Preparation process of special sealing primer for construction surface with water

Abstract

The invention discloses a process for preparing a special sealing primer for a construction surface with water, which comprises the following steps of: acquiring a product surface image of the special sealing primer for the construction surface with water through a camera, and carrying out grid division and HOG (Histogram of Oriented Gradient) feature extraction on the product surface image by adopting an image recognition and analysis technology based on computer vision; therefore, whether product particles are uneven or not is automatically judged according to the HOG features of the surface grid images of the products and semantic difference distribution features between the features obtained after clustering of the HOG features of the surface grid images of the products. Therefore, the surface image of the product is automatically acquired through the camera, and the surface image of the product is analyzed by using a computer vision technology, so that the quality inspection speed can be greatly improved, and the time required by manual inspection is reduced. And meanwhile, the distribution condition of particles on the surface of the product can be identified and analyzed more accurately, so that errors caused by subjective judgment are reduced, and the intelligent level of sealing primer quality inspection is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent preparation, and more specifically, to a preparation process of a special sealing primer for water-bearing construction surfaces. Background Art

[0002] In the construction and decoration industry, sealant is an important coating, which is widely used in surface treatment of walls, floors, etc. to improve the adhesion and moisture resistance of the coating surface. Especially in humid or high humidity environments, sealant can effectively prevent moisture penetration, protect buildings from damage, and improve the durability and aesthetics of the entire coating system.

[0003] However, traditional sealers often fail to perform optimally in wet conditions. When the construction surface contains moisture or is in a high humidity environment, these sealers may suffer from poor adhesion, blistering, and shedding. These problems not only affect the coating effect, but may also cause the coating to fail prematurely, increasing maintenance costs. In addition, slow drying speed will extend the construction period and increase costs, and insufficient adhesion may cause the coating to fall off, affecting the final construction quality.

[0004] Therefore, a preparation process of a special sealing primer for water-bearing construction surfaces is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a preparation process of a special sealing primer for water-bearing construction surfaces, which collects the product surface image of the special sealing primer for water-bearing construction surfaces through a camera, and uses computer vision-based image recognition and analysis technology to perform grid division and HOG feature extraction of the product surface image, so as to automatically judge whether the product particles are uneven according to the HOG features of each product surface grid image and the semantic difference distribution features after clustering the HOG features of each product surface grid image. In this way, by automatically collecting product surface images through a camera and analyzing product surface images using computer vision technology, the speed of quality inspection can be greatly improved and the time required for manual inspection can be reduced. At the same time, the distribution of particles on the product surface can be more accurately identified and analyzed, thereby reducing the errors caused by subjective judgment and improving the intelligent level of quality inspection of the sealing primer.

[0006] According to one aspect of the present application, a preparation process of a special sealing primer for a water-bearing construction surface is provided, which comprises:

[0007] Heat the epoxy resin to 50℃-60℃;

[0008] Adding a plasticizer to the heated epoxy resin and stirring the mixture to obtain a first mixed material;

[0009] Adding a filler during stirring of the first mixed material to obtain a second mixed material, wherein the filler is talcum powder;

[0010] Adding an auxiliary agent during stirring the second mixed material to obtain a third mixed material, wherein the auxiliary agent is any one or a combination of a defoaming agent, a leveling agent and a lubricant;

[0011] adding a solvent to the third mixed material to obtain a fourth mixed material, wherein the solvent is ethanol or acetone;

[0012] Adding a curing agent to the fourth mixed material and stirring evenly to obtain a special sealing primer for water-bearing construction surfaces;

[0013] The special sealing primer for water-bearing construction surface is subjected to quality inspection to obtain the quality inspection result.

[0014] Compared with the prior art, the present application provides a preparation process for a special sealing primer for water-bearing construction surfaces, which uses a camera to collect the product surface image of the special sealing primer for water-bearing construction surfaces, and uses computer vision-based image recognition and analysis technology to perform grid division and HOG feature extraction of the product surface image, so as to automatically judge whether the product particles are uneven based on the HOG features of each product surface grid image and the semantic difference distribution features after clustering the HOG features of each product surface grid image. In this way, by automatically collecting product surface images through cameras and analyzing product surface images using computer vision technology, the speed of quality inspection can be greatly improved and the time required for manual inspection can be reduced. At the same time, the distribution of particles on the product surface can be more accurately identified and analyzed, thereby reducing the errors caused by subjective judgment and improving the intelligent level of quality inspection of sealed bottom glue. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 This is a flow chart of a preparation process of a special sealing primer for water-bearing construction surfaces according to an embodiment of the present application;

[0017] Figure 2 It is a data flow diagram of a preparation process of a special sealing primer for water-bearing construction surfaces according to an embodiment of the present application;

[0018] Figure 3This is a flow chart of sub-step S7 of the process for preparing a sealing primer specifically for water-bearing construction surfaces according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0020] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] Traditional sealers often fail to perform optimally under wet conditions. When the construction surface contains moisture or is in a high humidity environment, these sealers may experience problems such as poor adhesion, bubbling, and shedding. These problems not only affect the coating effect, but may also cause the coating to fail prematurely, increasing maintenance costs. In addition, slow drying speed will extend the construction cycle and increase costs, and insufficient adhesion may cause the coating to fall off, affecting the final construction quality. Therefore, a process for preparing a sealer specifically for construction surfaces with water is desired.

[0025] In the technical solution of the present application, a preparation process of a special sealing primer for water-bearing construction surfaces is proposed. Figure 1This is a flow chart of a process for preparing a sealing primer specifically for water-bearing construction surfaces according to an embodiment of the present application. Figure 2 This is a data flow diagram of the preparation process of a special sealing primer for water-bearing construction surfaces according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the embodiment of the present application, the preparation process of the special sealing primer for water-bearing construction surface includes the following steps: S1, heating the epoxy resin to 50°C-60°C; S2, adding a plasticizer to the heated epoxy resin and stirring evenly to obtain a first mixed material; S3, adding a filler during stirring of the first mixed material to obtain a second mixed material, wherein the filler is talcum powder; S4, adding an auxiliary agent during stirring of the second mixed material to obtain a third mixed material, wherein the auxiliary agent is any one or a combination of several of a defoaming agent, a leveling agent and a lubricant; S5, adding a solvent to the third mixed material to obtain a fourth mixed material, wherein the solvent is ethanol or acetone; S6, adding a curing agent to the fourth mixed material and stirring evenly to obtain a special sealing primer for water-bearing construction surface; S7, conducting quality inspection on the special sealing primer for water-bearing construction surface to obtain a quality inspection result.

[0026] In particular, in the S1 and S2, the epoxy resin is heated to 50°C-60°C; and a plasticizer is added to the heated epoxy resin and stirred to obtain a first mixed material. It should be understood that heating the epoxy resin can reduce its viscosity, making it easier to mix with the plasticizer. The plasticizer is usually a low molecular weight liquid that can reduce the overall viscosity of the epoxy resin, making it easier to flow and apply. In addition, the plasticizer can improve the wettability of the epoxy resin, allowing it to better adhere to the surface of the substrate. This can enhance the adhesion of the coating and reduce the formation of bubbles and voids.

[0027] In particular, S3, a filler is added during stirring of the first mixed material to obtain a second mixed material, wherein the filler is talcum powder. Wherein, talcum powder is an inert, low-density mineral that can increase the volume and weight of the closed primer without significantly changing its other properties. This is useful in applications where the amount or weight of the primer needs to be increased, such as in construction and industrial coatings. It is worth mentioning that talcum powder can be combined with other ingredients in the primer to enhance the adhesion of the primer to the substrate. This is very important for ensuring that the primer can adhere firmly to various surfaces.

[0028] In particular, in S4, an auxiliary agent is added during stirring of the second mixed material to obtain a third mixed material, wherein the auxiliary agent is any one or a combination of a defoamer, a leveling agent and a lubricant. The defoamer can remove bubbles, and the leveling agent can improve the surface finish, and together they can obtain a mixture without bubbles and with a smooth surface, while the lubricant can reduce friction, and the leveling agent can improve the surface finish, and together they can obtain a mixture with a smooth surface that is easy to brush or shape and easy to flow and shape.

[0029] In particular, in S5, a solvent is added to the third mixed material to obtain a fourth mixed material, wherein the solvent is ethanol or acetone. It should be understood that both ethanol and acetone are volatile organic solvents that can reduce the viscosity of the mixture, making it easier to flow and apply. In addition, both ethanol and acetone are volatile solvents that can evaporate quickly, thereby accelerating the drying process of the mixture.

[0030] In particular, in S6, a curing agent is added to the fourth mixed material and stirred evenly to obtain a special sealing primer for water-bearing construction surfaces. The curing agent is a chemical substance that can react with the resin in the primer to solidify it into a hard protective layer.

[0031] In particular, the S7 is to conduct a quality inspection on the special sealing primer for water-carrying construction surface to obtain a quality inspection result. However, in the process of conducting a quality inspection on the special sealing primer for water-carrying construction surface to obtain a quality inspection result, the traditional quality inspection of the sealing primer often relies on the experience and subjective judgment of the quality inspectors, which may lead to inconsistency of the results, and it is difficult to observe some minor defects, and it may also increase the risk of missed detection or misjudgment. In addition, it takes a long time to manually check the surface quality of each sample, especially in the case of large-scale production, manual quality inspection is difficult to keep up with the production rhythm, thereby affecting production efficiency. Based on this, in the above-mentioned quality inspection of the special sealing primer for water-carrying construction surface to obtain a quality inspection result, the technical concept of the present application is to collect the product surface image of the special sealing primer for water-carrying construction surface through a camera, and use image recognition and analysis technology based on computer vision to perform grid division and HOG feature extraction of the product surface image, so as to automatically judge whether the product particles are uneven according to the semantic difference distribution characteristics between the HOG features of each product surface grid image and the features after clustering the HOG features of each product surface grid image. In this way, by automatically collecting product surface images through cameras and analyzing product surface images using computer vision technology, the speed of quality inspection can be greatly improved and the time required for manual inspection can be reduced. At the same time, the distribution of particles on the product surface can be more accurately identified and analyzed, thereby reducing the errors caused by subjective judgment and improving the intelligent level of sealed bottom glue quality inspection. In particular, in a specific example of the present application, Figure 3As shown, the S7 includes: S71, acquiring the product surface image of the special sealing primer for water-bearing construction surface collected by a camera; S72, meshing the product surface image of the special sealing primer for water-bearing construction surface and extracting HOG features to obtain a set of HOG feature vectors of product surface mesh granularity; S73, clustering analysis on the set of HOG feature vectors of product surface mesh granularity to obtain a cluster center vector of product surface mesh granularity texture features; S74, calculating the texture semantic difference coefficient between each product surface mesh granularity HOG feature vector in the set of HOG feature vectors of product surface mesh granularity and the cluster center vector of product surface mesh granularity texture features to obtain a texture semantic difference distribution topology matrix composed of multiple texture semantic difference coefficients; S75, based on the texture semantic difference distribution topology matrix, obtaining a quality inspection result, and the quality inspection result is used to indicate whether the product particles are uneven.

[0032] Specifically, the S71 and S72 obtain the product surface image of the special sealing primer for water-bearing construction surface collected by the camera; and extract the HOG feature after meshing the product surface image of the special sealing primer for water-bearing construction surface to obtain a set of HOG feature vectors of product surface mesh granularity. Considering that different local areas in the product surface image contain different amounts of product surface feature information, in order to be able to more carefully analyze and process the product characteristics of each local area, in the technical solution of the present application, the product surface image of the special sealing primer for water-bearing construction surface is meshed to obtain a set of product surface mesh granularity images. In this way, the product surface can be divided into multiple small areas, which is convenient for analyzing the image features of each local area separately, so as to more finely identify surface unevenness or defects. Then, considering that each product surface mesh granularity image in the set of product surface mesh granularity images contains texture and edge feature information about the product surface, and the HOG feature can effectively characterize the local texture information in the image, which is very useful for analyzing the particle unevenness or other surface characteristics of the product surface. Based on this, in the technical solution of the present application, the HOG features of each product surface grid granularity image in the set of product surface grid granularity images are extracted to obtain a set of product surface grid granularity HOG feature vectors. That is, the HOG features contain the description of the edges and shapes in the product surface grid granularity images, which helps to more accurately identify and distinguish different surface defect modes.

[0033] Specifically, the S73 performs cluster analysis on the set of the product surface mesh granularity HOG feature vectors to obtain the product surface mesh granularity texture feature cluster center vector. Considering that each product surface mesh granularity HOG feature in the set of the product surface mesh granularity HOG feature vectors expresses the texture information of the product surface mesh granularity contained in a local grid, and in order to better understand the central trend of the texture features of the entire product surface image, so as to identify and understand the typical texture patterns and common features of the product surface, in the technical solution of the present application, a cluster analysis is performed on the set of the product surface mesh granularity HOG feature vectors to obtain the product surface mesh granularity texture feature cluster center vector. In particular, in a specific embodiment of the present application, the cluster analysis can be performed by calculating the mean vector of the set of the product surface mesh granularity HOG feature vectors as the product surface mesh granularity texture feature cluster center vector.

[0034] Specifically, the S74 calculates the texture semantic difference coefficient between each product surface mesh granularity HOG feature vector in the set of the product surface mesh granularity HOG feature vector and the product surface mesh granularity texture feature cluster center vector to obtain a texture semantic difference distribution topological matrix composed of multiple texture semantic difference coefficients. Considering that each product surface mesh granularity HOG feature vector in the set of the product surface mesh granularity HOG feature vector expresses the local texture and shape information of the product surface in different mesh areas, it reflects the detailed features of each local mesh surface, such as granularity, scratches, unevenness or other surface defects. The product surface mesh granularity texture feature cluster center vector is calculated from multiple product surface mesh granularity HOG feature vectors, representing the common features of a group of mesh areas with similar texture characteristics. Therefore, in order to analyze and compare the defect information in each grid area in a more fine-grained manner, in the technical solution of the present application, the texture semantic difference coefficient between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector is calculated to obtain a texture semantic difference distribution topological matrix composed of multiple texture semantic difference coefficients. Specifically, firstly, by calculating the difference vector and covariance matrix between each product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector, the difference between each local product surface grid granularity HOG feature vector and the overall texture feature cluster center is quantified and measured to identify areas that are significantly different from typical texture patterns, which may indicate defects or abnormalities.

[0035] In an embodiment of the present application, the texture semantic difference coefficient between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector is calculated to obtain a texture semantic difference distribution topological matrix composed of multiple texture semantic difference coefficients, including: calculating the position difference between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector to obtain a set of product surface grid granularity HOG difference feature vectors; calculating the position difference between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector; The invention relates to a method for obtaining a set of HOG inverse covariance matrices of product surface mesh granularity based on the covariance matrix between the clustering center vectors of the texture feature clusters at the product surface mesh granularity, and calculating the inverse of the covariance matrix to obtain a set of HOG inverse covariance matrices of the product surface mesh granularity; obtaining a set of HOG matching values ​​of the product surface mesh granularity based on the matching values ​​between each group of corresponding HOG differential feature vectors of the product surface mesh granularity and the HOG inverse covariance matrix of the product surface mesh granularity in the set of HOG differential feature vectors of the product surface mesh granularity and the HOG inverse covariance matrix of the product surface mesh granularity; calculating the square root of each HOG matching value of the product surface mesh granularity in the set of HOG matching values ​​of the product surface mesh granularity to obtain the texture semantic difference distribution topological matrix composed of a plurality of the texture semantic difference coefficients.

[0036] Among them, based on the matching value between each group of corresponding product surface mesh granularity HOG differential eigenvectors and the product surface mesh granularity HOG inverse covariance matrix in the set of the product surface mesh granularity HOG differential eigenvectors and the product surface mesh granularity HOG inverse covariance matrix, a set of product surface mesh granularity HOG matching values ​​is obtained, including: calculating the transposed vector of the product surface mesh granularity HOG differential eigenvector and the product surface mesh granularity HOG inverse covariance matrix and the product surface mesh granularity HOG differential eigenvector to obtain the product surface mesh granularity HOG matching value.

[0037] In summary, in the above embodiment, the texture semantic difference coefficient between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector is calculated to obtain a texture semantic difference distribution topological matrix composed of multiple texture semantic difference coefficients, including: calculating the texture semantic difference coefficient between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature cluster center vector using the following semantic difference calculation formula to obtain multiple texture semantic difference coefficients; wherein, the semantic difference calculation formula is:

[0038]

[0039] Among them, x i is the i-th product surface mesh granularity HOG feature vector in the set of product surface mesh granularity HOG feature vectors, v c is the cluster center vector of the product surface grid granularity texture feature, (·) T is the transpose of the vector, S i is the covariance matrix between the HOG feature vector of the i-th product surface grid granularity and the cluster center vector of the texture feature of the product surface grid granularity, D(x i ,v c ) is the texture semantic difference coefficient between the HOG feature vector of the i-th product surface grid granularity and the cluster center vector of the texture feature of the product surface grid granularity.

[0040] Specifically, the S75 obtains a quality inspection result based on the texture semantic difference distribution topology matrix, and the quality inspection result is used to indicate whether the product particles are uneven. In a specific example of the present application, the texture semantic difference distribution topology matrix is ​​input into a quality inspection module based on a classifier to obtain the quality inspection result, and the quality inspection result is used to indicate whether the product particles are uneven. That is, the texture semantic difference distribution topology features obtained by performing semantic difference calculation on the HOG feature vectors of the surface mesh granularity of each product in the set of the HOG feature vectors of the surface mesh granularity of the product and the clustering center vector of the texture feature of the surface mesh granularity of the product are used for classification processing, so as to automatically determine whether the product particles are uneven. In this way, the product surface image is automatically collected by the camera, and the product surface image is analyzed by computer vision technology, which can greatly improve the speed of quality inspection and reduce the time required for manual inspection. At the same time, it can more accurately identify and analyze the distribution of particles on the product surface, thereby reducing the error caused by subjective judgment and improving the intelligent level of closed bottom glue quality inspection. More specifically, the texture semantic difference distribution topology matrix is ​​input into a quality inspection module based on a classifier to obtain the quality inspection result, and the quality inspection result is used to indicate whether the product particles are uneven, including: expanding the texture semantic difference distribution topology matrix into a classification feature vector based on a row vector or a column vector; using multiple fully connected layers of the classifier to fully connect encode the classification feature vector to obtain an encoded classification feature vector; and passing the encoded classification feature vector through the Softmax classification function of the classifier to obtain the quality inspection result.

[0041] In a preferred example of the present application, considering that the set of product surface mesh granularity HOG feature vectors respectively express the HOG features of each product surface mesh granularity image, when performing cluster analysis on them and calculating the texture semantic difference coefficient between each product surface mesh granularity HOG feature vector and the product surface mesh granularity texture feature cluster center vector, the texture semantic difference feature offset caused by the uneven mapping of each product surface mesh granularity HOG feature vector to the cluster center is taken into account, and it is expected to further improve the feature difference aggregation regression expression effect of the texture semantic difference distribution topological vector, thereby improving the accuracy of the quality inspection result obtained by inputting the classifier-based quality inspection module.

[0042] Therefore, when the texture semantic difference distribution topology vector is input into a quality inspection module based on a classifier, the present application optimizes the texture semantic difference distribution topology vector, and the optimization includes the following steps:

[0043] Arranging the eigenvalues ​​of the texture semantic difference distribution topology vector in ascending order to form a texture semantic difference distribution order topology vector;

[0044] In response to the absolute value of the difference between the i-th eigenvalue and the i+1-th eigenvalue of the texture semantic difference distribution order topological vector being less than or equal to the distance difference hyperparameter ε, a weighted sum between the i-th eigenvalue and the i+1-th eigenvalue is calculated as the optimized i+1-th eigenvalue, that is:

[0045] v′ i+1 =α×v i +β×v i+1

[0046] Among them, v i 、v i+1 are the i-th eigenvalue and i+1-th eigenvalue of the texture semantic difference distribution order topological vector, respectively, v′ i+1 is the optimized i+1th eigenvalue, α and β are different weight parameters;

[0047] In response to the absolute value of the difference between the i-th eigenvalue and the i+1-th eigenvalue of the texture semantic difference distribution order topological vector being greater than the distance difference hyperparameter ε, calculating the square root of the sum of squares of all eigenvalues ​​of the texture semantic difference distribution topological vector, multiplying the square root by 2 and then dividing it by the square of the length of the texture semantic difference distribution topological vector to obtain a texture semantic difference distribution space primitive value γ;

[0048] After multiplying the texture semantic difference distribution space primitive value by the i-th eigenvalue, the weighted subtraction between the product and the i+1-th eigenvalue is calculated to obtain the optimized i+1-th eigenvalue, that is:

[0049] v′ i+1 =δ×γ×v i -θ×v i+1

[0050] Among them, δ and θ represent different weight parameters;

[0051] The optimized (i+1)th eigenvalues ​​of the texture semantic difference distribution order topology vector are combined to obtain an optimized texture semantic difference distribution topology vector, wherein the first eigenvalue of the texture semantic difference distribution order topology vector remains unchanged.

[0052] In this way, in order to address the problem of insufficient global feature difference aggregation regression representation capability of the feature set of the texture semantic difference distribution topological vector under a predetermined eigenvalue sequential distribution due to a long distance exceeding a predetermined local distribution interval threshold, a high-dimensional feature space primitive representation based on self-inner product fusion of the texture semantic difference distribution topological vector is used to capture the complex structure of the global network interaction of its eigenvalues, thereby reconstructing the difference aggregation regression relationship between the eigenvalues ​​of the texture semantic difference distribution topological vector by simulating scale-based high-dimensional feature space potential primitives, so as to achieve encoding reconstruction of the real sequence distribution behavior of the texture semantic difference distribution topological vector under a long distance, improve the aggregation expression effect of the texture semantic difference distribution topological vector, and improve the accuracy of the quality inspection results obtained by inputting it into a classifier-based quality inspection module.

[0053] Therefore, for the high-dimensional feature manifold of the texture semantic difference distribution topology vector, the eigenvalue of the feature set is used as the vector field representation of the aggregation dimension, and the superposition value of the vector field of the texture semantic difference distribution topology vector at the isolated zero position is used as the order information to fix the local position of the eigenvalue of the feature set, and add the bias of the reversibility of the feature regression distribution field of the texture semantic difference distribution topology vector as a reward to achieve the mapping target tracking of the regression distribution of the texture semantic difference distribution topology vector for the eigenvalue position, so that the feature set of the texture semantic difference distribution topology vector perceives the mapping migration to the aggregate distribution, thereby improving the accuracy of the quality inspection result obtained by the quality inspection module based on the classifier input of the texture semantic difference distribution topology matrix by improving the feature difference aggregation regression comprehensibility of the texture semantic difference distribution topology vector. In this way, the product surface image is automatically collected by the camera, and the product surface image is analyzed by computer vision technology, which can greatly improve the speed of quality inspection and reduce the time required for manual inspection. At the same time, it can more accurately identify and analyze the distribution of particles on the product surface, thereby reducing the error caused by subjective judgment and improving the intelligent level of closed bottom glue quality inspection.

[0054] In summary, according to the preparation process of the special sealing primer for water-bearing construction surface according to the embodiment of the present application, the product surface image of the special sealing primer for water-bearing construction surface is illustrated, and the product surface image is captured by a camera, and the image recognition and analysis technology based on computer vision is used to perform grid division and HOG feature extraction of the product surface image, so as to automatically judge whether the product particles are uneven according to the semantic difference distribution characteristics between the features after clustering the HOG features of each product surface grid image and the HOG features of each product surface grid image. In this way, by automatically capturing the product surface image through the camera and analyzing the product surface image using computer vision technology, the speed of quality inspection can be greatly improved and the time required for manual inspection can be reduced. At the same time, the distribution of particles on the product surface can be more accurately identified and analyzed, thereby reducing the errors caused by subjective judgment and improving the intelligent level of quality inspection of the sealing primer.

[0055] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A preparation process of a special sealing primer for water-bearing construction surfaces, characterized in that: include: Heat the epoxy resin to 50℃-60℃; Adding a plasticizer to the heated epoxy resin and stirring the mixture to obtain a first mixed material; Adding a filler during stirring of the first mixed material to obtain a second mixed material, wherein the filler is talcum powder; Adding an auxiliary agent during stirring the second mixed material to obtain a third mixed material, wherein the auxiliary agent is any one or a combination of a defoaming agent, a leveling agent and a lubricant; adding a solvent to the third mixed material to obtain a fourth mixed material, wherein the solvent is ethanol or acetone; Adding a curing agent to the fourth mixed material and stirring evenly to obtain a special sealing primer for water-bearing construction surfaces; The special sealing primer for water-bearing construction surface is subjected to quality inspection to obtain the quality inspection result.

2. The preparation process of the special sealing primer for water-bearing construction surface according to claim 1, characterized in that: The curing agent is a polyamide curing agent or an amine curing agent.

3. The preparation process of the special sealing primer for water-bearing construction surface according to claim 2, characterized in that: The special sealing primer for water-bearing construction surface is subjected to quality inspection to obtain quality inspection results, including: Acquire a product surface image of the special sealing primer for water-bearing construction surfaces collected by a camera; Gridding the product surface image of the special sealer for water-bearing construction surface and extracting HOG features to obtain a set of HOG feature vectors of the product surface grid granularity; Performing cluster analysis on the set of HOG feature vectors of the product surface mesh granularity to obtain a cluster center vector of the product surface mesh granularity texture feature; Calculating the texture semantic difference coefficient between each product surface grid granularity HOG feature vector in the set of the product surface grid granularity HOG feature vector and the product surface grid granularity texture feature clustering center vector to obtain a texture semantic difference distribution topology matrix composed of multiple texture semantic difference coefficients; Based on the texture semantic difference distribution topological matrix, a quality inspection result is obtained, and the quality inspection result is used to indicate whether the product particles are uneven.

4. The preparation process of the special sealing primer for water-bearing construction surface according to claim 3 is characterized in that: After meshing the product surface image of the special sealer for water-bearing construction surface, HOG features are extracted to obtain a set of HOG feature vectors of the product surface mesh granularity, including: Meshing the product surface image of the special sealing primer for water-bearing construction surface to obtain a set of product surface mesh granularity images; The HOG features of each product surface grid granularity image in the set of product surface grid granularity images are extracted to obtain a set of product surface grid granularity HOG feature vectors.

5. The preparation process of the special sealing primer for water-bearing construction surface according to claim 4, characterized in that: The set of the product surface mesh granularity HOG feature vectors is clustered and analyzed to obtain the product surface mesh granularity texture feature cluster center vector, including: calculating the mean vector of the set of the product surface mesh granularity HOG feature vectors as the product surface mesh granularity texture feature cluster center vector.

6. The preparation process of the special sealing primer for water-bearing construction surface according to claim 5, characterized in that: Calculating the texture semantic difference coefficient between each product surface mesh granularity HOG feature vector in the set of the product surface mesh granularity HOG feature vector and the product surface mesh granularity texture feature clustering center vector to obtain a texture semantic difference distribution topology matrix composed of multiple texture semantic difference coefficients, including: Calculating the position difference between each product surface mesh granularity HOG feature vector in the set of the product surface mesh granularity HOG feature vectors and the product surface mesh granularity texture feature clustering center vector to obtain a set of product surface mesh granularity HOG difference feature vectors; Calculating the covariance matrix between each product surface mesh granularity HOG feature vector in the set of the product surface mesh granularity HOG feature vectors and the product surface mesh granularity texture feature clustering center vector, and calculating the inverse of the covariance matrix to obtain a set of product surface mesh granularity HOG inverse covariance matrices; Based on the matching value between each corresponding group of the product surface mesh granularity HOG differential eigenvectors and the product surface mesh granularity HOG inverse covariance matrix in the set of the product surface mesh granularity HOG differential eigenvectors and the product surface mesh granularity HOG inverse covariance matrix, a set of product surface mesh granularity HOG matching values ​​is obtained; The square root of each product surface mesh granularity HOG matching value in the set of product surface mesh granularity HOG matching values ​​is calculated to obtain the texture semantic difference distribution topology matrix composed of a plurality of the texture semantic difference coefficients.

7. The preparation process of the special sealing primer for water-bearing construction surface according to claim 6, characterized in that: Based on the matching value between each corresponding group of product surface mesh granularity HOG differential eigenvectors and the product surface mesh granularity HOG inverse covariance matrix in the set of the product surface mesh granularity HOG differential eigenvectors and the product surface mesh granularity HOG inverse covariance matrix, a set of product surface mesh granularity HOG matching values ​​is obtained, including: calculating the transposed vector of the product surface mesh granularity HOG differential eigenvector and the product surface mesh granularity HOG inverse covariance matrix and the product surface mesh granularity HOG differential eigenvector to obtain the product surface mesh granularity HOG matching value.

8. The preparation process of the special sealing primer for water-bearing construction surface according to claim 7, characterized in that: Based on the texture semantic difference distribution topological matrix, a quality inspection result is obtained, and the quality inspection result is used to indicate whether the product particles are uneven, including: inputting the texture semantic difference distribution topological matrix into a quality inspection module based on a classifier to obtain the quality inspection result, and the quality inspection result is used to indicate whether the product particles are uneven.

9. The preparation process of the special sealing primer for water-bearing construction surface according to claim 8, characterized in that: The texture semantic difference distribution topology matrix is ​​input into a quality inspection module based on a classifier to obtain the quality inspection result, which is used to indicate whether the product particles are uneven, including: Expanding the texture semantic difference distribution topology matrix into a classification feature vector based on a row vector or a column vector; Performing full connection encoding on the classification feature vector using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and The encoded classification feature vector is passed through the Softmax classification function of the classifier to obtain the quality inspection result.

Images