CN112287953A - Method and system for GIS insulation defect category identification - Google Patents
Method and system for GIS insulation defect category identification Download PDFInfo
- Publication number
- CN112287953A CN112287953A CN201910671136.8A CN201910671136A CN112287953A CN 112287953 A CN112287953 A CN 112287953A CN 201910671136 A CN201910671136 A CN 201910671136A CN 112287953 A CN112287953 A CN 112287953A
- Authority
- CN
- China
- Prior art keywords
- prps
- gis
- partial discharge
- map data
- svm classifier
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 80
- 238000009413 insulation Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 40
- 102100025142 Beta-microseminoprotein Human genes 0.000 claims abstract description 59
- 101000576812 Homo sapiens Beta-microseminoprotein Proteins 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 10
- 239000002923 metal particle Substances 0.000 claims description 6
- 238000005339 levitation Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 73
- 238000012360 testing method Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 5
- 239000000725 suspension Substances 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 229910052751 metal Inorganic materials 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000003822 epoxy resin Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 229920000647 polyepoxide Polymers 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
Abstract
The invention discloses a method for identifying the type of GIS insulation defects, which comprises the following steps: the training step comprises: (1) collecting case PRPS partial discharge map data and preprocessing the data; (2) extracting effective characteristic quantity to construct a characteristic space; (3) constructing a multi-core SVM classifier, inputting the feature space into the multi-core SVM classifier by adopting a multi-core function, and training the multi-core SVM classifier so as to enable the multi-core SVM classifier to output GIS insulation defect categories corresponding to the feature spaces; the identification step comprises: (a) acquiring PRPS partial discharge map data of GIS equipment to be identified, and preprocessing the PRPS partial discharge map data; (b) extracting effective characteristic quantity to construct a characteristic space; (c) inputting the feature space into the trained multi-core SVM classifier, and outputting a GIS insulation defect type recognition result by the multi-core SVM classifier.
Description
Technical Field
The present invention relates to a fault identification method and system in an electrical power system, and in particular, to a fault identification method and system for electrical power equipment.
Background
A closed combined electrical appliance (GIS for short) is made up of SF6Gas-insulated metal-enclosed switchgear with gas as the insulating medium. Compared with the traditional open-type transformer substation, the GIS has the remarkable advantages of small occupied area, high operation reliability, strong safety, long maintenance period and the like. Therefore, since the practical use of the 20 th century in the 60 th era, GIS has been widely used in domestic and foreign electric power systems.
Because of the wide application and importance of GIS in the power grid, its operation condition is closely related to whether the whole power grid can work normally and safely. The GIS partial discharge is monitored on line, so that negative effects caused by shutdown can be avoided while the insulation condition of the GIS partial discharge is mastered, the GIS current insulation state can be more represented by detection in a non-shutdown state, and the GIS partial discharge online monitoring method has important significance for ensuring safe and stable operation of the whole power system.
Based on the above, it is desirable to obtain a method for identifying the type of the insulation defect of the GIS, which can perform pattern identification with extremely high accuracy when the GIS device is subjected to partial discharge, and is beneficial to ensuring the safe and stable operation of the whole power system.
Disclosure of Invention
One of the purposes of the invention is to provide a method for GIS insulation defect category identification, which is based on a support vector machine (SVM for short) neural network classifier, realizes the identification of GIS insulation defects and improves the intelligent level of a GIS partial discharge detection system.
According to the above object, the present invention provides a method for identifying the type of a GIS insulation defect, which comprises a training step and an identification step:
wherein the training step comprises:
(1) acquiring case PRPS partial discharge map data of a GIS and preprocessing the data;
(2) extracting effective characteristic quantity in case PRPS partial discharge map data to construct a characteristic space of the case PRPS partial discharge map data;
(3) constructing a multi-core SVM classifier, inputting the feature space into the multi-core SVM classifier by adopting a multi-core function, and training the multi-core SVM classifier so as to enable the multi-core SVM classifier to output GIS insulation defect categories corresponding to the feature spaces;
the identification step comprises:
(a) acquiring PRPS partial discharge map data of GIS equipment to be identified, and preprocessing the PRPS partial discharge map data;
(b) extracting effective characteristic quantity in PRPS partial discharge map data to construct a characteristic space of the PRPS partial discharge map data;
(c) inputting the feature space into the trained multi-core SVM classifier, and outputting a GIS insulation defect type recognition result by the multi-core SVM classifier.
According to the method for identifying the GIS insulation defect types, the multi-core SVM classifier with higher accuracy is constructed by extracting effective characteristic quantities in case PRPS partial discharge map data, and the multi-core SVM classifier adopts a multi-core function, so that the original traditional prior art adopting a single-core function is replaced, and the accuracy of classification of the PRPS partial discharge map data to be finally identified is higher.
Further, in the method for identifying the GIS insulation defect category, the effective characteristic quantity at least comprises a color characteristic, a texture characteristic and a shape characteristic.
Further, in the method for identifying the GIS insulation defect category, the preprocessing comprises the step of carrying out normalization processing on the case PRPS partial discharge map data and the PRPS partial discharge map data of the GIS equipment to be identified.
Further, in the method for GIS insulation defect category identification according to the present invention, the pattern of the GIS insulation defect includes at least corona discharge, levitation discharge, and free metal particle discharge.
Further, in the method for identifying the GIS insulation defect type, the multi-core function is constructed by at least one local core function and at least one global core function.
Further, in the method for identifying the GIS insulation defect category, the local kernel function is selected from at least one of a linear kernel function and a Gaussian radial basis kernel function; and/or the global kernel function is selected from a polynomial kernel function and a Sigmoid kernel function.
Accordingly, another object of the present invention is to provide a system for GIS insulation defect category identification, which can identify different GIS insulation defect types efficiently, accurately and quickly.
According to the above object, the present invention provides a system for identifying the insulation defect category of a GIS, which comprises a data acquisition device and a data processing module, wherein:
the data acquisition device acquires case PRPS partial discharge map data of the GIS and PRPS partial discharge map data of GIS equipment to be identified;
the data processing module is configured to perform the following training and recognition steps:
wherein the training step comprises:
(1) preprocessing the partial discharge map data of the case PRPS of the GIS;
(2) extracting effective characteristic quantity in case PRPS partial discharge map data to construct a characteristic space of the case PRPS partial discharge map data;
(3) constructing a multi-core SVM classifier, inputting the feature space into the multi-core SVM classifier by adopting a multi-core function, and training the multi-core SVM classifier so as to enable the multi-core SVM classifier to output GIS insulation defect categories corresponding to the feature spaces;
the identification step comprises:
(a) preprocessing PRPS partial discharge map data of GIS equipment to be identified;
(b) extracting effective characteristic quantity in PRPS partial discharge map data to construct a characteristic space of the PRPS partial discharge map data;
(c) inputting the feature space into a trained multi-core SVM classifier, and outputting a GIS insulation defect type recognition result by the multi-core SVM classifier.
Further, in the system for identifying the GIS insulation defect category, the effective characteristic quantity at least comprises a color characteristic, a texture characteristic and a shape characteristic.
Further, in the system for GIS insulation defect class identification according to the present invention, the multi-core function is constructed by at least one local core function and at least one global core function.
Further, in the system for identifying the GIS insulation defect category, the local kernel function is selected from at least one of a linear kernel function and a Gaussian radial basis kernel function; and/or the global kernel function is selected from a polynomial kernel function and a Sigmoid kernel function.
The method and the system for identifying the GIS insulation defect categories have the advantages and beneficial effects as follows:
according to the method for identifying the GIS insulation defect types, the multi-core SVM classifier with higher accuracy is constructed by extracting effective characteristic quantities in case PRPS partial discharge map data, and the multi-core SVM classifier adopts a multi-core function, so that the original traditional prior art adopting a single-core function is replaced, and the accuracy of classification of the PRPS partial discharge map data to be finally identified is higher.
In addition, the system for GIS insulation defect category identification has the advantages and beneficial effects.
Drawings
Fig. 1 is a schematic flow chart of a training step of the method for GIS insulation defect class identification according to some embodiments of the present invention.
Fig. 2 is a schematic flow chart of the identification step of the method for GIS insulation defect system identification according to some embodiments of the present invention.
Fig. 3 schematically shows a PRPS partial discharge map under a corona discharge defect model in some embodiments of the method for GIS insulation defect class identification according to the present invention.
Fig. 4 schematically shows a PRPS partial discharge map under a suspension discharge defect model in some embodiments of the method for GIS insulation defect class identification according to the present invention.
Fig. 5 schematically shows a PRPS partial discharge map under a free metal particle discharge defect model in some embodiments of the method for GIS insulation defect classification identification according to the present invention.
Detailed Description
The method for identifying the GIS insulation defect category according to the present invention will be further explained and explained with reference to the drawings and the specific embodiments of the specification, however, the explanation and the explanation do not unduly limit the technical solution of the present invention.
In the embodiment, the system for identifying the GIS insulation defect type comprises a data acquisition device and a data processing module, wherein the data acquisition device acquires case PRPS partial discharge map data of a GIS and PRPS partial discharge map data of GIS equipment to be identified.
Wherein, GIS's insulating defect can adopt and obtain with the lower model simulation:
corona discharge defect model: the tip of the high-voltage conductor is made of aluminum metal material, the distance between the two electrodes is 20mm, and the corona discharge in a GIS is simulated.
Suspension discharge defect model: a cylinder is made of epoxy resin, a piece of metal is placed in the cylinder, high voltage and grounding are applied to the upper surface and the lower surface of the cylinder respectively, and then the metal in the epoxy resin can be approximately regarded as a suspension electrode to simulate suspension discharge in a GIS.
Free metal particle discharge defect model: a metal pellet is placed between the upper and lower electrodes to simulate a free metal particle discharge.
When the case PRPS partial discharge spectrum data is collected, a system test loop can be connected, and voltage is applied to start a test. The test voltage was slowly increased, and attention was paid to the partial discharge detector and oscilloscope. When partial discharge occurs, the voltage boosting is stopped, the voltage U applied to the device and the apparent discharge quantity Q at the moment are recorded, and the discharge signal is sampled.
Fig. 3 to 5 illustrate the signals of the PRPS partial discharge maps obtained for different defects. Fig. 3 schematically shows a PRPS partial discharge map under a corona discharge defect model in some embodiments of the method for GIS insulation defect class identification according to the present invention. Fig. 4 schematically shows a PRPS partial discharge map under a suspension discharge defect model in some embodiments of the method for GIS insulation defect class identification according to the present invention. Fig. 5 schematically shows a PRPS partial discharge map under a free metal particle discharge defect model in some embodiments of the method for GIS insulation defect classification identification according to the present invention.
As can be seen from fig. 3 to 5, since the image includes a large amount of information in the experiment, the data amount is huge, and the processing takes a long time and is inefficient, the image can be preprocessed to extract the most effective information, remove other redundant information, reduce the data amount, and synthesize all effective characteristic amounts to construct a characteristic space, so that the pattern recognition of the partial discharge image can be efficiently and accurately completed.
Wherein the effective characteristic quantity at least comprises color characteristics, texture characteristics and shape characteristics.
After the feature space construction is completed, a multi-core SVM classifier is constructed because: when linear inseparability is encountered in pattern recognition, linear inseparable samples in a low-dimensional space need to be mapped to a high-dimensional feature space through a kernel function, and if the samples are linearly separable in the high-dimensional space, an optimal classification hyperplane can be constructed. Therefore, the kernel function has a great influence on the generalization capability of the SVM.
For example, after the kernel function K (X, Y) is adopted, the optimization problem by the lagrange multiplier method is changed into:
subscripts i and j represent ith and jth training samples, and N is the total number of the training samples; x is the number ofiTo train the feature quantities of the sample, yiIs a class label of the specimen, αiTo optimize parameters, C is a penalty function to reduce sample fraction errors while reducing machine learning complexity. L represents a Lagrange equation, and solving the equation under the condition of satisfying the constraint condition enables the distance between different classes of hyperplanes to be maximum, ajRepresents the optimized parameters of the jth sample
At the same time, the decision function also turns into:
f (z) is the decision function, sgn () is the sign function, SVs is the set of all support vectors,
is the ith support vector, yiIs a category label of a support vector, K is a kernel function, α'iFor optimization of the parameters, b'iIs the positive intercept parameter, and z is the sample feature quantity.
The kernel functions can be further specifically classified into two types, namely local kernel functions and global kernel functions, and the classification criteria are whether the kernel functions have local characteristics or global characteristics. In the embodiment, the multi-core SVM classifier adopts a multi-core function which is constructed by at least one local core function and at least one global core function, wherein the local core function is selected from at least one of a linear core function and a Gaussian radial basis core function; and/or the global kernel function is selected from a polynomial kernel function and a Sigmoid kernel function.
This is because the linear function and the gaussian radial basis kernel function have local characteristics, and have strong learning ability but weak generalization ability; the polynomial kernel function and the Sigmoid kernel function have global characteristics, and have strong generalization capability but weak learning capability. The multi-core function is constructed by combining the local kernel function and the global kernel function, and the single kernel function in the prior art can be replaced, so that the classification accuracy of the method for identifying the GIS insulation defect categories in the embodiment is higher.
The specific case of the kernel function is as follows:
linear kernel function:
K(X，Y)＝(X·Y)
in the above formula, K represents a linear kernel function, (X, Y) represents a training sample, X represents a feature quantity of the sample, Y represents a class label of the sample, and (X · Y) represents the inner product of the two.
It should be noted that the linear kernel function has the advantages of low computational complexity, high approximation accuracy and generalization capability, and is suitable for use in small sample situations.
Polynomial kernel function:
K(X，Y)＝(X·Y+c)d
in the above formula, K represents a polynomial kernel function, (X, Y) is a training sample, X is a feature quantity of the sample, Y is a class label of the sample, (X · Y) represents the inner product of the two, c is a manually set polynomial constant, and d is a polynomial order.
It should be noted that the use of this kernel function is very efficient when all training data has been normalized. When c is 0 and d is 1, the polynomial kernel is converted to a linear kernel.
Gaussian radial basis kernel function
In the formula, K represents a Gaussian radial basis kernel function, (X, Y) is a training sample, X is the characteristic quantity of the sample, and Y is the class label of the sample; | | X-Y | | is the distance between two vectors, and σ is a gaussian parameter.
The gaussian radial basis function has the advantage of strong learning ability, and the learning ability can be controlled by a parameter σ, and the learning ability is stronger when σ is smaller, because the gaussian parameter σ represents the width in the gaussian function, and as the value of σ is reduced, namely, the gaussian function is narrowed, the coverage area is reduced, the required support vectors are increased, and the learning ability is enhanced, but the overfitting condition is easy to occur. Therefore, the value range of the sigma can be adjusted according to the actual situation of the sample.
Sigmoid kernel function:
K(X，Y)＝tanh(v(X，Y)-c)
in the above formula, K represents a Sigmoid kernel function, (X, Y) is a training sample, X is a characteristic quantity of the sample, Y is a class label of the sample, v is a scale parameter, and c is an attenuation parameter.
The Sigmoid kernel function is from the field of neural networks, and has the advantages that the SVM obtained after training by using the Sigmoid kernel function is a multilayer perceptron in the neural network, the number of hidden nodes can be automatically determined, and meanwhile, the defect of local minimum points can be avoided.
And inputting the feature space into the constructed multi-core SVM classifier, and training the multi-core SVM classifier so as to enable the multi-core SVM classifier to output the GIS insulation defect categories corresponding to the feature spaces.
The training steps are executed in a data processing module, and fig. 1 is a flow chart illustrating the training steps of the method for GIS insulation defect class identification according to some embodiments of the present invention.
As shown in fig. 1, the training step includes:
(1) preprocessing the partial discharge map data of the case PRPS of the GIS;
(2) extracting effective characteristic quantity in case PRPS partial discharge map data to construct a characteristic space of the case PRPS partial discharge map data;
(3) and constructing a multi-core SVM classifier, inputting the feature space into the multi-core SVM classifier by adopting a multi-core function, and training the multi-core SVM classifier so as to enable the multi-core SVM classifier to output the GIS insulation defect categories corresponding to the feature spaces.
Subsequently, the data processing module performs the identifying step. Fig. 2 is a schematic flow chart of the identification step of the method for GIS insulation defect system identification according to some embodiments of the present invention.
As shown in fig. 2, the identifying step includes:
(a) preprocessing PRPS partial discharge map data of GIS equipment to be identified;
(b) extracting effective characteristic quantity in PRPS partial discharge map data to construct a characteristic space of the PRPS partial discharge map data;
(c) inputting the feature space into a trained multi-core SVM classifier, and outputting a GIS insulation defect type recognition result by the multi-core SVM classifier.
In order to verify the identification accuracy of the method for the GIS insulation defect type mode, 300 groups of GIS insulation defect partial discharge data are collected through a partial discharge experiment, Gabor transformation is carried out on the GIS insulation defect partial discharge data, the characteristic quantity of the GIS insulation defect partial discharge data is extracted, the obtained samples are divided into two parts, namely a training sample and a test sample, 200 groups are randomly selected as the training samples, and the remaining 100 groups are the test samples and used for testing the trained multi-core SVM classifier and the neural network classifier in the prior art.
The test results are listed in table 1, and it should be noted that comparative examples 1 to 4 respectively adopt different kernel functions to respectively establish four single-kernel SVM classifiers, and the present application adopts the constructed multi-kernel function to establish a multi-kernel SVM classifier. The training samples are put into each neural network classifier for learning, and then the classifier which completes training identifies the test samples in a classification way.
Table 1.
As can be seen from table 1, the method for identifying the GIS insulation defect category in embodiment 1 has the highest identification accuracy, which indicates that the method of the present invention is stable for identifying various GIS insulation defects.
In summary, in the method for identifying the insulation defect category of the GIS according to the present invention, a multi-core SVM classifier with a higher accuracy is constructed by extracting effective feature quantities in case PRPS partial discharge map data, and the multi-core SVM classifier uses a multi-core function, thereby replacing the conventional prior art that uses a single-core function, so that the accuracy of classification of the finally-identified PRPS partial discharge map data is higher.
In addition, the system for GIS insulation defect category identification has the advantages and beneficial effects.
It should be noted that the prior art in the protection scope of the present invention is not limited to the examples given in the present application, and all the prior art which is not inconsistent with the technical scheme of the present invention, including but not limited to the prior patent documents, the prior publications and the like, can be included in the protection scope of the present invention.
In addition, the combination of the features in the present application is not limited to the combination described in the claims of the present application or the combination described in the embodiments, and all the features described in the present application may be freely combined or combined in any manner unless contradictory to each other.
It should also be noted that the above-mentioned embodiments are only specific embodiments of the present invention. It is apparent that the present invention is not limited to the above embodiments and similar changes or modifications can be easily made by those skilled in the art from the disclosure of the present invention and shall fall within the scope of the present invention.
Claims (10)
1. A method for GIS insulation defect category identification is characterized by comprising a training step and an identification step:
wherein the training step comprises:
(1) acquiring case PRPS partial discharge map data of a GIS and preprocessing the data;
(2) extracting effective characteristic quantity in case PRPS partial discharge map data to construct a characteristic space of the case PRPS partial discharge map data;
(3) constructing a multi-core SVM classifier, wherein the multi-core SVM classifier adopts a multi-core function, inputs the feature space into the multi-core SVM classifier and trains the multi-core SVM classifier so that the multi-core SVM classifier outputs GIS insulation defect categories corresponding to the feature spaces;
the identifying step includes:
(a) acquiring PRPS partial discharge map data of GIS equipment to be identified, and preprocessing the PRPS partial discharge map data;
(b) extracting effective characteristic quantity in PRPS partial discharge map data to construct a characteristic space of the PRPS partial discharge map data;
(c) inputting the feature space into a trained multi-core SVM classifier, and outputting a GIS insulation defect type recognition result by the multi-core SVM classifier.
2. The method for GIS insulation defect category identification as claimed in claim 1, wherein the effective feature quantity includes at least color features, texture features and shape features.
3. The method for GIS insulation defect category identification as claimed in claim 1 wherein the preprocessing comprises normalizing the case PRPS partial discharge map data and the PRPS partial discharge map data of the GIS device to be identified.
4. The method for GIS insulation defect category identification as claimed in claim 1, wherein the GIS insulation defect patterns include at least corona discharge, levitation discharge and free metal particle discharge.
5. The method for GIS insulation defect category identification of claim 1, wherein the multi-kernel function is constructed from at least one local kernel function and at least one global kernel function.
6. The method for GIS insulation defect category identification as claimed in claim 5 wherein the local kernel function is selected from at least one of a linear kernel function and a gaussian radial basis kernel function; and/or
The global kernel is selected from a polynomial kernel and a Sigmoid kernel.
7. A system for GIS insulation defect category identification, which is characterized by comprising a data acquisition device and a data processing module, wherein:
the data processing module acquires case PRPS partial discharge map data of the GIS and PRPS partial discharge map data of GIS equipment to be identified;
the data processing module is configured to perform the following training and recognition steps:
wherein the training step comprises:
(1) preprocessing the partial discharge map data of the case PRPS of the GIS;
(2) extracting effective characteristic quantity in case PRPS partial discharge map data to construct a characteristic space of the case PRPS partial discharge map data;
(3) constructing a multi-core SVM classifier, wherein the multi-core SVM classifier adopts a multi-core function, inputs the feature space into the multi-core SVM classifier and trains the multi-core SVM classifier so that the multi-core SVM classifier outputs GIS insulation defect categories corresponding to the feature spaces;
the identifying step includes:
(a) preprocessing PRPS partial discharge map data of GIS equipment to be identified;
(b) extracting effective characteristic quantity in PRPS partial discharge map data to construct a characteristic space of the PRPS partial discharge map data;
(c) inputting the feature space into a trained multi-core SVM classifier, and outputting a GIS insulation defect type recognition result by the multi-core SVM classifier.
8. The system for GIS insulation defect category identification of claim 7 wherein the effective feature quantities include at least color features, texture features, and shape features.
9. The system for GIS insulation defect category identification of claim 7, wherein the multi-kernel function is constructed from at least one local kernel function and at least one global kernel function.
10. The system for GIS insulation defect category identification of claim 9 wherein the local kernel function is selected from at least one of a linear kernel function and a gaussian radial basis kernel function; and/or
The global kernel is selected from a polynomial kernel and a Sigmoid kernel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910671136.8A CN112287953A (en) | 2019-07-24 | 2019-07-24 | Method and system for GIS insulation defect category identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910671136.8A CN112287953A (en) | 2019-07-24 | 2019-07-24 | Method and system for GIS insulation defect category identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287953A true CN112287953A (en) | 2021-01-29 |
Family
ID=74418921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910671136.8A Pending CN112287953A (en) | 2019-07-24 | 2019-07-24 | Method and system for GIS insulation defect category identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287953A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780308A (en) * | 2021-08-27 | 2021-12-10 | 吉林省电力科学研究院有限公司 | GIS partial discharge mode identification method and system based on kernel principal component analysis and neural network |
| CN113902745A (en) * | 2021-12-10 | 2022-01-07 | 山东捷瑞数字科技股份有限公司 | Method and device for identifying accurate fault of gearbox of commercial vehicle based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102809718A (en) * | 2012-07-25 | 2012-12-05 | 华南理工大学 | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) |
| CN103048593A (en) * | 2012-12-12 | 2013-04-17 | 安徽省电力公司亳州供电公司 | Identification method of insulation defect type of gas-insulated switchgear |
| CN109102012A (en) * | 2018-07-30 | 2018-12-28 | 上海交通大学 | A kind of defect identification method and system of local discharge signal |
| CN109102508A (en) * | 2018-08-31 | 2018-12-28 | 上海交通大学 | The recognition methods of ac cable insulation defect based on shelf depreciation characteristics of image |
| CN109871746A (en) * | 2018-12-30 | 2019-06-11 | 国网辽宁省电力有限公司电力科学研究院 | A kind of mode identification method based on the diagnosis of GIS insulation defect |
-
2019
- 2019-07-24 CN CN201910671136.8A patent/CN112287953A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102809718A (en) * | 2012-07-25 | 2012-12-05 | 华南理工大学 | Ultra-high-frequency partial discharge signal identification method for gas insulated switchgear (GIS) |
| CN103048593A (en) * | 2012-12-12 | 2013-04-17 | 安徽省电力公司亳州供电公司 | Identification method of insulation defect type of gas-insulated switchgear |
| CN109102012A (en) * | 2018-07-30 | 2018-12-28 | 上海交通大学 | A kind of defect identification method and system of local discharge signal |
| CN109102508A (en) * | 2018-08-31 | 2018-12-28 | 上海交通大学 | The recognition methods of ac cable insulation defect based on shelf depreciation characteristics of image |
| CN109871746A (en) * | 2018-12-30 | 2019-06-11 | 国网辽宁省电力有限公司电力科学研究院 | A kind of mode identification method based on the diagnosis of GIS insulation defect |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780308A (en) * | 2021-08-27 | 2021-12-10 | 吉林省电力科学研究院有限公司 | GIS partial discharge mode identification method and system based on kernel principal component analysis and neural network |
| CN113902745A (en) * | 2021-12-10 | 2022-01-07 | 山东捷瑞数字科技股份有限公司 | Method and device for identifying accurate fault of gearbox of commercial vehicle based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Song et al. | GIS partial discharge pattern recognition via deep convolutional neural network under complex data source | |
| Firuzi et al. | Partial discharges pattern recognition of transformer defect model by LBP & HOG features | |
| Afrasiabi et al. | Integration of accelerated deep neural network into power transformer differential protection | |
| Duan et al. | Identification of partial discharge defects based on deep learning method | |
| He et al. | A naive-Bayes-based fault diagnosis approach for analog circuit by using image-oriented feature extraction and selection technique | |
| CN108573225A (en) | A kind of local discharge signal mode identification method and system | |
| Do et al. | Convolutional-neural-network-based partial discharge diagnosis for power transformer using UHF sensor | |
| CN109871746A (en) | A kind of mode identification method based on the diagnosis of GIS insulation defect | |
| CN111160241B (en) | Power distribution network fault classification method, system and medium based on deep learning | |
| Wang et al. | Few-shot transfer learning with attention mechanism for high-voltage circuit breaker fault diagnosis | |
| CN112287953A (en) | Method and system for GIS insulation defect category identification | |
| Zou et al. | Double convolutional neural network for fault identification of power distribution network | |
| Wang et al. | Novel metric-based meta-learning model for few-shot diagnosis of partial discharge in a gas-insulated switchgear | |
| Todeschini et al. | An image-based deep transfer learning approach to classify power quality disturbances | |
| Xi et al. | Transmission line fault detection and classification based on SA-MobileNetV3 | |
| CN114091549A (en) | Equipment fault diagnosis method based on deep residual error network | |
| Zhang et al. | Encoding time series as images: A robust and transferable framework for power system DIM identification combining rules and VGGNet | |
| CN112132226A (en) | Method for diagnosing defects of +/-1100 kV composite insulator | |
| CN116911161A (en) | Data-enhanced deep learning transient voltage stability evaluation method | |
| Wei et al. | Deep belief network based faulty feeder detection of single-phase ground fault | |
| CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
| Adaminejad et al. | An algorithm for power quality events core vector machine based classification | |
| He et al. | Partial discharge pattern recognition algorithm based on sparse self-coding and extreme learning machine | |
| Zhang et al. | A convolutional neural network-based UHF partial discharge atlas classification system for GIS | |
| Hao et al. | Insulator fouling monitoring based on acoustic signal and one-dimensional convolutional neural network |
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: 20210129 |