An image processing-based secondary equipment maintenance assistance method and system

Abstract

The application provides a secondary equipment maintenance auxiliary method based on image processing, which comprises the following steps: periodically acquiring color maintenance images of a target secondary equipment; preprocessing the color maintenance images acquired in each period into corresponding gray images, and calculating row pixel characteristic values and column pixel characteristic values of the gray images in each period; further comparing each row pixel characteristic value calculated by the gray images in each period with the pixel characteristic value in the same row calculated by the gray images in the previous period, and comparing each column pixel characteristic value calculated by the gray images in each period with the pixel characteristic value in the same column calculated by the gray images in the previous period, so as to determine the difference points between the gray images in adjacent periods; and locating the fault position of the target secondary equipment according to the determined difference points. By implementing the application, the problem of inaccurate state verification caused by the deviation between the fault judgment of the traditional method and the actual scene and the timeliness of processing can be solved.

Description

Technical Field

[0001] This invention relates to the field of power equipment maintenance technology, and in particular to a secondary equipment maintenance auxiliary method and system based on image processing. Background Technology

[0002] Secondary equipment in substations is an important part of monitoring high-voltage equipment. Due to its large number and different interfaces, the operation conditions, equipment failures, and secondary line faults of the equipment make maintenance and auxiliary work of secondary equipment quite difficult.

[0003] Currently, monitoring electrical quantities to assist in the maintenance of secondary equipment relies on on-site video surveillance. However, this method suffers from several drawbacks. First, inconsistent data acquisition standards and disorganized data recording and analysis methods make it difficult to pinpoint the specific faulty secondary equipment, leading to discrepancies between monitoring personnel's fault assessments and the actual situation. Second, timeliness issues result in faults not being detected promptly or incomplete maintenance coverage, leading to inaccurate verification of secondary equipment status and posing certain safety hazards.

[0004] Therefore, there is an urgent need for a new auxiliary method for secondary equipment maintenance that can solve the problems of inaccurate status verification caused by deviations between the fault diagnosis and the actual site conditions and the timeliness of processing in traditional methods. Summary of the Invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a secondary equipment maintenance auxiliary method and system based on image processing, which can solve the problems of inaccurate status verification caused by deviation between the fault judgment and the actual site and the timeliness of processing in traditional methods.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a secondary equipment maintenance assistance method based on image processing, the method comprising the following steps:

[0007] Periodically acquire color maintenance images of the target secondary equipment;

[0008] The color inspection images acquired in each cycle are preprocessed into corresponding grayscale images, and the row pixel feature values ​​and column pixel feature values ​​of the grayscale images in each cycle are calculated. Furthermore, the pixel feature values ​​of each row calculated in the grayscale images of each cycle are compared with the pixel feature values ​​of the same row calculated in the grayscale images of the previous cycle, and the pixel feature values ​​of each column calculated in the grayscale images of each cycle are compared with the pixel feature values ​​of the same column calculated in the grayscale images of the previous cycle, so as to determine the differences between grayscale images in adjacent cycles.

[0009] Based on the identified differences, the fault location of the target secondary equipment can be determined.

[0010] The specific steps involved in preprocessing the color inspection images acquired in each cycle into corresponding grayscale images, calculating the row and column pixel feature values ​​of the grayscale images in each cycle, further comparing each row pixel feature value calculated in each cycle with the pixel feature value of the same row calculated in the previous cycle, and comparing each column pixel feature value calculated in each cycle with the pixel feature value of the same column calculated in the previous cycle, to determine the differences between grayscale images in adjacent cycles, include:

[0011] The color maintenance images acquired in each cycle are processed into grayscale images in Ycbcr format and the Y component is extracted to obtain the grayscale image corresponding to each cycle.

[0012] According to the formula Calculate the pixel feature value S(m) of each row of the grayscale image in each period; where m∈[1,2,...,M]; M is the total number of rows in the grayscale images in each period, N is the total number of columns in the grayscale images in each period; I(i) is the value of the i-th pixel in each row;

[0013] According to the formula Calculate the pixel feature value S(n) of each column of the grayscale image for each period; where n∈[1,2,...,N]; I(j) is the value of the j-th pixel in each column;

[0014] Each row of pixel feature values ​​calculated for each grayscale image in each period is compared with the pixel feature values ​​of the same row calculated for the grayscale image in the previous period. If it is determined that the difference between the pixel feature values ​​of two grayscale images in adjacent periods at least in the kth row is less than or equal to the first preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the kth row; where 1≤k≤M.

[0015] Each column of pixel feature values ​​calculated for each grayscale image in each period is compared with the same column of pixel feature values ​​calculated for the grayscale image in the previous period. If it is determined that the difference between the pixel feature values ​​of at least the l-th column of two grayscale images in adjacent periods is less than or equal to the second preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the l-th row; where 1≤l≤N.

[0016] The specific steps for locating the fault location of the target secondary equipment based on the determined differences include:

[0017] Based on the row and / or column where each difference point is located, draw one or more regions and locate each drawn region as the fault location of the target secondary equipment.

[0018] The color inspection images of the target secondary equipment were captured in real time on-site by the same camera.

[0019] This invention also provides a secondary equipment maintenance auxiliary system based on image processing, comprising:

[0020] The information acquisition module is used to periodically acquire color maintenance images of the target secondary equipment;

[0021] The image comparison module is used to preprocess the color inspection images acquired in each cycle into corresponding grayscale images, calculate the row pixel feature values ​​and column pixel feature values ​​of the grayscale images in each cycle, and further compare each row pixel feature value calculated in each cycle with the pixel feature value calculated in the same row of the grayscale images in the previous cycle, and compare each column pixel feature value calculated in each cycle with the pixel feature value calculated in the same column of the grayscale images in the previous cycle, so as to determine the differences between grayscale images in adjacent cycles.

[0022] The classification and analysis module is used to locate the fault location of the target secondary equipment based on the identified differences.

[0023] The image comparison module includes:

[0024] The image processing submodule is used to process the color inspection images acquired in each cycle into grayscale images in Ycbcr format and extract the Y component to obtain the grayscale image corresponding to each cycle.

[0025] The row pixel feature value calculation submodule is used to calculate the feature value according to the formula. Calculate the pixel feature value S(m) of each row of the grayscale image in each period; where m∈[1,2,...,M]; M is the total number of rows in the grayscale images in each period, N is the total number of columns in the grayscale images in each period; I(i) is the value of the i-th pixel in each row;

[0026] The column pixel feature value calculation submodule is used to calculate the feature value according to the formula. Calculate the pixel feature value S(n) of each column of the grayscale image for each period; where n∈[1,2,...,N]; I(j) is the value of the j-th pixel in each column;

[0027] The first difference point marking submodule is used to compare the pixel feature value of each row of the grayscale image calculated in each period with the pixel feature value of the same row of the grayscale image calculated in the previous period. If it is determined that the difference between the pixel feature values ​​of the two grayscale images in adjacent periods is less than or equal to the first preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the kth row; where 1≤k≤M;

[0028] The second difference point marking submodule is used to compare each column of pixel feature value calculated for each grayscale image in each period with the pixel feature value of the same column calculated for the grayscale image in the previous period. If it is determined that the difference between the pixel feature values ​​of the two grayscale images in adjacent periods is less than or equal to the second preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the l-th row; where 1≤l≤N.

[0029] The color inspection images of the target secondary equipment were captured in real time on-site by the same camera.

[0030] Implementing the embodiments of the present invention has the following beneficial effects:

[0031] 1. In this invention, the color maintenance images of the target secondary equipment in each cycle are preprocessed into corresponding grayscale images. By extracting the pixel feature values ​​of each row and each column of each grayscale image, the difference points between adjacent grayscale images are compared to accurately locate the fault location of the target secondary equipment. This can help monitoring personnel accurately locate the specific faulty equipment when making fault judgments and verifying the status of the secondary equipment. This achieves the goal of solving the problem of inaccurate status verification caused by the deviation between the fault judgment and the actual site and the timeliness of the processing in traditional methods.

[0032] 2. In this invention, the color inspection images of the target secondary equipment are captured in real time on-site by the same camera, thereby ensuring the timeliness of on-site operation and maintenance of the secondary equipment. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, obtaining other drawings based on these drawings without creative effort still falls within the scope of the present invention.

[0034] Figure 1 A flowchart illustrating an image processing-based auxiliary method for secondary equipment maintenance, provided in an embodiment of the present invention;

[0035] Figure 2This is a schematic diagram of a secondary equipment maintenance auxiliary system based on image processing, provided in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0037] like Figure 1 As shown in the figure, an image processing-based auxiliary method for secondary equipment maintenance is provided in an embodiment of the present invention. The method includes the following steps:

[0038] Step S1: Periodically acquire color inspection images of the target secondary equipment;

[0039] Step S2: The color inspection images acquired in each cycle are preprocessed into corresponding grayscale images, and the row pixel feature values ​​and column pixel feature values ​​of the grayscale images in each cycle are calculated. Furthermore, the pixel feature values ​​of each row of the grayscale images in each cycle are compared with the pixel feature values ​​of the same row of the grayscale images in the previous cycle, and the pixel feature values ​​of each column of the grayscale images in each cycle are compared with the pixel feature values ​​of the same column of the grayscale images in the previous cycle, so as to determine the differences between grayscale images in adjacent cycles.

[0040] Step S3: Based on the identified differences, locate the fault location of the target secondary equipment.

[0041] The specific process is as follows: In step S1, a camera captures a color inspection image of the target secondary equipment in real time on site and sends it to a computing device. The computing device then periodically collects the color image through a predefined acquisition cycle for subsequent analysis.

[0042] In step S2, firstly, the color inspection images acquired in each cycle are processed into grayscale images in Ycbcr format and the Y component is extracted to obtain the grayscale images corresponding to each cycle.

[0043] Secondly, according to the formula Calculate the pixel feature value S(m) of each row of the grayscale image in each period; where m∈[1,2,...,M]; M is the total number of rows in the grayscale images in each period, N is the total number of columns in the grayscale images in each period; I(i) is the value of the i-th pixel in each row;

[0044] Next, according to the formula Calculate the pixel feature value S(n) of each column of the grayscale image for each period; where n∈[1,2,...,N]; I(j) is the value of the j-th pixel in each column;

[0045] Then, the pixel feature value calculated for each row of grayscale image in each period is compared with the pixel feature value calculated for the same row of grayscale image in the previous period. If it is determined that the difference between the pixel feature values ​​of two grayscale images in adjacent periods is less than or equal to the first preset threshold at least in the kth row, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the kth row; where 1≤k≤M.

[0046] Finally, each column of pixel feature values ​​calculated for each grayscale image in each period is compared with the same column of pixel feature values ​​calculated for the grayscale image in the previous period. If it is determined that the difference between the pixel feature values ​​of at least the l-th column of two grayscale images in adjacent periods is less than or equal to the second preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the l-th row; where 1≤l≤N.

[0047] It should be noted that the comparison of pixel feature values ​​in the same row or column between two grayscale images in adjacent periods is not limited to difference calculation. It can also be done through Euclidean distance calculation or other methods. The specific method can be flexibly adjusted.

[0048] In step S3, one or more regions are drawn based on the row and / or column where each difference point is located, and each drawn region is located as the fault location of the target secondary equipment.

[0049] Understandably, the color inspection images of the target secondary equipment carry information such as the time and location of the shooting. Therefore, while locating the fault location of the target secondary equipment, it is possible to know the time of the fault and the location of the equipment, thereby further ensuring the timeliness of on-site operation and maintenance of the secondary equipment.

[0050] like Figure 2 As shown in the figure, an image processing-based auxiliary system for secondary equipment maintenance is provided in an embodiment of the present invention, comprising:

[0051] The information acquisition module 110 is used to periodically acquire color maintenance images of the target secondary equipment;

[0052] The image comparison module 120 is used to preprocess the color inspection images acquired in each cycle into corresponding grayscale images, calculate the row pixel feature values ​​and column pixel feature values ​​of the grayscale images in each cycle, and further compare each row pixel feature value calculated in each cycle with the pixel feature value calculated in the same row of the grayscale image in the previous cycle, and compare each column pixel feature value calculated in each cycle with the pixel feature value calculated in the same column of the grayscale image in the previous cycle, so as to determine the difference points between grayscale images in adjacent cycles.

[0053] The classification analysis module 139 is used to locate the fault location of the target secondary equipment based on the identified differences.

[0054] The image comparison module includes:

[0055] The image processing submodule is used to process the color inspection images acquired in each cycle into grayscale images in Ycbcr format and extract the Y component to obtain the grayscale image corresponding to each cycle.

[0056] The row pixel feature value calculation submodule is used to calculate the feature value according to the formula. Calculate the pixel feature value S(m) of each row of the grayscale image in each period; where m∈[1,2,...,M]; M is the total number of rows in the grayscale images in each period, N is the total number of columns in the grayscale images in each period; I(i) is the value of the i-th pixel in each row;

[0057] The column pixel feature value calculation submodule is used to calculate the feature value according to the formula. Calculate the pixel feature value S(n) of each column of the grayscale image for each period; where n∈[1,2,...,N]; I(j) is the value of the j-th pixel in each column;

[0058] The first difference point marking submodule is used to compare the pixel feature value of each row of the grayscale image calculated in each period with the pixel feature value of the same row of the grayscale image calculated in the previous period. If it is determined that the difference between the pixel feature values ​​of the two grayscale images in adjacent periods is less than or equal to the first preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the kth row; where 1≤k≤M;

[0059] The second difference point marking submodule is used to compare each column of pixel feature value calculated for each grayscale image in each period with the pixel feature value of the same column calculated for the grayscale image in the previous period. If it is determined that the difference between the pixel feature values ​​of the two grayscale images in adjacent periods is less than or equal to the second preset threshold, then it is determined that there is a difference point between the grayscale images in adjacent periods, and the difference point is marked as being located in the l-th row; where 1≤l≤N.

[0060] The color inspection images of the target secondary equipment were captured in real time on-site by the same camera.

[0061] Implementing the embodiments of the present invention has the following beneficial effects:

[0062] 1. In this invention, the color maintenance images of the target secondary equipment in each cycle are preprocessed into corresponding grayscale images. By extracting the pixel feature values ​​of each row and each column of each grayscale image, the difference points between adjacent grayscale images are compared to accurately locate the fault location of the target secondary equipment. This can help monitoring personnel accurately locate the specific faulty equipment when making fault judgments and verifying the status of the secondary equipment. This achieves the goal of solving the problem of inaccurate status verification caused by the deviation between the fault judgment and the actual site and the timeliness of the processing in traditional methods.

[0063] 2. In this invention, the color inspection images of the target secondary equipment are captured in real time on-site by the same camera, thereby ensuring the timeliness of on-site operation and maintenance of the secondary equipment.

[0064] It is worth noting that the various system modules included in the above system embodiments are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional module are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0065] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as ROM / RAM, disk, optical disk, etc.

[0066] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A secondary equipment maintenance auxiliary method based on image processing, characterized in that, The method includes the following steps: Periodically acquire color maintenance images of the target secondary equipment; The color inspection images acquired in each cycle are preprocessed into corresponding grayscale images, and the row pixel feature values ​​and column pixel feature values ​​of the grayscale images in each cycle are calculated. Furthermore, the pixel feature values ​​of each row calculated in the grayscale images of each cycle are compared with the pixel feature values ​​of the same row calculated in the grayscale images of the previous cycle, and the pixel feature values ​​of each column calculated in the grayscale images of each cycle are compared with the pixel feature values ​​of the same column calculated in the grayscale images of the previous cycle, so as to determine the differences between grayscale images in adjacent cycles. Based on the identified differences, the fault location of the target secondary equipment is located. The specific steps involved in preprocessing the color inspection images acquired in each cycle into corresponding grayscale images, calculating the row and column pixel feature values ​​of the grayscale images in each cycle, further comparing each row pixel feature value calculated in each cycle with the pixel feature value of the same row calculated in the previous cycle, and comparing each column pixel feature value calculated in each cycle with the pixel feature value of the same column calculated in the previous cycle, to determine the differences between grayscale images in adjacent cycles, include: The color maintenance images acquired in each cycle are processed into grayscale images in Ycbcr format and the Y component is extracted to obtain the grayscale image corresponding to each cycle. According to the formula Calculate the pixel feature values ​​of each row in the grayscale image for each period. ;in, ; This represents the total number of rows common to grayscale images across all periods. This represents the total number of columns common to grayscale images across all periods. For each row, the first The value of each pixel; ; According to the formula Calculate the pixel feature values ​​of each column in the grayscale image for each period. ;in, ; For each column The value of each pixel; ; Each row of pixel feature values ​​calculated for the grayscale image in each period is compared with the pixel feature values ​​of the same row calculated for the grayscale image in the previous period. If it is determined that two grayscale images in adjacent periods are at least in the [number missing]th period... If the difference in pixel feature values ​​between rows is less than or equal to a first preset threshold, then it is determined that there is a difference point between grayscale images of adjacent periods, and the difference point is marked as being located in the first period. Above; among them, ; Each column of pixel feature values ​​calculated for each grayscale image period is compared with the same column of pixel feature values ​​calculated for the grayscale image of the previous period. If it is determined that two grayscale images from adjacent periods are at least in the [number missing]th period... If the difference in pixel feature values ​​of a column is less than or equal to a second preset threshold, then it is determined that there is a difference point between grayscale images of adjacent periods, and the difference point is marked as being located in the first period. Above; among them, .

2. The secondary equipment maintenance auxiliary method based on image processing as described in claim 1, characterized in that, The specific steps for locating the fault location of the target secondary equipment based on the determined difference points include: Based on the row and / or column where each difference point is located, draw one or more regions and locate each drawn region as the fault location of the target secondary equipment.

3. The secondary equipment maintenance auxiliary method based on image processing as described in claim 1, characterized in that, The color inspection images of the target secondary equipment were captured in real time on-site by the same camera.

4. A secondary equipment maintenance auxiliary system based on image processing, characterized in that, include: The information acquisition module is used to periodically acquire color maintenance images of the target secondary equipment; The image comparison module is used to preprocess the color inspection images acquired in each cycle into corresponding grayscale images, calculate the row pixel feature values ​​and column pixel feature values ​​of the grayscale images in each cycle, and further compare each row pixel feature value calculated in each cycle with the pixel feature value calculated in the same row of the grayscale images in the previous cycle, and compare each column pixel feature value calculated in each cycle with the pixel feature value calculated in the same column of the grayscale images in the previous cycle, so as to determine the differences between grayscale images in adjacent cycles. The classification and analysis module is used to locate the fault location of the target secondary equipment based on the identified differences. The image comparison module includes: The image processing submodule is used to process the color inspection images acquired in each cycle into grayscale images in Ycbcr format and extract the Y component to obtain the grayscale image corresponding to each cycle. The row pixel feature value calculation submodule is used to calculate the feature value according to the formula. Calculate the pixel feature values ​​of each row in the grayscale image for each period. ;in, ; This represents the total number of rows common to grayscale images across all periods. This represents the total number of columns common to grayscale images across all periods. For each row, the first The value of each pixel; ; The column pixel feature value calculation submodule is used to calculate the feature value according to the formula. Calculate the pixel feature values ​​of each column in the grayscale image for each period. ;in, ; For each column The value of each pixel; ; The first difference point marking submodule is used to compare the pixel feature value of each row calculated for each grayscale image in each period with the pixel feature value of the same row calculated for the grayscale image in the previous period. If it is determined that two grayscale images in adjacent periods are at least in the [number missing]th period, the submodule will mark the difference point. If the difference in pixel feature values ​​between rows is less than or equal to a first preset threshold, then it is determined that there is a difference point between grayscale images of adjacent periods, and the difference point is marked as being located in the first period. Above; among them, ; The second difference point marking submodule is used to compare each column of pixel feature values ​​calculated for each grayscale image in each period with the pixel feature values ​​of the same column calculated for the grayscale image in the previous period. If it is determined that two grayscale images in adjacent periods are at least in the [number missing]th period, the submodule will mark the difference point marking submodule. If the difference in pixel feature values ​​of a column is less than or equal to a second preset threshold, then it is determined that there is a difference point between grayscale images of adjacent periods, and the difference point is marked as being located in the first period. Above; among them, .

5. The secondary equipment maintenance auxiliary system based on image processing as described in claim 4, characterized in that, The color inspection images of the target secondary equipment were captured in real time on-site by the same camera.

Images