Power transformation equipment defect evaluation method based on image processing

Abstract

The invention discloses a power transformation equipment defect evaluation method based on image processing, which relates to the technical field of image processing, and comprises the following steps of: classifying a second image after second numbering according to a first identification result, calculating isolation, insulation and oil leakage degree, and calculating a first identification result; and setting an average value of the isolation degree, the insulation degree and the oil leakage degree as a defect value, and dividing defect grades of the to-be-detected equipment according to the defect value. According to the invention, primary processing is carried out through the video to extract and enhance useful information, comprehensive evaluation is carried out on the power transformation equipment through a plurality of classifications and indexes, comprehensive and standardized processing of defect detection is ensured, consistency and comparability of defect evaluation results are ensured, and the detection accuracy is improved. Accurate defect positioning and evaluation information is provided through methods of key point distance calculation, feature quantity extraction and the like, image processing and machine learning technologies are combined, and the accuracy and efficiency of substation equipment defect detection are effectively improved through detailed processing and calculation steps.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for evaluating defects of substation equipment based on image processing. Background Art

[0002] In recent years, image processing technology has developed rapidly and has been widely used in power equipment inspection. It can identify power equipment faults through image acquisition and processing.

[0003] At present, a Chinese invention patent with publication number CN 113077063 B discloses a defect management method and device for substation equipment based on voice and image recognition. The method uses an image camera to quickly find equipment-related defects, and intuitively displays complex defect problems through data analysis and data visualization technology, assisting substation operation and maintenance personnel to fully control the defect process, improve defect elimination capabilities, and enable substation equipment to quickly return to normal status, ensuring safe and stable operation. However, the related technology does not screen images according to their quality, which is not conducive to the rapidity of recognition response, does not construct a comprehensive evaluation amount based on multiple parameters, and lacks the linkage and integrity of parameters. Summary of the invention

[0004] The technical problem solved by the present invention is that the related art does not screen images according to their quality, which is not conducive to the rapidity of recognition response, does not construct a comprehensive evaluation amount based on multiple parameters, and lacks the linkage and integrity of parameters.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a method for defect assessment of substation equipment based on image processing comprises the following steps: Step S1, collecting a video of the device to be detected, performing a first preprocessing on the video to obtain a first image, and performing a first numbering on the first image in chronological order; Step S2, performing a second preprocessing on the second-numbered first image to obtain a second image, performing a second numbering on the second image, recognizing the second-numbered second image to obtain a first recognition result, and classifying the second-numbered second image according to the first recognition result, wherein the classification includes disconnector classification, insulator classification, and transformer classification; Step S3, setting key points for isolating switch classification, calculating the distances between the key points, and calculating the average value of the distances between the key points, setting the average value of the distances between the key points as the isolation degree, extracting feature quantities for insulator classification, calculating the similarity between the standard feature quantities and the feature quantities for insulator classification, and calculating the average value of the similarities, setting the average value of the similarities as the insulation degree, graying the transformer classification to obtain a third image, setting a standard grayscale interval, calculating the average value of pixels in the third image that are not distributed in the standard grayscale interval, and setting it as the oil leakage degree; Step S4, standardize the isolation, insulation and oil leakage, calculate the average values ​​of the isolation, insulation and oil leakage, set the average values ​​of the isolation, insulation and oil leakage as defect values, and classify the defect levels of the equipment to be tested according to the defect values.

[0006] As a preferred solution of the method for defect assessment of substation equipment based on image processing described in the present invention, step S1 includes the following sub-steps: Step S11, setting the first time period as a first operation cycle, and collecting a video of the device to be detected during the first operation cycle; Step S12, performing a first preprocessing on the video to obtain Q first images, wherein the first preprocessing includes frame segmentation and windowing processing and invalid frame removal processing, and the first images are first numbered in chronological order, wherein the first numbers include X1, X2, ..., X Q .

[0007] As a preferred solution of the method for defect assessment of substation equipment based on image processing described in the present invention, the processing logic for removing invalid frames includes: Acquire the image after the frame and window processing, count the total number of pixels of the image after the frame and window processing, identify the number of pixels belonging to the device to be detected in the image after the frame and window processing, and calculate the ratio of the number of pixels belonging to the device to be detected in the image after the frame and window processing to the total number of pixels of the image after the frame and window processing, which is recorded as a first ratio; The first value is set as the minimum validity value, and the first ratio is compared with the minimum validity value. When the first ratio is greater than or equal to the minimum validity value, the corresponding framed and windowed image is set as the first image, otherwise the corresponding image is deleted.

[0008] As a preferred solution of the method for defect assessment of substation equipment based on image processing described in the present invention, step S2 includes the following sub-steps: Step S21, performing a second preprocessing on the second numbered first image to obtain a second image, wherein the second preprocessing includes denoising and filtering; Step S22, assigning a second number to the second image, and identifying the second image after the second numbering to obtain a first identification result, wherein the first identification result is represented by the outline of the key image in the second image, wherein the key image includes the disconnector image, the insulator image, and the transformer image, and the second number corresponds to the first number, and the second number corresponding to X1 includes X 11 , X 12 , ..., X 1N , the second number corresponding to X2 includes X 21 ,X 22 , ..., X 2N , ..., with X Q The corresponding second number includes X Q1 , X Q2 ,...,X QN , where N is a natural number; Step S23, classifying the second image after the second numbering according to the first recognition result, wherein the classification includes disconnector classification, insulator classification and transformer classification.

[0009] As a preferred solution of the substation defect assessment method based on image processing described in the present invention, the recognition logic of the contour of the key image includes: Acquire standard images, the standard images including a standard disconnector image, a standard insulator image and a standard transformer image, grayscale the standard disconnector image, the standard insulator image and the standard transformer image, calculate the grayscale average of each grayscale image, grayscale the second image after the second numbering, and calculate the grayscale average of the second image after the grayscale processing; Calculate the difference between the grayscale average value of each image after grayscale processing and the grayscale average value of the second image after grayscale processing, record it as the first difference, set the second value as the difference threshold, compare the first difference with the difference threshold, and when the first difference is less than or equal to the difference threshold, set the standard image corresponding to the first difference as the classification of the second image.

[0010] As a preferred solution of the method for defect assessment of substation equipment based on image processing described in the present invention, step S3 includes the following sub-steps: Step S31, setting key points for isolating switch classification, wherein the key points for isolating switch classification are upper electric shock and lower electric shock, calculating the distance between key points by using a distance formula, and calculating the average value of the distance between the key points, and setting the average value of the distance between the key points as the isolation degree; Step S32, extracting the characteristic quantity of the insulator classification, the characteristic quantity of the insulator classification is the surface characteristic quantity of the insulator, obtaining a standard insulator image, extracting the characteristic quantity of the standard insulator image, recording it as the standard characteristic quantity, calculating the similarity between the standard characteristic quantity and the characteristic quantity of the insulator classification by a cosine similarity formula, calculating the average value of the similarity, and setting the average value of the similarity as the insulation degree; Step S33, classify the transformer and perform grayscale processing to obtain a third image, set the third value as the upper limit of the standard grayscale interval, set the fourth value as the lower limit of the standard grayscale interval, obtain the third image that is not distributed in a value greater than the point value or less than the fourth value, calculate the average value of the pixels in the third image that are not distributed in a value greater than the point value or less than the fourth value, and set it as the oil leakage degree.

[0011] As a preferred solution of the method for defect assessment of substation equipment based on image processing described in the present invention, step S4 includes the following sub-steps: Step S41, standardizing the isolation, insulation and oil leakage so that the isolation, insulation and oil leakage are standardized and distributed between 0 and 1; Step S42, calculating the average values ​​of isolation, insulation and oil leakage, and setting the average values ​​of isolation, insulation and oil leakage as defect values; Step S43, classifying the defect levels of the equipment to be inspected according to the defect values, wherein the defect levels include a first defect level, a second defect level and a third defect level.

[0012] As a preferred solution of the method for defect assessment of substation equipment based on image processing described in the present invention, the defect level classification logic includes: The fifth value and the sixth value are set as the division critical value, and the defect value is compared with the division critical value. When the defect value is greater than or equal to the fifth value, the defect level is set to the first defect level. When the defect value is less than the fifth value and greater than or equal to the sixth value, the defect level is set to the second defect level. When the defect value is less than the sixth value, the defect level is set to the third defect level, wherein the fifth value is greater than the sixth value, and the fifth value and the sixth value are distributed between 0 and 1.

[0013] In a second aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the systems described above are executed.

[0014] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in the system described in any one of the above items are executed.

[0015] The beneficial effects of the present invention include: preliminary processing of the video to extract and enhance useful information, generating a first image, numbering the first image in chronological order, providing a sequential basis for subsequent image processing, and automating the detection method to reduce the workload of manual inspection and improve detection efficiency and accuracy. The substation equipment is comprehensively evaluated through multiple classifications and indicators to ensure the comprehensiveness of defect detection. Based on video data, real-time monitoring and evaluation are supported to improve the operational safety of the equipment. Through standardized processing, the consistency and comparability of defect evaluation results are ensured. Methods such as key point distance calculation and feature extraction provide accurate defect location and evaluation information. Image processing and machine learning techniques are combined to effectively improve the accuracy and efficiency of substation equipment defect detection through detailed processing and calculation steps. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A basic flow chart of a method for defect assessment of substation equipment based on image processing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0018] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for defect assessment of substation equipment based on image processing, comprising the following steps: Step S1, collecting a video of the device to be detected, performing a first preprocessing on the video to obtain a first image, and performing a first numbering on the first image in chronological order; Step S2, performing a second preprocessing on the second-numbered first image to obtain a second image, performing a second numbering on the second image, recognizing the second-numbered second image to obtain a first recognition result, and classifying the second-numbered second image according to the first recognition result, wherein the classification includes disconnector classification, insulator classification, and transformer classification; Step S3, setting key points for isolating switch classification, calculating the distances between the key points, and calculating the average value of the distances between the key points, setting the average value of the distances between the key points as the isolation degree, extracting feature quantities for insulator classification, calculating the similarity between the standard feature quantities and the feature quantities for insulator classification, and calculating the average value of the similarities, setting the average value of the similarities as the insulation degree, graying the transformer classification to obtain a third image, setting a standard grayscale interval, calculating the average value of pixels in the third image that are not distributed in the standard grayscale interval, and setting it as the oil leakage degree; Step S4, standardizing the isolation, insulation and oil leakage, calculating the average values ​​of the isolation, insulation and oil leakage, setting the average values ​​of the isolation, insulation and oil leakage as defect values, and dividing the defect levels of the equipment to be tested according to the defect values.

[0019] The present invention performs preliminary processing on the video to extract and enhance useful information, generates a first image, and numbers the first image in chronological order to provide a sequential basis for subsequent image processing. The automated detection method reduces the workload of manual inspection and improves detection efficiency and accuracy. The substation equipment is comprehensively evaluated through multiple classifications and indicators to ensure the comprehensiveness of defect detection. Based on video data, real-time monitoring and evaluation are supported to improve the operational safety of the equipment. Through standardized processing, the consistency and comparability of defect evaluation results are ensured. Methods such as key point distance calculation and feature extraction provide accurate defect location and evaluation information. The image processing and machine learning technologies are combined to effectively improve the accuracy and efficiency of substation equipment defect detection through detailed processing and calculation steps.

[0020] The step S1 includes the following sub-steps: Step S11, setting the first time period as a first operation cycle, and collecting a video of the device to be detected during the first operation cycle; Step S12, performing a first preprocessing on the video to obtain Q first images, wherein the first preprocessing includes frame segmentation and windowing processing and invalid frame removal processing, and the first images are first numbered in chronological order, wherein the first numbers include X1, X2, ..., X Q .

[0021] In a specific implementation, a time period is defined, called the first operating cycle, during which video data is collected so that the video data is concentrated in a specific operating cycle to facilitate subsequent analysis and comparison. The collected video is decomposed into multiple frames, and these frames are windowed to help highlight areas of interest and reduce background noise, or other image enhancement operations are performed to eliminate frames with no valid information or poor quality, which may not contribute to subsequent analysis or may introduce errors, thereby making the quality of subsequent processed data higher.

[0022] The processing logic for removing invalid frames includes: Acquire the image after the frame and window processing, count the total number of pixels of the image after the frame and window processing, identify the number of pixels belonging to the device to be detected in the image after the frame and window processing, and calculate the ratio of the number of pixels belonging to the device to be detected in the image after the frame and window processing to the total number of pixels of the image after the frame and window processing, which is recorded as a first ratio; The first value is set as the minimum validity value, and the first ratio is compared with the minimum validity value. When the first ratio is greater than or equal to the minimum validity value, the corresponding framed and windowed image is set as the first image, otherwise the corresponding image is deleted.

[0023] In the specific implementation, through effectiveness comparison, images with a low proportion of device area are automatically eliminated, reducing the interference of irrelevant or noisy images on subsequent analysis, so that subsequent processing and analysis are only based on images containing sufficient device information, thereby improving the accuracy of the detection results. Effectiveness filtering reduces low-quality or irrelevant images in the image data set and optimizes the overall quality and processing efficiency of the data.

[0024] The step S2 includes the following sub-steps: Step S21, performing a second preprocessing on the second numbered first image to obtain a second image, wherein the second preprocessing includes denoising and filtering; Step S22, assigning a second number to the second image, and identifying the second image after the second numbering to obtain a first identification result, wherein the first identification result is represented by the outline of the key image in the second image, wherein the key image includes the disconnector image, the insulator image, and the transformer image, and the second number corresponds to the first number, and the second number corresponding to X1 includes X 11 , X 12 , ..., X 1N , the second number corresponding to X2 includes X 21 ,X 22 , ..., X 2N , ..., with X Q The corresponding second number includes X Q1 , XQ2 ,...,X QN , where N is a natural number; Step S23, classifying the second image after the second numbering according to the first recognition result, wherein the classification includes disconnector classification, insulator classification and transformer classification.

[0025] In a specific implementation, noise in the image is removed and the clarity and signal quality of the image are enhanced, such as filtering algorithms, median filtering and Gaussian filtering, and the second image is numbered to keep a corresponding relationship with the first number in step S12. The classification step based on the recognition result can effectively classify the image into different categories, thereby facilitating subsequent analysis.

[0026] The recognition logic of the outline of the key image includes: Acquire standard images, the standard images including a standard disconnector image, a standard insulator image and a standard transformer image, grayscale the standard disconnector image, the standard insulator image and the standard transformer image, calculate the grayscale average of each grayscale image, grayscale the second image after the second numbering, and calculate the grayscale average of the second image after the grayscale processing; Calculate the difference between the grayscale average value of each image after grayscale processing and the grayscale average value of the second image after grayscale processing, record it as the first difference, set the second value as the difference threshold, compare the first difference with the difference threshold, and when the first difference is less than or equal to the difference threshold, set the standard image corresponding to the first difference as the classification of the second image.

[0027] In the specific implementation, through grayscale processing and difference calculation, the similarity between the image to be detected and the standard image can be accurately judged, thereby improving the accuracy of recognition. The second image can be correctly classified into the corresponding category in the standard image, such as disconnectors, insulators and transformers, thereby providing a clear classification basis for subsequent processing and analysis. The use of grayscale and average value difference calculation simplifies the image analysis process and reduces the computational complexity and resource consumption.

[0028] The step S3 includes the following sub-steps: Step S31, setting key points for isolating switch classification, wherein the key points for isolating switch classification are upper electric shock and lower electric shock, calculating the distance between key points by using a distance formula, and calculating the average value of the distance between the key points, and setting the average value of the distance between the key points as the isolation degree; Step S32, extracting the characteristic quantity of the insulator classification, the characteristic quantity of the insulator classification is the surface characteristic quantity of the insulator, obtaining a standard insulator image, extracting the characteristic quantity of the standard insulator image, recording it as the standard characteristic quantity, calculating the similarity between the standard characteristic quantity and the characteristic quantity of the insulator classification by a cosine similarity formula, calculating the average value of the similarity, and setting the average value of the similarity as the insulation degree; Step S33, classify the transformer and perform grayscale processing to obtain a third image, set the third value as the upper limit of the standard grayscale interval, set the fourth value as the lower limit of the standard grayscale interval, obtain the third image that is not distributed in a value greater than the point value or less than the fourth value, calculate the average value of the pixels in the third image that are not distributed in a value greater than the point value or less than the fourth value, and set it as the oil leakage degree.

[0029] In the specific implementation, by calculating the distance between key points, the isolation performance of the disconnector can be accurately evaluated to ensure the safety of the equipment. By using cosine similarity calculation, insulators can be accurately identified and classified to improve the efficiency of equipment management and maintenance. By gray value filtering and pixel average calculation, it can effectively detect whether the transformer has oil leakage problems, thereby reducing potential equipment failures and risks. It provides a comprehensive equipment classification and detection solution, which improves the level of equipment maintenance and safety management.

[0030] The step S4 includes the following sub-steps: Step S41, standardizing the isolation, insulation and oil leakage so that the isolation, insulation and oil leakage are standardized and distributed between 0 and 1; Step S42, calculating the average values ​​of isolation, insulation and oil leakage, and setting the average values ​​of isolation, insulation and oil leakage as defect values; Step S43, classifying the defect levels of the equipment to be inspected according to the defect values, wherein the defect levels include a first defect level, a second defect level and a third defect level.

[0031] The defect level classification logic includes: The fifth value and the sixth value are set as the division critical value, and the defect value is compared with the division critical value. When the defect value is greater than or equal to the fifth value, the defect level is set to the first defect level. When the defect value is less than the fifth value and greater than or equal to the sixth value, the defect level is set to the second defect level. When the defect value is less than the sixth value, the defect level is set to the third defect level, wherein the fifth value is greater than the sixth value, and the fifth value and the sixth value are distributed between 0 and 1.

[0032] In the specific implementation, the data of different metrics are put on the same scale to facilitate subsequent comparison and analysis, reduce the complexity of data processing, make the contribution of different indicators to the final evaluation consistent, and aggregate multiple indicators into one defect value, providing a comprehensive assessment of the overall status of the equipment. The clear defect level division makes the management of equipment status more orderly.

[0033] The present invention performs preliminary processing on the video to extract and enhance useful information, generates a first image, and numbers the first image in chronological order to provide a sequential basis for subsequent image processing. The automated detection method reduces the workload of manual inspection and improves detection efficiency and accuracy. The substation equipment is comprehensively evaluated through multiple classifications and indicators to ensure the comprehensiveness of defect detection. Based on video data, real-time monitoring and evaluation are supported to improve the operational safety of the equipment. Through standardized processing, the consistency and comparability of defect evaluation results are ensured. Methods such as key point distance calculation and feature extraction provide accurate defect location and evaluation information. The image processing and machine learning technologies are combined to effectively improve the accuracy and efficiency of substation equipment defect detection through detailed processing and calculation steps.

[0034] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0035] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating defects in substation equipment based on image processing, characterized in that: The following steps are involved: Step S1, collecting a video of the device to be detected, performing a first preprocessing on the video to obtain a first image, and performing a first numbering on the first image in chronological order; Step S2, performing a second preprocessing on the second-numbered first image to obtain a second image, performing a second numbering on the second image, recognizing the second-numbered second image to obtain a first recognition result, and classifying the second-numbered second image according to the first recognition result, wherein the classification includes disconnector classification, insulator classification, and transformer classification; Step S3, setting key points for isolating switch classification, calculating the distances between the key points, and calculating the average value of the distances between the key points, setting the average value of the distances between the key points as the isolation degree, extracting feature quantities for insulator classification, calculating the similarity between the standard feature quantities and the feature quantities for insulator classification, and calculating the average value of the similarities, setting the average value of the similarities as the insulation degree, graying the transformer classification to obtain a third image, setting a standard grayscale interval, calculating the average value of pixels in the third image that are not distributed in the standard grayscale interval, and setting it as the oil leakage degree; Step S4, standardizing the isolation, insulation and oil leakage, calculating the average values ​​of the isolation, insulation and oil leakage, setting the average values ​​of the isolation, insulation and oil leakage as defect values, and dividing the defect levels of the equipment to be tested according to the defect values.

2. A defect assessment method for substation equipment based on image processing as claimed in claim 1, characterized in that: The step S1 includes the following sub-steps: Step S11, setting the first time period as a first operation cycle, and collecting a video of the device to be detected during the first operation cycle; Step S12, performing a first preprocessing on the video to obtain Q first images, wherein the first preprocessing includes frame segmentation and windowing processing and invalid frame removal processing, and the first images are first numbered in chronological order, wherein the first numbers include X1, X2, ..., X Q .

3. A defect assessment method for substation equipment based on image processing as claimed in claim 2, characterized in that: The processing logic for removing invalid frames includes: Acquire the image after the frame and window processing, count the total number of pixels of the image after the frame and window processing, identify the number of pixels belonging to the device to be detected in the image after the frame and window processing, and calculate the ratio of the number of pixels belonging to the device to be detected in the image after the frame and window processing to the total number of pixels of the image after the frame and window processing, which is recorded as a first ratio; The first value is set as the minimum validity value, and the first ratio is compared with the minimum validity value. When the first ratio is greater than or equal to the minimum validity value, the corresponding framed and windowed image is set as the first image, otherwise the corresponding image is deleted.

4. The defect assessment method for substation equipment based on image processing according to claim 1, characterized in that: The step S2 includes the following sub-steps: Step S21, performing a second preprocessing on the second numbered first image to obtain a second image, wherein the second preprocessing includes denoising and filtering; Step S22, assigning a second number to the second image, and identifying the second image after the second numbering to obtain a first identification result, wherein the first identification result is represented by the outline of the key image in the second image, wherein the key image includes the disconnector image, the insulator image, and the transformer image, and the second number corresponds to the first number, and the second number corresponding to X1 includes X 11 , X 12 , ..., X 1N , the second number corresponding to X2 includes X 21 ,X 22 , ..., X 2N , ..., with X Q The corresponding second number includes X Q1 , X Q2 ,...,X QN , where N is a natural number; Step S23, classifying the second image after the second numbering according to the first recognition result, wherein the classification includes disconnector classification, insulator classification and transformer classification.

5. A defect assessment method for substation equipment based on image processing as claimed in claim 4, characterized in that: The recognition logic of the outline of the key image includes: Acquire standard images, the standard images including a standard disconnector image, a standard insulator image and a standard transformer image, grayscale the standard disconnector image, the standard insulator image and the standard transformer image, calculate the grayscale average of each grayscale image, grayscale the second image after the second numbering, and calculate the grayscale average of the second image after the grayscale processing; Calculate the difference between the grayscale average value of each image after grayscale processing and the grayscale average value of the second image after grayscale processing, record it as the first difference, set the second value as the difference threshold, compare the first difference with the difference threshold, and when the first difference is less than or equal to the difference threshold, set the standard image corresponding to the first difference as the classification of the second image.

6. A defect assessment method for substation equipment based on image processing as claimed in claim 1, characterized in that: The step S3 includes the following sub-steps: Step S31, setting key points for isolating switch classification, wherein the key points for isolating switch classification are upper electric shock and lower electric shock, calculating the distance between key points by using a distance formula, and calculating the average value of the distance between the key points, and setting the average value of the distance between the key points as the isolation degree; Step S32, extracting the characteristic quantity of the insulator classification, the characteristic quantity of the insulator classification is the surface characteristic quantity of the insulator, obtaining a standard insulator image, extracting the characteristic quantity of the standard insulator image, recording it as the standard characteristic quantity, calculating the similarity between the standard characteristic quantity and the characteristic quantity of the insulator classification by a cosine similarity formula, calculating the average value of the similarity, and setting the average value of the similarity as the insulation degree; Step S33, classify the transformer and perform grayscale processing to obtain a third image, set the third value as the upper limit of the standard grayscale interval, set the fourth value as the lower limit of the standard grayscale interval, obtain the third image that is not distributed in a value greater than the point value or less than the fourth value, calculate the average value of the pixels in the third image that are not distributed in a value greater than the point value or less than the fourth value, and set it as the oil leakage degree.

7. A defect assessment method for substation equipment based on image processing as claimed in claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, standardizing the isolation, insulation and oil leakage so that the isolation, insulation and oil leakage are standardized and distributed between 0 and 1; Step S42, calculating the average values ​​of isolation, insulation and oil leakage, and setting the average values ​​of isolation, insulation and oil leakage as defect values; Step S43, classifying the defect levels of the equipment to be inspected according to the defect values, wherein the defect levels include a first defect level, a second defect level and a third defect level.

8. A method for evaluating defects of substation equipment based on image processing as claimed in claim 7, characterized in that: The defect level classification logic includes: The fifth value and the sixth value are set as the division critical value, and the defect value is compared with the division critical value. When the defect value is greater than or equal to the fifth value, the defect level is set to the first defect level. When the defect value is less than the fifth value and greater than or equal to the sixth value, the defect level is set to the second defect level. When the defect value is less than the sixth value, the defect level is set to the third defect level, wherein the fifth value is greater than the sixth value, and the fifth value and the sixth value are distributed between 0 and 1.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for defect assessment of substation equipment based on image processing as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for defect assessment of substation equipment based on image processing according to any one of claims 1 to 8 is implemented.

Images