CN112508940B - Method for identifying switching state of functional protection pressing plate of transformer substation - Google Patents
Method for identifying switching state of functional protection pressing plate of transformer substation Download PDFInfo
- Publication number
- CN112508940B CN112508940B CN202011533308.4A CN202011533308A CN112508940B CN 112508940 B CN112508940 B CN 112508940B CN 202011533308 A CN202011533308 A CN 202011533308A CN 112508940 B CN112508940 B CN 112508940B
- Authority
- CN
- China
- Prior art keywords
- pressing plate
- state
- image
- identifying
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000011218 segmentation Effects 0.000 claims abstract description 28
- 230000000877 morphologic effect Effects 0.000 claims abstract description 22
- 238000007500 overflow downdraw method Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 22
- 238000003064 k means clustering Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 239000006002 Pepper Substances 0.000 claims description 3
- 235000002566 Capsicum Nutrition 0.000 claims description 2
- 235000016761 Piper aduncum Nutrition 0.000 claims description 2
- 235000017804 Piper guineense Nutrition 0.000 claims description 2
- 244000203593 Piper nigrum Species 0.000 claims description 2
- 235000008184 Piper nigrum Nutrition 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims description 2
- 150000003839 salts Chemical class 0.000 claims description 2
- 230000002401 inhibitory effect Effects 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000005286 illumination Methods 0.000 abstract description 2
- 238000003702 image correction Methods 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000282836 Camelus dromedarius Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The method for identifying the switching state of the functional protection pressing plate of the transformer substation comprises the following steps: collecting a color image of a screen cabinet containing all pressing plates; intercepting a pressing plate area and carrying out image correction; extracting an effective pressing plate area by adopting a multi-strategy segmentation and fusion method; and acquiring the direction angle and width-length ratio morphological characteristics of the effective pressing plate in the target area, and identifying the on-off state of the pressing plate. The method solves the problems of image distortion caused by the photographing angle and low recognition rate caused by complicated screen background and shadow generated under the influence of illumination. The method and the device can accurately and quickly identify the pressing plate on-off state under various complex background interferences, effectively improve the operation and maintenance work efficiency of the transformer substation, and are beneficial to reducing potential safety hazards.
Description
Technical Field
The invention relates to the technical field of power equipment state identification, in particular to a method for identifying the switching-on and switching-off states of a functional protection pressing plate of a transformer substation.
Background
With the rapid development of economy, the demand of society on electric energy is increasing, and higher requirements are put forward on the operation and maintenance of a transformer substation. In order to ensure the safe and stable operation of the transformer substation, the work state of the secondary equipment of the transformer substation is regularly patrolled and examined. The protection pressing plate is used as important content of the routing inspection of secondary equipment, and the requirement of intellectualization is difficult to meet by means of traditional manual detection. And the manual inspection often has the phenomenon of wrong detection and missed detection due to visual fatigue, memory errors and the like, so that potential safety hazards exist. Therefore, a transformer substation protection pressing plate switching state identification method based on a new technology is developed, and the establishment of a transformer substation intelligent operation and maintenance system deployment scheme is urgent. At present, certain research is carried out on the state identification of the intelligent substation protection pressing plate based on image processing, but the current research usually ignores the segmentation of the pressing plate image, particularly the pressing plate image with large background interference, and is difficult to ensure higher identification accuracy. Therefore, the method for reliably segmenting and identifying the functional protection pressing plate image of the transformer substation has important theoretical and practical significance.
Disclosure of Invention
In order to solve the problems of image distortion caused by a photographing angle and low identification rate caused by complicated screen background, shadow generation caused by illumination and the like, the invention provides the method for identifying the switching-on/off state of the functional protection pressing plate of the transformer substation, which can accurately and quickly identify the switching-on/off state of the pressing plate under various complicated background interferences, effectively improves the operation and maintenance work efficiency of the transformer substation and is beneficial to reducing potential safety hazards.
The technical scheme adopted by the invention is as follows:
the method for identifying the switching state of the functional protection pressing plate of the transformer substation comprises the following steps:
s1: collecting a screen cabinet color image containing all pressing plates through mobile terminal equipment;
s2: preprocessing the collected color image, and intercepting and correcting a pressing plate area in the image;
s3: extracting an effective pressing plate area based on a multi-strategy segmentation and fusion method of multi-threshold and K-means clustering, and performing morphological processing;
s4: and calculating the direction angle and width-length ratio morphological characteristics of the effective pressing plate area, respectively identifying the pressing plate states corresponding to the two characteristics, and fusing the results of the two pressing plate states to determine the final on-off state of the pressing plate.
S2 includes the steps of:
s 21: preprocessing the collected color image, and marking four vertexes of a quadrangle containing all the pressing plate areas;
s 22: intercepting a quadrilateral area containing all the pressing plates, and removing an invalid area of the screen cabinet;
s 23: and correcting the pressure plate area by adopting perspective transformation.
S3 includes the steps of:
s 31: respectively converting the corrected pressing plate image into an HSV color space and a Lab color space;
s 32: performing multi-threshold segmentation on the HSV color space platen image, and performing K-means clustering segmentation on the Lab color space platen image;
s 33: firstly, performing median filtering on a processing result graph of two segmentation modes, and then performing region fusion to obtain a complete effective pressing plate region;
s 34: the noise and small connected regions are removed by morphological processing of the effective platen area.
s31 includes the steps of:
s 311: converting the RGB color space pressing plate image into HSV color space, and calculating the H component value of the HSV color space pressing plate image according to the formula (1), wherein the formula (1) is as follows:
in the formula: r, G, B are red, green and blue channel values, max is the maximum value of R, G, B, min is the minimum value of R, G, B;
s 312: the RGB color space platen image is converted to Lab color space.
s32 includes the steps of:
s 321: segmenting the HSV color space platen image using a multi-threshold method, wherein: the minimum value of the H component is 0.01, the maximum value is 0.1, and a red characteristic pressing plate area is obtained;
s 322: and (4) segmenting the Lab color space pressing plate image by using a K-means clustering method to obtain yellow and green characteristic pressing plate areas.
Step s33 includes the following steps:
s 331: firstly, adding salt-pepper noise to an image processed by two segmentation methods of multi-threshold value clustering and K-means clustering, and then denoising by using a median filtering processing mode;
s 332: and fusing the effective color characteristic pressing plate area after filtering treatment to obtain a complete effective pressing plate area.
s34 includes the steps of:
s 341: performing open operation by adopting linear structural elements with the length of 5 and the angle of 90 degrees to remove linear interference areas;
s 342: performing closed operation by using a circular structural element with the radius of 3 to remove burrs and isolated points;
s 343: and performing expansion treatment on the circular structural element with the radius of 2, and filling holes in the target area, so that depth noise is inhibited, depth missing holes are filled, and the quality of the target area is improved.
S4 includes the steps of:
s 41: extracting the direction angle and width-length ratio morphological characteristics of an effective pressing plate area in the image, and identifying pressing plate on-off states respectively corresponding to the two morphological characteristics;
s 42: and fusing the results of the two states to determine the final on-off state of the pressing plate.
s41 includes the steps of:
s 411: substituting the acquired direction angle state characteristics into a formula (2) for calculation, identifying the pressing plate in and out state, recording the in state as 1 and the out state as 0, and recording the formula (2) as follows:
in the formula: vsIn the state of pressing plate, VoIs the pressing plate direction angle;
s 412: substituting the acquired width-length ratio morphological characteristics into a formula (3) for calculation, identifying the pressing plate on-off state, recording the on-off state as 1 and the off-off state as 0, wherein the formula (3) is as follows:
in the formula: vsIn the state of pressing plate, VaIs the width-to-length ratio of the platen area.
s42 includes the steps of:
s 421: and (3) fusing the shape feature identification results of the direction angle and the width-length ratio of the pressing plate, and determining the final on-off state of the pressing plate by using a formula (4), wherein the on-off state is marked as 1, the off-off state is marked as 0, and the formula (4) is as follows:
in the formula: vsIn the state of pressing plate, Vs1As a result of the feature identification of the orientation angle, Vs2The result is the form feature identification result of the width-length ratio;
s 422: verifying the identified pressing plate on-off state result and outputting a pressing plate state identification code.
The invention discloses a method for identifying the switching state of a functional protection pressing plate of a transformer substation, which has the beneficial effects that:
1) the method for identifying the switching-on and switching-off states of the functional protection pressing plate of the transformer substation effectively solves distortion influence caused by shooting angles, can accurately identify the switching-on and switching-off states of the pressing plate under various complex background interferences, and has important theoretical and practical significance for intelligent routing inspection of the protection pressing plate of the transformer substation.
2) In addition, the multi-strategy segmentation and fusion processing method provided by the invention is not only suitable for the segmentation of the pressing plate image, but also has important reference value for the segmentation of other types of images.
3) In the aspect of identifying the state of the pressing plate, the invention adopts multi-feature identification fusion, and compared with a method for identifying the state of the pressing plate by using a single feature, the invention effectively improves the identification reliability.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a flow chart of the segmentation method of the present invention.
FIG. 3 is a flowchart illustrating a state identification method according to the present invention.
Fig. 4 is a diagram of a protection pressing plate of a substation cabinet.
FIG. 5 is a graph of the apex markers of a quadrilateral encompassing all of the platen areas.
FIG. 6 is a quadrilateral area encompassing all of the platens.
Fig. 7 is a graph showing the result of the correction processing.
Fig. 8 is an HSV color space platen image.
Fig. 9 is Lab color space platen image.
Fig. 10 is a diagram showing the result of the multi-threshold segmentation process.
Fig. 11 is a graph of the results of the K-means clustering segmentation process.
FIG. 12 is a graph of the complete effective platen area results.
Fig. 13 is a graph showing the results of morphological processing.
Detailed Description
For the understanding of those skilled in the art, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments thereof:
the embodiment of the invention provides a method for identifying the switching state of a functional protection pressing plate of a transformer substation, which comprises the following steps of:
s1: shooting a color image of the screen cabinet containing all the pressing plates through the mobile terminal equipment;
the mobile terminal equipment adopts a mobile inspection robot or a handheld inspection instrument.
S2: preprocessing the obtained image, extracting and correcting an image pressing plate area, and solving the distortion problem caused by the photographing angle;
s3: extracting an effective pressing plate area based on a multi-strategy segmentation and fusion method of multi-threshold and K-means clustering, and performing morphological processing;
s4: and calculating the direction angle and width-length ratio morphological characteristics of the effective pressing plate area, further respectively identifying the pressing plate states corresponding to the two characteristics, and fusing the results of the two states to determine the final on-off state of the pressing plate.
The step S2 includes the following steps:
s 21: the resulting image is labeled platen area for FIG. 4, which contains the four vertices of the quadrilateral for all platen areas, as shown in FIG. 5;
s 22: intercepting a quadrilateral area containing all the pressing plates, wherein the quadrilateral frame contains all the pressing plates including red, green and yellow effective pressing plates, invalid pressing plates with other colors and a background as shown in FIG. 6; the outer side of the quadrilateral frame, such as a pressing plate label, a screen cabinet boundary, the ground and the like, is an invalid area;
s 23: when gathering screen cabinet clamp plate image, because shoot the visual angle reason, the image that leads to gathering often has certain skew, can realize clamp plate image correction through perspective transform. Obtaining a perspective transformation matrix from the four vertexes of the quadrilateral of the obtained pressing plate areaFurther by the formulaAnd perspective transformation is realized, and rotation and scaling correction of the image of the pressing plate area are completed. Fig. 7 shows the results of correction performed by selecting four vertices of a quadrangle including all the platen regions as input source coordinates, obtaining a perspective transformation matrix, and performing perspective transformation on the obtained matrix.
The step S3 includes the following steps:
s 31: respectively converting the corrected pressing plate image into an HSV color space and a Lab color space; the HSV color space is a color space formed according to the visual characteristics of colors, and because the components of the HSV color space keep relative independence, the HSV color space can well highlight the color characteristics, and has better effect when the specified color is segmented; the Lab color space is an equipment-independent color system and is used for better covering effect on a background part when the specified color is divided, and noise interference can be reduced to the maximum extent;
s 32: performing multi-threshold segmentation on the HSV color space platen image, and performing K-means clustering segmentation on the Lab color space platen image;
s 33: firstly, performing median filtering on a processing result graph of two segmentation modes, and then performing region fusion to obtain a complete effective pressing plate region;
s 34: the noise and small connected regions are removed by morphological processing of the effective platen area.
The step s31 comprises the following steps:
s 311: calling an RGB2HSV function in matlab to convert the RGB color space platen image into an HSV color space, and calculating an H component value of the HSV color space platen image according to a formula (1) in the converted image as shown in fig. 8, wherein the formula (1) is as follows:
in the formula: r, G, B are red, green and blue channel values, max is the maximum value of R, G, B, min is the minimum value of R, G, B;
s 312: and calling the RGB2Lab function in matlab to convert the RGB color space platen image into Lab color space, wherein the converted image is shown in FIG. 9.
The step s32 comprises the following steps:
s 321: the red characteristic pressing plate area, namely the red pressing plate in the screen cabinet image is obtained by using a multi-threshold method, and because the color of the red characteristic pressing plate area is similar to that of a background frame, an ideal segmentation effect is difficult to obtain by using a conventional method; considering that the correlation of each component in the Lab color space is weak, the HSV color space platen image is segmented by multi-threshold segmentation, wherein the minimum value of the H component is 0.01, the maximum value of the H component is 0.1, a red characteristic platen area is segmented and binarized, and the obtained result is shown in figure 10;
s 322: dividing yellow and green characteristic pressing plate areas, namely yellow and green pressing plates in a screen cabinet image by using a K-means clustering method, wherein the yellow and green pressing plates are easily confused with a camel background, so that more noise areas are generated after division; considering that the Lab color space has a good covering effect on the background part, the K-means clustering segmentation method is used to segment the Lab color space platen image to obtain yellow and green characteristic platen regions and perform binarization, and the obtained result is shown in fig. 11.
The step s33 comprises the following steps:
s 331: after obtaining a binary result image processed by two segmentation methods of multi-threshold value clustering and K-means clustering, in order to prevent the noise area from being enlarged during area fusion, firstly, carrying out denoising processing on the obtained image; adding salt and pepper noise to the images obtained in the step s321 and the step s322, and then denoising by using a median filtering processing mode;
s 332: and fusing the effective color characteristic pressing plate areas after filtering processing, so that the red, green and yellow effective pressing plate areas are fused on the same image, and thus obtaining a complete effective pressing plate area, as shown in fig. 12.
The step s34 comprises the following steps:
s 341: after the complete effective pressing plate area is obtained through the step s33, a noise area and a linear interference area still exist, firstly, a specific linear structural element is adopted to carry out open operation to remove the linear interference area; the length of the arranged linear structure is 5 degrees, the angle is 90 degrees, namely the vertical line segment area with the length of 5 degrees;
s 342: considering that the noise of isolated points cannot be removed by open operation, performing closed operation through a circular structural element to remove burrs and isolated points; the radius of the circular structure is 3, namely a plane disc-shaped area with the radius of 3 is arranged;
s 343: in order to prevent missing isolated points, the circular structural element with the radius of 2 is used for expansion processing, hole filling is carried out on the target area, depth image noise is restrained, depth missing holes are filled, and the quality of the target area is improved; the final effective platen area obtained by the morphological treatment is shown in fig. 13.
The step S4 includes the following steps:
s 41: extracting the direction angle and width-length ratio morphological characteristics of an effective pressing plate area in the image, and identifying pressing plate on-off states respectively corresponding to the two morphological characteristics;
s 42: and fusing the results of the two states to determine the final on-off state of the pressing plate.
The step s41 comprises the following steps:
s 411: substituting the acquired orientation angle state characteristics into a formula (2) to calculate, identifying the pressing plate input and output states, recording the input state as 1, recording the output state as 0, and recording the formula (2) as follows:
in the formula: vsIn the state of pressing plate, VoIs the pressing plate area direction angle;
s 412: substituting the acquired width-length ratio morphological characteristics into a formula (3) for calculation, identifying the pressing plate on-off state, recording the on-off state as 1 and the off-off state as 0, wherein the formula (3) is as follows:
in the formula: vsIn the state of pressing plate, VaIs the width-to-length ratio of the platen area.
The step s42 comprises the following steps:
s 421: and (3) fusing the shape feature identification results of the direction angle and the width-length ratio of the pressing plate, and determining the final on-off state of the pressing plate by using a formula (4), wherein the on-off state is marked as 1, the off-off state is marked as 0, and the formula (4) is as follows:
in the formula: vsIn the state of pressing plate, Vs1As a result of the determination of the direction angle characteristics, Vs2The result is the width-length ratio characteristic judgment result;
s 422: verifying the identified pressing plate on-off state result and outputting a pressing plate state identification code.
The embodiment is as follows:
the screen cabinet platen image collected in this example is shown in fig. 4, and has a resolution of 1920 × 1080 pixels, a horizontal and vertical resolution of 96dpi, and a size of 832 KB. The screen cabinet has 6 rows of pressing plates, each row has 9, and the number of the effective pressing plates in the whole screen is 46. As can be seen from observation, the image of the screen cabinet pressing plate has more invalid areas, the pressing plate area only occupies the middle part, and small-angle distortion also exists. First, a quadrilateral region including all the platens in the image is cut out, and perspective transformation is adopted to correct the quadrilateral region, and the processing result is shown in fig. 7. Then, the images of the segmentation results obtained by the multi-threshold method and the K-means clustering method are respectively segmented, and the complete segmentation result is obtained as shown in FIG. 12. Further, the morphological processing means is used to remove noise interference and perform dilation processing, and the processing result is shown in fig. 13.
Then, the on-off state of the effective pressing plate is identified, firstly, the form characteristics of the direction angle and the width-length ratio of the communication area of the effective pressing plate are extracted, and the on-off state V of the pressing plate corresponding to the two form characteristics is identified according to the formulas (2) and (3)s1And Vs2Then, determining the final on-off state V of the pressing plate according to the formula (4)s. The relevant data are shown in table 1. And a total of 46 effective pressing plates are identified, wherein 18 pressing plates are in the input state, 28 pressing plates are in the exit state, and the identification result is completely consistent with the real input and exit states of the pressing plates in the corresponding areas.
TABLE 1 Multi-feature identification results Table
Claims (9)
1. The method for identifying the switching state of the functional protection pressing plate of the transformer substation is characterized by comprising the following steps of:
s1: collecting a screen cabinet color image containing all pressing plates through mobile terminal equipment;
s2: preprocessing the collected color image, and intercepting and correcting a pressing plate area in the image;
s3: extracting an effective pressing plate area based on a multi-strategy segmentation and fusion method of multi-threshold and K-means clustering, and performing morphological processing;
s3 includes the steps of:
s 31: respectively converting the corrected pressing plate image into an HSV color space and a Lab color space;
s 32: performing multi-threshold segmentation on the HSV color space platen image, and performing K-means clustering segmentation on the Lab color space platen image;
s 33: firstly, performing median filtering on a processing result graph of two segmentation modes, and then performing region fusion to obtain a complete effective pressing plate region;
s 34: removing noise and small communication areas by performing morphological processing on the effective pressing plate area;
s4: and calculating the direction angle and width-length ratio morphological characteristics of the effective pressing plate area, respectively identifying the pressing plate states corresponding to the two characteristics, and fusing the results of the two pressing plate states to determine the final on-off state of the pressing plate.
2. The method for identifying the switching state of the functional protection pressing plate of the transformer substation according to claim 1, characterized in that:
s2 includes the steps of:
s 21: preprocessing the collected color image, and marking four vertexes of a quadrangle including all pressing plate areas;
s 22: intercepting a quadrilateral area containing all the pressing plates, and removing an invalid area of the screen cabinet;
s 23: the platen area is corrected using a perspective transformation.
3. The method for identifying the switching state of the functional protection pressing plate of the transformer substation according to claim 1, characterized in that:
s31 includes the steps of:
s 311: converting the RGB color space pressing plate image into HSV color space, and calculating the H component value of the HSV color space pressing plate image according to the formula (1), wherein the formula (1) is as follows:
in the formula: r, G, B are red, green and blue channel values, max is the maximum value of R, G, B, min is the minimum value of R, G, B;
s 312: the RGB color space platen image is converted to Lab color space.
4. The method for identifying the switching state of the functional protection pressing plate of the transformer substation according to claim 1, characterized in that:
s32 includes the steps of:
s 321: segmenting the HSV color space platen image using a multi-threshold method, wherein: the minimum value of the H component is 0.01, the maximum value is 0.1, and a red characteristic pressing plate area is obtained;
s 322: and (4) segmenting the Lab color space pressing plate image by using a K-means clustering method to obtain yellow and green characteristic pressing plate areas.
5. The method for identifying the switching state of the functional protection pressing plate of the transformer substation according to claim 1, characterized in that:
s33 includes the steps of:
s 331: firstly, adding salt and pepper noise to an image processed by two segmentation methods of multi-threshold value clustering and K-means clustering, and then denoising by using a median filtering processing mode;
s 332: and fusing the effective color characteristic pressing plate area after filtering treatment to obtain a complete effective pressing plate area.
6. The method for identifying the switching state of the functional protection pressing plate of the transformer substation according to claim 1, characterized in that:
s34 includes the steps of:
s 341: performing open operation by adopting linear structural elements with the length of 5 and the angle of 90 degrees to remove linear interference areas;
s 342: performing closed operation by using a circular structural element with the radius of 3 to remove burrs and isolated points;
s 343: and performing expansion treatment by using a circular structural element with the radius of 2, filling holes in the target area, inhibiting depth noise, filling depth missing holes and improving the quality of the target area.
7. The method for identifying the switching state of the functional protection pressing plate of the transformer substation according to claim 1, characterized in that:
s4 includes the steps of:
s 41: extracting the direction angle and width-length ratio morphological characteristics of an effective pressing plate area in the image, and identifying pressing plate on-off states respectively corresponding to the two morphological characteristics;
s 42: and fusing the results of the two states to determine the final on-off state of the pressing plate.
8. The method for identifying the switching-on/off state of the functional protection pressing plate of the transformer substation according to claim 7, characterized in that:
s41 includes the steps of:
s 411: substituting the acquired direction angle state characteristics into a formula (2) for calculation, identifying the pressing plate in and out state, recording the in state as 1 and the out state as 0, and recording the formula (2) as follows:
in the formula: vsIn the state of pressing plate, VoIs the pressing plate direction angle;
s 412: substituting the acquired width-length ratio morphological characteristics into a formula (3) for calculation, identifying the pressing plate on-off state, recording the on-off state as 1 and the off-off state as 0, wherein the formula (3) is as follows:
in the formula: vsIn the state of pressing plate, VaIs the width-to-length ratio of the platen area.
9. The method for identifying the switching-on/off state of the functional protection pressing plate of the transformer substation according to claim 7, characterized in that:
s42 includes the steps of:
s 421: and (3) fusing the shape feature identification results of the direction angle and the width-length ratio of the pressing plate, and determining the final on-off state of the pressing plate by using a formula (4), wherein the on-off state is marked as 1, the off-off state is marked as 0, and the formula (4) is as follows:
in the formula: vsIn the state of pressing plate, Vs1As a result of the feature identification of the orientation angle, Vs2The result is the form feature identification result of the width-length ratio;
s 422: verifying the identified pressing plate on-off state result and outputting a pressing plate state identification code.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210467476.0A CN114998581A (en) | 2020-12-22 | 2020-12-22 | Protection pressing plate effective pressing plate area extraction method based on multi-threshold and K-means clustering |
CN202011533308.4A CN112508940B (en) | 2020-12-22 | 2020-12-22 | Method for identifying switching state of functional protection pressing plate of transformer substation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011533308.4A CN112508940B (en) | 2020-12-22 | 2020-12-22 | Method for identifying switching state of functional protection pressing plate of transformer substation |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210467476.0A Division CN114998581A (en) | 2020-12-22 | 2020-12-22 | Protection pressing plate effective pressing plate area extraction method based on multi-threshold and K-means clustering |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112508940A CN112508940A (en) | 2021-03-16 |
CN112508940B true CN112508940B (en) | 2022-06-03 |
Family
ID=74923117
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210467476.0A Pending CN114998581A (en) | 2020-12-22 | 2020-12-22 | Protection pressing plate effective pressing plate area extraction method based on multi-threshold and K-means clustering |
CN202011533308.4A Active CN112508940B (en) | 2020-12-22 | 2020-12-22 | Method for identifying switching state of functional protection pressing plate of transformer substation |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210467476.0A Pending CN114998581A (en) | 2020-12-22 | 2020-12-22 | Protection pressing plate effective pressing plate area extraction method based on multi-threshold and K-means clustering |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN114998581A (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117437589B (en) * | 2023-10-30 | 2024-08-09 | 国网四川省电力公司绵阳供电公司 | Method, system, equipment and medium for preventing false detection of relay protection equipment of transformer substation |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004000503A (en) * | 2002-03-15 | 2004-01-08 | Terumo Corp | Liquid separating apparatus and liquid separating method |
JP4777024B2 (en) * | 2005-09-06 | 2011-09-21 | キヤノン株式会社 | Image processing apparatus and image processing apparatus control method |
CN107563396B (en) * | 2017-08-10 | 2019-08-30 | 南京大学 | The construction method of protection screen intelligent identifying system in a kind of electric inspection process |
CN109509169A (en) * | 2018-09-05 | 2019-03-22 | 广东电网有限责任公司 | The pressing plate condition checkout gear and method of learning distance metric based on nearest neighbour classification |
CN111242939B (en) * | 2020-01-17 | 2023-09-19 | 广东驰行电力设备有限公司 | Method for identifying state of pressing plate |
CN114926391A (en) * | 2020-07-03 | 2022-08-19 | 三峡大学 | Perspective transformation method based on improved RANSAC algorithm |
CN113344047A (en) * | 2021-05-24 | 2021-09-03 | 广西电网有限责任公司电力科学研究院 | Platen state identification method based on improved K-means algorithm |
-
2020
- 2020-12-22 CN CN202210467476.0A patent/CN114998581A/en active Pending
- 2020-12-22 CN CN202011533308.4A patent/CN112508940B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112508940A (en) | 2021-03-16 |
CN114998581A (en) | 2022-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886974B (en) | Seal removing method | |
CN109785285B (en) | Insulator damage detection method based on ellipse characteristic fitting | |
CN103258201B (en) | A kind of form lines extracting method of amalgamation of global and local message | |
CN109409355B (en) | Novel transformer nameplate identification method and device | |
CN113313677B (en) | Quality detection method for X-ray image of wound lithium battery | |
CN102426649A (en) | Simple steel seal digital automatic identification method with high accuracy rate | |
CN104598907B (en) | Lteral data extracting method in a kind of image based on stroke width figure | |
CN111915509B (en) | Protection pressing plate state identification method based on shadow removal optimization of image processing | |
CN109344820A (en) | Digital electric meter Recognition of Reading method based on computer vision and deep learning | |
CN108133216A (en) | The charactron Recognition of Reading method that achievable decimal point based on machine vision is read | |
CN112508940B (en) | Method for identifying switching state of functional protection pressing plate of transformer substation | |
CN108389215A (en) | A kind of edge detection method, device, computer storage media and terminal | |
CN111861866A (en) | Panoramic reconstruction method for substation equipment inspection image | |
CN106558044B (en) | Method for measuring resolution of image module | |
CN111046782B (en) | Quick fruit identification method for apple picking robot | |
CN114241047A (en) | Binocular vision identification and positioning method for garden hedgerow trimming | |
CN112418226B (en) | Method and device for identifying opening and closing states of fisheyes | |
CN111414877B (en) | Table cutting method for removing color frame, image processing apparatus and storage medium | |
CN113947563A (en) | Cable process quality dynamic defect detection method based on deep learning | |
CN111815542A (en) | Tree ring image medullary center positioning and ring measuring method | |
CN107367514A (en) | A kind of POS defect inspection method based on machine vision | |
CN106815580A (en) | A kind of license plate locating method | |
CN112396638A (en) | Image processing method, terminal and computer readable storage medium | |
CN114913370A (en) | State automatic detection method and device based on deep learning and morphology fusion | |
CN114069844A (en) | Transformer substation secondary equipment state image recognition method based on deep learning |
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 |