A method, system and device for detecting deformation of a kettle cover mold

Abstract

The present application relates to the technical field of mold deformation detection, and specifically to a method, system and device for detecting the deformation of a kettle cover mold. The method comprises: determining the symmetric matrix of each matrix based on the position distribution of each matrix in its corresponding contour matrix; determining the discrimination between each matrix and its symmetric matrix based on the distribution of all quantized contour data in each matrix and its symmetric matrix, and the similarity of all column vectors between each matrix and its symmetric matrix, and combining the complexity of each matrix and its symmetric matrix; determining the abnormal value of each kettle cover mold based on the difference between the discrimination between all matrixes and their respective symmetric matrixes in different measurements, and detecting the kettle cover mold. The present application comprehensively analyzes the complexity of the contour of the kettle cover mold and its probability of deformation, so as to improve the sensitivity of the deformation detection of the kettle cover mold.

Description

Technical Field

[0001] The present application relates to the technical field of mold deformation detection, and specifically to a method, system and equipment for detecting deformation of a kettle lid mold. Background Art

[0002] Injection molding is one of the main methods for producing kettle lids. To ensure the seal between the kettle lid and the pot mouth, high injection molding precision is required. During the kettle lid injection molding process, the extrusion and collision of the kettle lid mold parting surface during mold opening and closing, the pressure of the melt on the inner wall of the kettle lid mold cavity, and the clamping force of the injection molding machine cause the kettle lid mold to undergo elastic deformation in a short period of time. After long-term operation, the cumulative effect of various factors will cause parts of the kettle lid mold to undergo permanent plastic deformation, resulting in a decrease in the dimensional accuracy of the injection-molded kettle lid and affecting the seal between the kettle lid and the pot mouth. Therefore, it is necessary to regularly inspect the kettle lid mold for deformation and replace it promptly if deformation occurs.

[0003] Laser profile scanning, as a non-contact measurement method, improves measurement accuracy while avoiding the mold clamping problem in the traditional measurement process. It is now a commonly used method for detecting kettle lid mold deformation. At present, when using laser profile scanners to inspect kettle lid molds, whether deformation has occurred is determined only based on the difference in mold profile data collected twice adjacently. This ignores the fact that the probability of deformation in different areas of the mold is different. In areas with low deformation probability, even small measurement differences may lead to misjudgment as deformation, thereby triggering unnecessary maintenance or inspection. In areas with high deformation rates, if the deformation amplitude is smaller than the detection resolution, or the deformation pattern does not match the detection method, the real deformation problem may be missed. The above two situations will lead to inaccurate assessment of the mold health status, thereby reducing the sensitivity of kettle lid mold deformation detection. Summary of the Invention

[0004] In a first aspect, an embodiment of the present application provides a method for detecting deformation of a kettle lid mold, the method comprising the following steps:

[0005] Within a preset time, each kettle lid mold is scanned multiple times using a laser profile scanner, and the profile data of all scanning points in each scan are measured and formed into a profile data vector for each scan. The profile data vectors of all scans are used to form a profile matrix for each kettle lid mold, and the profile matrix is ​​evenly divided into multiple square matrices, where the profile data is the distance from the laser beam emitted by the laser profile scanner to all scanning points;

[0006] In each kettle lid mold, based on the maximum value of all contour data in each square matrix, the contour variation interval of each square matrix is ​​determined, and the contour variation interval is evenly divided into multiple sub-intervals of equal length. The complexity of each square matrix is ​​determined based on the proportion of all contour data in each sub-interval in all contour data in the square matrix, as well as the degree of discreteness of the number of rows and columns of all contour data in each sub-interval in each square matrix;

[0007] Based on the position distribution of each square matrix in its corresponding profile matrix, determine the square matrix that is positionally symmetric with each square matrix, and record the square matrix that is positionally symmetric with each square matrix as the symmetric square matrix of each square matrix; replace all the profile data in each subinterval of each square matrix with the value of the upper limit of the subinterval, and record all the replaced data as quantized profile data; based on the distribution of all quantized profile data in each square matrix and its symmetric square matrix, and the similarity of all column vectors between each square matrix and its opposite square matrix, determine the symmetry coefficient between each square matrix and its symmetric square matrix, and combine the complexity of each square matrix and its symmetric square matrix to determine the discrimination between each square matrix and its symmetric square matrix;

[0008] Based on the difference in the degree of discrimination between all square matrices and their symmetrical square matrices in different measurements, the outlier value of each kettle lid mold is determined and the kettle lid mold is tested.

[0009] Preferably, the method for determining the profile change interval of each square matrix is:

[0010] The maximum and minimum values ​​of all contour data in each matrix are used as the upper and lower limits of the contour change range respectively.

[0011] Preferably, the complexity expression of each square matrix is: Where, represents the complexity of the matrix i; 、 They represent the discrete degree of the number of rows and the discrete degree of the number of columns of all the contour data in subinterval k in the matrix i respectively; It represents the proportion of all the contour data in subinterval k in matrix i to all the contour data in matrix i; represents the number of all subintervals in the contour change interval of the matrix i; ln( ) represents the logarithmic function with a natural constant as the base.

[0012] Preferably, determining a square matrix that is positionally symmetrical with each square matrix comprises:

[0013] In the contour matrix of each kettle lid mold, the contour data is symmetrically distributed about the central axis of the kettle lid mold according to the shape of the kettle lid mold. If the matrix D and the matrix E are mirror-symmetrical about the central axis of the kettle lid mold, then the matrix D and the matrix E are positionally symmetrical matrices to each other.

[0014] Preferably, the method for determining the symmetry coefficient between each matrix and its symmetric matrix is:

[0015] All quantized contour data of each matrix are used as input of the maximum inter-class variance algorithm, and the maximum inter-class variance of each matrix is ​​output;

[0016] Symmetry coefficient between matrix i and its symmetric matrix The expression is: Where, It represents the sum of the maximum inter-class variance of matrix i and the maximum inter-class variance of the symmetric matrix of matrix i; Represents the j-th column vector of matrix i and the j-th column vector of the symmetric matrix of matrix i The similarity between column vectors; W represents the total number of columns in each square matrix; norm() represents the normalization function.

[0017] Preferably, the method for determining the degree of distinction between each matrix and its symmetrical matrix is:

[0018] The sum of the complexities of each square matrix and its symmetric square matrix is ​​calculated, and the ratio of the sum to the symmetry coefficient is used as the discrimination between each square matrix and its symmetric square matrix.

[0019] Preferably, the outlier value of each kettle lid mold is a normalized result of taking the mean of the differences between all measurements of the discrimination between all square matrices and their symmetric square matrices in each kettle lid mold.

[0020] Preferably, the process of detecting the kettle cover mold is:

[0021] The mean of the outlier values ​​of all kettle lid molds is used as the deformation threshold. If the outlier value of the kettle lid mold is greater than the deformation threshold, the kettle lid mold is deformed; otherwise, the kettle lid mold is not deformed.

[0022] In a second aspect, an embodiment of the present application provides a kettle lid mold deformation detection system, the system comprising:

[0023] The kettle lid mold data acquisition module is used to scan each kettle lid mold multiple times within a preset time using a laser profile scanner, measure the profile data of all scanning points in each scan, and form a profile data vector for each scan. The profile data vectors of all scans form a profile matrix for each kettle lid mold, and the profile matrix is ​​evenly divided into multiple square matrices, wherein the profile data is the distance from the laser beam emitted by the laser profile scanner to all scanning points;

[0024] A kettle lid mold weight acquisition module is used to determine the contour change interval of each square matrix in each kettle lid mold based on the maximum value of all contour data in each square matrix, evenly divide the contour change interval into multiple sub-intervals of equal length, and determine the complexity of each square matrix based on the proportion of all contour data in each sub-interval in each square matrix to all contour data in the square matrix, as well as the degree of discreteness of the number of rows and columns of all contour data in each sub-interval in each square matrix;

[0025] Based on the position distribution of each square matrix in its corresponding profile matrix, determine the square matrix that is positionally symmetric with each square matrix, and record the square matrix that is positionally symmetric with each square matrix as the symmetric square matrix of each square matrix; replace all the profile data in each subinterval of each square matrix with the value of the upper limit of the subinterval, and record all the replaced data as quantized profile data; based on the distribution of all quantized profile data in each square matrix and its symmetric square matrix, and the similarity of all column vectors between each square matrix and its opposite square matrix, determine the symmetry coefficient between each square matrix and its symmetric square matrix, and combine the complexity of each square matrix and its symmetric square matrix to determine the discrimination between each square matrix and its symmetric square matrix;

[0026] The kettle cover mold detection module is used to determine the outlier value of each kettle cover mold based on the difference in the discrimination between all square matrices and their symmetrical square matrices between different measurements, and to detect the kettle cover mold.

[0027] In a third aspect, an embodiment of the present application also provides a kettle cover mold deformation detection device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned kettle cover mold deformation detection methods when executing the computer program.

[0028] As can be seen from the above embodiments, the kettle lid mold deformation detection method provided by the embodiments of the present application has at least the following beneficial effects:

[0029] The present application uses a laser profile scanner to scan each kettle lid mold multiple times within a preset time, measures the profile data of all scanning points in each scan, and forms a profile data vector for each scan. The profile data vectors of all scans constitute a profile matrix of each kettle lid mold, and the profile matrix is ​​evenly divided into a plurality of square matrices; in each kettle lid mold, based on the extreme distribution of all profile data in each square matrix, the profile change interval of each square matrix is ​​determined, the profile change interval is evenly divided into a plurality of sub-intervals, and the complexity of each square matrix is ​​determined based on the proportion of all profile data located in each sub-interval in all profile data in the square matrix, and the degree of discreteness of the number of rows and columns of all profile data located in each sub-interval in each square matrix. The beneficial effect lies in utilizing the correlation characteristics between the profile complexity of the kettle lid mold and the probability of its deformation, and calculating and obtaining a characteristic value reflecting the shape complexity of the kettle lid mold by analyzing the distribution of the size and position of the profile data in the square matrix, thereby enhancing the subsequent detection of the deformation-prone area of ​​the kettle lid mold and improving the sensitivity of deformation detection;

[0030] The present application determines the symmetric matrix of each matrix based on the position distribution of each matrix in its corresponding contour matrix; replaces all contour data in each subinterval of each matrix with the value of the right endpoint of the subinterval, and records all the replaced data as quantized contour data; determines the symmetry coefficient between each matrix and its symmetric matrix based on the distribution of all quantized contour data in each matrix and its symmetric matrix, and the similarity of all column vectors between each matrix and its opposite matrix; and determines the discrimination between each matrix and its symmetric matrix in combination with the complexity of each matrix and its symmetric matrix. The beneficial effect is that the detection capability of subtle deformation in the complex contour area of ​​the kettle lid mold can be enhanced; at the same time, the contour features of the kettle lid mold pot mouth edge are utilized to improve the subsequent detection sensitivity of the deformation of the kettle lid mold pot mouth edge;

[0031] The present application measures multiple times and obtains the degree of distinction between all square matrices of each kettle lid mold and its respective symmetrical square matrices, and based on the difference in the degree of distinction between all square matrices and its respective symmetrical square matrices between different measurements, determines the abnormal value of each kettle lid mold, and inspects the kettle lid mold, thereby improving the accuracy of detecting areas prone to deformation and improving the sensitivity of detecting deformation of the kettle lid mold. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0033] Figure 1 A flowchart of a method for detecting deformation of a kettle lid mold provided in one embodiment of the present application;

[0034] Figure 2 A schematic diagram of a process for constructing a profile matrix according to an embodiment of the present application;

[0035] Figure 3 A schematic diagram of a subinterval division process provided in one embodiment of the present application;

[0036] Figure 4 A schematic diagram of the distribution of quantitative profile data of a kettle lid mold provided in one embodiment of the present application;

[0037] Figure 5 A schematic diagram of the quantitative profile data distribution of the mouth and bottom of a kettle lid mold provided in one embodiment of the present application;

[0038] Figure 6 A flowchart of the discrimination extraction steps provided in one embodiment of the present application;

[0039] Figure 7 A block diagram of a kettle lid mold deformation detection system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0040] To further illustrate the technical means and effectiveness employed by this application to achieve the intended invention objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method, system, and device for detecting deformation of a kettle lid mold, including its specific implementation, structure, features, and effectiveness. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0041] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0042] The following describes in detail a method, system and device for detecting deformation of a kettle lid mold provided by the present application with reference to the accompanying drawings.

[0043] See also Figure 1 , which shows a flowchart of a kettle lid mold deformation detection method provided by one embodiment of the present application, the method comprising the following steps:

[0044] Step S1: Within a preset time, use a laser profile scanner to scan each kettle lid mold multiple times, measure the profile data of all scanning points in each scan, and form a profile data vector for each scan. The profile data vectors of all scans constitute the profile matrix of each kettle lid mold, and the profile matrix is ​​evenly divided into multiple square matrices, where the profile data is the distance from the laser beam emitted by the laser profile scanner to all scanning points.

[0045] Place the kettle lid mold on a horizontal measuring table controlled by a linear motor, install a laser profile scanner above the horizontal measuring table, make the measurement reference line of the laser profile scanner perpendicular to the axis direction of the kettle lid mold, and set the speed of the linear motor to v.

[0046] Within a preset duration, a laser profile scanner is used to scan each kettle lid mold multiple times, obtaining profile data of all scanned points during each scan and forming a profile data vector for each scan. The profile data vectors of all scans are then used to form a profile matrix for each kettle lid mold in ascending order of scan time, and the profile matrix is ​​evenly divided into M square matrices, each of which has W rows and columns. The scanning frequency of the laser scanner is set to f, and the number of profile data obtained during each scan is L. The preset measurement duration is t, and the profile data of the kettle lid mold is scanned and obtained, wherein the number of scans per second of the laser profile scanner is f, and L profile data are obtained during each scan. The profile data is the distance from the laser beam emitted by the laser profile scanner to all scanned points. Since the central axis of the kettle lid mold is parallel to the central axis of the horizontal measuring platform and the projection of the central axis of the kettle lid mold coincides with the horizontal measuring platform, the profile data in the profile matrix are symmetrical about the central axis of the kettle lid mold.

[0047] It should be noted that the speed v of the linear motor, the preset time t, the scanning frequency f, the number of contour data obtained in each scan L, the number of matrix M, and the number of matrix rows and columns W are all set manually. In this embodiment, the speed v of the linear motor is 0.3m / s, the preset time t is 1s, the scanning frequency f is 3000Hz, the number of contour data obtained in each scan L is 3000, the number of matrix M is 50, and the number of matrix rows and columns W is 100. The implementers can also set the data settings according to the specific circumstances, and this embodiment does not impose any special restrictions.

[0048] In addition, it should be understood that in the process of evenly dividing the contour matrix into multiple square matrices, if there are insufficient columns and rows to constitute square matrices of equal size, these columns and rows will not be considered, and the division of the square matrices will be carried out in the order from left to right and from top to bottom according to the contour data in the contour matrix. The implementer may also adopt other division methods. This embodiment does not impose any special restrictions on the specific method of dividing the square matrices.

[0049] Preferably, the schematic diagram of the outline matrix construction process provided in this embodiment is as follows: Figure 2 shown.

[0050] Step S2: In each kettle lid mold, for any measurement, based on the extreme distribution of all contour data in each matrix, determine the contour change interval of each matrix, divide the contour change interval into multiple sub-intervals, and determine the complexity of each matrix based on the proportion of all contour data in each sub-interval in each matrix to all contour data in the matrix, and the degree of discreteness of the number of rows and columns of all contour data in each sub-interval in each matrix.

[0051] Since the kettle lid mold has more sharp corners and thinner walls in the area with greater contour complexity, the probability of deformation during injection molding is greater. It is necessary to obtain the distribution complexity of different matrix contour data to reflect the probability of deformation of the kettle lid mold.

[0052] Therefore, based on the extreme distribution of all contour data in each square matrix, the contour change interval of each square matrix is ​​determined, and the contour change interval is evenly divided into multiple sub-intervals. Based on the proportion of all contour data in each sub-interval in each square matrix, and the degree of discreteness of the number of rows and columns of all contour data in each sub-interval in each square matrix, the complexity of each square matrix is ​​determined to enhance the subsequent detection of deformation-prone areas of the kettle lid mold and improve the accuracy of deformation detection. Specifically:

[0053] (1) In each kettle lid mold, for any measurement, the maximum and minimum values ​​of all contour data in each matrix are used as the upper and lower limits of the contour change interval, respectively, and the contour data change interval is divided into K subintervals of equal length;

[0054] It should be noted that the number of subintervals K is manually set. In this embodiment, the number of subintervals K is 10. The implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions. Wherein, a subinterval is an interval that is open on the left and closed on the right.

[0055] Preferably, the schematic diagram of the subinterval division process provided in this embodiment is as follows: Figure 3 shown.

[0056] (2) Further, based on the proportion of all the contour data in each subinterval in each matrix and the degree of discreteness of the number of rows and columns of all the contour data in each subinterval in each matrix, the complexity of each matrix is ​​determined, specifically:

[0057] The complexity of the matrix i The expression is: Where, 、 They represent the discrete degree of the number of rows and the discrete degree of the number of columns of all the contour data in subinterval k in the matrix i respectively; It represents the proportion of all the contour data in subinterval k in matrix i to all the contour data in matrix i; represents the number of all subintervals within the profile variation interval of matrix i; ln() represents a logarithmic function with a natural constant as its base. It should be noted that there are many methods for measuring the degree of dispersion of a set of data. In this embodiment, the degree of dispersion of the rows and columns of all profile data within the subintervals of the matrix is ​​measured by calculating the coefficient of variation of the rows and columns. Implementers may also use other methods for measuring the degree of data dispersion, such as variance and standard deviation. This embodiment does not impose any particular restrictions on the method used to measure the degree of dispersion of a set of data.

[0058] The calculation steps of the coefficient of variation are well-known techniques, and the specific calculation process will not be described in detail.

[0059] Furthermore, according to the complexity of each square matrix, it can be understood that the greater the proportion of all contour data located in the subinterval of the square matrix in all contour data of the square matrix, the more complex the shape of the corresponding kettle lid mold part is, and the greater the complexity obtained by calculation; the greater the degree of discreteness of the number of rows and columns of all contour data located in the subinterval of the square matrix, the more dispersed the position distribution of the contour data located in the same subinterval of the square matrix is, reflecting that the shape of the kettle lid mold is more complex and the corresponding area is more likely to deform, and the greater the complexity obtained by calculation; conversely, the smaller the proportion of all contour data located in the subinterval of the square matrix in all contour data of the square matrix, the simpler the shape of the corresponding kettle lid mold part is, and the smaller the complexity obtained by calculation; the smaller the degree of discreteness of the number of rows and columns of all contour data located in the subinterval of the square matrix, the more concentrated the position distribution of the contour data located in the same subinterval of the square matrix is, reflecting that the shape of the kettle lid mold is simpler and the corresponding area is less likely to deform, and the smaller the complexity obtained by calculation.

[0060] Step S3: Based on the position distribution of each square matrix in its corresponding contour matrix, determine the symmetric square matrix of each square matrix; replace all contour data in each subinterval of each square matrix with the value of the right endpoint of the subinterval, and record all replaced data as quantized contour data. Based on the distribution of all quantized contour data in each square matrix and its symmetric square matrix, and the similarity of all column vectors between each square matrix and its opposite square matrix, determine the symmetry coefficient between each square matrix and its symmetric square matrix, and combine the complexity of each square matrix and its symmetric square matrix to determine the discrimination between each square matrix and its symmetric square matrix.

[0061] In the contour matrix of each kettle lid mold, the contour data is symmetrically distributed about the central axis of the mold, according to the shape of the mold. If matrix D and matrix E are mirror-symmetrical about the central axis of the mold, then matrix D and matrix E are positionally symmetrical, and matrix D is recorded as the symmetrical matrix of matrix E (or matrix E is recorded as the symmetrical matrix of matrix D). When a certain area in the mold deforms, the similarity between the contour data of the corresponding matrix and its symmetrical matrix decreases. In addition, the mouth of the kettle lid mold has a relatively complex shape, and the small threaded protrusions are easily deformed during demolding. Moreover, the mouth of the mold has a significant impact on the sealing performance of the kettle lid after injection molding, necessitating enhanced deformation detection. At the same time, near the mouth of the kettle lid mold, the distribution of the contour data in the square matrix changes greatly, and two relatively obvious peaks appear in the contour data. The closer the heights of the two peaks are, the closer the proportions of the contour data corresponding to the top and bottom of the pot mouth in the square matrix are, and the more likely the contour data in the square matrix are the data measured at the mouth of the kettle lid mold. Preferably, the schematic diagram of the quantitative contour data distribution of the kettle lid mold provided in this embodiment is as follows: Figure 4 As shown, Figure 4 The horizontal axis represents the quantitative contour data, in mm; the vertical axis represents the frequency, dimensionless. Figure 5 As shown, Figure 5 The horizontal axis represents the quantitative profile data in mm; the vertical axis represents the frequency, which is dimensionless.

[0062] Therefore, based on the distribution of all quantized contour data in each matrix and its symmetric matrix, as well as the similarity of all column vectors between each matrix and its symmetric matrix, the symmetry coefficient between each matrix and its symmetric matrix is ​​determined. In addition, combined with the complexity of each matrix and its symmetric matrix, the discrimination between each matrix and its symmetric matrix is ​​determined to improve the detection sensitivity of the deformation of the kettle lid mold mouth edge. Specifically:

[0063] (1) Replace all the contour data in each subinterval in each matrix with the upper limit value of the subinterval, and record all the replaced data as quantitative contour data;

[0064] All quantized contour data of each matrix are used as input of the maximum inter-class variance algorithm, and the maximum inter-class variance of each matrix is ​​output;

[0065] The maximum inter-class variance algorithm is a well-known technology, and the specific process of calculating the maximum inter-class variance will not be described in detail.

[0066] (2) Further, based on the distribution of all quantized profile data in each matrix and its symmetric matrix, as well as the similarity of all column vectors between each matrix and its symmetric matrix, the symmetry coefficient between each matrix and its symmetric matrix is ​​determined, specifically:

[0067] Symmetry coefficient between matrix i and its symmetric matrix The expression is: Where, It represents the sum of the maximum inter-class variance of matrix i and the maximum inter-class variance of the symmetric matrix of matrix i; Represents the j-th column vector of matrix i and the j-th column vector of the symmetric matrix of matrix i The similarity between column vectors; W represents the total number of columns in each matrix; norm() represents the normalization function.

[0068] It should be understood that the norm normalization here is to normalize the sum of the maximum inter-class variance of matrix i and the maximum inter-class variance of the symmetric matrix of matrix i. Each matrix has a , and normalize it. In addition, there are many commonly used normalization functions. The linear normalization method is used in this embodiment. The implementer can also use other normalization methods such as the maximum and minimum value normalization method. Regarding the selection of the normalization method, this embodiment does not impose any special restrictions.

[0069] Among them, the linear normalization method is a well-known technology, and the specific process of normalizing the data is not described again.

[0070] It should be noted that there are many methods for measuring the similarity between vectors. In this embodiment, the similarity between the jth column vector of the matrix i and the jth column vector of the symmetric matrix of the matrix i is calculated. The cosine similarity between column vectors is used to measure the similarity between column vectors. The implementer may also use other methods that can measure the similarity between vectors, such as the inverse of the Euclidean distance. This embodiment does not impose any special restrictions on the selection of the method for measuring the similarity between vectors.

[0071] The calculation process of cosine similarity is a well-known technology, and its specific calculation steps are not repeated here.

[0072] Furthermore, according to the symmetry coefficient between each square matrix and its symmetric square matrix, it can be understood that the greater the similarity between the square matrix and the column vectors in its symmetric square matrix that are symmetrical about the axis of the kettle lid mold, the greater the degree of symmetry between the two, and the larger the calculated symmetry coefficient; when the mold area corresponding to the square matrix is ​​deformed, the symmetry coefficient will become smaller, thereby detecting the mold deformation. In addition, in order to strengthen the deformation detection of the edge of the mold mouth, the sum of the maximum inter-class variances of the square matrix and the symmetric square matrix is ​​used as the weight, and the larger the sum of the maximum inter-class variances, the greater the probability that the square matrix is ​​at the edge of the pot mouth, and the larger the calculated symmetry coefficient; at the same time, when the pot mouth edge of the kettle lid mold is deformed, the change in the symmetry coefficient is large. The contour features of the pot mouth edge of the kettle lid mold are used to amplify the change in the symmetry coefficient when deformation occurs, thereby improving the subsequent detection sensitivity of the deformation of the pot mouth edge of the kettle lid mold; conversely, the smaller the similarity between the column vectors of the square matrix and its symmetric square matrix that are symmetrical about the axis of the kettle lid mold, the smaller the degree of symmetry between the two, and the smaller the calculated symmetry coefficient; the smaller the sum of the maximum inter-class variances of the square matrix and the symmetric square matrix, the smaller the calculated symmetry coefficient.

[0073] (3) Further, the sum of the complexity of each matrix and its symmetric matrix is ​​calculated, and the ratio of the sum to the symmetry coefficient is used as the discrimination between each matrix and its symmetric matrix.

[0074] Based on the discrimination between each matrix and its symmetrical matrix, it can be understood that when the kettle lid mold deforms, the similarity between the matrix and its symmetrical matrix's contour data decreases, the symmetry coefficient decreases, and the calculated discrimination increases. Furthermore, when the complexity of the matrix and its symmetrical matrix in reflecting the complexity of the kettle lid mold's shape increases, the probability of deformation in the corresponding area of ​​the kettle lid mold increases, and the calculated discrimination increases. Consequently, when the corresponding area of ​​the mold deforms, the change in discrimination is large, facilitating subsequent and timely detection of mold deformation. Conversely, when the kettle lid mold does not deform, the similarity between the matrix and its symmetrical matrix's contour data increases, the symmetry coefficient increases, and the calculated discrimination decreases. Furthermore, when the complexity of the matrix and its symmetrical matrix in reflecting the complexity of the kettle lid mold's shape decreases, the probability of deformation in the corresponding area of ​​the kettle lid mold decreases, and the calculated discrimination decreases.

[0075] Preferably, the flowchart of the discrimination extraction step provided in this embodiment is as follows: Figure 6 shown.

[0076] Step S4: perform multiple measurements and obtain the discrimination between all square matrices of each kettle lid mold and its respective symmetrical square matrices under different measurements, and determine the abnormal value of each kettle lid mold based on the difference in the discrimination between all square matrices and their respective symmetrical square matrices between different measurements, and detect the kettle lid mold.

[0077] In order to improve the accuracy of kettle lid mold detection, steps S1-S3 are performed multiple times to obtain the discrimination between all square matrices and their respective symmetrical square matrices in each kettle lid mold under multiple measurements. Based on the difference in the discrimination between all square matrices and their respective symmetrical square matrices between different measurements, the outlier value of each kettle lid mold is determined, specifically:

[0078] For the convenience of expression, the discrimination between each matrix and its symmetrical matrix is ​​simply recorded as the discrimination of each matrix. In each kettle lid mold, the difference between the discrimination of any two matrixes in all measurements is calculated and recorded as the inter-matrix difference between any two matrixes. The normalized result of the inter-matrix difference between all pairwise combinations is taken as the outlier of each kettle lid mold.

[0079] It should be noted that there are many methods for measuring the differences between data groups. In this embodiment, the DTW distance between the discrimination of any two matrices in all measurements is calculated to measure the difference between the discrimination of any two matrices and their corresponding matrices in all measurements. The implementer may also use other methods for measuring the differences between data groups, such as Euclidean distance and Manhattan distance. This embodiment does not impose any special restrictions on the selection of methods for measuring the differences between data groups.

[0080] The calculation process of the DTW distance is a well-known technique, and its specific calculation steps are not repeated here. In this embodiment, the number of measurements is set to 50, and the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0081] The greater the difference in the degree of distinction between all square matrices in each kettle lid mold and its symmetric square matrices between all measurements, the greater the probability that the kettle lid mold will be deformed, and the larger the calculated outlier value; conversely, the smaller the difference in the degree of distinction between all square matrices in each kettle lid mold and its symmetric square matrices between all measurements, the smaller the probability that the kettle lid mold will be deformed, and the smaller the calculated outlier value.

[0082] Furthermore, the mean of the outlier values ​​of all kettle lid molds is used as the deformation threshold. If the outlier value of the kettle lid mold is greater than the deformation threshold, the kettle lid mold is deformed. Conversely, if the outlier value of the kettle lid mold is greater than the deformation threshold but less than or equal to the deformation threshold, the kettle lid mold is not deformed.

[0083] Based on the same inventive concept as the above method, the embodiment of the present application further provides a kettle lid mold deformation detection system, comprising:

[0084] The kettle lid mold data acquisition module is used to scan each kettle lid mold multiple times within a preset time using a laser profile scanner, measure the profile data of all scanning points in each scan, and form a profile data vector for each scan. The profile data vectors of all scans form a profile matrix for each kettle lid mold, and the profile matrix is ​​evenly divided into multiple square matrices, wherein the profile data is the distance from the laser beam emitted by the laser profile scanner to all scanning points;

[0085] A kettle lid mold weight acquisition module is used to determine the contour change interval of each square matrix in each kettle lid mold based on the maximum value of all contour data in each square matrix, evenly divide the contour change interval into multiple sub-intervals of equal length, and determine the complexity of each square matrix based on the proportion of all contour data in each sub-interval in each square matrix to all contour data in the square matrix, as well as the degree of discreteness of the number of rows and columns of all contour data in each sub-interval in each square matrix;

[0086] Based on the position distribution of each square matrix in its corresponding profile matrix, determine the square matrix that is positionally symmetric to each square matrix; replace all profile data in each subinterval of each square matrix with the value of the upper limit of the subinterval, and record all the replaced data as quantized profile data; based on the distribution of all quantized profile data in each square matrix and its symmetric square matrix, and the similarity of all column vectors between each square matrix and its opposite square matrix, determine the symmetry coefficient between each square matrix and its symmetric square matrix, and combine the complexity of each square matrix and its symmetric square matrix to determine the discrimination between each square matrix and its symmetric square matrix;

[0087] The kettle cover mold detection module is used to determine the outlier value of each kettle cover mold based on the difference in the discrimination between all square matrices and their symmetrical square matrices between different measurements, and to detect the kettle cover mold.

[0088] The embodiment of the present application provides a block diagram of a kettle lid mold deformation detection system, such as Figure 7 shown.

[0089] Based on the same inventive concept as the above method, an embodiment of the present application also provides a kettle cover mold deformation detection device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned kettle cover mold deformation detection methods are implemented.

[0090] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0092] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for detecting deformation of a kettle cover mold, characterized in that: The method comprises the following steps: Within a preset time, each kettle lid mold is scanned multiple times by using a laser profile scanner, the profile data of all scanning points in each scan are measured, and the profile data vectors of each scan are formed, the profile data vectors of all scans form a profile matrix of each kettle lid mold, and the profile matrix is ​​evenly divided into multiple square matrices, wherein the profile data is the distance from the laser beam emitted by the laser profile scanner to all scanning points; In each kettle lid mold, based on the maximum value of all contour data in each square matrix, the contour change interval of each square matrix is ​​determined, and the contour change interval is evenly divided into multiple sub-intervals of equal length. Based on the proportion of all contour data in each sub-interval in each square matrix in all contour data in the square matrix, and the degree of discreteness of the number of rows and columns of all contour data in each sub-interval in each square matrix, the complexity of each square matrix is ​​determined; Based on the position distribution of each square matrix in its corresponding contour matrix, determine the square matrix that is positionally symmetrical with each square matrix, and record the square matrix that is positionally symmetrical with each square matrix as the symmetric square matrix of each square matrix; replace all contour data in each sub-interval of each square matrix with the value of the upper limit of the sub-interval, record all the replaced data as quantized contour data, and based on the distribution of all quantized contour data in each square matrix and its symmetric square matrix, and the similarity of all column vectors between each square matrix and its opposite square matrix, determine the symmetry coefficient between each square matrix and its symmetric square matrix, and combine the complexity of each square matrix and its symmetric square matrix to determine the discrimination between each square matrix and its symmetric square matrix; Based on the difference in the degree of distinction between all square arrays and their symmetrical square arrays in different measurements, the outlier value of each kettle lid mold is determined and the kettle lid mold is tested.

2. A method for detecting deformation of a kettle cover mold as claimed in claim 1, characterized in that: The method for determining the contour change interval of each square matrix is: The maximum and minimum values ​​of all contour data in each square matrix are used as the upper and lower limits of the contour change range respectively.

3. A kettle cover mold deformation detection method as claimed in claim 1, characterized in that: The expression of the complexity of each square matrix is: ; In the formula, represents the complexity of square matrix i; , They represent the discrete degree of the number of rows and the discrete degree of the number of columns of all contour data in subinterval k in square matrix i respectively; It represents the proportion of all contour data in subinterval k in square matrix i to all contour data in square matrix i; represents the number of all subintervals in the contour change interval of square matrix i; ln( ) represents the logarithmic function with a natural constant as the base.

4. A kettle cover mold deformation detection method as claimed in claim 1, characterized in that: The step of determining a square matrix that is positionally symmetrical to each square matrix comprises: In the contour matrix of each kettle lid mould, the contour data are symmetrically distributed about the central axis of the kettle lid mould according to the shape of the kettle lid mould. If the square matrix D and the square matrix E are mirror-symmetrical about the central axis of the kettle lid mould, then the square matrix D and the square matrix E are positionally symmetrical to each other.

5. A kettle cover mold deformation detection method as claimed in claim 1, characterized in that: The method for determining the symmetry coefficient between each square matrix and its symmetric square matrix is: All quantized contour data of each square matrix are used as the input of the maximum inter-class variance algorithm, and the maximum inter-class variance of each square matrix is ​​output; Symmetry coefficient between matrix i and its symmetric matrix The expression is: ; In the formula, It represents the sum of the maximum between-class variance of matrix i and the maximum between-class variance of the symmetric matrix of matrix i; Represents the jth column vector of square matrix i and the jth column vector of the symmetric square matrix of square matrix i The similarity between column vectors; W represents the total number of columns in each square matrix; norm() represents the normalization function.

6. A kettle cover mold deformation detection method as claimed in claim 1, characterized in that: The method for determining the degree of distinction between each square matrix and its symmetric square matrix is: The sum of the complexity of each square matrix and its symmetric square matrix is ​​calculated, and the ratio of the sum to the symmetry coefficient is used as the discrimination between each square matrix and its symmetric square matrix.

7. A method for detecting deformation of a kettle cover mold as claimed in claim 1, characterized in that: The outlier value of each kettle cover mold is a normalized result of taking the average of the differences between all measurements of the discrimination between all square matrices and their symmetric square matrices in each kettle cover mold.

8. A method for detecting deformation of a kettle cover mold as claimed in claim 1, characterized in that: The process of detecting the kettle cover mold is as follows: The mean of the outliers of all kettle cover molds is taken as the deformation threshold. If the outlier value of the kettle cover mold is greater than the deformation threshold, the kettle cover mold is deformed; otherwise, the kettle cover mold is not deformed.

9. A kettle cover mold deformation detection system, implementing a kettle cover mold deformation detection method as claimed in any one of claims 1 to 8, characterized in that: The system comprises: The kettle cover mold data acquisition module is used to use a laser profile scanner to scan each kettle cover mold multiple times within a preset time, measure the profile data of all scanning points in each scan, and form a profile data vector for each scan, and the profile data vectors of all scans constitute a profile matrix of each kettle cover mold, and evenly divide the profile matrix into multiple square matrices, wherein the profile data is the distance from the laser beam emitted by the laser profile scanner to all scanning points; A kettle cover mold weight acquisition module is used to determine the contour change interval of each square matrix in each kettle cover mold based on the maximum value of all contour data in each square matrix, evenly divide the contour change interval into multiple sub-intervals of equal length, and determine the complexity of each square matrix based on the proportion of all contour data in each sub-interval in each square matrix in all contour data in the square matrix, and the discrete degree of the number of rows and columns of all contour data in each sub-interval in each square matrix; Based on the position distribution of each square matrix in its corresponding contour matrix, determine the square matrix that is positionally symmetrical with each square matrix, and record the square matrix that is positionally symmetrical with each square matrix as the symmetric square matrix of each square matrix; replace all contour data in each sub-interval of each square matrix with the value of the upper limit of the sub-interval, record all the replaced data as quantized contour data, and based on the distribution of all quantized contour data in each square matrix and its symmetric square matrix, and the similarity of all column vectors between each square matrix and its opposite square matrix, determine the symmetry coefficient between each square matrix and its symmetric square matrix, and combine the complexity of each square matrix and its symmetric square matrix to determine the discrimination between each square matrix and its symmetric square matrix; The kettle cover mold detection module is used to determine the abnormal value of each kettle cover mold based on the difference between the discrimination between all square arrays and their symmetrical square arrays in different measurements, and detect the kettle cover mold.

10. A kettle cover mold deformation detection device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a kettle cover mold deformation detection method as described in any one of claims 1-8 are implemented.

Images