CN109860742B - Method for identifying electrolyte leakage of communication power supply storage battery of transformer substation - Google Patents
Method for identifying electrolyte leakage of communication power supply storage battery of transformer substation Download PDFInfo
- Publication number
- CN109860742B CN109860742B CN201910166095.7A CN201910166095A CN109860742B CN 109860742 B CN109860742 B CN 109860742B CN 201910166095 A CN201910166095 A CN 201910166095A CN 109860742 B CN109860742 B CN 109860742B
- Authority
- CN
- China
- Prior art keywords
- pixel
- picture
- storage battery
- value
- area
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for identifying electrolyte leakage of a storage battery of a communication power supply of a transformer substation, which comprises the steps of identifying characteristic objects of the outer surface of a storage battery shell and positive and negative shell covers in a picture according to color characteristics, then segmenting characteristic areas of the outer surface of the storage battery shell and the positive and negative shell covers in the picture, identifying positions of the outer surface of the storage battery shell and the positive and negative shell covers in the picture by adopting a method of combining RGB color characteristics and gray scale characteristics, and finally eliminating other interferences according to the symmetrical characteristics of the outer surface of the storage battery shell and the positive and negative shell covers in the picture, so that whether electrolyte leakage exists on the outer surface of the storage battery shell and the positive and negative shell covers of the communication power supply of the transformer substation according to RGB color. The method has reliable anti-interference capability, can effectively avoid the interference phenomena such as picture jitter, blurring and the like, and has higher accuracy and practicability.
Description
Technical Field
The invention relates to a method for identifying electrolyte leakage of a storage battery of a communication power supply of a transformer substation, and belongs to the technical field of communication of transformer substations.
Background
Due to the fact that the number of substations is large, the number of storage batteries to be maintained is large, the discharging time is long, maintenance personnel are few and the like, a large amount of manpower and material resources are required to be invested to carry out maintenance work every year, and due to the fact that operation and maintenance personnel are limited and heavy in work, most storage batteries cannot be effectively maintained. And the electrolyte leakage of the storage battery seriously affects the safe and stable operation of a power grid, so that the automatic identification of the electrolyte leakage of the storage battery of the communication power supply of the transformer substation is realized by adopting an automatic technical means, so that the inspection work efficiency is effectively improved, the inspection workload of personnel is reduced, and the safe and reliable operation of the transformer substation is effectively improved.
Disclosure of Invention
The invention aims to provide a method for identifying the electrolyte leakage of a communication power supply storage battery of a transformer substation, which overcomes the defect of low identification accuracy in the prior art and realizes the automatic identification of the electrolyte leakage of the communication power supply storage battery.
The purpose of the invention is realized by the following technical scheme:
a method for identifying electrolyte leakage of a storage battery of a communication power supply of a transformer substation comprises the following steps:
step 1) carrying out mean value filtering processing on the obtained original picture of the storage battery;
step 2), for each pixel of the picture after the average filtering processing, when three color component values of the pixel R, G, B are all higher than 200, setting the value of the pixel point to be R-255, G-255, and B-255;
step 3) calculating the average difference value of three color components of each pixel of the picture after the average filtering processing, wherein the calculation method comprises the following steps:
Avg＝(R+G+B)/3
Avg_d＝((Avg-R)+(Avg-G)+(Avg-B))/3
in the above formula, Avg is an average value, Avg _ d is an average difference value, and when the average difference value Avg _ d is greater than 50, the value of the pixel point is set to be that R is 255, G is 255, and B is 255;
step 4) setting a pixel value which does not satisfy the conditions of the step 2) and the step 3) as R-0, G-0 and B-0;
step 5) converting the picture processed in the step into a gray picture;
step 6) processing the gray level picture by adopting an image expansion algorithm of a 3 multiplied by 3 pixel area;
step 7) searching the area of the white pixel point of the picture after the image expansion algorithm processing to form an external contour area;
step 8) calculating the area of each outer contour region, and when the area is smaller than 1/50 of the picture size, ignoring the region;
step 9) aiming at each external contour region searched in the step, corresponding each external contour region range to the original picture region range;
step 10), processing according to each pixel RGB component value in each area range in the original picture, and when R > G +10 and G > B +30, setting the pixel value as R-255, G-255 and B-255;
step 11), processing is performed in each area range in the original picture according to the RGB component value of each pixel, and when the three color component values of the pixel R, G, B are all higher than 200, the value of the pixel point is set to be R ═ 0, G ═ 0, and B ═ 0;
step 12) the pixel points of the black pixel values and the pixel points of the white pixel values in the processing results of the steps 10) and 11) respectively represent a storage battery shell and a positive and negative shell;
step 13) calculating 2/50 that the number of white pixels in each region exceeds the total number of pixels in the region according to the picture formed in the previous step, and indicating that the electrolyte of the storage battery leaks.
The object of the invention can be further achieved by the following technical measures:
the method for identifying the electrolyte leakage of the storage battery of the communication power supply of the transformer substation comprises the following steps in step 1):
let Sxy represent the filter window with the size of mxn with the center point at (x, y), calculate the pixel mean of the window area, and then assign the mean to the pixel at the window center point, the formula is as follows:
wherein g (s, t) represents the original image, and f (x, y) represents the image obtained after mean filtering.
The method for identifying the electrolyte leakage of the storage battery of the communication power supply of the transformer substation comprises the following steps in step 6):
(1) obtaining pixels of a source image of a gray level picture;
(2) creating a target image with the same size as the source image and black pixels;
(3) in order to prevent border crossing, pixels at the leftmost side, the rightmost side, the topmost side and the bottommost side are not processed, pixel points in a source image are checked from the 2 nd row and the 2 nd column, and if only one point in a 3 x 3 pixel region structural element is white, the current pixel point in a target image is set to be white;
(4) circularly executing the step (3) until the source image is processed;
(5) the obtained target image is the expansion result.
The method for identifying the electrolyte leakage of the storage battery of the communication power supply of the transformer substation further comprises the following step 14):
and according to the picture formed in the step 12), when the number of the white pixels in each area exceeds 1/50 of the total number of the pixels in the area and is less than 2/50, indicating that the electrolyte leakage of the storage battery possibly exists, and prompting and alarming.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps of identifying characteristic objects of the outer surface of a storage battery shell and positive and negative shell covers in a picture according to color characteristics, then segmenting characteristic regions of the outer surface of the storage battery shell and the positive and negative shell covers in the picture, then identifying positions of the outer surface of the storage battery shell and the positive and negative shell covers in the picture by adopting a method of combining RGB color characteristics and gray characteristics, and finally eliminating other interferences according to the symmetrical characteristics of the outer surface of the storage battery shell and the positive and negative shell covers in the picture, thereby judging whether electrolyte leakage exists on the outer surface of the storage battery shell and the positive and negative shell covers of the communication power supply of the transformer substation according to RGB color characteristic values and gray characteristic values of.
The method has reliable anti-interference capability, can effectively avoid the interference phenomena such as picture jitter, blurring and the like, has higher accuracy and practicability, and also has wide environmental adaptability. The method is easy to realize and apply, is mainly applied to the identification of the leakage of the electrolyte of the storage battery of the communication power supply of the transformer substation, and has a promoting effect on the development and improvement of the intelligent level of the power grid.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
As shown in fig. 1, a flow chart of a method for identifying leakage of electrolyte of a storage battery of a communication power supply of a transformer substation is shown, and the method mainly comprises four processing steps: the method comprises the steps of image preprocessing, object identification based on color characteristics, image segmentation of an object characteristic region, identification of a storage battery shell, a positive electrode shell and a negative electrode shell which are combined by RGB color characteristics and gray scale characteristics, and identification of electrolyte leakage of the storage battery according to multi-characteristic criteria.
In order to identify the storage battery in the monitored image, the image preprocessing and object identification processing steps based on the color characteristics comprise:
(1) carrying out mean value filtering processing on the obtained original picture of the storage battery;
the mean filtering process can remove uniform noise and gaussian noise, let Sxy represent the filter window with the size of mxn with the center point at (x, y). The arithmetic mean filter simply calculates the mean of the pixels in the window area, and then assigns the mean to the pixels at the center point of the window:
wherein g (s, t) represents the original image, and f (x, y) represents the image obtained after mean filtering. Based on the formula, the average filtering processing can be carried out on the original picture of the storage battery.
(2) For the filtered picture, for each pixel in the picture, when the three color component values of the pixel R, G, B are all higher than 200, setting the value of the pixel point to be R-255, G-255, and B-255;
(3) calculating the average difference value of three color components of each pixel of the processed picture, wherein the calculation method comprises the following steps:
Avg＝(R+G+B)/3
Avg_d＝((Avg-R)+(Avg-G)+(Avg-B))/3
in the above formula, Avg is an average value, Avg _ d is an average difference value, and when the average difference value Avg _ d is greater than 50, the value of the pixel point is set to be that R is 255, G is 255, and B is 255;
(4) pixel values that do not satisfy the above two conditions are set to R ═ 0, G ═ 0, and B ═ 0.
In order to cut the battery image in the monitoring image and obtain the external contour thereof, the image segmentation of the object characteristic region comprises the following steps:
1) converting the picture of the processing result of the previous step into a gray picture;
2) the image expansion algorithm of a 3 x 3 pixel area is adopted for processing the gray level picture, and the following function processing flow is processed:
(1) obtaining pixels of a source image;
(2) creating a target image with the same size as the source image and black pixels;
(3) in order to prevent border crossing, pixels at the leftmost side, the rightmost side, the topmost side and the bottommost side are not processed, pixel points in a source image are checked from the 2 nd row and the 2 nd column, and if only one point in a 3 x 3 pixel region structural element is white, the current pixel point in a target image is set to be white;
(4) the step (3) is circulated until the source image is processed;
(5) the obtained target image is the expansion result.
3) Searching the areas of the white pixel points of the expanded picture to form a series of external contour areas;
4) the area size of each outline region is calculated and when the area size is smaller than 1/50, the region is ignored.
The outer contour of the battery image is obtained by the above processing.
In order to distinguish the storage battery shell from the positive and negative shells in the storage battery image, the identification method of the storage battery shell and the positive and negative shells by combining the RGB color characteristics and the gray scale characteristics comprises the following steps:
(1) aiming at each contour area searched in the last step, corresponding each contour area range to the original image area range;
(2) setting the pixel value to be R255, G255 and B255 when R > G +10 and G > B +30 in each region range in the original image according to each pixel RGB component value;
(3) in each area range in the original image, according to the RGB component value of each pixel, when all three color component values of the pixel R, G, B are higher than 200, the value of the pixel is set to be R ═ 0, G ═ 0, and B ═ 0;
(4) the black pixel value and the white pixel value in the two processing results respectively represent the characteristics of the storage battery shell and the positive and negative shells.
The method for identifying the electrolyte leakage of the storage battery according to the multi-feature criterion comprises the following steps:
(1) calculating 2/50 that the number of white pixels in each region exceeds the total number of pixels in each region according to the picture formed in the previous step, and indicating that the electrolyte of the storage battery leaks;
(2) and according to the picture formed in the last step, when the number of the white pixels in each area exceeds 1/50 of the total number of the pixels in the area and is less than 2/50, the leakage of the electrolyte of the storage battery is indicated, and a prompt alarm can be given at the moment, and the leakage detection is prevented by further judging and identifying manually.
The method of the invention requires the lowest configuration of computer hardware: the PC computer with P4, 3.0GCPU and 2G memory adopts C/C + + language programming to realize the method on the hardware of the configuration level. The operating system may be based on various operating systems such as Windows or Linux.
In addition to the above embodiments, the present invention may have other embodiments, and any technical solutions formed by equivalent substitutions or equivalent transformations fall within the scope of the claims of the present invention.
Claims (4)
1. The method for identifying the electrolyte leakage of the storage battery of the communication power supply of the transformer substation is characterized by comprising the following steps of:
step 1) carrying out mean value filtering processing on the obtained original picture of the storage battery;
step 2), for each pixel of the picture after the average filtering processing, when three color component values of the pixel R, G, B are all higher than 200, setting the value of the pixel point to be R-255, G-255, and B-255;
step 3) calculating the average difference value of three color components of each pixel of the picture after the average filtering processing, wherein the calculation method comprises the following steps:
Avg＝(R+G+B)/3
Avg_d＝((Avg-R)+(Avg-G)+(Avg-B))/3
in the above formula, Avg is an average value, Avg _ d is an average difference value, and when the average difference value Avg _ d is greater than 50, the value of the pixel point is set to be that R is 255, G is 255, and B is 255;
step 4) setting a pixel value which does not satisfy the conditions of the step 2) and the step 3) as R-0, G-0 and B-0;
step 5) converting the picture processed in the step into a gray picture;
step 6) processing the gray level picture by adopting an image expansion algorithm of a 3 multiplied by 3 pixel area;
step 7) searching the area of the white pixel point of the picture after the image expansion algorithm processing to form an external contour area;
step 8) calculating the area of each outer contour region, and when the area is smaller than 1/50 of the picture size, ignoring the region;
step 9) aiming at each external contour region searched in the step, corresponding each external contour region range to the original picture region range;
step 10), processing according to each pixel RGB component value in each area range in the original picture, and when R > G +10 and G > B +30, setting the pixel value as R-255, G-255 and B-255;
step 11), processing is performed in each area range in the original picture according to the RGB component value of each pixel, and when the three color component values of the pixel R, G, B are all higher than 200, the value of the pixel point is set to be R ═ 0, G ═ 0, and B ═ 0;
step 12) the pixel points of the black pixel values and the pixel points of the white pixel values in the processing results of the step 10) and the step 11) respectively represent a storage battery shell and a positive and negative shell;
step 13) calculating 2/50 that the number of white pixels in each region exceeds the total number of pixels in the region according to the picture formed in the previous step, and indicating that the electrolyte of the storage battery leaks.
2. The substation communication power supply storage battery electrolyte leakage identification method of claim 1, wherein the average filtering process of step 1) comprises the steps of:
let Sxy represent the filter window with the size of mxn with the center point at (x, y), calculate the pixel mean of the window area, and then assign the mean to the pixel at the window center point, the formula is as follows:
wherein g (s, t) represents the original image, and f (x, y) represents the image obtained after mean filtering.
3. The substation communication power supply storage battery electrolyte leakage identification method of claim 1, wherein the image expansion algorithm processing of step 6) comprises the steps of:
(1) obtaining pixels of a source image of a gray level picture;
(2) creating a target image with the same size as the source image and black pixels;
(3) in order to prevent border crossing, pixels at the leftmost side, the rightmost side, the topmost side and the bottommost side are not processed, pixel points in a source image are checked from the 2 nd row and the 2 nd column, and if only one point in a 3 x 3 pixel region structural element is white, the current pixel point in a target image is set to be white;
(4) circularly executing the step (3) until the source image is processed;
(5) the obtained target image is the expansion result.
4. The substation communication power supply storage battery electrolyte leakage identification method of claim 1, further comprising step 14):
and according to the picture formed in the step 12), when the number of the white pixels in each area exceeds 1/50 of the total number of the pixels in the area and is less than 2/50, indicating that the electrolyte leakage of the storage battery possibly exists, and prompting and alarming.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910166095.7A CN109860742B (en) | 2019-03-06 | 2019-03-06 | Method for identifying electrolyte leakage of communication power supply storage battery of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910166095.7A CN109860742B (en) | 2019-03-06 | 2019-03-06 | Method for identifying electrolyte leakage of communication power supply storage battery of transformer substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109860742A CN109860742A (en) | 2019-06-07 |
| CN109860742B true CN109860742B (en) | 2020-11-06 |
Family
ID=66899830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910166095.7A Active CN109860742B (en) | 2019-03-06 | 2019-03-06 | Method for identifying electrolyte leakage of communication power supply storage battery of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109860742B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1794512A (en) * | 2004-12-22 | 2006-06-28 | 丰田自动车株式会社 | Battery, manufacturing method of battery, and check method of electrolyte leakage |
| CN107749057A (en) * | 2017-09-16 | 2018-03-02 | 河北工业大学 | A kind of method of solar battery sheet outward appearance spillage defects detection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102171864A (en) * | 2008-12-24 | 2011-08-31 | 日本碍子株式会社 | Plate-shaped particles for positive electrode active material of lithium secondary batteries, films of said material as well as lithium secondary batteries |
-
2019
- 2019-03-06 CN CN201910166095.7A patent/CN109860742B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1794512A (en) * | 2004-12-22 | 2006-06-28 | 丰田自动车株式会社 | Battery, manufacturing method of battery, and check method of electrolyte leakage |
| CN107749057A (en) * | 2017-09-16 | 2018-03-02 | 河北工业大学 | A kind of method of solar battery sheet outward appearance spillage defects detection |
Non-Patent Citations (1)
| Title |
|---|
| 基于图像处理的电池异常事件监控技术;陈善伟;《中国优秀硕士学位论文全文数据库》;20130228;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109860742A (en) | 2019-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| CN109325935B (en) | Power transmission line detection method based on unmanned aerial vehicle image | |
| Wang et al. | Recognition and drop-off detection of insulator based on aerial image | |
| CN107679495B (en) | Detection method for movable engineering vehicles around power transmission line | |
| CN111179232A (en) | Steel bar size detection system and method based on image processing | |
| CN111815623B (en) | Power transmission line cotter pin missing identification method | |
| CN113313677B (en) | Quality detection method for X-ray image of wound lithium battery | |
| CN114241364A (en) | Method for quickly calibrating foreign object target of overhead transmission line | |
| CN108334824B (en) | High-voltage isolating switch state identification method based on background difference and iterative search | |
| CN111047564A (en) | EL defect detection method applied to photovoltaic power station site | |
| CN107657260B (en) | Method for detecting ground hidden danger in power transmission line surrounding environment | |
| CN108154496B (en) | Electric equipment appearance change identification method suitable for electric power robot | |
| CN114594114A (en) | Full-automatic online nondestructive detection method for lithium battery cell | |
| CN114549393B (en) | Image labeling method, device, equipment and computer storage medium | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN109860742B (en) | Method for identifying electrolyte leakage of communication power supply storage battery of transformer substation | |
| CN113763397A (en) | Composite insulator fault detection method and system | |
| CN110766675B (en) | Solar cell panel defect detection method | |
| Wei et al. | Stain detection method of solar panel based on spot elimination | |
| CN106251351B (en) | A kind of transmission line forest fire monitoring threshold computational methods based on Cloud transform | |
| CN111353507A (en) | Image recognition method and device for oil stains on surface of transformer substation device | |
| CN105163076B (en) | The substation breakers state video intelligent parser mapped using transversal scanning | |
| CN107609556B (en) | Detection method for high-altitude operation machine in power transmission line environment | |
| CN115761644A (en) | Transmission line foreign matter detection method based on deep learning and frame difference method | |
| CN116091996A (en) | Identification method, device, equipment and storage medium for disconnecting link switching state |
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 |