A laser cleaning method for insulator contamination, a storage medium and an electronic device

Abstract

The present application relates to the technical field of laser cleaning, in particular to a laser cleaning method for insulator contamination, a storage medium and electronic equipment, which comprises the following steps: capturing an image before laser cleaning, reading a gray scale image, calculating the proportion of the area of the black pixel image in the total area, and drawing a graph for display; using a three-dimensional scanner to scan the cleaning area picture, calculating the thickness of the contamination layer, setting the laser scanning path and the initial laser process parameters; starting the power supply of the laser cleaning device and starting the laser cleaning work; capturing an image after laser cleaning, performing image processing, recording the proportion of the black pixel image in the total area, and checking the cleaning effect. The present application is ingenious in design, realizes non-contact cleaning of laser cleaning of insulator contamination, makes up for the defect that the cleaning effect of post-processing of laser cleaning technology lacks detection, and reduces the cost of external insulation contamination cleaning operation of power transformation equipment.

Description

Technical Field

[0001] This invention relates to the technical field of laser cleaning, and in particular to a laser cleaning method, storage medium, and electronic device for cleaning contaminated insulators. Background Technology

[0002] Insulators are commonly used devices in electrical external insulation. Their working conditions are often harsh, making them prone to large amounts of dirt accumulation. In humid environments, they are highly susceptible to flashover accidents, affecting the safety of the power system. Existing methods for cleaning transmission line insulators include manual cleaning, live-line water cleaning, dry ice cleaning, and chemical cleaning, but all have many shortcomings. Traditional manual cleaning is inefficient, labor-intensive, and requires power outages. Live-line water cleaning requires the preparation of deionized water and carries a significant risk of nearby flashover during the rinsing process. Dry ice cleaning suffers from high dry ice preparation costs and bulky equipment, hindering its widespread application in substations. Chemical cleaning may corrode equipment and pollute the environment due to the use of cleaning agents. Therefore, the power system urgently needs a new insulator cleaning technology that is efficient, safe, reliable, economical, and environmentally friendly.

[0003] Laser cleaning technology is a rapidly developing new cleaning technology in recent years. Compared with traditional cleaning methods, laser cleaning has advantages such as being non-contact, safe, efficient, and environmentally friendly. However, most existing technologies focus on the application of laser cleaning techniques, while methods for detecting the effectiveness of laser cleaning are almost non-existent. Therefore, a method for detecting the effectiveness of laser cleaning on insulators is urgently needed. Summary of the Invention

[0004] This invention addresses the problems of existing technologies by providing a laser cleaning method, storage medium, and electronic device for insulator contamination. It employs a 3D scanner to capture images of the cleaning area, calculates the contamination layer thickness using the image data, generates a grayscale image, and calculates the contamination percentage using an algorithm. After laser cleaning, the contamination percentage of the cleaning area is collected again to obtain the laser cleaning rate. Simultaneously, it determines whether the cleaning standard has been met; if not, the cleaning process is repeated; if it meets the standard, the cleaning is complete. This achieves non-contact laser cleaning of insulator contamination, overcoming the deficiency of lacking post-processing detection in laser cleaning technology, and reducing the cost of cleaning external insulation contamination operations for substation equipment.

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] This invention provides a laser cleaning method for insulator contamination, comprising the following steps:

[0007] Step S001: Capture the image before laser cleaning, read the grayscale image, calculate the proportion of the area of ​​the black pixel image to the total area, and plot the result.

[0008] Step S002: Use a 3D scanner to scan the cleaning area, calculate the thickness of the dirt layer, and set the laser scanning path and initial laser process parameters;

[0009] Step S003: Turn on the power to the laser cleaning device and start the laser cleaning operation;

[0010] Step S004: Capture the image after laser cleaning, perform image processing, record the proportion of black pixel images to the total area, and check the cleaning effect.

[0011] In step S001, the method for reading the grayscale image and calculating the proportion of the area of ​​black pixels to the total area is as follows:

[0012] Input image path;

[0013] The command `img = cv2.imread()` is used to read the image in black and white mode, reading only the grayscale image.

[0014] The image size W*H can be obtained by using the commands height and width, and the area of ​​the image can be obtained from this.

[0015] By using the commands ret and thresh, a threshold of 127 is set. When a pixel in the image is greater than the threshold, the pixel is set to 255; otherwise, it is set to 0, which is equivalent to binarizing the image.

[0016] Calculate the number of pixels in the image that have a value of 0;

[0017] Calculate the proportion of the black area to the total area and plot it.

[0018] In step S002, the specific operation method of the laser scanning path is as follows: determine the cleaning path range in the Cartesian coordinate system based on the area of ​​the measured black pixel image.

[0019] In step S002, the formula for calculating the thickness of the dirt layer is:

[0020]

[0021] In the formula, n x and n y d(x) represents the number of sampling points along the x and y axes of the image, respectively; i y j ) represents (x i y j The center height at the location.

[0022] In step S002, the relevant conditions for the initial laser process parameters are as follows:

[0023]

[0024] In the formula, d th is the depth of thermal stress cleaning, r0 is the radius of the laser spot, 0 < S ≤ 1 is the cumulative coefficient, q is the output energy of the laser, v is the cleaning speed, and R p is the laser absorption rate, taking 0.8; according to the thickness of the contaminated layer, making the depth of thermal stress cleaning equal to the thickness of the contaminated layer, the parameter combination of the laser output energy and the scanning speed is obtained.

[0025] Among them, the method further includes a compensation step for the cleaning effect of the cleaning area: First, divide the image of the cleaning area into sub-areas, and select the sub-areas that only contain dirt. Then, extract the statistical quantities and texture features affected by the degree of laser energy absorption in the selected sub-areas that only contain dirt. Finally, use the non-uniform features as the input of the compensation model to estimate the measurement errors of each sub-area and obtain an accurate cleaning effect.

[0026] Among them, in the step S004, the method for checking the cleaning effect includes:

[0027] After the cleaning is completed, collect an image of the cleaning area;

[0028] Binarize the image, calculate the proportion area S1 of the black pixel point area, and calculate the cleaning rate:

[0029]

[0030] If η < 95%, repeat steps S001 - S003; if η ≥ 95%, complete the cleaning work.

[0031] The present invention also provides a computer storage medium. The computer storage medium stores computer instructions, which are used to execute the laser cleaning method for insulator contamination when the computer instructions are called.

[0032] The present invention also provides an electronic device. Among them, the electronic device includes: a processor; and a memory arranged to store computer-executable instructions, and the computer-executable instructions cause the processor to execute the laser cleaning method for insulator contamination when executed.

[0033] The beneficial effects of the present invention:

[0034] This invention is ingeniously designed. It determines the average thickness of the contaminant layer based on the pixel height acquired from a 3D scan image. By controlling the laser output energy and scanning speed, it achieves a match between the laser cleaning depth and the contaminant layer thickness. Simultaneously, an image processing algorithm-based detection method is used to compare the change in the proportion of contaminants before and after laser cleaning, yielding a specific cleaning rate. Compared to existing methods using the naked eye or cameras, this invention is more precise and eliminates the need for subjective human judgment. This invention also improves the workflow for laser cleaning insulators. Attached Figure Description

[0035] Figure 1 This is a flowchart of a laser cleaning method for insulator contamination according to the present invention.

[0036] Figure 2 This is a schematic diagram of the contaminated area of ​​an insulator sample under a microscope.

[0037] Figure 3 This is a flowchart illustrating the image processing method after the initial cleaning.

[0038] Figure 4 This is a schematic diagram of the soiled area of ​​the sample in Example 1 after it has been cleaned by the cleaning method of the present invention. Detailed Implementation

[0039] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and accompanying drawings. The content mentioned in the embodiments is not intended to limit the present invention. The present invention will be described in detail below with reference to the accompanying drawings.

[0040] Example 1

[0041] Embodiment 1 of this application provides a laser cleaning method for insulator contamination, which includes the following steps:

[0042] Step S001: Capture the image before laser cleaning, read the grayscale image, calculate the proportion of the area of ​​the black pixel image to the total area, and plot the result.

[0043] Step S002: Use a 3D scanner to scan the cleaning area, calculate the thickness of the dirt layer, and set the laser scanning path and initial laser process parameters;

[0044] Step S003: Turn on the power to the laser cleaning device and start the laser cleaning operation;

[0045] Step S004: Capture the image after laser cleaning, perform image processing, record the proportion of black pixel images to the total area, and check the cleaning effect.

[0046] In this embodiment of the application, the method for reading the grayscale image and calculating the proportion of the area of ​​the black pixel image to the total area in step S001 is as follows:

[0047] Input image path;

[0048] The command `img = cv2.imread()` is used to read the image in black and white mode, reading only the grayscale image.

[0049] By using the commands height and width, we can obtain the size W*H of the image and the area of ​​the image (i.e., the total number of pixels).

[0050] Using the commands ret and thresh, the threshold is set to 127. When a pixel in the image is greater than the threshold, the pixel is set to 255; otherwise, it is set to 0. Here, 0 represents black and 255 represents white, which is to binarize the image.

[0051] Calculate the number of pixels with a value of 0 in the image (calculate the area of ​​the black part of the image);

[0052] The proportion of the black image area to the total area was calculated and plotted; among them, the schematic diagram of the contaminated area of ​​the insulator sample under the microscope is shown in Figure 2; the contamination layer is distributed on the entire surface of the insulator in the picture.

[0053] In the first embodiment of this application, the specific operation method of the laser scanning path in step S002 is as follows: determine the cleaning path range in the Cartesian coordinate system based on the area of ​​the measured black pixel image.

[0054] In Embodiment 1 of this application, in step S002, a 3D scanner is used to scan the cleaning area, calculate the thickness of the contaminant layer, and set the laser scanning path and initial laser process parameters. The laser output position in the laser cleaning system is controlled by an electric control panel, and the coordinate system x and y ranges are set on the computer control terminal; x is 0–50 cm, and y is 0–30 cm. The formula for calculating the contaminant layer thickness is:

[0055]

[0056] In the formula, n x and n y d(x) represents the number of sampling points along the x and y axes of the image, respectively; i y j ) represents (x i y j The center height at the location.

[0057] The test samples in this application embodiment had a ash density of 0.8 mg / cm2 and a salt density of 0.1 mg / cm2, with an average thickness of 0.1 mm.

[0058] Among them, in the step S002, the relevant conditions of the initial laser process parameters are as follows:

[0059]

[0060] In the formula, d th is the thermal stress cleaning depth, r0 is the laser spot radius, 0 < S ≤ 1 is the cumulative coefficient, q is the laser output energy, v is the cleaning speed, R p is the laser absorption rate, taking 0.8; according to the thickness of the dirt layer, making the thermal stress cleaning depth equal to the thickness of the dirt layer, the optimal parameter combination of the laser output energy and the scanning speed is obtained.

[0061] The output parameters of the test laser in the embodiment of the present application: the power is 28W, and the scanning speed is 2m / s.

[0062] In the first embodiment of the present application, turn on the power supply of the laser cleaning device to start the laser cleaning work; turn on the power supply of the laser cleaning device, wait for the air cooling system to operate normally, determine the laser cleaning range, adjust the laser output parameters and the equipment scanning speed; after all the preparation work is completed, the computer control terminal confirms to start working.

[0063] In the step S004, capture the image after laser cleaning, perform image processing, record the proportion of the black pixel image in the total area, and the method for checking the cleaning effect includes:

[0064] After the cleaning is completed, collect images of the cleaning area;

[0065] Binarize the image, calculate the proportion area S1 of the black pixel point area, and calculate the cleaning rate:

[0066]

[0067] If η < 95%, repeat steps S001 - S003; if η ≥ 95%, complete the cleaning work.

[0068] After the first cleaning is completed, after image processing, as Figure 3 shown; through algorithm calculation, the laser cleaning rate is 96.87%, as Figure 4 shown. Meeting the cleaning rate requirement means completing the laser cleaning work.

[0069] Embodiment 2

[0070] In Embodiment 2 of this application, the method further includes a step of compensating for the cleaning effect of the cleaning area: first, the image of the cleaning area is divided into sub-regions, and a sub-region containing only dirt is selected. Then, statistical quantities and texture features affected by the degree of laser energy absorption are extracted from the selected sub-region containing only dirt. Finally, non-uniform features are used as input to the compensation model to estimate the measurement error of each sub-region and obtain an accurate cleaning effect.

[0071] Example 3

[0072] In Embodiment 3 of this application, a computer storage medium is provided, which stores computer instructions. When the computer instructions are invoked, they are used to execute a laser cleaning method for insulator contamination.

[0073] Example 4

[0074] In Embodiment 4 of this application, an electronic device is provided, comprising: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform a laser cleaning method for insulator contamination.

[0075] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and modifications made to the above embodiments based on the present invention without departing from the scope of the present invention are within the scope of the present invention.

Claims

1. A laser cleaning method for insulator contamination, characterized in that... This includes the following steps: Step S001: Capture the image before laser cleaning, read the grayscale image, calculate the proportion of the area of ​​the black pixel image to the total area, and plot the result. Step S002: Use a 3D scanner to scan the cleaning area, calculate the thickness of the dirt layer, and set the laser scanning path and initial laser process parameters; Step S003: Turn on the power to the laser cleaning device and start the laser cleaning operation; Step S004: Capture the image after laser cleaning, perform image processing, record the proportion of black pixel images to the total area, and check the cleaning effect; In step S001, the method for reading the grayscale image and calculating the proportion of the area of ​​black pixels to the total area is as follows: Input image path; In black and white mode, only grayscale images are read; Get the image size W*H, and then get the image area; The preset threshold is 127. When a pixel in the image is greater than the threshold, the pixel is set to 255; otherwise, it is set to 0, which is to binarize the image. Calculate the number of pixels in the image that have a value of 0; Calculate the proportion of the black area to the total area and plot it. In step S002, the relevant conditions for the initial laser process parameters are as follows: ； In the formula, d th r0 is the thermal stress cleaning depth, and r0 is the laser spot radius. p The laser absorptivity is set to 0.

8. Based on the thickness of the contaminant layer, the thermal stress cleaning depth is made equal to the thickness of the contaminant layer to obtain the parameter combination of laser output energy and scanning speed.​ The output parameters of the experimental laser are: power of 28W and scanning speed of 2m / s. Turn on the power to the laser cleaning device to start the laser cleaning operation; turn on the power to the laser cleaning device, wait for the air-cooling system to operate normally, determine the laser cleaning range, and adjust the laser output parameters and the equipment scanning speed; after all preparations are completed, confirm the start of the operation on the computer control terminal. In step S004, the method for capturing the image after laser cleaning, performing image processing, recording the proportion of black pixels in the total area, and checking the cleaning effect includes: After cleaning is completed, images of the cleaned area are acquired; Divide the image into two halves, calculate the area S1 of the black pixel region, and then calculate the cleaning rate. ; If η < 95%, repeat steps S001 to S003; if η ≥ 95%, the cleaning process is complete. The method also includes a step to compensate for the cleaning effect of the cleaning area: first, the image of the cleaning area is divided into sub-regions, and the sub-region containing only dirt is selected. Then, the statistical quantity and texture features affected by the degree of laser energy absorption are extracted from the selected sub-region containing only dirt. Finally, the non-uniform features are used as the input of the compensation model to estimate the measurement error of each sub-region and obtain an accurate cleaning effect.

2. The laser cleaning method for insulator contamination according to claim 1, characterized in that: In step S002, the specific operation method of the laser scanning path is as follows: determine the cleaning path range in the Cartesian coordinate system based on the area of ​​the measured black pixel image.

3. The laser cleaning method for insulator contamination according to claim 1, characterized in that: In step S002, the formula for calculating the thickness of the dirt layer is: ； In the formula, n x and n y d(x) represents the number of sampling points along the x and y axes of the image, respectively; i y j ) represents (x i y j The center height at the location.

4. A computer storage medium storing computer instructions, which, when invoked, are used to perform the laser cleaning method for insulator contamination as described in any one of claims 1-3.

5. An electronic device, wherein, The electronic device includes: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the laser cleaning method for insulator contamination as described in any one of claims 1-3.

Images