Control method and system for detecting spraying quality of waterproof paint based on image recognition

Abstract

The invention discloses a control method and system for detecting the spraying quality of waterproof paint based on image recognition, and the method comprises the following operation steps: enabling an intelligent spraying control system to obtain a spraying image of quick-setting rubber asphalt waterproof paint sprayed on a dam body of a pumped storage upper reservoir dam through a high-precision camera installed on spraying equipment; a spraying surface image is obtained; analyzing the spraying surface image to obtain spraying data; the spraying defects of the spraying data are analyzed, and the intelligent spraying control system adjusts spraying parameters according to the spraying defects; and the intelligent spraying control system optimizes the spraying quality according to the adjusted spraying parameters.

Description

Technical Field

[0001] The invention relates to the field of quick-setting rubber asphalt waterproof coatings, and in particular to a method and system for controlling the spraying quality of waterproof coatings based on image recognition detection. Background Art

[0002] The dam of a pumped-storage upper reservoir refers to an artificial reservoir built on a mountain. At present, in the waterproof construction project of the dam of a pumped-storage upper reservoir, a quick-setting rubber asphalt waterproof coating with high viscosity is often used for anti-seepage and waterproofing. Studies have found that this quick-setting rubber asphalt waterproof coating has high viscosity, and its mixed coating contains a quick-setting agent; this quick-setting rubber asphalt waterproof coating often also causes uneven regional coating or some points are missed due to the problem of excessive viscosity, resulting in whitening problems.

[0003] With the development of technology, image recognition technology has been introduced into the field of spraying quality control. The image of the spraying surface is acquired through a high-precision camera, and the nozzle angle, spraying speed, and paint flow rate are detected in real time using an intelligent analysis system, thereby improving the accuracy of spraying quality control.

[0004] However, research has found that although there are many automated spraying systems, they can usually only rely on experience to adjust the control parameters of the spraying operation before or during the spraying process, and cannot correct defects that occur during the spraying process in real time. Summary of the invention

[0005] In order to solve the above problems, this technology proposes a spraying quality control method based on image recognition. This method uses a high-precision camera installed on the spraying equipment to capture the image of the spraying surface, analyze the spraying data to detect the coating thickness and uniformity, and adjust the spraying parameters according to the analysis results. In this way, coating defects can be corrected in real time during the spraying process, the overall quality of the spraying can be improved, and the spraying standards of the quick-setting rubber asphalt waterproof coating can be ensured. This method not only improves the stability of the spraying quality, but also effectively reduces manual intervention and errors.

[0006] The purpose of the present invention is to provide a method and system for controlling the spraying quality of waterproof coatings based on image recognition detection, which solves the above-mentioned technical problems pointed out in the prior art.

[0007] The present invention provides a method for controlling the spray quality of waterproof coatings based on image recognition, comprising the following steps:

[0008] The intelligent spraying control system uses a high-precision camera installed on the spraying equipment to obtain the spraying image of the quick-setting rubber asphalt waterproof coating sprayed on the dam body of the pumped storage reservoir, and obtains the spraying surface image;

[0009] Analyze the spray surface image to obtain spray data; analyze the spray data for spray defects, and the intelligent spray control system adjusts the spray parameters according to the spray defects;

[0010] The intelligent spraying control system optimizes the spraying quality according to the adjusted spraying parameters.

[0011] Preferably, the spraying data includes coating thickness and coating flatness of the spraying surface.

[0012] Preferably, the adjustment of spraying parameters includes nozzle angle, spraying speed, and paint flow rate.

[0013] Preferably, the spraying data is analyzed for spraying defects, and the specific operation steps are as follows:

[0014] Segmenting the spraying surface image into sub-region images; analyzing the spraying data of each sub-region image;

[0015] Extract the color channel of each sub-region image; let the color channel matrix of the sub-region be and let the color value matrix of the sub-region be and Calculate the mean of the color channels of each sub-region image

[0016]

[0017] In the formula, C represents the color channel;

[0018] Calculate the standard deviation of the color channels of each sub-region image

[0019]

[0020] Grayscale each sub-region image, calculate the pixel grayscale value, and set the grayscale value matrix of each sub-region grayscale image as I sub ;

[0021] Calculate the mean gray value of the gray image in the sub-region

[0022]

[0023] Where Ii is the grayscale value of the i-th pixel in the grayscale image of the sub-region, and N is the total number of pixels in the sub-region;

[0024] Calculate the standard deviation σ of the grayscale value of the sub-region grayscale image sub :

[0025]

[0026] Preset standard deviation threshold w to determine the standard deviation of the sub-region image and the standard deviation σ of the sub-region grayscale image sub Determine whether it is less than the preset standard deviation threshold w;

[0027] If not, it is determined that there is a spraying defect of the quick-setting rubber asphalt waterproof coating on the surface of the pumped storage upper reservoir dam in the sprayed surface image;

[0028] If so, it is determined that the surface quick-setting rubber asphalt waterproof coating of the pumped storage reservoir dam body of the sprayed surface image is intact and has no defects.

[0029] Preferably, segmenting the sprayed surface image into sub-region images comprises the steps of: calculating pixel brightness values ​​of the sprayed surface image, and sorting the pixel brightness values ​​in descending order;

[0030] Select the minimum pixel brightness value as the seed point for neighborhood growth, and determine whether the brightness value of the seed point is less than or equal to the brightness value of the neighboring pixel point;

[0031] If so, the seed point grows the pixels in the neighborhood;

[0032] If not, the growth of the seed point is stopped; and finally each sub-region image is obtained by segmentation.

[0033] Preferably, the intelligent spray control system adjusts the spray parameters according to the spray defects, and the specific operation steps are: the intelligent spray control system analyzes the defect type of the spray defects and adjusts the corresponding spray parameters according to the defect type.

[0034] Preferably, the intelligent spray control system analyzes the defect type of the spray defect and adjusts the corresponding spray parameters according to the defect type. The specific operation steps are as follows:

[0035] A spraying range threshold t is preset, and whether the spraying range of the quick-setting rubber asphalt waterproof coating with the spraying defect is greater than the spraying range threshold t;

[0036] If yes, the spraying range of the quick-setting rubber asphalt waterproof coating with spraying defects is determined to be a coating thickness defect;

[0037] If not, the spraying range of the quick-setting rubber asphalt waterproof coating with spraying defects is determined to be a coating flatness defect;

[0038] adjusting the coating flow rate in the spraying parameters according to the coating thickness defect;

[0039] The nozzle angle and the spraying speed in the spraying parameters are adjusted according to the flatness defect of the coating.

[0040] Accordingly, the present invention also proposes a waterproof coating spraying quality control system based on image recognition detection, comprising: an acquisition module; an analysis module; a feedback module;

[0041] The acquisition module is used for the intelligent spraying control system to acquire the spraying image of the quick-setting rubber asphalt waterproof coating sprayed on the dam body of the pumped storage reservoir through the high-precision camera installed on the spraying equipment, and obtain the spraying surface image;

[0042] The analysis module is used to analyze the spray surface image to obtain spray data; analyze the spray data for spray defects, and the intelligent spray control system adjusts the spray parameters according to the spray defects;

[0043] The feedback module is used for the intelligent spraying control system to optimize the spraying quality according to the adjusted spraying parameters.

[0044] Compared with the prior art, the embodiments of the present invention have at least the following technical advantages:

[0045] It can be seen from the analysis of the above-mentioned waterproof coating spraying quality control method based on image recognition detection provided by the present invention that in specific applications, by acquiring the spraying surface image and analyzing the spraying surface image to obtain the spraying data, the coating thickness and coating flatness of the dam body surface of the pumped storage reservoir dam after the quick-setting rubber asphalt waterproof coating is sprayed can be understood according to the spraying data;

[0046] Furthermore, the coating thickness and coating flatness of the spraying data are further analyzed to determine whether the quick-setting rubber asphalt waterproof coating meets the spraying standard during the spraying process, so that the quick-setting rubber asphalt waterproof coating is uneven and the surface thickness is different, thereby causing the quick-setting rubber asphalt waterproof coating on the surface of the pumped storage upper reservoir dam to be not sprayed in place and the surface is uneven; by segmenting the spraying surface image into sub-region images, the calculation speed is increased and the time for analyzing the spraying data is reduced;

[0047] Furthermore, the standard deviation of the color value of the color channel of the sub-region image is calculated, and the different color distributions of each channel can be used to identify whether the distribution of the quick-setting rubber asphalt waterproof coating is flat or whether the spraying thickness is the same; at the same time, the sub-region image is grayed, the standard deviation of the gray value is calculated, and the gray value change of the pixel point is judged by the single-channel standard deviation of the grayscale, so as to judge the flatness or thickness of the spraying of the quick-setting rubber asphalt waterproof coating; the standard deviation of the color channel and the standard deviation of the grayscale are used to double judge whether there are defects in the spraying flatness and spraying thickness of the sprayed surface image, so as to make the detection result more accurate;

[0048] Furthermore, the detected defect results are judged by the spraying range threshold according to the spraying range of the quick-setting rubber asphalt waterproof coating; when the spraying distribution area of ​​the quick-setting rubber asphalt waterproof coating is large, the density will decrease, and the quick-setting rubber asphalt waterproof coating will be dispersed, thereby causing the uneven defect of the quick-setting rubber asphalt waterproof coating; and if the spraying distribution area of ​​the quick-setting rubber asphalt waterproof coating is small, the density will increase, and the quick-setting rubber asphalt waterproof coating will be more concentrated, thereby causing the problem of excessive or insufficient thickness; the defect type is distinguished by judging the spraying range threshold, so that the nozzle angle parameter and the spraying speed parameter, as well as the coating flow parameter, can be better adjusted according to the existing defects;

[0049] Furthermore, the intelligent spraying control system optimizes the spraying quality based on the adjusted spraying parameters, and has achieved the standard spraying effect of quick-setting rubber asphalt waterproof coating. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 An overall flow chart of a method for controlling the spray quality of waterproof coatings based on image recognition detection provided in the first embodiment of the present invention;

[0052] Figure 2 A flow chart of analyzing spraying defects of a method for controlling spraying quality of waterproof coatings based on image recognition provided in the first embodiment of the present invention;

[0053] Figure 3 A flow chart of adjusting spraying parameters of a method for controlling the spraying quality of waterproof coatings based on image recognition detection provided in the first embodiment of the present invention;

[0054] Figure 4 A flowchart of a waterproof coating spraying quality control system based on image recognition detection provided in the second embodiment of the present invention;

[0055] Label: acquisition module 10; analysis module 20; feedback module 30. DETAILED DESCRIPTION

[0056] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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.

[0057] The present invention is further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0058] Embodiment 1

[0059] like Figure 1 As shown, the present invention proposes a method for controlling the spray quality of waterproof coatings based on image recognition, which includes the following steps:

[0060] S10: The intelligent spraying control system acquires the spraying image of the quick-setting rubber asphalt waterproof coating sprayed on the dam body of the pumped storage reservoir through the high-precision camera installed on the spraying equipment, and obtains the spraying surface image;

[0061] It should be noted that installing a high-precision camera on the spraying equipment can take pictures of the quick-setting rubber asphalt waterproof coating sprayed by the spraying equipment, and obtain the spray surface image of the quick-setting rubber asphalt waterproof coating of the dam body of the pumped storage upper reservoir;

[0062] S20: Analyze the spray surface image to obtain spray data; analyze the spray data for spray defects, and the intelligent spray control system adjusts spray parameters according to the spray defects;

[0063] The spraying data includes the coating thickness and coating flatness of the spraying surface;

[0064] The spraying parameters to be adjusted include nozzle angle, spraying speed, and paint flow rate;

[0065] It should be noted that the obtained spray surface image is analyzed to determine the coating thickness and coating flatness formed after the quick-setting rubber asphalt waterproof coating is sprayed on the dam body of the upper pumped storage reservoir dam; the coating thickness and coating flatness are analyzed to determine whether the quick-setting rubber asphalt waterproof coating sprayed by the spraying equipment meets the spraying standard during the spraying process (i.e., spraying defects, which include problems such as inadequate spraying and uneven surface (i.e., when the quick-setting rubber asphalt waterproof coating is uneven, the thickness of the sprayed surface will be uneven, resulting in inadequate spraying of the quick-setting rubber asphalt waterproof coating on the surface of the upper pumped storage reservoir dam and uneven surface spraying)), and the spraying parameters are adjusted according to the spraying defects, such as correcting the coating thickness, improving uniformity and expanding coverage, so as to improve the standard quality of the spraying by changing these parameters;

[0066] S30: The intelligent spraying control system optimizes the spraying quality according to the adjusted spraying parameters.

[0067] It should be noted that the intelligent spray control system will readjust the nozzle angle, spray speed, and paint flow rate according to the adjusted spray parameters to correct the coating thickness, improve uniformity, and re-spray to meet the spraying quality standards of quick-setting rubber asphalt waterproof coatings.

[0068] Specifically, Figure 2 As shown, in step S20, the spray surface image is analyzed to obtain spray data; the spray data is analyzed for spray defects, and the intelligent spray control system adjusts the spray parameters according to the spray defects. The specific operation steps are as follows:

[0069] S21: Segment the sprayed surface image into sub-region images; analyze spraying data (i.e., coating thickness, coating flatness) for each sub-region image;

[0070] It should be noted that, specifically, the sub-region image segmentation of the sprayed surface image includes the following steps: calculating the brightness values ​​of the pixels of the sprayed surface image, and sorting the brightness values ​​of the pixels in descending order; selecting the minimum pixel brightness value as the seed point for neighborhood growth, and judging whether the brightness value of the seed point is less than or equal to the brightness value of the neighboring pixel points; if so, the seed point grows the pixel points of the neighborhood; if not, the seed point stops growing; and finally segmenting to obtain each sub-region image;

[0071] By segmenting the spraying surface image into sub-region images, the subsequent analysis of spraying defects in small regions (i.e., sub-region images) can be maximized, avoiding direct large-scale analysis of spraying defects on the spraying surface image, thus avoiding excessive detection time and the possibility of low accuracy; (region growing)

[0072] S22: Extract color channels (i.e., red channel, green channel, blue channel) from each sub-region image; let the color channel matrix of the sub-region be and Calculate the mean of the color channels of each sub-region image (That is, in the RGB model, the mean CR of the red channel represents the average intensity of all red components in the sub-region image; the mean CG of the green channel and the mean CB of the blue channel represent the average intensity of the green and blue components respectively, so using Calculate the mean of the color channels of each sub-region image):

[0073]

[0074] In the formula, C represents the color channel;

[0075] Calculate the standard deviation of the color channels of each sub-region image

[0076]

[0077] It should be noted that when the sub-region image is a color image, it contains multiple color channels (such as red, green, and blue), and each channel may have different uniformity characteristics. Because the color distribution of each channel may be inconsistent, calculating the standard deviation of the color channel helps to identify the problem of color unevenness, so that it can be judged whether the distribution of the quick-setting rubber asphalt waterproof coating is uneven and whether the spraying thickness is the same;

[0078] S23: grayscale each sub-region image, calculate the grayscale value of the pixel, and set the grayscale value matrix of each sub-region grayscale image as I sub ;

[0079] Calculate the mean gray value of the gray image in the sub-region

[0080]

[0081] Where Ii is the grayscale value of the i-th pixel in the grayscale image of the sub-region, and N is the total number of pixels in the sub-region;

[0082] Calculate the standard deviation σ of the grayscale value of the sub-region grayscale image sub :

[0083]

[0084] It should be noted that in the above formula, the standard deviation of the grayscale value of the sub-region grayscale image can be used to evaluate the uniformity of the coating. The sub-region grayscale image has only one channel, and the grayscale value standard deviation can reflect the change of the grayscale value of the pixel in the sub-region grayscale image. According to the change of the grayscale value, it is judged whether the quick-setting rubber asphalt waterproof coating is uniform after spraying. If the distribution is uniform, it means that the grayscale values ​​of the pixels in the sub-region grayscale image are similar (that is, the grayscale values ​​are uniform and similar), and the distribution quality is good, which reflects the flatness and thickness of the quick-setting rubber asphalt waterproof coating on the surface of the pumped storage reservoir dam;

[0085] S24: Preset the standard deviation threshold w to determine the standard deviation of the sub-region image and the standard deviation σ of the sub-region grayscale image sub Determine whether it is less than the preset standard deviation threshold w;

[0086] If not, it is determined that there is a spraying defect of the quick-setting rubber asphalt waterproof coating on the surface of the pumped storage upper reservoir dam in the sprayed surface image;

[0087] If so, it is determined that the surface quick-setting rubber asphalt waterproof coating of the pumped storage upper reservoir dam body of the sprayed surface image is intact and has no defects;

[0088] It should be noted that the standard deviation of the sub-region image (i.e. the sub-region image is a color image) and the standard deviation σ of the sub-region grayscale image sub (i.e. the grayscale image of the sub-region is a grayscale image) represents the distribution of grayscale values ​​and color values ​​within the sub-region; the smaller the standard deviation of the two, the more uniform the coating of the sub-region, and the smaller the fluctuation of the color value or grayscale value; the larger the standard deviation of the two, the poorer the uniformity of the coating (i.e. the quick-setting rubber asphalt waterproof coating is not sprayed evenly), and the color value or grayscale value fluctuates greatly; and through the standard deviation of the sub-region image and the standard deviation σ of the sub-region grayscale image sub The double judgment can make the spray surface image detection more accurate;

[0089] When the quick-setting rubber asphalt waterproof coating is sprayed unevenly on the dam body of the upper reservoir of the pumped storage energy source (i.e., the spraying is uneven), it means that the quick-setting rubber asphalt waterproof coating may also cause the spraying thickness to not meet the standard; because the quick-setting rubber asphalt waterproof coating is uneven, it means that the spraying thickness of the quick-setting rubber asphalt waterproof coating is too large or too small (i.e., the spraying thickness of the quick-setting rubber asphalt waterproof coating is uneven), so when the quick-setting rubber asphalt waterproof coating is uneven, the spraying thickness of the quick-setting rubber asphalt waterproof coating may also be uneven (i.e., conversely, when the spraying thickness of the quick-setting rubber asphalt waterproof coating is uneven, the quick-setting rubber asphalt waterproof coating may be uneven); when the quick-setting rubber asphalt waterproof coating has uneven coating and different spraying thickness, the quick-setting rubber asphalt waterproof coating on the surface of the dam body of the upper reservoir of the pumped storage energy source is sprayed unevenly and not sprayed in place;

[0090] Therefore, the standard deviation of the sub-region image in the above and the standard deviation σ of the sub-region grayscale image sub It can detect the spraying defects on the sprayed surface image, whether it is a coating thickness defect or a coating flatness defect;

[0091] S25: The intelligent spraying control system analyzes the defect type of the spraying defect and adjusts the corresponding spraying parameters according to the defect type;

[0092] It should be noted that the intelligent spray control system will analyze the defect type according to the spray defect, specifically whether the quick-setting rubber asphalt waterproof coating is uneven or the thickness is different; adjust different spray parameters according to different defect problems; for example: if the quick-setting rubber asphalt waterproof coating is uneven, it may be necessary to adjust the nozzle angle and spray speed to improve the uneven problem; and the spray thickness requires adjusting the coating flow rate. If the coating is too thin or insufficiently covered, increase the flow rate; if the coating is too thick or sagging occurs, reduce the flow rate; according to different defect problems, the spray equipment will be used to improve the spray quality of the quick-setting rubber asphalt waterproof coating to meet the spraying requirements;

[0093] Specifically, Figure 3 As shown, in step S25, the intelligent spraying control system analyzes the defect type of the spraying defect and adjusts the corresponding spraying parameters according to the defect type. The specific operation steps are as follows:

[0094] S251: Preset a spraying range threshold t, and analyze whether the spraying range of the quick-setting rubber asphalt waterproof coating with the spraying defect is greater than the spraying range threshold t;

[0095] If yes, the spraying range of the quick-setting rubber asphalt waterproof coating with spraying defects is determined to be a coating thickness defect;

[0096] If not, the spraying range of the quick-setting rubber asphalt waterproof coating with spraying defects is determined to be a coating flatness defect;

[0097] It should be noted that, by presetting the spray range threshold t, the distribution of the quick-setting rubber asphalt waterproof coating with spray defects during the spraying process can be understood, such as: the spraying density and the spraying coverage area;

[0098] When the spray distribution is greater than the spray range threshold t, it means that the distribution area of ​​the quick-setting rubber asphalt waterproof coating is small (i.e., the coverage area is small), which results in a high density of the quick-setting rubber asphalt waterproof coating and uneven coating thickness (i.e., the coverage area of ​​the quick-setting rubber asphalt waterproof coating becomes smaller, and the quick-setting rubber asphalt waterproof coating on the dam body of the pumped storage reservoir will be too concentrated, resulting in a problem of too large or too small thickness);

[0099] When the spray distribution is less than or equal to the spray range threshold t, it means that the distribution area of ​​the quick-setting rubber asphalt waterproof coating is large (i.e., the coverage area is large), the density of the quick-setting rubber asphalt waterproof coating is small, and the coating is uneven (i.e., the coverage area of ​​the quick-setting rubber asphalt waterproof coating becomes larger, and the quick-setting rubber asphalt waterproof coating on the dam body of the pumped storage reservoir will be spread out, and unevenness may occur);

[0100] S252: adjusting the coating flow rate in the spraying parameters according to the coating thickness defect;

[0101] It should be noted that the coating flow directly affects the amount of coating deposited during the spraying process. The greater the coating flow, the more coating is sprayed at each moment, and the coating thickness will also increase. On the contrary, a smaller flow will reduce the coating thickness. Therefore, by adjusting the coating flow in the spraying parameters to change the coating thickness defect, the best spraying effect has been achieved.

[0102] S253: adjusting the nozzle angle and the spraying speed in the spraying parameters according to the coating flatness defect;

[0103] It should be noted that the nozzle angle affects the coverage and distribution of the paint. If the nozzle angle is inappropriate, it may cause uneven distribution of the paint, resulting in uncovered areas on the coating surface. Adjusting the nozzle angle can change the spray direction and range of the paint, thereby improving the uniform distribution of the paint on the surface of the pumped storage reservoir dam.

[0104] At the same time, the spraying speed determines the deposition speed of the paint on the surface. Spraying too fast may cause the paint to not have enough time to be evenly distributed on the surface, resulting in uneven coating. Adjusting the spraying speed can give the paint more time to evenly cover the surface of the pumped storage upper reservoir dam, thereby improving the uniformity of the coating. For example, slowing down the spraying speed can make the paint flow more evenly on the surface, avoiding the phenomenon of thin or too thick coating.

[0105] Embodiment 2

[0106] like Figure 2 As shown, accordingly, the present invention also proposes a waterproof coating spraying quality control system based on image recognition detection, comprising: an acquisition module 10; an analysis module 20; a feedback module 30;

[0107] The acquisition module 10 is used for the intelligent spraying control system to acquire the spraying image of the quick-setting rubber asphalt waterproof coating sprayed on the dam body of the pumped storage reservoir through the high-precision camera installed on the spraying equipment, so as to obtain the spraying surface image;

[0108] The analysis module 20 is used to analyze the spray surface image to obtain spray data; analyze the spray data for spray defects, and the intelligent spray control system adjusts the spray parameters according to the spray defects;

[0109] The feedback module 30 is used by the intelligent spraying control system to optimize the spraying quality according to the adjusted spraying parameters.

[0110] In summary, the present invention proposes a method for controlling the spraying quality of waterproof coatings based on image recognition detection, which obtains spraying surface images and analyzes the spraying surface images to obtain spraying data. According to the spraying data, the coating thickness and coating flatness of the surface of the dam body of the pumped storage reservoir after the quick-setting rubber asphalt waterproof coating is sprayed can be understood;

[0111] Furthermore, the coating thickness and coating flatness of the spraying data are further analyzed to determine whether the quick-setting rubber asphalt waterproof coating meets the spraying standard during the spraying process, so that the quick-setting rubber asphalt waterproof coating is uneven and the surface thickness is different, thereby causing the quick-setting rubber asphalt waterproof coating on the surface of the pumped storage upper reservoir dam to be not sprayed in place and the surface is uneven; by segmenting the spraying surface image into sub-region images, the calculation speed is increased and the time for analyzing the spraying data is reduced;

[0112] Furthermore, the standard deviation of the color value of the color channel of the sub-region image is calculated, and the different color distributions of each channel can be used to identify whether the distribution of the quick-setting rubber asphalt waterproof coating is flat or whether the spraying thickness is the same; at the same time, the sub-region image is grayed, the standard deviation of the gray value is calculated, and the gray value change of the pixel point is judged by the single-channel standard deviation of the grayscale, so as to judge the flatness or thickness of the spraying of the quick-setting rubber asphalt waterproof coating; the standard deviation of the color channel and the standard deviation of the grayscale are used to double judge whether there are defects in the spraying flatness and spraying thickness of the sprayed surface image, so as to make the detection result more accurate;

[0113] Furthermore, the detected defect results are judged by the spraying range threshold according to the spraying range of the quick-setting rubber asphalt waterproof coating; when the spraying distribution area of ​​the quick-setting rubber asphalt waterproof coating is large, the density will decrease, and the quick-setting rubber asphalt waterproof coating will be dispersed, thereby causing the uneven defect of the quick-setting rubber asphalt waterproof coating; and if the spraying distribution area of ​​the quick-setting rubber asphalt waterproof coating is small, the density will increase, and the quick-setting rubber asphalt waterproof coating will be more concentrated, thereby causing the problem of excessive or insufficient thickness; the defect type is distinguished by judging the spraying range threshold, so that the nozzle angle parameter and the spraying speed parameter, as well as the coating flow parameter, can be better adjusted according to the existing defects;

[0114] Furthermore, the intelligent spraying control system optimizes the spraying quality based on the adjusted spraying parameters, and has achieved the standard spraying effect of quick-setting rubber asphalt waterproof coating.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. A person skilled in the art may modify the technical solutions described in the above embodiments, or replace part or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling the spraying quality of waterproof coatings based on image recognition, characterized in that: The steps are as follows: The intelligent spraying control system uses a high-precision camera installed on the spraying equipment to obtain the spraying image of the quick-setting rubber asphalt waterproof coating sprayed on the dam body of the pumped storage reservoir, and obtains the spraying surface image; Analyze the spray surface image to obtain spray data; analyze the spray data for spray defects, and the intelligent spray control system adjusts the spray parameters according to the spray defects; The intelligent spraying control system optimizes the spraying quality according to the adjusted spraying parameters.

2. According to claim 1, a method for controlling the quality of waterproof coating spraying based on image recognition detection is characterized in that: The spraying data includes the coating thickness and coating flatness of the spraying surface.

3. According to claim 2, a method for controlling the spray quality of waterproof coatings based on image recognition detection is characterized in that: The adjustment of spraying parameters includes nozzle angle, spraying speed, and paint flow rate.

4. According to claim 3, a method for controlling the quality of spraying waterproof coatings based on image recognition detection is characterized in that: The spraying data is analyzed for spraying defects, and the specific operation steps are as follows: Segmenting the spraying surface image into sub-region images; analyzing the spraying data of each sub-region image; Extract the color channel of each sub-region image; let the color channel matrix of the sub-region be and let the color value matrix of the sub-region be and Calculate the mean of the color channels of each sub-region image In the formula, C represents the color channel; Calculate the standard deviation of the color channels of each sub-region image Grayscale each sub-region image, calculate the pixel grayscale value, and set the grayscale value matrix of each sub-region grayscale image as I sub ; Calculate the mean gray value of the gray image in the sub-region Where Ii is the grayscale value of the i-th pixel in the grayscale image of the sub-region, and N is the total number of pixels in the sub-region; Calculate the standard deviation σ of the grayscale value of the sub-region grayscale image sub : Preset standard deviation threshold w to determine the standard deviation of the sub-region image and the standard deviation σ of the sub-region grayscale image sub Determine whether it is less than the preset standard deviation threshold w; If not, it is determined that there is a spraying defect of the quick-setting rubber asphalt waterproof coating on the surface of the pumped storage upper reservoir dam in the sprayed surface image; If so, it is determined that the surface quick-setting rubber asphalt waterproof coating of the pumped storage reservoir dam body of the sprayed surface image is intact and has no defects.

5. According to claim 4, a method for controlling the quality of spraying waterproof coatings based on image recognition detection is characterized in that: The spray-painted surface image is segmented into sub-region images, comprising the steps of: calculating pixel brightness values ​​of the spray-painted surface image, and sorting the pixel brightness values ​​in descending order; Select the minimum pixel brightness value as the seed point for neighborhood growth, and determine whether the brightness value of the seed point is less than or equal to the brightness value of the neighboring pixel point; If so, the seed point grows the pixels in the neighborhood; If not, the growth of the seed point is stopped; and finally each sub-region image is obtained by segmentation.

6. According to claim 5, a method for controlling the spray quality of waterproof coating based on image recognition detection is characterized in that: The intelligent spray control system adjusts the spray parameters according to the spray defects. The specific operation steps are: the intelligent spray control system analyzes the defect type of the spray defects and adjusts the corresponding spray parameters according to the defect type.

7. According to claim 6, a method for controlling the quality of spraying waterproof coatings based on image recognition detection is characterized in that: The intelligent spray control system analyzes the defect type of the spray defect and adjusts the corresponding spray parameters according to the defect type. The specific operation steps are as follows: A spraying range threshold t is preset, and whether the spraying range of the quick-setting rubber asphalt waterproof coating with the spraying defect is greater than the spraying range threshold t; If yes, the spraying range of the quick-setting rubber asphalt waterproof coating with spraying defects is determined to be a coating thickness defect; If not, the spraying range of the quick-setting rubber asphalt waterproof coating with spraying defects is determined to be a coating flatness defect; adjusting the coating flow rate in the spraying parameters according to the coating thickness defect; The nozzle angle and the spraying speed in the spraying parameters are adjusted according to the flatness defect of the coating.

8. A waterproof coating spraying quality control system based on image recognition detection, characterized in that: include: Get module; Analysis module; Feedback module; The acquisition module is used for the intelligent spraying control system to acquire the spraying image of the quick-setting rubber asphalt waterproof coating sprayed on the dam body of the pumped storage reservoir through the high-precision camera installed on the spraying equipment, and obtain the spraying surface image; The analysis module is used to analyze the spray surface image to obtain spray data; analyze the spray data for spray defects, and the intelligent spray control system adjusts the spray parameters according to the spray defects; The feedback module is used for the intelligent spraying control system to optimize the spraying quality according to the adjusted spraying parameters.

Images