer and an output layer;
step S103, inputting the current data of the training set into an LSTM current prediction model for training, and obtaining an optimal LSTM current prediction model through a current data test model of the test set;
step S104, inputting the current value of the current transformer into an LSTM current prediction model to obtain a predicted value i p 。
In the embodiment, a certain 500kV transformer substation outgoing line current in a D5000 system is selected as original data, sampling intervals are 15 minutes, a total of 27552 points are taken, a front 23232 point in the original data is taken as a training set, a rear 4320 point is taken as a test set, an LSTM current prediction model is constructed by an input layer, 3 hidden layers and an output layer, the iteration number of the LSTM neural network is selected to be 150, the initial learning rate is 0.005, the factor 0.2 is multiplied after 125 rounds, the learning rate is reduced, the current value of a current transformer is input into the LSTM current prediction model, and a current prediction value i is obtained p 。
Further, each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer is calculated, including:
step S105, setting faults with an equivalent fault transformation ratio K to obtain fault data, and recording the fault data as an actual current value i r ;
Step S106, predicting value i p And current actual value i r The actual value i of the current after filtering is obtained through wavelet noise reduction treatment rf And predictive value i pf ;
Step S107, calculating current real timeValue i rf Is a time domain statistic of (1);
step S108, calculating a predicted value i pf Is a time domain statistic of the (c).
In this embodiment, 30 kinds of faults are manually set, one kind of faults is set every day, 96 sampling points are set every day, faults are set from the 21 st sampling point, the equivalent fault transformation ratio of the first fifteen days is from +1% to +15%, the equivalent fault transformation ratio of the last fifteen days is from-1% to-15%, fault data containing 30 kinds of faults are obtained, and the fault data are recorded as current actual values i r The method comprises the steps of carrying out a first treatment on the surface of the The purpose of self-setting fault data is to detect the feasibility and accuracy of the fault detection mode; predicted value of current l p And current actual value i r The actual wavelet noise reduction treatment comprises the following specific processes: first, the number of base wavelets and decomposition levels are determined, then the predicted value l p And current actual value i r Performing wavelet decomposition, selecting new wavelet coefficient, and reconstructing to obtain filtered current actual value i rf And predictive value l pf The method comprises the steps of carrying out a first treatment on the surface of the In this embodiment, the predicted value l can be smoothed by wavelet noise reduction p And current actual value i r The degradation of diagnosis accuracy caused by a large deviation of the predicted value from the actual value due to special conditions such as weather mutation is reduced.
Further, calculating the correlation coefficient r of the current transformer secondary side current and corresponding time domain statistics thereof under normal and different faults ij Comprising:
calculating each time domain statistic of the current transformer secondary side normal current history value in the D5000 system;
calculating time domain statistics of secondary side currents of the current transformer under different faults;
calculating the correlation coefficient r of the secondary side current of the current transformer and corresponding time domain statistics thereof under normal and different faults according to the formula (1) ij :
In the formula (1), C ov Representing covariance, V ar Representing variance, x ij Each time domain statistic of the secondary side current of the current transformer is represented, wherein i is the number of fault degrees, and j is the number of time domain statistics;
according to the correlation coefficient r ij After the arrangement from high to low, the time domain statistics of the first ten of the phase relation numbers are taken; the value of the correlation coefficient is 0-1.
Further, calculating each time domain statistic of the secondary side current of the current transformer under different faults comprises the following steps:
converting the current history value to a primary side according to a transformation ratio, substituting the current history value into the formula (2) to obtain secondary side current during faults, changing a deviation constant d to obtain secondary side current under different faults, and further obtaining time domain statistics of the secondary side current under different faults;
i 2 =ki 1 +v x ±d(t-t s ) (2);
in the formula (2), i 2 Representing the secondary side current of the current transformer; i.e 1 Representing primary side current of the current transformer; k represents the transformation ratio of the current transformer; v x Representing a measurement error; d represents the deviation constant t s Indicating the moment of occurrence of the fault; t represents any time of measurement after a fault.
Specifically, the current history value in the D5000 system is calculated according to the transformation ratio: the rated current of the circuit is converted into the current of the secondary side to the primary side by 1A or 5A, the current is substituted into the circuit (2), the deviation constant d is changed to be 1% -m%, and the current i of the secondary side under different faults is obtained 21 ,i 22 ,…,i 2m Obtaining secondary side current i under different faults according to a calculation formula of each time domain statistic 21 ,i 22 ,…,i 2m Is the time domain statistics x of ij I=0, 1, …, m, m is the number of fault degrees, j=1, 2, …, n, n is the number of time domain statistics.
Further, calculating the total fault state characteristic quantity of the actual value and the predicted value of the current transformer comprises the following steps:
calculating the current actual value and the predicted value of the current transformer according to the formula (3):
in the formula (3), y 0 Representing the total characteristic quantity of the fault state of the current actual value of the current transformer; x is x rf1 ,x rf2 ,…x rfL Representing the actual value i of the current rf Each time domain statistic obtained through calculation; y is 1 Representing the total characteristic quantity of the fault state of the predicted value of the current transformer; x is x pf1 ,x pf2 ,…x pfL Representing the predicted value i pf Each time domain statistic obtained through calculation; k (k) 1 ,k 2 ,…,k L Weighting coefficients for the time domain statistics are preserved for each.
The time domain statistics comprise maximum value, minimum value, peak-to-peak value, average value, absolute average value, root mean square, standard deviation, skewness, variance, kurtosis, variation coefficient, peak factor, waveform factor, pulse factor, square root amplitude, margin index and clearance factor; the maximum value calculation formula is: x is x 1 =max(i 2 ) The method comprises the steps of carrying out a first treatment on the surface of the The minimum value calculation formula is: x is x 2 =min(i 2 ) The method comprises the steps of carrying out a first treatment on the surface of the The peak-to-peak calculation formula is: x is x 3 =x 1 -x 2 The method comprises the steps of carrying out a first treatment on the surface of the The average value calculation formula is:the absolute average value calculation formula is: />The root mean square calculation formula is: />The standard deviation calculation formula is: />The deflection calculation formula is: />The variance calculation formula is: />The kurtosis calculation formula is:the coefficient of variation calculation formula is: />The peak factor calculation formula is: />The calculation formula of the waveform factor is as follows: />The impulse factor calculation formula is: />The square root amplitude value calculation formula is as follows: />The margin index calculation formula is->The clearance factor calculation formula is:
a computer device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the current transformer fault diagnosis method as described above.
A computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the current transformer fault diagnosis method as described above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The schemes in the embodiments of the present application may be implemented in various computer languages, for example, C language, VHDL language, verilog language, object-oriented programming language Java, and transliteration scripting language JavaScript, etc.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (10)
1. A current transformer fault diagnosis method, comprising:
calculating each time domain statistic of the current actual value and the predicted value after wavelet noise reduction of the current transformer;
calculating the correlation coefficient r of the current of the secondary side of the current transformer and corresponding time domain statistics of the current transformer under normal and different faults ij ;
Time domain statistics and correlation coefficient r according to current actual value and predicted value ij Calculating the total characteristic quantity of fault states of the actual value and the predicted value of the current transformer;
and judging whether the ratio of the current actual value to the total fault state characteristic quantity of the predicted value exceeds a threshold value, if so, the current transformer fails.
2. The method for diagnosing a fault of a current transformer according to claim 1, wherein the calculating each time-domain statistic of the actual value and the predicted value of the current after wavelet denoising of the current transformer comprises:
collecting outgoing line current data of a transformer substation, and dividing the outgoing line current data into a training set and a testing set;
constructing an LSTM current prediction model;
inputting the current data of the training set into an LSTM current prediction model for training, and obtaining an optimal LSTM current prediction model through a current data test model of the test set;
inputting the current value of the current transformer into an LSTM current prediction model to obtain a predicted value i p 。
3. The method for diagnosing a fault of a current transformer according to claim 2, wherein the calculating each time-domain statistic of the actual value and the predicted value of the current after wavelet denoising of the current transformer comprises:
setting faults by using an equivalent fault transformation ratio K to obtain fault data, and recording the fault data as an actual current value i r ;
Will predict the value i p And current actual value i r The actual value i of the current after filtering is obtained through wavelet noise reduction treatment rf And predictive value i pf ;
Calculating the actual value i of the current rf Is a time domain statistic of (1);
calculating a predicted value i pf Is a time domain statistic of the (c).
4. A current transformer fault diagnosis method according to claim 3, wherein the correlation coefficient r of the secondary side current of the current transformer under normal and different faults and the corresponding time domain statistics thereof is calculated ij Comprising:
calculating each time domain statistic of the current transformer secondary side normal current history value;
calculating time domain statistics of secondary side currents of the current transformer under different faults;
calculating the correlation coefficient r of the secondary side current of the current transformer and corresponding time domain statistics thereof under normal and different faults according to the formula (1) ij :
In the formula (1), C ov Representing covariance, V ar Representing variance, x ij Each time domain statistic of the secondary side current of the current transformer is represented, wherein i is the number of fault degrees, and j is the number of time domain statistics;
according to the correlation coefficient r ij After the arrangement from high to low, the time domain statistics of the first ten of the phase relation numbers are taken.
5. The method of claim 4, wherein calculating time domain statistics of secondary current of the current transformer for different faults comprises:
converting the current history value to a primary side according to a transformation ratio, substituting the current history value into the formula (2) to obtain secondary side current during faults, changing a deviation constant d to obtain secondary side current under different faults, and further obtaining time domain statistics of the secondary side current under different faults;
i 2 =ki 1 +v x ±d(t-t s ) (2);
in the formula (2), i 2 Representing the secondary side current of the current transformer; i.e 1 Representing primary side current of the current transformer; k represents the transformation ratio of the current transformer; v x Representing a measurement error; d represents the deviation constant t s Indicating the moment of occurrence of the fault; t represents any time of measurement after a fault.
6. The current transformer fault diagnosis method according to claim 4, wherein the calculating the total feature of the fault state of the actual value and the predicted value of the current transformer comprises:
calculating the current actual value and the predicted value of the current transformer according to the formula (3):
in the formula (3), y 0 Representing the total characteristic quantity of the fault state of the current actual value of the current transformer; x is x rf1 ,x rf2 ,…x rfL Representing the actual value i of the current rf Each time domain statistic obtained through calculation; y is 1 Representing the total characteristic quantity of the fault state of the predicted value of the current transformer; x is x pf1 ,x pf2 ,…x pfL Representing the predicted value i pf Each calculated time domain statistic.
7. The current transformer fault diagnosis method of claim 1, wherein the time domain statistics comprise a maximum value, a minimum value, a peak-to-peak value, an average value, an absolute average value, a root mean square, a standard deviation, a skewness, a variance, a kurtosis, a coefficient of variation, a peak factor, a waveform factor, a pulse factor, a square root amplitude, a margin index, and a clearance factor.
8. The current transformer fault diagnosis method according to claim 2, wherein the LSTM current prediction model includes an input layer, a hidden layer, and an output layer.
9. A computer device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the current transformer fault diagnosis method of any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon; the computer program is executed by a processor to implement the current transformer fault diagnosis method as claimed in any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311309493.2A CN117368824A (en) | 2023-10-10 | 2023-10-10 | Current transformer fault diagnosis method, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311309493.2A CN117368824A (en) | 2023-10-10 | 2023-10-10 | Current transformer fault diagnosis method, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117368824A true CN117368824A (en) | 2024-01-09 |
Family
ID=89397562
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311309493.2A Pending CN117368824A (en) | 2023-10-10 | 2023-10-10 | Current transformer fault diagnosis method, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117368824A (en) |
-
2023
- 2023-10-10 CN CN202311309493.2A patent/CN117368824A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110766059A (en) | Transformer fault prediction method, device and equipment | |
CN108139432B (en) | Method for correcting saturation effect in current transformer and intelligent electronic equipment thereof | |
CN107992665B (en) | Online fault diagnosis and analysis method for alternating current filter of extra-high voltage converter station | |
CN115800272B (en) | Power grid fault analysis method, system, terminal and medium based on topology identification | |
CN111612128A (en) | Active early warning method and device for SF6 high-voltage circuit breaker state | |
CN113657622B (en) | Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment | |
CN116739829B (en) | Big data-based power data analysis method, system and medium | |
CN114169631A (en) | Oil field power load management and control system based on data analysis | |
Cai et al. | Multivariate detection of power system disturbances based on fourth order moment and singular value decomposition | |
CN111079591B (en) | Bad data restoration method and system based on improved multi-scale principal component analysis | |
JP7437584B2 (en) | Machine learning-based method and apparatus for power line disturbance classification | |
CN117368824A (en) | Current transformer fault diagnosis method, electronic equipment and storage medium | |
Marsadek et al. | Risk based security assessment of power system using generalized regression neural network with feature extraction | |
CN115409245A (en) | Prediction auxiliary state estimation method, device, equipment and medium for power system | |
CN115292901A (en) | Method and device for evaluating running state of transformer | |
CN115964951A (en) | Power system operation reliability assessment method and device and electronic equipment | |
CN113671366B (en) | Signal processing method, application device thereof and storage medium | |
CN115389865A (en) | Power equipment fault diagnosis method and system based on cloud edge terminal cooperative architecture | |
CN109888338B (en) | SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics | |
Babu et al. | Use of wavelet and neural network (BPFN) for transformer fault diagnosis | |
CN110619413A (en) | Method and device for evaluating health degree of wind generating set | |
CN117388637B (en) | AI-based converter station direct current system abnormal signal identification and auxiliary decision-making method | |
CN117743815B (en) | Method and system for optimizing signals of multi-path vibration sensor of circuit breaker | |
Hammer et al. | Estimation of reliability characteristics of power oil transformers | |
TWI693415B (en) | Transformer diagnosis method, system, computer program product and computer readable recording medium |
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 |