CN109860742A - Transformer substation communication battery of electric power electrolyte reveals recognition methods - Google Patents
Transformer substation communication battery of electric power electrolyte reveals recognition methods Download PDFInfo
- Publication number
- CN109860742A CN109860742A CN201910166095.7A CN201910166095A CN109860742A CN 109860742 A CN109860742 A CN 109860742A CN 201910166095 A CN201910166095 A CN 201910166095A CN 109860742 A CN109860742 A CN 109860742A
- Authority
- CN
- China
- Prior art keywords
- pixel
- picture
- value
- region
- battery
- 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
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
Abstract
The invention discloses a kind of transformer substation communication battery of electric power electrolyte to reveal recognition methods, the feature object of battery jar external surface and positive and negative anodes cap in picture is identified according to color characteristic, next is partitioned into the characteristic area of battery jar external surface and positive and negative anodes cap in picture, the method combined again using RGB color feature and gray feature, identify that battery jar external surface and positive and negative anodes cap are in the position in picture, the finally symmetrical feature according to battery jar external surface and positive and negative anodes cap in picture, exclude other interference, to according to the RGB color characteristic value and gray feature value of battery jar external surface and positive and negative anodes cap, judge that transformer substation communication battery of electric power housing outer surface and positive and negative anodes cap are revealed with the presence or absence of electrolyte.Method of the invention has reliable anti-interference ability, can effectively evade due to interference phenomenons, accuracy with higher and the practicability such as picture shake, fuzzy.
Description
Technical field
The present invention relates to a kind of transformer substation communication battery of electric power electrolyte to reveal recognition methods, belongs to transformer substation communication skill
Art field.
Background technique
Since substation's quantity is more, the battery group quantity of required maintenance is more, discharge time is long, maintenance personnel's originals such as less
Cause needs to put into every year a large amount of human and material resources and carries out maintenance work, since operation maintenance personnel is limited, work is heavy, leads to big portion
Divide battery group that cannot effectively safeguard.And battery liquid leakage seriously affects the safe and stable operation of power grid, therefore,
The automatic identification revealed transformer substation communication battery of electric power electrolyte is realized using the technological means of automation, to effectively improve
Inspection working efficiency reduces personnel's inspection workload, effectively improves the security reliability of substation operation with highly important
Meaning.
Summary of the invention
The purpose of the present invention is to provide a kind of transformer substation communication battery of electric power electrolyte to reveal recognition methods, overcomes existing
The deficiency for having technology recognition accuracy low realizes the automatic identification revealed accumulator for communication power supply electrolyte.
The purpose of the present invention is achieved by the following technical programs:
A kind of transformer substation communication battery of electric power electrolyte leakage recognition methods, comprising the following steps:
1) mean filter processing is carried out to the original image of the battery got；
2) to each pixel of mean filter treated picture, when tri- color component values of pixel R, G, B are above 200
When, the value that the pixel is arranged is R=255, G=255, B=255；
3) mean difference of three color components of each pixel of mean filter treated picture, calculation method are calculated
It is as follows:
Avg=(R+G+B)/3
Avg_d=((Avg-R)+(Avg-G)+(Avg-B))/3
Avg in above formula is average value, and Avg_d is mean difference, and when mean difference Avg_d is greater than 50, the picture is arranged
The value of vegetarian refreshments is R=255, G=255, B=255；
4) above-mentioned steps 2 will be unsatisfactory for), the pixel value of step 3) condition be set as R=0, G=0, B=0；
5) by above-mentioned steps, treated that picture is converted to gray scale picture；
6) the image expansion algorithm process of 3 × 3 pixel regions is used to gray scale picture；
7) to the region of the picture searching white pixel point after progress image expansion algorithm process, exterior contour area is formed
Domain；
8) area for calculating each exterior contour region ignores the region when area is less than the 1/50 of picture size；
9) for each exterior contour region found in above-mentioned steps, each exterior contour regional scope is corresponding extremely
Original image regional scope；
10) it in each regional scope in original image, is handled according to each pixel RGB component value, works as R > G+
10, and when G > B+30, it is R=255, G=255, B=255 that the pixel value, which is arranged,；
11) it in each regional scope in original image, is handled according to each pixel RGB component value, works as pixel
R, when tri- color component values of G, B are above 200, the value that the pixel is arranged is R=0, G=0, B=0；
12) above-mentioned steps 10), 11) pixel of the pixel and white pixel value of the black pixel value in processing result
Show respectively accumulator housing and positive and negative pole housing；
13) picture formed according to previous step, the number for calculating white pixel in each region is more than the total pixel in region
Number 2/50 when, indicate there are battery liquid leakages.
The purpose of the present invention can also be further realized by following technical measures:
Aforementioned transformer substation communication battery of electric power electrolyte reveals recognition methods, wherein step 1) the mean filter processing
The following steps are included:
Sxy is enabled to indicate central point at (x, y), size is the filtering window of m × n, and the pixel in calculation window region is equal
Value, is then assigned to the pixel at window center point for mean value, formula is as follows:
Wherein, g (s, t) indicates that original image, f (x, y) indicate the image obtained after mean filter.
Aforementioned transformer substation communication battery of electric power electrolyte reveals recognition methods, wherein step 6) described image expansion algorithm
Processing the following steps are included:
(1) pixel of the source images of gray scale picture is obtained；
(2) one width size of creation is identical as source images, and all pixels set black target image；
(3) to prevent from crossing the border, Far Left, rightmost, the top and pixel bottom are not handled, from the 2nd row, the 2nd column
Start to check the pixel in source images, if as long as having a point in 3 × 3 pixel region structural elements is white, by mesh
Current pixel point in logo image is set to white；
(4) circulation executes step (3), until having handled source images；
(5) resulting target image is expansion results.
Aforementioned transformer substation communication battery of electric power electrolyte reveals recognition methods, further includes step 14):
According to the picture that step 12) is formed, the number for calculating white color pixel in each region is more than the total pixel in region
Several 1/50 and when less than 2/50, it indicates to carry out prompt alarm there may be battery liquid leakage.
Compared with prior art, the beneficial effects of the present invention are: identifying accumulator housing in picture according to color characteristic
The feature object of outer surface and positive and negative anodes cap, next is partitioned into battery jar external surface in picture and positive and negative anodes cap
Characteristic area, then the method combined using RGB color feature and gray feature identify battery jar external surface and positive and negative
Pole cap is in the position in picture, finally the symmetrical spy according to battery jar external surface and positive and negative anodes cap in picture
Sign, excludes other interference, thus according to the RGB color characteristic value and gray feature of battery jar external surface and positive and negative anodes cap
Value judges that transformer substation communication battery of electric power housing outer surface and positive and negative anodes cap are revealed with the presence or absence of electrolyte.
Method of the invention has reliable anti-interference ability, can effectively evade due to the interference such as picture shake, fuzzy
Phenomenon, accuracy with higher and practicability, meanwhile, also have extensive environmental suitability.Method of the invention is easy to real
It now and applies, is mainly used in the leakage identification of transformer substation communication battery of electric power electrolyte, the development to smart grid level
There is facilitation with improving.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples.
Recognition methods flow chart is revealed for transformer substation communication battery of electric power electrolyte as shown in Figure 1, this method is mainly wrapped
Include four processing steps: picture pretreatment and the Object identifying based on color characteristic, the picture segmentation in characteristics of objects region, RGB
The accumulator housing and positive and negative pole housing that color characteristic and gray feature combine are identified, are electrolysed according to multiple features criterion battery
Liquid leakage identification.
In order to identify battery in monitoring image, at the picture pretreatment and the Object identifying based on color characteristic
Managing step includes:
(1) mean filter processing is carried out to the original image of the battery got；
Mean filter processing can remove Uniform noise and Gaussian noise, enable Sxy expression central point at (x, y), size
For the filtering window of m × n.Arithmetic equal value filter is exactly the pixel mean value in simple calculation window region, then by mean value
The pixel being assigned at window center point:
Wherein, g (s, t) indicates that original image, f (x, y) indicate the image obtained after mean filter.Based on above-mentioned formula,
Mean filter processing can be carried out to the original image of battery.
(2) for the picture after filtering processing, for each pixel in picture, when tri- color components of pixel R, G, B
When value is above 200, the value that the pixel is arranged is R=255, G=255, B=255；
(3) after calculation processing three color components of each pixel of picture mean difference, calculation method is as follows:
Avg=(R+G+B)/3
Avg_d=((Avg-R)+(Avg-G)+(Avg-B))/3
Avg in above formula is average value, and Avg_d is mean difference, and when mean difference Avg_d is greater than 50, the picture is arranged
The value of vegetarian refreshments is R=255, G=255, B=255；
(4) R=0, G=0, B=0 are set by the pixel value for being unsatisfactory for above-mentioned two condition.
In order to be cut into battery image in monitoring image, its exterior contour, the characteristics of objects area are obtained
The picture segmentation in domain includes:
1) picture of previous step processing result is converted into gray scale picture；
2) the image expansion algorithm process of 3 × 3 pixel regions is used to gray scale picture, processing such as minor function process flow:
(1) pixel of source images is obtained；
(2) one width size of creation is identical as source images, and all pixels set black target image；
(3) to prevent from crossing the border, Far Left, rightmost, the top and pixel bottom are not handled, from the 2nd row, the 2nd column
Start to check the pixel in source images, if as long as having a point in 3 × 3 pixel region structural elements is white, by mesh
Current pixel point in logo image is set to white；
(4) circulation step (3, until handled source images；
(5) resulting target image is expansion results.
3) to the region of the picture searching white pixel point after expansion process, a series of exterior contour region is formed；
4) size for calculating each contour area ignores the area when size is less than the 1/50 of picture size
Domain.
The exterior contour of battery image is obtained by above-mentioned processing.
In order to distinguish accumulator housing and positive and negative pole housing, the RGB color feature and gray scale in battery image
Accumulator housing and positive and negative pole housing recognition methods that feature combines the following steps are included:
(1) for each contour area found in previous step, each contour area range is corresponding to original image area
Domain range；
(2) in each regional scope in original image, according to each pixel RGB component value, work as R > G+10, and G > B+30
When, it is R=255, G=255, B=255 that the pixel value, which is arranged,；
(3) in each regional scope in original image, according to each pixel RGB component value, when tri- colors of pixel R, G, B
When component value is above 200, the value that the pixel is arranged is R=0, G=0, B=0；
(4) black pixel value in above-mentioned two processing result and white pixel value show respectively accumulator housing and just
Anode housing feature.
It is described recognition methods is revealed according to multiple features criterion battery liquid to include:
(1) picture formed according to previous step, the number for calculating white pixel in each region is more than the total pixel in region
Number 2/50 when, indicate there are battery liquid leakages；
(2) picture formed according to previous step, the number for calculating white color pixel in each region is more than the total picture in region
Plain number 1/50 and when less than 2/50, indicate that there may be battery liquid leakages, at this moment can carry out prompt alarm, by
Artificial further judgement identification, to prevent leak-stopping inspection.
The computer hardware minimalist configuration that method of the invention needs are as follows: the PC machine of P4,3.0G CPU, 2G memory, herein
On the hardware of configuration level, this method is realized using C/C++ Programming with Pascal Language.Operating system can be based on each of Windows or Linux
Type operating system.
In addition to the implementation, the present invention can also have other embodiments, all to use equivalent substitution or equivalent transformation shape
At technical solution, be all fallen within the protection domain of application claims.
Claims (4)
1. a kind of transformer substation communication battery of electric power electrolyte reveals recognition methods, which comprises the following steps:
1) mean filter processing is carried out to the original image of the battery got；
2) to each pixel of mean filter treated picture, when tri- color component values of pixel R, G, B are above 200,
The value that the pixel is arranged is R=255, G=255, B=255；
3) mean difference of three color components of each pixel of mean filter treated picture is calculated, calculation method is such as
Under:
Avg=(R+G+B)/3
Avg_d=((Avg-R)+(Avg-G)+(Avg-B))/3
Avg in above formula is average value, and Avg_d is mean difference, and when mean difference Avg_d is greater than 50, the pixel is arranged
Value be R=255, G=255, B=255；
4) above-mentioned steps 2 will be unsatisfactory for), the pixel value of step 3) condition be set as R=0, G=0, B=0；
5) by above-mentioned steps, treated that picture is converted to gray scale picture；
6) the image expansion algorithm process of 3 × 3 pixel regions is used to gray scale picture；
7) to the region of the picture searching white pixel point after progress image expansion algorithm process, exterior contour region is formed；
8) area for calculating each exterior contour region ignores the region when area is less than the 1/50 of picture size；
9) for each exterior contour region found in above-mentioned steps, each exterior contour regional scope is corresponding to original
Picture region range；
10) it in each regional scope in original image, is handled according to each pixel RGB component value, works as R > G+10, and
And when G > B+30, it is R=255, G=255, B=255 that the pixel value, which is arranged,；
11) it in each regional scope in original image, is handled according to each pixel RGB component value, as pixel R, G, B
When three color component values are above 200, the value that the pixel is arranged is R=0, G=0, B=0；
12) above-mentioned steps 10), 11) the pixel difference of the pixel and white pixel value of the black pixel value in processing result
Illustrate accumulator housing and positive and negative pole housing；
13) picture formed according to previous step, the number for calculating white pixel in each region is more than the total number of pixels in region
2/50 when, indicate there are battery liquid leakages.
2. transformer substation communication battery of electric power electrolyte as described in claim 1 reveals recognition methods, which is characterized in that step
1) mean filter processing the following steps are included:
Enable Sxy expression central point at (x, y), filtering window of the size for m × n, the pixel mean value in calculation window region, so
Mean value is assigned to the pixel at window center point afterwards, formula is as follows:
Wherein, g (s, t) indicates that original image, f (x, y) indicate the image obtained after mean filter.
3. transformer substation communication battery of electric power electrolyte as described in claim 1 reveals recognition methods, which is characterized in that step
6) described image expansion algorithm processing the following steps are included:
(1) pixel of the source images of gray scale picture is obtained；
(2) one width size of creation is identical as source images, and all pixels set black target image；
(3) to prevent from crossing the border, Far Left, rightmost, the top and pixel bottom are not handled, since the 2nd row, the 2nd column
The pixel in source images is checked, if as long as having a point in 3 × 3 pixel region structural elements is white, by target figure
Current pixel point as in is set to white；
(4) circulation executes step (3), until having handled source images；
(5) resulting target image is expansion results.
4. transformer substation communication battery of electric power electrolyte as described in claim 1 reveals recognition methods, which is characterized in that also wrap
Include step 14):
According to the picture that step 12) is formed, the number for calculating white color pixel in each region is more than the total number of pixels in region
1/50 and when less than 2/50, it indicates to carry out prompt alarm there may be battery liquid leakage.
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 true CN109860742A (en) | 2019-06-07 |
| CN109860742B 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 (3)
| 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 |
| US20100159330A1 (en) * | 2008-12-24 | 2010-06-24 | Ngk Insulators, Ltd. | Plate-like particle for cathode active material of a lithium secondary battery, a cathode active material film of a lithium secondary battery, and a lithium secondary battery |
| 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 |
-
2019
- 2019-03-06 CN CN201910166095.7A patent/CN109860742B/en active Active
Patent Citations (3)
| 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 |
| US20100159330A1 (en) * | 2008-12-24 | 2010-06-24 | Ngk Insulators, Ltd. | Plate-like particle for cathode active material of a lithium secondary battery, a cathode active material film of a lithium secondary battery, and a lithium secondary battery |
| 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 |
|---|
| 陈善伟: "基于图像处理的电池异常事件监控技术", 《中国优秀硕士学位论文全文数据库》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109860742B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| CN107314819B (en) | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image | |
| CN111815623B (en) | Power transmission line cotter pin missing identification method | |
| CN111179232A (en) | Steel bar size detection system and method based on image processing | |
| CN113902641B (en) | Data center hot zone judging method and system based on infrared image | |
| CN108665464A (en) | A kind of foreign matter detecting method based on morphologic high tension electric tower and high-tension bus-bar | |
| CN109308448A (en) | A method of it prevents from becoming distribution maloperation using image processing techniques | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN110992321A (en) | Solar cell grid line extraction method | |
| CN111353507B (en) | Image recognition method and device for oil stains on surface of transformer substation device | |
| CN110516565A (en) | A kind of sea ship recognition methods based on Zernike and SVM | |
| CN114241522A (en) | Method, system, equipment and storage medium for field operation safety wearing identification | |
| Wei et al. | Stain detection method of solar panel based on spot elimination | |
| CN110766675B (en) | Solar cell panel defect detection method | |
| CN109860742A (en) | Transformer substation communication battery of electric power electrolyte reveals recognition methods | |
| CN105163076B (en) | The substation breakers state video intelligent parser mapped using transversal scanning | |
| CN117036825A (en) | Solar cell panel detection method, medium and system | |
| CN110207783A (en) | A kind of sensed water level method based on video identification | |
| CN114926774A (en) | Method and device for identifying photovoltaic module fire based on video image | |
| CN106960437B (en) | Liquid level detection method for oil-immersed power transformer of power inspection robot | |
| CN112818836B (en) | Method and system for detecting personnel target of transformer substation scene | |
| CN115619796A (en) | Method and device for obtaining photovoltaic module template and nonvolatile storage medium | |
| CN114565551A (en) | Label detection method, device, equipment and computer readable storage medium | |
| CN114998371A (en) | Method and device for judging falling of photovoltaic module, storage medium and electronic equipment | |
| CN117095389B (en) | Image data processing method and system based on liquid crystal visual recognition unit |
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 |