A method for recognizing corrosion state of grounding grid based on image processing

Abstract

The application discloses a kind of based on image processing's ground net corrosion state identification method, it is related to electric power system ground net corrosion detection technical field, solve the technical problem that existing ground net corrosion detection method exists low detection efficiency, poor accuracy, cannot intuitively evaluate corrosion degree.Solution points are as follows: obtain ground net surface image;The image is preprocessed, and the preprocessed image is obtained;Extract the corrosion feature parameter of preprocessed image, and the corrosion feature parameter includes color feature parameter and texture feature parameter;Based on the corrosion feature parameter, corrosion state identification model is used to identify the corrosion state of ground net, and corrosion state identification result is obtained.The application is mainly used for the corrosion state of electric power system ground net fast, accurate identification, improve the safety and reliability of ground net operation.

Description

Technical Field

[0001] This invention relates to the field of power system grounding grid corrosion detection technology, and in particular to a grounding grid corrosion status identification method based on image processing. Background Technology

[0002] The grounding grid is a crucial piece of equipment in power system substations. Its primary function is to provide grounding protection for electrical equipment, ensuring the safe and stable operation of the power system. However, because grounding grids are buried underground for extended periods, they are susceptible to corrosion and even breakage due to factors such as soil corrosion and electrochemical corrosion. This severely impacts the conductivity of the grounding grid and the safe operation of the power system.

[0003] Currently, the main methods for detecting grounding grid corrosion include: excavation inspection, electrochemical detection, and electromagnetic field detection. Excavation inspection is the most direct method, but it suffers from drawbacks such as high workload, high cost, and strong destructiveness. Electrochemical detection determines the corrosion state by measuring parameters such as the polarization resistance of the grounding grid, but its accuracy is greatly affected by the soil environment. Electromagnetic field detection infers the grounding grid state by measuring the distribution of the electromagnetic field on the ground surface, but it suffers from low resolution and susceptibility to interference.

[0004] With the development of image processing and artificial intelligence technologies, image-based corrosion detection methods have been widely used in industrial inspection. However, existing image processing methods for grounding grid corrosion detection still have the following problems: corrosion feature extraction is not comprehensive enough, and relying on a single feature is insufficient to accurately describe the corrosion state; the robustness and accuracy of corrosion state recognition models need to be improved; and there is a lack of quantitative assessment and visualization of the degree of grounding grid corrosion.

[0005] Therefore, an image processing-based method for identifying the corrosion status of grounding grids is needed. Summary of the Invention

[0006] To address the technical problems of low detection efficiency, poor accuracy, and inability to intuitively assess the degree of corrosion in existing grounding grid corrosion detection methods, this invention provides a grounding grid corrosion state identification method, system, medium, and processor based on image processing. This method enables rapid and accurate identification of the grounding grid corrosion state and provides intuitive corrosion state assessment results. The specific technical solution is as follows: A grounding grid corrosion status identification method based on image processing includes: S1: Obtain an image of the grounding grid surface; S2: Preprocess the image to obtain a preprocessed image. The preprocessing includes: S102-1: While acquiring images of the grounding grid surface, the soil resistivity at the sampling points is obtained using a soil resistivity meter, a soil moisture sensor, and a pH meter.ρ Soil volumetric moisture content θ and soil pH; S102-2: Calculation of Soil Corrosion Activity Index ; S102-3: Based on the calculated SCAI value, dynamically adjust the preprocessing parameters, including contrast stretching and color correction; S3: Extract the erosion feature parameters of the preprocessed image, the erosion feature parameters including color feature parameters and texture feature parameters; S4: Based on the corrosion characteristic parameters, a preset corrosion state identification model is used to identify the corrosion state of the grounding grid, and the corrosion state identification result is obtained.

[0007] Preferably, the calculation process for the soil corrosion activity index is as follows: In the formula, The soil corrosion activity index characterizes the degree to which the soil environment promotes grounding grid corrosion and the intensity of interference with image acquisition. For soil resistivity, For reference soil resistivity, the resistivity of typical neutral dry soil is used; Indicates soil volumetric moisture content. This indicates a reference value for soil volumetric moisture content. This represents the maximum volumetric water content of the soil. Soil pH These are the soil resistivity weighting coefficient, soil moisture content weighting coefficient, and soil pH weighting coefficient, respectively.

[0008] Preferably, the process of dynamically adjusting the preprocessing parameters based on the calculated SCAI value is as follows: When SCAI reaches the set threshold, a dehazing algorithm based on dark channel prior is used to correct the image fogging caused by soil moisture evaporation. The dehazing intensity coefficient k is positively correlated with SCAI. Adjust the clipLimit parameter of histogram equalization based on SCAI; When |pH - 7| is greater than the set threshold, the white balance is corrected using the gray world assumption.

[0009] Preferably, the color feature parameters include: color moment features, color histogram features, and the mean and standard deviation of the hue components in the HSV color space.

[0010] Preferably, the texture feature parameters include: gray-level co-occurrence matrix features, local binary mode features, and Gabor filter features.

[0011] Preferably, the step of identifying the corrosion state of the grounding grid based on the corrosion characteristic parameters using a preset corrosion state identification model includes: The color feature parameters and texture feature parameters are fused to obtain a fused feature vector; The fused feature vector is input into a preset corrosion state recognition model, and the corrosion state recognition result is output. The corrosion status identification results include: no corrosion, slight corrosion, moderate corrosion, and severe corrosion.

[0012] Preferably, the preset corrosion state recognition model is trained through the following steps: Obtain a dataset of corrosion sample images of the grounding grid, and label the corrosion status level of the sample images; Extract the erosion feature parameters from the sample image; Using the corrosion feature parameters as input and the corresponding corrosion state level as output, a support vector machine classifier or a convolutional neural network is trained to obtain a corrosion state recognition model.

[0013] Preferably, the method further includes: Based on the corrosion status identification results, a corrosion status distribution map of the grounding grid is generated; Based on the corrosion status distribution map, the overall corrosion status of the grounding grid is assessed, and a maintenance recommendation report is generated.

[0014] A grounding grid corrosion status identification system based on image processing, applied to the method described above, includes: The image acquisition module is used to acquire images of the grounding grid surface; The preprocessing module is used to preprocess the image to obtain a preprocessed image; The feature extraction module is used to extract erosion feature parameters from the preprocessed image, including color feature parameters and texture feature parameters. The corrosion identification module is used to identify the corrosion state of the grounding grid based on the corrosion characteristic parameters and a preset corrosion state identification model, and obtain the corrosion state identification result.

[0015] A computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the image processing-based grounding grid corrosion status identification method as described above.

[0016] A processor for running a program, wherein the program executes the image processing-based grounding grid corrosion status identification method as described above.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention comprehensively describes the visual characteristics of the corrosion area of ​​the grounding grid by combining color feature parameters and texture feature parameters, thereby improving the accuracy of corrosion status identification; 2. This invention uses a preset corrosion state recognition model to automatically identify the corrosion state, realizing intelligent and rapid detection of grounding grid corrosion state, and greatly improving detection efficiency; 3. This invention can generate a grounding grid corrosion status distribution map and maintenance suggestion report, providing an intuitive decision-making basis for the maintenance and repair of the grounding grid, and helping to improve the safe operation level of the power system. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0019] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0020] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] In one embodiment of the present invention, a grounding grid corrosion status identification method based on image processing is provided, such as... Figure 1 As shown, it includes the following steps: S101: Obtain an image of the grounding grid surface.

[0025] In this embodiment, images of the grounding grid surface can be acquired using a high-resolution digital camera or an industrial camera. For buried grounding grids, images can be acquired after partially excavating to expose the grounding grid conductors, or non-destructive testing methods such as endoscopy can be used to obtain images of the grounding grid surface. During acquisition, uniform lighting conditions should be ensured to avoid interference from shadows and reflections.

[0026] S102: Preprocess the image to obtain a preprocessed image.

[0027] Specifically, the preprocessing process includes: (1) Grayscale conversion: Convert the color image to a grayscale image to reduce computational complexity. The weighted average method can be used for grayscale conversion, and the formula is: Gray = 0.299R + 0.587G + 0.114B.

[0028] (2) Filtering and denoising: Median filtering or Gaussian filtering is used to denoise the image and eliminate noise interference introduced during image acquisition.

[0029] (3) Image enhancement processing: Histogram equalization or contrast stretching methods are used to enhance image contrast and highlight the detailed features of the eroded area.

[0030] Furthermore, the specific steps are as follows: S102-1: While acquiring images of the grounding grid surface, the soil resistivity at the sampling points is obtained using a soil resistivity meter, a soil moisture sensor, and a pH meter. ρ Soil volumetric moisture content θ and soil pH; S102-2: Calculate the soil corrosion activity index, as follows: In the formula, The soil corrosion activity index characterizes the degree to which the soil environment promotes grounding grid corrosion and the intensity of interference with image acquisition. For soil resistivity, For reference soil resistivity, the resistivity of typical neutral dry soil is used; Indicates soil volumetric moisture content. This indicates a reference value for soil volumetric moisture content. This represents the maximum volumetric water content of the soil. Soil pH These are the soil resistivity weighting coefficient, soil moisture content weighting coefficient, and soil pH weighting coefficient, respectively.

[0031] S102-3: Dynamically adjust the preprocessing parameters based on the calculated SCAI values: 1. Adaptive Dehazing Enhancement: When SCAI>3, a dehazing algorithm based on dark channel prior is adopted to correct the image fogging caused by soil moisture evaporation. The dehazing intensity coefficient k is positively correlated with SCAI: k = 0.1 × SCAI; 2. Adaptive Contrast Stretching: Adjusts the clipLimit parameter of histogram equalization based on SCAI. For example, when SCAI ≤ 3, clipLimit = 2.0 (normal enhancement); For example, 3 <scai ≤ 6时，cliplimit="3.0（中等增强）；" 示例性的，scai>At 6 o'clock, clipLimit = 4.0 (strong enhancement to address uneven surface reflection caused by highly corrosive and reactive soil).

[0032] 3. Color constancy correction: When |pH - 7|>2 (strong acid or strong alkaline soil), the white balance is corrected using the gray world assumption to eliminate color temperature shift caused by soil acidity or alkalinity.

[0033] S103: Extract the erosion feature parameters of the preprocessed image.

[0034] In this embodiment, the corrosion feature parameters include color feature parameters and texture feature parameters: Color feature parameters include: Color moment features: Calculate the first moment (mean), second moment (standard deviation), and third moment (slope) of the image in the RGB color space, for a total of 9 dimensions; Color histogram features: Statistically analyze the histogram distribution of the H component of the image in the HSV color space and extract the main color distribution features; HSV Hue Component Statistical Characteristics: Calculate the mean and standard deviation of the H component to describe the color distribution characteristics of the eroded area.

[0035] Texture feature parameters include: Gray-level co-occurrence matrix (GLCM) features: Calculate the gray-level co-occurrence matrix of an image in four directions: 0°, 45°, 90°, and 135°, and extract features such as contrast, correlation, energy, and homogeneity; Local Binary Pattern (LBP) features: Extract local texture structure features from an image to describe the microscopic texture information of a corroded surface; Gabor filtering features: The image is filtered using a multi-scale, multi-directional Gabor filter bank to extract the texture frequency features of the eroded area.

[0036] S104: Based on the corrosion characteristic parameters, a preset corrosion state identification model is used to identify the corrosion state of the grounding grid, and the corrosion state identification result is obtained.

[0037] In this embodiment, color feature parameters and texture feature parameters are first fused to construct a fused feature vector. Then, the fused feature vector is input into a preset corrosion state recognition model to output the corrosion state recognition result.

[0038] The corrosion status identification results are divided into four levels: no corrosion (no obvious corrosion traces on the grounding grid surface), slight corrosion (slight rust on the surface, with some metallic luster visible), moderate corrosion (more obvious rust, with some metal surfaces covered by corrosion products), and severe corrosion (severe corrosion, with a large amount of rust on the metal surface, and possible corrosion pits or thinning).

[0039] The training process for the pre-defined corrosion state recognition model is as follows: (1) Collect a large number of grounding grid corrosion sample images, covering grounding grid surface images under different corrosion levels and environmental conditions; (2) The corrosion status level of the sample images is marked by professionals; (3) Extract the erosion feature parameters (color features and texture features) of all sample images; (4) Train a classification model using corrosion feature parameters as input and corrosion state level as output. A support vector machine (SVM) classifier can be used, and the kernel function parameters and penalty coefficient can be optimized through grid search; or a convolutional neural network (CNN) can be used, and the pre-trained model can be used for feature extraction and classification through transfer learning.

[0040] S105: Generate corrosion status distribution map and maintenance recommendation report.

[0041] Based on the corrosion status identification results, a spatial distribution map of the grounding grid's corrosion status is generated, visually displaying the corrosion condition of each area of ​​the grounding grid. Simultaneously, based on the corrosion status distribution map, the overall corrosion status of the grounding grid is assessed, and a targeted maintenance recommendation report is generated, providing decision support for the inspection and maintenance of the grounding grid.

[0042] In one embodiment of the present invention, a grounding grid corrosion status identification system based on image processing is provided, such as... Figure 1 As shown, it includes: The image acquisition module is used to acquire images of the grounding grid surface; The preprocessing module is used to preprocess the image to obtain a preprocessed image; The feature extraction module is used to extract erosion feature parameters of the preprocessed image, including color feature parameters and texture feature parameters; The corrosion identification module is used to identify the corrosion state of the grounding grid based on the corrosion characteristic parameters and a preset corrosion state identification model, and obtain the corrosion state identification result.

[0043] In another embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute the grounding grid corrosion state identification method based on image processing described above.

[0044] In another embodiment of the present invention, a processor is provided for running a program, wherein the program executes the image processing-based grounding grid corrosion status identification method described above.

[0045] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0046] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0047] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0048] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0049] 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 foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.< / scai>

Claims

1. A method for identifying the corrosion status of a grounding grid based on image processing, characterized in that, include: S1: Obtain an image of the grounding grid surface; S2: Preprocess the image to obtain a preprocessed image. The preprocessing includes: S102-1: While acquiring images of the grounding grid surface, the soil resistivity at the sampling points is obtained using a soil resistivity meter, a soil moisture sensor, and a pH meter. ρ Soil volumetric moisture content θ and soil pH; S102-2: Calculation of Soil Corrosion Activity Index ; S102-3: Based on the calculated SCAI value, dynamically adjust the preprocessing parameters, including contrast stretching and color correction; S3: Extract the erosion feature parameters of the preprocessed image, the erosion feature parameters including color feature parameters and texture feature parameters; S4: Based on the corrosion characteristic parameters, a preset corrosion state identification model is used to identify the corrosion state of the grounding grid, and the corrosion state identification result is obtained.

2. The grounding grid corrosion status identification method based on image processing according to claim 1, characterized in that, The calculation process for the soil corrosion activity index is as follows: In the formula, The soil corrosion activity index characterizes the degree to which the soil environment promotes grounding grid corrosion and the intensity of interference with image acquisition. For soil resistivity, For reference soil resistivity, the resistivity of typical neutral dry soil is used; Indicates soil volumetric moisture content. This indicates a reference value for soil volumetric moisture content. This represents the maximum volumetric water content of the soil. Soil pH These are the soil resistivity weighting coefficient, soil moisture content weighting coefficient, and soil pH weighting coefficient, respectively.

3. The grounding grid corrosion status identification method based on image processing according to claim 1, characterized in that, The process of dynamically adjusting the preprocessing parameters based on the calculated SCAI value is as follows: When SCAI reaches the set threshold, a dehazing algorithm based on dark channel prior is used to correct the image fogging caused by soil moisture evaporation. The dehazing intensity coefficient k is positively correlated with SCAI. Adjust the clipLimit parameter of histogram equalization based on SCAI; When |pH - 7| is greater than the set threshold, the white balance is corrected using the gray world assumption.

4. The grounding grid corrosion status identification method based on image processing according to claim 1, characterized in that, The texture feature parameters include: gray-level co-occurrence matrix features, local binary mode features, and Gabor filter features.

5. The grounding grid corrosion status identification method based on image processing according to claim 1, characterized in that, The step of identifying the corrosion state of the grounding grid based on the corrosion characteristic parameters and using a preset corrosion state identification model includes: The color feature parameters and texture feature parameters are fused to obtain a fused feature vector; The fused feature vector is input into a preset corrosion state recognition model, and the corrosion state recognition result is output. The corrosion status identification results include: no corrosion, slight corrosion, moderate corrosion, and severe corrosion.

6. The grounding grid corrosion status identification method based on image processing according to claim 1, characterized in that, The preset corrosion state recognition model is trained through the following steps: Obtain a dataset of corrosion sample images of the grounding grid, and label the corrosion status level of the sample images; Extract the erosion feature parameters from the sample image; Using the corrosion feature parameters as input and the corresponding corrosion state level as output, a support vector machine classifier or a convolutional neural network is trained to obtain a corrosion state recognition model.

7. The grounding grid corrosion status identification method based on image processing according to claim 1, characterized in that, The method further includes: Based on the corrosion status identification results, a corrosion status distribution map of the grounding grid is generated; Based on the corrosion status distribution map, the overall corrosion status of the grounding grid is assessed, and a maintenance recommendation report is generated.

8. A grounding grid corrosion status identification system based on image processing, characterized in that, The method applied to any one of claims 1 to 7 includes: The image acquisition module is used to acquire images of the grounding grid surface; The preprocessing module is used to preprocess the image to obtain a preprocessed image; The feature extraction module is used to extract erosion feature parameters from the preprocessed image, including color feature parameters and texture feature parameters. The corrosion identification module is used to identify the corrosion state of the grounding grid based on the corrosion characteristic parameters and a preset corrosion state identification model, and obtain the corrosion state identification result.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the image processing-based grounding grid corrosion status identification method according to any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run a program, wherein the program executes the image processing-based grounding grid corrosion status identification method according to any one of claims 1 to 7.

Images