CN106680285B - Method for recognizing insulator contamination state based on infrared image assisted visible light image - Google Patents
Method for recognizing insulator contamination state based on infrared image assisted visible light image Download PDFInfo
- Publication number
- CN106680285B CN106680285B CN201611027566.9A CN201611027566A CN106680285B CN 106680285 B CN106680285 B CN 106680285B CN 201611027566 A CN201611027566 A CN 201611027566A CN 106680285 B CN106680285 B CN 106680285B
- Authority
- CN
- China
- Prior art keywords
- visible light
- insulator
- light image
- image
- pollution
- 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
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- 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)
- Image Processing (AREA)
Abstract
The invention relates to a visible light image recognition insulator contamination state method based on infrared image assistance, which comprises the following steps: collecting an insulator visible light image, and performing insulator visible light image processing and visible light characteristic value extraction; acquiring an insulator infrared image, and performing insulator infrared image processing and infrared characteristic value extraction; establishing a visible light image-based pollution grade identification mathematical model and a visible light image pollution state identification mathematical model based on infrared image information assistance; and selecting a corresponding mathematical model according to the relative humidity of the environment to obtain the pollution level of the insulator. Compared with the prior art, the method has the advantages of removing the influence of ambient illumination, considering the influence of high relative humidity environment on a visible light method, being simple and universal in mathematical model and the like.
Description
Technical Field
The invention relates to a method for identifying the pollution state of an insulator, in particular to a method for identifying the pollution state of the insulator based on a visible light image assisted by an infrared image.
Background
The insulator occupies an important position in a power transmission and distribution network, and various particles such as dust, saline-alkali, industrial smoke dust and the like in the air or bird dung are accumulated on the outer surface of the insulator to form a dirty layer, so that the insulating strength of the insulator is reduced, pollution flashover is easy to occur, and great economic loss is caused. If can convenient, safe, accurately survey filthy degree to formulate reasonable cleaning plan according to this, can prevent and treat the pollution flashover more effectively, strengthen the electric wire netting steady operation, reduce the economic loss that the pollution flashover brought.
In order to accurately determine the cleaning or washing period of the insulator, the methods for detecting the pollution quantity value of the insulator adopted at home and abroad at present mainly comprise an equivalent salt deposit density method and a leakage current method. The equivalent salt deposit density method is used for determining the salt density of a power transmission line after power failure and washing, and the real condition of an insulator in operation is difficult to reflect. The leakage current method is used for detecting the pollution degree of the insulator by detecting the change of the current flowing through the surface of the insulator under the action of the operating voltage. Although the leakage current method can reflect a more serious insulation fault, the time for operators to process after judging the insulation failure is limited, the method is difficult to be widely applied, a set of detection device is required to be installed on each insulator string, the cost is overhigh, and the maintenance and the overhaul of the device need to be carried out by power failure.
In contrast, the image-based insulator pollution state detection method has the advantages of low cost, no need of disassembly, no need of power failure, no need of installation of a complex device, low possibility of electromagnetic interference, long-distance non-contact measurement and the like, and comprises a visible light image method, an infrared image method and an ultraviolet image method. The temperature information of the infrared image and the discharge light spot information of the ultraviolet image are sufficiently obvious only in the discharge process under the environment with high relative humidity, and no obvious characteristics exist at ordinary times, so that the two methods have considerable limitations, but the temperature information is more stable and easier to capture than the discharge information, and the price of the thermal infrared imager is generally lower than that of the ultraviolet imager. The visible light image method can reflect the amount of the accumulated dirt of the insulator according to the color characteristics of the surface of the insulator, the acquisition of the accumulated dirt information does not require the insulator to discharge, if the difficulty of environmental illumination influence (color temperature, illumination and the like) can be overcome, a proper visible light characteristic value is selected, the corresponding relation between the characteristic value and the accumulated dirt amount is found, and the grade of the dirt of the insulator can be identified through the visible light image. And the dirt is diluted after being affected with damp under high relative humidity, the color characteristics of the dirt are changed, the dirt grade identification accuracy is reduced, and therefore other information is applied to assist the visible light method when the relative humidity is high.
In recent years, most insulator pollution level identification methods are based on artificial intelligence methods, such as artificial neural networks, support vector machines and the like, but therefore, a large number of insulator samples need to be collected in advance, and the pollution levels of the samples are measured by methods of cleaning insulator disc surfaces and the like, so that a model can be trained to high precision. If a simple and universal mathematical model can be established by utilizing the characteristic that the surface color characteristic and the temperature characteristic of the polluted insulator gradually change along with different pollution accumulation amounts, the acquisition and the measurement of a large number of training samples can be omitted, and the field practicability of the insulator pollution grade identification method is practically improved.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a visible light image recognition insulator pollution state method based on infrared image assistance, which can eliminate the influence of environmental illumination, quickly establish a simple and universal insulator pollution grade recognition model by considering the relative humidity of the environment, accurately and reliably analyze the pollution states of a large number of insulators in current operation, provide a basis for timely cleaning the insulator pollution and reduce the insulator pollution flashover power failure accidents.
The purpose of the invention can be realized by the following technical scheme:
a visible light image recognition insulator contamination state method based on infrared image assistance comprises the following steps:
step S1, collecting a visible light image of the insulator;
step S2, processing the visible light image of the insulator and extracting the characteristic value of the visible light;
step S3, acquiring an insulator infrared image;
step S4, insulator infrared image processing and infrared characteristic value extraction;
step S5, establishing a visible light image-based pollution grade identification mathematical model and a visible light image pollution state identification mathematical model assisted by infrared image information;
and step S6, selecting the corresponding mathematical model in the step S5 according to the relative humidity of the environment, substituting the mathematical model into the data in the step S2 and the data in the step S4, and obtaining the pollution level of the insulator.
In the step S1, the insulator visible light image is collected, and the influence of ambient light needs to be removed in advance, and the specific operations are as follows:
before the visible light image is obtained, the color temperature of the camera is corrected by using the white card, the influence of the color temperature of the ambient light is reduced, and the influence of the illumination of the ambient light is reduced by using the exposure correction of the camera by using the gray card.
The specific operations of processing the visible light image of the insulator and extracting the visible light characteristic value in the step S2 include:
converting the visible light image of the insulator into a gray scale image; extracting the insulator disc surface area from the gray level image by a seed area growing method, and obtaining a corresponding visible light image disc surface area; extracting a U component mean value and a V component mean value of a visible light image disc surface area in a YUV color space; and comparing the absolute value of the difference between the U component mean values of the disc surface colors of the 0-level and IV-level pollution insulators and the absolute value of the difference between the V component mean values of the disc surface colors of the 0-level and IV-level pollution insulators, and selecting the component corresponding to the larger absolute value as the final characteristic value.
The specific operations of insulator infrared image processing and infrared characteristic value extraction in the step S4 include: converting the infrared image into a gray image by using the temperature value of each pixel as a gray value; extracting the insulator disc surface area from the gray level image by using a maximum inter-class variance method, and obtaining a corresponding infrared image disc surface area; extracting maximum temperature rise T of infrared image disk surface areamaxAs an infrared image feature value.
In step S6, the mathematical model method applied according to the environmental relative humidity is determined as follows: when the relative humidity RH of the environment is less than 60%, calculating an equivalent salt deposit density value by using a pollution grade recognition mathematical model based on the visible light image; when the relative humidity RH of the environment is more than or equal to 60%, the characteristic value of the infrared image is required to be subjected to auxiliary identification, the weight of visible light image information and infrared image information is determined according to the relative humidity RH of the environment, and an equivalent salt deposit density value is calculated by utilizing a visible light image pollution state identification mathematical model based on the assistance of the infrared image information; and judging the pollution grade of the insulator according to the obtained equivalent salt deposit density value.
The pollution grade identification mathematical model based on the visible light image is as follows:
wherein, ESDD: equivalent salt deposit density value;
v: the average value of the V components of the characteristic value of the visible light image of the dirty insulator to be identified;
V1: the average value of the V components of the visible light image characteristic value of the IV-level pollution insulator;
V0: the average value of the V components of the visible light image characteristic values of the 0-level pollution insulators;
RH: ambient relative humidity.
The visible light image pollution state identification mathematical model based on the assistance of infrared image information is as follows:
wherein, ESDD: equivalent salt deposit density value;
v: the average value of the V components of the characteristic value of the visible light image of the dirty insulator to be identified;
V1: the average value of the V components of the visible light image characteristic value of the IV-level pollution insulator;
V0: the average value of the V components of the visible light image characteristic values of the 0-level pollution insulators;
Tmax: the maximum temperature rise value of the infrared image disc surface area of the pollution insulator to be identified;
RH: ambient relative humidity.
Compared with the prior art, the invention has the following advantages:
1) the influence on color temperature and illumination intensity in the acquisition process of the visible light image of the insulator is primarily removed; the visible light characteristic U component (or V component) is used as the difference between the B component (or R component) and the brightness signal Y in the RGB color space, the brightness information difference in the image is further removed by a mathematical method, and finally the influence on the environmental illumination is removed, so that the accuracy and the efficiency of the pollution grade identification are improved;
2) the influence of a high relative humidity environment on a visible light method is considered, infrared information is adopted to assist the visible light method, and accurate identification of the pollution levels of the insulators under different relative humidity is achieved;
3) the characteristics that the surface color characteristic and the temperature characteristic of the insulator are gradually changed along with different accumulated dirt amount are utilized to establish a simple and universal mathematical model, so that the collection and the measurement of a large number of training samples are avoided, and the field practicability of the insulator dirt grade identification method is practically improved;
4) the tower detection device has the advantages of no need of installing any equipment on the tower, low operation and maintenance cost, simple operation, safe and reliable use and high detection precision.
Drawings
Fig. 1 is a flowchart of an embodiment of a visible light image-based insulator contamination state identification method assisted by infrared image information according to the present invention;
FIG. 2 is a visible light image of an insulator captured in accordance with the present invention;
FIG. 3 is a graph of the processing result of the insulator visible light image collected in the present invention;
FIG. 4 is an insulator infrared image collected in the present invention;
fig. 5 is a diagram showing the processing result of the insulator infrared image collected in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Examples
The invention provides a visible light image recognition insulator pollution state method based on infrared image assistance, which can eliminate the influence of environmental illumination, quickly establish a simple and universal insulator pollution grade recognition model by considering the environmental relative humidity, accurately and reliably analyze the pollution states of a large number of insulators in current operation, provide a basis for timely cleaning the insulator pollution and reduce the insulator pollution flashover power failure accidents.
Referring to fig. 1, the invention provides a visible light image recognition insulator contamination state method based on infrared image assistance, comprising the following steps:
step 10, collecting an insulator visible light image;
specifically, collecting an insulator visible light image by using a digital camera;
in the specific implementation, before the visible light image is acquired, the color temperature of the camera needs to be corrected by using a white card so as to reduce the influence of the color temperature of the ambient light, and the exposure correction of the camera is performed by using a gray card so as to reduce the influence of the illumination of the ambient light. The gray card is used for correcting the exposure value, and the shutter speed is automatically adjusted by the camera after the aperture of the camera is fixed;
preferably, the shooting distance is 0.5-4 m, the depression angle is 15-45 degrees, and the shooting is performed in a direct light manner;
besides the visible light image of the insulator with the pollution grade to be detected, a 0-grade pollution insulator (ESDD) is also required to be collected<0.01mg/cm2) Visible light image and a IV-level pollution insulator (ESDD is more than or equal to 0.3 mg/cm)2) The visible light image is used for establishing a pollution grade identification mathematical model; if no IV-class pollution insulator exists on site, the pollutants on the disk surface of a plurality of pollution insulators can be swept down, and shooting is carried out after the pollutants are accumulated to a sufficient thickness, so that a color characteristic value close to the color characteristic of the disk surface of the IV-class pollution insulator is obtained.
Step 11, processing an insulator visible light image and extracting a visible light characteristic value;
firstly, converting a visible light image of the insulator into a gray scale image;
the seed region growing method is a graph segmentation algorithm for gradually expanding from seed points to adjacent pixels by a certain threshold value so as to segment regions with similar characteristics, uniformly selecting a plurality of disc surface seed points for a gray scale image obtained by converting an insulator visible light image, setting a threshold value epsilon (for example, epsilon is 15) for seed growth, extracting the insulator disc surface region in the gray scale image, and then obtaining the corresponding visible light image disc surface region. The collected visible light image of the insulator and the image processing result are shown in fig. 2 (fig. 2 is not a necessary diagram for the present invention) and fig. 3 (fig. 3 is not a necessary diagram for the present invention).
When the visible light image is collected in step 10, the difference of the illumination condition is reduced by the camera, but the color temperature, the aperture and the shutter are all regulated and controlled in an extreme manner, and certain deviation exists. The YUV color space is a color coding method adopted by european television systems, which includes a luminance component Y, chrominance components U and V, and the equation of Y, U, V for representing the YUV color space with R, G, B for the RGB color space is as follows:
Y＝0.299*R+0.587*G+0.114*B
U＝0.492*(B-Y)
V＝0.877*(R-Y)
as can be seen from the equation, the chrominance component U, V is B, R minus the luminance component Y, mathematically removing the effect of the luminance difference. The characteristic enables the U and V components to be more suitable for serving as the characteristic values of the insulator visible light image disc surface color under different illumination conditions in the characteristic components of various color spaces.
Because there is the difference in the insulator quotation color feature of different models and the filthy color feature at different scene, so in concrete the realization, need accept and give up in order to obtain better filthy grade discernment rate of accuracy to U weight and V weight, its essence is that the change of choosing insulator quotation to filthy color feature transition from original color feature after U weight and V weight is bigger: obtaining a 0-grade polluted insulator (ESDD)<0.01mg/cm2) The average value U of the characteristic value U components of the visible light image0And the mean value V of the V components0Obtaining a class IV filthy insulator (ESDD is more than or equal to 0.3 mg/cm)2) The average value U of the characteristic value U components of the visible light image1And the mean value V of the V components1(ii) a If U0-U1|>|V0-V1And if not, taking the variable V as the characteristic value of the final visible light image.
Step 12, collecting an insulator infrared image;
collecting an insulator infrared image by using an infrared thermal imager;
preferably, the recommended shooting distance is 0.5-4 m, the depression angle is 15-30 degrees, and the background complexity is preferably reduced as much as possible while all the insulating disk surfaces to be tested are obtained in actual shooting.
Step 13, insulator infrared image processing and infrared characteristic value extraction;
converting the infrared image into a gray image by using the temperature value of each pixel as a gray value;
extracting the insulator disc surface area from the gray level image by using a maximum inter-class variance method, and obtaining a corresponding infrared image disc surface area;
extracting maximum temperature rise T of infrared image disk surface areamaxAs an infrared image feature value.
The method comprises the following specific steps:
extracting the insulator disc surface area by using a maximum inter-class variance method for the gray level image, wherein the equation of the method is as follows:
σ2(T)＝WA(μA-μ)2+WB(μB-μ)2
in the formula, T is a segmentation threshold value of a target area A and a background area B, and the value range is 0-255; mu.sAAverage gray scale of the area A; wAThe number of pixels in the area A is the proportion of the image; mu.sBAverage gray scale of the region B; wBThe pixel number of the region B accounts for the proportion of the image; μ is the total average gray scale of the image; sigma2(T) is the variance of regions A and B. When T is taken to be sigma2And (T) when the difference between the area A and the area B is maximum, dividing the gray image by using the gray value as a threshold value to obtain a target area A, namely the insulator disc surface area, and finally obtaining the infrared image disc surface area corresponding to the gray image. The collected insulator infrared image and the image processing result are shown in fig. 4 (fig. 4 is not a necessary diagram for the present invention) and fig. 5 (fig. 5 is not a necessary diagram for the present invention).
Extracting maximum temperature rise T of infrared image disk surface areamaxAs an infrared image feature value.
Step 14, establishing a visible light image-based pollution grade identification mathematical model and a visible light image pollution state identification mathematical model based on infrared image information assistance;
in specific implementation, the application range of the pollution level identification mathematical model based on the visible light image is relative humidity RH<60 percent. Taking artificial diatomite-smeared reddish brown ceramic insulators with different pollution grades as an example, the V component is selected as the visible light characteristic in the step 11, and a 0-grade pollution insulation is obtainedSub-eigenvalue V0And a characteristic value V of a class IV filthy insulator1Then, the V-ESDD relationship can be listed:
V＝V1-(V1-V0)e-10·ESDD
the simplified ESDD-V relational expression is the pollution grade identification mathematical model based on the visible light image:
in the specific implementation, the application range of the visible light image pollution state identification mathematical model based on the infrared image information assistance is that the relative humidity RH is more than or equal to 60%. Taking artificial diatomite-smeared reddish brown ceramic insulators with different pollution grades as an example, the V component is selected as the visible light characteristic in the step 11, and a 0-grade pollution insulator characteristic value V is obtained0And a characteristic value V of a class IV filthy insulator1Later, considering the relative humidity RH, the relationship V-ESDD can be listed:
V＝[V1-(V1-V0)e-10·ESDD-V0]·e-0.3(RH-60％)/10％+V0
the simplified ESDD-V relational expression is the visible light part of the visible light image pollution state identification mathematical model based on the infrared image information assistance:
taking artificial diatomite-smeared reddish brown ceramic insulators with different pollution grades as an example, the infrared characteristic T is selected through the step 13maxAfter that, and taking into account the relative humidity RH, T can be listedmax-ESDD relation:
Tmax＝(12-12e-10·ESDD)·e0.3(RH-100％)/10％
the simplified ESDD-V relational expression is the infrared part of the visible light image pollution state identification mathematical model based on the infrared image information assistance:
and finally, performing weighted sum on the visible light part and the infrared part according to the relative humidity RH, wherein the higher the RH is, the lower the weight of the visible light part is, and the higher the weight of the infrared part is.
In conclusion, a visible light image-based pollution grade identification mathematical model and an infrared image information-assisted visible light image pollution state identification mathematical model are established according to the following formulas:
wherein, RH value needs to be read from a hygrometer, and each variable means:
ESDD: equivalent salt deposit density value;
v: the average value of the V components of the characteristic value of the visible light image of the dirty insulator to be identified;
V1: the average value of the V components of the visible light image characteristic value of the IV-level pollution insulator;
V0: the average value of the V components of the visible light image characteristic values of the 0-level pollution insulators;
Tmax: the maximum temperature rise value of the infrared image disc surface area of the pollution insulator to be identified;
RH: ambient relative humidity.
Step 15, solving the pollution grade of the insulator;
the pollution level identification mathematical model based on the visible light image and the pollution state identification mathematical model based on the visible light image assisted by the infrared image information substantially take the relative humidity RH of the environment as 60% as a boundary point: relative humidity of the environment RH<At 60%, ESDD is a function of V; when the relative humidity RH of the environment is more than or equal to 60 percent, the characteristic value of the infrared image is required to be subjected to auxiliary identification, and the ESDD is about V, TmaxAnd RH, and determining the weight of the visible light image information and the infrared image information according to the RH.
In concrete implementation, the mathematical model established in step 14 is substituted into the characteristic value V (RH) of the insulator sample to be tested<60%), or V, TmaxAnd RH (RH is more than or equal to 60 percent), and then the ESDD can be calculated, thereby obtaining the corresponding pollution grade.
According to the insulator contamination state identification method based on the infrared image information assisted visible light image, the insulator visible light image is collected, the visible light characteristic value is extracted through the image processing technology, a contamination level identification mathematical model based on the visible light image is established, the infrared image information assisted visible light image contamination state identification mathematical model is established, insulator contamination level identification is achieved, and a cleaning plan is formulated. The method eliminates the influence of illumination on visible light images, introduces infrared image information under high relative humidity for assistance, and realizes accurate identification of the pollution level of the insulator under complex environmental conditions; the characteristics that the surface color characteristic and the temperature characteristic of the insulator are gradually changed along with different accumulated dirt amount are utilized to establish a simple and universal mathematical model, so that the collection and the measurement of a large number of training samples are avoided, and the field practicability of the insulator dirt grade identification method is practically improved; any extra equipment does not need to be installed on the tower, power failure does not need to be avoided, manpower, material resources and financial resources are saved, and the tower is safe, economical and reliable.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (1)
1. A visible light image recognition insulator pollution state method based on infrared image assistance is characterized by comprising the following steps:
step S1, collecting the insulator visible light image, and removing the environmental illumination influence in advance, wherein the method specifically comprises the following steps:
before the visible light image is obtained, the white card is used for correcting the color temperature of the camera, so that the influence of the color temperature of the ambient light is reduced, and the gray card is used for correcting the exposure of the camera, so that the influence of the illumination of the ambient light is reduced;
step S2, the processing of the visible light image of the insulator and the extraction of the visible light characteristic value, the specific operations of the processing of the visible light image of the insulator and the extraction of the visible light characteristic value include:
converting the visible light image of the insulator into a gray scale image; extracting the insulator disc surface area from the gray level image by a seed area growing method, and obtaining a corresponding visible light image disc surface area; extracting a U component mean value and a V component mean value of a visible light image disc surface area in a YUV color space; comparing the absolute value of the difference between the U component mean values of the disc surfaces of the 0-level and IV-level pollution insulators and the absolute value of the difference between the V component mean values of the disc surfaces of the 0-level and IV-level pollution insulators, and selecting the component corresponding to the larger absolute value as the final characteristic value;
step S3, acquiring an insulator infrared image;
step S4, insulator infrared image processing and infrared characteristic value extraction, wherein the specific operations of insulator infrared image processing and infrared characteristic value extraction comprise: converting the infrared image into a gray image by using the temperature value of each pixel as a gray value; extracting the insulator disc surface area from the gray level image by using a maximum inter-class variance method, and obtaining a corresponding infrared image disc surface area; extracting maximum temperature rise T of infrared image disk surface areamaxAs an infrared image feature value;
step S5, establishing a visible light image-based pollution level identification mathematical model and a visible light image pollution state identification mathematical model assisted by infrared image information, wherein the visible light image-based pollution level identification mathematical model is as follows:
wherein, ESDD: equivalent salt deposit density value;
v: the average value of the V components of the characteristic value of the visible light image of the dirty insulator to be identified;
V1: the average value of the V components of the visible light image characteristic value of the IV-level pollution insulator;
V0: the average value of the V components of the visible light image characteristic values of the 0-level pollution insulators;
RH: ambient relative humidity;
the visible light image pollution state identification mathematical model based on the assistance of infrared image information is as follows:
wherein, ESDD: equivalent salt deposit density value;
v: the average value of the V components of the characteristic value of the visible light image of the dirty insulator to be identified;
V1: the average value of the V components of the visible light image characteristic value of the IV-level pollution insulator;
V0: the average value of the V components of the visible light image characteristic values of the 0-level pollution insulators;
Tmax: the maximum temperature rise value of the infrared image disc surface area of the pollution insulator to be identified;
RH: ambient relative humidity;
step S6, according to the relative humidity of the environment, selecting the corresponding mathematical model in step S5, substituting the data in step S2 and step S4, obtaining the pollution level of the insulator, and determining the applied mathematical model according to the relative humidity of the environment, wherein the mathematical model comprises the following steps: when the relative humidity RH of the environment is less than 60%, calculating an equivalent salt deposit density value by using a pollution grade recognition mathematical model based on the visible light image; when the relative humidity RH of the environment is more than or equal to 60%, the characteristic value of the infrared image is required to be subjected to auxiliary identification, the weight of visible light image information and infrared image information is determined according to the relative humidity RH of the environment, and an equivalent salt deposit density value is calculated by utilizing a visible light image pollution state identification mathematical model based on the assistance of the infrared image information; and judging the pollution grade of the insulator according to the obtained equivalent salt deposit density value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611027566.9A CN106680285B (en) | 2016-11-17 | 2016-11-17 | Method for recognizing insulator contamination state based on infrared image assisted visible light image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611027566.9A CN106680285B (en) | 2016-11-17 | 2016-11-17 | Method for recognizing insulator contamination state based on infrared image assisted visible light image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106680285A CN106680285A (en) | 2017-05-17 |
| CN106680285B true CN106680285B (en) | 2022-04-05 |
Family
ID=58866677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611027566.9A Active CN106680285B (en) | 2016-11-17 | 2016-11-17 | Method for recognizing insulator contamination state based on infrared image assisted visible light image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106680285B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107240095A (en) * | 2017-05-25 | 2017-10-10 | 武汉大学 | A kind of DC line pollution severity of insulators state recognition method based on visible images |
| CN107292246A (en) * | 2017-06-05 | 2017-10-24 | 河海大学 | Infrared human body target identification method based on HOG PCA and transfer learning |
| CN107464233B (en) * | 2017-07-19 | 2021-11-05 | 国家电网公司 | Composite insulator image detection method and system based on Lab color mode |
| CN107767364B (en) * | 2017-09-12 | 2021-03-23 | 中国林业科学研究院林业研究所 | Method for accurately extracting temperature of tree canopy based on infrared thermal image |
| CN107729397B (en) | 2017-09-21 | 2020-01-14 | 国网天津市电力公司电力科学研究院 | Method for judging ice and snow covering type by using RGB (red, green and blue) components of image |
| CN107885921A (en) * | 2017-10-27 | 2018-04-06 | 国家电网公司 | Composite insulator rod core aging evaluation method |
| CN108872819A (en) * | 2018-07-29 | 2018-11-23 | 湖南湖大华龙电气与信息技术有限公司 | Isolator detecting unmanned plane and method based on infrared thermal imagery and visible light |
| CN110567964B (en) * | 2019-07-19 | 2022-07-05 | 华瑞新智科技（北京）有限公司 | Method and device for detecting defects of power transformation equipment and storage medium |
| CN110824311A (en) * | 2019-11-22 | 2020-02-21 | 南京信息工程大学 | Zinc oxide valve plate breakdown point detection device and method based on image recognition |
| CN112966576B (en) * | 2021-02-24 | 2022-09-16 | 西南交通大学 | System and method for aiming insulator water washing robot based on multi-light source image |
| CN113241228B (en) * | 2021-05-31 | 2022-09-27 | 江西尚高电瓷电气有限公司 | Antifouling self-cleaning type line column type porcelain insulator |
| CN113884500A (en) * | 2021-10-12 | 2022-01-04 | 国家电网有限公司 | Porcelain insulator defect detection method based on ultraviolet imaging |
| CN116071368B (en) * | 2023-04-07 | 2023-06-16 | 国网山西省电力公司电力科学研究院 | Insulator pollution multi-angle image detection and fineness analysis method and device |
| CN116679171B (en) * | 2023-05-15 | 2023-11-10 | 江苏云峰科技股份有限公司 | Insulation state judging system of insulation piece of wind power generation switch |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102809568A (en) * | 2012-08-28 | 2012-12-05 | 广东电网公司佛山供电局 | Method and system for monitoring contamination distribution of insulator |
| CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Visible image based insulator detection method and device thereof |
| CN103411980A (en) * | 2013-07-23 | 2013-11-27 | 同济大学 | External insulation filth status identification method based on visible-light images |
-
2016
- 2016-11-17 CN CN201611027566.9A patent/CN106680285B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102809568A (en) * | 2012-08-28 | 2012-12-05 | 广东电网公司佛山供电局 | Method and system for monitoring contamination distribution of insulator |
| CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Visible image based insulator detection method and device thereof |
| CN103411980A (en) * | 2013-07-23 | 2013-11-27 | 同济大学 | External insulation filth status identification method based on visible-light images |
Non-Patent Citations (4)
| Title |
|---|
| Condition Evaluation of the Contaminated Insulators by Visible Light Images Assisted With Infrared Information;Lijun Jin 等;《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》;20170630;第1349-1358页 * |
| Detection and Processing for ±660 Composite Insulator Abnormal Discharge;LIU Hui 等;《2014 International Conference on Power System Technology 》;20141031;第1404-1409页 * |
| 基于红外与可见光图像信息融合的绝缘子污秽等级识别;金立军等;《中国电机工程学报》;20160715;第3682-3690页 * |
| 金立军等.基于红外与可见光图像信息融合的绝缘子污秽等级识别.《中国电机工程学报》.2016,第3682-3691页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106680285A (en) | 2017-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106680285B (en) | Method for recognizing insulator contamination state based on infrared image assisted visible light image | |
| CN110458839B (en) | Effective wire and cable monitoring system | |
| CN103234465B (en) | A kind of electric power line ice-covering thickness detection method and system | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN108734689B (en) | Method for detecting scattered strands of conducting wires based on region growth | |
| CN110567964B (en) | Method and device for detecting defects of power transformation equipment and storage medium | |
| CN111583198A (en) | Insulator picture defect detection method combining FasterR-CNN + ResNet101+ FPN | |
| CN103196380B (en) | Transmission line of electricity image collecting device and electric power line ice-covering thickness detection system | |
| CN102288884B (en) | External insulation discharging detecting method based on ultraviolet light spots | |
| CN102831393A (en) | Rapid image recognizing method of power tower pole outline | |
| CN112001260A (en) | Cable trench fault detection method based on infrared and visible light image fusion | |
| CN102519846B (en) | Hyperspectrum-based composite insulator hydrophobicity detection method | |
| CN110726725A (en) | Transmission line hardware corrosion detection method and device | |
| CN105096305A (en) | Method and device for analyzing state of insulators | |
| CN111008967B (en) | Insulator RTV coating defect identification method | |
| CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
| CN113065484A (en) | Insulator contamination state assessment method based on ultraviolet spectrum | |
| CN110276787B (en) | Conductor galloping monitoring method based on marker image detection | |
| CN113487559A (en) | Method for detecting opening and closing states of disconnecting switch of transformer substation in real time | |
| CN113269744A (en) | Infrared intelligent identification method and system applied to defects of power transmission line equipment | |
| CN111307267A (en) | Conductor galloping monitoring method based on concentric circle detection | |
| CN116758425A (en) | Automatic acceptance checking method and device for large-base photovoltaic power station | |
| CN112001271A (en) | Construction site road cleaning method, device and system | |
| CN112489018A (en) | Intelligent power line inspection method and inspection line | |
| CN108898080B (en) | Ridge line neighborhood evaluation model-based crack connection 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 |