Mutual inductor operation state evaluation method and system

Abstract

The invention relates to the technical field of measurement, in particular to a mutual inductor operation state evaluation method and system. The method comprises the following steps: acquiring a grey-scale map of an ultraviolet image of a mutual inductor irradiated by an ultraviolet light source; analyzing the grey-scale map to obtain a skeleton isolation function of each pixel point in the grey-scale map; obtaining the neighborhood structure consistency of each pixel point; calculating an enhancement coefficient of each pixel point; taking the product of the enhancement coefficient and the gray value of each pixel point as an enhanced gray value, and further obtaining an enhanced gray-scale map; and carrying out binarization segmentation on the enhanced grey-scale map to obtain a light spot region so as to determine the discharge condition of the mutual inductor. According to the scheme of the invention, the discharge of the mutual inductor can be accurately and effectively identified, so that the operation state of the mutual inductor can be accurately evaluated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of measurement. More particularly, the present application relates to a method and system for evaluating the running state of a mutual inductor. BACKGROUND

[0002] A mutual inductor is a special transformer that reduces high voltage and large current to low voltage and small current signals through a set ratio to deliver information to measuring instruments, meters and protection devices. It is also the most commonly used primary equipment.

[0003] Mutual inductors can be divided into electromagnetic, capacitive and electronic types. Currently, it is difficult to implement the specified periodic verification work of capacitive voltage mutual inductors. The reasons are mainly as follows: 1. It is difficult to power off in a substation. Even if there is a power-off maintenance plan, it is mainly for testing the insulation performance of the equipment, and it is difficult to arrange time for mutual inductor error characteristic testing; 2. With the increase of voltage level, the volume and weight of the equipment for testing the error characteristics of mutual inductors increase, and the difficulty, labor intensity and implementation cost of on-site work are greatly improved; 3. The increase in the number of related personnel is much slower than the expansion of the power grid, and the traditional mutual inductor error characteristic testing mode is difficult to continue to implement.

[0004] Therefore, the method for evaluating the running state of a mutual inductor using an ultraviolet image has the advantages of saving manpower and being convenient and intuitive.

[0005] However, the traditional image recognition algorithm cannot effectively recognize the small light spots or the pixel points near the light spots of the ultraviolet image of the mutual inductor in the discharge state, which is easily confused with background noise, and when filtering, it is extremely easy to filter the small light spots together, affecting the recognition effect, and thus the running state of the mutual inductor cannot be accurately evaluated.

[0006] Therefore, an image processing method is needed to effectively distinguish small light spots from noise and only enhance light spots to accurately identify whether the mutual inductor is discharging, so as to evaluate the running state of the mutual inductor. SUMMARY

[0007] The purpose of the present application is to provide a mutual inductor running state evaluation method and system to solve the problem that the discharge of the mutual inductor cannot be accurately and effectively recognized in the prior art. To this end, the present application provides a solution in the following two aspects.

[0008] In the first aspect, the present application provides a mutual inductor running state evaluation method, comprising: obtaining a gray image of an ultraviolet image of a mutual inductor after irradiation by an ultraviolet light source; The grayscale image is analyzed to obtain the skeleton isolation function of each pixel in the grayscale image; the skeleton isolation function is negatively correlated with the normalized value of the minimum skeleton distance of the corresponding pixel and the isolation, and positively correlated with the grayscale value of the corresponding pixel; the isolation characterizes the difference between any pixel and the pixels in its neighborhood. Obtain the neighborhood structure consistency of each pixel; the neighborhood structure consistency is negatively correlated with the difference between any two pixels in the neighborhood centered on any pixel. Calculate the enhancement coefficient for each pixel. The enhancement coefficient is positively correlated with the skeleton isolation function and negatively correlated with the neighborhood structure consistency. The product of the enhancement coefficient and the gray value of each pixel is used as the enhanced gray value, thus obtaining the enhanced grayscale image; The enhanced grayscale image is binarized and segmented to obtain the spot region, so as to determine the discharge status of the transformer.

[0009] The above scheme analyzes the grayscale image of the ultraviolet image captured by the current transformer to obtain the skeleton isolation function and neighborhood structure consistency of each pixel in the grayscale image. Based on the skeleton isolation function and neighborhood structure consistency, the enhancement coefficient of each pixel is determined to enhance the pixels in the grayscale image. Then, the spot area is extracted from the enhanced grayscale image, which can accurately identify the discharge status of the current transformer.

[0010] Optionally, the enhancement coefficient for: ; in, It is a pixel. The skeleton isolation function, It is a pixel. Neighborhood structure consistency It is the first coefficient. It is the second coefficient. In pixels The neighborhood centered on it.

[0011] The above scheme proposes a method for accurately calculating the enhancement coefficient.

[0012] Optionally, the skeleton isolation function for: ; in, It is a pixel. The skeleton isolation function, It is a pixel. The normalized value of the minimum skeleton distance. , respectively are setting parameters, is a gray value of a pixel point , is a maximum gray value of a pixel point in a gray image, is an adjustment parameter, is an isolatedness of a pixel point , and exp( ) is an exponential function.

[0013] The scheme provides a method for accurately calculating a skeleton isolatedness function.

[0014] Optionally, the neighborhood structure consistency is: ; wherein, is a neighborhood with a pixel point as a center, and denote a gray value of a first pixel point and a gray value of a second pixel point in an i-th pixel point pair in the neighborhood, and denote a coordinate of the first pixel point and a coordinate of the second pixel point, is an adjustment parameter of tolerance to a gray difference, is a total number of pixel point pairs in the neighborhood, and exp( ) is an exponential function; the pixel point pair is any two pixel points selected from all pixel points in the neighborhood without repetition.

[0015] Optionally, the isolatedness is a ratio of a number of differences greater than a difference threshold value to a total number of pixel points in the neighborhood; the difference is an absolute value of a difference between any pixel point and each pixel point in the neighborhood of the pixel point.

[0016] The neighborhood structure consistency can represent a difference condition between any pixel point and each pixel point in the neighborhood of the pixel point.

[0017] Optionally, the neighborhood is an eight-neighborhood or a circular region with any pixel point as a center and a neighborhood radius r set.

[0018] Optionally, the enhanced gray image is binarized and segmented to obtain a light spot region, so as to determine a discharge condition of the mutual inductor, including: setting a segmentation threshold value; setting a gray value of a pixel point greater than the segmentation threshold value to 1 and setting a gray value of a pixel point less than or equal to the segmentation threshold value to 0 to obtain a binary image; performing edge detection on the binary image to output a light spot image; if an area of a light spot region in the light spot image is greater than an area threshold value, the mutual inductor has a discharge condition.

[0019] Optionally, the skeleton distance is obtained by a skeleton extraction algorithm based on distance transformation.

[0020] Optionally, the process of acquiring the ultraviolet image is as follows: When the difference between the temperature at the later time and the temperature at the previous time is greater than the set difference temperature, the ultraviolet image of the mutual inductor is captured by the ultraviolet imager.

[0021] The above scheme can improve the efficiency of discharge identification by using temperature to preliminarily screen the ultraviolet image of the mutual inductor.

[0022] In a second aspect, a mutual inductor operating state evaluation system comprises: a processor; a memory storing computer instructions for mutual inductor operating state evaluation, which, when executed by the processor, causes the system to perform the mutual inductor operating state evaluation method described above.

[0023] The present application has the following advantages: The scheme of the present application effectively enhances the light spot area, and does not enhance or slightly enhances the background and noise, so that the enhanced gray scale image can accurately identify the discharge condition of the mutual inductor, thereby effectively evaluating the operating state of the mutual inductor. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 A step flowchart of a mutual inductor operating state evaluation method in the embodiment is schematically shown; Figure 2 A structure block diagram of a mutual inductor operating state evaluation system in the embodiment is schematically shown. DETAILED DESCRIPTION

[0025] The technical scheme in the embodiment of the present application will be described clearly and completely below with reference to the drawings in the embodiment of the present application.

[0026] As Figure 1 shown, the mutual inductor operating state evaluation method in the embodiment comprises the following steps: Step S1, acquiring a gray scale image of an ultraviolet image of the mutual inductor after irradiation by an ultraviolet light source.

[0027] In the embodiment, the "daylight mode" of the ultraviolet imager (e.g., OFIL SuperB) is turned on to automatically filter sunlight, the lens is aimed at the mutual inductor 5-10 meters away, and the front surface, left side surface and right side surface of the porcelain sleeve and the umbrella skirt of the mutual inductor can be focused and photographed.

[0028] Wherein, during the shooting process, when there are blue and white small light spots on the screen, it is suspected to be discharge, at this time, the temperature of the mutual inductor is measured by using the infrared temperature measuring gun, when the temperature difference between the next moment and the adjacent previous moment is greater than 0.5℃, it is confirmed to be discharge, the ultraviolet image at this time is recorded, it should be noted that, as far as possible, a camera with high resolution is used, which has important influence on subsequent light spot detection.

[0029] In the embodiment, the screened ultraviolet image is converted into a gray scale image, and a Gaussian filter is used to filter random noise of the gray scale image to obtain a filtered gray scale image.

[0030] In step S2, the gray scale values of each pixel point in the gray scale image are enhanced to obtain an enhanced gray scale image.

[0031] In the embodiment, an enhancement coefficient is obtained according to a previously constructed skeleton isolation function and neighborhood structure consistency, and the gray scale values of each pixel point in the gray scale image are enhanced by using the enhancement coefficient to obtain enhanced gray scale values.

[0032] The skeleton isolation function is constructed according to the minimum skeleton distance, the isolation of the pixel point and the gray scale feature obtained by the algorithm of skeleton extraction based on distance transformation.

[0033] Specifically, the process of obtaining the skeleton isolation function is as follows: Firstly, the isolation of each pixel point in the gray scale image is obtained.

[0034] In the embodiment, the difference between the gray scale values of each pixel point and the pixel points in its neighborhood is obtained, the difference is compared with a difference threshold value, and the ratio of the number of differences greater than the difference threshold value to the total number of pixel points in the neighborhood is taken as the isolation of the corresponding pixel point.

[0035] It should be noted that, in the ultraviolet image of the mutual inductor discharge, there are small light spots and large light spots, wherein the small light spots are regions with less than 4 pixel points, and the large light spots are regions with more than or equal to 4 pixel points; generally, isolated small light spots and light spot edges are difficult to be checked out, therefore, the isolation of each pixel point needs to be analyzed.

[0036] The above-mentioned neighborhood is an eight-neighborhood or a circular region with a neighborhood radius r centered on any pixel point. The pixel points in the neighborhood are the pixel points in the eight-neighborhood or the pixel points in the circular region with the neighborhood radius r centered on any pixel point. The value of the neighborhood radius can be greater than or equal to the length of 5 pixel points, and can be 5 or 7.

[0037] The above-mentioned difference is the absolute value of the difference between the gray scale values of any pixel point and the pixel points in its neighborhood; the value of the difference threshold value can be 15, and of course it can also be determined according to the actual situation.

[0038] Secondly, the minimum skeleton distance is calculated.

[0039] Wherein, when the spot is particularly small (small spot), the signal characteristics of the spot itself are interfered by noise, the artifacts of dust on the camera device, and the eigenvalues of the three are high and similar, so it is difficult to accurately distinguish the spot and the interference. However, in fact, the small spot is still different from the noise, the small spot has a clear center bright spot, the center brightness is high, and the gray value is large, while the noise gray value is similar to the background, the center brightness is low, and the gray value is small.

[0040] Therefore, in the embodiment, by introducing the algorithm of skeleton extraction based on distance transformation, setting the gray threshold and binarizing the image, the centerline transformation is performed on the binary image to obtain the centerline distance field and the centerline image, and then the thinning operation is performed on the centerline image to obtain the skeleton region; the coordinates of the center point of the skeleton region are taken as the coordinates of the skeleton region, and subsequent operations are performed on the gray image, that is, the minimum skeleton distance of each pixel point to the nearest skeleton is calculated, and the normalized value of the minimum skeleton distance is obtained, denoted as .

[0041] Wherein, the normalized value is the ratio of the minimum skeleton distance to the set neighborhood radius. Wherein, the set neighborhood radius is the radius of the circular region, and the set neighborhood radius is introduced to eliminate the dimension effect of the skeleton distance.

[0042] The coordinates of the skeleton in the above are the center points of the "skeleton" in the extracted gray image, such as the skeleton of a circular spot can be the center of the circular spot.

[0043] It should be noted that since the skeleton is generated from the center axis of the bright area connected structure in the gray image, it only exists in the obvious discharge structure (such as the region of the larger spot), and does not exist in the background. Therefore, for larger spots (there are 4 or more pixel points in the spot), each spot will form a skeleton; and when the number of pixel points in the spot is less than 4 (small spot), the pixel points in the small spot will be confused with the pixel points in the background region and the noise pixel points, and it is difficult to distinguish them well.

[0044] Wherein, the algorithm of skeleton extraction based on distance transformation is a technology based on mathematical morphology theory, and the specific steps include: (1) the image is initially binarized; (2) the pixel points in the binarized image are classified to obtain internal points, boundary points and isolated points. (3) the distance from each internal point to non-internal point is calculated, and the distance is assigned to the pixel point. (4) the assigned image is binarized until the binarization result of the image after the next assignment is all 0.

[0045] Since the algorithm for skeleton extraction based on distance transformation is existing technology, it will not be described in detail here.

[0046] In this embodiment, the distance between pixels belonging to the background, noise, and smaller light spots and the nearest skeleton, i.e., the smallest skeleton distance, must be relatively large.

[0047] Then, construct the skeleton isolation function.

[0048] This embodiment constructs a skeleton isolation function based on the minimum skeleton distance between pixels, pixel isolation, and grayscale features. The aim is to increase the difference between the light spot, background, and noise.

[0049] Specifically, the skeleton isolation function is: ; in, It is a pixel. The skeleton isolation function, It is a pixel. The normalized value of the minimum skeleton distance. , These are setting parameters, It is a pixel. grayscale value, It is the maximum gray value of a pixel in a grayscale image. It's about adjusting parameters. For pixels Due to the isolation of exp(), it is an exponential function.

[0050] in, Its function is to control The influence It is a constant greater than 0, with an empirical value of 0.7. This is a setting parameter for adjusting the influence of isolation; an empirical value of 0.6 is used. Used for magnification Take 2 experience points.

[0051] It should be noted that since the skeleton only forms in the area where the larger light spot is located, for pixels in the background area, the distance from that pixel to the nearest skeleton is relatively large. The size is relatively large, and due to the low isolation of the background area, Smaller, therefore, formula In this case, both the numerator and denominator are relatively large. This will result in slight changes (i.e., a slight increase or decrease); at the same time, the grayscale value of the background is significantly lower, therefore... It was also lower, resulting in The value is also low.

[0052] For the pixel point belonging to noise, the distance from the pixel point to the nearest skeleton is also far, at this time, the skeleton distance is large, and the isolation of the pixel point belonging to noise is generally high, so The value is maximum, so The value is greatly reduced; and the gray value of noise is obviously lower (the noise commonly seen in ultraviolet images is thermal noise of sensor thermal current fluctuation, optical scattering interference noise of ultraviolet lens inner surface reflection, stray light, and background ultraviolet stray light noise of reflection of non-discharge light source in the environment, which is more common and has lower gray value than the light spot), so It is also lower, and it is concluded that The value will be the lowest.

[0053] For the pixel points in the larger light spot area (when the number of pixel points is greater than or equal to 4), the skeleton formed is located at the pixel point itself or near the pixel point, Tends to 0, Tends to 1, and the brightness is almost the maximum in the whole image, so Tends to 1, The value is maximum, and the output The value is also the highest.

[0054] For the pixel points in the smaller light spot area (when the number of pixel points is less than 4), since the number of pixel points in the smaller light spot area is too small to form a skeleton, the distance from the pixel point to the nearest skeleton is far, It is large, and the isolation of the light spot area is high, It is large, so The value is maximum, so The value is greatly reduced. However, since the gray value of the pixel point in the smaller light spot area is larger than that of the pixel point of noise or background, at this time The correction term plays a role, and the high brightness makes It is large, and the obtained The value is between the Corresponding to the background and the Corresponding to the larger light spot area, so Can increase the contrast between the light spot and the noise.

[0055] The Of the above four areas is sorted as follows: noise < background < smaller light spot < larger light spot. Among them, The setting of n = 2 makes the Corresponding to the pixel point in the smaller light spot area and the Corresponding to the pixel point in the background area have a large difference.

[0056] It should be noted that the purpose of introducing the algorithm of skeleton extraction based on distance transformation is to distinguish the pixel points belonging to the light spot from the background and noise, especially for the smaller light spot, the pixel points can be better distinguished from the background and noise, which is beneficial to the subsequent recognition of the discharging of the mutual inductor.

[0057] The acquisition process of the neighborhood structure consistency in the embodiment is as follows: First, the neighborhood of each pixel point is acquired, and all the pixel points in the neighborhood are paired to obtain different pixel point pairs, the gray difference of the two pixel points in each pixel point pair is calculated, and the neighborhood structure consistency is obtained according to the gray difference.

[0058] The above-mentioned pairing is to select any two different pixel points from all the pixel points without repetition, that is, to select all possible combinations of 2 pixel points from all the pixel points.

[0059] Specifically, it is known that each pixel point has a circular region with the pixel point as the center. If the neighborhood contains a discharging light spot, the high brightness of the light spot relative to the background will disturb the structural continuity of the neighborhood, so calculating the structural consistency of a neighborhood can also reflect whether the neighborhood contains a light spot, and the neighborhood structural consistency needs to be calculated , specifically: ; Among them, is the neighborhood with the pixel point I(x, y) as the center, and represent the gray value of the first pixel point and the gray value of the second pixel point in the i-th pixel point pair in the neighborhood, and represent the coordinates of the first pixel point and the coordinates of the second pixel point, is a parameter of the tolerance of the gray difference, is the total number of pixel point pairs in the neighborhood.

[0060] In the background area, the gray change of the pixel points in the neighborhood is relatively smooth and regular; if there is a discharging light spot area, the gray change will be inconsistent and chaotic, therefore, by traversing several pixel pairs from a neighborhood, the gray difference of the selected i-th pair of traversed pixel points will present a large fluctuation. is the gray difference of the selected i-th pair of traversed pixel points; is an adjustment setting parameter for controlling the tolerance of the gray difference.

[0061] The neighborhood structure consistency is negatively correlated with the gray difference of all pixel pairs in the neighborhood; that is, the greater the gray difference, the smaller the neighborhood structure consistency of the corresponding pixel points. That is, when the number of pixel points in the neighborhood of any pixel point that have a large difference with any pixel point is increasing, The value of the neighborhood structure consistency is first reduced and then increased (from a value close to 1 to a value close to 0, and then increased to a value close to 1). The specific reason is that if the gray values of the pixel points in the neighborhood of any pixel point have a difference, then the pixel points in the neighborhood of any pixel point may have pixel points belonging to the light spot; when the number of pixel points belonging to the light spot is increasing, the gray difference of the pixel pairs is from small to large and then small again.

[0062] The above large difference can be obtained by comparing the difference between two pixel points with a difference threshold value. When the difference is greater than the difference threshold value, it is considered that the gray value difference between the two pixel points is large. The value of the difference threshold value can be 15, of course, it can also be determined according to the actual situation.

[0063] In this embodiment, the enhancement coefficient is: ; Wherein, is the skeleton isolation function of the pixel point , the neighborhood structure consistency of the pixel point is the neighborhood structure consistency of the pixel point , the first coefficient is , and the second coefficient is .

[0064] Wherein, is the first coefficient of the skeleton isolation function, controls the enhancement effect of the pixel point skeleton isolation function, and the empirical coefficient is 2.0; is the second coefficient of , controls the overall enhancement amplitude of the structure disturbance region, and the empirical coefficient is 1.2.

[0065] The above enhancement coefficient increases with the number of pixel points in the neighborhood of any pixel point (the pixel points in the neighborhood are pixel points that have a large difference with any pixel point, that is, pixel points that may belong to the light spot region), the value of is first reduced and then increased, the value of is first increased and then decreased, so that the pixel points with strong enhancement are the pixel points close to the skeleton and the pixel points in the skeleton region; and for the pixel points far away from the skeleton region, the amplitude of the pixel point enhancement is small.

[0066] The pixel point close to the skeleton has a different enhancement amplitude from the pixel point in the skeleton region. The pixel point close to the skeleton can be an edge pixel point of the skeleton region, and the gray value of the pixel point is obviously enhanced, so that whether the pixel point truly belongs to the skeleton region (the skeleton region corresponds to the light spot region) can be identified.

[0067] Exemplarily, when the neighborhood of the pixel point does not contain a pixel point with a large difference, that is, the pixel point in the neighborhood is background and / or noise, the value of is small, the value of is close to 1, and the pixel point is not enhanced or is slightly enhanced.

[0068] The above-described different degrees of enhancement of the pixel points in the gray scale image according to the isolation degree and the neighborhood structure consistency of the pixel points obviously enhances the pixel points near the light spot region, and does not enhance or slightly enhances the pixel points belonging to the background and / or noise, thereby increasing the difference between the light spot, the background and the noise, and highlighting the light spot.

[0069] Specifically, the gray value of the enhanced pixel point is: ; wherein, is the gray value of the pixel point , and is the enhancement coefficient of the pixel point .

[0070] In step S3, the enhanced gray scale image is binarized and segmented to obtain a light spot region, so as to determine the discharge condition of the mutual inductor.

[0071] For the enhanced gray scale image, if ≥ , the corresponding gray value is assigned as 1, and if < , the corresponding gray value is assigned as 0, and a binary image is output.

[0072] wherein, the segmentation threshold value is set, wherein is the gray mean value of the enhanced image, is the gray standard deviation, is the coefficient of , and the empirical value is 1.5.

[0073] The binary image is subjected to edge detection, and a light spot image is output. If all the light spot areas in the light spot image are greater than an area threshold value, the mutual inductor has discharge abnormality, and needs to be immediately shut down for maintenance.

[0074] Wherein the edge detection adopts a canny edge detection algorithm, and many small circular regions, i.e., light spots, in the binary image can be detected.

[0075] The total area of the many circular regions can represent the abnormal condition of the discharge of the mutual inductor, i.e., when the area is small, the mutual inductor has low-grade discharge, at this time, the mutual inductor can correspond to a normal operation or an early warning state, at this time, it is only necessary to monitor regularly; when the area is large, it can indicate that the insulation performance is declining or approaching failure, and it is necessary to take maintenance measures or immediately stop for repair. Therefore, in the embodiment, an area threshold is set to judge the normal or abnormal point of the discharge of the mutual inductor, so as to accurately evaluate the operation state of the mutual inductor.

[0076] The area threshold in the above can be obtained by enhancing the grayscale image of the mutual inductor in normal operation (without discharge) and obtaining the corresponding light spot image, and taking the mean value of the light spot area in the light spot image as the area threshold.

[0077] The scheme of the present application can obviously enhance the pixel points near the light spot region by obtaining the skeleton isolation function and the neighborhood structure consistency, and does not enhance or slightly enhances other pixel points (pixel points belonging to background and / or noise), so as to achieve the purpose of highlighting the light spot, avoid the problem that small light spots are not easy to detect, and can effectively identify the discharge condition of the subsequent mutual inductor.

[0078] The present application also provides a mutual inductor operation state evaluation system. Figure 2 As shown in the figure, the system comprises a processor and a memory, and the memory stores computer program instructions, when the computer program instructions are executed by the processor, the mutual inductor operation state evaluation method according to the present application is realized.

[0079] The system also comprises a communication bus and a communication interface and other components familiar to those skilled in the art, and the settings and functions thereof are known in the art, so they will not be described here.

[0080] In this description, the term "application" also means any computer program product storing such a program for use with or in connection with a computer system, apparatus or device. The program can be stored on any apparatus-readable medium, for example, but not limited to, any volatile memory or non-volatile memory. In this description, the term "memory" also means any computer program product storing such a program for use with or in connection with a computer system, apparatus or device. The program can be stored on any apparatus-readable medium, for example, but not limited to, any volatile memory or non-volatile memory. In this description, the term "computer-readable medium" means any tangible medium that stores, communicates, or otherwise provides data that can be used by an instruction execution system, apparatus or device. The computer-readable medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as, for example, resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), and the like, or any other medium that can be used to store the desired information and that can be accessed by an application, module, or both. Any such computer storage media can be part of the device or accessible or connectable thereto. Any application or module described in this description can be implemented by computer-readable / executable instructions stored or otherwise held by such computer-readable media.

[0081] In the description of the present description, the meaning of "a plurality of" is at least two, for example, two, three or more, and the like, unless otherwise explicitly specified.

[0082] Although the present description has shown and described several embodiments of the present application, it will be apparent to those skilled in the art that many modifications, changes and substitutions can be made thereto without departing from the spirit and scope of the present application.

Claims

1. A method for evaluating the operating status of a current transformer, characterized in that, include: Obtain a grayscale image of the current transformer after it has been irradiated by an ultraviolet light source. The grayscale image is analyzed to obtain the skeleton isolation function of each pixel in the grayscale image; The skeleton isolation function is negatively correlated with the normalized value of the minimum skeleton distance of the corresponding pixel and positively correlated with the gray value of the corresponding pixel; the isolation characterizes the difference between any pixel and its neighboring pixels. Obtain the neighborhood structure consistency of each pixel; the neighborhood structure consistency is negatively correlated with the difference between any two pixels in the neighborhood centered on any pixel. Calculate the enhancement coefficient for each pixel. The enhancement coefficient is positively correlated with the skeleton isolation function and negatively correlated with the neighborhood structure consistency. The product of the enhancement coefficient and the gray value of each pixel is used as the enhanced gray value, thus obtaining the enhanced grayscale image; The enhanced grayscale image is binarized and segmented to obtain the spot region, so as to determine the discharge status of the transformer.

2. The method for evaluating the operating status of a current transformer according to claim 1, characterized in that, The enhancement coefficient for: ； in, It is a pixel. The skeleton isolation function, It is a pixel. Neighborhood structure consistency It is the first coefficient. It is the second coefficient. In pixels The neighborhood centered on it.

3. The method for evaluating the operating status of a current transformer according to claim 2, characterized in that, The skeleton isolation function for: ； in, It is a pixel. The skeleton isolation function, It is a pixel. The normalized value of the minimum skeleton distance. , These are setting parameters, It is a pixel. grayscale value, It is the maximum gray value of a pixel in a grayscale image. It's about adjusting parameters. For pixels Due to the isolation of exp(), it is an exponential function.

4. The method for evaluating the operating status of a current transformer according to claim 2, characterized in that, The neighborhood structure consistency for: ； in, Based on pixels The neighborhood centered on, and This represents the grayscale values ​​of the first and second pixels in the i-th pair of pixels in the neighborhood. and This represents the coordinates of the first pixel and the second pixel. It is an adjustment parameter for the tolerance of grayscale differences. It is the total number of pixel pairs in the neighborhood, and exp() is an exponential function; the pixel pair is composed of any two pixels selected without repetition from all pixels in the neighborhood.

5. The method for evaluating the operating status of a current transformer according to claim 3, characterized in that, The isolation is the ratio of the number of pixels with differences greater than the difference threshold to the total number of pixels in the neighborhood; the difference is the absolute value of the difference between the grayscale values ​​of any pixel and all pixels in its neighborhood.

6. A method for evaluating the operating status of a current transformer according to claim 1 or 4, characterized in that, The neighborhood can be an eight-neighborhood or a circular region centered on any pixel with a radius of r.

7. The method for evaluating the operating status of a current transformer according to claim 1, characterized in that, The step of binarizing and segmenting the enhanced grayscale image to obtain the spot region, in order to determine the discharge status of the transformer, includes: Set the segmentation threshold; The gray values ​​of pixels with values ​​greater than the segmentation threshold are set to 1, and the gray values ​​of pixels with values ​​less than or equal to the segmentation threshold are set to 0, thus obtaining a binary image. Edge detection is performed on the binary image to output a spot image; If the area of ​​all spot regions in the spot image is greater than the area threshold, the transformer has a discharge abnormality and needs to be shut down for maintenance immediately.

8. The method for evaluating the operating status of a current transformer according to claim 3, characterized in that, The skeleton distance is obtained using a skeleton extraction algorithm based on distance transformation.

9. The method for evaluating the operating status of a current transformer according to claim 8, characterized in that, The process of acquiring the ultraviolet image is as follows: The current transformer is measured using an infrared thermometer. When the temperature difference between the next moment and the temperature of the adjacent previous moment is greater than the set difference temperature, an ultraviolet imager is used to capture an ultraviolet image of the current transformer.

10. A current transformer operating status evaluation system, characterized in that, include: processor; A memory storing computer instructions for evaluating the operating status of a current transformer, which, when executed by the processor, cause the system to perform a method for evaluating the operating status of a current transformer according to any one of claims 1-9.

Images