Method and system for distinguishing, analyzing and processing consistency of partial discharge image

Abstract

The invention provides a partial discharge image consistency discrimination analysis processing method and system, and belongs to the technical field of image processing, and the method specifically comprises the steps: determining an insulation defect part of power equipment through the distribution data of an insulation defect image feature and a corona discharge feature in a fused image; the method comprises the following steps of: determining a reference inspection video according to the moment of the power equipment, and determining a historical inspection image and credibility of the power equipment of the unmanned aerial vehicle according to the similar condition of different image frames of the reference inspection video; according to the method, the change conditions of the insulation defect image characteristics and the corona discharge characteristics of the insulation defect part are determined, and the partial discharge state value of the power equipment is determined in combination with the credibility of different historical inspection images, so that the accuracy of the evaluation of the partial discharge state of the power equipment is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a method and system for identifying and analyzing the consistency of partial discharge images. Background Art

[0002] The insulation defect problem of power equipment in transmission lines is the core factor threatening the safety of transmission line operation. In the existing technical solutions, the insulation defect problem is often identified by ultraviolet cameras. Specifically, similar technical solutions are given in the invention patent applications CN202410764478.5 "Insulator detection method and system based on ultraviolet images" and CN202410408469.2 "A method for detecting the severity of insulator discharge in a substation based on target detection". However, the above technical solutions all have the following technical problems: Since ultraviolet partial discharge images lack detailed features of the power equipment itself, it is impossible to accurately assess the severity of partial discharge of power equipment by relying solely on ultraviolet partial discharge images. Therefore, how to combine multiple types of monitoring images to assess the partial discharge status of power equipment has become a technical problem that needs to be solved urgently.

[0003] In order to solve the above technical problems, the present invention provides a method and system for identifying and analyzing the consistency of partial discharge images. Summary of the invention

[0004] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: In order to solve the above technical problems, the present invention provides a method for identifying and analyzing the consistency of partial discharge images, which specifically includes: S1 uses a drone to acquire an ultraviolet partial discharge image of the power equipment, and when it is determined that there is a suspected abnormality in the partial discharge state of the power equipment based on the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image and the operating voltage, proceeds to the next step; S2: obtaining a visualized image of the power equipment, and obtaining a fused image based on a consistency evaluation result of the image features of the visualized image and the ultraviolet partial discharge image, and determining the insulation defect location of the power equipment through the distribution data of the insulation defect image features and the corona discharge features in the fused image; S3 determines the benchmark inspection video based on the time when the power equipment is located, and determines the historical inspection image of the power equipment of the drone and the credibility based on the similarity of the image frames different from the benchmark inspection video; S4 determines the changes in the insulation defect image characteristics and corona discharge characteristics of the insulation defect location based on the historical inspection images and the fused images, and determines the partial discharge state value of the power equipment in combination with the credibility of different historical inspection images.

[0005] The beneficial effects of the present invention are: 1. In the present invention, whether there is any suspected abnormality in the partial discharge state of the power equipment is determined based on the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image and the operating voltage, thereby realizing the screening of the power equipment with suspected abnormality in the partial discharge state from the perspective of the operating voltage of the power equipment and the severity of the corona discharge characteristics, avoiding the technical problem of low efficiency of evaluation and processing caused by evaluating the partial discharge state values ​​of all power equipment, and improving the pertinence and processing efficiency of the partial discharge state evaluation.

[0006] 2. In the present invention, the insulation defect location of the power equipment is determined by fusing the distribution data of the insulation defect image features and the corona discharge features in the image, thereby avoiding the technical problem of low recognition accuracy of the insulation defect location caused by the use of a single image. The screening of the insulation defect location from the perspective of multiple images is fully considered, which improves the recognition and processing accuracy of the insulation defect location and also lays a foundation for further evaluating the partial discharge state value of the power equipment based on the insulation defect location.

[0007] A further technical solution is that the ultraviolet partial discharge image of the power equipment is acquired based on the ultraviolet camera device of the drone.

[0008] A further technical solution is that the distribution data of the corona discharge characteristics include the corona discharge characteristics at different locations of the ultraviolet partial discharge image.

[0009] A further technical solution is that the method for determining the reference inspection video is: The time at which the electric power equipment is located is determined by using the inspection time corresponding to the electric power equipment, and the inspection monitoring video within a preset time period close to the time at which the electric power equipment is located is used as a reference inspection video.

[0010] A further technical solution is that the method for determining the historical inspection image of the power equipment is: Obtaining inspection video data of the drone during different historical inspection processes, and dividing the inspection video data into a plurality of segmented time periods using the duration of the reference inspection video; Determining image similarity coefficients of different image frames based on similarities between the divided time periods and different image frames of the reference inspection video; The video similarity coefficient between the segmented time period and the reference inspection video is determined by image similarity coefficients of different image frames, and the credibility of the segmented time period is determined by using the video similarity coefficient. Based on the credibility, it is determined whether the segmented time period is a historical inspection image.

[0011] A further technical solution is that when the credibility of the segmented time period is greater than a preset credibility, the segmented time period is determined to be a historical inspection image.

[0012] On the other hand, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned method for identifying and analyzing partial discharge image consistency.

[0013] Other features and advantages will be described in the following description, and partly become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0014] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0016] Figure 1 It is a flow chart of a method for identifying and analyzing the consistency of partial discharge images; Figure 2 is a flow chart of a method for constructing a fused image; Figure 3 It is a flow chart of the method of determining the insulation defect location. DETAILED DESCRIPTION

[0017] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0018] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0019] Example 1 To solve the above problems, according to one aspect of the present invention, Figure 1As shown, according to one aspect of the present invention, a method for identifying and analyzing the consistency of a partial discharge image is provided, which specifically includes: S1 uses a drone to acquire an ultraviolet partial discharge image of the power equipment, and when it is determined that there is a suspected abnormality in the partial discharge state of the power equipment based on the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image and the operating voltage, proceeds to the next step; S2: obtaining a visualized image of the power equipment, and obtaining a fused image based on a consistency evaluation result of the image features of the visualized image and the ultraviolet partial discharge image, and determining the insulation defect location of the power equipment through the distribution data of the insulation defect image features and the corona discharge features in the fused image; S3 determines the benchmark inspection video based on the time when the power equipment is located, and determines the historical inspection image of the power equipment of the drone and the credibility based on the similarity of the image frames different from the benchmark inspection video; S4 determines the changes in the insulation defect image characteristics and corona discharge characteristics of the insulation defect location based on the historical inspection images and the fused images, and determines the partial discharge state value of the power equipment in combination with the credibility of different historical inspection images.

[0020] Furthermore, the ultraviolet partial discharge image of the power equipment is acquired based on the ultraviolet camera device of the drone.

[0021] It should be noted that the distribution data of the corona discharge characteristics include the corona discharge characteristics at different locations of the ultraviolet partial discharge image.

[0022] Specifically, determining that there is a suspected abnormality in the partial discharge state of the power equipment includes: Determining the operating voltage deviation of the electric equipment according to the deviation between the operating voltage of the electric equipment and the rated operating voltage, and determining the limited interval of corona discharge using the operating voltage deviation; Determine the corona discharge characteristics of different parts in the ultraviolet partial discharge image by using the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image, and determine the discharge severity of different parts according to the corona discharge characteristics of different parts; Whether there is suspected abnormality in the partial discharge state of the electric power equipment is determined by the deviation of the discharge severity of different parts from the limited interval of the corona discharge.

[0023] It can be understood that when there is a portion where the severity of discharge is not within the limited range of corona discharge, it is determined that there is a suspected abnormality in the partial discharge state of the electric power equipment.

[0024] It should also be noted that determining that the partial discharge state of the power equipment is suspected to be abnormal includes: Determining the operating voltage deviation of the electric equipment according to the deviation between the operating voltage of the electric equipment and the rated operating voltage, and determining the corona discharge reference characteristic of the corona discharge using the operating voltage deviation; Determine the corona discharge characteristics of different parts in the ultraviolet partial discharge image by using the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image, and determine the discharge abnormality values ​​of different parts according to the deviation between the corona discharge characteristics of different parts and the corona discharge reference characteristics; The partial discharge abnormality value of the electric power equipment is determined by the discharge abnormality values ​​of different parts, and the partial discharge abnormality value is used to determine whether there is a suspected abnormality in the partial discharge state of the electric power equipment.

[0025] Specifically, when the partial discharge abnormal value does not meet the requirement, it is determined that there is a suspected abnormality in the partial discharge state of the electric power equipment.

[0026] In another possible embodiment, determining that there is a suspected abnormality in the partial discharge state of the electric power equipment specifically includes: S11 determines the corona discharge characteristics of different parts in the ultraviolet partial discharge image using the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image; S12: taking the location where corona discharge exists as the corona discharge location, determining the operating voltage deviation of the electric equipment according to the deviation between the operating voltage of the electric equipment and the rated operating voltage, and determining the corona discharge reference feature of the corona discharge using the operating voltage deviation, and determining the corona discharge features of different locations in the ultraviolet partial discharge image using the distribution data of the corona discharge features in the ultraviolet partial discharge image; S13 determines the partial discharge abnormality value of the electric power equipment through the discharge abnormality values ​​of different parts, and determines whether there is a suspected abnormality in the partial discharge state of the electric power equipment by using the partial discharge abnormality value.

[0027] Optionally, the above step S11 includes the following contents: The distribution data of the corona discharge characteristics in the ultraviolet partial discharge image is used to determine the corona discharge characteristics of different parts in the ultraviolet partial discharge image, and the corona discharge characteristics are used to determine whether there is a part of the electric equipment with corona discharge. If so, the process proceeds to step S12; if not, it is determined that there is no suspected abnormality in the partial discharge state of the electric equipment.

[0028] Optionally, the above step S12 includes the following contents: S121: taking the part where corona discharge exists as the corona discharge part, judging whether there is a corona discharge part whose corona discharge characteristics do not meet the requirements, if yes, determining that the partial discharge state of the electric power equipment is suspected to be abnormal, if no, proceeding to the next step; S122 determines whether the number of the corona discharge parts is less than the preset number of parts, if so, proceeds to the next step, if not, proceeds to step S13; S123: determining the operating voltage deviation of the electric equipment according to the deviation between the operating voltage of the electric equipment and the rated operating voltage, and determining the corona discharge reference characteristic of the corona discharge by using the operating voltage deviation; S124 determines the corona discharge characteristics of different parts in the ultraviolet partial discharge image using the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image, and determines the discharge abnormality values ​​of different parts according to the deviation between the corona discharge characteristics of different parts and the corona discharge baseline characteristics, and judges whether there are parts whose discharge abnormality values ​​do not meet the requirements. If so, enter step S13; if not, determine that there is no suspected abnormality in the partial discharge state of the power equipment.

[0029] Specifically, Figure 2 As shown, the method for constructing the fused image is: Determining similar positions of the image features of the visualized image and the ultraviolet partial discharge image based on a consistency evaluation result of the image features of the visualized image and the ultraviolet partial discharge image; The visualization image and the ultraviolet partial discharge image are aligned using the similar positions to obtain the fused image.

[0030] Specifically, Figure 3 As shown, the method for determining the insulation defect location is: Determining the position of the electric power equipment with corona discharge in the fused image based on the distribution data of the corona discharge characteristics, and taking the position of the electric power equipment with corona discharge as the corona discharge position; Determine image features at different insulation defect dimensions using the insulation defect image features at the corona discharge position, and determine insulation image abnormality values ​​at the corona discharge position using the image features at different insulation defect dimensions; The corona discharge abnormal value of the corona discharge position is determined according to the corona discharge characteristics of the corona discharge position, the insulation defect abnormal value of the corona discharge position is determined by the corona discharge abnormal value and the insulation image abnormal value, and the insulation defect part in the corona discharge position is determined by using the insulation defect abnormal value.

[0031] Further, when the insulation defect abnormal value of the corona discharge position is not within a preset threshold range, the corona discharge position is determined to be an insulation defect position.

[0032] In another embodiment, the method for determining the insulation defect location is: S21 determines the position of the electric power equipment having corona discharge in the fused image based on the distribution data of the corona discharge characteristics; S22: determining a corona discharge abnormal value at the corona discharge position according to the corona discharge characteristics of the corona discharge position, and determining an insulation image abnormal value at the corona discharge position by using image characteristics at different insulation defect dimensions; S23 determines the insulation defect abnormal value of the corona discharge position according to the corona discharge abnormal value and the insulation image abnormal value, and determines the insulation defect part in the corona discharge position by using the insulation defect abnormal value.

[0033] Optionally, the above step S21 includes the following contents: Based on the distribution data of the corona discharge characteristics, the position of the electric equipment with corona discharge in the fused image is determined, and the position of the electric equipment with corona discharge is used as the corona discharge position, and it is judged whether the corona discharge characteristics of the corona discharge position meet the requirements. If not, it is determined that the corona discharge characteristics belong to the insulation defect part. If so, it goes to step S22.

[0034] Optionally, the above step S22 includes the following contents: S221 determines the corona discharge abnormal value of the corona discharge position according to the corona discharge characteristics of the corona discharge position, and judges whether the corona discharge abnormal value of the corona discharge position is greater than a preset abnormal threshold value. If so, proceed to the next step; if not, proceed to step S23; S222: using the insulation defect image feature of the corona discharge position to determine the image features at different insulation defect dimensions, and judging whether there is an insulation defect dimension whose image feature does not meet the requirements at the corona discharge position; if so, determining that the corona discharge feature belongs to the insulation defect position; if not, proceeding to the next step; S223 uses image features at different insulation defect dimensions to determine the insulation image abnormality value of the corona discharge position, and judges whether the insulation image abnormality value of the corona discharge position meets the requirements. If not, it is determined that the corona discharge feature belongs to the insulation defect position. If so, enter step S23.

[0035] Furthermore, the method for determining the benchmark inspection video is: The time at which the electric power equipment is located is determined by using the inspection time corresponding to the electric power equipment, and the inspection monitoring video within a preset time period close to the time at which the electric power equipment is located is used as a reference inspection video.

[0036] Specifically, the method for determining the historical inspection image of the power equipment is: Obtaining inspection video data of the drone during different historical inspection processes, and dividing the inspection video data into a plurality of segmented time periods using the duration of the reference inspection video; Determining image similarity coefficients of different image frames based on similarities between the divided time periods and different image frames of the reference inspection video; The video similarity coefficient between the segmented time period and the reference inspection video is determined by image similarity coefficients of different image frames, and the credibility of the segmented time period is determined by using the video similarity coefficient. Based on the credibility, it is determined whether the segmented time period is a historical inspection image.

[0037] It should also be noted that when the credibility of the segmented time period is greater than a preset credibility, the segmented time period is determined to be a historical inspection image.

[0038] It can also be understood that the method for determining the historical inspection image of the power equipment is: Obtaining inspection video data of the drone during different historical inspection processes, and dividing the inspection video data into a plurality of segmented time periods using the duration of the reference inspection video; Determine the image similarity coefficients of different image frames based on the similarity between the divided time period and the different image frames of the reference inspection video, and use the image similarity coefficients to determine whether there are similar video frames in the image frames, if so, proceed to the next step, if not, determine that the divided time period does not belong to the historical inspection image of the power equipment; Determine whether the average value of the image similarity coefficients of the image frames different from the reference inspection video meets the requirement, if so, proceed to the next step, if not, determine that the divided time period does not belong to the historical inspection image of the power equipment; Using the image similarity coefficient, determine the similar video frames between the segmented time period and the reference inspection video, and judge whether the number ratio of the similar video frames meets the requirement. If so, proceed to the next step; if not, determine that the segmented time period does not belong to the historical inspection image of the power equipment; The video similarity coefficient between the segmented time period and the reference inspection video is determined by image similarity coefficients of different image frames, and the credibility of the segmented time period is determined by using the video similarity coefficient. Based on the credibility, it is determined whether the segmented time period is a historical inspection image.

[0039] Furthermore, the method for determining the partial discharge state value of the electric power equipment is: Determine the insulation defect variation of different historical inspection images according to the insulation defect image characteristics of the insulation defect part and the change of the corona discharge characteristics between the historical inspection image and the fused image; Determine the duration between different historical inspection images and the current moment based on the corresponding moments of different historical inspection images, and determine the partial discharge state change values ​​of different historical inspection images in combination with the insulation defect change amounts and credibility of different historical inspection images; Determine the partial discharge problem state value of the insulation defect part by using the insulation defect image characteristics and corona discharge characteristics of the insulation defect part, and further determine the partial discharge state evaluation value of the insulation defect position in combination with the partial discharge state change values ​​of different historical inspection images; The partial discharge state value of the electric power equipment is determined according to the partial discharge state evaluation amount at different insulation defect positions.

[0040] Example 2 On the other hand, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned method for identifying and analyzing partial discharge image consistency.

[0041] Through the above embodiments, the present invention achieves the following beneficial effects: 1. In the present invention, whether there is any suspected abnormality in the partial discharge state of the power equipment is determined based on the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image and the operating voltage, thereby realizing the screening of the power equipment with suspected abnormality in the partial discharge state from the perspective of the operating voltage of the power equipment and the severity of the corona discharge characteristics, avoiding the technical problem of low efficiency of evaluation and processing caused by evaluating the partial discharge state values ​​of all power equipment, and improving the pertinence and processing efficiency of the partial discharge state evaluation.

[0042] 2. In the present invention, the insulation defect location of the power equipment is determined by fusing the distribution data of the insulation defect image features and the corona discharge features in the image, thereby avoiding the technical problem of low recognition accuracy of the insulation defect location caused by the use of a single image. The screening of the insulation defect location from the perspective of multiple images is fully considered, which improves the recognition and processing accuracy of the insulation defect location and also lays a foundation for further evaluating the partial discharge state value of the power equipment based on the insulation defect location.

[0043] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0044] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0045] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for identifying and analyzing the consistency of partial discharge images, characterized in that: Specifically include: The ultraviolet partial discharge image of the power equipment is acquired by using a drone, and when it is determined that there is a suspected abnormality in the partial discharge state of the power equipment based on the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image and the operating voltage, the next step is entered; Acquire a visualized image of the electric power equipment, and obtain a fused image based on a consistency evaluation result of the image features of the visualized image and the ultraviolet partial discharge image, and determine the insulation defect location of the electric power equipment through distribution data of insulation defect image features and corona discharge features in the fused image; Determine the benchmark inspection video based on the time when the power equipment is located, and determine the historical inspection image of the power equipment of the drone and the credibility based on the similarity of different image frames with the benchmark inspection video; Based on the historical inspection images and fused images, the changes in the insulation defect image characteristics and corona discharge characteristics of the insulation defect location are determined, and the partial discharge state value of the power equipment is determined in combination with the credibility of different historical inspection images.

2. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: The ultraviolet partial discharge image of the electric power equipment is acquired according to the ultraviolet camera device of the UAV.

3. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: The distribution data of the corona discharge characteristics include the corona discharge characteristics at different locations of the ultraviolet partial discharge image.

4. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: Determine that the partial discharge state of the power equipment is suspected to be abnormal, specifically including: Determining the operating voltage deviation of the electric equipment according to the deviation between the operating voltage of the electric equipment and the rated operating voltage, and determining the limited interval of corona discharge using the operating voltage deviation; Determine the corona discharge characteristics of different parts in the ultraviolet partial discharge image by using the distribution data of the corona discharge characteristics in the ultraviolet partial discharge image, and determine the discharge severity of different parts according to the corona discharge characteristics of different parts; Whether there is suspected abnormality in the partial discharge state of the electric power equipment is determined by the deviation of the discharge severity of different parts from the limited interval of the corona discharge.

5. The method for identifying and analyzing the consistency of partial discharge images according to claim 4, characterized in that: When there is a portion where the severity of the discharge is not within the limited range of the corona discharge, it is determined that there is a suspected abnormality in the partial discharge state of the electric power equipment.

6. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: The method for constructing the fused image is: Determining similar positions of the image features of the visualized image and the ultraviolet partial discharge image based on a consistency evaluation result of the image features of the visualized image and the ultraviolet partial discharge image; The visualization image and the ultraviolet partial discharge image are aligned using the similar positions to obtain the fused image.

7. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: The method for determining the insulation defect location is: Determining the position of the electric power equipment with corona discharge in the fused image based on the distribution data of the corona discharge characteristics, and taking the position of the electric power equipment with corona discharge as the corona discharge position; Determine image features at different insulation defect dimensions using the insulation defect image features at the corona discharge position, and determine insulation image abnormality values ​​at the corona discharge position using the image features at different insulation defect dimensions; The corona discharge abnormal value of the corona discharge position is determined according to the corona discharge characteristics of the corona discharge position, the insulation defect abnormal value of the corona discharge position is determined by the corona discharge abnormal value and the insulation image abnormal value, and the insulation defect part in the corona discharge position is determined by using the insulation defect abnormal value.

8. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: The method for determining the benchmark inspection video is: The time at which the electric power equipment is located is determined by using the inspection time corresponding to the electric power equipment, and the inspection monitoring video within a preset time period close to the time at which the electric power equipment is located is used as a reference inspection video.

9. The method for identifying and analyzing the consistency of partial discharge images according to claim 1, characterized in that: The method for determining the historical inspection image of the power equipment is: Obtaining inspection video data of the drone during different historical inspection processes, and dividing the inspection video data into a plurality of segmented time periods using the duration of the reference inspection video; Determining image similarity coefficients of different image frames based on similarities between the divided time periods and different image frames of the reference inspection video; The video similarity coefficient between the segmented time period and the reference inspection video is determined by image similarity coefficients of different image frames, and the credibility of the segmented time period is determined by using the video similarity coefficient. Based on the credibility, it is determined whether the segmented time period is a historical inspection image.

10. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, a partial discharge image consistency identification and analysis processing method as described in any one of claims 1-9 is executed.

Images