Power grid state evaluation method and device, terminal equipment and storage medium

Abstract

The invention discloses a power grid state evaluation method and device, terminal equipment and a storage medium, and the method comprises the steps: carrying out the calculation of the slope and the slope value of each pixel point in a to-be-detected region of a power grid equipment picture, further calculating the amplification data, carrying out the convolution processing and binary processing, and carrying out the calculation to obtain crack labeling graph data, and finally, counting the number of abnormal pixel points according to the crack labeling graph data of all the pixel points, and further evaluating the state of the power grid. According to the power grid state evaluation method provided by the invention, the crack annotation graph data can be automatically generated according to the power grid equipment picture, the crack state can be determined according to the crack annotation graph data, and the state of the power grid is further evaluated. Compared with artificial visual detection, the method is higher in precision, saves manpower, and improves the power grid state evaluation accuracy and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of power transmission and transformation equipment fault identification, and in particular to a power grid state assessment method, device, terminal equipment and storage medium based on graph data processing. Background Art

[0002] With the continuous expansion of the scale of power grids and the continuous development of smart grid technology, information technology and operation and maintenance technology, the status data of power transmission and transformation equipment in power grids gradually presents big data characteristics such as large volume and multiple types; accurately assessing the operating status of power transmission and transformation equipment (such as power transformers, high-voltage circuit breakers, GIS, insulators, etc.) of power grids and formulating targeted maintenance and operation strategies in a timely manner are of great significance to ensure the safe, reliable and economic operation of power systems. For important power transmission and transformation equipment such as transformers and power boxes that are exposed to the outdoors for a long time, there is a risk of cracks due to humidity, temperature, soil settlement and even salinity abnormalities, which will cause changes in the operating status of power transmission and transformation equipment and even cause emergency status in power grid operation. Therefore, the crack risk of power transmission and transformation equipment in power grids should be regarded as an important part of power grid status assessment. At present, the commonly used crack detection method for power transmission and transformation equipment is mainly visual detection, which relies on the naked eye observation of patrol personnel. This method has low detection accuracy for subtle defects such as small cracks and requires a lot of manpower costs, resulting in low accuracy and efficiency of power grid status assessment based on crack detection. Summary of the invention

[0003] The present invention provides a power grid state assessment method, device, terminal equipment and storage medium to solve the technical problems of low detection accuracy and labor-intensiveness caused by reliance on human visual detection in the prior art.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a power grid state assessment method, including:

[0005] Obtaining a picture of a power grid device; wherein the picture of the power grid device has circled an area to be detected where cracks may exist;

[0006] For each pixel point in the area to be detected, the slope degree and slope value of the pixel point are calculated according to the coordinate information and pixel value of the pixel point; the enlarged data of the pixel point is calculated according to the slope degree and slope value; the enlarged data is convolved to obtain a convolution result; the convolution result is binarized to obtain binarized data; the crack annotation map data of the pixel point is calculated according to the binarized data;

[0007] According to the crack marking map data of all pixels in the area to be detected, the number of abnormal pixels whose grayscale values ​​of the crack marking map data are less than a preset grayscale reference value is counted; if the number of abnormal pixels is less than a preset first threshold, the power grid state is determined to be a normal operating state; if the number of abnormal pixels is not less than the first threshold and less than a preset second threshold, the power grid state is determined to be a warning state; if the number of abnormal pixels is not less than the second threshold, the power grid state is determined to be an emergency state; wherein the first threshold is less than the second threshold.

[0008] As a preferred solution, the coordinate information includes: horizontal coordinates and vertical coordinates;

[0009] The calculating the slope degree and the slope value of the pixel point according to the coordinate information and the pixel value of the pixel point comprises:

[0010] Calculating the horizontal slope of the pixel point according to the horizontal coordinate and the pixel value of the pixel point;

[0011] Calculating the vertical slope of the pixel point according to the vertical coordinate and pixel value of the pixel point;

[0012] Calculate the slope degree and slope value of the pixel point according to the horizontal slope and the vertical slope;

[0013] The calculation formula of the slope is:

[0014]

[0015] Wherein, SL(p) represents the slope of the p-th pixel in the area to be detected; atan represents the inverse tangent function; ‖·‖ represents the norm function; LF() represents the filter function; represents the horizontal slope of the p-th pixel in the area to be detected; represents the vertical slope of the p-th pixel in the area to be detected;

[0016] The calculation formula of the slope value is:

[0017]

[0018] Wherein, VSL(p) represents the slope value of the p-th pixel in the area to be detected.

[0019] As a preferred solution, the filter function is a linear filter function, a mean filter function, a median filter function or a Gaussian filter function.

[0020] As a preferred solution, the calculation formula for the amplified data is:

[0021]

[0022] Wherein, AMP(p) represents the amplified data of the p-th pixel in the area to be detected; VSL(p) represents the slope value of the p-th pixel in the area to be detected; SL(p) represents the slope degree of the p-th pixel in the area to be detected; K1 is the preset amplification adjustment coefficient.

[0023] As a preferred solution, the formula for the convolution process is:

[0024] FEE(p) = conv(AMP(p)NIE);

[0025]

[0026] Wherein, FEE(p) represents the convolution result of the p-th pixel in the area to be detected; conv() represents the convolution function; NIE represents the convolution kernel; K2 is the preset convolution kernel adjustment coefficient.

[0027] As a preferred solution, the binary processing...

[0028] As a preferred solution, the calculation formula of the crack annotation map data is:

[0029]

[0030] Wherein, LH(p) represents the crack annotation map data of the p-th pixel point in the area to be detected; BFEE(p) represents the binary data of the p-th pixel point in the area to be detected; max() represents taking the maximum value.

[0031] Based on the above embodiment, another embodiment of the present invention provides a power grid state assessment device, including: a data acquisition module, a data processing module and a state assessment module;

[0032] The data acquisition module is used to acquire a picture of the power grid equipment; wherein the picture of the power grid equipment has circled the area to be detected where cracks may exist;

[0033] The data processing module is used to calculate the slope degree and slope value of each pixel point in the area to be detected according to the coordinate information and pixel value of the pixel point; calculate the enlarged data of the pixel point according to the slope degree and slope value; perform convolution processing on the enlarged data to obtain a convolution result; perform binarization processing on the convolution result to obtain binarized data; and calculate the crack annotation map data of the pixel point according to the binarized data;

[0034] The state evaluation module is used to count the number of abnormal pixels whose grayscale values ​​of the crack annotation map data are less than a preset grayscale reference value based on the crack annotation map data of all pixels in the area to be detected; if the number of abnormal pixels is less than a preset first threshold, the power grid state is determined to be a normal operating state; if the number of abnormal pixels is not less than the first threshold and less than a preset second threshold, the power grid state is determined to be a warning state; if the number of abnormal pixels is not less than the second threshold, the power grid state is determined to be an emergency state; wherein the first threshold is less than the second threshold.

[0035] Based on the above embodiments, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the power grid status assessment method described in the above embodiments of the invention is implemented.

[0036] Based on the above embodiments, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the power grid status assessment method described in the above invention embodiment.

[0037] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0038] The present invention calculates the slope degree and slope value for each pixel point in the area to be detected in the power grid equipment image, further calculates the amplified data, then performs convolution processing and binary processing, and then calculates the crack annotation map data, and finally counts the number of abnormal pixels based on the crack annotation map data of all pixels to further evaluate the power grid state. The power grid state evaluation method provided by the present invention can automatically generate crack annotation map data based on the power grid equipment image, and the state of the crack can be determined based on the crack annotation map data, and the state of the power grid can be further evaluated. Compared with manual visual detection, the present invention has higher accuracy, saves manpower, and improves the accuracy and efficiency of power grid state evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of a method for evaluating a power grid state provided by an embodiment of the present invention;

[0040] Figure 2 is an original image of the area to be detected provided by an embodiment of the present invention;

[0041] Figure 3 This is a crack detection effect diagram provided by an embodiment of the present invention;

[0042] Figure 4It is a structural diagram of a power grid status assessment device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] Please refer to Figure 1 , is a flow chart of a method for evaluating a power grid state provided by an embodiment of the present invention, comprising:

[0046] S1. Obtain a picture of a power grid device; wherein the picture of the power grid device has circled an area to be detected where cracks may exist.

[0047] It should be noted that the grid equipment images are photos of grid power transmission and transformation equipment taken by high-definition cameras, and the areas to be inspected where cracks may exist are preliminarily circled manually, or preliminarily identified through simple image recognition methods.

[0048] S2. For each pixel point in the area to be detected, the slope degree and slope value of the pixel point are calculated according to the coordinate information and pixel value of the pixel point; the amplified data of the pixel point is calculated according to the slope degree and slope value; the amplified data is convolved to obtain a convolution result; the convolution result is binarized to obtain binarized data; the crack annotation map data of the pixel point is calculated according to the binarized data.

[0049] It should be noted that the crack annotation data refers to the data information used to display the cracks and is used to draw Figure 3 Data from the attached figure shown.

[0050] In a preferred embodiment, the coordinate information includes: horizontal coordinates and vertical coordinates;

[0051] The calculating the slope degree and the slope value of the pixel point according to the coordinate information and the pixel value of the pixel point comprises:

[0052] Calculating the horizontal slope of the pixel point according to the horizontal coordinate and the pixel value of the pixel point;

[0053] Calculating the vertical slope of the pixel point according to the vertical coordinate and pixel value of the pixel point;

[0054] Calculate the slope degree and slope value of the pixel point according to the horizontal slope and the vertical slope;

[0055] The calculation formula of the slope is:

[0056]

[0057] Wherein, SL(p) represents the slope of the p-th pixel in the area to be detected; atan represents the inverse tangent function; ‖·‖ represents the norm function; LF() represents the filter function; represents the horizontal slope of the p-th pixel in the area to be detected; represents the vertical slope of the p-th pixel in the area to be detected;

[0058] The calculation formula of the slope value is:

[0059]

[0060] Wherein, VSL(p) represents the slope value of the p-th pixel in the area to be detected.

[0061] It should be noted that the horizontal slope is the ratio of the change in pixel value of a pixel relative to the pixel origin to the change in horizontal coordinate; the vertical slope is the ratio of the change in pixel value of a pixel relative to the pixel origin to the change in vertical coordinate. The pixel origin refers to the pixel with coordinates (0,0) in the pixel coordinate system. For example, the horizontal slope of the pixel point (2,4) is the pixel value of the pixel point (2,4) minus the pixel value of the pixel origin (0,0), divided by 2; the vertical slope of the pixel point (2,4) is the pixel value of the pixel point (2,4) minus the pixel value of the pixel origin (0,0), divided by 4.

[0062] In a preferred embodiment, the filter function is a linear filter function, a mean filter function, a median filter function or a Gaussian filter function.

[0063] In a preferred embodiment, the calculation formula of the amplified data is:

[0064]

[0065] Wherein, AMP(p) represents the amplified data of the p-th pixel in the area to be detected; VSL(p) represents the slope value of the p-th pixel in the area to be detected; SL(p) represents the slope degree of the p-th pixel in the area to be detected; K1 is the preset amplification adjustment coefficient.

[0066] It should be noted that the amplification adjustment coefficient K1 is preferably set to 57.

[0067] In a preferred embodiment, the formula for the convolution process is:

[0068] FEE(p) = conv(AMP(p)NIE);

[0069]

[0070] Wherein, FEE(p) represents the convolution result of the p-th pixel in the area to be detected; conv() represents the convolution function; NIE represents the convolution kernel; K2 is the preset convolution kernel adjustment coefficient.

[0071] It should be noted that the convolution function conv() is a one-dimensional convolution function. The convolution kernel adjustment coefficient K2 is a random number greater than 1 and less than 2.

[0072] The convolution processing after amplifying the pixel data can adjust the contrast of the crack edge to enhance the clarity and details of the crack, that is, to achieve sharpening and highlighting effects, so that the crack can be better identified.

[0073] In a preferred embodiment, the binarization of the convolution result to obtain binarized data includes:

[0074] According to the preset convolution threshold, the convolution result is divided into foreground and background;

[0075] The foreground is taken as the binarized data.

[0076] It should be noted that the preset convolution threshold may be a threshold at which the inter-class variance of the pixel means of the foreground and background pixels is the largest.

[0077] The process of determining the convolution threshold includes: first initializing a threshold T and dividing the convolution result into foreground and background, counting the number of foreground pixels in the foreground and the number of background pixels in the background; calculating the pixel mean according to the number of foreground pixels and the number of background pixels, and calculating the inter-class variance of the pixel mean; continuously adjusting the threshold and recalculating the inter-class variance of the pixel mean of the foreground area and the background area, and finding the threshold that makes the inter-class variance of the pixel mean of the foreground area and the background area the largest, as the convolution threshold.

[0078] In a preferred embodiment, the calculation formula of the crack annotation map data is:

[0079]

[0080] Wherein, LH(p) represents the crack annotation map data of the p-th pixel point in the area to be detected; BFEE(p) represents the binary data of the p-th pixel point in the area to be detected; max() represents taking the maximum value.

[0081] It should be noted that max(|BFEE(p)|) represents the maximum absolute value of the binary data of all the pixels in the intercepted suspected crack area.

[0082] S3. According to the crack marking map data of all the pixels in the area to be detected, the number of abnormal pixels whose grayscale values ​​of the crack marking map data are less than the preset grayscale reference value is counted; if the number of abnormal pixels is less than a preset first threshold, the power grid state is determined to be a normal operating state; if the number of abnormal pixels is not less than the first threshold and less than a preset second threshold, the power grid state is determined to be a warning state; if the number of abnormal pixels is not less than the second threshold, the power grid state is determined to be an emergency state; wherein the first threshold is less than the second threshold.

[0083] It should be noted that the crack annotation map data needs to be gray-scale processed to obtain gray-scale values. The gray-scale processing can be achieved by directly calling the function in Matlab, which belongs to the existing image gray-scale processing method.

[0084] In order to intuitively see the crack location, the crack marking map data can be output as image data and displayed. Figure 2 and Figure 3 , Figure 2 The grayscale image of the original image of the area to be inspected of the power grid equipment is shown. There are slight defects, rust and tiny cracks on the surface of the equipment that are difficult to detect with the naked eye. Figure 3 From the effect diagram of outputting crack annotation data using the present invention, it can be seen that there are about 10 black irregular lines of uneven thickness, and there are about 10 cracks on the surface of the power transmission and transformation equipment detected on the surface. The detected crack positions are located on the left side and upper middle side of the picture, and the black lines are obvious and easy to identify with the naked eye.

[0085] When there are multiple small cracks or minor defects, Figure 3 The displayed analysis results may still not be directly identifiable by the naked eye. Therefore, the present invention can evaluate the power grid status according to the crack annotation map data and the preset threshold value, specifically, calculating the number of grayscale values ​​of the crack annotation map data that are less than the grayscale reference value. When the number of values ​​less than the grayscale reference value is less than the first preset threshold value, it can be determined that the degree of cracks in the power transmission and transformation equipment of the power grid is low, and the power grid status is considered to be a normal operating state; when the number of values ​​less than the grayscale reference value is greater than or equal to the first preset threshold value and less than the second preset threshold value, it can be determined that the degree of cracks in the power transmission and transformation equipment of the power grid is aggravated, and the power grid status is considered to be a warning state; when the number of values ​​less than the grayscale reference value is greater than or equal to the second preset threshold value, it can be determined that the degree of cracks in the power transmission and transformation equipment of the power grid is serious, and the power grid status is considered to be an emergency state.

[0086] Since the value 0 represents black and the value 255 represents white in a grayscale image, the grayscale reference value should be close to 0, for example, 0.5 or 1. The values ​​of the first preset threshold and the second preset threshold can be flexibly set according to inspection requirements.

[0087] Embodiment 2

[0088] Please refer to Figure 4 , is a schematic diagram of the structure of a power grid status assessment device provided by an embodiment of the present invention, comprising: a data acquisition module, a data processing module and a status assessment module;

[0089] The data acquisition module is used to acquire a picture of the power grid equipment; wherein the picture of the power grid equipment has circled the area to be detected where cracks may exist;

[0090] The data processing module is used to calculate the slope degree and slope value of each pixel point in the area to be detected according to the coordinate information and pixel value of the pixel point; calculate the enlarged data of the pixel point according to the slope degree and slope value; perform convolution processing on the enlarged data to obtain a convolution result; perform binarization processing on the convolution result to obtain binarized data; and calculate the crack annotation map data of the pixel point according to the binarized data;

[0091] The state evaluation module is used to count the number of abnormal pixels whose grayscale values ​​of the crack annotation map data are less than a preset grayscale reference value based on the crack annotation map data of all pixels in the area to be detected; if the number of abnormal pixels is less than a preset first threshold, the power grid state is determined to be a normal operating state; if the number of abnormal pixels is not less than the first threshold and less than a preset second threshold, the power grid state is determined to be a warning state; if the number of abnormal pixels is not less than the second threshold, the power grid state is determined to be an emergency state; wherein the first threshold is less than the second threshold.

[0092] Embodiment 3

[0093] Accordingly, an embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the power grid status assessment method described in the above-mentioned embodiment of the invention.

[0094] Embodiment 4

[0095] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the power grid state assessment method described in the above-mentioned embodiment of the invention.

[0096] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0097] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0098] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0099] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0100] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0101] The storage medium is a storage medium, and the computer program is stored in the storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0102] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for evaluating power grid status, characterized in that: include: Obtaining a picture of a power grid device; wherein the picture of the power grid device has circled an area to be detected where cracks may exist; For each pixel point in the area to be detected, the slope degree and slope value of the pixel point are calculated according to the coordinate information and pixel value of the pixel point; the enlarged data of the pixel point is calculated according to the slope degree and slope value; the enlarged data is convolved to obtain a convolution result; the convolution result is binarized to obtain binarized data; the crack annotation map data of the pixel point is calculated according to the binarized data; According to the crack marking map data of all pixels in the area to be detected, the number of abnormal pixels whose grayscale values ​​of the crack marking map data are less than a preset grayscale reference value is counted; if the number of abnormal pixels is less than a preset first threshold, the power grid state is determined to be a normal operating state; if the number of abnormal pixels is not less than the first threshold and less than a preset second threshold, the power grid state is determined to be a warning state; if the number of abnormal pixels is not less than the second threshold, the power grid state is determined to be an emergency state; wherein the first threshold is less than the second threshold.

2. The power grid status assessment method according to claim 1, characterized in that: The coordinate information includes: horizontal coordinates and vertical coordinates; The calculating the slope degree and the slope value of the pixel point according to the coordinate information and the pixel value of the pixel point comprises: Calculating the horizontal slope of the pixel point according to the horizontal coordinate and the pixel value of the pixel point; Calculating the vertical slope of the pixel point according to the vertical coordinate and pixel value of the pixel point; Calculate the slope degree and slope value of the pixel point according to the horizontal slope and the vertical slope; The calculation formula of the slope is: Wherein, SL(p) represents the slope of the p-th pixel in the area to be detected; atan represents the inverse tangent function; ‖·‖ represents the norm function; LF() represents the filter function; represents the horizontal slope of the p-th pixel in the area to be detected; represents the vertical slope of the p-th pixel in the area to be detected; The calculation formula of the slope value is: Wherein, VSL(p) represents the slope value of the p-th pixel in the area to be detected.

3. The power grid status assessment method according to claim 2, characterized in that: The filter function is a linear filter function, a mean filter function, a median filter function or a Gaussian filter function.

4. The method for evaluating the state of a power grid according to claim 1, wherein: The calculation formula of the amplified data is: Wherein, AMP(p) represents the amplified data of the p-th pixel in the area to be detected; VSL(p) represents the slope value of the p-th pixel in the area to be detected; SL(p) represents the slope degree of the p-th pixel in the area to be detected; K1 is the preset amplification adjustment coefficient.

5. The method for evaluating the state of a power grid according to claim 1, wherein: The formula for the convolution process is: FEE(p) = conv(AMP(p)NIE); Wherein, FEE(p) represents the convolution result of the p-th pixel in the area to be detected; conv() represents the convolution function; NIE represents the convolution kernel; K2 is the preset convolution kernel adjustment coefficient.

6. The power grid status assessment method according to claim 1, characterized in that: The step of performing binary processing on the convolution result to obtain binary data includes: According to the preset convolution threshold, the convolution result is divided into foreground and background; The foreground is taken as the binarized data.

7. The method for evaluating the state of a power grid according to claim 1, wherein: The calculation formula of the crack annotation map data is: Wherein, LH(p) represents the crack annotation map data of the p-th pixel point in the area to be detected; BFEE(p) represents the binary data of the p-th pixel point in the area to be detected; max() represents taking the maximum value.

8. A power grid status assessment device, characterized in that: include: Data acquisition module, data processing module and status assessment module; The data acquisition module is used to acquire a picture of the power grid equipment; wherein the picture of the power grid equipment has circled the area to be detected where cracks may exist; The data processing module is used to calculate the slope degree and slope value of each pixel point in the area to be detected according to the coordinate information and pixel value of the pixel point; calculate the enlarged data of the pixel point according to the slope degree and slope value; perform convolution processing on the enlarged data to obtain a convolution result; perform binarization processing on the convolution result to obtain binarized data; and calculate the crack annotation map data of the pixel point according to the binarized data; The state evaluation module is used to count the number of abnormal pixels whose grayscale values ​​of the crack annotation map data are less than a preset grayscale reference value based on the crack annotation map data of all pixels in the area to be detected; if the number of abnormal pixels is less than a preset first threshold, the power grid state is determined to be a normal operating state; if the number of abnormal pixels is not less than the first threshold and less than a preset second threshold, the power grid state is determined to be a warning state; if the number of abnormal pixels is not less than the second threshold, the power grid state is determined to be an emergency state; wherein the first threshold is less than the second threshold.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for evaluating the state of a power grid according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the power grid state assessment method according to any one of claims 1 to 7.

Images