CN110929673A - Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) - Google Patents
Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) Download PDFInfo
- Publication number
- CN110929673A CN110929673A CN201911212789.6A CN201911212789A CN110929673A CN 110929673 A CN110929673 A CN 110929673A CN 201911212789 A CN201911212789 A CN 201911212789A CN 110929673 A CN110929673 A CN 110929673A
- Authority
- CN
- China
- Prior art keywords
- svm
- transformer winding
- cgwo
- itd
- permutation entropy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004804 winding Methods 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012706 support-vector machine Methods 0.000 title claims description 16
- 230000009466 transformation Effects 0.000 title description 5
- 239000013598 vector Substances 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 25
- 230000001133 acceleration Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 12
- 238000012885 constant function Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 17
- 230000000694 effects Effects 0.000 abstract description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000001845 vibrational spectrum Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 241000282461 Canis lupus Species 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
A transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM is disclosed. The method comprises the following steps: collecting vibration signals of a transformer winding in normal and fault states in a switching process; and decomposing the vibration signal by adopting the ITD, performing complex calculation on the decomposed signal by utilizing the permutation entropy to extract a feature vector, training the feature vector as the input quantity of the CWGO-SVM, and comparing the feature vector with the GWO-SVM and the SVM. The method can effectively extract the fault characteristics of the transformer winding, has high diagnosis result precision, realizes intelligent diagnosis of the transformer winding fault, can find the fault at the early stage of the latent fault, has stronger operability, and has the technical effect superior to that of the traditional SVM.
Description
Technical Field
The invention belongs to the technical field of transformer winding fault diagnosis, and particularly relates to a transformer winding vibration signal identification method based on ITD (inverse transformation induced breakdown) permutation entropy and CGWO-SVM (Carrier-support vector machine).
Background
In recent years, the power grid in China gradually moves towards extra-high voltage, long-distance large-capacity power transmission and smart power grids, the mutual association in the system is gradually diversified, combined and greatly enlarged, and the requirement on the continuous and stable operation capacity of a single link in the system is more and more strict. The condition that each single link in the power system does not fail is a precondition that the whole framework does not fail, and the condition is an indispensable part in constructing a strong smart grid. According to the national grid operation safety assessment report of the national grid company 2001-2010 totaling ten years, the main factors of abnormal operation of the power system include four types of power equipment abnormality, natural disasters, worker responsibility accidents and the like. According to the relevant data, the abnormal operation of the power grid caused by the single equipment failure of a single link accounts for 37.1% -61.1% of the total abnormal operation of the power grid, the proportion of the abnormal operation of the power grid in some years is even more than half, and the average value of 2001-2010 also reaches 45.9%, which is a high value proportion which cannot be ignored. The combination of all statistical results can lead to that the fault state of single equipment in a single link gradually becomes a core factor of the abnormal operation of the whole system. Because winding faults caused by insufficient short-circuit resistance of the transformer are increased year by year and increasingly become the main reason of the faults of the power transformer, a method capable of accurately judging the mechanical state of the winding is urgently needed.
Conventional transformer winding fault detection methods either require the transformer to be taken out of service or have hysteresis in the detection of a latent fault, making it difficult to detect the fault early in the occurrence of the latent fault. Existing transformer fault detection analysis methods include vibration analysis, which has many advantages, such as no electrical connection to the transformer bushings and lead-outs, no interference with transformer operation, and vibration spectrum sensitive to many anomalies of the transformer. The vibration spectrum on the transformer box can reflect the health degree of the transformer comprising the iron core and the winding, wherein the 100Hz amplitude of the vibration spectrum is an important consideration factor for estimating the health degree and fault judgment of the transformer. Therefore, it is necessary to obtain and further analyze the vibration spectrum on the transformer tank, and find a relevant way for analyzing the working state of the transformer by using the vibration spectrum.
Because the existing transformer winding fault detection method has low diagnosis precision and needs to improve the diagnosis effect, the intelligent diagnosis of the transformer winding fault and the fault finding in the early stage of the latent fault are urgently needed to be realized with high precision, and the method needs strong operability.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for identifying the transformer winding vibration signal based on the ITD permutation entropy and the CGWO-SVM, and the method has the advantages of high diagnosis result accuracy, simple structure and strong operability.
Specifically, the invention provides a power transformer winding vibration signal identification method based on ITD (empirical Entropy) and CGWO-SVM (compact finite impulse support vector machine) analysis, so as to realize accurate diagnosis of early latent faults of a power transformer winding. Therefore, the invention introduces ITD (Intrinsic Time-scale decomposition) into the fault diagnosis of the power transformer winding, decomposes a plurality of PR components, quantitatively describes the first PR components containing equipment signals as characteristic quantities by using the arrangement entropy as CGWO-SVM input quantity, and establishes a Support Vector Machine (SVM) fault diagnosis model of chaotic grey wolf optimization (chaotic grey wolf optimizer), thereby realizing the intelligent diagnosis of the power transformer winding fault.
The invention provides a transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine), which comprises the following steps of:
loading an original signal of a transformer winding;
carrying out ITD decomposition;
carrying out PR component permutation entropy calculation;
CGWO-SVM input training;
and carrying out accuracy comparison.
Specifically, the invention provides a transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (space-vector machine), which comprises the following steps of:
step 1) selecting a transformer to be detected, determining an acceleration sensor according to requirements to ensure proper sensitivity and device reliability, acquiring and loading vibration signals of a transformer winding in a normal state and vibration signals of a transformer winding in a fault state through the acceleration sensor, and preprocessing the vibration signals;
step 2) carrying out ITD decomposition on the acquired, loaded and preprocessed transformer winding vibration signals, and constructing a characteristic vector to be used as the input of the SVM;
the ITD decomposition comprises the following specific steps:
(a) assuming that X (i) is an original signal to be analyzed, i is more than or equal to 0, a base line extraction operator L is defined before decomposition, and a residual signal left after the base line is removed from the original signal becomes an inherent rotation component; the expression of the first decomposition is:
X(i)＝LXi+(1-L)Xi＝Li+Xi
Liextracting an operator for the ith baseline; wherein XiFor the signal to be decomposed, L is a defined baseline extraction algorithm; (b) determining an extremum X of the signals X (i)kAnd corresponding time tkK is 1, 2, 3, …, M, where M is the number of extreme points, and a baseline extraction operator L is calculatedk+1Comprises the following steps:
wherein k is 1, 2, …, M-2; 0< a < 1;
(c) the piecewise linear baseline extraction operator that defines the signal is as follows:
(d) will baseline signal LkRepeating the above steps (a) - (c) as the original signal until the baseline signal is a monotonic or constant function; the original signal X (i) is decomposedComprises the following steps:
X(i)＝LXi+(1-L)Xi＝Li+Xi＝(H+L)LXi+HXi＝＝Ht 1+Ht 2+…+Ht p+Lt P
wherein H is an inherent rotational component, Ht iIs the intrinsic rotational component, L, separated by the ith iterationt PIs a monotonic trend or residual term, p is an integer greater than 1;
(e) when the transformer winding is in different fault states, the distribution of the generated vibration signal energy along with the frequency is different; after the signal is subjected to ITD decomposition, the frequency components contained in the n-1 PR components are different, and PR is obtained by adopting ITD decomposition1、PR2、…、PRnRespectively calculate their permutation entropy PE1、PE2、…、PEj、…、PEn，EjThe permutation entropy of the jth PR component accounts for the proportion of the total permutation entropy PE, where j is 1, 2, …, n; the first five PE values account for more than 95% of the total energy by adding, and the characteristics of the signal are completely characterized, so the first 5 PE values are selected as characteristic quantities;
and 3) training the CGWO-SVM, inputting the feature vector constructed in the step 2) into the CGWO-SVM, training the CGWO-SVM, and inputting the transformer winding vibration signal data acquired in real time into the trained CGWO-SVM, so as to judge the fault mode of the transformer winding.
According to one embodiment, when the acceleration sensor is installed in the step 1), the positions of the selected measuring points are respectively the top, the side, the back and the front of the transformer.
According to one embodiment, the position of the selected measuring point is arranged on top of the transformer when the acceleration sensor is mounted in step 1).
According to one embodiment, in step 1), the acceleration sensor is selected from an electric acceleration sensor LC0154J from lancet.
According to one embodiment, the fault state of the transformer winding refers to three fault conditions of falling of a cushion block of the transformer winding, radial extension of the winding and torsion of the winding. 7. The transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM of claim 6, wherein in step 2) (b), a is 0.5.
According to one embodiment, during the training of the step 3), the feature quantity is normalized to be between [0, 1] by using mapminmax of the matlab, and then the training and prediction of the CGWO-SVM are carried out.
The invention has the following beneficial effects:
1. the ITD adopted by the invention can overcome the problems of relatively serious endpoint effect and false component in Empirical Mode Decomposition (EMD) and Local Mean Decomposition (LMD), and is suitable for extracting the permutation entropy after ITD decomposition as the characteristic quantity.
2. The invention does not need a large amount of data to train the CGWO-SVM, and has higher diagnosis precision.
3. The diagnosis effect of the invention on OLTC is obviously better than that of the traditional SVM.
4. The invention can realize intelligent diagnosis of the transformer winding fault.
5. The invention can find the fault at the early stage of the latent fault and has strong operability.
Drawings
FIG. 1 is a flow chart of a transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM according to the present invention;
fig. 2 is a mounting diagram of a mounting position of a vibration sensor according to the present invention.
Detailed Description
The invention is further described below. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
According to an embodiment of the invention, fig. 1 is a flowchart of a transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM according to the invention, and the transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM includes:
loading an original signal of a transformer winding;
carrying out ITD decomposition;
carrying out PR component permutation entropy calculation;
CGWO-SVM input training;
and carrying out accuracy comparison.
In an embodiment of the invention, the method can identify four working conditions of normal winding of the transformer, falling of a winding cushion block, radial extension of the winding and torsion of the winding, wherein the falling of the winding cushion block, the radial extension of the winding and the torsion of the winding are main faults, and the method for identifying the vibration signal of the winding of the transformer based on the ITD array entropy and the CGWO-SVM comprises the following steps:
step 1) selecting a transformer to be detected, determining an acceleration sensor according to requirements of measuring range, precision and anti-interference capacity to ensure proper sensitivity and device reliability, collecting vibration signals of a transformer winding in a normal state and vibration signals of a transformer winding in a fault state through the acceleration sensor, and preprocessing the vibration signals.
Fig. 2 is a mounting diagram of a mounting position of a vibration sensor according to the present invention. In the installation of the acceleration sensor, the positions of the selected measuring points are respectively the top, the side, the back and the front of the transformer.
Preferably, the location of the selection point is arranged on top of the transformer.
Preferably, the acceleration sensor is an electric acceleration sensor LC0154J from lancet company. And 2) carrying out ITD decomposition on the acquired transformer winding vibration signals, and constructing a characteristic vector to be used as the input of the SVM.
The ITD decomposition comprises the following specific steps:
(a) assuming that X (i) is an original signal to be analyzed, i is more than or equal to 0, a base line extraction operator L is defined before decomposition, and a residual signal left after the base line is removed from the original signal becomes an inherent rotation component; the expression of the first decomposition is:
X(i)＝LXi+(1-L)Xi＝Li+Xi
Liextracting an operator for the ith baseline;wherein XiFor the signal to be decomposed, L is a defined baseline extraction algorithm; (b) determining an extremum X of the signals X (i)kAnd corresponding time tkK is 1, 2, 3, …, M, where M is the number of extreme points, and a baseline extraction operator L is calculatedk+1Comprises the following steps:
wherein k is 1, 2, …, M-2; 0< a < 1;
(c) the piecewise linear baseline extraction operator that defines the signal is as follows:
(d) will baseline signal LkRepeating the above steps (a) - (c) as the original signal until the baseline signal is a monotonic or constant function; the original signal x (i) is decomposed into:
X(i)＝LXi+(1-L)Xi＝Li+Xi＝(H+L)LXi+HXi＝＝Ht 1+Ht 2+…+Ht p+Lt P
wherein H is an inherent rotational component, Ht iIs the intrinsic rotational component, L, separated by the ith iterationt PIs a monotonic trend or residual term, p is an integer greater than 1;
(e) when the transformer winding is in different fault states, the distribution of the generated vibration signal energy along with the frequency is different; after the signal is subjected to ITD decomposition, the frequency components contained in the n-1 PR components are different, and PR is obtained by adopting ITD decomposition1、PR2、…、PRnRespectively calculate their permutation entropy PE1、PE2、…、PEj、…、PEn，EjThe permutation entropy of the jth PR component accounts for the proportion of the total permutation entropy PE, where j is 1, 2, …, n; since the first five PE values together account for more than 95% of the total energy, the signal is completely characterizedThus, the first 5 are selected as the feature quantities;
and 3) training the CGWO-SVM, inputting the feature vector constructed in the step 2) into the CGWO-SVM, training the CGWO-SVM, and inputting the transformer winding vibration signal data acquired in real time into the trained CGWO-SVM, so as to judge the fault mode of the transformer winding.
Preferably, their permutation entropy PE is calculated1、PE2、PE3、PE4And PE5Mixing PE1、PE2、PE3、PE4And PE5As a feature vector for transformer winding fault diagnosis.
And 3) training the CGWO-SVM, inputting the feature vector constructed in the step 2) into the CGWO-SVM, training the CGWO-SVM, and inputting test data into the trained SVM so as to judge the fault mode of the transformer winding.
Further, the method of the present invention further comprises: and 4) comparing the diagnosis effect of the CGWO-SVM based on the permutation entropy characteristic quantity on the transformer winding with the traditional SVM.
The following classification is made on 40 groups of characteristic vector data of each working condition of the four working conditions of normal transformer winding, falling off of a winding cushion block, radial extension of the winding and torsion of the winding: the front 30 groups of feature vectors of each working condition are used for training a diagnostic model, and the total of 120 groups of training samples of 4 working conditions; the last 10 sets of feature vectors for each condition were used to test the diagnostic accuracy, with a total of 40 test samples for 4 conditions. These samples were input to CGWO-SVM, SVM and GWO-SVM for training and prediction was performed on the 40 groups of data, and table 1 is a comparison of the prediction results of the various SVMs.
TABLE 1
As can be seen from the table 1, the transformer winding based on the ITD and the CWO-SVM can effectively identify the fault type, wherein the prediction accuracy is respectively improved by 11.14% -40%, 2.36% -30%, 1.57% -10% and 0.6% -30% aiming at four working conditions of normal transformer winding, falling-off of winding cushion blocks, radial extension of winding and torsion of winding, and the diagnosis effect of the invention is superior to that of the traditional GWO-SVM and SVM in all aspects.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (8)
1. A transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM is characterized by comprising the following steps:
loading an original signal of a transformer winding;
carrying out ITD decomposition;
carrying out PR component permutation entropy calculation;
CGWO-SVM input training;
and carrying out accuracy comparison.
2. A transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM is characterized by comprising the following steps:
step 1) selecting a transformer to be detected, determining an acceleration sensor according to requirements to ensure proper sensitivity and device reliability, acquiring and loading vibration signals of a transformer winding in a normal state and vibration signals of a transformer winding in a fault state through the acceleration sensor, and preprocessing the vibration signals;
step 2) carrying out ITD decomposition on the acquired, loaded and preprocessed transformer winding vibration signals, and constructing a characteristic vector to be used as the input of the SVM;
the ITD decomposition comprises the following specific steps:
(a) assuming that X (i) is an original signal to be analyzed, i is more than or equal to 0, a base line extraction operator L is defined before decomposition, and a residual signal left after the base line is removed from the original signal becomes an inherent rotation component; the expression of the first decomposition is:
X(i)＝LXi+(1-L)Xi＝Li+Xi
Liextracting an operator for the ith baseline; wherein XiFor the signal to be decomposed, L is a defined baseline extraction algorithm; (b) determining an extremum X of the signals X (i)kAnd corresponding time tkK is 1, 2, 3, …, M, where M is the number of extreme points, and a baseline extraction operator L is calculatedk+1Comprises the following steps:
wherein k is 1, 2, …, M-2; 0< a < 1;
(c) the piecewise linear baseline extraction operator that defines the signal is as follows:
(d) will baseline signal LkRepeating the above steps (a) - (c) as the original signal until the baseline signal is a monotonic or constant function; the original signal x (i) is decomposed into:
in the formula, H is an inherent rotational component,
is the intrinsic rotational component separated by the ith iteration,
is a monotonic trend or residual term, p is an integer greater than 1;
(e) the transformer winding is inWhen in the same fault state, the energy of the generated vibration signal is also different along with the distribution of the frequency; after the signal is subjected to ITD decomposition, the frequency components contained in the n-1 PR components are different, and PR is obtained by adopting ITD decomposition1、PR2、…、PRnRespectively calculate their permutation entropy PE1、PE2、…、PEj、…、PEn，EjThe permutation entropy of the jth PR component accounts for the proportion of the total permutation entropy PE, where j is 1, 2, …, n; the first five PE values account for more than 95% of the total energy by adding, and the characteristics of the signal are completely characterized, so the first 5 PE values are selected as characteristic quantities;
and 3) training the CGWO-SVM, inputting the feature vector constructed in the step 2) into the CGWO-SVM, training the CGWO-SVM, and inputting the transformer winding vibration signal data acquired in real time into the trained CGWO-SVM, so as to judge the fault mode of the transformer winding.
3. The transformer winding vibration signal identification method based on ITD (integrated circuit device) permutation entropy and CGWO-SVM (support vector machine) as claimed in claim 2, wherein when the acceleration sensor is installed in the step 1), the positions of the selected measuring points are respectively the top, the side, the back and the front of the transformer.
4. The transformer winding vibration signal recognition method based on ITD permutation entropy and CGWO-SVM of claim 2, wherein the position of the selected measuring point is set on the top of the transformer when the acceleration sensor is installed in the step 1).
5. The transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM of claim 3 or 4, wherein in the step 1), the acceleration sensor selects an electric acceleration sensor LC0154J of Lance corporation.
6. The transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM of claim 5, wherein: the fault state of the transformer winding refers to three fault conditions of falling of a cushion block of the transformer winding, radial extension of the winding and torsion of the winding.
7. The transformer winding vibration signal identification method based on ITD permutation entropy and CGWO-SVM of claim 6, wherein in step 2) (b), a is 0.5.
8. The method for identifying the OLTC transformer winding vibration signal based on the ITD permutation entropy and the CGWO-SVM as recited in claim 7, wherein in the training of the step 3), the feature quantity is normalized to be between [0, 1] by using mapminmax of matlab, and then the training and prediction of the CGWO-SVM are carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911212789.6A CN110929673A (en) | 2019-12-02 | 2019-12-02 | Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911212789.6A CN110929673A (en) | 2019-12-02 | 2019-12-02 | Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929673A true CN110929673A (en) | 2020-03-27 |
Family
ID=69848134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911212789.6A Pending CN110929673A (en) | 2019-12-02 | 2019-12-02 | Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929673A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111751763A (en) * | 2020-06-08 | 2020-10-09 | 武汉大学 | Power transformer winding fault diagnosis method based on GSMallat-NIN-CNN network |
| CN112729531A (en) * | 2020-12-25 | 2021-04-30 | 国网浙江省电力有限公司电力科学研究院 | Distribution transformer equipment fault studying and judging method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2012100373A4 (en) * | 2011-04-05 | 2012-05-03 | Airservice Digital Pty Ltd | Retail Venue Ordering System and Method |
| CN104155108A (en) * | 2014-07-21 | 2014-11-19 | 天津大学 | Rolling bearing failure diagnosis method base on vibration temporal frequency analysis |
| CN106355192A (en) * | 2016-08-16 | 2017-01-25 | 温州大学 | Support vector machine method based on chaos and grey wolf optimization |
| CN106789359A (en) * | 2017-02-15 | 2017-05-31 | 广东工业大学 | A kind of net flow assorted method and device based on grey wolf algorithm |
| CN107450085A (en) * | 2017-06-19 | 2017-12-08 | 昆明理工大学 | A kind of small Cycle Slips Detection based on ITD fuzzy entropies |
| CN108398252A (en) * | 2018-02-28 | 2018-08-14 | 河海大学 | OLTC mechanical failure diagnostic methods based on ITD and SVM |
| CN109916628A (en) * | 2019-04-04 | 2019-06-21 | 哈尔滨理工大学 | Based on the Fault Diagnosis of Roller Bearings for improving multiple dimensioned amplitude perception arrangement entropy |
| CN110146293A (en) * | 2019-06-04 | 2019-08-20 | 昆明理工大学 | A kind of Fault Diagnosis of Roller Bearings based on PCA and ELM |
-
2019
- 2019-12-02 CN CN201911212789.6A patent/CN110929673A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2012100373A4 (en) * | 2011-04-05 | 2012-05-03 | Airservice Digital Pty Ltd | Retail Venue Ordering System and Method |
| CN104155108A (en) * | 2014-07-21 | 2014-11-19 | 天津大学 | Rolling bearing failure diagnosis method base on vibration temporal frequency analysis |
| CN106355192A (en) * | 2016-08-16 | 2017-01-25 | 温州大学 | Support vector machine method based on chaos and grey wolf optimization |
| CN106789359A (en) * | 2017-02-15 | 2017-05-31 | 广东工业大学 | A kind of net flow assorted method and device based on grey wolf algorithm |
| CN107450085A (en) * | 2017-06-19 | 2017-12-08 | 昆明理工大学 | A kind of small Cycle Slips Detection based on ITD fuzzy entropies |
| CN108398252A (en) * | 2018-02-28 | 2018-08-14 | 河海大学 | OLTC mechanical failure diagnostic methods based on ITD and SVM |
| CN109916628A (en) * | 2019-04-04 | 2019-06-21 | 哈尔滨理工大学 | Based on the Fault Diagnosis of Roller Bearings for improving multiple dimensioned amplitude perception arrangement entropy |
| CN110146293A (en) * | 2019-06-04 | 2019-08-20 | 昆明理工大学 | A kind of Fault Diagnosis of Roller Bearings based on PCA and ELM |
Non-Patent Citations (1)
| Title |
|---|
| 程军圣等 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111751763A (en) * | 2020-06-08 | 2020-10-09 | 武汉大学 | Power transformer winding fault diagnosis method based on GSMallat-NIN-CNN network |
| CN111751763B (en) * | 2020-06-08 | 2021-08-10 | 武汉大学 | Power transformer winding fault diagnosis method based on GSMallat-NIN-CNN network |
| CN112729531A (en) * | 2020-12-25 | 2021-04-30 | 国网浙江省电力有限公司电力科学研究院 | Distribution transformer equipment fault studying and judging method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | Fault diagnosis of a power transformer using an improved frequency-response analysis | |
| CN109839263B (en) | GIS (geographic information System) feature extraction and mechanical defect diagnosis method based on vibration information | |
| CN105547465A (en) | Transformer vibration signal winding state feature extraction method | |
| CN109406949B (en) | Power distribution network early fault detection method and device based on support vector machine | |
| CN110728257B (en) | Transformer winding fault monitoring method based on vibration gray level image | |
| Yang et al. | Fault identification for circuit breakers based on vibration measurements | |
| CN109029959B (en) | Method for detecting mechanical state of transformer winding | |
| CN109581270B (en) | Method for rapidly identifying CVT fault based on wavelet multi-scale transformation | |
| CN110991481B (en) | High-voltage shunt reactor internal loosening fault diagnosis method based on cross wavelet transformation | |
| CN110929673A (en) | Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) | |
| CN108398252A (en) | OLTC mechanical failure diagnostic methods based on ITD and SVM | |
| CN112149569B (en) | Voiceprint fault diagnosis method of transformer based on fuzzy C-means clustering algorithm | |
| CN113553930A (en) | Method for diagnosing mechanical fault of on-load tap-changer of transformer | |
| CN112083328A (en) | Fault diagnosis method, system and device for high-voltage circuit breaker | |
| CN110703078A (en) | GIS fault diagnosis method based on spectral energy analysis and self-organizing competition algorithm | |
| CN111551352B (en) | Method and system for detecting state of breaker of GIS (geographic information System) equipment | |
| CN114325361A (en) | Transformer tap switch state online monitoring method based on vibration principle | |
| CN104778348A (en) | Voltage sag action characteristic modeling method of low-voltage release | |
| CN109270383B (en) | Non-invasive charging pile automatic detection method | |
| CN113238165A (en) | Reactor turn-to-turn short circuit fault detection method based on IFRA and SVM | |
| CN115343579B (en) | Power grid fault analysis method and device and electronic equipment | |
| Hosseini | Short circuit fault classification and location in transmission lines using a combination of wavelet transform and support vector machines | |
| CN113705637B (en) | Method, system, equipment and readable storage medium for detecting mechanical faults of circuit breaker | |
| CN116340810A (en) | Transformer outgoing line part partial discharge diagnosis method and device based on random forest | |
| CN115728628A (en) | On-line monitoring and early warning method and device for circuit breaker control loop fault |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |