Method and device for testing component circuit based on high-voltage switchgear

Abstract

The present invention relates to the field of artificial intelligence technology, and discloses a method and device for testing the component circuit of a high-voltage switchgear. The method includes: obtaining a circuit image of the component of the target high-voltage switchgear, generating a positioning point of the component according to a preset similarity threshold circuit image, performing angle correction and displacement correction on the circuit image according to the positioning point to obtain a displacement-corrected image; using a preset pixel adjustment algorithm to perform pixel integerization processing on the displacement-corrected image to obtain an adjusted image of the displacement-corrected image; performing noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, performing region division on the noise-reduced image to obtain a region image of the noise-reduced image; using a preset reference image to generate a difference feature of the region image, and using the difference feature to perform abnormal circuit positioning on the component. The present invention can improve the efficiency of testing the component circuit of a high-voltage switchgear.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a method and device for testing the component circuit of a high-voltage switchgear. Background Art

[0002] A large number of various types of electronic components are used in high-voltage switchgear. Most of the equipment failures are caused by the failure or damage of electronic components. Therefore, it is particularly important to correctly detect electronic components.

[0003] When the components are already encapsulated in the high-voltage switchgear, it is more difficult to locate abnormal circuits using traditional diode detection methods. At the same time, using the diode detection method requires individual experiments to determine the quality of the components, resulting in low efficiency. Therefore, how to improve the testing efficiency of the component circuit of high-voltage switchgear has become an urgent problem to be solved. Summary of the Invention

[0004] The present invention provides a method and device for testing the component circuit of a high-voltage switchgear, and its main purpose is to solve the problem of low efficiency in testing the component circuit of a high-voltage switchgear.

[0005] To achieve the above object, a method for testing the component circuit of a high-voltage switchgear provided by the present invention includes:[[]]

[0006] Obtaining a circuit image of the components of the target high-voltage switchgear, generating positioning points of the components according to the circuit image, and performing angle correction on the circuit image according to the positioning points to obtain an angle-corrected image of the circuit image;

[0007] Performing displacement correction on the angle-corrected image to obtain a displacement-corrected image of the angle-corrected image;

[0008] Using a preset pixel adjustment algorithm to perform pixel integerization processing on the displacement-corrected image to obtain an adjusted image of the displacement-corrected image, where the preset pixel adjustment algorithm is:

[0009] g(i′,j′)=(1-i′+m)(1-j′+n)g(m,n)+(i′-m)(1-j′+n)g(m+1,n)+(1-i′+m)(j′-n)g(m,n+1)+(i′-m)(j′-n)g(m+1,n+1)

[0010] Among them, g(i′, j′) is the gray value of the interpolation point (i′, j′) of the displacement-corrected image, i′ is the horizontal coordinate of the interpolation point (i′, j′), j′ is the vertical coordinate of the interpolation point (i′, j′), (m, n) is a pixel point of the displacement-corrected image. Among them, the pixel point (m, n), the pixel point (m + 1, n), the pixel point (m + 1, n + 1), and the pixel point (m, n + 1) are the nearest neighbor pixel points of the interpolation point (i′, j′), g(m, n) is the gray value of the pixel point (m, n), g(m + 1, n) is the gray value of the pixel point (m + 1, n), g(m, n + 1) is the gray value of the pixel point (m, n + 1), g(m + 1, n + 1) is the gray value of the pixel point (m + 1, n + 1), m is the horizontal coordinate of the pixel point (m, n), and n is the vertical coordinate of the pixel point (m, n);

[0011] Perform noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, and perform region division on the noise-reduced image to obtain a region image of the noise-reduced image;

[0012] Generate a difference feature of the region image using a preset reference image, and use the difference feature to perform abnormal circuit location on the component body.

[0013] Optionally, the generating the positioning point of the component body according to the circuit image includes:

[0014] Generate an image component of the circuit image using a preset color component algorithm, and perform binarization processing on the circuit image using the image component and a preset component threshold to obtain a binarized image of the circuit image;

[0015] Determine an initial positioning region of the component body according to the binarized image, generate an initial region centroid of the initial positioning region one by one, and generate a positioning point of the component body according to the initial region centroid.

[0016] Optionally, the generating the image component of the circuit image using a preset color component algorithm includes:

[0017] Generate the image component of the circuit image using the following color component algorithm:

[0018]

[0019] Wherein, H is the image hue of the circuit image, S is the image saturation of the circuit image, I is the image brightness of the circuit image, R is the red light value of the circuit image, G is the green light value of the circuit image, B is the blue light value of the circuit image, min(*) is the minimum value function, and arccos(*) is the arccosine function.

[0020] Optionally, the angle correction of the circuit image according to the positioning point to obtain the angle-corrected image of the circuit image includes:

[0021] Generating a correction baseline of the circuit image according to the positioning point;

[0022] Performing angle rotation on the circuit image according to the correction baseline to obtain the angle-corrected image of the circuit image.

[0023] Optionally, the pixel integerization process of the displacement-corrected image by using a preset pixel adjustment algorithm to obtain the adjusted image of the displacement-corrected image includes:

[0024] Selecting one pixel point in the displacement-corrected image as an interpolation point and obtaining the nearest pixel point of the interpolation point;

[0025] Generating the gray value of the interpolation point of the displacement-corrected image according to the gray value of the nearest pixel point and the preset pixel adjustment algorithm;

[0026] Performing pixel integerization on the displacement-corrected image according to the gray value of the interpolation point to obtain the adjusted image of the displacement-corrected image.

[0027] Optionally, the noise reduction process of the adjusted image to obtain the noise-reduced image of the adjusted image includes:

[0028] Performing noise reduction on the adjusted image by using the following Gaussian convolution algorithm to obtain the noise-reduced image of the adjusted image:

[0029]

[0030] Wherein, Gauss(r, c, σ) is the Gaussian matrix of the adjusted image, σ is the image pixel variance of the adjusted image, r is the horizontal position of the image pixel of the adjusted image, and c is the vertical position of the image pixel of the adjusted image.

[0031] Optionally, the region division of the noise-reduced image to obtain the region image of the noise-reduced image includes:

[0032] Performing region division on the noise-reduced image according to the preset line features to obtain the sub-images of the noise-reduced image;

[0033] Perform region identification on the sub-image to obtain the image label of the sub-image;

[0034] Generate the region image of the noise reduction image according to the image label and the sub-image.

[0035] Optionally, the generating the distinguishing feature of the region image by using a preset reference image includes:

[0036] Perform region selection on the preset reference image according to the region image to obtain the target region of the preset reference image;

[0037] Obtain the reference feature of the target region, and calculate the feature similarity between the reference feature and the feature of the region image;

[0038] Generate the distinguishing feature of the region image according to the feature similarity and a preset similarity threshold.

[0039] Optionally, the positioning of abnormal circuits on the component body by using the distinguishing feature includes:

[0040] Determine the region image corresponding to the distinguishing feature, and generate the abnormal region of the component body according to the image label of the region image;

[0041] Use the abnormal region to perform abnormal circuit positioning on the target component body.

[0042] To solve the above problems, the present invention also provides a component body circuit test device based on a high-voltage switchgear, and the device includes:

[0043] An angle correction module, configured to obtain a circuit image of a component body of a target high-voltage switchgear, generate a positioning point of the component body according to the circuit image, and perform angle correction on the circuit image according to the positioning point to obtain an angle-corrected image of the circuit image;

[0044] A displacement correction module, configured to perform displacement correction on the angle-corrected image to obtain a displacement-corrected image of the angle-corrected image;

[0045] A pixel integerization module, configured to perform pixel integerization processing on the displacement-corrected image by using a preset pixel adjustment algorithm to obtain an adjusted image of the displacement-corrected image, where the preset pixel adjustment algorithm is:

[0046] g(i′,j′)=(1 - i′ + m)(1 - j′ + n)g(m,n)+(i′ - m)(1 - j′ + n)g(m + 1,n)+(1 - i′ + m)(j′ - n)g(m,n + 1)+(i′ - m)(j′ - n)g(m + 1,n + 1)

[0047] Among them, g(i′, j′) is the gray value of the interpolation point (i′, j′) of the displacement-corrected image, i′ is the horizontal coordinate of the interpolation point (i′, j′), j′ is the vertical coordinate of the interpolation point (i′, j′), (m, n) is the pixel point of the displacement-corrected image. Among them, the pixel point (m, n), the pixel point (m + 1, n), the pixel point (m + 1, n + 1), and the pixel point (m, n + 1) are the nearest neighbor pixel points of the interpolation point (i′, j′), g(m, n) is the gray value of the pixel point (m, n), g(m + 1, n) is the gray value of the pixel point (m + 1, n), g(m, n + 1) is the gray value of the pixel point (m, n + 1), g(m + 1, n + 1) is the gray value of the pixel point (m + 1, n + 1), m is the horizontal coordinate of the pixel point (m, n), and n is the vertical coordinate of the pixel point (m, n);

[0048] An image noise reduction module, configured to perform noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, and perform region division on the noise-reduced image to obtain a region image of the noise-reduced image;

[0049] An abnormal circuit location module, configured to generate a difference feature of the region image by using a preset reference image, and perform abnormal circuit location on the component by using the difference feature.

[0050] In an embodiment of the present invention, by acquiring a circuit image of a component of a target high-voltage switchgear, determining an object to be analyzed, generating a positioning point of the component according to the circuit image, and performing angle correction and displacement correction on the circuit image according to the positioning point, the errors caused by angle problems and light problems are solved. Pixel integerization processing and noise reduction processing are performed on the generated displacement-corrected image to further reduce the error of abnormal analysis and improve the positioning accuracy. Finally, a difference feature of the region image is generated by using a preset reference image, and the difference feature is used to achieve rapid positioning of the abnormal circuit of the component. Therefore, the present invention provides a method and device for testing a component circuit of a high-voltage switchgear, which can solve the problem of low efficiency in testing the component circuit of a high-voltage switchgear. Description of the Drawings

[0051] Figure 1 It is a schematic flowchart of a method for testing a component circuit of a high-voltage switchgear provided by an embodiment of the present invention;

[0052] Figure 2 It is a schematic flowchart of integerization of image pixels provided by an embodiment of the present invention;

[0053] Figure 3 It is a schematic flowchart of image region division provided by an embodiment of the present invention;

[0054] Figure 4 It is a functional module diagram of a component circuit test device based on a high-voltage switchgear provided by an embodiment of the present invention;

[0055] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] An embodiment of the present application provides a method for testing a component circuit based on a high-voltage switchgear. The execution subject of the method for testing a component circuit based on a high-voltage switchgear includes but is not limited to at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for testing a component circuit based on a high-voltage switchgear can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0058] Refer to Figure 1 As shown, it is a flow diagram of a method for testing a component circuit based on a high-voltage switchgear provided by an embodiment of the present invention. In this embodiment, the method for testing a component circuit based on a high-voltage switchgear includes:

[0059] S1. Obtain a circuit image of a component of a target high-voltage switchgear, generate a positioning point of the component according to the circuit image, and perform angle correction on the circuit image according to the positioning point to obtain an angle-corrected image of the circuit image.

[0060] In an embodiment of the present invention, the target high-voltage switchgear refers to a high-voltage switchgear that needs to be studied. The high-voltage switchgear refers to an electrical appliance with a rated voltage of 1 kV or above, mainly used for opening and closing a conductive circuit. It is a general term for a high-voltage switch and its corresponding control, measurement, protection, regulation devices, as well as accessories, enclosures, supports and other components and their electrical and mechanical connections. It is an important control device for connecting and disconnecting circuits and removing and isolating faults.

[0061] Specifically, an X-ray can be used to obtain a circuit image of the component body in the target high-voltage switchgear.

[0062] Specifically, generating the positioning points of the component body according to the circuit image is to prevent detection errors caused by the angle problem of the circuit image, and the positioning points are used to correct the orientation of the circuit image.

[0063] In the embodiment of the present invention, generating the positioning points of the component body according to the circuit image includes:

[0064] Using a preset color component algorithm to generate image components of the circuit image, and performing binarization processing on the circuit image using the image components and a preset component threshold to obtain a binarized image of the circuit image;

[0065] Determining an initial positioning area of the component body according to the binarized image, generating initial area centroids of the initial positioning area one by one, and generating positioning points of the component body according to the initial area centroids.

[0066] Specifically, determining the initial positioning area of the component body according to the binarized image means determining the initial positioning area of the component body according to the pixel distribution of the binarized image. Assume that the initial positioning area is a positioning circle, and the number of positioning circles can be three or four.

[0067] Further, generating the initial area centroids of the initial positioning area one by one means determining the centroids of all positioning circles, and the centroid calculation formula can be used; generating the positioning points of the component body according to the initial area centroids means taking the area centroids as the positioning points of the component body.

[0068] Specifically, since traditional binarization mainly processes the target image through a global threshold or a local threshold, but these two methods cannot achieve good results in application. Due to the influence of light and the factors of the high-voltage switchgear itself on the circuit image, there are often situations of uneven brightness distribution and gray level mutation in the image to be processed. Especially when processing the image collected by rays, due to the certain angle between the ray collection position and the high-voltage switchgear and the uncertainty of the position of the ambient light source, the collected image is blurred, or the contrast between the target numbers and the background color in the image is not high, making it difficult to distinguish through gray level processing. Therefore, it is difficult to effectively separate the target numbers from the background using traditional binarization methods.

[0069] Further, performing binarization processing on the circuit image using the image components and a preset component threshold means determining the thresholds for image processing through three image components respectively, and then superimposing the processing results to achieve the purpose of binarizing the image.

[0070] Specifically, generating the image components of the circuit image by using a preset color component algorithm includes:

[0071] Generating the image components of the circuit image by using the following color component algorithm:

[0072]

[0073] Where H is the image hue of the circuit image, S is the image saturation of the circuit image, I is the image brightness of the circuit image, R is the red light value of the circuit image, G is the green light value of the circuit image, B is the blue light value of the circuit image, min(*) is the minimum value function, and arccos(*) is the arccosine function.

[0074] Specifically, compared with the RGB model, the colors represented by the preset color component algorithm are more adaptable to the colors actually interpreted by humans. The preset color component algorithm starts from the human visual system and describes colors in terms of hue, color saturation, and brightness.

[0075] Specifically, the preset component thresholds are determined empirically. Assuming that the component threshold of the image hue is (10°, 40°), when the image hue of the circuit image is within (10°, 40°), this area of the circuit image can be selected; the component threshold of the image saturation can be (0.1, 0.6).

[0076] In the embodiment of the present invention, performing angle correction on the circuit image according to the positioning points to obtain the angle-corrected image of the circuit image includes:

[0077] Generating a correction baseline of the circuit image according to the positioning points;

[0078] Performing angle rotation on the circuit image according to the correction baseline to obtain the angle-corrected image of the circuit image.

[0079] Specifically, generating the correction baseline of the circuit image according to the positioning points means connecting the positioning points to obtain the connection line of the positioning points, and using the connection line as the correction baseline of the circuit image.

[0080] Specifically, when the circuit image is deflected, it is not conducive to the generation and preservation of standard information. Therefore, it is necessary to perform rotation correction on the image according to its deflection situation.

[0081] S2. Performing displacement correction on the angle-corrected image to obtain the displacement-corrected image of the angle-corrected image.

[0082] In the embodiment of the present invention, the displacement correction of the angle-corrected image means that after the angle correction of the circuit image, further correction needs to be performed on the horizontal and vertical position offsets of the image to be detected.

[0083] S3. Use a preset pixel adjustment algorithm to perform pixel integerization processing on the displacement-corrected image to obtain an adjusted image of the displacement-corrected image.

[0084] In the embodiment of the present invention, the reason for using a preset pixel adjustment algorithm to perform pixel integerization processing on the displacement-corrected image is that when the circuit image is rotated, the coordinates and pixel values of each pixel will change. This is because the coordinates of the circuit image are integers, and the rotated coordinates may not exactly fall on integer coordinates. Therefore, it is necessary to estimate the pixel values at the integer coordinate positions after rotation, that is, interpolation needs to be performed using a preset pixel adjustment algorithm.

[0085] In the embodiment of the present invention, refer Figure 2 As shown, using a preset pixel adjustment algorithm to perform pixel integerization processing on the displacement-corrected image to obtain an adjusted image of the displacement-corrected image includes:

[0086] S21. Select one pixel point in the displacement-corrected image as an interpolation point, and obtain the nearest neighbor pixel points of the interpolation point;

[0087] S22. Generate the gray value of the interpolation point of the displacement-corrected image according to the gray value of the nearest neighbor pixel point and the preset pixel adjustment algorithm;

[0088] S23. Perform pixel integerization processing on the displacement-corrected image according to the gray value of the interpolation point to obtain an adjusted image of the displacement-corrected image.

[0089] Specifically, assume that the coordinates of the interpolation point are (i′, j′), and there can be four nearest neighbor pixel points of the interpolation point, which are pixel point (m, n), pixel point (m + 1, n), pixel point (m + 1, n + 1), and pixel point (m, n + 1), where m < i′ < m + 1) and n < j′ < n + 1).

[0090] Specifically, the interval between white and black is divided into several levels according to a logarithmic relationship, which is called "gray level". The range of gray values generally ranges from 0 to 255, with white being 255 and black being 0.

[0091] Specifically, the preset pixel adjustment algorithm is:

[0092] g(i′,j′) = (1 - i′ + m)(1 - j′ + n)g(m,n) + (i′ - m)(1 - j′ + n)g(m + 1,n) + (1 - i′ + m)(j′ - n)g(m,n + 1) + (i′ - m)(j′ - n)g(m + 1,n + 1)

[0093] Wherein, g(i′,j′) is the gray value of the interpolation point (i′,j′) of the displacement-corrected image, i′ is the horizontal coordinate of the interpolation point (i′,j′), j′ is the vertical coordinate of the interpolation point (i′,j′), (m,n) is the pixel point of the displacement-corrected image. Among them, the pixel point (m,n), the pixel point (m + 1,n), the pixel point (m + 1,n + 1) and the pixel point (m,n + 1) are the nearest neighbor pixel points of the interpolation point (i′,j′), g(m,n) is the gray value of the pixel point (m,n), g(m + 1,n) is the gray value of the pixel point (m + 1,n), g(m,n + 1) is the gray value of the pixel point (m,n + 1), g(m + 1,n + 1) is the gray value of the pixel point (m + 1,n + 1), m is the horizontal coordinate of the pixel point (m,n), and n is the vertical coordinate of the pixel point (m,n).

[0094] S4. Perform noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, and perform region division on the noise-reduced image to obtain a region image of the noise-reduced image.

[0095] In the embodiment of the present invention, the reason for performing noise reduction processing on the adjusted image is that the image is easily interfered by light sources, backgrounds, and other random factors during the acquisition process, generating noise, and phenomena such as blurring and speckles appear on the image, reducing the image quality. The noise reduction processing refers to filtering out the internal noise of the image while retaining the original information of the image.

[0096] In the embodiment of the present invention, performing noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image includes:

[0097] Performing noise reduction processing on the adjusted image by using the following Gaussian convolution algorithm to obtain a noise-reduced image of the adjusted image:

[0098]

[0099] Wherein, Gauss(r,c,σ) is the Gaussian matrix of the adjusted image, σ is the image pixel variance of the adjusted image, r is the horizontal position of the image pixel of the adjusted image, and c is the vertical position of the image pixel of the adjusted image.

[0100] Specifically, the Gaussian convolution algorithm has strong adaptability and effectively eliminates the interference of noise on the image.

[0101] Specifically, the values of the horizontal position of the image pixels of the adjusted image and the vertical position of the image pixels of the adjusted image are determined according to the size of the convolution kernel during Gaussian convolution. Assuming that the convolution kernel is 5*5, then the value of the horizontal position of the image pixels of the adjusted image is an integer from 0 to 4, and the value of the vertical position of the image pixels of the adjusted image is an integer from 0 to 4.

[0102] Specifically, the Gaussian matrix of the adjusted image is calculated using the Gaussian convolution algorithm. When calculating the sum of the matrix of the Gaussian matrix, the sum of the matrix is divided by its own sum to obtain the Gaussian convolution kernel of the adjusted image, and the adjusted image is denoised using the Gaussian convolution kernel.

[0103] In the embodiment of the present invention, refer Figure 3 As shown, the region division of the denoised image to obtain the region image of the denoised image includes:

[0104] S31. Regionally divide the denoised image according to the preset line features to obtain the sub-images of the denoised image;

[0105] S32. Regionally identify the sub-images to obtain the image labels of the sub-images;

[0106] S33. Generate the region image of the denoised image according to the image labels and the sub-images.

[0107] Specifically, the preset line features refer to the line distribution features in the component body. For example, if the lines in the component body exist in the upper left and lower right of the component body, then only the image regions in the upper left and lower right of the component body need to be acquired; the regionally identifying the sub-images to obtain the image labels of the sub-images refers to image identification of the sub-images; the generating the region image of the denoised image according to the image labels and the sub-images refers to establishing the region image of the denoised image using the one-to-one correspondence between the image labels and the sub-images.

[0108] S5. Generate the difference features of the region image using a preset reference image, and use the difference features to locate abnormal lines in the component body.

[0109] In the embodiment of the present invention, the generating the difference features of the region image using a preset reference image includes:

[0110] Regionally select the preset reference image according to the region image to obtain the target region of the preset reference image;

[0111] Obtain the reference features of the target area, and calculate the feature similarity between the reference features and the features of the area image;

[0112] Generate the distinguishing features of the area image according to the feature similarity and a preset similarity threshold.

[0113] Specifically, the preset reference image is an image of a normal component, which is used as a reference image for the component to be tested; the selecting of the preset reference image according to the area image means selecting the preset reference image according to the position represented by the area image. For example, if the area image represents position A of the component, then position A is also selected in the preset reference image.

[0114] Specifically, the reference features of the target area refer to the normal features of the target position of the component, and the normal features are the features when the component can operate normally; the calculation of the feature similarity between the reference features and the features of the area image can use the Euclidean distance algorithm, and the feature similarity is represented by the reciprocal of the feature distance between the reference features and the image features of the area image. The greater the feature similarity between the two, the more similar they are, and the greater the feature similarity between the two, the greater the difference between them.

[0115] Specifically, the generating of the distinguishing features of the area image according to the feature similarity and a preset similarity threshold means that when the feature similarity is less than the preset similarity threshold, it is determined that the area image corresponding to the feature similarity has distinguishing features, and the distinguishing features are the places that are different from the preset reference image.

[0116] In the embodiment of the present invention, the abnormal circuit positioning of the component by using the distinguishing features includes:

[0117] Determine the area image corresponding to the distinguishing features, and generate the abnormal area of the component according to the image label of the area image;

[0118] Use the abnormal area to perform abnormal circuit positioning on the target component.

[0119] Specifically, the abnormal circuit positioning of the target component by using the abnormal area is carried out by using the one-to-one correspondence between the abnormal area and the circuit distribution of the target component.

[0120] In the embodiment of the present invention, by acquiring the circuit image of the component of the target high-voltage switchgear, determining the object to be analyzed, generating the positioning points of the component according to the circuit image, and performing angle correction and displacement correction on the circuit image according to the positioning points, the errors caused by angle problems and light problems are solved. Pixel integerization processing and noise reduction processing are performed on the generated displacement correction image to further reduce the errors of abnormal analysis, improve the positioning accuracy, and finally generate the difference features of the area image according to the preset comparison image. The abnormal circuit of the component is quickly located by using the difference features. Therefore, the present invention proposes a circuit test method for the component of the high-voltage switchgear, which can solve the problem of low test efficiency of the component circuit of the high-voltage switchgear.

[0121] As Figure 4 shown, it is a functional module diagram of a circuit test device for the component of a high-voltage switchgear provided by an embodiment of the present invention.

[0122] The circuit test device 100 for the component of the high-voltage switchgear according to the present invention can be installed in an electronic device. According to the realized functions, the circuit test device 100 for the component of the high-voltage switchgear can include an angle correction module 101, a displacement correction module 102, a pixel integerization module 103, an image noise reduction module 104, and an abnormal circuit positioning module 105. The modules in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0123] In this embodiment, the functions of each module / unit are as follows:

[0124] The angle correction module 101 is configured to acquire the circuit image of the component of the target high-voltage switchgear, generate the positioning points of the component according to the circuit image, and perform angle correction on the circuit image according to the positioning points to obtain the angle correction image of the circuit image;

[0125] The displacement correction module 102 is configured to perform displacement correction on the angle correction image to obtain the displacement correction image of the angle correction image;

[0126] The pixel integerization module 103 is configured to perform pixel integerization processing on the displacement correction image by using a preset pixel adjustment algorithm to obtain the adjusted image of the displacement correction image, where the preset pixel adjustment algorithm is:

[0127] g(i′,j′) = (1 - i′ + m)(1 - j′ + n)g(m,n) + (i′ - m)(1 - j′ + n)g(m + 1,n) + (1 - i′ + m)(j′ - n)g(m,n + 1) + (i′ - m)(j′ - n)g(m + 1,n + 1)

[0128] Wherein, g(i′,j′) is the gray value of the interpolation point (i′,j′) of the displacement-corrected image, i′ is the horizontal coordinate of the interpolation point (i′,j′), j′ is the vertical coordinate of the interpolation point (i′,j′), (m,n) is a pixel point of the displacement-corrected image. Among them, the pixel point (m,n), the pixel point (m + 1,n), the pixel point (m + 1,n + 1) and the pixel point (m,n + 1) are the nearest neighbor pixel points of the interpolation point (i′,j′), g(m,n) is the gray value of the pixel point (m,n), g(m + 1,n) is the gray value of the pixel point (m + 1,n), g(m,n + 1) is the gray value of the pixel point (m,n + 1), g(m + 1,n + 1) is the gray value of the pixel point (m + 1,n + 1), m is the horizontal coordinate of the pixel point (m,n), and n is the vertical coordinate of the pixel point (m,n);

[0129] The image noise reduction module 104 is configured to perform noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, and perform region division on the noise-reduced image to obtain a region image of the noise-reduced image;

[0130] The abnormal circuit positioning module 105 is configured to generate a difference feature of the region image by using a preset reference image, and perform abnormal circuit positioning on the component by using the difference feature.

[0131] In several embodiments provided by the present invention, it should be understood that the disclosed methods and apparatuses can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0132] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, in each embodiment of the present invention, each functional module can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0134] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0135] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0136] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application device that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use the knowledge to obtain the best results.

[0137] In addition, obviously, the term "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the apparatus claims can also be implemented by one unit or device through software or hardware. The terms such as "first" and "second" are used to indicate names and do not indicate any specific order.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A test method for the component circuit of a high-voltage switchgear, characterized in that, The method includes: Obtaining a circuit image of the component body of the target high-voltage switchgear, generating a positioning point of the component body according to the circuit image, and performing angle correction on the circuit image according to the positioning point to obtain an angle-corrected image of the circuit image; Performing displacement correction on the angle-corrected image to obtain a displacement-corrected image of the angle-corrected image; Performing pixel integerization processing on the displacement-corrected image by using a preset pixel adjustment algorithm to obtain an adjusted image of the displacement-corrected image, where the preset pixel adjustment algorithm is: , where is the interpolation point of the displacement-corrected image gray value, is the interpolation point abscissa, is the interpolation point ordinate, is the pixel of the displacement-corrected image, where the pixel , the pixel , the pixel and the pixel are the nearest neighbor pixels of the interpolation point , is the gray value of the pixel , is the gray value of the pixel , is the gray value of the pixel , is the gray value of the pixel , is the pixel abscissa, is the pixel ordinate; Performing noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, and performing region division on the noise-reduced image to obtain a region image of the noise-reduced image; Generating a difference feature of the region image by using a preset reference image, and performing abnormal circuit positioning on the component body by using the difference feature; The generating the positioning point of the component body according to the circuit image includes: Generating an image component of the circuit image by using a preset color component algorithm, and performing binarization processing on the circuit image by using the image component and a preset component threshold to obtain a binarized image of the circuit image; Determining an initial positioning region of the component body according to the binarized image, generating an initial region centroid of the initial positioning region one by one, and generating a positioning point of the component body according to the initial region centroid.

2. The method for testing the component circuit based on the high-voltage switchgear according to claim 1, wherein, The generating the image component of the circuit image by using a preset color component algorithm includes: Generating the image component of the circuit image by using the following color component algorithm: , where H is the image hue of the circuit image, S is the image saturation of the circuit image, I is the image brightness of the circuit image, R is the red light value of the circuit image, G is the green light value of the circuit image, and B is the blue light value of the circuit image, is the minimum value function, is the arccosine function.

3. The method for testing the component circuit based on the high-voltage switchgear according to claim 1, wherein The performing angle correction on the circuit image according to the positioning point to obtain an angle-corrected image of the circuit image includes: Generating a correction baseline of the circuit image according to the positioning point; Performing angle rotation on the circuit image according to the correction baseline to obtain an angle-corrected image of the circuit image.

4. The method for testing the component circuit based on the high-voltage switchgear according to claim 1, characterized in that, The performing pixel integerization processing on the displacement-corrected image by using a preset pixel adjustment algorithm to obtain an adjusted image of the displacement-corrected image includes: Selecting one pixel point in the displacement-corrected image as an interpolation point, and obtaining the nearest pixel point of the interpolation point; Generating an interpolation point gray value of the displacement-corrected image according to the gray value of the nearest pixel point and the preset pixel adjustment algorithm; Performing pixel integerization processing on the displacement-corrected image according to the interpolation point gray value to obtain an adjusted image of the displacement-corrected image.

5. The method for testing the component circuit based on the high-voltage switchgear according to claim 1, wherein, The performing noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image includes: Performing noise reduction processing on the adjusted image by using the following Gaussian convolution algorithm to obtain a noise-reduced image of the adjusted image: , where is the Gaussian matrix of the adjusted image, is the image pixel variance of the adjusted image, r is the horizontal position of the image pixel of the adjusted image, and c is the vertical position of the image pixel of the adjusted image.

6. The method for testing the component circuit based on the high-voltage switchgear according to claim 1, characterized in that, The performing region division on the noise-reduced image to obtain a region image of the noise-reduced image includes: Performing region division on the noise-reduced image according to a preset circuit feature to obtain a sub-image of the noise-reduced image; Performing region identification on the sub-image to obtain an image label of the sub-image; Generating a region image of the noise-reduced image according to the image label and the sub-image.

7. The method for testing the component circuit based on the high-voltage switchgear according to claim 1, characterized in that, The generating the difference feature of the region image by using a preset reference image includes: Select a region of a preset reference image according to the regional image to obtain a target region of the preset reference image; Obtain the reference features of the target region, and calculate the feature similarity between the reference features and the features of the regional image; Generate the distinguishing features of the regional image according to the feature similarity and a preset similarity threshold.

8. The method for testing the component circuit based on the high-voltage switchgear according to any one of claims 1 to 7, characterized in that The abnormal circuit positioning of the component using the distinguishing features includes: Determine the regional image corresponding to the distinguishing features, and generate an abnormal region of the component according to the image label of the regional image; Use the abnormal region to perform abnormal circuit positioning on the component.

9. A component circuit test device based on high-voltage switchgear, characterized in that, The device includes: An angle correction module, configured to obtain a circuit image of a component of a target high-voltage switchgear, generate a positioning point of the component according to the circuit image, and perform angle correction on the circuit image according to the positioning point to obtain an angle-corrected image of the circuit image; A displacement correction module, configured to perform displacement correction on the angle-corrected image to obtain a displacement-corrected image of the angle-corrected image; A pixel integerization module, configured to perform pixel integerization processing on the displacement-corrected image by using a preset pixel adjustment algorithm to obtain an adjusted image of the displacement-corrected image, where the preset pixel adjustment algorithm is: , where is the interpolation point of the displacement-corrected image 's gray value, is the interpolation point 's horizontal coordinate, is the interpolation point 's vertical coordinate, is the pixel of the displacement-corrected image, where the pixel , the pixel , the pixel and the pixel are the nearest neighbor pixels of the interpolation point , is the gray value of the pixel , is the gray value of the pixel , is the gray value of the pixel , is the gray value of the pixel , m is the horizontal coordinate of the pixel , n is the vertical coordinate of the pixel ; An image noise reduction module, configured to perform noise reduction processing on the adjusted image to obtain a noise-reduced image of the adjusted image, and perform regional division on the noise-reduced image to obtain a regional image of the noise-reduced image; An abnormal circuit positioning module, configured to generate the distinguishing features of the regional image by using a preset reference image, and perform abnormal circuit positioning on the component by using the distinguishing features, The generating the positioning point of the component according to the circuit image includes: Generate an image component of the circuit image by using a preset color component algorithm, perform binarization processing on the circuit image by using the image component and a preset component threshold to obtain a binarized image of the circuit image; Determine an initial positioning region of the component according to the binarized image, generate initial region centroids of the initial positioning region one by one, and generate a positioning point of the component according to the initial region centroids.

Images