CN110954792B - Characteristic waveband extraction method based on hyperspectral imaging composite insulator umbrella skirt aging - Google Patents
Characteristic waveband extraction method based on hyperspectral imaging composite insulator umbrella skirt aging Download PDFInfo
- Publication number
- CN110954792B CN110954792B CN201911262368.4A CN201911262368A CN110954792B CN 110954792 B CN110954792 B CN 110954792B CN 201911262368 A CN201911262368 A CN 201911262368A CN 110954792 B CN110954792 B CN 110954792B
- Authority
- CN
- China
- Prior art keywords
- image
- characteristic
- band
- aging
- bands
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G01R31/1227—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 of components, parts or materials
- G01R31/1245—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 of components, parts or materials of line insulators or spacers, e.g. ceramic overhead line cap insulators; of insulators in HV bushings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- 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
- G01R31/1218—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 using optical methods; using charged particle, e.g. electron, beams or X-rays
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Ceramic Engineering (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses a hyperspectral imaging-based method for extracting characteristic wave bands of ageing of umbrella skirts of composite insulators, which comprises the following steps: manufacturing a composite insulator umbrella skirt slice with known aging degree, and shooting a hyperspectral image of the composite insulator umbrella skirt slice in the same view field; matrixing the hyperspectral image and performing principal component analysis to obtain a first principal component image; analyzing the superposition proportion of each waveband image in the first main component image, namely the contribution rate of each waveband, and taking the first A wavebands with high contribution rates as alternative characteristic wavebands; b characteristic wave bands are preset and finally extracted, the respective image information entropies H (P) of the A alternative characteristic wave bands are calculated, and then the joint information entropies Hcor (P) among any B wave bands in the A characteristic wave bands are calculated; and defining an optimal waveband index Q, wherein the Q is a function of the image information entropy and the joint information entropy, and combining the characteristic wavebands with the maximum Q into the optimal B characteristic wavebands.
Description
Technical Field
The invention belongs to the technical field of power equipment detection, and particularly relates to a hyperspectral imaging-based characteristic waveband extraction method for composite insulator umbrella skirt aging.
Background
The invention relates to aging state diagnosis of power equipment, in particular to a method suitable for diagnosing the aging state of a silicon rubber composite insulator. The silicon rubber composite insulator has the advantages of strong hydrophobicity, high pollution flashover voltage and the like, and is widely applied to a power distribution network part of power equipment. However, the outdoor insulator is exposed to a severe natural environment for a long time, such as strong ultraviolet radiation and acid rain erosion, the surface insulation state of the outdoor insulator is degraded, and phenomena such as hydrophobicity reduction, material flexibility reduction, corona onset voltage reduction and the like are shown, so that the outdoor insulator poses a potential threat to the safe operation of a power system. The current common detection method of the insulator is a voltage and current measurement method, and the method can accurately obtain the running state of the insulator by measuring the electrical parameters such as voltage, leakage current and the like flowing through the insulator. However, the method cannot realize non-contact measurement, and has high detection cost and low efficiency. For example, in the traditional evaluation of the aging state of the umbrella skirt of the silicon rubber composite insulator, the aging state of the insulator is evaluated by measuring electrical parameters such as voltage and leakage current flowing through the insulator, and the method needs to carry out power failure maintenance on a line, belongs to contact measurement, and is low in efficiency and safety.
The above information disclosed in this background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a hyperspectral imaging-based method for extracting characteristic wave bands of umbrella skirt aging of a composite insulator. The method provides a good data cleaning means for the subsequent aging state detection of the insulator shed, converts high-dimensional image information into 3-5-dimensional low-dimensional image information, and has significant practical significance for the rapid diagnosis of the aging state of the silicon rubber composite insulator shed, the realization of non-contact online monitoring and the improvement of the safety of a power transmission line.
The invention aims to realize the following technical scheme, and the method for extracting the characteristic waveband of the aged composite insulator umbrella skirt based on hyperspectral imaging comprises the following steps:
in the first step, a composite insulator umbrella skirt slice with known aging degree is manufactured, and hyperspectral images of the composite insulator umbrella skirt slice are shot in the same view field;
in the second step, matrixing the hyperspectral image and performing principal component analysis to obtain a first principal component image;
in the third step, the superposition proportion of each waveband image in the first main component image is analyzed, namely the contribution rate of each waveband is analyzed, and the first A wavebands with high contribution rates are used as alternative characteristic wavebands;
in the fourth step, B characteristic wave bands are preset to be finally extracted, the respective image information entropies H (P) of A standby characteristic wave bands are calculated, and then the joint information entropies Hcor (P) among any B wave bands in the A characteristic wave bands are calculated;
in the fifth step, an optimal waveband index Q is defined, wherein the Q is a function of the image information entropy and the joint information entropy, and the characteristic wavebands with the maximum Q are combined into the optimal B characteristic wavebands.
In the method, in the first step, when the composite insulator umbrella skirt slice with known aging degree is manufactured, the aging types comprise acid aging, thermal aging and electrical aging, and the characteristic wave bands corresponding to different aging types are different.
In the method, in the second step, the hyperspectral image is matrixed, the hyperspectral image has M wave bands, the grayscale image of each wave band has N pixel points, and then the hyperspectral data is a matrix with M rows and N columns.
In the method, in the second step, each row of the matrix is used as input to carry out principal component analysis to obtain a first principal component image, and the first principal component image is obtained by superposing and fusing M gray level images according to a certain proportion.
In the method, in the second step, the superposition proportion of each waveband image in the first main component image, namely the contribution rate of each waveband, is analyzed, a waveband-contribution rate curve is drawn, and wavebands corresponding to A local contribution rate peak values are found out to be used as alternative characteristic wavebands.
In the method, in the fourth step,
wherein p isiIs the ratio of the gray value i to the total pixel value, pi，j，k，…，nThe gray scale value in the image of the first characteristic wave band is i, the gray scale value in the image of the second characteristic wave band is j, the gray scale value in the image of the third characteristic wave band is k, and the gray scale value of the B-th image is the product of the probabilities of n.
In the fifth step of the method, the defined optimal band index Q is:
the Q values of all band combinations are calculated,
wherein H1(p)、H2(p)、H3(p)...HB(p) represents the information entropy of each of the B band images, HcorAnd (p) represents joint information entropy among the B images, and the optimal B characteristic wave bands are combined by taking the characteristic wave band with the maximum Q.
In the method, B characteristic wave bands form an insulator umbrella skirt aging state characteristic library, wherein the insulator umbrella skirt aging state characteristic library comprises composite insulator umbrella skirt aging types, characteristic wave bands and aging degrees.
In the method, the number of characteristic wave bands is not more than 5.
In the method, the composite insulator shed comprises a silicon rubber composite insulator shed.
Compared with the prior art, the invention has the following advantages:
the method comprises the steps of manufacturing a composite insulator shed slice with known aging degree, shooting a hyperspectral picture of the insulator shed slice in the same view field, analyzing the shot hyperspectral image, carrying out primary screening through principal component analysis, calculating an optimal band combination through defining an optimal band index Q, and carrying out refined extraction of a characteristic band. The traditional characteristic wave band extraction method is usually selected manually, and is time-consuming and labor-consuming; in the new method, after the contribution value of the first principal component is calculated, the waveband with a larger contribution value is used as the characteristic waveband, the characteristic waveband extracted by the method has a higher dimension, and the characteristic waveband still needs to be further manually screened through a visual image. The method for extracting the characteristic wave band has the advantages of non-manual intervention, high efficiency, accuracy, strong applicability and the like, belongs to non-contact measurement, and can be applied to the characteristic wave band extraction of the aging state of the silicon rubber composite insulator.
Drawings
Various other advantages and benefits of the present invention will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. Also, like parts are designated by like reference numerals throughout the drawings.
In the drawings:
FIG. 1 is a schematic flow chart of a method for extracting characteristic wave bands of ageing of a composite insulator shed based on hyperspectral imaging according to one embodiment of the invention;
fig. 2(a) is an acid-aged insulator shed sample slice of a hyperspectral imaging-based composite insulator shed aging characteristic band extraction method according to an embodiment of the invention, fig. 2(b) is a grayscale image of a first principal component, fig. 2(c) is a final fused image, and from the figure, it can be clearly seen that different aged insulators have different spectral reflectances, which are reflected on the images, that is, the grays are different;
fig. 3 shows the loading rate, which may also be referred to as a contribution rate, of each band image in the first principal component image.
The invention is further explained below with reference to the figures and examples.
Detailed Description
Specific embodiments of the present invention will be described in more detail below with reference to fig. 1 to 3. While specific embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
It should be noted that certain terms are used throughout the description and claims to refer to particular components. As one skilled in the art will appreciate, various names may be used to refer to a component. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. The description which follows is a preferred embodiment of the invention, but is made for the purpose of illustrating the general principles of the invention and not for the purpose of limiting the scope of the invention. The scope of the present invention is defined by the appended claims.
For the purpose of facilitating understanding of the embodiments of the present invention, the following description will be made by taking specific embodiments as examples with reference to the accompanying drawings, and the drawings are not to be construed as limiting the embodiments of the present invention.
For better understanding, fig. 1 is a schematic flow chart of a method according to an embodiment of the present invention, and as shown in fig. 1, the method for extracting a characteristic waveband of umbrella skirt aging of a composite insulator based on hyperspectral imaging includes the following steps:
in a first step S1, manufacturing a composite insulator shed slice with known aging degree, and shooting a hyperspectral image of the composite insulator shed slice in the same view field;
in a second step S2, matrixing the hyperspectral image and performing principal component analysis to obtain a first principal component image;
in a third step S3, analyzing the ratio of overlapping each band image in the first principal component image, that is, the contribution rate of each band, and using the first a bands with large contribution rates as candidate feature bands;
in the fourth step S4, B feature bands are predetermined to be finally extracted, the respective image information entropies h (p) of the a candidate feature bands are calculated, and then the joint information entropies hcor (p) between any B bands in the a feature bands are calculated;
in the fifth step S5, an optimal band index Q is defined, where Q is a function of the image information entropy and the joint information entropy, and the characteristic bands with the maximum Q are combined into the optimal B characteristic bands.
In a preferred embodiment of the method, in the first step S1, when the composite insulator shed slices with known aging degrees are manufactured, the aging types include acid aging, thermal aging and electrical aging, and the characteristic bands corresponding to different aging types are different.
In a preferred embodiment of the method, in the second step S2, the hyperspectral image is matrixed, the hyperspectral image has M bands, and the grayscale image of each band has N pixels, so that the hyperspectral data is a matrix of M rows and N columns.
In a preferred embodiment of the method, in the second step S2, a principal component analysis is performed with each row of the matrix as an input to obtain a first principal component image, where the first principal component image is obtained by superimposing and fusing M grayscale images according to a certain ratio.
In a preferred embodiment of the method, in the second step S2, a ratio of overlapping each band image in the first principal component image, that is, a contribution ratio of each band, is analyzed, a band-contribution ratio curve is drawn, and a band corresponding to a number a of local contribution ratio peaks is found as a candidate characteristic band.
In a preferred embodiment of the method, in a fourth step S4,
wherein p isiIs the ratio of the gray value i to the total pixel value, pi，j，k，…，nThe gray scale value in the image of the first characteristic wave band is i, the gray scale value in the image of the second characteristic wave band is j, the gray scale value in the image of the third characteristic wave band is k, and the gray scale value of the B-th image is the product of the probabilities of n.
In a preferred embodiment of the method, in the fifth step S5, the defined optimal band index Q is:
the Q values of all band combinations are calculated,
wherein H1(p)、H2(p)、H3(p)...HB(p) represents the information entropy of each of the B band images, HcorAnd (p) represents joint information entropy among the B images, and the optimal B characteristic wave bands are combined by taking the characteristic wave band with the maximum Q.
In a preferred embodiment of the method, the B characteristic bands form an insulator shed aging state characteristic library, wherein the insulator shed aging state characteristic library includes a composite insulator shed aging type, a characteristic band and an aging degree.
For further understanding of the present invention, the following description is given in conjunction with the accompanying drawings and the practical examples. This case takes the evaluation of the acid aging state of the composite silicone rubber insulator as an example.
An acid-aged silicone rubber composite insulator shed slice was prepared as shown in fig. 2 (a). The samples prepared were: the slice size is about 5cm x 2mm, dilute sulfuric acid with the concentration of 1mol/L is used in the accelerated acid aging experiment, and the soaking time is 0h, 24h, 48h and 72h respectively.
Shooting a hyperspectral image of a silicon rubber composite insulator shed slice, as shown in fig. 2(b), acquiring an image of a first principal component by a principal component analysis method, analyzing the contribution rate of each waveband image in the image of the first principal component, and finding out the waveband of the first five local peak values as a candidate characteristic waveband: 399.2nm, 415.2nm, 698.8nm, 716.2nm and 949.7nm, as shown in FIG. 3.
Calculating respective information entropy H of gray images under five wave bands1(p)-H5(P) and calculating the joint information entropy H between any threecor(p) of the formula (I). The total 10Q values are calculated, the highest Q value is taken, and the obtained optimal waveband combination is as follows: 698.8nm, 716.2nm, 949.7 nm.
Three optical filters with the bandwidth of 10nm are prepared, and the central frequencies are 699nm, 716nm and 950nm respectively. Three filters are installed on a multispectral camera, a gray scale image under three characteristic wave bands is shot, image fusion and image rendering are carried out, and the result is shown in the attached figure 2 (c).
Diagnostic evaluation rules are formulated as shown in table 1.
And (4) performing a verification test by using the rest samples, wherein the accuracy in 20 verification tests is 85%, which indicates that the diagnosis evaluation rule has higher confidence. Therefore, the information such as the aging type, the characteristic band range, the number of characteristic bands, the gray-scale image and the fused image under the characteristic bands, the diagnosis rule, and the like can be recorded in the database.
In one embodiment, the method comprises establishing a composite insulator shed aging state feature library: and manufacturing a composite insulator shed slice with known aging degree, and shooting a hyperspectral picture of the insulator shed slice in the same view field. And analyzing the hyperspectral image obtained by shooting, calculating an optimal waveband index by a statistical method, and extracting a characteristic waveband. The gray level image under the characteristic wave band can represent the insulation state of the insulator. And (3) assembling the optical filter corresponding to the characteristic wave band on the multispectral camera, shooting a gray image under the characteristic wave band by using the multispectral camera, and performing image data processing and image visual fusion. And finally, summarizing the corresponding relation between the aging degree and the gray value of the fused image, and making a corresponding diagnosis rule to form an insulator umbrella skirt aging state feature library. When diagnosis is needed, the insulator umbrella skirt is cleaned, and standard umbrella skirt slices are prepared. And shooting a multispectral image of the wave band of the umbrella skirt section by using a multispectral camera, processing the image, comparing with an insulator umbrella skirt aging state feature library, and judging the aging degree of the insulator material according to the gray value of the image.
In one embodiment, the feature library contains the following types of data information: the aging type, the characteristic wave band, the aging degree evaluation standard, the gray level image under the characteristic wave band, and the corresponding relation between the gray level value and the aging degree. The aging types generally include acid aging, thermal aging and electrical aging, and the characteristic bands corresponding to different aging are generally different.
In one embodiment, the sheds slices should be taken from the cleaned composite insulator without significant dirt and scratches on the surface. The sample is cut perpendicular to the surface of the shed, and the length and width of the cut piece is about 5cm x 5cm, i.e. the thickness is the original thickness of the shed, and is usually 1-2 cm.
In one embodiment, the number of eigenbands is usually no more than 5, and 3 eigenbands are exemplified in this patent. The gray scale image under the characteristic wave band should satisfy the following three conditions as much as possible: the information content of the image is as large as possible; the correlation between pictures is as small as possible; the aging state diagnosis can be realized by matching images of different wave bands. And satisfying the optimal solution of the conditions to obtain the wave band which is the characteristic wave band.
In one embodiment, a method for extracting aging state characteristic wave bands of a silicon rubber composite insulator umbrella skirt.
S1: firstly, the hyperspectral images of the umbrella skirt sections of the composite insulator are matrixed, the hyperspectral images are provided with M wave bands, the gray level images of each wave band are provided with N pixel points, and then hyperspectral data is a matrix with M rows and N columns.
S2: taking each row of the matrix as input, carrying out principal component analysis on the data to obtain a first principal component image, wherein the image is obtained by superposing and fusing M gray level images according to a certain proportion.
S3: analyzing the superposition proportion of each waveband image in the first main component image, namely the contribution rate of each waveband, and finding out a waveband with a larger contribution rate as a candidate characteristic waveband;
s4: taking the final extraction of three characteristic wave bands as an example, the image information entropies H (i) of all the candidate characteristic wave bands are calculated, and the joint information entropies H (i, j, k) among any three are calculated, as shown in formulas 1 and 2.
In the formula, piThe gray value i is the probability of the occurrence of the gray value i in the whole image, namely the proportion of the pixel point with the gray value i in all the pixel values, and the gray value i represents the richness of the image gray.
In the formula, pi，j，kThe product of probability probabilities of i being the gray scale value in image 1, j being the gray scale value in image 2, and k being the gray scale value in image 3. Hcor(p) characterizes the degree of correlation between the three images. Similarly, for the correlations of N characteristic bands, their joint information entropy can still be written like 2.
S5: the richer the image information is, the larger the information entropy of the image is; the smaller the correlation between images, the smaller their joint information entropy. Therefore, the patent defines an optimal band index Q, and calculates Q values of all band combinations, as shown in formula 3. And (4) combining the characteristic wave bands with the maximum Q, namely the optimal three characteristic wave bands.
In the formula, H1(p)、H2(p)、H3And (p) respectively representing the information entropy of the first three graphs. Hcor(p) characterizes the degree of correlation between the three images.
Although the embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to the above-described embodiments and application fields, and the above-described embodiments are illustrative, instructive, and not restrictive. Those skilled in the art, having the benefit of this disclosure, may effect numerous modifications thereto without departing from the scope of the invention as defined by the appended claims.
Claims (6)
1. A method for extracting characteristic wave bands of composite insulator umbrella skirt aging based on hyperspectral imaging comprises the following steps:
in the first step (S1), making a composite insulator shed slice with known aging degree, and shooting a hyperspectral image of the composite insulator shed slice in the same view field;
in a second step (S2), matrixing the hyperspectral image and performing principal component analysis to obtain a first principal component image;
in the third step (S3), analyzing the ratio of overlapping each band image in the first principal component image, i.e., the contribution rate of each band, taking the first a bands with a large contribution rate as candidate feature bands, analyzing the ratio of overlapping each band image in the first principal component image, i.e., the contribution rate of each band, drawing a band-contribution rate curve, and finding out the bands corresponding to a local contribution rate peak as candidate feature bands;
in the fourth step (S4), B characteristic wave bands are preset to be finally extracted, the image information entropy H (P) of each A candidate characteristic wave band is calculated, the joint information entropy Hcor (P) among any B wave bands in the A characteristic wave bands is calculated,
wherein p isiIs the ratio of the gray value i to the total pixel value, pi，j，k，…，nThe gray value of the image of the first characteristic wave band is i, the gray value of the image of the second characteristic wave band is j, the gray value of the image of the third characteristic wave band is k, and the gray value of the B-th image is the product of the probabilities of n;
in the fifth step (S5), an optimal band index Q is defined, where Q is a function of the image information entropy and the joint information entropy, and the characteristic bands with the maximum Q are combined into the optimal B characteristic bands.
2. The method as claimed in claim 1, wherein, in the first step (S1), when the composite insulator shed slices with known aging degree are manufactured, the aging types include acid aging, thermal aging and electric aging, and the characteristic wave bands corresponding to different aging types are different.
3. The method according to claim 1, wherein in the second step (S2), the hyperspectral image is matrixed, the hyperspectral image has M bands, the grayscale image of each band has N pixel points, and the hyperspectral data is a matrix of M rows and N columns.
4. The method according to claim 3, wherein in the second step (S2), a principal component analysis is performed with each row of the matrix as input to obtain a first principal component image, and the first principal component image is obtained by superposing and fusing the M gray-scale images in a certain proportion.
5. The method according to claim 1, wherein in the fifth step (S5), the defined optimal band index Q is:
the Q values of all band combinations are calculated,
wherein H1(p)、H2(p)、H3(p)...HB(p) represents the information entropy of each of the B band images, HcorAnd (p) represents joint information entropy among the B images, and the optimal B characteristic wave bands are combined by taking the characteristic wave band with the maximum Q.
6. The method of claim 1, wherein the B characteristic bands form an insulator shed aging status feature library, wherein the insulator shed aging status feature library comprises a composite insulator shed aging type, a characteristic band, and an aging level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911262368.4A CN110954792B (en) | 2019-12-10 | 2019-12-10 | Characteristic waveband extraction method based on hyperspectral imaging composite insulator umbrella skirt aging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911262368.4A CN110954792B (en) | 2019-12-10 | 2019-12-10 | Characteristic waveband extraction method based on hyperspectral imaging composite insulator umbrella skirt aging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110954792A CN110954792A (en) | 2020-04-03 |
| CN110954792B true CN110954792B (en) | 2021-04-09 |
Family
ID=69980794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911262368.4A Active CN110954792B (en) | 2019-12-10 | 2019-12-10 | Characteristic waveband extraction method based on hyperspectral imaging composite insulator umbrella skirt aging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110954792B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858858B (en) * | 2021-03-26 | 2022-08-02 | 云南电网有限责任公司电力科学研究院 | Dimension reduction-based partial discharge spectrum characteristic waveband extraction method and device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011123431A (en) * | 2009-12-14 | 2011-06-23 | Toshiba Elevator Co Ltd | Life determining device of light-emitting device display device |
| CN102520323A (en) * | 2011-12-15 | 2012-06-27 | 国网电力科学研究院 | Hyperspectrum-based composite insulator aging operating state detection method |
| CN103941120A (en) * | 2014-03-31 | 2014-07-23 | 张奇 | Device for hydrophobicity detection and aging evaluation of composite insulator |
| CN104751179A (en) * | 2015-04-01 | 2015-07-01 | 河海大学 | Multi-target high spectral remote sensing image wave band selection method based on game theory |
| CN104764748A (en) * | 2015-05-04 | 2015-07-08 | 成都唐源电气有限责任公司 | Method and system for positioning insulators and method and system for fault detection |
| US20180232883A1 (en) * | 2017-02-13 | 2018-08-16 | Amit Sethi | Systems & Methods for Computational Pathology using Points-of-interest |
| CN109145135A (en) * | 2018-08-03 | 2019-01-04 | 厦门大学 | A kind of human face portrait aging method based on principal component analysis |
| CN109239024A (en) * | 2018-09-05 | 2019-01-18 | 国网河北省电力有限公司电力科学研究院 | Composite insulator Aging level evaluation method and system |
| CN109781614A (en) * | 2019-03-29 | 2019-05-21 | 云南电网有限责任公司电力科学研究院 | A kind of method for comprehensive detection of composite insulator degree of aging |
| CN110376155A (en) * | 2019-09-02 | 2019-10-25 | 云南电网有限责任公司电力科学研究院 | Composite insulator degradation detecting method and system based on infrared spectroscopy |
| CN110441647A (en) * | 2019-09-06 | 2019-11-12 | 云南电网有限责任公司电力科学研究院 | Arc light assessment of risks method and device based on spectral intensity information |
-
2019
- 2019-12-10 CN CN201911262368.4A patent/CN110954792B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011123431A (en) * | 2009-12-14 | 2011-06-23 | Toshiba Elevator Co Ltd | Life determining device of light-emitting device display device |
| CN102520323A (en) * | 2011-12-15 | 2012-06-27 | 国网电力科学研究院 | Hyperspectrum-based composite insulator aging operating state detection method |
| CN103941120A (en) * | 2014-03-31 | 2014-07-23 | 张奇 | Device for hydrophobicity detection and aging evaluation of composite insulator |
| CN104751179A (en) * | 2015-04-01 | 2015-07-01 | 河海大学 | Multi-target high spectral remote sensing image wave band selection method based on game theory |
| CN104764748A (en) * | 2015-05-04 | 2015-07-08 | 成都唐源电气有限责任公司 | Method and system for positioning insulators and method and system for fault detection |
| US20180232883A1 (en) * | 2017-02-13 | 2018-08-16 | Amit Sethi | Systems & Methods for Computational Pathology using Points-of-interest |
| CN109145135A (en) * | 2018-08-03 | 2019-01-04 | 厦门大学 | A kind of human face portrait aging method based on principal component analysis |
| CN109239024A (en) * | 2018-09-05 | 2019-01-18 | 国网河北省电力有限公司电力科学研究院 | Composite insulator Aging level evaluation method and system |
| CN109781614A (en) * | 2019-03-29 | 2019-05-21 | 云南电网有限责任公司电力科学研究院 | A kind of method for comprehensive detection of composite insulator degree of aging |
| CN110376155A (en) * | 2019-09-02 | 2019-10-25 | 云南电网有限责任公司电力科学研究院 | Composite insulator degradation detecting method and system based on infrared spectroscopy |
| CN110441647A (en) * | 2019-09-06 | 2019-11-12 | 云南电网有限责任公司电力科学研究院 | Arc light assessment of risks method and device based on spectral intensity information |
Non-Patent Citations (4)
| Title |
|---|
| Diagnosis of Operating Insulator Aging Status Based on Image Processing and Hyperspectral Analysis;Bin Wang等;《 2019 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)》;20191023;全文 * |
| Electric field calculation of transmission line composite insulator and umbrella skirt optimization;Hongxia Miao等;《 International Conference on Software Intelligence Technologies and Applications & International Conference on Frontiers of Internet of Things 2014》;20141206;全文 * |
| 基于图谱特征的复合绝缘子老化神经网络评估方法;邵瑰玮等;《高电压技术》;20140331;第40卷(第3期);全文 * |
| 复合绝缘子运行状态在线非接触检测技术研究;王永浩;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20170315(第3期);第17页倒数第2段至第40页第2段，第46页第1段至第52页最后一段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110954792A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110954793B (en) | Composite insulator umbrella skirt aging detection method and detection device based on spectral imaging | |
| CN110111256B (en) | Image super-resolution reconstruction method based on residual distillation network | |
| Zheng et al. | No-reference quality assessment for screen content images based on hybrid region features fusion | |
| CN105160667A (en) | Blind image quality evaluation method based on combining gradient signal and Laplacian of Gaussian (LOG) signal | |
| CN110954792B (en) | Characteristic waveband extraction method based on hyperspectral imaging composite insulator umbrella skirt aging | |
| CN116612098B (en) | Insulator RTV spraying quality evaluation method and device based on image processing | |
| Wu et al. | Beyond synthetic data: A blind deraining quality assessment metric towards authentic rain image | |
| CN109886927B (en) | Image quality evaluation method based on nuclear sparse coding | |
| Wei et al. | Effects of lossy compression on remote sensing image classification based on convolutional sparse coding | |
| CN114359167A (en) | Insulator defect detection method based on lightweight YOLOv4 in complex scene | |
| CN108010023A (en) | High dynamic range images quality evaluating method based on tensor domain curvature analysis | |
| CN117392065A (en) | Cloud edge cooperative solar panel ash covering condition autonomous assessment method | |
| CN116519710A (en) | Method and system for detecting surface pollution state of composite insulator | |
| CN108776958B (en) | Mix the image quality evaluating method and device of degraded image | |
| CN107590796B (en) | Full-reference mixed distortion image quality evaluation method based on sparse decomposition residual | |
| CN111813996B (en) | Video searching method based on sampling parallelism of single frame and continuous multi-frame | |
| CN114037632A (en) | Multi-scale residual error attention map image defogging method based on LAB color space | |
| Liu et al. | A new image quality approach based on decision fusion | |
| Klima et al. | Image quality evaluation in security imaging systems | |
| CN114220084A (en) | Distribution equipment defect identification method based on infrared image | |
| Wu et al. | Joint entropy degradation based blind image quality assessment | |
| CN111179224A (en) | Joint learning-based reference-free evaluation method for aerial image restoration quality | |
| Liu et al. | An Evaluation Method of Composite Insulator Aging Grade Based on Probabilistic Neural Network | |
| Klíma et al. | Subjective image quality evaluation in security imaging systems | |
| Srinath et al. | Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment |
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 |