CN112560888B - Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation - Google Patents
Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation Download PDFInfo
- Publication number
- CN112560888B CN112560888B CN202011144451.4A CN202011144451A CN112560888B CN 112560888 B CN112560888 B CN 112560888B CN 202011144451 A CN202011144451 A CN 202011144451A CN 112560888 B CN112560888 B CN 112560888B
- Authority
- CN
- China
- Prior art keywords
- transformer
- xin
- jihe
- circuit resistance
- components
- 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 31
- 238000004804 winding Methods 0.000 title claims abstract description 31
- 230000009466 transformation Effects 0.000 title claims abstract description 15
- 125000002347 octyl group Chemical group [H]C([*])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])[H] 0.000 title claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000003416 augmentation Effects 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- YBJHBAHKTGYVGT-ZKWXMUAHSA-N (+)-Biotin Chemical compound N1C(=O)N[C@@H]2[C@H](CCCCC(=O)O)SC[C@@H]21 YBJHBAHKTGYVGT-ZKWXMUAHSA-N 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- FEPMHVLSLDOMQC-UHFFFAOYSA-N virginiamycin-S1 Natural products CC1OC(=O)C(C=2C=CC=CC=2)NC(=O)C2CC(=O)CCN2C(=O)C(CC=2C=CC=CC=2)N(C)C(=O)C2CCCN2C(=O)C(CC)NC(=O)C1NC(=O)C1=NC=CC=C1O FEPMHVLSLDOMQC-UHFFFAOYSA-N 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000012549 training Methods 0.000 abstract description 2
- 238000013210 evaluation model Methods 0.000 abstract 1
- 230000007774 longterm Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- 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
- 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
Abstract
The invention provides a method and a system for evaluating the short circuit resistance of a transformer winding based on octyl geometric transformation, and belongs to the technical field of power equipment monitoring. According to the method, the collected transformer vibration signals are subjected to octave geometric modal decomposition to obtain a plurality of single components, similarity detection is carried out on all the single components by using Pearson correlation coefficients, a threshold is set, significance analysis is carried out on the single components, and the components are combined, so that Xin Jihe modal components are obtained. And calculating the kurtosis factor of Xin Jihe modal components, presetting default values to form a group of feature vectors, setting an evaluation standard, training a limit learning machine to obtain a Xin Jihe transformation-limit learning machine winding short-circuit resistance evaluation model, and taking the feature vectors as the input of the model to obtain an evaluation result. The method has better instantaneity and higher discrimination accuracy, and can effectively screen potential safety hazards of long-term operation latency of the transformer.
Description
Technical Field
The invention relates to the technical field of power equipment monitoring.
Background
Power transformers carry the important task of transmitting electricity in power systems. The operation environment and the working state are very complex, short-circuit current impact caused by the unresistible short-circuit fault often occurs, and the short-circuit current can lead the winding to be deformed due to the huge electromagnetic force. The winding deformation has a certain cumulative effect. When the deformation is not large, the normal operation of the transformer is slightly influenced; when the deformation of the transformer is accumulated to a certain threshold value, even small overcurrent can cause mechanical failure or insulation breakdown of the transformer, and the power failure fault caused by the excessive overcurrent can bring about huge economic loss. This places higher demands on the detection of the short-circuit resistance of the transformer windings. In the running process of the transformer, the vibration signal of the body contains abundant winding health information, and the characteristic quantity of the vibration signal is extracted and analyzed, so that the short circuit resistance of the transformer winding can be effectively evaluated in real time. The most reliable detection technology at present is off-line detection, namely, after the fault occurs, fault screening and positioning are carried out on the transformer. Although the off-line method has high reliability, the off-line method can cause huge economic loss due to shutdown and off-line caused by the fault of the transformer, large-scale power failure and self damage.
During operation of the transformer, the vibration signal of the body contains rich winding health information, and therefore, many experts and scholars do many works in on-line monitoring of the transformer winding based on the vibration signal. The existing technology for analyzing the vibration signals mainly comprises wavelet analysis, an empirical mode decomposition method and integrated empirical mode decomposition; wavelet analysis: according to the method, the original vibration signals are fitted through selecting wavelet basis functions, so that the energy characteristics of the vibration signals on different frequency bands are obtained, but the wavelet basis functions of the method are difficult to adapt to the signals and need to be selected continuously, and the frequency resolution is reduced along with the increase of the frequency; empirical mode decomposition: the method comprises the steps of firstly, obtaining upper and lower envelope curves of a signal by cubic spline interpolation, calculating the average value of the upper and lower envelope curves, subtracting the average value from an original signal to form a new discrete sequence, and continuously repeating the steps until the average value of the upper and lower envelope curves is zero if the sequence still has a local maximum value or a local minimum value, so as to obtain a plurality of eigen-mode functions, wherein the method has the problem of modal aliasing when frequency components are more and noise is larger, and the decomposition effect is not ideal; aggregate empirical mode decomposition: the method is improved empirical mode decomposition, and uniform Gaussian white noise is added before decomposition so as to reduce modal aliasing, but false components exist after decomposition due to the added noise, and the calculation time is relatively prolonged due to the added noise.
Disclosure of Invention
The invention aims to: in order to solve the problems in the background art, the invention provides a method and a system for evaluating the short-circuit resistance of a transformer winding based on the octave geometric transformation.
The technical scheme is as follows: the invention provides a method for evaluating the short-circuit resistance of a transformer winding based on octyl geometric transformation, which comprises the following steps:
step 1: the acceleration vibration sensor is arranged on the surface of the transformer box body, and discrete vibration signals about amplitude-time are collected in real time;
step 2: performing octave geometric modal decomposition on the acquired discrete vibration signals so as to obtain a plurality of single-component signals;
step 3: traversing all single component signals by using Pearson correlation coefficients, and judging the similarity between the two single component signals; thus obtaining a plurality of groups of Xin Jihe components, and the Pearson correlation coefficient among the single components in each group Xin Jihe of components is positioned in a preset range;
step 4: calculating the kurtosis factor of each Xin Jihe component group; based on a preset default value, each kurtosis factor is formed into a group of augmentation feature vectors;
step 5: establishing an extreme learning machine model, acquiring historical augmentation feature vectors of the transformer in different running states and related to discrete vibration signals according to the steps 1-4, and evaluating the short-circuit resistance of windings of the transformer in different running states based on the model of the transformer; the history augmentation feature vector is used as input of an extreme learning machine model, and the extreme learning machine model is trained and optimized;
step 6: and inputting the real-time augmented feature vector into a trained extreme learning machine model to obtain an evaluation result of the short circuit resistance of the winding of the transformer in the current state.
Further, in the step 2, specifically: sequentially carrying out phase space reconstruction, xin Jihe similar transformation and diagonal averaging on the discrete vibration signals; constructing a track matrix X of the discrete vibration signals according to the following formula when phase space reconstruction is carried out:
wherein m=n- (d-1); τ is the delay time, d is the embedding dimension, n is the signal length, x m An mth sampling signal in the discrete vibration signals; when f max /f s ＜10 -3 D=n/3, otherwise d=1.2× (f s /f max ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein f max Is the maximum peak frequency, f, in the power spectral density of the discrete signal s For the sampling frequency, n is the signal length of the discrete vibration signal.
Further, in the step 3, the Pearson correlation coefficient R > 0.6 and the saliency index P < 0.05 are combined.
Further, in the step 4, the kurtosis factor S of each Xin Jihe component group is calculated by the following formula:
n is the signal length of the discrete vibration signal, s i For the i-th element in the set Xin Jihe component,for the average value of the set Xin Jihe component, x rms Is the root mean square value of the set Xin Jihe of components.
The system for evaluating the short-circuit resistance of the transformer winding based on the octyl geometric transformation comprises an on-site substation upper computer, a cloud platform and a remote dispatching desk upper computer; the on-site substation upper computer comprises a data analysis module and a data sending module, wherein the data analysis module performs octyl geometric mode decomposition on the discrete vibration signals, evaluates the short circuit resistance of windings of the transformer based on the Xin Jihe mode decomposition result, and stores the discrete vibration signals and evaluation results in an SQL database of the on-site substation; the data sending module sets the evaluation result as a data frame, packs the data frame according to an MQTT protocol, and uploads the packed data frame to the cloud platform by adopting a GPRS network; the remote dispatching desk upper computer comprises a data receiving module and a data summarizing, displaying and dispatching module, wherein the data receiving module receives data frames corresponding to each transformer in each field transformer substation on the cloud platform according to an MQTT protocol, decomposes the data frames so as to obtain an evaluation result, and simultaneously stores the evaluation result into an SQL table of the remote dispatching desk so as to establish a history database; and the data summarizing display and scheduling module displays the evaluation results of each transformer by the label, and distributes colors for the evaluation results according to the fault priority, so as to give overhaul prompts.
The beneficial effects are that: compared with the traditional Fourier transform, the invention can clearly show the change of signal components on each time scale along with the change of time, so that the evaluation result has a time label and can accurately reflect the short-circuit resistance along with the change of time; the method has good decomposing capability on non-stationary nonlinear signals and abrupt signals, so that the method has strong robustness and noise reduction effect; meanwhile, all parameters in the method are self-adaptive along with the change of signals, and manual parameter adjustment is not needed. Compared with various empirical mode algorithms, the method has the characteristics of high calculation speed, low time delay and smaller influence of mode aliasing, the real-time monitoring of the Internet of things based on the Xin Jihe mode decomposition algorithm can be realized, and the characteristic quantity representation of each component is more complete due to smaller mode aliasing, so that the evaluation result has higher accuracy.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
fig. 2 is a system configuration diagram of the present invention.
Detailed Description
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
As shown in fig. 1, the invention provides a method for evaluating the short-circuit resistance of a transformer winding based on the octave geometric transformation, which specifically comprises the following steps:
step 1: and the acceleration vibration sensor is arranged at a proper position of the transformer box body, and is acquired by the acquisition card, so that a group of discrete vibration signals about amplitude-time are obtained.
Step 2: the discrete vibration signals obtained are subjected to octave geometric modal decomposition (Symplectic Geometry Mode Decomposition, SGMD) to obtain a plurality of single-component signals.
Step 3: and (3) carrying out similarity test on the plurality of single-component signals by using the Pearson correlation coefficient, combining the two components meeting the condition, traversing all components, and obtaining Xin Jihe components (Symplectic Geometry Component, SGC) containing the same frequency similarity characteristic components.
Step 4: and calculating kurtosis factors of SGCs to form a group of real-time health state feature vectors of the transformer winding, and integrating the characteristics of the transformer, presetting default values to form an augmentation feature vector.
Step 5: and establishing an extreme learning machine (Extreme Learning Machine, ELM) model, carrying out tests on the transformer to be shipped under different running states, acquiring relevant characteristic parameters, and reasonably training the ELM model.
Step 6: and (3) inputting the augmented feature vector formed in the step (4) into a trained extreme learning machine model to obtain an evaluation result of the short circuit resistance of the winding of the transformer in the current state.
In this embodiment, the step 2 specifically includes:
phase space reconstruction of signals and construction of a trajectory matrix according to the Takens theorem, an embedding theorem for phase space reconstruction technique with respect to time series:
wherein m=n- (d-1); τ is the delay time, d is the embedding dimension, n is the signal length, x m An mth sampling signal in the discrete vibration signals; when f max /f s ＜10 -3 D=n/3, otherwise d=1.2× (f s /f max ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein f max Is the maximum peak frequency, f, in the power spectral density of the discrete signal s For sampling frequencyThe rate, n, is the signal length of the discrete vibration signal.
Construction of Hamilton matrix M
A＝X T X
Wherein X is T The transposition of X is realized, and A is a covariance symmetric array;
schursul decomposition is carried out on the matrix M to obtain quadrature Xin Juzhen Q
Wherein H is an upper triangular matrix block in the matrix after Schur decomposition, and R is a real matrix;
calculating eigenvalues (lambda) of the upper triangular matrix H 1 ,λ 2 ,…,λ D ) According to the Hamilton matrix propertyD is the minimum value in the number of rows and columns of the track matrix X, sigma is the characteristic value of the matrix A, Q i Is sigma (sigma) i The reconstructed phase space matrix Z can be obtained by calculating the feature vector and the track matrix:
Z＝Z 1 +Z 2 +…+Z i +…+Z D
phase space matrix single component Z i Converted into Xin Jihe component, for easy calculation, the parameters are defined as follows: phase space matrix Z IJ Representing Z i The elements of the I row and the J column in the matrix, wherein, I is more than or equal to 1 and less than or equal to d 1 and less than or equal to J and less than or equal to m.
Single component matrix Z i A matrix D of m x D is the minimum between m and D, m is the maximum between m and D,Representing the new matrix in this condition equal to the original matrix +.>Representing that the new matrix is a transpose of the original matrix under the condition;
for Z reconstructed according to the above i The matrix is diagonally averaged:
wherein,meaning of reconstructed Z i Column vectors of elements on the kth diagonal of the matrix, q, are the count variables in the sum iteration process. Reconstructed Z i After diagonal averaging, Z i Converted to y k (k is 1 to n). The reconstructed Z is transformed into a matrix Y. Y is a D x n matrix. That is, the discrete time series of length n is decomposed into D discrete time series of length n.
D single component signals can be obtained.
In this embodiment, in the step 3, the Pearson correlation coefficient is used to determine the signal similarity, all components are traversed, the correlation coefficient threshold is set, and the saliency analysis is performed, and when R is greater than 0.6 and P is less than 0.05, the two component components are combined.
In this embodiment, the kurtosis factor S of each Xin Jihe component group is calculated in step 4 by the following formula:
n is the signal length of the discrete vibration signal, s i For the i-th element in the set Xin Jihe component,for the average value of the set Xin Jihe component, x rms Is the root mean square value of the set Xin Jihe of components.
In this embodiment, in the step 5, an ELM (ELM) model of the extreme learning machine is built and trained, and winding evaluation criteria are classified into three categories based on the type of the transformer, and the criteria are shown in table 1:
TABLE 1
As shown in fig. 2, the system for evaluating the short-circuit resistance of the transformer winding based on the octave geometric transformation comprises an on-site substation upper computer, a cloud platform and a remote dispatching desk upper computer; the on-site substation upper computer comprises a data analysis module and a data transmission module, wherein the data analysis module carries out octyl geometric mode decomposition on discrete vibration signals, evaluates the short circuit resistance of windings of the transformer based on the Xin Jihe mode decomposition result, stores the discrete vibration signals and evaluation results into an SQL database of the on-site substation, and sets the evaluation results into data frames, packs the data frames according to an MQTT protocol and uploads the data frames to the cloud platform by adopting a GPRS network; the remote dispatching desk upper computer comprises a data receiving module and a data summarizing, displaying and dispatching module, wherein the data receiving module receives data frames corresponding to each transformer in each field transformer substation according to an MQTT protocol, decomposes the data frames to obtain an evaluation result, stores the evaluation result into a specified SQL table, and establishes a historical database; and the data summarizing display and scheduling module displays the evaluation results of each transformer by the label, and distributes colors for the evaluation results according to the fault priority, so as to give overhaul prompts.
And constructing an SQL database on the site console and the cloud platform, marking the characteristic quantity of the transformer by a time stamp, storing the characteristic quantity, and optimizing SGMD-ELM by using historical data. And effectively monitoring and evaluating the multi-transformer by using a GPRS network, uploading relevant characteristics of vibration signals of each transformer to an upper computer of a remote monitoring station, and monitoring in real time.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the spirit of the present invention.
Claims (5)
1. The method for evaluating the short circuit resistance of the transformer winding based on the octyl geometric transformation is characterized by comprising the following steps of:
step 1: the acceleration vibration sensor is arranged on the surface of a box body of the transformer, and discrete vibration signals about amplitude-time are collected in real time;
step 2: performing octave geometric modal decomposition on the acquired discrete vibration signals so as to obtain a plurality of single-component signals;
step 3: traversing all single component signals by using Pearson correlation coefficients, and judging the similarity between the two single component signals; thus obtaining a plurality of groups of Xin Jihe components, and the Pearson correlation coefficient among the single components in each group Xin Jihe of components is positioned in a preset range;
step 4: calculating kurtosis factors of each group of Xin Jihe components, and forming each kurtosis factor into a group of amplified feature vectors based on a preset default value;
step 5: establishing an extreme learning machine model, acquiring historical augmentation feature vectors of the transformer in different running states and related to discrete vibration signals according to the steps 1-4, and evaluating the short-circuit resistance of windings of the transformer in different running states based on the model of the transformer; the history augmentation feature vector is used as input of an extreme learning machine model, and the extreme learning machine model is trained and optimized;
step 6: and inputting the real-time augmented feature vector into a trained extreme learning machine model to obtain an evaluation result of the short circuit resistance of the winding of the transformer in the current state.
2. The method for evaluating the short-circuit resistance of the transformer winding based on the octave geometry transformation according to claim 1, wherein the step 2 is specifically: sequentially carrying out phase space reconstruction, xin Jihe similar transformation and diagonal averaging on the discrete vibration signals; constructing a track matrix X of the discrete vibration signals according to the following formula when phase space reconstruction is carried out:
wherein m=n- (d-1); τ is the delay time, d is the embedding dimension, x m An mth sampling signal in the discrete vibration signals; when f max /f s ＜10 -3 D=n/3, otherwise d=1.2× (f s /f max ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein f max Is the maximum peak frequency, f, in the power spectral density of the discrete signal s For the sampling frequency, n is the signal length of the discrete vibration signal.
3. The method for evaluating the short-circuit resistance of a transformer winding based on the octave geometry transformation according to claim 1, wherein the Pearson correlation coefficient R > 0.6 and the two components of the saliency index P < 0.05 are combined in the step 3.
4. The method for evaluating the short-circuit resistance of a transformer winding based on the octave geometry transformation according to claim 1, wherein the kurtosis factor S of each group Xin Jihe of components is calculated in the step 4 by the following formula:
n is the signal length of the discrete vibration signal, s i For the i-th element in the set Xin Jihe component,for the average value of the set Xin Jihe component, x rms Is the root mean square value of the set Xin Jihe of components.
5. The system for evaluating the short-circuit resistance of the transformer winding based on the octave geometric transformation according to claim 1, wherein the system comprises a field transformer substation upper computer, a cloud platform and a remote dispatching desk upper computer; the on-site substation upper computer comprises a data analysis module and a data sending module, wherein the data analysis module performs octyl geometric mode decomposition on the discrete vibration signals, evaluates the short circuit resistance of windings of the transformer based on the Xin Jihe mode decomposition result, and stores the discrete vibration signals and evaluation results in an SQL database of the on-site substation; the data sending module sets the evaluation result as a data frame, packs the data frame according to an MQTT protocol, and uploads the packed data frame to the cloud platform by adopting a GPRS network; the remote dispatching desk upper computer comprises a data receiving module and a data summarizing, displaying and dispatching module, wherein the data receiving module receives data frames corresponding to each transformer in each field transformer substation on the cloud platform according to an MQTT protocol, decomposes the data frames so as to obtain an evaluation result, and simultaneously stores the evaluation result into an SQL table of the remote dispatching desk so as to establish a history database; and the data summarizing display and scheduling module displays the evaluation results of each transformer by the label, and distributes colors for the evaluation results according to the fault priority, so as to give overhaul prompts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011144451.4A CN112560888B (en) | 2020-10-23 | 2020-10-23 | Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011144451.4A CN112560888B (en) | 2020-10-23 | 2020-10-23 | Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112560888A CN112560888A (en) | 2021-03-26 |
| CN112560888B true CN112560888B (en) | 2024-02-23 |
Family
ID=75042800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011144451.4A Active CN112560888B (en) | 2020-10-23 | 2020-10-23 | Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560888B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114659785A (en) * | 2021-12-27 | 2022-06-24 | 三一重能股份有限公司 | Fault detection method and device for transmission chain of wind driven generator |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103163420A (en) * | 2011-12-08 | 2013-06-19 | 沈阳工业大学 | Intelligent power transformer on-line state judgment method |
| CN106771527A (en) * | 2016-12-28 | 2017-05-31 | 国网浙江省电力公司电力科学研究院 | A kind of method for early warning and device of the resistance to shorting electric current based on transformer |
| CN111273100A (en) * | 2020-02-20 | 2020-06-12 | 浙江大学 | Power transformer winding state evaluation method based on vibration phase |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109884459B (en) * | 2019-01-30 | 2020-12-01 | 国网浙江省电力有限公司电力科学研究院 | Intelligent online diagnosis and positioning method for winding deformation of power transformer |
-
2020
- 2020-10-23 CN CN202011144451.4A patent/CN112560888B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103163420A (en) * | 2011-12-08 | 2013-06-19 | 沈阳工业大学 | Intelligent power transformer on-line state judgment method |
| CN106771527A (en) * | 2016-12-28 | 2017-05-31 | 国网浙江省电力公司电力科学研究院 | A kind of method for early warning and device of the resistance to shorting electric current based on transformer |
| CN111273100A (en) * | 2020-02-20 | 2020-06-12 | 浙江大学 | Power transformer winding state evaluation method based on vibration phase |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112560888A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112327219A (en) | Distribution transformer fault diagnosis method with automatic feature mining and automatic parameter optimization | |
| CN112147444B (en) | Power transformer working state monitoring method and system | |
| CN110070102B (en) | Method for establishing sequence-to-sequence model for identifying power quality disturbance type | |
| CN111582551A (en) | Method and system for predicting short-term wind speed of wind power plant and electronic equipment | |
| CN110796121A (en) | Method for diagnosing mechanical fault of high-voltage circuit breaker by S transformation and optimized random forest | |
| CN105572501A (en) | Power quality disturbance identification method based on SST conversion and LS-SVM | |
| CN113379164B (en) | Load prediction method and system based on deep self-attention network | |
| CN111878322B (en) | Wind power generator device | |
| CN112986870A (en) | Distributed power transformer winding state monitoring method and system based on vibration method | |
| CN112560888B (en) | Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation | |
| CN111694827B (en) | Classification interpolation method and system for missing values of power equipment state monitoring data | |
| CN111861023A (en) | Statistical-based hybrid wind power prediction method and device | |
| CN112083328A (en) | Fault diagnosis method, system and device for high-voltage circuit breaker | |
| CN208076016U (en) | A kind of GIL On-line Faults monitoring system based on vibration signal support vector machines | |
| CN114298080A (en) | Hydro-turbo generator set monitoring method based on throw data mining | |
| CN115684908A (en) | State monitoring method for power GIS equipment, storage medium and electronic device | |
| CN116644361A (en) | Overhead transmission line fault diagnosis method and computer readable medium | |
| CN114157023B (en) | Distribution transformer early warning information acquisition method | |
| CN114970610A (en) | Power transformer state identification method and device based on gram angular field enhancement | |
| CN114838923A (en) | Fault diagnosis model establishing method and fault diagnosis method for on-load tap-changer | |
| CN114114001A (en) | GIS equipment disconnecting switch mechanical state monitoring method and system | |
| CN114137915A (en) | Fault diagnosis method for industrial equipment | |
| CN103018658A (en) | Circuit board health condition monitoring method based on volt-ampere characteristic curves | |
| Wenjiao et al. | A Fault Diagnosis Model of High-Voltage Circuit Breaker Based on Multidimensional Features of Vibration Signal | |
| CN116243230A (en) | On-line fault diagnosis method for voltage transformer |
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 |