CN108805038A - A kind of transformer substation protection pressure plate state identification method - Google Patents
A kind of transformer substation protection pressure plate state identification method Download PDFInfo
- Publication number
- CN108805038A CN108805038A CN201810502596.3A CN201810502596A CN108805038A CN 108805038 A CN108805038 A CN 108805038A CN 201810502596 A CN201810502596 A CN 201810502596A CN 108805038 A CN108805038 A CN 108805038A
- Authority
- CN
- China
- Prior art keywords
- region
- effective
- pressing plate
- image
- state
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A kind of transformer substation protection pressure plate state identification method acquires the screen cabinet image of function pressing plate, output clamping, spare pressing plate;According to rgb value to acquiring the effective color lump of image zooming-out;Morphological scale-space is carried out to gained image, perforated is filled with connected region;All connected regions are analyzed, zoning elemental area, zone boundary Pixel Dimensions, region equivalent length-width ratio etc., and carry out threshold value and combine to compare, determines effective platen region number;Judge whether the effective pressing plate number filtered out is equal to it is known that continuing if equal, otherwise re-starting Image Acquisition and repeating above-mentioned flow;State is moved back in the throwing of each pressing plate to be identified according to deflection criterion to effective platen region;According to each regional barycenter, effective pressing plate sequence is determined according to sequence from top to bottom, from left to right, and then identifies that the effective pressing plate of screen cabinet throws the mark sequence for state of moving back.The present invention efficiently solves the problems, such as maloperation when manual inspection, can provide certain technical support for intelligent substation construction and operation.
Description
Technical field
The invention belongs to electric system secondary side application fields, and in particular to a kind of transformer substation protection pressure plate state recognition side
Method.
Background technology
With the high speed development of China's economic society, NETWORK STRUCTURE PRESERVING POWER SYSTEM is increasingly sophisticated.Especially in intermittent new energy
Extensively under access, the safe and stable operation of electric system faces more challenges.In this context, the intelligence with significant advantage
Substation, which just gradually becomes, builds hot spot.To promote substation safety, stabilization, Effec-tive Function, secondary device fortune need to be effectively promoted
Row and maintenance levels, especially relay equipment inspection are horizontal.As to primary side carry out observing and controlling and relay protection operation important equipment,
The structure even more complex of substation secondary device screen cabinet, pressing plate quantity are increased.And protect pressing plate management as relay equipment
The important content of inspection, informationization, intelligent level are relatively low, can not be with substation's totality intelligent level phase
Match, it is difficult to meet the needs of intelligent substation management.
In addition, the monitoring of existing secondary device pressing plate state is still mainly by manually carrying out inspection completion.And when personal monitoring
Due to visual fatigue, memory are obscured etc., the phenomenon that leading to pressing plate leakage operation, maloperation, happens occasionally.And it ought artificially not
When controllable factor leads to occur misoperation, only after related accidents appearance, it can be found and be restored, seriously
Endanger power system security stabilization.Under intelligent development opportunity, in conjunction with automation and computer information technology, carry out pressing plate
State recognition is studied, and the throwing for accurately identifying Power Secondary pressing plate moves back state, it will help promoted substation operation safety and
Reliability has stronger realistic meaning.
Invention content
The object of the present invention is to provide a kind of transformer substation protection pressure plate state identification methods, can accurately identify transforming plant protecting
Pressing plate throws/state is moved back, effectively solve the problems, such as maloperation when manual inspection.
The technical solution that the present invention takes is:
A kind of transformer substation protection pressure plate state identification method, includes the following steps:
Step 1:Acquire the screen cabinet image of function pressing plate, output clamping, spare pressing plate;
Step 2:According to rgb value to the effective color lump of screen cabinet image zooming-out of acquisition;
Step 3:Gray processing, binary conversion treatment are carried out to gained image, improve the accuracy of pressing plate feature extraction;
Step 4:Morphological scale-space is carried out to binary image, perforated is filled with connected region, in order to carry out
Morphometric analysis;
Step 5:To all connected regions carry out areal analysis, dimension analysis, shape analysis, zoning elemental area,
Zone boundary Pixel Dimensions, region equivalent length-width ratio, and carry out threshold value and combine to compare, determine effective platen region number;
Step 6:Judge whether the effective platen region number filtered out is equal to it is known that if equal in next step, otherwise weighing
It is new to carry out Image Acquisition and repeat the above steps, wherein the effective platen region number identified is treated as effective pressing plate number;
Step 7:To effective platen region, identify that state is moved back in the throwing of each pressing plate according to deflection criterion;
Step 8:According to each regional barycenter effective pressing plate sequence is determined according to sequence from top to bottom, from left to right, into
And it identifies the effective pressing plate of screen cabinet and throws the mark sequence for state of moving back.
In the step 2, the screen cabinet image of acquisition is mostly coloured image, contains different color block areas, different colors
Block region has different rgb values;Wherein, spare platen region is invalid color lump, is displayed in white, effective platen region is effective
Color lump shows red, green, yellow color;By the way that certain RGB threshold decisions are arranged, you can filtered out from the screen cabinet image of acquisition
Color block areas is imitated, while R, G, B of the non-effective color block areas in image are set as equal value, i.e., background is set as black;This
When, other elements, mark and light, shooting angle disturbing factor on picture can cause the non-platen region in part to be divided into
Effective color lump.
In the step 3, after filtering out effective color block areas, for ease of extracting correlated characteristic information, image is carried out
Gray processing processing, and then inquire into binary-state threshold, the gray level image based on 0~255 brightness degree of the threshold value pair carries out image
Binaryzation obtains remaining to the whole binary image with local feature of reflection image.
The step 4 expands step 3 gained binary picture, burn into is opened, arrangement for closed configuration processing, realizes side
Boundary smooths, and perforated is filled with connected region, in order to carry out Morphometric analysis.
All connected regions that the step 5 obtains step 4 carry out areal analysis under pixel meaning, dimension analysis,
Shape analysis;
The areal analysis:By finding have to the two-value map analysis comprising effective platen region and background interference region
The elemental area size of effect pressing plate is stood out, and considers that there may be carried on the back caused by illumination, shooting angle, screen cabinet other identifier
It is smaller that scape interference region and part effectively pressing plate correspond to color lump, is defined as follows the effective platen region screening of area threshold progress:
Wherein, Area (i) is the arrangement according to region area from big to small, which is:The big float of elemental area
In first 5 region area average value, multiplied by using 0.3 as nargin is judged, elemental area is more than threshold value Threshold_Area
Region can be considered alternative effective platen region, be otherwise considered as background interference region.
The dimension analysis:Since effective pressing plate tool has the dimensions, corresponding region should be occupied certain on the image
Pixel ratio, i.e. zone boundary have certain ratio with image in the pixel size of X, Y-direction respectively along X, Y length for tieing up direction
Value.For this purpose, being defined as follows Pixel Dimensions threshold value:
Threshold_Xwidth=Pixel_Xmax/100
Threshold_Ywidth=Pixel_Ymax/100
Wherein, Pixel_Xmax、Pixel_YmaxRespectively image is in X, the pixel of Y-direction, if zone boundary is along X, the side Y
To length be all higher than corresponding threshold value, then the region is alternative effective platen region, is otherwise considered as background interference region.
The shape analysis, since effective pressing plate has certain shape, corresponding region has certain etc. on the image
Length-width ratio is imitated, i.e., under pixel meaning, there is the ratio of the transverse and minor axis length of identical standard second-order moment around mean with region,
To extract effective platen region, it is defined as follows aspect ratio threshold value:
Threshold_RatioShape=2
Even the corresponding equivalent length and width ratio in region is more than 2, then the region is alternative effective platen region, is otherwise considered as the back of the body
Scape interference region;
By above-mentioned three kinds of morphological analyses, it is final effectively pressing plate area that can be classified as alternative effectively platen region simultaneously
Otherwise domain is considered as background interference region.
Effective pressing plate number that step 6 comparison step 5 filters out, if be equal to it is known that if equal in next step, it is no
It then re-starts Image Acquisition and repeats step 2~step 5.
The step 7 is to identify that state is moved back in effective pressing plate throwing, defines the areas deflection Angle, Ji Yu of pressing plate image-region
Domain has the angle of cut of the elliptical long axis and x-axis of identical standard second-order moment around mean, and when pressing plate puts into state, deflection is ± 90
Degree;When exiting state, deflection is ± 45 degree;State is moved back in throwing for the effective pressing plate of accurate judgement, and considers to shield cabinet Image Acquisition
Certain judgement nargin is arranged in the influence of angle offset, takes ± 10 degree, it is as follows that state State identical criterions are moved back in the throwing of gained pressing plate:
The step 8, according to each regional barycenter, effectively according to 5 gained of order determination step from top to bottom, from left to right
The sequence of pressing plate, and then obtain the mark sequence that the effective pressing plate of screen cabinet throws state of moving back 1 be input, 0 is to exit.
The present invention provides a kind of transformer substation protection pressure plate state identification method, has the beneficial effect that:
1) morphological features such as elemental area, Pixel Dimensions, equivalent length-width ratio and the deflection of pressing plate, are taken full advantage of, with
Realization fully describes effective pressing plate state.
2), by carrying out the setting analysis of joint threshold value in terms of elemental area, Pixel Dimensions, equivalent length-width ratio etc. three come really
Fixed effective platen region number effectively reduces on screen cabinet the disturbing factors such as other elements and light, shooting angle to identification
The influence of effect.
3), the method for the present invention effective integration advantage of image procossing and Morphometric analysis improves the knowledge of pressing plate state
Other precision, application example show that institute's extracting method has preferable state recognition effect.
Description of the drawings
Fig. 1 is the pressing plate state recognition particular flow sheet of the embodiment of the present invention.
Fig. 2 is that status diagram is moved back in the pressing plate throwing of the embodiment of the present invention.
Fig. 3 is collected substation secondary screen cabinet pressing plate image in the embodiment of the present invention.
Fig. 4 is that the collected effective color lump of substation secondary screen cabinet pressing plate image extracts result figure in the embodiment of the present invention.
Fig. 5 is collected substation secondary screen cabinet pressing plate image gray processing, binaryzation result figure in the embodiment of the present invention.
Fig. 6 is collected substation secondary screen cabinet pressing plate morphological image process result figure in the embodiment of the present invention.
Specific implementation mode
The present invention is described in further details in the following with reference to the drawings and specific embodiments.Being given for example only property of attached drawing is said
It is bright, it is not equal to the limitation to this patent.For same domain worker, the part known features and related description of attached drawing are omited
There is omission, cannot limit the scope of the invention accordingly.
A kind of transformer substation protection pressure plate state identification method, as shown in Figure 1, including the following steps:
Step 1:Acquisition comprising functional pressing plate, output clamping, spare pressing plate screen cabinet image.
Step 2:According to rgb value to acquiring the effective color lump of image zooming-out.
Step 3:Gray processing, binary conversion treatment are carried out to gained image, and then improve the accuracy of pressing plate feature extraction.
Step 4:Morphological scale-space is carried out to binary image, perforated is filled with connected region, in order to carry out
Morphometric analysis.
Step 5:To all connected regions carry out areal analysis, dimension analysis, shape analysis, zoning elemental area,
Zone boundary Pixel Dimensions, region equivalent length-width ratio etc., and carry out threshold value and combine to compare, determine effective platen region number.
Step 6:Judge whether the effective platen region number filtered out is equal to it is known that if equal in next step, otherwise weighing
It is new to carry out Image Acquisition and repeat the above steps, wherein the effective platen region number identified is treated as effective pressing plate number.
Step 7:State is moved back in the throwing of each pressing plate to be identified according to deflection criterion to effective platen region.
Step 8:According to each regional barycenter, effective pressing plate sequence is determined according to sequence from top to bottom, from left to right, in turn
Identify that the effective pressing plate of screen cabinet throws the mark sequence for state of moving back.
The screen cabinet image that the step 2 acquires is mostly coloured image, and containing different color block areas (has different
Rgb value), wherein spare platen region is invalid color lump (white), effective platen region is effective color lump (red, green, yellow color).It is logical
It crosses and certain RGB threshold decisions is set, you can filter out effective color block areas from acquisition image, while non-in image being had
R, G, B of effect color block areas are set as equal value, i.e., background are set as black.At this point, other elements, mark and light on picture
The disturbing factors such as line, shooting angle can cause the non-platen region in part to be divided into effective color lump.
The step 3 is after filtering out effective color block areas, and for ease of extracting correlated characteristic information, gray scale is carried out to image
Change is handled, and then inquires into binary-state threshold.Gray level image based on 0~255 brightness degree of the threshold value pair carries out image two-value
Change, obtains remaining to the whole binary image with local feature of reflection image.
The Morphological scale-spaces such as the step 4 expands step 3 gained binary picture, burn into is opened, is closed, are realized
Edge smoothing, and perforated is filled with connected region, in order to carry out Morphometric analysis.
All connected regions that the step 5 obtains step 4 carry out areal analysis under pixel meaning, dimension analysis,
Shape analysis.
1), areal analysis.By being found to the two-value map analysis comprising effective platen region and background interference region, effectively
Elemental area (the pixel total number in region) size of pressing plate is stood out.Consider that there may be because of illumination, shooting angle, screen cabinet
It is smaller that background interference region caused by other identifier etc. and part effectively pressing plate correspond to color lump, is defined as follows area threshold and carries out
Effective platen region screening:
Wherein, Area (i) is the arrangement according to region area from big to small.The threshold value meaning is:The big float of elemental area
In first 5 region area average value, multiplied by using 0.3 as judging nargin.Elemental area is more than threshold value Threshold_Area
Region can be considered alternative effective platen region, be otherwise considered as background interference region.
2), dimension analysis.Since effective pressing plate tool has the dimensions, corresponding region should occupy certain picture on the image
Plain ratio, i.e. zone boundary tie up pixel size of the length (pixel) in direction respectively with image in X, Y-direction along X, Y to be had centainly
Ratio.For this purpose, being defined as follows Pixel Dimensions threshold value:
Threshold_Xwidth=Pixel_Xmax/100
Threshold_Ywidth=Pixel_Ymax/100
Wherein, Pixel_Xmax、Pixel_YmaxRespectively image is in X, the pixel of Y-direction.If zone boundary is along X, the side Y
To length be all higher than corresponding threshold value, then the region is alternative effective platen region, is otherwise considered as background interference region.
3), shape analysis.Since there is effective pressing plate certain shape, corresponding region to have centainly equivalent on the image
Length-width ratio that is, under pixel meaning, has the ratio of the transverse and minor axis length of identical standard second-order moment around mean with region, is
Extract effective platen region.It is defined as follows aspect ratio threshold value:
Threshold_RatioShape=2
Even the corresponding equivalent length and width ratio in region is more than 2, then the region is alternative effective platen region, is otherwise considered as the back of the body
Scape interference region.
By above-mentioned three kinds of morphological analyses, it is final effectively pressing plate area that can be classified as alternative effectively platen region simultaneously
Otherwise domain is considered as background interference region.
Effective pressing plate number that step 6 comparison step 5 filters out whether be equal to it is known that if equal in next step, it is no
It then re-starts Image Acquisition and repeats step 2~step 5.
The step 7 is to identify that state is moved back in effective pressing plate throwing, defines the areas deflection Angle, Ji Yu of pressing plate image-region
Domain has the angle of cut of the elliptical long axis and x-axis of identical standard second-order moment around mean.When pressing plate puts into state, deflection is ± 90
Degree;When exiting state, deflection is ± 45 degree.As shown in Figure 2.State is moved back in throwing for the effective pressing plate of accurate judgement, and considers to shield
The influence of cabinet image capturing angle offset, is arranged certain judgement nargin, takes ± 10 degree, the throwing of gained pressing plate is moved back state State and known
Other criterion is as follows:
The step 8 is according to each regional barycenter, effectively according to 5 gained of order determination step from top to bottom, from left to right
The sequence of pressing plate, and then obtain the mark sequence that the effective pressing plate of screen cabinet throws state of moving back 1 be input, 0 is to exit.
Invention is made with reference to certain collected substation secondary screen cabinet pressing plate image recognition example further detailed
Explanation.
Embodiment:
Certain collected substation secondary screen cabinet pressing plate image resolution ratio is 1280x960 pixels in this example, horizontal and vertical
Straight resolution ratio is 96dpi, as shown in Figure 3.As seen from the figure, shield and contain 14 effective pressing plates on cabinet, corresponding characterization on off state
It is 11100111011000 to identify sequence.Effective color lump part therein is extracted by the rgb value of image, and rest part is set
For black matrix, the results are shown in Figure 4, and then carries out binaryzation to it, and acquired results are as shown in Figure 5.As shown in Figure 5, due to image
Resolution ratio is relatively low and shooting angle reason, lead to that the effective pressing plate area extracted is different and boundary is more irregular.Based on shape
State method carries out holes filling, and gained image is as shown in Figure 6.
The morphological feature of all areas is calculated the binaryzation result figure after gained holes filling, and according to institute's pressure-raising plate
Effective platen region, the number (No) of corresponding region, the pixel total number (Area) in each region, side are therefrom selected in state recognition methods
Boundary along X dimensions direction length (Xwidth), boundary along Y dimensions direction length (Ywidth), with region have identical standard
Elliptical long axis length (the A of second-order moment around meanmajor) and elliptical minor axis length of the region with identical standard second-order moment around mean
(Aminor) etc. morphological features be shown in Table 1.
The morphological feature of 1 effective platen region of table
As shown in Table 1, the effective platen region number identified is equal with effective pressing plate number to be identified, is 14,
Further calculate the angle of cut (deflection of the elliptical long axis and x-axis that there is identical standard second-order moment around mean with each effective coverage
) and corresponding position of centre of gravity (X Anglecore、Ycore), it is shown in Table 2.It brings all directions angle into pressing plate throwing and moves back state recognition criterion
In, identify that state (State) is moved back in the throwing of effective platen region, further according to each effective platen region center of gravity according to from up to
Under, sequence from left to right effective pressing plate is sorted, gained number order is:#2,#6,#20,#23,#40,#36,#42,#1,#
4, #15, #30, #35, #41, #29, it is 11100111011000 that status switch is moved back in corresponding throwing.The effective pressing plate status switch of gained with
Known completely the same, i.e., institute's extracting method has been recognized accurately the throwings of all effective pressing plates and has moved back state.
The deflection and center of gravity of 2 effective pressing plate of table
Claims (8)
1. a kind of transformer substation protection pressure plate state identification method, it is characterised in that include the following steps:
Step 1:Acquire the screen cabinet image of function pressing plate, output clamping, spare pressing plate;
Step 2:According to rgb value to the effective color lump of screen cabinet image zooming-out of acquisition;
Step 3:Gray processing, binary conversion treatment are carried out to gained image, improve the accuracy of pressing plate feature extraction;
Step 4:Morphological scale-space is carried out to binary image, perforated is filled with connected region, in order to carry out form
Signature analysis;
Step 5:Areal analysis, dimension analysis, shape analysis, zoning elemental area, region are carried out to all connected regions
Boundary pixel size, region equivalent length-width ratio, and carry out threshold value and combine to compare, determine effective platen region number;
Step 6:Judge whether effective platen region number for filtering out is equal to it is known that if equal in next step, otherwise again into
Row Image Acquisition simultaneously repeats the above steps, wherein the effective platen region number identified is treated as effective pressing plate number;
Step 7:To effective platen region, identify that state is moved back in the throwing of each pressing plate according to deflection criterion;
Step 8:According to each regional barycenter effective pressing plate sequence, Jin Ershi are determined according to sequence from top to bottom, from left to right
Do not go out to shield the mark sequence that the effective pressing plate of cabinet throws state of moving back.
2. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
In the step 2, the screen cabinet image of acquisition is mostly coloured image, contains different color block areas, different color lump areas
Domain has different rgb values;Wherein, spare platen region is invalid color lump, is displayed in white, and effective platen region is effective color
Block shows red, green, yellow color;By the way that certain RGB threshold decisions are arranged, you can filtered out from the screen cabinet image of acquisition effectively
Color block areas, while R, G, B of the non-effective color block areas in image are set as equal value, i.e., background is set as black;At this point,
Other elements, mark and light, shooting angle disturbing factor on picture, can cause the non-platen region in part to be divided into effectively
Color lump.
3. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
In the step 3, after filtering out effective color block areas, for ease of extracting correlated characteristic information, gray scale is carried out to image
Change is handled, and then inquires into binary-state threshold, and the gray level image based on 0~255 brightness degree of the threshold value pair carries out image two-value
Change, obtains remaining to the whole binary image with local feature of reflection image.
4. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
The step 4 expands step 3 gained binary picture, burn into is opened, arrangement for closed configuration processing, realizes that boundary is flat
Cunningization, and perforated is filled with connected region, in order to carry out Morphometric analysis.
5. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
Areal analysis, dimension analysis under all connected regions progress pixel meaning that the step 5 obtains step 4, shape
Analysis;
The areal analysis:By being found to the two-value map analysis comprising effective platen region and background interference region, effectively press
The elemental area size of plate is stood out, and considers that there may be the background caused by illumination, shooting angle, screen cabinet other identifier is dry
Disturbing region and part effectively pressing plate, to correspond to color lump smaller, is defined as follows the effective platen region screening of area threshold progress:
Wherein, Area (i) is the arrangement according to region area from big to small, which is:Elemental area size comes preceding 5
The region area average value of position, multiplied by using 0.3 as judging nargin, region of the elemental area more than threshold value Threshold_Area
It can be considered alternative effective platen region, be otherwise considered as background interference region;
The dimension analysis:Since effective pressing plate tool has the dimensions, corresponding region should occupy certain pixel on the image
Than that is, pixel size of the length in direction respectively with image in X, Y-direction is tieed up in zone boundary along X, Y has certain ratio;For
This, is defined as follows Pixel Dimensions threshold value:
Threshold_Xwidth=Pixel_Xmax/100
Threshold_Ywidth=Pixel_Ymax/100
Wherein, Pixel_Xmax、Pixel_YmaxRespectively image is in X, the pixel of Y-direction, if zone boundary is along X, Y-direction
Length is all higher than corresponding threshold value, then the region is alternative effective platen region, is otherwise considered as background interference region;
The shape analysis, since there is effective pressing plate certain shape, corresponding region to have certain equivalent length on the image
Wide ratio that is, under pixel meaning, has the ratio of the transverse and minor axis length of identical standard second-order moment around mean with region, to carry
Effective platen region is taken, aspect ratio threshold value is defined as follows:
Threshold_RatioShape=2
Even the corresponding equivalent length and width ratio in region is more than 2, then the region is alternative effective platen region, and it is dry to be otherwise considered as background
Disturb region;
By above-mentioned three kinds of morphological analyses, it is final effective platen region that can be classified as alternative effectively platen region simultaneously, no
Then it is considered as background interference region.
6. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
Whether effective pressing plate number that step 6 comparison step 5 filters out is equal to it is known that if equal in next step, otherwise weighing
It is new to carry out Image Acquisition and repeat step 2~step 5.
7. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
The step 7 is to identify that state is moved back in effective pressing plate throwing, defines the deflection Angle of pressing plate image-region, i.e., has with region
There are the elliptical long axis of identical standard second-order moment around mean and the angle of cut of x-axis, when pressing plate puts into state, deflection is ± 90 degree;It moves back
When doing well, deflection is ± 45 degree;State is moved back in throwing for the effective pressing plate of accurate judgement, and considers that screen cabinet image capturing angle is inclined
Certain judgement nargin is arranged in the influence of shifting, takes ± 10 degree, it is as follows that state State identical criterions are moved back in the throwing of gained pressing plate:
8. a kind of transformer substation protection pressure plate state identification method according to claim 1, it is characterised in that:
The step 8, according to each regional barycenter, according to the 5 effective pressing plate of gained of order determination step from top to bottom, from left to right
Sequence, and then obtain the mark sequence that the effective pressing plate of screen cabinet throws state of moving back, 1 be input, 0 be to exit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810502596.3A CN108805038B (en) | 2018-05-23 | 2018-05-23 | Transformer substation protection pressing plate state identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810502596.3A CN108805038B (en) | 2018-05-23 | 2018-05-23 | Transformer substation protection pressing plate state identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108805038A true CN108805038A (en) | 2018-11-13 |
CN108805038B CN108805038B (en) | 2021-06-04 |
Family
ID=64091499
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810502596.3A Active CN108805038B (en) | 2018-05-23 | 2018-05-23 | Transformer substation protection pressing plate state identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108805038B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109687382A (en) * | 2018-12-13 | 2019-04-26 | 广东电网有限责任公司 | It is a kind of based on color stencil matching relay-protection pressing plate throwing move back state identification method |
CN110148107A (en) * | 2019-02-26 | 2019-08-20 | 国网安徽省电力有限公司铜陵供电公司 | Protection pressing plate state identification method based on chromacity distortions Yu phase Competition coding |
CN110675397A (en) * | 2019-10-14 | 2020-01-10 | 国网山东省电力公司泰安供电公司 | Transformer substation protection pressing plate state checking method |
CN111191721A (en) * | 2019-12-30 | 2020-05-22 | 国网浙江省电力有限公司宁波供电公司 | Protection pressing plate state identification method based on AI technology |
CN111242869A (en) * | 2020-01-17 | 2020-06-05 | 广东驰行电力设备有限公司 | Method for filtering background of photo |
CN112733957A (en) * | 2021-01-21 | 2021-04-30 | 广东电网有限责任公司 | Transformer substation protection pressing plate state checking method, device, equipment and storage medium |
CN113096120A (en) * | 2021-04-30 | 2021-07-09 | 随锐科技集团股份有限公司 | Method and system for identifying on-off state of protection pressing plate |
CN116778407A (en) * | 2023-05-17 | 2023-09-19 | 国网江苏省电力有限公司南通供电分公司 | Identification analysis method and device for automatically identifying state of device in transformer substation protection screen |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030054543A1 (en) * | 1997-06-16 | 2003-03-20 | Lafferty William Michael | Device for moving a selected station of a holding plate to a predetermined location for interaction with a probe |
CN103413130A (en) * | 2013-07-25 | 2013-11-27 | 中国农业大学 | Recognition method of protection pressing plate state |
CN105828049A (en) * | 2016-05-20 | 2016-08-03 | 国网山东省电力公司日照供电公司 | Intelligent remote viewing system of transformer substation |
CN107527344A (en) * | 2017-09-18 | 2017-12-29 | 广东电网有限责任公司珠海供电局 | A kind of relay-protection pressing plate condition detecting system and detection method |
-
2018
- 2018-05-23 CN CN201810502596.3A patent/CN108805038B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030054543A1 (en) * | 1997-06-16 | 2003-03-20 | Lafferty William Michael | Device for moving a selected station of a holding plate to a predetermined location for interaction with a probe |
CN103413130A (en) * | 2013-07-25 | 2013-11-27 | 中国农业大学 | Recognition method of protection pressing plate state |
CN105828049A (en) * | 2016-05-20 | 2016-08-03 | 国网山东省电力公司日照供电公司 | Intelligent remote viewing system of transformer substation |
CN107527344A (en) * | 2017-09-18 | 2017-12-29 | 广东电网有限责任公司珠海供电局 | A kind of relay-protection pressing plate condition detecting system and detection method |
Non-Patent Citations (2)
Title |
---|
HONGMIN ZHU等: "《Real-Time State Analysis of Digitron and Press Plate in Transformer Substations》", 《 2016 9TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN》 * |
许超 等: "《基于模型聚类匹配和形态特征识别的保护压板状态辨识技术》", 《陕西电力》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109687382A (en) * | 2018-12-13 | 2019-04-26 | 广东电网有限责任公司 | It is a kind of based on color stencil matching relay-protection pressing plate throwing move back state identification method |
CN109687382B (en) * | 2018-12-13 | 2020-04-14 | 广东电网有限责任公司 | Relay protection pressing plate switching state identification method based on color template matching |
CN110148107A (en) * | 2019-02-26 | 2019-08-20 | 国网安徽省电力有限公司铜陵供电公司 | Protection pressing plate state identification method based on chromacity distortions Yu phase Competition coding |
CN110148107B (en) * | 2019-02-26 | 2023-07-11 | 国网安徽省电力有限公司铜陵供电公司 | Protection pressing plate state identification method based on chromatic aberration and phase competition coding |
CN110675397A (en) * | 2019-10-14 | 2020-01-10 | 国网山东省电力公司泰安供电公司 | Transformer substation protection pressing plate state checking method |
CN110675397B (en) * | 2019-10-14 | 2023-03-28 | 国网山东省电力公司泰安供电公司 | Transformer substation protection pressing plate state checking method |
CN111191721A (en) * | 2019-12-30 | 2020-05-22 | 国网浙江省电力有限公司宁波供电公司 | Protection pressing plate state identification method based on AI technology |
CN111242869A (en) * | 2020-01-17 | 2020-06-05 | 广东驰行电力设备有限公司 | Method for filtering background of photo |
CN111242869B (en) * | 2020-01-17 | 2023-04-28 | 广东驰行电力设备有限公司 | Method for background filtering of photo |
CN112733957A (en) * | 2021-01-21 | 2021-04-30 | 广东电网有限责任公司 | Transformer substation protection pressing plate state checking method, device, equipment and storage medium |
CN113096120A (en) * | 2021-04-30 | 2021-07-09 | 随锐科技集团股份有限公司 | Method and system for identifying on-off state of protection pressing plate |
CN116778407A (en) * | 2023-05-17 | 2023-09-19 | 国网江苏省电力有限公司南通供电分公司 | Identification analysis method and device for automatically identifying state of device in transformer substation protection screen |
Also Published As
Publication number | Publication date |
---|---|
CN108805038B (en) | 2021-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108805038A (en) | A kind of transformer substation protection pressure plate state identification method | |
CN105741291B (en) | A kind of high-speed railway touching net suspension arrangement equipotential line fault detection method | |
CN104851085B (en) | The automatic method and system for obtaining detection zone in image | |
CN101403703B (en) | Real-time detection method for foreign fiber in lint | |
CN106296666B (en) | A kind of color image removes shadow method and application | |
CN105354530B (en) | A kind of body color recognition methods and device | |
Quan et al. | The method of the road surface crack detection by the improved Otsu threshold | |
CN105205489B (en) | Detection method of license plate based on color and vein analyzer and machine learning | |
CN102663358B (en) | Video image identification method of operating state of secondary protection equipment of substation | |
WO2020224458A1 (en) | Method for detecting corona discharge employing image processing | |
CN106384117B (en) | A kind of vehicle color identification method and device | |
CN109859171A (en) | A kind of flooring defect automatic testing method based on computer vision and deep learning | |
CN102226907A (en) | License plate positioning method and apparatus based on multiple characteristics | |
CN110458821A (en) | A kind of sperm morphology analysis method based on deep neural network model | |
CN103745226A (en) | Dressing safety detection method for worker on working site of electric power facility | |
CN104036262B (en) | A kind of method and system of LPR car plates screening identification | |
CN106680285A (en) | Infrared image-assisted method of recognizing contamination condition of insulator by visible light image | |
CN109086687A (en) | The traffic sign recognition method of HOG-MBLBP fusion feature based on PCA dimensionality reduction | |
CN101251898A (en) | Skin color detection method and apparatus | |
CN108268832A (en) | Electric operating monitoring method, device, storage medium and computer equipment | |
CN106529592A (en) | License plate recognition method based on mixed feature and gray projection | |
CN105894015B (en) | A kind of banister state analysis method and system | |
CN106650752A (en) | Vehicle body color recognition method | |
CN103218615A (en) | Face judgment method | |
CN102980659A (en) | Digitalized characterization method of monochrome tight fabric surface color |
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 |