A method and system for detecting gypsum board surface defects based on machine vision

By collecting process manufacturing parameters and composition ratios in the gypsum board surface detection system, and combining machine vision technology to calculate the strength coefficient and defect risk coefficient of gypsum board, the problem of insufficient defect recognition ability in the existing technology is solved and the detection accuracy is improved and range.

CN118799331BActive Publication Date: 2024-12-06TAISHAN GYPSUM (NANTONG) CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411290287.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-06
Estimated Expiration
2044-09-14

AI Technical Summary

Technical Problem

The existing gypsum board surface defect detection methods fail to effectively collect process manufacturing parameters and composition ratios, resulting in insufficient defect recognition capabilities and lack of specific parameter processing for different types of defect characteristics, affecting the detection accuracy and range.

Method used

Using a machine vision-based method, the surface image of the gypsum board is collected through a CCD camera, and the process manufacturing parameters and composition ratio are recorded, the characteristic parameters of the crack are obtained, and the strength coefficient and defect risk coefficient of the gypsum board are calculated based on the linear regression equation to evaluate the defect risk. grade.

Benefits of technology

It improves the ability to identify specific defects, quantifies the defect situation of gypsum board, improves the accuracy and range of defect detection, and can more accurately evaluate the defect risk level of gypsum board.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118799331B_ABST
    Figure CN118799331B_ABST
Patent Text Reader

Abstract

The present invention provides a gypsum board surface defect detection method and system based on machine vision, which relates to the technical field of gypsum board surface defect detection. The specific steps include: S1. Using a CCD camera to collect a gypsum board surface image and record relevant process manufacturing parameters and component ratios; S2. According to the collected gypsum board surface image and the recorded process manufacturing parameters and component ratios, the defect information of the gypsum board is obtained, and the defect information includes characteristic parameters of cracks on the gypsum board surface, and characteristic parameters related to the process manufacturing parameters and component ratios, and the characteristic parameters of the cracks include crack size and crack density. On the one hand, the present invention improves the recognition ability of specific defects by collecting the process manufacturing parameters, component ratios and defect information of the gypsum board, and on the other hand, by collecting specific gypsum board cracks and processing their data, the defect conditions of the gypsum board can be quantified, and the accuracy and range of gypsum board defect detection can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of gypsum board surface defect detection, and in particular to a gypsum board surface defect detection method and system based on machine vision. Background Art

[0002] The machine vision-based gypsum board surface defect detection method and system aim to utilize computer vision technology to analyze and process the gypsum board surface image to realize automatic detection and classification of gypsum board surface defects.

[0003] In the prior art, publication number CN117269189A discloses a gypsum board defect detection method and device, wherein the gypsum board defect detection method includes: determining a defect detection type; determining detection parameters and light source parameters based on the defect detection type; detecting a gypsum board image based on the detection parameters and light source parameters, and determining a detection result. By determining a defect detection type; determining detection parameters and light source parameters based on the defect detection type; detecting a gypsum board image based on the detection parameters and light source parameters, and determining a detection result, the defect detection accuracy is improved, the efficiency is improved, the labor cost is reduced, and the quality of the gypsum board can be guaranteed.

[0004] However, there are still the following deficiencies. As can be seen from the above statements, only the collection of detection parameters and light source parameters is discussed, but the specific parameters related to the gypsum board, such as process manufacturing parameters, component ratios and defect information, are not disclosed. On the one hand, process manufacturing parameters and component ratios can affect the quality and surface characteristics of the gypsum board, thereby affecting the formation and manifestation of defects. The lack of this information will lead to insufficient recognition of certain specific defects by the detection system. On the other hand, different types of gypsum board defects have different characteristics and forms, and the above scheme does not specifically collect parameter information of any defect, such as cracks, and process its data to quantify the defects of the gypsum board, so that the accuracy and range of gypsum board defect detection are limited.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a gypsum board surface defect detection method and system based on machine vision to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for detecting surface defects of gypsum boards based on machine vision, the specific steps comprising:

[0009] S1. Use a CCD camera to capture the surface image of the gypsum board and record the relevant process manufacturing parameters and component ratios;

[0010] S2. Obtain defect information of the gypsum board according to the collected surface image of the gypsum board and the recorded process manufacturing parameters and component ratio, the defect information including characteristic parameters of cracks on the surface of the gypsum board and characteristic parameters related to the process manufacturing parameters and component ratio, the characteristic parameters of the cracks including crack size, crack density and crack shape, the characteristic parameters related to the process manufacturing parameters including molding pressure, molding temperature and pressing time, and the characteristic parameters related to the component ratio including the ratio and mass of gypsum, cellulose and filler;

[0011] in,

[0012] The crack size is the area of ​​the crack;

[0013] Crack density is the number of cracks per unit area on the surface of the gypsum board;

[0014] The crack shape is the crack sharpness index;

[0015] S3. The molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board are input into the linear regression equation to obtain the strength coefficient of the gypsum board;

[0016] S4. Integrate the data of the crack area to generate a crack area array, obtain the maximum value of the crack area based on the crack area array, integrate the data of the number of cracks per unit area on the surface of the gypsum board to generate a crack density array, obtain the average density of the cracks based on the crack density array, integrate the data of the crack sharpness index to generate a crack shape array, and obtain the maximum value of the crack sharpness index based on the crack shape array;

[0017] S5. Perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks, and the maximum value of the crack sharpness index to generate a crack state coefficient, and perform data processing on the crack state coefficient and the strength coefficient of the gypsum board to generate a defect risk coefficient of the gypsum board;

[0018] S6. An evaluation module is used to compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result.

[0019] Furthermore, the molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board are input into the linear regression equation to obtain the strength coefficient of the gypsum board according to the following formula:

[0020] Q=β0+β1P+β2T+β3t+β4G+β5F+β6M+β7Qg +β8Q f +β9Q m +ε

[0021] Among them, Q is the strength coefficient of the gypsum board, that is, the strength level of the gypsum board, P, T, t, G, F, M represent the molding pressure, molding temperature, pressing time, the proportion of gypsum, cellulose and filler, Q g , Q f , Q m represent the mass of gypsum, cellulose and filler respectively, β0 is the intercept term, β1, β2, β3, β4, β5, β6, β7, β8 and β9 are regression coefficients, indicating the influence of each parameter on the strength of gypsum board, β1+β2+β3+β4+β5+β6+β7+β8+β9=1, and ε is the error term.

[0022] Furthermore, the data of the areas of N gypsum board cracks are integrated to generate an array of crack areas. Based on the array of crack areas, the process of obtaining the maximum value of the crack area is as follows:

[0023] Assuming that the crack area array is A, A = [a1, a2, ..ai.., aN], where ai represents the area of ​​the i-th group of cracks, i is the index of the crack area, and N is the number of crack area arrays, the formula for obtaining the maximum crack area is as follows:

[0024] S=max(A)

[0025] Among them, S is the maximum value of the crack area, and max(A) represents the maximum value in the crack area array A, that is, the maximum crack area.

[0026] Furthermore, the number of cracks per unit area on the surface of N gypsum boards is integrated to generate a crack density array. Based on the crack density array, the process of obtaining the average density of cracks is as follows:

[0027]

[0028] in, is the average density of cracks, indicating the average number of cracks per unit area, and D is an array of crack densities, D = D1, D2, ..., D j ,...,D M M is the number of crack density arrays, D j is the crack density of the jth group.

[0029] Furthermore, the crack sharpness index is integrated to generate a crack shape array. According to the crack shape array, the process of obtaining the maximum value of the crack sharpness index is as follows:

[0030] Normalization:

[0031]

[0032] Among them, the crack sharpness index array K = [k1, k2, .. ki.., kN], k i′ is the normalized sharpness index, min(K) and max(K) are the minimum and maximum values ​​in the array (K), respectively, and (ki) represents the sharpness index of the i-th crack;

[0033] Extraction of maximum sharpness index:

[0034] K max =max[f(k 1′ ), f(k 2′ ), ..., f(k N′ )]

[0035] Among them, K max is the maximum value of the crack sharpness index.

[0036] Furthermore, the maximum value of the crack area, the average density of the cracks and the maximum value of the crack sharpness index are subjected to data processing and correlation analysis to generate the crack state coefficient, based on the following formula:

[0037]

[0038] Where C is the crack state coefficient, w A is the weight coefficient of the maximum value of the crack area, w D is the weight coefficient of the average density of cracks, w K is the weight coefficient of the crack sharpness index, w A >w D >w K , w A +w D +w K =1.

[0039] Furthermore, the crack state coefficient and the strength coefficient of the gypsum board are processed to generate the defect risk coefficient of the gypsum board, based on the following formula:

[0040]

[0041] Among them, R represents the defect risk coefficient of the gypsum board, C represents the crack state coefficient, which indicates the comprehensive state of cracks on the gypsum board, and Q represents the strength coefficient of the gypsum board, which reflects the strength level of the gypsum board.

[0042] Furthermore, the defect risk coefficient of the gypsum board is compared with the threshold value of the defect risk coefficient. According to the comparison result, the process of evaluating the defect risk level of the gypsum board is as follows:

[0043] When 0<R≤0.8YZ, it means that the defect risk level of the gypsum board is low risk;

[0044] When 0.8YZ<R≤YZ, it means that the defect risk level of the gypsum board is medium risk;

[0045] When R>YZ, it means that the defect risk level of the gypsum board is high risk.

[0046] A gypsum board surface defect detection system based on machine vision, the system is used to execute any of the above-mentioned gypsum board surface defect detection methods based on machine vision, comprising:

[0047] A data acquisition module is used to collect images of the surface of the gypsum board using a CCD camera and record relevant process manufacturing parameters and component ratios;

[0048] A parameter determination module is used to obtain defect information of the gypsum board according to the collected surface image of the gypsum board and the recorded process manufacturing parameters and component ratio, wherein the defect information includes characteristic parameters of cracks on the surface of the gypsum board and characteristic parameters related to the process manufacturing parameters and the component ratio, wherein the characteristic parameters of the cracks include crack size, crack density and crack shape, the characteristic parameters related to the process manufacturing parameters include molding pressure, molding temperature and pressing time, and the characteristic parameters related to the component ratio include the ratio and mass of gypsum, cellulose and filler;

[0049] in,

[0050] The crack size is the area of ​​the crack;

[0051] Crack density is the number of cracks per unit area on the surface of the gypsum board;

[0052] The crack shape is the crack sharpness index;

[0053] A function building module is used to input the molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board into a linear regression equation to obtain the strength coefficient of the gypsum board;

[0054] The data processing module is used to integrate the data of the crack area to generate a crack area array, obtain the maximum value of the crack area according to the crack area array, integrate the data of the number of cracks per unit area on the surface of the gypsum board to generate a crack density array, obtain the average density of the cracks according to the crack density array, integrate the data of the crack sharpness index to generate a crack shape array, and obtain the maximum value of the crack sharpness index according to the crack shape array;

[0055] A data analysis module is used to perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks and the maximum value of the crack sharpness index to generate a crack state coefficient, and to perform data processing on the crack state coefficient and the strength coefficient of the gypsum board to generate a defect risk coefficient of the gypsum board;

[0056] The evaluation module is used to compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The present invention collects process manufacturing parameters, component ratios and defect information of the gypsum board, and inputs the process manufacturing parameters and component ratios of the gypsum board into a linear regression equation, so as to obtain the strength coefficient of the gypsum board, integrate the data of the area of ​​the cracks, and obtain the maximum value of the crack area, integrate the data of the number of cracks per unit area on the surface of the gypsum board, and obtain the average density of the cracks, integrate the data of the cusp index of the cracks, and obtain the maximum value of the cusp index of the cracks, perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks and the maximum value of the cusp index of the cracks, and generate a crack state coefficient, perform data processing on the crack state coefficient and the strength coefficient of the gypsum board, and generate a defect risk coefficient of the gypsum board, compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result. Therefore, on the one hand, by collecting the process manufacturing parameters, component ratios and defect information of the gypsum board, the ability to identify specific defects is improved. On the other hand, by collecting specific gypsum board cracks and processing their data, the defects of the gypsum board can be quantified, thereby improving the accuracy and range of gypsum board defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0060] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0061] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0062] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0063] Example:

[0064] See also Figure 1 , the present invention provides a technical solution:

[0065] A method for detecting surface defects of gypsum boards based on machine vision, the specific steps comprising:

[0066] S1. Use a CCD camera to capture the surface image of the gypsum board and record the relevant process manufacturing parameters and component ratios;

[0067] S2. Obtain defect information of the gypsum board according to the collected surface image of the gypsum board and the recorded process manufacturing parameters and component ratio, the defect information including characteristic parameters of cracks on the surface of the gypsum board and characteristic parameters related to the process manufacturing parameters and component ratio, the characteristic parameters of the cracks including crack size, crack density and crack shape, the characteristic parameters related to the process manufacturing parameters including molding pressure, molding temperature and pressing time, and the characteristic parameters related to the component ratio including the ratio and mass of gypsum, cellulose and filler;

[0068] in,

[0069] The crack size is the area of ​​the crack;

[0070] Crack density is the number of cracks per unit area on the surface of the gypsum board;

[0071] The crack shape is the crack sharpness index;

[0072] S3. The molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board are input into the linear regression equation to obtain the strength coefficient of the gypsum board;

[0073] S4. Integrate the data of the crack area to generate a crack area array, obtain the maximum value of the crack area based on the crack area array, integrate the data of the number of cracks per unit area on the surface of the gypsum board to generate a crack density array, obtain the average density of the cracks based on the crack density array, integrate the data of the crack sharpness index to generate a crack shape array, and obtain the maximum value of the crack sharpness index based on the crack shape array;

[0074] S5. Perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks, and the maximum value of the crack sharpness index to generate a crack state coefficient, and perform data processing on the crack state coefficient and the strength coefficient of the gypsum board to generate a defect risk coefficient of the gypsum board;

[0075] S6. An evaluation module is used to compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result.

[0076] When the crack size, crack density and crack sharpness index of the gypsum board exceed the set threshold, the gypsum board will break. The specific reasons are as follows:

[0077] Stress concentration: Increased crack size and density will lead to increased stress concentration on the gypsum board, thereby increasing the stress at the cracks and making the gypsum board more likely to break.

[0078] Insufficient strength: When the size, density and sharpness index of the cracks exceed a certain threshold, it may exceed the bearing capacity of the gypsum board, making it insufficiently strong to support the load and break.

[0079] Structural deformation: The presence of cracks can cause the gypsum board to deform and deform. When the crack size and density exceed a certain level, it may lead to increased instability and deformation of the gypsum board structure, and eventually lead to fracture.

[0080] In summary, when the crack size, density and sharpness index of the gypsum board exceed the set threshold, the main reasons for the rupture of the gypsum board include stress concentration, insufficient strength and structural deformation.

[0081] When the forming pressure, forming temperature and pressing time of the gypsum board are higher or longer, the strength of the gypsum board will be higher. The specific reasons are as follows:

[0082] Grain refinement: Under high pressure and high temperature conditions, gypsum particles are prone to plastic deformation, resulting in grain refinement. Grain refinement can increase the strength of the material because the stress concentration at the grain boundaries is reduced, thereby slowing down the propagation of cracks.

[0083] Particle compaction: High pressure can better compact gypsum particles, increase the contact area between particles, and thus improve the density and strength of the material.

[0084] Changes in crystal structure: Under high temperature conditions, the bonding ability between gypsum particles is enhanced, and the crystal structure may change, forming a tighter structure and improving the strength of the material.

[0085] Moisture removal: The long pressing process helps to remove moisture from the gypsum, reducing the porosity and defects in the material and improving its density and strength.

[0086] Crystallization water binding: Under high temperature conditions, the crystallization water in gypsum can better combine with gypsum particles to form a more solid crystal structure, thereby improving the strength and stability of the material.

[0087] In summary, the higher or longer the molding pressure, molding temperature and pressing time, the more it can promote the processes of grain refinement, particle compaction, crystal structure change, moisture removal and crystal water binding of the gypsum board material, thereby improving the strength of the gypsum board.

[0088] The higher the ratio and quality of gypsum, cellulose and filler in the gypsum board, the stronger the gypsum board will be. Here are the specific reasons:

[0089] The role of reinforcing fillers: reinforcing fillers such as cellulose can increase the toughness and tensile strength of gypsum board. Cellulose forms a network structure in the gypsum matrix, which hinders the expansion of cracks and thus improves the tensile strength and toughness of the gypsum board.

[0090] Adding fillers: Adding fillers can increase the density and uniformity of the gypsum board, making the gypsum board tighter. Adding fillers can also help reduce the pores and defects in the material and improve the density and strength of the material.

[0091] Interaction between gypsum and filler: An appropriate amount of filler can improve the interaction between gypsum and filler and improve the overall performance of the material. Filler can increase the elastic modulus and hardness of the gypsum board, thereby improving the overall strength of the gypsum board.

[0092] Balanced quality: The right ratio of gypsum, cellulose and filler can make the composition of the gypsum board more balanced, thus ensuring the strength and stability of the material.

[0093] Bonding effect: Fillers such as cellulose can effectively bond with the gypsum matrix to form a more stable structure. This bonding effect helps to enhance the overall strength of the gypsum board.

[0094] In summary, a higher ratio and quality of gypsum, cellulose and filler in the gypsum board generally means better filling effect, better filling structure and better bonding effect, so the strength of the gypsum board will also be higher.

[0095] Linear regression models can be used to describe the linear relationship between independent variables and dependent variables, that is, a linear relationship is assumed between the dependent variable and the independent variable, and the least squares method is used to fit the data. In this case, it is assumed that there is a linear relationship between the strength of the gypsum board (dependent variable) and the molding pressure, molding temperature, pressing time, and the proportion and mass of gypsum, cellulose, and filler (independent variables).

[0096] On the basis of the above embodiment, the molding pressure, molding temperature, pressing time, the ratio and mass of gypsum, cellulose and filler of the gypsum board are input into the linear regression equation to obtain the strength coefficient of the gypsum board, according to the following formula:

[0097] Q=β0+β1P+β2T+β3t+β4G+β5F+β6M+β7Q g +β8Q f +β9Q m +ε

[0098] Among them, Q is the strength coefficient of the gypsum board, that is, the strength level of the gypsum board, P, T, t, G, F, M represent the molding pressure, molding temperature, pressing time, the proportion of gypsum, cellulose and filler, Q g , Q f , Q m represent the mass of gypsum, cellulose and filler respectively, β0 is the intercept term, β1, β2, β3, β4, β5, β6, β7, β8 and β9 are regression coefficients, indicating the influence of each parameter on the strength of gypsum board, β1+β2+β3+β4+β5+β6+β7+β8+β9=1, and ε is the error term.

[0099] According to the functional relationship between the molding pressure, molding temperature, pressing time, the ratio and mass of gypsum, cellulose and filler and the strength coefficient of the gypsum board, a data table is established. The table content is as follows:

[0100]

[0101] Through the analysis of experimental data, we can draw the following conclusions:

[0102] The increase in molding pressure, molding temperature and pressing time has a positive correlation with the strength of gypsum board, that is, as these parameters increase, the strength coefficient of gypsum board also increases. This shows that within a certain range, increasing molding pressure, molding temperature and pressing time can significantly improve the strength of gypsum board. This is because higher molding pressure and temperature and longer pressing time can promote tighter bonding of gypsum during the molding process, thereby improving the strength of gypsum board.

[0103] The ratio and mass of gypsum, cellulose and filler also have a significant effect on the strength of gypsum board. With the decrease of gypsum ratio and the increase of cellulose ratio, or the increase of gypsum and cellulose mass and the decrease of filler mass, the strength coefficient of gypsum board shows an upward trend.

[0104] This shows that within a certain range, increasing the proportion of cellulose and filler appropriately can enhance the structural strength of the gypsum board and improve its compressive properties, while too high a proportion of gypsum may cause the board to be too brittle and reduce the strength of the gypsum board.

[0105] On the basis of the above embodiment, the data of the areas of N gypsum board cracks are integrated to generate an array of crack areas. According to the array of crack areas, the process of obtaining the maximum value of the crack area is as follows:

[0106] Assuming that the crack area array is A, A = [a1, a2, ..ai.., aN], where ai represents the area of ​​the i-th group of cracks, i is the index of the crack area, and N is the number of crack area arrays, the formula for obtaining the maximum crack area is as follows:

[0107] S=max(A)

[0108] Among them, S is the maximum value of the crack area, and max(A) represents the maximum value in the crack area array A, that is, the maximum crack area.

[0109] The range of the crack area should be non-negative real numbers, because the area cannot be negative. Therefore, the range of the crack area is [0, S], where S is the maximum crack area actually measured. The maximum crack area S represents the maximum crack area in the gypsum board cracks. This value reflects the size of the maximum crack area on the gypsum board.

[0110] Based on the above embodiment, the number of cracks per unit area on the surface of N gypsum boards is integrated to generate a crack density array. According to the crack density array, the process of obtaining the average density of the cracks is as follows:

[0111]

[0112] in, is the average density of cracks, indicating the average number of cracks per unit area, and D is the array of crack densities D = D1, D2, ..., D j ,...,D M , M is the number of crack density arrays, D j is the crack density of the jth group.

[0113] On the basis of the above embodiment, the cusp index of the crack is integrated to generate a crack shape array. According to the crack shape array, the process of obtaining the maximum value of the cusp index of the crack is as follows:

[0114] Normalization:

[0115]

[0116] Among them, the crack sharpness index array K = [k1, k2, .. ki.., kN], k i′ is the normalized sharpness index, min(K) and max(K) are the minimum and maximum values ​​in the array (K), respectively, and (ki) represents the sharpness index of the i-th crack;

[0117] Extraction of maximum sharpness index:

[0118] K max =max[f(k 1′ ), f(k 2′ ),…,f(k N′ )]

[0119] Among them, K max is the maximum value of the crack sharpness index.

[0120] K max The value range is [0,1], K max A value close to 1 indicates that one or more cracks have significant cusp characteristics, which may be structural weaknesses or areas of high stress concentration.

[0121] On the basis of the above embodiment, the maximum value of the crack area, the average density of the crack and the maximum value of the crack sharpness index are subjected to data processing and correlation analysis to generate the crack state coefficient, according to the following formula:

[0122]

[0123] Where C is the crack state coefficient, w A is the weight coefficient of the maximum value of the crack area, w D is the weight coefficient of the average density of cracks, w K is the weight coefficient of the crack sharpness index, w A >w D >wK , w A +w D +w K =1.

[0124] The assessment of crack status depends not only on the area of ​​the crack, but also on the density and morphological characteristics of the crack. This linear combination allows these factors to be taken into account in a single indicator, thus providing a more comprehensive assessment of the crack status.

[0125] The weight coefficients in the formula allow users to adjust the importance of different factors according to actual conditions and engineering needs. For example, if the area of ​​the crack is more critical to the structure in a specific case, its weight can be adjusted higher to more accurately reflect the actual situation.

[0126] On the basis of the above embodiment, the crack state coefficient and the strength coefficient of the gypsum board are processed to generate the defect risk coefficient of the gypsum board, and the formula is as follows:

[0127]

[0128] Among them, R represents the defect risk coefficient of the gypsum board, C represents the crack state coefficient, which indicates the comprehensive state of cracks on the gypsum board, and Q represents the strength coefficient of the gypsum board, which reflects the strength level of the gypsum board.

[0129] Interaction rule: When the crack state coefficient C increases, the defect risk coefficient R of the gypsum board will increase, because the deterioration of the crack state will increase the defect risk, and when the strength coefficient Q of the gypsum board increases, the defect risk coefficient R of the gypsum board will decrease, because a stronger board will reduce the defect risk.

[0130] According to the functional relationship between the crack state coefficient, the strength coefficient of the gypsum board and the defect risk coefficient of the gypsum board, a data table is established. The table content is as follows:

[0131]

[0132] Through the above table data, we can clearly see the impact of different crack states and strength coefficients on the defect risk coefficient of gypsum board. First, with the increase of crack state coefficient C, the defect risk coefficient R shows an increasing trend, which is in line with expectations, that is, the more serious the crack state, the higher the defect risk of the gypsum board; secondly, the increase in strength coefficient Q will lead to a decrease in the defect risk coefficient R, indicating that gypsum boards with higher strength have lower defect risks.

[0133] On the basis of the above embodiment, the defect risk coefficient of the gypsum board is compared with the threshold value of the defect risk coefficient. According to the comparison result, the process of evaluating the defect risk level of the gypsum board is as follows:

[0134] When 0<R≤0.8YZ, it means that the defect risk level of the gypsum board is low risk. For example, the crack state coefficient C is 0.3, the strength coefficient Q of the gypsum board is 0.9, the defect risk coefficient R of the gypsum board is 1.15, and the threshold value of the defect risk coefficient is 1.5;

[0135] When 0.8YZ<R≤YZ, it means that the defect risk level of the gypsum board is medium risk. For example, the crack state coefficient C is 0.5, the strength coefficient Q of the gypsum board is 0.7, the defect risk coefficient R of the gypsum board is 1.43, and the threshold of the defect risk coefficient is 1.5;

[0136] When R>YZ, it indicates that the defect risk level of the gypsum board is high risk. For example, the crack state coefficient C is 0.7, the strength coefficient Q of the gypsum board is 0.5, the defect risk coefficient R of the gypsum board is 2.3, and the threshold value of the defect risk coefficient is 1.5.

[0137] The specific values ​​of β1, β2, β3, β4, β5, β6, β7, β8 and β9 in the formula are generally determined by technical personnel in this field according to actual conditions. The essence of this formula is a comprehensive analysis based on weighted summation. Technical personnel in this field collect multiple groups of sample data, and set corresponding preset proportional coefficients for each group of sample data. The preset proportional coefficients and the collected sample data are substituted into the formula. Through repeated experiments and parameter adjustments, the accuracy of the model output and the rationality of the results are observed, and these factor coefficients are gradually adjusted. The performance and effect of the model under different parameter settings are compared to find the optimal coefficient combination. The calculated factor coefficients are screened and averaged to obtain the values ​​of β1, β2, β3, β4, β5, β6, β7, β8 and β9.

[0138] In addition, the size of the preset factor coefficient is to quantify each parameter to obtain a specific value. In order to facilitate subsequent comparison, the size of the coefficient depends on the amount of sample data and the preset proportional coefficient initially set by technical personnel in this field for each set of sample data. It is not unique as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0139] See also Figure 2 , the present invention also provides a technical solution:

[0140] A gypsum board surface defect detection system based on machine vision, the system is used to execute any of the above-mentioned gypsum board surface defect detection methods based on machine vision, comprising:

[0141] A data acquisition module is used to collect images of the surface of the gypsum board using a CCD camera and record relevant process manufacturing parameters and component ratios;

[0142] A parameter determination module is used to obtain defect information of the gypsum board according to the collected surface image of the gypsum board and the recorded process manufacturing parameters and component ratio, wherein the defect information includes characteristic parameters of cracks on the surface of the gypsum board and characteristic parameters related to the process manufacturing parameters and the component ratio, wherein the characteristic parameters of the cracks include crack size, crack density and crack shape, the characteristic parameters related to the process manufacturing parameters include molding pressure, molding temperature and pressing time, and the characteristic parameters related to the component ratio include the ratio and mass of gypsum, cellulose and filler;

[0143] in,

[0144] The crack size is the area of ​​the crack;

[0145] Crack density is the number of cracks per unit area on the surface of the gypsum board;

[0146] The crack shape is the crack sharpness index;

[0147] A function building module is used to input the molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board into a linear regression equation to obtain the strength coefficient of the gypsum board;

[0148] The data processing module is used to integrate the data of the crack area to generate a crack area array, obtain the maximum value of the crack area according to the crack area array, integrate the data of the number of cracks per unit area on the surface of the gypsum board to generate a crack density array, obtain the average density of the cracks according to the crack density array, integrate the data of the crack sharpness index to generate a crack shape array, and obtain the maximum value of the crack sharpness index according to the crack shape array;

[0149] A data analysis module is used to perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks and the maximum value of the crack sharpness index to generate a crack state coefficient, and to perform data processing on the crack state coefficient and the strength coefficient of the gypsum board to generate a defect risk coefficient of the gypsum board;

[0150] The evaluation module is used to compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result.

[0151] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0152] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for detecting surface defects of gypsum boards based on machine vision, characterized in that: The specific steps include: S1. Use a CCD camera to capture the surface image of the gypsum board and record the relevant process manufacturing parameters and component ratios; S2. Obtain defect information of the gypsum board according to the collected surface image of the gypsum board and the recorded process manufacturing parameters and component ratio, the defect information including characteristic parameters of cracks on the surface of the gypsum board and characteristic parameters related to the process manufacturing parameters and component ratio, the characteristic parameters of the cracks including crack size, crack density and crack shape, the characteristic parameters related to the process manufacturing parameters including molding pressure, molding temperature and pressing time, and the characteristic parameters related to the component ratio including the ratio and mass of gypsum, cellulose and filler; Among them, the crack size is the area of ​​the crack; Crack density is the number of cracks per unit area on the surface of the gypsum board; The crack shape is the crack sharpness index; S3. The molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board are input into the linear regression equation to obtain the strength coefficient of the gypsum board; S4. Integrate the data of the crack area to generate a crack area array, obtain the maximum value of the crack area based on the crack area array, integrate the data of the number of cracks per unit area on the surface of the gypsum board to generate a crack density array, obtain the average density of the cracks based on the crack density array, integrate the data of the crack sharpness index to generate a crack shape array, and obtain the maximum value of the crack sharpness index based on the crack shape array; S5. Perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks, and the maximum value of the crack sharpness index to generate a crack state coefficient, and perform data processing on the crack state coefficient and the strength coefficient of the gypsum board to generate a defect risk coefficient of the gypsum board; S6. An evaluation module, used to compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result; The maximum value of the crack area, the average density of the cracks and the maximum value of the crack sharpness index are processed and correlated to generate the crack state coefficient based on the following formula: Where C is the crack state coefficient, w A is the weight coefficient of the maximum crack area, S is the maximum crack area, w D is the weight coefficient of the average density of cracks, is the average density of cracks, w K is the weight coefficient of the crack sharpness index, K max is the maximum value of the crack sharpness index, w A >w D >w K , w A +w D +w K =1; The crack state coefficient and the strength coefficient of the gypsum board are processed to generate the defect risk coefficient of the gypsum board, based on the following formula: Among them, R represents the defect risk coefficient of the gypsum board, C represents the crack state coefficient, which indicates the comprehensive state of cracks on the gypsum board, and Q represents the strength coefficient of the gypsum board, which reflects the strength level of the gypsum board.

2. The method for detecting surface defects of gypsum boards based on machine vision according to claim 1, characterized in that: The molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board are input into the linear regression equation to obtain the strength coefficient of the gypsum board according to the following formula: Q=β0+β1P+β2T+β3t+β4G+β5F+β6M+β7Q g +β8Q f +β9Q m +e Among them, P, T, t, G, F, M represent the molding pressure, molding temperature, pressing time, the proportion of gypsum, cellulose and filler, respectively, and Q g , Q f , Q m represent the mass of gypsum, cellulose and filler respectively, β0 is the intercept term, β1, β2, β3, β4, β5, β6, β7, β8 and β9 are regression coefficients, indicating the influence of each parameter on the strength of gypsum board, β1+β2+β3+β4+β5+β6+β7+β8+β9=1, and ε is the error term.

3. The method for detecting surface defects of gypsum boards based on machine vision according to claim 1, characterized in that: The area of ​​the cracks in the gypsum board is integrated to generate an array of crack areas. Based on the array of crack areas, the process of obtaining the maximum value of the crack area is as follows: Assuming that the crack area array is A, A = a1, a2, .. ai.., aN, where ai represents the area of ​​the i-th crack group, i is the index of the crack area, and N is the number of crack area arrays, the formula for obtaining the maximum crack area is as follows: S=max(A) Among them, S is the maximum value of the crack area, and max(A) represents the maximum value in the crack area array A, that is, the maximum crack area.

4. The method for detecting surface defects of gypsum boards based on machine vision according to claim 1, characterized in that: The number of cracks per unit area on the surface of the gypsum board is integrated to generate a crack density array. Based on the crack density array, the process of obtaining the average density of the cracks is as follows: in, is the average density of cracks, indicating the average number of cracks per unit area, and D is an array of crack densities, D = D1, D2, ..., D j ,...,D M , M is the number of crack density arrays, D j is the crack density of the jth group.

5. The method for detecting surface defects of gypsum boards based on machine vision according to claim 1, characterized in that: The crack sharpness index is integrated to generate a crack shape array. According to the crack shape array, the process of obtaining the maximum value of the crack sharpness index is as follows: Normalization: Among them, the crack sharpness index array K = [k1, k2, .. ki.., kN], k i′ is the normalized sharpness index, min(K) and max(K) are the minimum and maximum values ​​in the array (K), respectively, and (ki) represents the sharpness index of the i-th crack; Extraction of maximum sharpness index: K max =max[f(k 1′ ),f(k 2′ ),...,f(k N′ )] Among them, K max is the maximum value of the crack sharpness index.

6. The method for detecting surface defects of gypsum boards based on machine vision according to claim 1, characterized in that: The defect risk factor of the gypsum board is compared with the threshold value of the defect risk factor. According to the comparison result, the process of evaluating the defect risk level of the gypsum board is as follows: When 0<R≤0.8YZ, it means that the defect risk level of the gypsum board is low risk; When 0.8YZ<R≤YZ, it means that the defect risk level of the gypsum board is medium risk; When R>YZ, it means that the defect risk level of the gypsum board is high risk.

7. A gypsum board surface defect detection system based on machine vision, the system is used to execute the gypsum board surface defect detection method based on machine vision according to any one of claims 1 to 6, characterized in that: include: A data acquisition module is used to collect images of the surface of the gypsum board using a CCD camera and record relevant process manufacturing parameters and component ratios; A parameter determination module is used to obtain defect information of the gypsum board according to the collected surface image of the gypsum board and the recorded process manufacturing parameters and component ratio, wherein the defect information includes characteristic parameters of cracks existing on the surface of the gypsum board and characteristic parameters related to the process manufacturing parameters and the component ratio, wherein the characteristic parameters of the cracks include crack size, crack density and crack shape, the characteristic parameters related to the process manufacturing parameters include molding pressure, molding temperature and pressing time, and the characteristic parameters related to the component ratio include the ratio and mass of gypsum, cellulose and filler; in, The crack size is the area of ​​the crack; Crack density is the number of cracks per unit area on the surface of the gypsum board; The crack shape is the crack sharpness index; A function building module is used to input the molding pressure, molding temperature, pressing time, ratio and mass of gypsum, cellulose and filler of the gypsum board into a linear regression equation to obtain the strength coefficient of the gypsum board; The data processing module is used to integrate the data of the crack area to generate a crack area array, obtain the maximum value of the crack area according to the crack area array, integrate the data of the number of cracks per unit area on the surface of the gypsum board to generate a crack density array, obtain the average density of the cracks according to the crack density array, integrate the data of the crack sharpness index to generate a crack shape array, and obtain the maximum value of the crack sharpness index according to the crack shape array; A data analysis module is used to perform data processing and correlation analysis on the maximum value of the crack area, the average density of the cracks and the maximum value of the crack sharpness index to generate a crack state coefficient, and to perform data processing on the crack state coefficient and the strength coefficient of the gypsum board to generate a defect risk coefficient of the gypsum board; The evaluation module is used to compare the defect risk coefficient of the gypsum board with a threshold value of the defect risk coefficient, and evaluate the defect risk level of the gypsum board according to the comparison result.

Citation Information

Patent Citations

  • Gypsum board defect detection method and device

    CN117269189A

  • Tunnel construction segment and tunnel concrete structure durability and crack control method

    CN110714783A

  • Grouting process optimization method for rapid road repair

    CN117364593A

  • Welding seam nondestructive testing method and system with high detection precision

    CN118465220A

  • Method and system for veneer grading and stacking using vision system analysis

    US11222419B1