CN116049629B - Voltage transformer error state prediction method, system, equipment and medium - Google Patents
Voltage transformer error state prediction method, system, equipment and medium Download PDFInfo
- Publication number
- CN116049629B CN116049629B CN202310315558.8A CN202310315558A CN116049629B CN 116049629 B CN116049629 B CN 116049629B CN 202310315558 A CN202310315558 A CN 202310315558A CN 116049629 B CN116049629 B CN 116049629B
- Authority
- CN
- China
- Prior art keywords
- error
- historical
- matrix
- period
- trend
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 105
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 83
- 239000011159 matrix material Substances 0.000 claims description 96
- 230000000737 periodic effect Effects 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 19
- 238000010183 spectrum analysis Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 13
- 238000009499 grossing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000012804 iterative process Methods 0.000 claims 1
- 238000011156 evaluation Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 125000003275 alpha amino acid group Chemical group 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000008571 general function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012795 verification Methods 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Measurement Of Current Or Voltage (AREA)
Abstract
The invention relates to a method, a system, equipment and a medium for predicting error states of a voltage transformer, wherein the method comprises the following steps: acquiring historical error data of a target voltage transformer and fundamental zero sequence component deviation of historical three-phase voltage; decomposing the historical error data into a historical error period term, a historical error trend term and a historical error remainder; decomposing the fundamental wave zero-sequence component deviation of the historical three-phase voltage into a fundamental wave zero-sequence component deviation period item and a fundamental wave zero-sequence component deviation trend item; predicting a first error state, a second error state and a third error state of the target voltage transformer at the current moment through the decomposition term; and the first error state, the second error state and the third error state are used as input data to be input into a pre-trained echo state network, and a predicted value output by the echo state network is used as a final error state of the target voltage transformer at the current moment.
Description
Technical Field
The invention relates to a method, a system, equipment and a medium for predicting the error state of a voltage transformer, and belongs to the technical field of transformer state prediction.
Background
The voltage transformer is an important measurement device in the power system, a primary winding of the voltage transformer is connected to a high-voltage power grid, and a secondary winding of the voltage transformer is connected with devices such as measurement, metering and protection and the like and is used for converting a primary side high-pressure signal into a low-pressure small signal for the secondary device to use.
Long-term operation experience shows that the voltage transformer has a certain out-of-tolerance risk after a few years of operation due to the increase of the service life of the voltage transformer. The out-of-tolerance voltage transformer continues to operate to bring huge losses to the gateway metering trade settlement of the power supply and use parties, and even the stable operation of the power system is affected. Therefore, in order to ensure the accuracy of metering and the safe operation of the power system, the voltage transformer with abnormal error state needs to be timely evaluated and replaced. The existing mature offline evaluation method is used for periodically evaluating the voltage transformers offline, but because the high-voltage power transmission network is difficult to perform non-fault power failure operation, the method is difficult to cover all the voltage transformers to be verified in a specified period; and the difference exists between the environment electromagnetic field during offline evaluation and the online operation, so that a certain deviation exists between an evaluation result and the actual situation, and a large number of running voltage transformers in the transformer substation are out of date and have unknown errors.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method, a system, equipment and a medium for predicting the error state of a voltage transformer.
The technical scheme of the invention is as follows:
in one aspect, the invention provides a method for predicting an error state of a voltage transformer, comprising the following steps:
acquiring historical error data of a target voltage transformer and fundamental zero sequence component deviation of historical three-phase voltage;
decomposing the historical error data into a historical error period term, a historical error trend term and a historical error remainder by adopting a periodic trend decomposition method based on local weighted regression;
decomposing the fundamental wave zero-sequence component deviation of the historical three-phase voltage into a fundamental wave zero-sequence component deviation period item and a fundamental wave zero-sequence component deviation trend item;
based on the historical error period item and the fundamental wave zero sequence component deviation period item, predicting a first error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model; based on the historical error trend item and the fundamental zero sequence component deviation trend item, predicting a second error state of the target voltage transformer at the current moment by using a pre-trained time sequence prediction model; based on the historical error remainder, predicting a third error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model;
And the first error state, the second error state and the third error state are used as input data to be input into a pre-trained echo state network, and a predicted value output by the echo state network is used as a final error state of the target voltage transformer at the current moment.
As a preferred embodiment, the method for decomposing the historical error data into the historical error period term, the historical error trend term and the historical error remainder by adopting the periodic trend decomposition method based on local weighted regression specifically comprises the following steps:
historical error data of the target voltage transformer are recorded as follows:
；
wherein,,for history error data, t is history time, < +.>Error vector data representing the p-phase of the historical time, p comprising A, B, C;
decomposing the historical error data into the following steps by adopting a periodic trend decomposition method based on local weighted regression:
；
wherein,,、/>、/>respectively representing a history error period term, a history error trend term and a history error remainder;
the decomposition process includes an inner loop and an outer loop, and the process at the (i+1) th iteration is as follows:
trending item removal processing is carried out on the historical error data:
；
wherein,,historical error data results after removing the error trend term, < +.>Representing the result of the ith iteration of the error trend term;
Carrying out sub-sequence smoothing, forming a sub-sequence by sample points at the same position in each period of the historical error data, carrying out local weighted regression smoothing on each sub-sequence, and respectively extending a time point before and after the sub-sequence, so as to obtain a new sub-sequence by combination;
calculating error trend terms of the new subsequence by adopting low-pass filtering, removing the periodic difference, and then calculating error period terms of the new subsequence by the additivity of the time sequence:
；
wherein,,error period term for the (i+1) th iteration of the new subsequence,/and (ii)>For a new subsequence,/->Error trend terms for the new subsequence;
removing the error period term of the new subsequence to obtain an error period term and an error trend term of the original sequence:
；
；
wherein,,error trend term for the (i+1) th iteration,>representing a locally weighted regression of the data,error period term for the (i+1) th iteration;
judging whether the local weighted regression is converged or not, and if the local weighted regression is not converged, repeating the internal circulation process; if the convergence is carried out, the internal circulation is jumped out, and an error remainder is calculated:
；
wherein,,is the error remainder of the (i+1) th iteration.
As a preferred embodiment, the method for decomposing the fundamental zero-sequence component deviation of the historical three-phase voltage into the fundamental zero-sequence component deviation period term specifically comprises the following steps:
Decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting a singular spectrum analysis method;
fundamental zero sequence component deviation for historic three-phase voltages of a target voltage transformer of length t It is transformed into a matrix X according to a given embedding dimension K:
；
singular value decomposition is performed on a matrix X, and a matrix obtained by multiplying the matrix X by the transpose of the matrix X is obtainedAnd is arranged in descending order according to the characteristic values, and is marked as follows: />The characteristic values correspond to the characteristic vectors corresponding to the matrix X>：
；
Setting:；
wherein d is the rank of the matrix X, and rank represents the function of solving the rank;
definition:；
the singular value decomposition of matrix X is:
；
wherein,,；/>for the singular values of matrix X, set +.>Is a singular spectrum of the matrix X,is mainly composed of (a) herba Cistanchis>And->The left eigenvector and the right eigenvector in the eigenvectors of the matrix X are respectively;
each subsequence is reduced to a sequence of length t, specifically as follows: define matrix X asIs then:
；
；
；
if and only ifWhen (I)>Otherwise->The reconstructed sequence is as follows:
；
；
wherein RC represents the reconstructed sequence, n is the sequence number of the reconstructed sequence, m is the base number, K is the row of the reconstructed matrix, L is the column of the reconstructed matrix,elements of the ith row and jth column in the reconstruction matrix, >Elements of the ith row and the jth column in the matrix X;
grouping the same-period subsequences appearing in the decomposition by utilizing the sequence spectrum analysis and the characteristic value steep slope map, wherein the superposition result of the same-period subsequences is the fundamental wave zero sequence component deviation period item.
As a preferred embodiment, the method for decomposing the fundamental zero-sequence component deviation of the historical three-phase voltage into fundamental zero-sequence component deviation trend terms specifically comprises the following steps:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting an analytical mode decomposition method;
the fundamental zero sequence component deviation of the historical three-phase voltage is defined according to the following:
；
wherein,,for the fundamental zero sequence component deviation of the historic three-phase voltage, +.>Sampling values for fundamental zero sequence component deviations;
the corresponding frequency is +.>There is->The method comprises the following steps:
；
wherein,,dividing frequencies for boundaries;
the method comprises the following steps:
in the above-mentioned method, the step of,is the firstDecomposition function of i signals at time t, < ->Is->Shorthand for->=2,3,……，n-1；/>Is a Hilbert transform;
presetting a specified frequency fc to be less than the frequency fc and obtain a signal component by the above equationAs a fundamental zero sequence component bias trend term.
On the other hand, the invention also provides a system for predicting the error state of the voltage transformer, which comprises the following steps:
The data acquisition module is used for acquiring the historical error data of the target voltage transformer and the fundamental zero sequence component deviation of the historical three-phase voltage;
the historical error data decomposition module adopts a periodic trend decomposition method based on local weighted regression to decompose the historical error data into a historical error periodic term, a historical error trend term and a historical error remainder;
the fundamental wave zero sequence component deviation decomposition module is used for decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage into a fundamental wave zero sequence component deviation period item and a fundamental wave zero sequence component deviation trend item;
the preliminary state prediction module predicts a first error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model based on the historical error period item and the fundamental wave zero sequence component deviation period item, and predicts a second error state of the current moment of the target voltage transformer by using the pre-trained time sequence prediction model based on the historical error trend item and the fundamental wave zero sequence component deviation trend item; based on the historical error remainder, predicting a third error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model;
the final state prediction module is used for inputting the first error state, the second error state and the third error state as input data into the pre-trained echo state network, and taking a predicted value output by the echo state network as a final error state of the target voltage transformer at the current moment.
As a preferred embodiment, the historical error data decomposition module includes a definition unit and an STL decomposition unit:
the historical error data decomposition module comprises a definition unit and an STL decomposition unit:
the definition unit is used for recording historical error data of the target voltage transformer as:
；
wherein,,for history error data, t is history time, < +.>Error vector data representing the p-phase of the historical time, p comprising A, B, C;
the STL decomposition unit is used for decomposing the historical error data into the following parts based on a periodic trend decomposition method of local weighted regression:
；
wherein,,、/>、/>respectively represent a history error period term, a history error trend term and a historyError remainder;
the decomposition process includes an inner loop and an outer loop, and the process at the (i+1) th iteration is as follows:
trending item removal processing is carried out on the historical error data:
；
wherein,,historical error data results after removing the error trend term, < +.>Representing the result of the ith iteration of the error trend term;
carrying out sub-sequence smoothing, forming a sub-sequence by sample points at the same position in each period of the historical error data, carrying out local weighted regression smoothing on each sub-sequence, and respectively extending a time point before and after the sub-sequence, so as to obtain a new sub-sequence by combination;
Calculating error trend terms of the new subsequence by adopting low-pass filtering, removing the periodic difference, and then calculating error period terms of the new subsequence by the additivity of the time sequence:
；
wherein,,error period term for the (i+1) th iteration of the new subsequence,/and (ii)>For a new subsequence,/->Error trend terms for the new subsequence;
removing the error period term of the new subsequence to obtain an error period term and an error trend term of the original sequence:
；
；
wherein,,error trend term for the (i+1) th iteration,>representing a locally weighted regression of the data,error period term for the (i+1) th iteration;
judging whether the local weighted regression is converged or not, and if the local weighted regression is not converged, repeating the internal circulation process; if the convergence is carried out, the internal circulation is jumped out, and an error remainder is calculated:
；
wherein,,is the error remainder of the (i+1) th iteration.
As a preferred embodiment, the fundamental zero sequence component deviation decomposition module includes an SSA decomposition unit, specifically configured to:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting a singular spectrum analysis method;
fundamental zero sequence component deviation for historic three-phase voltages of a target voltage transformer of length t It is transformed into a matrix X according to a given embedding dimension K:
；
Singular value decomposition is performed on a matrix X, and a matrix obtained by multiplying the matrix X by the transpose of the matrix X is obtainedAnd is arranged in descending order according to the characteristic values, and is marked as follows: />The characteristic values correspond to the characteristic vectors corresponding to the matrix X>：
；
Setting:；
wherein d is the rank of the matrix X, and rank represents the function of solving the rank;
definition:；
the singular value decomposition of matrix X is:
；
wherein,,；/>for the singular values of matrix X, set +.>Is a singular spectrum of the matrix X,is mainly composed of (a) herba Cistanchis>And->The left eigenvector and the right eigenvector in the eigenvectors of the matrix X are respectively;
each subsequence is reduced to a sequence of length t, specifically as follows: define matrix X asIs then:
；
；
；
if and only ifWhen (I)>Otherwise->The reconstructed sequence is as follows:
；
；
wherein RC represents the reconstructed sequence, n is the sequence number of the reconstructed sequence, m is the base number, K is the row of the reconstructed matrix, L is the column of the reconstructed matrix,elements of the ith row and jth column in the reconstruction matrix,>elements of the ith row and the jth column in the matrix X;
grouping the same-period subsequences appearing in the decomposition by utilizing the sequence spectrum analysis and the characteristic value steep slope map, wherein the superposition result of the same-period subsequences is the fundamental wave zero sequence component deviation period item.
As a preferred embodiment, the fundamental zero sequence component deviation decomposition module includes an AMD decomposition unit, specifically configured to:
Decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting an analytical mode decomposition method;
the fundamental zero sequence component deviation of the historical three-phase voltage is defined according to the following:
；
wherein,,for the fundamental zero sequence component deviation of the historic three-phase voltage, +.>Sampling values for fundamental zero sequence component deviations;
the corresponding frequency is +.>There is->The method comprises the following steps:
；
wherein,,dividing frequencies for boundaries;
the method comprises the following steps:
in the above-mentioned method, the step of,for the decomposition function of the ith signal at time t, -/->Is->Shorthand for->=2,3,……，n-1；/>Is a Hilbert transform;
presetting a specified frequency fc to be less than the frequency fc and obtain a signal component by the above equationAs a fundamental zero sequence component bias trend term.
In yet another aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method for predicting the error state of the voltage transformer according to any embodiment of the present invention when executing the program.
In yet another aspect, the present invention further provides a computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements a method for predicting an error state of a voltage transformer according to any embodiment of the present invention.
The invention has the following beneficial effects:
according to the method, the system, the equipment and the medium for predicting the error state of the voltage transformer, the historical error data and the historical three-phase voltage data of the target voltage sensor are decomposed into the characteristic data, the characteristic data are utilized for sequence prediction, the echo state network is utilized for predicting the real-time error state of the target voltage transformer according to the prediction result, and the real-time online prediction of the error state of the voltage transformer is realized.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an echo state network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the step numbers used herein are for convenience of description only and are not limiting as to the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Embodiment one:
referring to fig. 1, in order to solve the defects in the periodic offline evaluation method in the prior art, the embodiment adopts an online evaluation method under the condition of no power failure to realize real-time online monitoring of the error state of the voltage transformer, and provides a voltage transformer error state prediction method based on an echo state network, which specifically comprises the following steps:
S100, acquiring historical error data of a target voltage transformer and fundamental wave zero sequence component deviation of the historical three-phase voltage.
S200, adopting a periodic trend decomposition method based on local weighted regression
(Seasonal-Trend decompositionprocedure based on Loess, STL) decomposes historical error data into a historical error period term, a historical error trend term, and a historical error remainder.
S300, decomposing the fundamental zero-sequence component deviation of the historical three-phase voltage into a fundamental zero-sequence component deviation period term of the historical three-phase voltage and a fundamental zero-sequence component deviation trend term of the historical three-phase voltage by adopting singular spectrum analysis (Singular Spectrum Analysis, SSA) and Analysis Mode Decomposition (AMD) respectively.
S400, based on a historical error period item and a fundamental wave zero sequence component deviation period item, predicting a first error state of a current moment of a target voltage transformer by using a pre-trained time sequence prediction model, wherein the specific method is that the historical error period item and the fundamental wave zero sequence component deviation period item of the target voltage transformer in a certain time period t are used as inputs of a time sequence prediction model (LSTM, ARIMA and the like), the historical state of the transformer in a next time period t+1 is used as output, training is carried out, a trained time sequence prediction model is obtained, and then the trained time sequence prediction model is used for obtaining the first error state at any future moment; based on the historical error trend item and the fundamental zero sequence component deviation trend item, predicting a second error state of the target voltage transformer at the current moment by using a pre-trained time sequence prediction model; based on the historical error remainder, predicting a third error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model; the second error state and the third error state are obtained in the same manner as the first error state, and are not described again.
S500, setting the first error stateSecond error state->And third error state->The final error state of the target voltage transformer at the current moment is +.>In this embodiment, the pre-training process of the echo state network is: for a target voltage transformer, the first error state, the second error state and the third error state at the historical moment are obtained through the step S400, meanwhile, the real error state (generally obtained through power failure verification) is obtained, the first error state, the second error state and the third error state at the historical moment are used as input, and the real error state is used as output, so that the training of the echo state network can be completed.
Specifically, echo State Networks (ESNs) are a new recurrent neural network that utilizes dynamic libraries to replace hidden layers of standard neural networks. The echo state network is as shown in fig. 2:
as can be seen from FIG. 2, the ESN has input units, reservoir units and output units, the input layer is set to have H input units, the dynamic reservoir has m reservoir units, the output layer has d output units, and four basic weight matrices are 、、/>、/>；
The ESN neural network comprises the following working processes:
；
；
；
；
wherein,,input data representing time t, < >>Output data representing time t, < >>The general function is represented by a function of the general,representing a generalized function->Representing the neuronal status.
As a preferred implementation manner of the present embodiment, the method for decomposing the historical error data into the historical error period term, the historical error trend term and the historical error remainder by using the periodic trend decomposition method based on local weighted regression specifically includes:
historical error data of the target voltage transformer is recorded as:
（1）
wherein,,for history error data, t is history time, < +.>Error vector data representing the p-phase at the historical time, p including A, B, C, i.e., a-phase, B-phase, C-phase;
according to the relevant conclusion of the steady-state analysis of the power system, the three-phase voltage vector sum of the neutral point effective grounding system is a zero sequence component, namely:
（2）
in the formula (2), the amino acid sequence of the compound,for zero sequence component->Respectively three-phase voltage vectors.
Considering CVT error conditions, the zero sequence component measurements are:
（3）
in the formula (3), the amino acid sequence of the compound,for taking into account the zero-sequence component measurement of the CVT error, the value is obtained by direct measurement of the three-phase voltage and superposition of the three-phase voltages>Error vectors of the three-phase CVT, respectively.
Subtracting the formula (2) from the formula (3) can obtain the deviation of zero sequence component caused by CVT error, namely:
（4）
The historical error data is decomposed into the following steps by adopting a periodic trend decomposition method (STL algorithm) based on local weighted regression:
（5）
wherein,,、/>、/>respectively representing a history error period term, a history error trend term and a history error remainder;
the specific decomposition process of STL can be divided into 2 steps including inner loop and outer loop, and the history error period term is updated by using smooth period during inner loopAnd historical error trend term->Removing abnormal disturbance of each component; during the outer loop, the history error remainder is calculated>The method comprises the steps of carrying out a first treatment on the surface of the The procedure at the i+1st iteration is as follows:
trending item removal processing is carried out on the historical error data:
（6）
wherein,,historical error data results after removing the error trend term, < +.>Representing the result of the ith iteration of the error trend term;
performing sub-sequence smoothing, wherein sample points at the same position in each period of the historical error data form a sub-sequence, which means a part of the historical error data which is segmented according to the period; carrying out local weighted regression (Lowess) smoothing treatment on each subsequence, and extending a time point before and after each subsequence to obtain a new subsequence by combining;
calculating error trend terms of the new subsequence by adopting low-pass filtering, removing the periodic difference, and then calculating error period terms of the new subsequence by the additivity of the time sequence:
（7）
Wherein,,error period term for the (i+1) th iteration of the new subsequence,/and (ii)>For a new subsequence,/->Error trend terms for the new subsequence;
removing the error period term of the new subsequence to obtain an error period term and an error trend term of the original sequence:
（8）
（9）
wherein,,error trend term for the (i+1) th iteration,>representing a locally weighted regression of the data,error period term for the (i+1) th iteration;
judging whether the internal circulation process is converged or not, and if the internal circulation process is not converged, repeating the internal circulation process; if the convergence is carried out, the internal circulation is jumped out, and an error remainder is calculated:
（10）
wherein,,and (3) obtaining an error remainder for the end of the inner loop in the (i+1) th iteration.
As a preferred implementation manner of this embodiment, the method for decomposing the fundamental zero sequence component deviation of the historical three-phase voltage into the fundamental zero sequence component deviation period term specifically includes:
the fundamental zero-sequence component deviation of the historical three-phase voltage is decomposed by adopting a Singular Spectrum Analysis (SSA), and the fundamental zero-sequence component deviation of the historical three-phase voltage can be decomposed into a fundamental zero-sequence component deviation period item of the historical three-phase voltage, and the specific process is as follows:
fundamental zero sequence component deviation for historic three-phase voltages of a target voltage transformer of length t It is transformed into a matrix X according to a given embedding dimension K:
（11）
Singular value decomposition (single ValueDecomposition, SVD) is performed on matrix X, and the matrix obtained by multiplying matrix X by its transpose is obtainedAnd is arranged in descending order according to the characteristic values, and is marked as follows: />Each eigenvalue corresponds to a corresponding eigenvector +.>：
（12）
Setting:（13）
wherein d is the rank of the matrix X, and rank represents the function of solving the rank;
definition:（14）
the singular value decomposition of matrix X is:
（15）/>
wherein,,（16）
wherein,,for the singular values of matrix X, set +.>Is the singular spectrum of matrix X, +.>Is an empirical orthogonal function of matrix X, +.>Is mainly composed of (a) herba Cistanchis>And->The left eigenvector and the right eigenvector in the eigenvectors of the matrix X are respectively;
diagonal averaging is performed to reduce each subsequence to a sequence of length t, as follows: define matrix X asIs then:
（17）
（18）
（19）
if and only ifWhen (I)>Otherwise->The reconstructed sequence is as follows:
（20）
（21）
wherein RC represents the reconstructed sequence, K is the row of the reconstructed matrix, L is the column of the reconstructed matrix,elements of the ith row and jth column in the reconstruction matrix,>elements of the ith row and the jth column in the matrix X;
the grouping is performed with the purpose of separating the target signal component from the other signal components. When the original sequence degree and the embedding dimension are large enough, the decomposition sequences corresponding to the characteristic values with two poles similar to each other of the matrix X are a pair of fluctuation components with the same periodic characteristics. By means of sequence spectrum analysis and characteristic value steep slope graphs, the same-period subsequences appearing in decomposition can be grouped, and the superposition result of the same-period subsequences is the fundamental wave zero sequence component deviation period item of the periodic components under the characteristic frequency of the original sequence.
As a preferred implementation manner of this embodiment, the method for decomposing the fundamental zero sequence component deviation of the historical three-phase voltage into the fundamental zero sequence component deviation trend term specifically includes:
decomposing fundamental zero sequence component deviation of the historical three-phase voltage by adopting an Analytical Mode Decomposition (AMD); AMD is a time-frequency analysis method, which can decompose the fundamental zero sequence component deviation of the historical three-phase voltage into fundamental zero sequence component deviation trend items of the historical three-phase voltage, and the specific process is as follows:
the fundamental zero sequence component deviation of the historical three-phase voltage is defined according to the following:
（22）/>
wherein,,for the fundamental zero sequence component deviation of the historic three-phase voltage, +.>Sampling values for fundamental zero sequence component deviations;
the corresponding frequency is +.>There is->The method comprises the following steps:
（23）
wherein,,dividing frequencies for boundaries;
the method comprises the following steps:
in the above-mentioned method, the step of,=2,3,……，n-1；/>is a Hilbert transform;
presetting a specified frequency fc to be less than the frequency fc and obtain a signal component by the above equationAs a fundamental zero sequence component bias trend term.
Embodiment two:
the embodiment provides a voltage transformer error state prediction system, which comprises:
the data acquisition module is used for acquiring the historical error data of the target voltage transformer and the fundamental zero sequence component deviation of the historical three-phase voltage; the module is used for implementing the function of step S100 in the first embodiment, and will not be described here again;
The historical error data decomposition module adopts a periodic trend decomposition method based on local weighted regression to decompose the historical error data into a historical error periodic term, a historical error trend term and a historical error remainder; the module is used for implementing the function of step S200 in the first embodiment, and will not be described in detail herein;
the fundamental wave zero sequence component deviation decomposition module is used for decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage into a fundamental wave zero sequence component deviation period item and a fundamental wave zero sequence component deviation trend item; the module is used for implementing the function of step S300 in the first embodiment, and will not be described in detail herein;
the preliminary state prediction module predicts a first error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model based on the historical error period item and the fundamental wave zero sequence component deviation period item, and predicts a second error state of the current moment of the target voltage transformer by using the pre-trained time sequence prediction model based on the historical error trend item and the fundamental wave zero sequence component deviation trend item; based on the historical error remainder, predicting a third error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model; the module is used for realizing the function of step S400 in the first embodiment, and will not be described in detail herein;
The final state prediction module is used for inputting the first error state, the second error state and the third error state as input data into a pre-trained echo state network, and taking a predicted value output by the echo state network as a final error state of the target voltage transformer at the current moment; the module is used to implement the function of step S500 in the first embodiment, and will not be described herein.
As a preferred implementation manner of this embodiment, the historical error data decomposition module includes a definition unit and an STL decomposition unit:
the definition unit is used for recording historical error data of the target voltage transformer as:
；/>
wherein,,for history error data, t is history time, < +.>Error vector data representing the p-phase of the historical time, p comprising A, B, C;
the decomposition unit is used for decomposing the historical error data into the following parts based on a periodic trend decomposition method of local weighted regression:
；
wherein,,、/>、/>respectively representing a history error period term, a history error trend term and a history error remainder;
the decomposition process comprises inner loop and outer loop, and the history error period term is updated by smooth period during inner loopAnd historical error trend term->The method comprises the steps of carrying out a first treatment on the surface of the During the outer loop, the history error remainder is calculated >The method comprises the steps of carrying out a first treatment on the surface of the The procedure at the i+1st iteration is as follows:
trending item removal processing is carried out on the historical error data:
；
wherein,,historical error data results after removing the error trend term, < +.>Representing the result of the ith iteration of the error trend term;
carrying out sub-sequence smoothing, forming a sub-sequence by sample points at the same position in each period of the historical error data, carrying out local weighted regression smoothing on each sub-sequence, and respectively extending a time point before and after the sub-sequence, so as to obtain a new sub-sequence by combination;
calculating error trend terms of the new subsequence by adopting low-pass filtering, removing the periodic difference, and then calculating error period terms of the new subsequence by the additivity of the time sequence:
；
wherein,,error period term for the (i+1) th iteration of the new subsequence,/and (ii)>For a new subsequence,/->Error trend terms for the new subsequence;
removing the error period term of the new subsequence to obtain an error period term and an error trend term of the original sequence:
；
；
wherein,,error trend term for the (i+1) th iteration,>representing a locally weighted regression of the data,error period term for the (i+1) th iteration;
judging whether the internal circulation process is converged or not, and if the internal circulation process is not converged, repeating the internal circulation process; if the convergence is carried out, the internal circulation is jumped out, and an error remainder is calculated:
；
Wherein,,is the error remainder of the (i+1) th iteration. />
As a preferred implementation manner of this embodiment, the fundamental wave zero sequence component deviation decomposition module includes an SSA decomposition unit, specifically configured to:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting a singular spectrum analysis method;
fundamental zero sequence component deviation for historic three-phase voltages of a target voltage transformer of length t It is transformed into a matrix X according to a given embedding dimension K:
；
singular value decomposition is performed on a matrix X, and a matrix obtained by multiplying the matrix X by the transpose of the matrix X is obtainedAnd is arranged in descending order according to the characteristic values, and is marked as follows: />Each eigenvalue corresponds to a corresponding eigenvector +.>：
；
Setting:；
wherein d is the rank of the matrix X, and rank represents the function of solving the rank;
definition:；
the singular value decomposition of matrix X is:
；
wherein,,；/>for the singular values of matrix X, set +.>Is a singular spectrum of the matrix X,is an empirical orthogonal function of matrix X, +.>Is mainly composed of (a) herba Cistanchis>And->The left eigenvector and the right eigenvector in the eigenvectors of the matrix X are respectively;
each subsequence is reduced to a sequence of length t, specifically as follows: define matrix X asIs then:
；
；
；
if and only ifWhen (I)>Otherwise- >The reconstructed sequence is as follows:
；/>
；
wherein RC represents the reconstructed sequence, K is the row of the reconstructed matrix, L is the column of the reconstructed matrix,elements of the ith row and jth column in the reconstruction matrix,>elements of the ith row and the jth column in the matrix X;
grouping the same-period subsequences appearing in the decomposition by utilizing the sequence spectrum analysis and the characteristic value steep slope map, wherein the superposition result of the same-period subsequences is the fundamental wave zero sequence component deviation period item.
As a preferred implementation manner of this embodiment, the fundamental zero sequence component deviation decomposition module includes an AMD decomposition unit, specifically configured to:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting an analytical mode decomposition method;
the fundamental zero sequence component deviation of the historical three-phase voltage is defined according to the following:
；
wherein,,for the fundamental zero sequence component deviation of the historic three-phase voltage, +.>Sampling values for fundamental zero sequence component deviations;
the corresponding frequency is +.>There is->The method comprises the following steps:
；
wherein,,dividing frequencies for boundaries;
the method comprises the following steps:
in the above-mentioned method, the step of,=2,3,……，n-1；/>is a Hilbert transform;
presetting a specified frequency fc to be less than the frequency fc and obtain a signal component by the above equationAs a fundamental zero sequence component bias trend term.
Embodiment III:
the embodiment provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor is used for realizing the voltage transformer error state prediction method according to any embodiment of the invention when executing the program.
Embodiment four:
the present embodiment proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for predicting the error state of a voltage transformer according to any embodiment of the present invention.
In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relation of association objects, and indicates that there may be three kinds of relations, for example, a and/or B, and may indicate that a alone exists, a and B together, and B alone exists. Wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.
Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in the embodiments disclosed herein can be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In several embodiments provided herein, any of the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (hereinafter referred to as ROM), a random access Memory (Random Access Memory) and various media capable of storing program codes such as a magnetic disk or an optical disk.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (4)
1. The voltage transformer error state prediction method is characterized by comprising the following steps of:
acquiring historical error data of a target voltage transformer and fundamental zero sequence component deviation of historical three-phase voltage;
decomposing the historical error data into a historical error period term, a historical error trend term and a historical error remainder by adopting a periodic trend decomposition method based on local weighted regression;
decomposing the fundamental wave zero-sequence component deviation of the historical three-phase voltage into a fundamental wave zero-sequence component deviation period item and a fundamental wave zero-sequence component deviation trend item;
based on the historical error period item and the fundamental wave zero sequence component deviation period item, predicting a first error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model; based on the historical error trend item and the fundamental zero sequence component deviation trend item, predicting a second error state of the target voltage transformer at the current moment by using a pre-trained time sequence prediction model; based on the historical error remainder, predicting a third error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model;
The first error state, the second error state and the third error state are used as input data to be input into a pre-trained echo state network, and a predicted value output by the echo state network is used as a final error state of the target voltage transformer at the current moment;
the method for decomposing the historical error data into the historical error period term, the historical error trend term and the historical error remainder by adopting the periodic trend decomposition method based on local weighted regression comprises the following specific steps:
historical error data of the target voltage transformer are recorded as follows:
；
wherein,,for history error data, t is history time, < +.>Error vector data representing the p-phase of the historic timeP comprises A, B, C;
decomposing the historical error data into the following steps by adopting a periodic trend decomposition method based on local weighted regression:
；
wherein,,、/>、/>respectively representing a history error period term, a history error trend term and a history error remainder;
the decomposition process comprises inner loop and outer loop, and the history error period term is updated by smooth period during inner loopAnd historical error trend term->Removing abnormal disturbance of each component; during the outer loop, the history error remainder is calculated>The procedure at the i+1st iteration is as follows:
trending item removal processing is carried out on the historical error data:
；
Wherein,,historical error data results after removing the error trend term, < +.>Representing the result of the ith iteration of the error trend term;
carrying out sub-sequence smoothing, forming a sub-sequence by sample points at the same position in each period of the historical error data, carrying out local weighted regression smoothing on each sub-sequence, and respectively extending a time point before and after the sub-sequence, so as to obtain a new sub-sequence by combination;
calculating error trend terms of the new subsequence by adopting low-pass filtering, removing the periodic difference, and then calculating error period terms of the new subsequence by the additivity of the time sequence:
；
wherein,,error period term for the (i+1) th iteration of the new subsequence,/and (ii)>For the new sub-sequence(s),error trend terms for the new subsequence;
removing the error period term of the new subsequence to obtain an error period term and an error trend term of the original sequence:
；
；
wherein,,error trend term for the (i+1) th iteration,>representing a locally weighted regression of the data,error period term for the (i+1) th iteration;
judging whether the local weighted regression is converged or not, and if the local weighted regression is not converged, repeating the internal circulation process; if the convergence is carried out, the internal circulation is jumped out, and an error remainder is calculated:
；
wherein,,error remainder for the (i+1) th iteration;
The method for decomposing the fundamental wave zero sequence component deviation of the historical three-phase voltage into fundamental wave zero sequence component deviation period items comprises the following specific steps:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting a singular spectrum analysis method;
fundamental zero sequence component deviation of historical three-phase voltage of target voltage transformer with length of historical time t It is transformed into a matrix X according to a given embedding dimension K:
；
singular value decomposition is performed on a matrix X, and a matrix obtained by multiplying the matrix X by the transpose of the matrix X is obtainedAnd is arranged in descending order according to the characteristic values, and is marked as follows: />The characteristic values correspond to the characteristic vectors corresponding to the matrix X>：
；
Setting:；
wherein d is the rank of the matrix X, and rank represents the function of solving the rank;
definition:；
the singular value decomposition of matrix X is:
；
wherein,,；/>for the singular values of matrix X, set +.>Is the singular spectrum of matrix X, +.>Is mainly composed of (a) herba Cistanchis>And->The left eigenvector and the right eigenvector in the eigenvectors of the matrix X are respectively;
each subsequence is reduced to a sequence of length t, specifically as follows: define matrix X asIs then:
；
；
；
if and only ifWhen (I)>Otherwise->The reconstructed sequence is as follows:
；
；
wherein RC represents the reconstructed sequence, n is the sequence number of the reconstructed sequence, m is the base number, K is the row of the reconstructed matrix, L is the column of the reconstructed matrix, Elements of the ith row and jth column in the reconstruction matrix,>elements of the ith row and the jth column in the matrix X;
grouping the same-period subsequences appearing in the decomposition by utilizing sequence spectrum analysis and a characteristic value steep slope map, wherein the superposition result of the same-period subsequences is a fundamental wave zero sequence component deviation period item;
the method for decomposing the fundamental wave zero sequence component deviation of the historical three-phase voltage into fundamental wave zero sequence component deviation trend items comprises the following specific steps:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting an analytical mode decomposition method;
the fundamental zero sequence component deviation of the historical three-phase voltage is defined according to the following:
；
wherein,,for the fundamental zero sequence component deviation of the historic three-phase voltage, +.>Sampling values for fundamental zero sequence component deviations;
the corresponding frequency is +.>There is->I=1, 2, …, n-1, satisfies:
；
wherein,,dividing frequencies for boundaries;
the method comprises the following steps:
in the above-mentioned method, the step of,for the decomposition function of the ith signal at time t, -/->Is->Shorthand for->=2,3,……，n-1；Is a Hilbert transform;
presetting a specified frequency fc to be less than the frequency fc and obtain a signal component by the above equationAs a fundamental zero sequence component bias trend term.
2. A voltage transformer error condition prediction system, comprising:
The data acquisition module is used for acquiring the historical error data of the target voltage transformer and the fundamental zero sequence component deviation of the historical three-phase voltage;
the historical error data decomposition module adopts a periodic trend decomposition method based on local weighted regression to decompose the historical error data into a historical error periodic term, a historical error trend term and a historical error remainder;
the fundamental wave zero sequence component deviation decomposition module is used for decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage into a fundamental wave zero sequence component deviation period item and a fundamental wave zero sequence component deviation trend item;
the preliminary state prediction module predicts a first error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model based on the historical error period item and the fundamental wave zero sequence component deviation period item, and predicts a second error state of the current moment of the target voltage transformer by using the pre-trained time sequence prediction model based on the historical error trend item and the fundamental wave zero sequence component deviation trend item; based on the historical error remainder, predicting a third error state of the current moment of the target voltage transformer by using a pre-trained time sequence prediction model;
the final state prediction module is used for inputting the first error state, the second error state and the third error state as input data into a pre-trained echo state network, and taking a predicted value output by the echo state network as a final error state of the target voltage transformer at the current moment;
The historical error data decomposition module comprises a definition unit and a periodic trend decomposition method decomposition unit:
the definition unit is used for recording historical error data of the target voltage transformer as:
；
wherein,,for history error data, t is history time, < +.>Error vector data representing the p-phase of the historical time, p comprising A, B, C;
the periodic trend decomposition method decomposition unit is used for decomposing the historical error data into the periodic trend decomposition method based on the local weighted regression:
；
wherein,,、/>、/>respectively representing a history error period term, a history error trend term and a history error remainder;
the decomposition process comprises inner loop and outer loop, and the history error period term is updated by smooth period during inner loopAnd historical error trend term->Removing abnormal disturbance of each component; during the outer loop, the history error remainder is calculated>At the (i+1) th timeThe iterative process is as follows:
trending item removal processing is carried out on the historical error data:
；
wherein,,historical error data results after removing the error trend term, < +.>Representing the result of the ith iteration of the error trend term;
carrying out sub-sequence smoothing, forming a sub-sequence by sample points at the same position in each period of the historical error data, carrying out local weighted regression smoothing on each sub-sequence, and respectively extending a time point before and after the sub-sequence, so as to obtain a new sub-sequence by combination;
Calculating error trend terms of the new subsequence by adopting low-pass filtering, removing the periodic difference, and then calculating error period terms of the new subsequence by the additivity of the time sequence:
；
wherein,,error period term for the (i+1) th iteration of the new subsequence,/and (ii)>For the new sub-sequence(s),error trend terms for the new subsequence;
removing the error period term of the new subsequence to obtain an error period term and an error trend term of the original sequence:
；
；
wherein,,error trend term for the (i+1) th iteration,>representing a locally weighted regression of the data,error period term for the (i+1) th iteration;
judging whether the local weighted regression is converged or not, and if the local weighted regression is not converged, repeating the internal circulation process; if the convergence is carried out, the internal circulation is jumped out, and an error remainder is calculated:
；
wherein,,error remainder for the (i+1) th iteration;
the fundamental wave zero sequence component deviation decomposition module comprises a singular spectrum analysis decomposition unit which is specifically used for:
decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting a singular spectrum analysis method;
history of target voltage transformer with length of history time tFundamental zero sequence component deviation of three-phase voltage It is transformed into a matrix X according to a given embedding dimension K:
；
Singular value decomposition is performed on a matrix X, and a matrix obtained by multiplying the matrix X by the transpose of the matrix X is obtainedAnd is arranged in descending order according to the characteristic values, and is marked as follows: />The characteristic values correspond to the characteristic vectors corresponding to the matrix X>：
；
Setting:；
wherein d is the rank of the matrix X, and rank represents the function of solving the rank;
definition:；
the singular value decomposition of matrix X is:
；
wherein,,；/>for the singular values of matrix X, set +.>Is the singular spectrum of matrix X, +.>Is mainly composed of (a) herba Cistanchis>And->The left eigenvector and the right eigenvector in the eigenvectors of the matrix X are respectively;
each subsequence is reduced to a sequence of length t, specifically as follows: define matrix X asIs then:
；
；
；
if and only ifWhen (I)>Otherwise->The reconstructed sequence is as follows:
；
；
wherein RC represents the reconstructed sequence, n is the sequence number of the reconstructed sequence, m is the base number, K is the row of the reconstructed matrix, L is the column of the reconstructed matrix,elements of the ith row and jth column in the reconstruction matrix,>elements of the ith row and the jth column in the matrix X;
grouping the same-period subsequences appearing in the decomposition by utilizing sequence spectrum analysis and a characteristic value steep slope map, wherein the superposition result of the same-period subsequences is a fundamental wave zero sequence component deviation period item;
the fundamental wave zero sequence component deviation decomposition module comprises an analysis mode decomposition method decomposition unit which is specifically used for:
Decomposing fundamental wave zero sequence component deviation of the historical three-phase voltage by adopting an analytical mode decomposition method;
the fundamental zero sequence component deviation of the historical three-phase voltage is defined according to the following:
；
wherein,,for the fundamental zero sequence component deviation of the historic three-phase voltage, +.>Sampling values for fundamental zero sequence component deviations;
the corresponding frequency is +.>There is->I=1, 2, …, n-1, satisfies:
；
wherein,,dividing frequencies for boundaries;
the method comprises the following steps:
in the above-mentioned method, the step of,for the decomposition function of the ith signal at time t, -/->Is->Shorthand for->=2,3,……，n-1；Is a Hilbert transform;
presetting a specified frequency fc to be less than the frequency fc and obtain a signal component by the above equationAs a fundamental zero sequence component bias trend term.
3. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the voltage transformer error state prediction method of claim 1 when the program is executed by the processor.
4. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the voltage transformer error state prediction method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310315558.8A CN116049629B (en) | 2023-03-29 | 2023-03-29 | Voltage transformer error state prediction method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310315558.8A CN116049629B (en) | 2023-03-29 | 2023-03-29 | Voltage transformer error state prediction method, system, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116049629A CN116049629A (en) | 2023-05-02 |
| CN116049629B true CN116049629B (en) | 2023-07-18 |
Family
ID=86116635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310315558.8A Active CN116049629B (en) | 2023-03-29 | 2023-03-29 | Voltage transformer error state prediction method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116049629B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702630B (en) * | 2023-08-07 | 2023-11-10 | 国网安徽省电力有限公司营销服务中心 | Error iterative evaluation method for capacitive voltage transformer CVT |
| CN116840765B (en) * | 2023-08-31 | 2023-11-07 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
| CN118068253B (en) * | 2024-04-18 | 2024-06-25 | 山东德源电力科技股份有限公司 | High-precision measurement transformer error measurement method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115616470A (en) * | 2022-12-20 | 2023-01-17 | 国网福建省电力有限公司 | Current transformer metering error state prediction method, system, equipment and medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008164374A (en) * | 2006-12-27 | 2008-07-17 | Sbc Co Ltd | Device and method for measuring leakage current |
| CN103091595B (en) * | 2012-07-23 | 2015-09-02 | 南京南瑞继保电气有限公司 | The method of discrimination that a kind of generator terminal voltage mutual inductor once breaks |
| CN107449979B (en) * | 2017-06-19 | 2019-11-29 | 国网湖南省电力公司计量中心 | A kind of Current Voltage state monitoring method and device based on fundamental wave zero sequence feature |
| CN115408864B (en) * | 2022-09-01 | 2023-10-31 | 国网安徽省电力有限公司电力科学研究院 | Electronic transformer error state self-adaptive prediction method, system and equipment |
| CN115587673B (en) * | 2022-11-10 | 2023-04-07 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state prediction method and system |
-
2023
- 2023-03-29 CN CN202310315558.8A patent/CN116049629B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115616470A (en) * | 2022-12-20 | 2023-01-17 | 国网福建省电力有限公司 | Current transformer metering error state prediction method, system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116049629A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116049629B (en) | Voltage transformer error state prediction method, system, equipment and medium | |
| CN110488204B (en) | Energy storage element SOH-SOC combined online estimation method | |
| CN114091766B (en) | CEEMDAN-LSTM-based space load prediction method | |
| Decanini et al. | Robust fault diagnosis in power distribution systems based on fuzzy ARTMAP neural network-aided evidence theory | |
| Kim et al. | Digital twin approach for on-load tap changers using data-driven dynamic model updating and optimization-based operating condition estimation | |
| CN115169232B (en) | Daily peak load prediction method, computer equipment and readable storage medium | |
| Sandoval-Chileño et al. | Robust State of Charge estimation for Li-ion batteries based on Extended State Observers | |
| JP2007240464A (en) | Core monitor unit of boiling water reactor | |
| CN113325357A (en) | Voltage transformer error evaluation method and system based on output time series difference | |
| CN115619025A (en) | Power load triangular fuzzy prediction method based on MEEMD and optimal combination integration | |
| Han et al. | Sensor drift detection based on discrete wavelet transform and grey models | |
| Zubida et al. | Optimal short-time measurements for Hamiltonian learning | |
| CN116701822A (en) | Load electric energy metering method based on sparrow search algorithm and variation modal decomposition | |
| Cevallos et al. | Performance of the estimators weighted least square, extended kalman filter, and the particle filter in the dynamic estimation of state variables of electrical power systems | |
| CN108829983B (en) | Equipment residual life prediction method based on multi-hidden-state fractional Brownian motion | |
| Peng et al. | Collaborative online RUL prediction of multiple assets with analytically recursive Bayesian inference | |
| Yu et al. | Nuclear norm subspace identification for continuous-time stochastic systems based on distribution theory method | |
| CN113960412A (en) | Method and device for processing fault traveling wave signals of power distribution network | |
| CN116702630B (en) | Error iterative evaluation method for capacitive voltage transformer CVT | |
| Liu et al. | Software reliability forecasting: singular spectrum analysis and ARIMA hybrid model | |
| CN111079591B (en) | Bad data restoration method and system based on improved multi-scale principal component analysis | |
| CN112991088A (en) | Monthly power demand prediction method based on VMD-ANFIS-ARIMA | |
| Lin et al. | Battery-supercapacitor state-of-health estimation for hybrid energy storage system using a fuzzy brain emotional learning neural network | |
| Tan et al. | An overview of power quality state estimation | |
| CN115409245A (en) | Prediction auxiliary state estimation method, device, equipment and medium for power system |
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 |