Phase resolution partial discharge map processing method and related device

Abstract

The invention provides a phase resolution partial discharge map processing method and a related device, and relates to the field of image processing, and the method comprises the steps: obtaining a binary map of a PRPD map; the distribution statistical characteristics of each row of pixels in the vertical coordinate direction and the distribution statistical characteristics of each column of pixels in the horizontal coordinate direction in the binary map are obtained, and the distribution statistical characteristics of each row of pixels in the vertical coordinate direction are used for indicating the distribution condition of each row of pixels in the phase; the distribution statistical characteristics of each column of pixels in the horizontal coordinate direction are used for indicating the amplitude range of each column of pixels; according to preset distribution statistical characteristics of noise pixels, the distribution statistical characteristics of each row of pixels in the vertical coordinate direction and the distribution statistical characteristics of each column of pixels in the horizontal coordinate direction, identifying the noise pixels in the binary map; according to the method, the interference pixels in the binary map are identified according to the preset distribution statistical characteristics of the interference pixels, so that the problem of curse of dimensionality is avoided, and the accuracy and the robust performance are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a phase-resolved partial discharge pattern processing method and related device. BACKGROUND

[0002] In order to ensure the safe operation of a gas insulated switchgear (GIS) device, it is crucial to identify the type of partial discharge of the GIS device. When the GIS device has partial discharge, a plurality of signals continuously generated by the GIS device are collected by an ultrahigh frequency sensor, and a phase-resolved partial discharge (PRPD) pattern can be obtained by counting all the signals. A partial discharge type identification model extracts features from the PRPD pattern, and the partial discharge type identification model identifies the type of partial discharge according to the features extracted from the PRPD pattern.

[0003] However, the ultrahigh frequency sensor not only collects partial discharge signals but also collects environmental noise signals and interference signals. The corresponding PRPD pattern contains three types of pixels: partial discharge pixels, noise pixels, and interference pixels. Partial discharge pixels are pixels that reflect the characteristics of the type of partial discharge, and thus the PRPD pattern input into the partial discharge type identification model contains not only partial discharge pixels required for identifying the type of partial discharge but also redundant pixels such as noise pixels and interference pixels, which interfere with partial discharge pixels. Therefore, the current partial discharge type identification has the problems of "curse of dimensionality" and low accuracy.

[0004] In addition, the PRPD patterns used to train the partial discharge type identification model are basically obtained in the laboratory measurement process. These PRPD patterns have strong repeatability and no redundant pixels such as noise and interference, which leads to poor robust performance of the partial discharge type identification model. SUMMARY

[0005] In view of the above problems, the present application provides a phase-resolved partial discharge pattern processing method and related device to avoid the problem of "curse of dimensionality" and improve accuracy and robust performance. The specific solutions are as follows:

[0006] The first aspect of the present application provides a phase-resolved partial discharge pattern processing method, comprising:

[0007] obtaining a binary pattern of a phase-resolved partial discharge (PRPD) pattern;

[0008] obtain a distribution statistical feature of each row of pixels in the binarized map in a vertical coordinate direction and a distribution statistical feature of each column of pixels in a horizontal coordinate direction, the distribution statistical feature of each row of pixels in the vertical coordinate direction being used to indicate a distribution of each row of pixels in a phase, and the distribution statistical feature of each column of pixels in the horizontal coordinate direction being used to indicate a range of amplitudes of each column of pixels;

[0009] identify noise pixels in the binarized map according to a preset distribution statistical feature of the noise pixels, the distribution statistical feature of each row of pixels in the vertical coordinate direction, and the distribution statistical feature of each column of pixels in the horizontal coordinate direction.

[0010] identify interference pixels in the binarized map according to a preset distribution statistical feature of the interference pixels.

[0011] In a possible implementation, the preset distribution statistical feature of the noise pixels includes that the noise pixels are uniformly distributed in the horizontal coordinate and the range of amplitudes of the noise pixels is smaller than that of partial discharge pixels, the partial discharge pixels being pixels in the map that embody characteristics of the partial discharge.

[0012] The preset distribution statistical feature of the interference pixels includes that a sparsity degree of the interference pixels is greater than a sparsity degree of the partial discharge pixels, and the sparsity degrees of the interference pixels and the partial discharge pixels are represented by density values.

[0013] In a possible implementation, the obtaining of the distribution statistical feature of each row of pixels in the binarized map in the vertical coordinate direction and the distribution statistical feature of each column of pixels in the horizontal coordinate direction includes:

[0014] project pixels in the binarized map onto a vertical coordinate and a horizontal coordinate respectively to obtain a first projection total amount of each row of pixels in the binarized map in the vertical coordinate direction and a second projection total amount of each column of pixels in the binarized map in the horizontal coordinate direction, the first projection total amount being the distribution statistical feature of each row of pixels in the vertical coordinate direction, and the second projection total amount being the distribution statistical feature of each column of pixels in the horizontal coordinate direction.

[0015] In a possible implementation, the identifying of the noise pixels in the binarized map according to the preset distribution statistical feature of the noise pixels, the distribution statistical feature of each row of pixels in the vertical coordinate direction, and the distribution statistical feature of each column of pixels in the horizontal coordinate direction includes:

[0016] if the first projection total amount is equal to a width of the binarized map, determine that all pixels under a row corresponding to the first projection total amount are suspected noise pixels, and the first projection total amount being equal to the width of the binarized map indicates that phases of all pixels under the row corresponding to the first projection total amount are uniformly distributed.

[0017] if the first total projection quantity is not equal to the width of the binary graph, determining that all pixels below the row corresponding to the first total projection quantity are not noise pixels;

[0018] obtaining position coordinates marked for each of the suspected noise pixels, the position coordinates including a position in a horizontal coordinate direction and a position in a vertical coordinate direction;

[0019] obtaining a minimum position from all positions in the vertical coordinate direction, the minimum position being a position with the minimum value among all positions;

[0020] determining a noise pixel screening condition according to the minimum position and a second total projection quantity with the minimum value among all second total projection quantities, the noise pixel screening condition being used to limit an amplitude range of the noise pixels;

[0021] if the position of the suspected noise pixel in the vertical coordinate direction satisfies the noise pixel screening condition, determining that the suspected noise pixel is a noise pixel;

[0022] if the position of the suspected noise pixel in the vertical coordinate direction does not satisfy the noise pixel screening condition, determining that the suspected noise pixel is not a noise pixel.

[0023] In a possible implementation, the identifying the interference pixels in the binary graph according to the preset statistical characteristics of the interference pixels includes:

[0024] determining a neighborhood region of a to-be-identified pixel in the binary graph, the to-be-identified pixel being a pixel other than the noise pixels in the binary graph;

[0025] calculating a density value of the to-be-identified pixel according to the gray values of pixels in the neighborhood region of the to-be-identified pixel;

[0026] if the density value of the to-be-identified pixel is less than or equal to a preset density threshold, determining that the to-be-identified pixel is an interference pixel;

[0027] if the density value of the to-be-identified pixel is greater than the preset density threshold, determining that the to-be-identified pixel is a partial discharge pixel, the partial discharge pixel being a pixel in the graph that embodies the characteristics of partial discharge, and the preset density threshold being a minimum density value when the to-be-identified pixel is the partial discharge pixel.

[0028] In a possible implementation, the binary graph of the phase-resolved partial discharge (PRPD) graph includes:

[0029] determining an effective pixel region in the PRPD graph, and performing standard processing on the size of the effective pixel region to obtain an effective pixel graph with a target size;

[0030] convert the effective pixel pattern into a gray scale pattern;

[0031] determine a gray scale threshold, and perform a binaryzation process on the gray scale pattern by using the gray scale threshold to obtain a binaryzation pattern.

[0032] The second aspect of the present application provides a phase resolution partial discharge pattern processing device, comprising:

[0033] a conversion unit configured to obtain a binaryzation pattern of a phase resolution partial discharge (PRPD) pattern;

[0034] an obtaining unit configured to obtain distribution statistical features of each row of pixels in a vertical coordinate direction and distribution statistical features of each column of pixels in a horizontal coordinate direction in the binaryzation pattern, wherein the distribution statistical features of each row of pixels in the vertical coordinate direction are used to indicate the distribution of each row of pixels in phase, and the distribution statistical features of each column of pixels in the horizontal coordinate direction are used to indicate the amplitude range of each column of pixels.

[0035] a recognition unit configured to recognize noise pixels in the binaryzation pattern according to preset distribution statistical features of the noise pixels, the distribution statistical features of each row of pixels in the vertical coordinate direction, and the distribution statistical features of each column of pixels in the horizontal coordinate direction, and to recognize interference pixels in the binaryzation pattern according to preset distribution statistical features of the interference pixels.

[0036] The third aspect of the present application provides a computer program product, comprising computer readable instructions, which, when executed on an electronic device, cause the electronic device to implement the phase resolution partial discharge pattern processing method of the first aspect or any implementation manner of the first aspect.

[0037] The fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0038] The memory is configured to store a computer program.

[0039] The processor is configured to execute the computer program, so that the electronic device can implement the phase resolution partial discharge pattern processing method of the first aspect or any implementation manner of the first aspect.

[0040] The fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the phase resolution partial discharge pattern processing method of the first aspect or any implementation manner of the first aspect.

[0041] By means of the technical solutions, the phase-resolved partial discharge pattern processing method and the related device provided by the application can identify noise pixels and interference pixels in the binary pattern of the PRPD pattern, so that only partial discharge pixels are input into the partial discharge type identification model, the pixel type and the pixel quantity input into the partial discharge type identification model are reduced, the problem of "dimension disaster" is avoided, and the accuracy is improved. Moreover, the noise pixels are identified according to the preset distribution statistical characteristics of the noise pixels, the distribution statistical characteristics of each row of pixels in the longitudinal direction of the pattern, and the distribution statistical characteristics of each column of pixels in the transverse direction of the pattern, and the interference pixels are identified according to the preset distribution statistical characteristics of the interference pixels, so that the distribution statistical characteristics of the noise pixels and the distribution statistical characteristics of the interference pixels (the distribution statistical characteristics can be regarded as expert knowledge) are effectively utilized for identification without any data set training, which is equivalent to unsupervised pixel identification and has higher robustness. Moreover, after the PRPD pattern is processed by the phase-resolved partial discharge pattern processing method provided by the application, the difference between the pattern input into the partial discharge type identification model and the PRPD pattern used for training the partial discharge type identification model is small, the manufacturing cost of the PRPD pattern used for training is reduced, and the robustness of the partial discharge type identification model is improved. BRIEF DESCRIPTION OF DRAWINGS

[0042] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals can refer to the same or similar elements. It should be understood that the drawings are schematic, and the sizes of the components and elements are not necessarily drawn to scale.

[0043] Figure 1 A flowchart of a phase-resolved partial discharge pattern processing method provided by the application;

[0044] Figure 2 A gray-scale pattern of a PRPD pattern provided by the application;

[0045] Figure 3 A binary pattern of the gray-scale pattern shown in Figure 2

[0046] Figure 4 A schematic diagram of a first projection total quantity and a second projection total quantity of the binary pattern shown in Figure 3

[0047] A schematic diagram of the binary pattern shown in Figure 5 Figure 2 A schematic diagram of the pattern shown in

[0048] Figure 6 Figure 5 A schematic diagram of the pattern shown in​​​

[0049] Figure 7 A structural schematic diagram of a phase resolution partial discharge pattern processing device provided in the present application is shown in the figure.

[0050] Figure 8 A structural schematic diagram of an electronic device provided in the present application is shown in the figure. DETAILED DESCRIPTION

[0051] The embodiments of the present application are described below in conjunction with the accompanying drawings. The terms used in the embodiment part of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0052] The embodiments of the present application are described below in conjunction with the accompanying drawings. It is known to those skilled in the art that as technology develops and new scenarios appear, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0053] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, and this is only a way of distinguishing the objects with the same attributes used in the description of the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, devices, products or equipment containing a series of units do not have to be limited to those units, but can include other units not clearly listed or inherent to these processes, methods, devices, products or equipment.

[0054] At present, the partial discharge type recognition model takes the PRPD pattern as input, and outputs the probability of the recognized partial discharge type, so as to determine the partial discharge type corresponding to the PRPD pattern through the probability of the partial discharge type. However, the input PRPD pattern includes three types of pixels, i.e. partial discharge pixels, noise pixels and interference pixels. The noise pixels and the interference pixels are redundant pixels in the partial discharge type recognition process and the redundant pixels will interfere with the partial discharge pixels, thereby causing the problems of "dimension disaster" and low accuracy in the partial discharge type recognition. Moreover, the PRPD patterns used for training the partial discharge type recognition model are basically obtained in the laboratory measurement process, and these PRPD patterns present strong repeatability and no noise interference and other redundant pixels, which leads to poor robust performance of the partial discharge type recognition model.

[0055] To solve the above technical problems, the embodiment of the present application provides a phase-resolved partial discharge pattern processing method and related device, which can identify noise pixels and interference pixels in the binary pattern of the PRPD pattern, so that only partial discharge pixels are input into the partial discharge type identification model, the pixel type and the number of pixels input into the partial discharge type identification model are reduced, thereby avoiding the problem of "dimension disaster" and improving the accuracy. Moreover, the noise pixels are identified according to the preset distribution statistical characteristics of the noise pixels, the distribution statistical characteristics of each row of pixels in the longitudinal coordinate direction of the pattern, and the distribution statistical characteristics of each column of pixels in the transverse coordinate direction of the pattern. The interference pixels are identified according to the preset distribution statistical characteristics of the interference pixels. Thus, the distribution statistical characteristics of the noise pixels and the distribution statistical characteristics of the interference pixels (the distribution statistical characteristics can be regarded as expert knowledge) are effectively utilized for identification without any dataset training, which is equivalent to unsupervised pixel identification and has higher robustness. Moreover, after the PRPD pattern is processed by the phase-resolved partial discharge pattern processing method provided by the embodiment of the present application, the difference between the pattern input into the partial discharge type identification model and the PRPD pattern used for training the partial discharge type identification model is small, the production cost of the PRPD pattern used for training is reduced, and the robustness of the partial discharge type identification model is improved.

[0056] The phase-resolved partial discharge pattern processing method provided by the embodiment of the present application will be described below with reference to the accompanying drawings. Please refer to Figure 1 which shows an optional flow of the phase-resolved partial discharge pattern processing method provided by the embodiment of the present application, which can include the following steps:

[0057] S101, acquiring a binary pattern of a PRPD pattern.

[0058] The PRPD pattern is a color image, which is first converted into a gray image, and then the binary pattern is obtained by binary processing of the gray image. Neither the binary pattern nor the gray image changes the pixel type in the pattern, so the type of any pixel in the binary pattern is the same as the type of the pixel in the PRPD pattern. For example, if a pixel in the binary pattern is a partial discharge pixel, the pixel in the PRPD pattern is also a partial discharge pixel.

[0059] In this embodiment, the grayscale values ​​of background pixels in the PRPD spectrum are the same, while the discharge frequencies corresponding to different partial discharge pixels are different. Therefore, the grayscale values ​​of the partial discharge pixels are different from the grayscale values ​​of the background pixels. Furthermore, the noise pixels and interference pixels are generated based on redundant signals (such as ambient noise signals and interference signals) collected during the partial discharge process. Therefore, the grayscale values ​​of the noise pixels and interference pixels are also different from the grayscale values ​​of the background pixels. Based on the principle that the grayscale values ​​of background pixels in the PRPD spectrum are different from the grayscale values ​​of partial discharge pixels, noise pixels, and interference pixels, this embodiment provides a method for setting a grayscale threshold to convert the grayscale image of the PRPD spectrum into a binary spectrum. The pixels in the binary spectrum are divided into background pixels and signal pixels. The signal pixels include three types of pixels: partial discharge pixels, noise pixels, and interference pixels. This facilitates the identification of partial discharge pixels, noise pixels, and interference pixels from the binary spectrum.

[0060] One possible method for setting a grayscale threshold is to obtain the grayscale value of the background pixel in the grayscale image and multiply the grayscale value of the background pixel by a preset grayscale threshold coefficient to obtain the grayscale threshold. A background grayscale range is generated based on the grayscale threshold. If the grayscale value of a pixel in the grayscale image is not within the background grayscale range, the pixel is determined to be a signal pixel, and the grayscale value of the pixel is 1. If the grayscale value of a pixel in the grayscale image is within the background grayscale range, the pixel is determined to be a background pixel, and the grayscale value of the pixel is 0. Because the grayscale values ​​of background pixels in a grayscale image vary to a certain extent (i.e., the grayscale values ​​of all background pixels are not unique), this embodiment uses the background grayscale range to identify background pixels.

[0061] The grayscale value of the background pixel can be determined manually, which is not limited in this embodiment. For example, the grayscale value range of the grayscale image is [0, 255], and the grayscale value of the background pixel G b is 125, the preset gray threshold α is 0.06, and the gray threshold G th =G b ×α=125×0.06=7.5, the background grayscale range can be [G b -G th , G b +G th ].

[0062] In this embodiment, the grayscale image may be a valid pixel area in the PRPD spectrum. Correspondingly, a feasible method for obtaining a binary spectrum of the PRPD spectrum is as follows:

[0063] Determine the effective pixel area in the PRPD map, standardize the size of the effective pixel area to obtain an effective pixel map with a target size; convert the effective pixel map into a grayscale map; determine the grayscale threshold, and use the grayscale threshold to binarize the grayscale map to obtain a binary map.

[0064] The effective pixel region in the PRPD map can be a region including the suspected signal pixels in the phase-amplitude coordinate system of the PRPD map. After the effective pixel region is determined, the size of the effective pixel region is normalized by using the scaling transformation to obtain an effective pixel map with a target size, which aims to normalize the effective pixel region of different PRPD maps to the target size, such as the size of rxc, where r is the width and c is the length. This is because the PRPD map can be obtained when the GIS equipment of different manufacturers has partial discharge, and the pixel resolution and the horizontal and vertical proportion when the PRPD map is drawn by different manufacturers are different. If the size of the effective pixel region is not normalized, the relative distribution of the pixels in the PRPD map will change even for the same type of partial discharge. Therefore, in order to reduce such changes, the size of the effective pixel region is normalized in this embodiment, so that the size of the effective pixel map of different PRPD maps is the target size.

[0065] The effective pixel map is converted into a gray-scale map by using a preset gray-scale conversion method, which can be, but is not limited to, any one of the average value method, the weighted method, the single-channel method, the maximum value method and the minimum value method. Then, the gray-scale threshold is determined by using the above-mentioned method of setting the gray-scale threshold, and the gray-scale map is binarized by using the gray-scale threshold to obtain a binarized map. The size of the binarized map is the target size.

[0066] The i-th pixel in the binarized map can be represented as g(x i ,y i ), where the value of g(x i ,y i ) is 0 or 1, x i is the horizontal coordinate of the i-th pixel, y i is the vertical coordinate of the i-th pixel, the value of x i is related to the length of the binarized map, and the value of y i is related to the width of the binarized map. As described above, the length of the binarized map is c and the width of the binarized map is r, so x i ∈[1,c] and y i ∈[1,r]. It can be seen that the final binarized map is a two-dimensional matrix, the number of rows of which is r (the width of the map), the number of columns of which is c (the length of the map), the size of the matrix is rxc, and the numerical value in the matrix is the gray-scale value of each pixel in the binarized map, which is 0 or 1.

[0067] S102. Obtain the distribution statistical characteristics of each row of pixels in the vertical direction and the distribution statistical characteristics of each column of pixels in the horizontal direction in the binary atlas. The distribution statistical characteristics of each row of pixels in the vertical direction are used to indicate the distribution of the phase of each row of pixels, and the distribution statistical characteristics of each column of pixels in the horizontal direction are used to indicate the amplitude range of each column of pixels.

[0068] In this embodiment, the distribution statistics of each row of pixels in the vertical direction and the distribution statistics of each column of pixels in the horizontal direction can be obtained by using the pixel value g(x i ,y i ) is obtained. One feasible way is:

[0069] Project the pixels in the binary atlas onto the horizontal and vertical coordinates respectively to obtain the first projection total of each row of pixels in the vertical direction and the second projection total of each column of pixels in the horizontal direction. The first projection total is the distribution statistical characteristics of each row of pixels in the vertical direction, and the second projection total is the distribution statistical characteristics of each column of pixels in the horizontal direction. The calculation formulas for the first projection total and the second projection total are as follows:

[0070]

[0071]

[0072] Where y_add(m) is the total first projection of the pixels in the mth row along the ordinate, and x_add(n) is the total second projection of the pixels in the nth column along the abscissa. The total first projection y_add(m) can be used to determine the number of background and signal pixels in the mth row, representing the distribution of the pixels in the mth row. The total second projection of the pixels in the nth column serves as the amplitude range of the pixels in the nth column.

[0073] S103 , identifying noise pixels in the binarized image according to preset distribution statistics of noise pixels, distribution statistics of pixels in each row in the vertical coordinate direction, and distribution statistics of pixels in each column in the horizontal coordinate direction.

[0074] It is found through research that the expert knowledge condition met by the noise pixels is that the noise distribution has no phase correlation, which is reflected in that the noise pixel distribution in the binary graph satisfies uniform distribution in the horizontal coordinate, that is, if there is no background pixel in the mth row of the binary graph, the pixels in the mth row are uniformly distributed in the horizontal coordinate, the horizontal coordinate corresponds to the phase of the graph, and the uniform distribution of the pixels in the mth row in the horizontal coordinate indicates that the pixels in the mth row are uniformly distributed in the phase of 0 to 360°. If the first projection total amount y_add(m) is taken as the distribution statistical feature of the pixels in the mth row in the vertical coordinate direction, the expert knowledge condition can be that the first projection total amount y_add(m) is the same as the width of the binary graph.

[0075] However, in addition to the noise pixels meeting the above expert knowledge condition, when the partial discharge signal is strong or the partial discharge frequency is high, the partial discharge pixels in the binary graph can also meet the above expert knowledge condition, and therefore other expert knowledge conditions need to be further given in order to distinguish the noise pixels and the partial discharge pixels. It can be understood that the noise pixels and the partial discharge pixels have amplitudes in addition to the phase, and therefore the embodiment can also distinguish the noise pixels and the partial discharge pixels from the amplitudes.

[0076] It is found through research that the amplitude range of the noise pixels is smaller than that of the partial discharge pixels, and accordingly the embodiment can identify the noise pixels through the amplitude range and whether the noise pixels are uniformly distributed in the horizontal coordinate direction, that is, in the embodiment, the preset distribution statistical feature of the noise pixels can be that the noise pixels are uniformly distributed in the horizontal coordinate and the amplitude range of the noise pixels is smaller than that of the partial discharge pixels. Correspondingly, according to the distribution statistical feature, the optional flow for identifying the noise pixels in the binary graph includes the following steps:

[0077] Step 1) If the first projection total amount is equal to the width of the binary graph, it is determined that all the pixels under the row corresponding to the first projection total amount are suspected noise pixels, and the fact that the first projection total amount is equal to the width of the binary graph indicates that the phases of all the pixels under the row corresponding to the first projection total amount are uniformly distributed.

[0078] Step 2) If the first projection total amount is not equal to the width of the binary graph, it is determined that all the pixels under the row corresponding to the first projection total amount are not noise pixels.

[0079]

[0080] wherein N is the suspected noise pixel set, if then all the pixels in the mth row are suspected noise pixels, the suspected noise pixels are divided into the suspected noise pixel set, and then whether the suspected noise pixels are noise pixels is determined from the amplitudes of the suspected noise pixels, the amplitudes correspond to the vertical coordinate, and therefore whether the suspected noise pixels are noise pixels can be determined according to the positions of the suspected noise pixels in the vertical coordinate.

[0081] Step 3) Obtain the position coordinates of each suspected noise pixel, the position coordinates including a position in the horizontal coordinate direction and a position in the vertical coordinate direction. In the embodiment, the position coordinates of the pixel with the minimum amplitude and the phase of 0 in the binary map are defined as (0, 0), and the position coordinates of the pixel with the maximum amplitude and the phase of 360° are defined as (c, r), and then the positions of the suspected noise pixels in the suspected noise pixel set are marked to mark the position coordinates of each suspected noise pixel. For example, the position coordinates of the i-th suspected noise pixel in the suspected noise pixel set can be represented as (x i , y i ).

[0082] Step 4) Obtain the minimum position from all positions in the vertical coordinate direction, the minimum position being the position with the minimum value in all positions.

[0083] Step 5) Determine the noise pixel screening condition according to the minimum position and the second projection total with the minimum value in all second projection totals, the noise pixel screening condition being used to limit the amplitude range of the noise pixel.

[0084] Step 6) If the position of the suspected noise pixel in the vertical coordinate direction satisfies the noise pixel screening condition, it is determined that the suspected noise pixel is a noise pixel.

[0085] Step 7) If the position of the suspected noise pixel in the vertical coordinate direction does not satisfy the noise pixel screening condition, it is determined that the suspected noise pixel is not a noise pixel.

[0086] One optional way of the noise pixel screening condition is: , wherein is the minimum position, is the minimum second projection total. Correspondingly, the way of screening the suspected noise pixel is as follows:

[0087]

[0088] The noise pixel set is obtained by dividing all the noise pixels into the noise pixel set by the above way.

[0089] S104, according to the preset statistical characteristics of the distribution of the interference pixels, identify the interference pixels in the binary map.

[0090] Research has found that the local discharge time is correlated throughout the entire voltage cycle. Therefore, in the PRPD spectrum, the local discharge pixels are clustered in the distribution of the PRPD spectrum, and the interference pixels do not have phase correlation. Therefore, the interference pixels are relatively sparse in the distribution of the PRPD spectrum. Therefore, this embodiment can identify the interference pixels by the degree of sparsity. The complexity of the interference pixel identification method is low, which can improve efficiency and reduce redundant pixels for local discharge type identification.

[0091] Based on the above research findings, the preset distribution statistical characteristics of the interference pixels can be: the sparsity of the interference pixels is greater than the sparsity of the partial discharge pixels, the sparsity of the interference pixels and the sparsity of the partial discharge pixels are represented by density values, and the interference pixels in the binary map are identified by the density values.

[0092] An optional process is: determine the neighborhood area of ​​the pixel to be identified in the binary map, the pixel to be identified is the pixel in the binary map other than the noise pixel, calculate the density value of the pixel to be identified based on the grayscale value of each pixel in the neighborhood area of ​​the pixel to be identified, if the density value of the pixel to be identified is less than or equal to a preset density threshold, determine that the pixel to be identified is an interference pixel, if the density value of the pixel to be identified is greater than the preset density threshold, determine that the pixel to be identified is a partial discharge pixel, and the preset density threshold is the minimum density value when the pixel to be identified is a partial discharge pixel.

[0093] Among them, one definition of the neighborhood area of ​​the pixel to be identified in the binary atlas is: with r as the radius, the coordinate position of the i-th pixel (x i ,y i ) is the center of the circle, and the area demarcated is R i , the region R i The value of r can be, but is not limited to, 4. A calculation formula for the density value is as follows:

[0094]

[0095] ρ i is the density value of the i-th pixel, if ρ i ρ th , then the i-th pixel is an interference pixel; if ρ i> ρ th , then the i-th pixel is a partial discharge pixel. ρ th is the preset density threshold, such as ρ th =4. The pixel to be identified is g(x i ,y i )=1, because the noise pixel in the binary image is identified in step S103, and g(x i ,y ipixels with g(x i ,y i )=1 are local discharge pixels, thus the noise pixels and interference pixels in the PRPD graph are identified through steps S103 and S104, the number of pixels input to the partial discharge type identification model is reduced, most of the pixels input to the partial discharge type identification model are local discharge pixels, the diversity of features in the PRPD graph is reduced, and thus the accuracy, precision and identification efficiency are improved.

[0096] The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 2 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 2 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 2 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 3 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 3 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 4 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 4 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 5 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 5 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method, Figure 6 The gray scale graph shown in FIG. 1 is processed by the phase-resolved partial discharge graph processing method,

[0097] As can be seen from the above technical solutions, the phase-resolved partial discharge (PRPD) pattern processing method provided in the embodiments of the present application can identify noise pixels and interference pixels in a binary PRPD pattern. Consequently, only PD pixels are input into the PD type recognition model, reducing the number and types of pixels required, thereby avoiding the "curse of dimensionality" problem and improving accuracy. Furthermore, noise pixels are identified based on preset distribution statistics of the noise pixels, the distribution statistics of each row of pixels in the pattern along the ordinate, and the distribution statistics of each column of pixels in the pattern along the abscissa. Interference pixels are identified based on preset distribution statistics of the interference pixels. This effectively utilizes the distribution statistics of the noise and interference pixels (which can be considered expert knowledge) for recognition without requiring any dataset training, resulting in unsupervised pixel recognition and highly robust performance. Moreover, after the PRPD spectrum is processed by the phase-resolved partial discharge spectrum processing method provided in the embodiment of the present application, the difference between the spectrum input into the partial discharge type recognition model and the PRPD spectrum used for training the partial discharge type recognition model is small, thereby reducing the production cost of the PRPD spectrum used for training and improving the robust performance of the partial discharge type recognition model.

[0098] A phase-resolved partial discharge pattern processing method provided by an embodiment of the present application has been described above. The following describes an apparatus for executing the phase-resolved partial discharge pattern processing method.

[0099] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of a phase-resolved partial discharge spectrum processing device provided in an embodiment of the present application. For detailed descriptions of each unit in the phase-resolved partial discharge spectrum processing device, please refer to the above method embodiment and will not be described in detail here. Figure 7 As shown, the phase-resolved partial discharge spectrum processing device may include: a conversion unit 10 , an acquisition unit 20 and an identification unit 30 .

[0100] The conversion unit 10 is configured to obtain a binary map of the phase-resolved partial discharge (PRPD) map. One method for the conversion unit 10 to obtain the binary map is to: determine an effective pixel region in the PRPD map, normalize the size of the effective pixel region to obtain an effective pixel map of a target size; convert the effective pixel map into a grayscale map; determine a grayscale threshold, and binarize the grayscale map using the grayscale threshold to obtain the binary map.

[0101] The acquisition unit 20 is configured to acquire a distribution statistical feature of each row of pixels in the binary map in a vertical coordinate direction and a distribution statistical feature of each column of pixels in a horizontal coordinate direction. The distribution statistical feature of each row of pixels in the vertical coordinate direction is used to indicate the distribution of each row of pixels in the phase. The distribution statistical feature of each column of pixels in the horizontal coordinate direction is used to indicate the amplitude range of each column of pixels.

[0102] In a possible implementation, the acquisition unit 20 projects the pixels in the binary map to the vertical coordinate and the horizontal coordinate respectively, to obtain a first projection total amount of each row of pixels in the vertical coordinate direction and a second projection total amount of each column of pixels in the horizontal coordinate direction in the binary map. The first projection total amount is the distribution statistical feature of each row of pixels in the vertical coordinate direction. The second projection total amount is the distribution statistical feature of each column of pixels in the horizontal coordinate direction.

[0103] The identification unit 30 is configured to identify noise pixels in the binary map according to a preset distribution statistical feature of the noise pixels, the distribution statistical feature of each row of pixels in the vertical coordinate direction, and the distribution statistical feature of each column of pixels in the horizontal coordinate direction, and to identify interference pixels in the binary map according to a preset distribution statistical feature of the interference pixels.

[0104] The preset distribution statistical feature of the noise pixels includes that the noise pixels are uniformly distributed in the horizontal coordinate and the amplitude range of the noise pixels is smaller than the amplitude range of partial discharge pixels. The partial discharge pixels are pixels in the map that reflect the characteristics of the partial discharge. The preset distribution statistical feature of the interference pixels includes that the sparsity of the interference pixels is greater than the sparsity of the partial discharge pixels. The sparsity of the interference pixels and the sparsity of the partial discharge pixels are represented by density values.

[0105] Correspondingly, the identification unit 30 identifies the noise pixels and the interference pixels as follows:

[0106] If the first projection total quantity is equal to the width of the binary graph, it is determined that all the pixels under the row corresponding to the first projection total quantity are suspected noise pixels, and the first projection total quantity being equal to the width of the binary graph indicates that the phases of all the pixels under the row corresponding to the first projection total quantity are uniformly distributed; if the first projection total quantity is not equal to the width of the binary graph, it is determined that all the pixels under the row corresponding to the first projection total quantity are not noise pixels; a position coordinate marked for each suspected noise pixel is obtained, the position coordinate including a position in a horizontal coordinate direction and a position in a vertical coordinate direction; a minimum position is obtained from all the positions in the vertical coordinate direction, the minimum position being a position with the minimum value among all the positions; a noise pixel screening condition is determined according to the minimum position and a second projection total quantity with the minimum value among all the second projection total quantities, the noise pixel screening condition being used to limit an amplitude range of the noise pixels; if the position of the suspected noise pixel in the vertical coordinate direction meets the noise pixel screening condition, it is determined that the suspected noise pixel is a noise pixel; if the position of the suspected noise pixel in the vertical coordinate direction does not meet the noise pixel screening condition, it is determined that the suspected noise pixel is not a noise pixel.

[0107] A neighborhood region of a to-be-identified pixel in the binary graph is determined, the to-be-identified pixel being a pixel other than the noise pixel in the binary graph; a density value of the to-be-identified pixel is calculated according to the gray values of the pixels in the neighborhood region of the to-be-identified pixel; if the density value of the to-be-identified pixel is less than or equal to a preset density threshold, it is determined that the to-be-identified pixel is an interference pixel; if the density value of the to-be-identified pixel is greater than the preset density threshold, it is determined that the to-be-identified pixel is a partial discharge pixel, the partial discharge pixel being a pixel in the graph that embodies the characteristics of the partial discharge, and the preset density threshold being the minimum density value when the to-be-identified pixel is the partial discharge pixel.

[0108] In the embodiments of the present application, an electronic device is also provided. Referring to FIG. 1, a structural schematic diagram of an electronic device suitable for implementing the electronic device in the embodiments of the present application is shown. The electronic device in the embodiments of the present application can include, but is not limited to, a fixed terminal such as a mobile phone, a notebook computer, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a desktop computer, and the like. Figure 8 The electronic device shown in FIG. 1 is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application. Figure 8 The electronic device shown in FIG. 1 is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0109] As shown in FIG. 1, the electronic device can include a processor 101, a memory 102, a communication interface 103, and a power supply 104. Figure 8As shown, the electronic device can include a processing device (e.g., a central processor, a graphics processor, etc.) 801 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 802 or loaded from a storage device 808 into a random access memory (RAM) 803. In a state where the electronic device is powered on, various programs and data required for operation of the electronic device are also stored in the RAM 803. The processing device 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804. The ROM 802, the RAM 803, and the storage device 808 can serve as a memory of the electronic device, and the processing device 801 can serve as a processor of the electronic device, the memory being used to store a computer program; the processor being used for the computer program to enable the electronic device to implement any one of the phase-resolved partial discharge pattern processing methods provided in the embodiments of the present application.

[0110] Generally, the following devices can be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a memory card, a hard disk, etc.; and communication devices 809. The communication devices 809 can allow the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 The electronic device is shown as having various devices, but it should be understood that all of the shown devices are not required. More or fewer devices can alternatively be implemented.

[0111] The embodiments of the present application also provide a computer program product including computer readable instructions, which, when executed on an electronic device, cause the electronic device to implement any one of the phase-resolved partial discharge pattern processing methods provided in the embodiments of the present application.

[0112] The embodiments of the present application also provide a computer readable storage medium carrying one or more computer programs, which, when executed by an electronic device, can cause the electronic device to implement any one of the phase-resolved partial discharge pattern processing methods provided in the embodiments of the present application.

[0113] It should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate units can or can not be physically separate, and the units displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment. In addition, the connection relationship between the modules in the apparatus embodiment provided in the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.

[0114] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and the necessary general hardware, and of course can also be realized by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. Generally, functions completed by computer programs can be easily realized by corresponding hardware, and the specific hardware structure for realizing the same function can also be various, such as analog circuit, digital circuit or special circuit, etc. However, for the present application, software program implementation is a better embodiment. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products, which are stored in readable storage media, such as computer floppy disks, U disks, mobile hard disks, ROM, RAM, magnetic or optical disks, etc., including a plurality of instructions for making a computer device (which can be a personal computer, a training device, or a network device, etc.) execute the methods described in various embodiments of the present application.

[0115] In the above embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, it can be realized in the form of a computer program product in whole or in part.

[0116] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, training device or data center to another website, computer, training device or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be stored by the computer or a data storage device such as a training device, a data center, etc. integrated with one or more available media sets. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

Claims

1. A phase-resolved partial discharge spectrum processing method, characterized in that: include: Obtain a binary map of the phase-resolved partial discharge PRPD map; Obtaining distribution statistical characteristics of each row of pixels in the ordinate direction and distribution statistical characteristics of each column of pixels in the abscissa direction in the binarized atlas, wherein the distribution statistical characteristics of each row of pixels in the ordinate direction are used to indicate the distribution of the phases of each row of pixels, and the distribution statistical characteristics of each column of pixels in the abscissa direction are used to indicate the amplitude range of each column of pixels; Identifying noise pixels in the binarized image based on preset distribution statistical characteristics of noise pixels, distribution statistical characteristics of pixels in each row in the ordinate direction, and distribution statistical characteristics of pixels in each column in the abscissa direction; According to the preset distribution statistical characteristics of the interference pixels, the interference pixels in the binarized image are identified.

2. The method according to claim 1, characterized in that The preset distribution statistical characteristics of the noise pixels include: the noise pixels are evenly distributed on the abscissa and the amplitude range of the noise pixels is smaller than the amplitude range of the partial discharge pixels, the partial discharge pixels being pixels in the atlas that exhibit characteristics of partial discharge; The preset distribution statistical characteristics of the interference pixels include: the sparsity of the interference pixels is greater than the sparsity of the partial discharge pixels, and the sparsity of the interference pixels and the sparsity of the partial discharge pixels are represented by density values.

3. The method according to claim 1 or 2, characterized in that The obtaining of the distribution statistical characteristics of each row of pixels in the vertical coordinate direction and the distribution statistical characteristics of each column of pixels in the horizontal coordinate direction in the binary atlas includes: The pixels in the binary atlas are projected onto the ordinate and the abscissa respectively to obtain a first projection total of each row of pixels in the ordinate direction and a second projection total of each column of pixels in the abscissa direction. The first projection total is the distribution statistical feature of the pixels in each row in the ordinate direction, and the second projection total is the distribution statistical feature of the pixels in each column in the abscissa direction.

4. The method according to claim 3, characterized in that The identifying of the noise pixels in the binarized image according to the preset distribution statistical characteristics of the noise pixels, the distribution statistical characteristics of the pixels in each row in the vertical coordinate direction, and the distribution statistical characteristics of the pixels in each column in the horizontal coordinate direction includes: If the first projection total amount is equal to the width of the binarized spectrum, it is determined that all pixels in the row corresponding to the first projection total amount are suspected noise pixels, and the fact that the first projection total amount is equal to the width of the binarized spectrum indicates that the phases of all pixels in the row corresponding to the first projection total amount are uniformly distributed; If the first projection total amount is not equal to the width of the binarized atlas, determining that all pixels in the row corresponding to the first projection total amount are not noise pixels; Obtaining position coordinates marked for each of the suspected noise pixels, the position coordinates including a position in the abscissa direction and a position in the ordinate direction; Obtaining a minimum position from all positions in the vertical coordinate direction, wherein the minimum position is the position with the smallest value among all positions; determining a noise pixel screening condition according to the minimum position and the second projection total amount with the smallest value among all the second projection total amounts, wherein the noise pixel screening condition is used to limit the amplitude range of the noise pixel; If the position of the suspected noise pixel in the vertical coordinate direction meets the noise pixel screening condition, determining that the suspected noise pixel is a noise pixel; If the position of the suspected noise pixel in the vertical coordinate direction does not meet the noise pixel screening condition, it is determined that the suspected noise pixel is not a noise pixel.

5. The method according to claim 1 or 2, characterized in that The step of identifying the interference pixels in the binary image according to the preset distribution statistical characteristics of the interference pixels includes: Determine a neighborhood area of ​​a pixel to be identified in the binary image, where the pixel to be identified is a pixel in the binary image excluding the noise pixel; Calculating the density value of the pixel to be identified based on the grayscale value of each pixel in the neighborhood area of ​​the pixel to be identified; If the density value of the pixel to be identified is less than or equal to a preset density threshold, determining that the pixel to be identified is an interference pixel; If the density value of the pixel to be identified is greater than the preset density threshold, the pixel to be identified is determined to be a partial discharge pixel. The partial discharge pixel is a pixel in the spectrum that reflects the characteristics of local discharge. The preset density threshold is the minimum density value when the pixel to be identified is the partial discharge pixel.

6. The method according to claim 1 or 2, characterized in that The method of obtaining a binary spectrum of a phase-resolved partial discharge (PRPD) spectrum comprises: Determining an effective pixel area in the PRPD map, and normalizing the size of the effective pixel area to obtain an effective pixel map with a target size; Converting the effective pixel map into a grayscale image; A grayscale threshold is determined, and the grayscale image is binarized using the grayscale threshold to obtain the binarized image spectrum.

7. A phase-resolved partial discharge spectrum processing device, characterized in that: include: A conversion unit, used for obtaining a binary spectrum of a phase-resolved partial discharge (PRPD) spectrum; an acquisition unit, configured to acquire distribution statistical characteristics of pixels in each row in the ordinate direction and distribution statistical characteristics of pixels in each column in the abscissa direction in the binarized atlas, wherein the distribution statistical characteristics of pixels in each row in the ordinate direction are used to indicate the distribution of the phases of the pixels in each row, and the distribution statistical characteristics of pixels in each column in the abscissa direction are used to indicate the amplitude range of the pixels in each column; An identification unit is used to identify noise pixels in the binarized image based on preset distribution statistical characteristics of noise pixels, distribution statistical characteristics of each row of pixels in the vertical coordinate direction, and distribution statistical characteristics of each column of pixels in the horizontal coordinate direction, and to identify interference pixels in the binarized image based on preset distribution statistical characteristics of interference pixels.

8. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the phase-resolved partial discharge spectrum processing method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so that the electronic device can implement the phase-resolved partial discharge spectrum processing method according to any one of claims 1 to 6.

10. A computer storage medium, characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the phase-resolved partial discharge spectrum processing method according to any one of claims 1 to 6.

Images