CN110596541A - Partial discharge positioning method and system based on fingerprint map - Google Patents
Partial discharge positioning method and system based on fingerprint map Download PDFInfo
- Publication number
- CN110596541A CN110596541A CN201810604468.XA CN201810604468A CN110596541A CN 110596541 A CN110596541 A CN 110596541A CN 201810604468 A CN201810604468 A CN 201810604468A CN 110596541 A CN110596541 A CN 110596541A
- Authority
- CN
- China
- Prior art keywords
- discharge
- fingerprint
- fingerprint map
- matrix
- map
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000009467 reduction Effects 0.000 claims abstract description 46
- 238000005259 measurement Methods 0.000 claims abstract description 45
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 239000011159 matrix material Substances 0.000 claims description 66
- 238000012545 processing Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 230000001131 transforming effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 6
- 230000004807 localization Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 15
- 238000004364 calculation method Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000009413 insulation Methods 0.000 description 6
- 238000003909 pattern recognition Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention relates to a partial discharge positioning method and a partial discharge positioning system based on a fingerprint map, which comprise the following steps: carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and a preset discharge fingerprint image in a BP neural network to obtain a highest similarity value; and determining a discharge positioning point according to the corresponding measurement point of the highest similarity value in the discharge fingerprint graph to be measured. The application provides a partial discharge positioning method and a partial discharge positioning system based on a fingerprint map, similarity recognition is carried out on a discharge fingerprint to be detected acquired by a wireless ultrahigh frequency sensor and a trained discharge fingerprint map in a BP neural network, a highest value of the similarity is obtained, and according to the highest value of the similarity, a measurement point corresponding to a to-be-detected discharge dimensionality reduction fingerprint map is determined as a discharge positioning point, so that the positioning accuracy can be effectively improved, and the overhaul efficiency of power equipment of a transformer substation is improved.
Description
Technical Field
The invention belongs to the field of operation and maintenance of power transmission and transformation equipment of a power system, and particularly relates to a partial discharge positioning method and system based on a fingerprint map.
Background
In an electric power system, online monitoring and fault detection of electric power equipment are very important links. The fault of the power equipment can be timely found through effective monitoring, the overhaul personnel can overhaul the power equipment quickly, spreading of accidents is effectively restrained, and major accidents are avoided. In a substation, a failure of an electric power equipment is mostly caused by poor insulation due to a high voltage class, and the cause of the reduction of the insulation performance of the equipment is mainly a manufacturing defect of the equipment, oil contamination on the surface of the equipment, aging of the equipment, and the like. Poor insulation usually results in too strong electric field in local area, which results in local insulation breakdown, which is finally manifested as partial discharge, and the partial discharge in turn can aggravate insulation deterioration, which finally results in large insulation breakdown, which finally causes equipment failure, even serious accident. Therefore, the device fault can be found out by rapidly detecting and pre-positioning the partial discharge, the maintenance efficiency is improved, and the device is an important guarantee for the safe operation of the power equipment. The partial discharge is generally generated by light, heat, ultrasonic waves, chemical reactions, ultrahigh frequency electromagnetic waves, and the like. The ultrahigh frequency electromagnetic wave is very suitable for detecting and positioning the partial discharge of the transformer substation due to the strong anti-interference performance, the fast transmission speed and the high sensitivity.
The conventional positioning method based on the uhf electromagnetic wave mainly includes Time Difference of Arrival (TDOS), Time of Arrival (TOA), Angle of Arrival (AOA), and Received Signal Strength (RSSI). The TDOS, TOA and AOA methods have been applied more, but have certain difficulty in implementation. The TDOS and TOA methods need to sample ultrahigh frequency signals, the hardware cost is high, the accuracy of the AOA method is influenced when the AOA method is used for non-line-of-sight positioning, the application range is limited, and certain difficulty is brought to overhaul of power equipment of a transformer substation.
Disclosure of Invention
In order to solve the problems that the positioning precision of partial discharge is inaccurate, the application range is limited, and certain difficulty is brought to the overhaul of power equipment of a transformer substation, the application provides a partial discharge positioning method based on a fingerprint map, and the method comprises the following steps:
carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and a preset discharge fingerprint image in a BP neural network to obtain a highest similarity value;
determining a discharge positioning point according to the corresponding measurement point of the highest similarity value in the discharge fingerprint graph to be measured;
wherein the pre-established discharge fingerprint map is determined by the discharge intensity of all measurement points.
Preferably, the pre-established discharge fingerprint map is determined by the discharge intensity of all the measurement points, and includes:
using an ultrahigh frequency sensor to acquire the discharge intensity of each measuring point by using an ultrahigh frequency signal;
measuring the measurement points for multiple times to obtain the average value of the discharge intensity of the measurement points, and setting the average value as the discharge fingerprint of the measurement points;
and forming a discharge fingerprint map by the discharge fingerprints of all the measuring points.
Preferably, the discharge fingerprint of the measurement point is calculated according to the following formula:
wherein the content of the first and second substances,denotes the discharge intensity measured by the sensor i at the τ th time when the partial discharge source is at the measurement point j, p denotes the number of measurements at each measurement point,is the discharge fingerprint of the measurement point.
Preferably, the discharge fingerprint map is represented by a matrix as follows:
wherein Ψ is a discharge fingerprint map matrix;representing a discharge intensity fingerprint measured by the sensor L at the measurement point N.
Preferably, the composing of the discharge fingerprint map by the discharge fingerprints of all the measurement points further comprises:
and carrying out noise component filtering treatment on the discharge fingerprint image, so that the discharge fingerprint image is reduced from a high dimension to a low dimension.
Preferably, the filtering the noise component of the discharge fingerprint map to reduce the discharge fingerprint map from a high dimension to a low dimension includes:
defining a matrix according to the column vectors of the discharge fingerprint image, and performing singular value decomposition on the matrix to obtain an orthogonal matrix;
and transforming the orthogonal matrix and then processing the orthogonal matrix and the discharge fingerprint image matrix to obtain a discharge dimension reduction fingerprint image.
Preferably, the column vector definition matrix of the discharge fingerprint map is as follows:
wherein Q is the discharge fingerprint measured at all sensors of the discharge fingerprint map matrix Ψ; r isjIs the discharge fingerprint measured at the jth measuring point of the discharge fingerprint map matrix Ψ, and N is the number of the measuring points; r isj TIs rjTransposition is carried out;
singular value decomposition of the matrix is performed as follows:
Q＝VΔVT
wherein V is an orthogonal matrix, and V ═ V1,v2,…vl)；VTIs the transposed matrix of V.
Preferably, the discharge dimension reduction fingerprint map is shown as follows:
F＝ΦΨ
f: a partial discharge dimension reduction fingerprint map; phi: and transforming the matrix.
Preferably, the determining a final discharge positioning point according to the measurement point corresponding to the highest similarity value in the to-be-detected discharge dimension reduction fingerprint map includes:
and determining the coordinates of the corresponding measuring points in the discharge dimension reduction fingerprint map according to the highest value of the similarity, and taking the coordinates of the measuring points as the positioning result of the partial discharge signal.
Preferably, before performing similarity identification in the BP neural network, the method further includes: and carrying out BP neural network training on the pre-established discharge fingerprint image.
A fingerprint map based partial discharge localization system, comprising:
an identification module: the device is used for carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and a pre-established discharge fingerprint image in a BP neural network to obtain a highest similarity value;
a positioning module: and the measuring point corresponding to the to-be-measured discharge dimension reduction fingerprint map is used as a discharge positioning point according to the highest similarity value.
Preferably, the device further comprises a discharge fingerprint map generation module;
the discharge fingerprint map generation module is used for generating a discharge fingerprint map according to the collected discharge intensity of each measuring point.
Preferably, the discharge fingerprint map generation module comprises a processing submodule;
the processing submodule is used for filtering noise components of the discharge fingerprint image to reduce the discharge fingerprint image from high dimension to low dimension, defining a matrix according to column vectors of the discharge fingerprint image and performing singular value decomposition on the matrix to obtain an orthogonal matrix; and transforming the orthogonal matrix and then processing the orthogonal matrix and the discharge fingerprint image matrix to obtain a discharge dimension reduction fingerprint image.
Moreover, compared with the closest prior art, the application also has the following beneficial effects:
1. the application provides a partial discharge positioning method and a partial discharge positioning system based on a fingerprint map, similarity identification is carried out on a discharge fingerprint to be detected acquired by a wireless ultrahigh frequency sensor and a preset discharge fingerprint map in a BP neural network to obtain a highest similarity value, and a measurement point corresponding to a discharge dimensionality reduction fingerprint map to be detected is determined as a discharge positioning point according to the highest similarity value, so that the positioning accuracy can be effectively improved, and the overhaul efficiency of power equipment of a transformer substation is improved;
2. the invention provides a partial discharge positioning method and system based on a fingerprint map, which ensure the safe operation of a power system, are convenient to popularize to other electrical equipment, establish a corresponding model and have good expandability.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a field survey of the present invention;
FIG. 3-a is a partial discharge fingerprint of a measured area of the present invention FIG. 1;
FIG. 3-b is a partial discharge fingerprint of a measured area of the present invention FIG. 2;
FIG. 3-c is a partial discharge fingerprint of a measured area of the present invention FIG. 3;
FIG. 3-d is a partial discharge fingerprint diagram 4 of a measured area of the present invention;
FIG. 4-a is a partial discharge dimension reduction fingerprint diagram 1 of a measured area according to the present invention;
FIG. 4-b is a partial discharge dimension reduction fingerprint of a measured area of the present invention FIG. 2;
FIG. 4-c is a partial discharge dimension reduction fingerprint of the measured area of the present invention FIG. 3;
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples.
Example 1: the invention provides a partial discharge positioning method based on a fingerprint map, which is shown in figure 1:
step 1: carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and the trained BP (back propagation) neural network to obtain a highest similarity value;
step 2: measuring points corresponding to the to-be-measured discharge dimensionality reduction fingerprint map according to the highest similarity value are discharge positioning points; wherein the pre-established discharge fingerprint map comprises: the discharge intensity of all measurement points.
Before similarity identification in the BP neural network, BP neural network training is carried out on a pre-established discharge fingerprint image.
The explanation of the above steps is specifically as follows:
the description of step 1 specifically includes:
1-1 creation of partial discharge fingerprint map
In the measured area, a standard partial discharge source is used for discharging at each measuring point (the number of the measuring points is N), L ultrahigh frequency sensors are used for ultrahigh frequency signal acquisition, and the discharge intensity of each measuring point, namely the discharge fingerprint, is measured. Suppose RPjPartial discharge occurs at the point, sensor APiThe measured discharge intensity value is Where p represents the number of measurements, the fingerprint map Ψ reflecting the RSSI characteristics in the measured environment:
wherein L represents the number of sensors, N represents the number of measurement points, p represents the number of measurements at each measurement point,indicating that the source is partially discharged at j measurement points RPjTime ith sensor APiThe measured discharge fingerprint (mean value of discharge intensity),denotes the discharge intensity measured by the sensor i at the τ th time when the partial discharge source is at the measurement point j, and p denotes the number of measurements at each measurement point.
Taking four wireless ultrahigh frequency sensors as an example, the field measurement diagram is shown in fig. 2, and the partial discharge fingerprint diagram of the measured area is shown in fig. 3-a, 3-b, 3-c and 3-d.
1-2 pattern recognition algorithm
The partial discharge positioning of the positioning system is realized by a BP (back propagation) neural network pattern recognition algorithm. Firstly, a BP (back propagation) neural network is trained by using a partial discharge dimensionality reduction fingerprint map of a measured area which is established in advance. Then, when the partial discharge signal in the transformer substation is positioned, the partial discharge signal is measured by using the ultrahigh frequency sensor array, and the discharge fingerprint of the partial discharge is obtained. And then carrying out dimensionality reduction treatment on the partial discharge to obtain the dimensionality reduction fingerprint of the partial discharge. Finally, the signal is input into a trained BP (back propagation) neural network for pattern recognition.
1-3 partial discharge fingerprint map dimension reduction treatment
The noise component contained in the partial discharge fingerprint may reduce the accuracy of pattern recognition. Therefore, the dimension reduction processing is performed on the partial discharge fingerprint image. In the dimension reduction process, most of the noise components are left in the high-dimensional space, and the noise components projected to the low-dimensional space are useful information. The process is equivalent to a filtering process, noise components are filtered, and a more compact and effective partial discharge dimension reduction fingerprint image is obtained. The dimension reduction process is as follows.
Defining a matrix Q:
rjis a column vector of the fingerprint map matrix Ψ, which is a discharge fingerprint measured at all sensors of the discharge fingerprint map matrix Ψ; r isjIs the discharge fingerprint measured at the jth measuring point of the discharge fingerprint map matrix Ψ, and N is the number of the measuring points; r isj TIs rjTransposition is carried out;
by performing Singular Value Decomposition (SVD) on Q, we can obtain:
Q＝VΔVT (4)
wherein V is (V)1,V2,…Vl) Is an orthogonal matrix of which the phase of the signal,Vi(i ═ 1,2, …, L) is a L × 1 vector, Δ ═ diag (λ)1,λ2,…λL),λ1≥λ2≥…≥λLAnd L is the number of sensors, i.e., the number of rows in the matrix Ψ.
Let the transformation matrix Φ be:
Φ＝[V1,V2,...,Vd]T (5)
the dimension reduction operation of the partial discharge fingerprint map is as follows:
ΦΨ(t)＝F(t) (6)
f is a partial discharge dimension reduction fingerprint image, dimension is reduced from L dimension to d dimension, and the partial discharge dimension reduction fingerprint image is used for a mode identification link.
The concrete explanation of step 2 is: and the coordinate of the measuring point corresponding to the dimensionality reduction fingerprint which is most similar to the dimensionality reduction fingerprint in the partial discharge dimensionality reduction fingerprint graph is the positioning result of the partial discharge signal.
The pattern recognition algorithm in the step 2 specifically performs field application verification as follows:
in order to verify the effectiveness of the algorithm, experimental verification is carried out on a substation site, and the size of the experimental site is 25m × 25 m.
A test split line stage and an on-line stage. Firstly, the establishment of a partial discharge dimension reduction fingerprint map and the training of a BP neural network are carried out in an off-line stage. And (3) discharging 20 times at each measuring point by using a standard partial discharge source, recording all partial discharge signals received by 4 ultrahigh frequency sensors, and generating a 4-dimensional partial discharge fingerprint map by using 20-625-12500 groups of data, and then performing dimensionality reduction on the fingerprint map to reduce the dimensionality of the fingerprint map from 4 dimensions to 3 dimensions. And testing a positioning algorithm in an online stage. And (3) performing partial discharge for 1 time at each measuring point by using a standard partial discharge source, performing the same dimensionality reduction on the partial discharge fingerprint measured by the ultrahigh frequency sensor, inputting the partial discharge fingerprint into a trained BP (back propagation) neural network, obtaining a positioning result through pattern recognition, and completing the positioning at an online stage.
The partial discharge dimension reduction fingerprint map corresponding to the measured area is shown in FIGS. 4-a, 4-b and 4-c; the positioning result of the positioning algorithm is shown in table 1, and the comparison of the positioning performance of the dimensionality reduction fingerprint and the original fingerprint is listed.
Partial discharge dimension reduction fingerprint map establishment result of detected area
Positioning result
In conclusion, the positioning error of the partial discharge positioning method based on the dimensionality reduction fingerprint diagram is 1.87m, and 93.4% of the positioning error is smaller than 5m, so that the positioning requirement of a transformer substation site is met. Compared with the original fingerprint, the dimension-reducing fingerprint provided by the method obviously improves the positioning precision of the partial discharge, and verifies the effectiveness of the method.
Example 2:
based on the same inventive concept, the invention also provides a partial discharge positioning system based on the fingerprint map, which comprises the following steps:
the method comprises the following steps:
an identification module: the device is used for carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and a pre-established discharge fingerprint image in a BP (back propagation) neural network to obtain a highest similarity value;
a positioning module: the measuring point corresponding to the to-be-measured discharge dimension reduction fingerprint map is used as a discharge positioning point according to the highest similarity value;
the discharge fingerprint map generation module: the device is used for generating a discharge fingerprint image according to the collected discharge intensity of each measuring point;
still including training module: the device is used for carrying out BP (back propagation) neural network training on the pre-established discharge fingerprint image;
the discharge fingerprint map generation module comprises a processing submodule;
the processing submodule is used for filtering noise components of the discharge fingerprint image to reduce the discharge fingerprint image from high dimension to low dimension, defining a matrix according to column vectors of the discharge fingerprint image and performing singular value decomposition on the matrix to obtain an orthogonal matrix; and transforming the orthogonal matrix and then processing the orthogonal matrix and the discharge fingerprint image matrix to obtain a discharge dimension reduction fingerprint image.
The processing submodule comprises a discharge fingerprint calculation unit, a discharge fingerprint graph calculation unit, a discharge dimension reduction fingerprint graph calculation unit and an orthogonal matrix calculation unit;
the discharge fingerprint calculation unit is used for calculating a discharge fingerprint according to the following formula:
whereinIndicating a local discharge source at the measurement point RPjTiming sensor APiThe measured average value of the partial discharge signal intensity, p represents the number of measurements at each measurement point,discharge fingerprints for measurement points;
the discharge fingerprint map calculation unit is used for calculating a discharge fingerprint map according to the following formula:
wherein, L represents the number of sensors, N represents the number of measuring points, and psi is a discharge fingerprint diagram matrix;represents the discharge fingerprint measured by the sensor L at the measurement point N;
the discharge dimension reduction fingerprint map in the discharge dimension reduction fingerprint map calculation unit is calculated as follows:
f ═ Φ Ψ formula, F: a partial discharge dimension reduction fingerprint map is obtained; phi: for transforming matrices, phi ═ V1,V2,...,Vd]TIn the formula, V: is an orthogonal matrix;
the orthogonal matrix in the orthogonal matrix calculation unit is calculated as follows:
defining a matrix:wherein r isjIs a column vector of the fingerprint map matrix Ψ, Q is a discharge fingerprint measured at all sensors of the discharge fingerprint map matrix Ψ; r isjIs the discharge fingerprint measured at the jth measuring point of the discharge fingerprint map matrix Ψ, and N is the number of the measuring points; r isj TIs rjTransposition is carried out;
performing singular value decomposition on Q to obtain: q ═ V Δ VTWherein V ═ V (V)1,v2,…vl) Is an orthogonal matrix, where Vi (i ═ 1,2, …, L) is an L × 1 vector; Δ ═ diag (λ 1, λ 2, … λ L), λ 1 ≧ λ 2 ≧ … ≧ λ L, L being the number of sensors, i.e., the number of rows of matrix Ψ.
It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (13)
1. A partial discharge positioning method based on a fingerprint map is characterized by comprising the following steps:
carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and a preset discharge fingerprint image in a BP neural network to obtain a highest similarity value;
determining a discharge positioning point according to the corresponding measurement point of the highest similarity value in the discharge fingerprint graph to be measured;
wherein, the preset discharge fingerprint map is determined by the discharge intensity of all the measuring points.
2. The partial discharge positioning method based on fingerprint map as claimed in claim 1, wherein the preset discharge fingerprint map is determined by the discharge intensity of all measurement points, comprising:
using an ultrahigh frequency sensor to acquire the discharge intensity of each measuring point by using an ultrahigh frequency signal;
measuring the measurement points for multiple times to obtain the average value of the discharge intensity of the measurement points, and setting the average value as the discharge fingerprint of the measurement points;
and forming a discharge fingerprint map by the discharge fingerprints of all the measuring points.
3. The partial discharge positioning method based on the fingerprint map as claimed in claim 2, wherein the discharge fingerprint of the measurement point is calculated according to the following formula:
wherein the content of the first and second substances,denotes the discharge intensity measured by the sensor i at the τ th time when the partial discharge source is at the measurement point j, p denotes the number of measurements at each measurement point,is the discharge fingerprint of the measurement point.
4. The partial discharge positioning method based on fingerprint map as claimed in claim 3,
the discharge fingerprint map is represented by the following matrix:
wherein Ψ is a discharge fingerprint map matrix;indicating passage through the sensor LDischarge fingerprint measured at measurement point N.
5. The partial discharge positioning method based on fingerprint map as claimed in claim 4, wherein said forming discharge fingerprint map by discharge fingerprints of all measurement points further comprises:
and carrying out noise component filtering treatment on the discharge fingerprint image, so that the discharge fingerprint image is reduced from a high dimension to a low dimension.
6. The partial discharge positioning method based on the fingerprint map as claimed in claim 5, wherein the step of filtering the discharge fingerprint map to remove noise components so as to reduce the discharge fingerprint map from high dimension to low dimension comprises:
defining a matrix according to the column vectors of the discharge fingerprint image, and performing singular value decomposition on the matrix to obtain an orthogonal matrix;
and transforming the orthogonal matrix and then processing the orthogonal matrix and the discharge fingerprint image matrix to obtain a discharge dimension reduction fingerprint image.
7. The partial discharge positioning method based on the fingerprint map as claimed in claim 6, wherein the column vector definition matrix of the discharge fingerprint map is as follows:
wherein Q is the discharge fingerprint measured at all sensors of the discharge fingerprint map matrix Ψ; r isjIs the discharge fingerprint measured at the jth measuring point of the discharge fingerprint map matrix Ψ, and N is the number of the measuring points; r isj TIs rjTransposition is carried out;
singular value decomposition of the matrix is performed as follows:
Q＝VΔVT
wherein V is an orthogonal matrix, and V ═ V1,v2,…vl)；VTIs the transposed matrix of V.
8. The partial discharge positioning method based on the fingerprint map as claimed in claim 7, wherein the discharge dimension reduction fingerprint map is represented by the following formula:
F＝ΦΨ
f: a partial discharge dimension reduction fingerprint map; phi: and transforming the matrix.
9. The method as claimed in claim 1, wherein the determining the final discharge location point according to the corresponding measurement point in the to-be-measured discharge dimensionality reduction fingerprint map of the highest similarity value includes:
and determining the coordinates of the corresponding measuring points in the discharge dimension reduction fingerprint map according to the highest value of the similarity, and taking the coordinates of the measuring points as the positioning result of the partial discharge signal.
10. The partial discharge positioning method based on the fingerprint map as claimed in claim 1, wherein before performing similarity identification in the BP neural network, further comprising: and carrying out BP neural network training on the pre-established discharge fingerprint image.
11. A fingerprint map based partial discharge localization system, comprising:
an identification module: the device is used for carrying out similarity identification on the discharge fingerprint to be detected acquired by the wireless ultrahigh frequency sensor and a pre-established discharge fingerprint image in a BP neural network to obtain a highest similarity value;
a positioning module: and the measuring point corresponding to the to-be-measured discharge dimension reduction fingerprint map is used as a discharge positioning point according to the highest similarity value.
12. The partial discharge location system based on fingerprint map as claimed in claim 11, further comprising a discharge fingerprint map generation module;
the discharge fingerprint map generation module is used for generating a discharge fingerprint map according to the collected discharge intensity of each measuring point.
13. The partial discharge positioning system based on fingerprint map of claim 12, wherein the discharge fingerprint map generation module includes a processing sub-module;
the processing submodule is used for filtering noise components of the discharge fingerprint image to reduce the discharge fingerprint image from high dimension to low dimension, defining a matrix according to column vectors of the discharge fingerprint image and performing singular value decomposition on the matrix to obtain an orthogonal matrix; and transforming the orthogonal matrix and then processing the orthogonal matrix and the discharge fingerprint image matrix to obtain a discharge dimension reduction fingerprint image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810604468.XA CN110596541B (en) | 2018-06-13 | 2018-06-13 | Partial discharge positioning method and system based on fingerprint image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810604468.XA CN110596541B (en) | 2018-06-13 | 2018-06-13 | Partial discharge positioning method and system based on fingerprint image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110596541A true CN110596541A (en) | 2019-12-20 |
| CN110596541B CN110596541B (en) | 2024-01-19 |
Family
ID=68848854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810604468.XA Active CN110596541B (en) | 2018-06-13 | 2018-06-13 | Partial discharge positioning method and system based on fingerprint image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110596541B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112147470A (en) * | 2020-09-03 | 2020-12-29 | 上海交通大学 | GIL partial discharge source positioning method and system |
| CN112147471A (en) * | 2020-09-03 | 2020-12-29 | 上海交通大学 | GIL partial discharge source positioning method and system |
| CN112881868A (en) * | 2021-01-11 | 2021-06-01 | 西安交通大学 | Transformer partial discharge space positioning method |
| CN113866569A (en) * | 2021-04-01 | 2021-12-31 | 全球能源互联网研究院有限公司 | Multi-partial discharge source fingerprint positioning method and device based on broadband radio frequency detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10170596A (en) * | 1996-12-09 | 1998-06-26 | Hitachi Ltd | System for diagnosing insulated apparatus and method for detecting partial discharge |
| CN101004436A (en) * | 2007-01-22 | 2007-07-25 | 西南交通大学 | High senitive system for detecting local discharging of high voltage electric power equipment with large capacity |
| CN101702002A (en) * | 2009-12-07 | 2010-05-05 | 上海市电力公司 | Local discharge electroacoustic united detection positioning system and positioning method thereof |
| CN105629136A (en) * | 2015-12-28 | 2016-06-01 | 国网甘肃省电力公司金昌供电公司 | Cable insulation state online automatic monitoring and diagnosis system |
| CN106291281A (en) * | 2016-08-08 | 2017-01-04 | 国网上海市电力公司 | A kind of substation equipment shelf depreciation alignment system and method thereof |
| CN205910298U (en) * | 2016-08-03 | 2017-01-25 | 国网甘肃省电力公司电力科学研究院 | Hyperfrequency partial discharge signal simulation source device |
-
2018
- 2018-06-13 CN CN201810604468.XA patent/CN110596541B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10170596A (en) * | 1996-12-09 | 1998-06-26 | Hitachi Ltd | System for diagnosing insulated apparatus and method for detecting partial discharge |
| CN101004436A (en) * | 2007-01-22 | 2007-07-25 | 西南交通大学 | High senitive system for detecting local discharging of high voltage electric power equipment with large capacity |
| CN101702002A (en) * | 2009-12-07 | 2010-05-05 | 上海市电力公司 | Local discharge electroacoustic united detection positioning system and positioning method thereof |
| CN105629136A (en) * | 2015-12-28 | 2016-06-01 | 国网甘肃省电力公司金昌供电公司 | Cable insulation state online automatic monitoring and diagnosis system |
| CN205910298U (en) * | 2016-08-03 | 2017-01-25 | 国网甘肃省电力公司电力科学研究院 | Hyperfrequency partial discharge signal simulation source device |
| CN106291281A (en) * | 2016-08-08 | 2017-01-04 | 国网上海市电力公司 | A kind of substation equipment shelf depreciation alignment system and method thereof |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112147470A (en) * | 2020-09-03 | 2020-12-29 | 上海交通大学 | GIL partial discharge source positioning method and system |
| CN112147471A (en) * | 2020-09-03 | 2020-12-29 | 上海交通大学 | GIL partial discharge source positioning method and system |
| CN112147470B (en) * | 2020-09-03 | 2021-07-20 | 上海交通大学 | GIL partial discharge source positioning method and system |
| CN112881868A (en) * | 2021-01-11 | 2021-06-01 | 西安交通大学 | Transformer partial discharge space positioning method |
| CN113866569A (en) * | 2021-04-01 | 2021-12-31 | 全球能源互联网研究院有限公司 | Multi-partial discharge source fingerprint positioning method and device based on broadband radio frequency detection |
| WO2022205834A1 (en) * | 2021-04-01 | 2022-10-06 | 全球能源互联网研究院有限公司 | Multi-partial-discharge-source fingerprint positioning method and apparatus based on broadband radio frequency detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110596541B (en) | 2024-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110596541B (en) | Partial discharge positioning method and system based on fingerprint image | |
| US8352204B2 (en) | Method of detecting system function by measuring frequency response | |
| CN109638862B (en) | CEEMDAN algorithm-based electric power system low-frequency oscillation mode identification method | |
| KR100729107B1 (en) | Methods of Input Vector formation for Auto-identification of partial discharge source using neural networks | |
| CN106841949B (en) | Method and device for monitoring stator insulation of three-phase asynchronous alternating current motor on line | |
| CN104200236A (en) | Quick target detection method based on DPM (deformable part model) | |
| CN104614653A (en) | Array antenna based multiple local discharge point positioning and distinguishing method for local discharge detection device | |
| DE602004025599D1 (en) | DETECTION OF ERRORS OF SYSTEM COMPONENTS IN A CONTINUOUS PROCESS | |
| CN107966638A (en) | Method and apparatus, storage medium and the processor of correction error | |
| CN109596951A (en) | A kind of Partial Discharge Sources localization method and system | |
| CN111241904A (en) | Operation mode identification method under underdetermined condition based on blind source separation technology | |
| CN105277826A (en) | Array antenna fault diagnosis system | |
| KR970002345A (en) | Measurement of Radiation Emissions in Giga-Hertz Transverse Electromagnetic (GTEM) Cells | |
| CN102981160B (en) | Method and device for ascertaining aerial target track | |
| CN112688324B (en) | Power system low-frequency oscillation mode identification method based on FastICA and TLS-ESPRIT | |
| CN111398433B (en) | Acoustic emission source positioning method and system based on linear weighted least square method | |
| Zarei et al. | Broken rotor bars detection via Park's vector approach based on ANFIS | |
| CN114578197A (en) | Transformer bushing partial discharge three-dimensional positioning method and system based on planar UHF sensor | |
| CN102914763A (en) | Method for positioning damage sound emission source of hydraulic concrete | |
| Tjen et al. | Ensemble of the Distance Correlation-Based and Entropy-Based Sensor Selection for Damage Detection | |
| CN114839482A (en) | Power frequency withstand voltage breakdown position positioning method and device of low-voltage comprehensive distribution box | |
| CN112284704A (en) | Rotating equipment fault diagnosis method and system based on test matrix and readable storage medium | |
| CN113156278A (en) | CNN network-based GIS partial discharge positioning method | |
| Rongjie et al. | Application of similarity in fault diagnosis of power electronics circuits | |
| KR102030526B1 (en) | Method for estimating direction of arrival based on continuous compressive sensing and apparatus therefor |
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 |