CN110632092A - Insulator surface contamination distribution characteristic detection method based on hyperspectral technology - Google Patents
Insulator surface contamination distribution characteristic detection method based on hyperspectral technology Download PDFInfo
- Publication number
- CN110632092A CN110632092A CN201911025950.9A CN201911025950A CN110632092A CN 110632092 A CN110632092 A CN 110632092A CN 201911025950 A CN201911025950 A CN 201911025950A CN 110632092 A CN110632092 A CN 110632092A
- Authority
- CN
- China
- Prior art keywords
- insulator
- value
- integral
- insulator surface
- position point
- 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
Images
Classifications
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
According to the method for detecting the pollution distribution characteristics on the surface of the insulator based on the hyperspectral technology, a hyperspectral image of a detected natural pollutant accumulation insulator is obtained, and a characteristic wave band and an insulator area are respectively extracted according to the insulator surface spectral line graph and the insulator surface camera image; obtaining the spectral line integral value of each position point by integrating the spectral lines of the characteristic wave band to calculate the area; obtaining integral difference values and integral minimum values of the whole according to the integral difference values and the integral minimum values, and judging whether the whole pollution condition on the surface of the insulator is uneven or not; obtaining the integral difference value of each position point and the gradient of the difference value in a position-integral difference value space; judging whether the pollution distribution near the point is uneven or not; the problem of traditional high spectrum build storehouse detection insulator surface filth distribution, the sample demand is high and cover limitedly, and the popularization nature is poor, receives shooting condition to influence greatly etc is overcome, for insulator surface filth provide the washing suggestion, improve transmission line's security.
Description
Technical Field
The application relates to the technical field of insulator safety performance detection, in particular to a method for detecting the distribution characteristics of insulator surface dirt based on a hyperspectral technology.
Background
The high-voltage direct-current transmission line has the advantages of long-distance large-capacity transmission and the like, and becomes an important part in the current power development, along with the rapid development of industry in recent years, the environmental pollution is increasingly severe, the number of severe weather days in various regions tends to increase, dirt particles are more easily deposited on the surface of the transmission line insulator to form a natural dirt-accumulating insulator, and are affected with damp in humid weather environments such as fog, hair rain and the like, water-soluble substances in the dirt are dissolved in water to form a conductive water film, so that the conductivity of the surface of the insulator is increased, further the leakage current is increased to cause local heating, finally, a dirt flashover accident is developed, even a large-area power failure is caused, and the safe operation of a power system is seriously affected.
The surface electric field distribution is uneven when the pollution on the surface of the natural pollution-accumulating insulator is uneven, and the pollution flashover is easier to cause in severe weather, so that the pollution distribution characteristic on the surface of the insulator is timely and accurately detected, the surface of the insulator can be timely cleaned when the pollution is uneven, and the pollution flashover accident is reduced.
At present, the pollution on the surface of an insulator is detected by hyperspectral remote sensing, uninterrupted measurement can be realized, and the operation is convenient and fast, but the traditional hyperspectral detection mode is to establish a library and compare a detected object with data of a sample library to obtain a measurement result, the sample quantity required for constructing the library is large, the interference factor is small, the popularization is poor, and the data dispersibility is large due to shooting conditions and other reasons; in addition, natural pollutants are very complex, the number of types of single pollutants is huge, the combination of multiple pollutants is more various, and the factors of different mixing proportions, different water contents and the like are added, so that the warehouse building detection has great limitation.
Disclosure of Invention
The application provides a method for detecting the pollution distribution characteristics on the surface of an insulator based on a hyperspectral technology, and the pollution distribution characteristics on the surface of the insulator can be timely and accurately detected.
In order to solve the technical problem, the embodiment of the application discloses the following technical scheme:
the application provides a method for detecting the distribution characteristics of dirt on the surface of an insulator based on a hyperspectral technology, which comprises the following steps:
acquiring a hyperspectral image of the surface of an insulator to be measured, wherein the hyperspectral image of the surface of the insulator comprises an insulator surface spectrum line graph and an insulator surface camera image;
respectively extracting a characteristic wave band and an insulator region according to the insulator surface spectral line graph and the insulator surface camera image;
acquiring an integral difference value between the maximum value and the minimum value of the integral value of the characteristic wave band;
judging the size of the integral difference value and a first preset threshold value;
if the integral difference value is larger than the first preset threshold value, judging that the integral contamination on the surface of the insulator is not uniform;
acquiring a mode of gradient of each position point of the insulator region;
judging the modulus of the gradient of the position point and the size of a second preset threshold;
if the modulus of the gradient of the position points is larger than the second preset threshold value, judging that the position points are unevenly distributed with filth, and marking as uneven filth points;
judging the number of the uneven points of the dirt and the size of a third preset threshold;
and if the number of the uneven points of the contamination is larger than the third preset threshold value, judging that the insulator is the insulator needing to be cleaned.
Optionally, the method further includes:
acquiring position information of each position point according to the image of the insulator surface camera;
specifying a color function for each position point based on an integrated difference between a maximum value and a minimum value of the integrated value for each position point;
and assigning the color function of each position point to the position information of each position point to obtain a visual pollution uneven content distribution diagram.
Optionally, the obtaining a model of the gradient of each position point of the insulator region includes:
acquiring position information of each position point according to the image of the insulator surface camera;
acquiring an integral difference value between the maximum value and the minimum value of the integral value of each position point according to the image of the insulator surface camera;
obtaining a position-integral difference value two-dimensional space of each position point according to the position information and the integral difference value;
and solving the mode of the gradient of each position point according to the position-integral difference value two-dimensional space.
Optionally, the first preset threshold is used to represent a critical value of the degree of the integral unevenness of the surface of the insulator.
Optionally, the second preset threshold is used to represent a critical value of the non-uniformity degree of each position point of the insulator.
Optionally, the third preset threshold is used to represent a critical value of the number of uneven filth points.
Optionally, before the extracting the characteristic wavelength band and the insulator region according to the insulator surface spectral line diagram and the insulator surface camera image, the method further includes:
preprocessing the insulator surface spectral line graph and the insulator surface camera image.
Optionally, the preprocessing the insulator surface spectral line map and the insulator surface camera image includes:
the pretreatment of the insulator surface spectral line graph comprises the following steps: black and white correction, smoothing, derivation, normalization, multivariate scattering correction, elimination of noise data and influence of illumination on reflectivity;
the remaining of the insulator surface camera image comprises: image graying, image enhancement, image segmentation and noise and background removal.
Compared with the prior art, the beneficial effect of this application is:
according to the technical scheme, the insulator surface contamination distribution characteristic detection method based on the hyperspectral technology obtains a hyperspectral image of a measured natural contamination insulator, then carries out denoising and image enhancement on the obtained hyperspectral image, removes noise and background, identifies an insulator part, and takes high spectral lines at various positions on the surface of the insulator for preprocessing; carrying out effective information screening on the hyperspectral spectral line to obtain a characteristic waveband; obtaining the spectral line integral value of each position point by integrating the spectral lines of the characteristic wave band to calculate the area; obtaining integral difference values and integral minimum values of the whole according to the integral difference values and the integral minimum values, and judging whether the whole pollution condition on the surface of the insulator is uneven or not; then, the integral difference value of each position point and the gradient of the difference value in a position-integral difference value space are obtained; judging whether the pollution distribution near the point is uneven or not; judging the uneven distribution degree of the integral contamination of the insulator by recording the number of the judged uneven points, and marking the insulator to be cleaned; the problem of traditional high spectrum build storehouse detection insulator surface filth distribution, the sample demand is high and cover limitedly, and popularization nature is poor, receives shooting condition to influence greatly etc is overcome, for insulator surface filth distribute inhomogeneous arouse surface electric field distortion, arouse the threat of flashover danger probability increase in bad weather to provide the washing suggestion, improve transmission line's security.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting contamination distribution characteristics on the surface of an insulator based on a hyperspectral technology according to an embodiment of the application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the 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 application.
Referring to the attached drawing 1, fig. 1 shows a schematic flow chart of a method for detecting contamination distribution characteristics on the surface of an insulator based on a hyperspectral technology according to an embodiment of the application. The following describes a method for detecting the distribution characteristics of contamination on the surface of an insulator based on a hyperspectral technology, provided by an embodiment of the application, with reference to fig. 1.
The application provides a method for detecting the distribution characteristics of dirt on the surface of an insulator based on a hyperspectral technology, which comprises the following steps:
s110: and acquiring a hyperspectral image of the surface of the insulator to be detected, wherein the hyperspectral image of the surface of the insulator comprises an insulator surface spectrum line graph and an insulator surface camera image.
The acquisition mode of hyperspectral image adopts unmanned aerial vehicle remote sensing to shoot, and shooting angle mainly selects to bow to shoot and pitch to shoot, also can adjust according to engineering actual conditions. The hyperspectral technology is a three-dimensional information technology integrating maps, and qualitatively and quantitatively identifies substances by processing and analyzing spectral information. Any substance can emit, absorb and reflect electromagnetic radiation, and different substances can generate difference on the action of electromagnetic waves due to own chemical and physical properties, so that different substances are classified and identified according to the characteristics. The hyperspectral image is divided into two parts, including an insulator surface spectrum line graph and an insulator surface camera image. Firstly, a hyperspectral image of the surface contamination of the natural contamination-accumulating insulator is acquired, and the content of the contamination can be detected through the difference between spectral lines because different contamination layer contents can absorb and reflect the spectral lines in different degrees.
S120: and respectively extracting a characteristic wave band and an insulator region according to the insulator surface spectral line graph and the insulator surface camera image.
The method comprises the following steps of preprocessing a hyperspectral image before extracting a characteristic wave band and an insulator region, and specifically comprises the following steps: preprocessing the acquired hyperspectral image, including image graying, image enhancement and image segmentation, so as to achieve the purposes of removing noise and background and identifying effective information of an insulator part; the method comprises the following steps of taking high spectral lines of all position points on the surface of an insulator, preprocessing spectral line data, including black-and-white correction, smoothing, derivation, normalization and multivariate scattering correction, and eliminating the influence of noise data and illumination on reflectivity; and (3) performing dimensionality reduction on the processed hyperspectral spectral lines, selecting a principal component analysis method, and acquiring an interested area of the hyperspectral spectral lines, wherein the interested area is a characteristic waveband of the hyperspectral spectral lines and aims to remove the waveband of excessive noise information or non-important information, reduce the calculated amount and improve the calculation efficiency.
S130: and acquiring an integral difference value between the maximum value and the minimum value of the integral value of the characteristic wave band.
The method specifically comprises the following steps: and acquiring an integral value of the characteristic spectral line, performing programming calculation by adopting MATLAB, and solving the area of the integral aiming at acquiring the whole information of the full waveband. Because the difference of the pollution components on the same insulator is small, the spectral line difference mainly lies in the amplitude, and the shape information can be eliminated through integration so as to simplify the data.
S140: and judging the size of the integral difference value and a first preset threshold value.
S150: and if the integral difference value is larger than the first preset threshold value, judging that the whole contamination on the surface of the insulator is not uniform.
And taking the maximum and minimum values of all the integral values to calculate the difference, comparing the difference value with a first preset threshold value, if the difference value is lower than the first preset threshold value, the whole is uniform, not performing the next step, and if the difference value exceeds the first preset threshold value, performing the next step.
S160: and acquiring a mode of the gradient of each position point of the insulator region.
In the above step, insulators with uneven surface contamination have been screened, and then, the position points of the insulators with uneven surface contamination need to be screened, and the specific method includes: acquiring position information of each position point according to the image of the insulator surface camera;
acquiring an integral difference value between the maximum value and the minimum value of the integral value of each position point according to the image of the insulator surface camera;
obtaining a position-integral difference value two-dimensional space of each position point according to the position information and the integral difference value;
and solving the mode of the gradient of each position point according to the position-integral difference value two-dimensional space.
S170: and judging the modulus of the gradient of the position point and the size of a second preset threshold value.
S180: and if the modulus of the gradient of the position points is greater than the second preset threshold value, judging that the position points are unevenly distributed with filth, and marking as the uneven filth points.
The method specifically comprises the following steps: the obtained gradient represents the direction and value of each position point with the highest pollution quantity change, and the non-uniform degree of the pollution of the position point and the adjacent points can be reflected;
comparing the modulus of the gradient of each point with a second preset threshold value, wherein the more exceeding indicates that the pollution degree is more uneven; the second preset threshold value represents the degree of change of the pollution amount, namely the judgment value of the distribution unevenness, and the position points with the changed pollution amount too fast, namely the position points of the insulators with uneven pollution, are screened.
S190: and judging the number of the uneven points of the filth and the size of a third preset threshold value.
S200: and if the number of the uneven points of the contamination is larger than the third preset threshold value, judging that the insulator is the insulator needing to be cleaned.
Recording the number of points exceeding the second preset threshold value, comparing the number of points exceeding the third preset threshold value, and marking the points exceeding the third preset threshold value as insulators needing to be cleaned; further, the third preset threshold value represents a determination value of how many uneven positions are located on the entire surface of the insulator, and the more uneven areas, the higher the possibility that the insulator surface will be subjected to contamination flashover in severe weather.
In addition, in order to observe the distribution characteristics of dirt on the surface of the insulator more intuitively, the method further comprises the following steps:
acquiring position information of each position point according to the image of the insulator surface camera;
specifying a color function for each position point based on an integrated difference between a maximum value and a minimum value of the integrated value for each position point;
and assigning the color function of each position point to the position information of each position point to obtain a visual pollution uneven content distribution diagram.
Acquiring a hyperspectral camera image to acquire position information of each position point, associating the integral difference value of each point with a preset chromatographic chart, and expressing different uneven pollution contents by different colors;
furthermore, the setting of the chromatographic chart is set by an experienced field engineer according to the field condition, the bottom of the chromatographic card represents the minimum value of the local pollution amount, the top represents the maximum value of the local accumulated pollution amount of the pollution, and the corresponding color function can be formulated according to the requirement;
assigning the color function of each position point to a corresponding position to obtain a visual distribution map of the uneven content of the pollutants;
furthermore, the distribution characteristics of the dirt on the surface of the insulator can be observed according to the change of the color in the distribution diagram, and visual criteria can be provided for manual identification.
In summary, according to the technical scheme provided by the embodiment of the application, firstly, a hyperspectral image of a natural fouling insulator to be detected is acquired, wherein the hyperspectral image of the natural fouling insulator comprises a natural fouling insulator spectral line graph and an insulator optical camera image; the acquisition mode adopts unmanned aerial vehicle remote sensing shooting, the shooting angle mainly selects a downward shooting and an upward shooting, and the adjustment can be carried out according to the actual engineering condition; preprocessing the acquired hyperspectral image, including image graying, image enhancement and image segmentation, so as to achieve the purposes of removing noise and background and identifying effective information of an insulator part; the method comprises the following steps of taking high spectral lines of all position points on the surface of an insulator, preprocessing spectral line data, including black-and-white correction, smoothing, derivation, normalization and multivariate scattering correction, and eliminating the influence of noise data and illumination on reflectivity; taking the processed hyperspectral spectral lines for dimensionality reduction, selecting a principal component analysis method, and obtaining an interested area of the hyperspectral spectral lines as a characteristic wave band of the hyperspectral spectral lines, aiming at removing wave bands with excessive noise information or non-important information and reducing the calculated amount and improving the calculation efficiency; integrating the characteristic wave band spectral lines to obtain the area, and obtaining the spectral line integral value of each position point, wherein the process can be realized by MATLAB programming and aims to obtain the whole information of the full wave band; taking the maximum and minimum values of all the integral values to calculate difference, comparing the difference value with a first preset threshold value, if the difference value is lower than the preset threshold value, the whole is uniform, the next step is not carried out, and if the difference value exceeds the threshold value, the next step is carried out; the first preset threshold value represents a judgment value of the overall uneven degree of the filth and is set by actual engineering personnel according to the local environment condition; calculating the difference between the integral value and the minimum value of each position point to obtain the integral difference value of each position point, recording the integral difference value of each position point in a position-integral difference value space, and obtaining the mode of the gradient of each position point; the obtained gradient represents the direction and value of each position point with the highest pollution quantity change, and the non-uniform degree of the pollution of the position point and the adjacent points can be reflected; comparing the modulus of the gradient of each point with a second preset threshold value, wherein the more exceeding indicates that the pollution degree is more uneven; the second preset threshold value represents the degree of change of the pollution amount, namely a judgment value of distribution unevenness, and a position point with the rapid change of the pollution amount is screened out; recording the number of points exceeding the second preset threshold value, comparing the number of points exceeding the third preset threshold value, and marking the points exceeding the third preset threshold value as insulators needing to be cleaned; the third preset threshold value represents a judgment value of the number of uneven positions of the whole surface of the insulator, and the more uneven areas, the higher the possibility that the surface of the insulator is polluted in severe weather.
Acquiring a hyperspectral camera image to acquire position information of each position point, associating the integral difference value of each point with a preset chromatographic chart, and expressing different uneven pollution contents by different colors; the setting of the chromatographic chart is set by an experienced field engineer according to the field condition, the bottom of the chromatographic card represents the minimum value of the local pollution amount, the top represents the maximum value of the local accumulated pollution amount, and the corresponding color function can be formulated according to the requirement; assigning the color function of each position point to a corresponding position to obtain a visual distribution map of the uneven content of the pollutants; the distribution characteristics of the dirt on the surface of the insulator can be observed according to the change of the color in the distribution diagram, and visual criteria can be provided for manual identification.
According to the technical scheme, firstly, a hyperspectral image of a measured natural fouling insulator is obtained, then denoising and image enhancement are carried out on the obtained hyperspectral image, noise and background are removed, insulator parts are identified, high spectral lines of all positions on the surface of the insulator are taken, and preprocessing is carried out; carrying out effective information screening on the hyperspectral spectral line to obtain a characteristic waveband; obtaining the spectral line integral value of each position point by integrating the spectral lines of the characteristic wave band to calculate the area; obtaining integral difference values and integral minimum values of the whole according to the integral difference values and the integral minimum values, and judging whether the whole pollution condition on the surface of the insulator is uneven or not; then, the integral difference value of each position point and the gradient of the difference value in a position-integral difference value space are obtained; judging whether the pollution distribution near the point is uneven or not; judging the uneven distribution degree of the integral contamination of the insulator by recording the number of the judged uneven points, and marking the insulator to be cleaned; acquiring position information of each position point by combining with the acquired hyperspectral camera image, associating the integral difference value of each point with a preset chromatographic chart, assigning the color function of each position point to the corresponding position, and acquiring a visual pollution uneven content distribution map; therefore, the visual criterion is provided for manual identification, the problems that the traditional hyperspectral warehouse building is used for detecting the surface contamination distribution of the insulator, the sample is high in demand and limited in coverage, poor in popularization, and greatly influenced by shooting conditions are solved, the surface electric field distortion is caused by the uneven surface contamination distribution of the insulator, the threat of flashover hazard probability increase caused by severe weather is provided with a cleaning prompt, and the safety of the power transmission line is improved.
Since the above embodiments are all described by referring to and combining with other embodiments, the same portions are provided between different embodiments, and the same and similar portions between the various embodiments in this specification may be referred to each other. And will not be described in detail herein.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
The above-described embodiments of the present application do not limit the scope of the present application.
Claims (8)
1. A method for detecting the distribution characteristics of dirt on the surface of an insulator based on a hyperspectral technology is characterized by comprising the following steps:
acquiring a hyperspectral image of the surface of an insulator to be measured, wherein the hyperspectral image of the surface of the insulator comprises an insulator surface spectrum line graph and an insulator surface camera image;
respectively extracting a characteristic wave band and an insulator region according to the insulator surface spectral line graph and the insulator surface camera image;
acquiring an integral difference value between the maximum value and the minimum value of the integral value of the characteristic wave band;
judging whether the integral difference value is larger than a first preset threshold value or not;
if the integral difference value is larger than the first preset threshold value, judging that the integral contamination on the surface of the insulator is not uniform;
acquiring a mode of gradient of each position point of the insulator region;
judging whether the modulus of the gradient of the position point is greater than a second preset threshold value or not;
if the modulus of the gradient of the position points is larger than the second preset threshold value, judging that the position points are unevenly distributed with filth, and marking as uneven filth points;
judging whether the number of the uneven points of the dirt is larger than a third preset threshold value or not;
and if the number of the uneven points of the contamination is larger than the third preset threshold value, judging that the insulator is the insulator needing to be cleaned.
2. The insulator surface contamination distribution characteristic detection method based on the hyperspectral technology according to claim 1, characterized by further comprising:
acquiring position information of each position point according to the image of the insulator surface camera;
specifying a color function for each position point based on an integrated difference between a maximum value and a minimum value of the integrated value for each position point;
and assigning the color function of each position point to the position information of each position point to obtain a visual pollution uneven content distribution diagram.
3. The method for detecting the contamination distribution characteristics on the surface of the insulator based on the hyperspectral technology according to claim 1 is characterized in that the obtaining of the modulus of the gradient of each position point in the insulator area comprises the following steps:
acquiring position information of each position point according to the image of the insulator surface camera;
acquiring an integral difference value between the maximum value and the minimum value of the integral value of each position point according to the image of the insulator surface camera;
obtaining a position-integral difference value two-dimensional space of each position point according to the position information and the integral difference value;
and solving the mode of the gradient of each position point according to the position-integral difference value two-dimensional space.
4. The insulator surface contamination distribution characteristic detection method based on the hyperspectral technology as claimed in claim 1, wherein the first preset threshold is a critical value used for representing the integral non-uniformity degree of the insulator surface.
5. The insulator surface contamination distribution characteristic detection method based on the hyperspectral technology as claimed in claim 1, wherein the second preset threshold is a critical value used for representing the degree of non-uniformity of each position point of the insulator.
6. The insulator surface contamination distribution characteristic detection method based on the hyperspectral technology as claimed in claim 1, wherein the third preset threshold is a critical value used for representing the number of uneven contamination.
7. The insulator surface contamination distribution characteristic detection method based on the hyperspectral technology according to claim 1, wherein before extracting a characteristic band and an insulator region according to the insulator surface spectral line graph and the insulator surface camera image respectively, the method further comprises:
preprocessing the insulator surface spectral line graph and the insulator surface camera image.
8. The insulator surface contamination distribution characteristic detection method based on the hyperspectral technology according to claim 7, wherein the preprocessing the insulator surface spectral line graph and the insulator surface camera image comprises:
the pretreatment of the insulator surface spectral line graph comprises the following steps: black and white correction, smoothing, derivation, normalization, multivariate scattering correction, elimination of noise data and influence of illumination on reflectivity;
the remaining of the insulator surface camera image comprises: image graying, image enhancement, image segmentation and noise and background removal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911025950.9A CN110632092B (en) | 2019-10-25 | 2019-10-25 | Method for detecting distribution characteristics of dirt on surface of insulator based on hyperspectral technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911025950.9A CN110632092B (en) | 2019-10-25 | 2019-10-25 | Method for detecting distribution characteristics of dirt on surface of insulator based on hyperspectral technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110632092A true CN110632092A (en) | 2019-12-31 |
| CN110632092B CN110632092B (en) | 2022-05-20 |
Family
ID=68977833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911025950.9A Active CN110632092B (en) | 2019-10-25 | 2019-10-25 | Method for detecting distribution characteristics of dirt on surface of insulator based on hyperspectral technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110632092B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112924333A (en) * | 2021-01-27 | 2021-06-08 | 云南电网有限责任公司电力科学研究院 | Multi-purpose device for hydrophobicity detection and hyperspectral image shooting of composite insulator |
| CN113295700A (en) * | 2021-05-11 | 2021-08-24 | 国网安徽省电力有限公司信息通信分公司 | Transmission line external insulation state monitoring method and system based on Internet of things |
| CN113588714A (en) * | 2021-08-26 | 2021-11-02 | 国网四川省电力公司成都供电公司 | Composite insulator defect detection method |
| CN113655072A (en) * | 2021-08-20 | 2021-11-16 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a surface of a sample |
| CN114167234A (en) * | 2021-11-29 | 2022-03-11 | 海南电网有限责任公司电力科学研究院 | Insulator aging detection method based on hyperspectrum of unmanned aerial vehicle |
| CN115631466A (en) * | 2022-12-22 | 2023-01-20 | 国网浙江省电力有限公司宁波供电公司 | Identification detection method and system for overhead transmission line |
| CN116068287A (en) * | 2023-03-10 | 2023-05-05 | 国网山西省电力公司电力科学研究院 | Method and device for measuring potential of polluted insulator |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02262039A (en) * | 1989-03-31 | 1990-10-24 | Ngk Insulators Ltd | Apparatus and method for measuring contamination of insulator |
| JP2003145548A (en) * | 2001-11-16 | 2003-05-20 | Towa Corp | Method and device for cleaning resin molding die |
| CN101739549A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Face detection method and system |
| CN103411980A (en) * | 2013-07-23 | 2013-11-27 | 同济大学 | External insulation filth status identification method based on visible-light images |
| US20150213364A1 (en) * | 2014-01-28 | 2015-07-30 | International Business Machines Corporation | Predicting pollution formation on insulator structures of power grids |
| CN108072667A (en) * | 2017-09-28 | 2018-05-25 | 江苏省电力试验研究院有限公司 | Insulator contamination level detection method and system based on EO-1 hyperion |
| CN109632655A (en) * | 2019-01-25 | 2019-04-16 | 西南交通大学 | A kind of pollution severity of insulators grade visible detection method based on TuPu method |
| CN109799245A (en) * | 2019-03-29 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | A kind of insulator contamination degree non-contact detection method and device |
| CN109799244A (en) * | 2019-03-29 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | A kind of direct current system pollution severity of insulators condition detection method and detection system |
| CN110222683A (en) * | 2019-06-11 | 2019-09-10 | 云南电网有限责任公司曲靖供电局 | A kind of quick-fried defect recognition localization method of electric transmission line isolator component based on depth convolutional neural networks |
| CN110261405A (en) * | 2019-07-31 | 2019-09-20 | 西南交通大学 | Insulator contamination ingredient recognition methods based on micro- hyperspectral technique |
-
2019
- 2019-10-25 CN CN201911025950.9A patent/CN110632092B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02262039A (en) * | 1989-03-31 | 1990-10-24 | Ngk Insulators Ltd | Apparatus and method for measuring contamination of insulator |
| JP2003145548A (en) * | 2001-11-16 | 2003-05-20 | Towa Corp | Method and device for cleaning resin molding die |
| CN101739549A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Face detection method and system |
| CN103411980A (en) * | 2013-07-23 | 2013-11-27 | 同济大学 | External insulation filth status identification method based on visible-light images |
| US20150213364A1 (en) * | 2014-01-28 | 2015-07-30 | International Business Machines Corporation | Predicting pollution formation on insulator structures of power grids |
| CN108072667A (en) * | 2017-09-28 | 2018-05-25 | 江苏省电力试验研究院有限公司 | Insulator contamination level detection method and system based on EO-1 hyperion |
| CN109632655A (en) * | 2019-01-25 | 2019-04-16 | 西南交通大学 | A kind of pollution severity of insulators grade visible detection method based on TuPu method |
| CN109799245A (en) * | 2019-03-29 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | A kind of insulator contamination degree non-contact detection method and device |
| CN109799244A (en) * | 2019-03-29 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | A kind of direct current system pollution severity of insulators condition detection method and detection system |
| CN110222683A (en) * | 2019-06-11 | 2019-09-10 | 云南电网有限责任公司曲靖供电局 | A kind of quick-fried defect recognition localization method of electric transmission line isolator component based on depth convolutional neural networks |
| CN110261405A (en) * | 2019-07-31 | 2019-09-20 | 西南交通大学 | Insulator contamination ingredient recognition methods based on micro- hyperspectral technique |
Non-Patent Citations (3)
| Title |
|---|
| YAN QIU ET AL.: "An Extreme-Learning-Machine-Based Hyperspectral Detection Method of Insulator Pollution Degree", 《IEEE ACCESS》 * |
| 李恒超等: "基于高光谱成像技术的绝缘子污秽度预测", 《西南交通大学学报》 * |
| 田治仁等: "基于彩色可见光图像的绝缘子污秽等级判别", 《电工电能新技术》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112924333A (en) * | 2021-01-27 | 2021-06-08 | 云南电网有限责任公司电力科学研究院 | Multi-purpose device for hydrophobicity detection and hyperspectral image shooting of composite insulator |
| CN113295700A (en) * | 2021-05-11 | 2021-08-24 | 国网安徽省电力有限公司信息通信分公司 | Transmission line external insulation state monitoring method and system based on Internet of things |
| CN113655072A (en) * | 2021-08-20 | 2021-11-16 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a surface of a sample |
| CN113655072B (en) * | 2021-08-20 | 2023-12-26 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a sample surface |
| CN113588714A (en) * | 2021-08-26 | 2021-11-02 | 国网四川省电力公司成都供电公司 | Composite insulator defect detection method |
| CN114167234A (en) * | 2021-11-29 | 2022-03-11 | 海南电网有限责任公司电力科学研究院 | Insulator aging detection method based on hyperspectrum of unmanned aerial vehicle |
| CN114167234B (en) * | 2021-11-29 | 2024-05-28 | 海南电网有限责任公司电力科学研究院 | Insulator aging detection method based on hyperspectrum of unmanned aerial vehicle |
| CN115631466A (en) * | 2022-12-22 | 2023-01-20 | 国网浙江省电力有限公司宁波供电公司 | Identification detection method and system for overhead transmission line |
| CN116068287A (en) * | 2023-03-10 | 2023-05-05 | 国网山西省电力公司电力科学研究院 | Method and device for measuring potential of polluted insulator |
| CN116068287B (en) * | 2023-03-10 | 2023-06-13 | 国网山西省电力公司电力科学研究院 | Method and device for measuring potential of polluted insulator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110632092B (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110632092B (en) | Method for detecting distribution characteristics of dirt on surface of insulator based on hyperspectral technology | |
| CN111179334B (en) | Sea surface small-area oil spill area detection system and detection method based on multi-sensor fusion | |
| CN110268190B (en) | Underground pipe gallery leakage detection method based on static infrared thermography processing | |
| CN106683075B (en) | Method for detecting bolt defects at cross arm of power transmission line tower | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN106296670B (en) | A kind of Edge detection of infrared image based on the watershed Retinex--Canny operator | |
| CN110261405B (en) | Insulator pollution component identification method based on microscopic hyperspectral technology | |
| CN108489996B (en) | Insulator defect detection method and system and terminal equipment | |
| CN110376214B (en) | Insulator pollution degree non-contact detection method based on hyperspectral technology | |
| CN110660065B (en) | Infrared fault detection and identification algorithm | |
| CN112365475A (en) | Power transmission line icing monitoring method and system based on image processing mode | |
| CN112414950A (en) | Insulator equivalent salt deposit density detection method cooperating with hyperspectral and infrared technologies | |
| WO2019184269A1 (en) | Landsat 8 snow-containing image-based cloud detection method | |
| CN111008967B (en) | Insulator RTV coating defect identification method | |
| CN116958036A (en) | Method for inspecting pollution state of insulator by unmanned aerial vehicle based on hyperspectral technology | |
| CN112465708A (en) | Improved image defogging method based on dark channel | |
| CN115753809A (en) | Insulator contamination detection method, device, equipment and storage medium | |
| CN110533626B (en) | All-weather water quality identification method | |
| CN110363749B (en) | Evaluation method for rusting degree of vibration damper based on image processing | |
| CN115984255A (en) | Defect identification method of online energy-taking movable intelligent vibration damper | |
| CN111353968B (en) | Infrared image quality evaluation method based on blind pixel detection and analysis | |
| CN110658208A (en) | Hyperspectrum-based transformer substation insulator dirt accumulation online monitoring system | |
| CN108198178B (en) | Method and device for determining atmospheric range radiation value | |
| CN116758056B (en) | Electrical terminal production defect detection method | |
| CN115830027B (en) | Machine vision-based automobile wire harness cladding defect detection method |
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 |