Profile product specification control method and device

Abstract

The invention relates to the technical field of process control, in particular to a profile product specification control method and device, and the method comprises the steps: constructing a specification control matrix according to product specification parameters and process control parameters; taking the comprehensive efficacy coefficients of the product specification parameters and the process control parameters as clustering parameters, and performing hierarchical clustering on the specification control matrix to obtain a plurality of process control parameter clusters corresponding to each product specification parameter in the specification control matrix; grading the product specification parameters according to the historical product specification parameters; determining a process control parameter cluster corresponding to each grade of product specification parameter, and calculating a weight distribution proportion of the process control parameter cluster of each grade; and adjusting the specification of the profile product according to the specification control matrix and the weight distribution proportion. According to the technical scheme provided by the invention, the relationship between the profile product specification parameters and the process control parameters can be quantitatively evaluated, so that the product specification control fluctuation can be effectively reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of process control, and particularly to a method and device for controlling the specifications of profile products. Background Art

[0002] Profiles refer to solid straight bars formed by plastic processing of metals with certain cross-sectional shapes and dimensions. Profiles are objects with certain geometric shapes made of iron, steel, or materials with certain strength and toughness through processes such as rolling, extrusion, and casting. The specifications of profile products are closely related to process control. Currently, during the production process of profiles, the in-plant control of product specifications mainly relies on manual adjustment, with a low qualified rate in one adjustment, large accidental errors in manual calculation, high technical inheritance costs, and large fluctuations in the specification dimensions of qualified products. Summary of the Invention

[0003] The present disclosure aims to solve at least one of the technical problems in the above technologies to some extent. For this purpose, the present disclosure proposes a method for controlling the specifications of profile products, including:

[0004] Constructing a specification control matrix based on product specification parameters and process control parameters;

[0005] Taking the comprehensive efficacy coefficient of product specification parameters and process control parameters as the clustering parameter, performing hierarchical clustering on the specification control matrix to obtain several process control parameter clusters corresponding to each product specification parameter in the specification control matrix;

[0006] Classifying the product specification parameters according to historical product specification parameters;

[0007] Determining the process control parameter clusters corresponding to each level of product specification parameters, and calculating the weight distribution ratio of each level of process control parameter clusters;

[0008] Adjusting the specifications of profile products according to the specification control matrix and the weight distribution ratio.

[0009] Further, the constructing a specification control matrix based on product specification parameters and process control parameters includes: selecting a target historical product with the smallest difference degree from the target specification parameters among several historical products, and constructing a specification control matrix according to the specification parameters and process control parameters of the target historical product.

[0010] Further, after constructing a specification control matrix according to the specification parameters and process control parameters of the target historical product, it further includes: adjusting the matrix elements of the specification control matrix based on the subjective weighting method.

[0011] Further, the calculation formula of the comprehensive efficacy coefficient of product specification parameters and process control parameters includes:

[0012]

[0013] Among them, ρ ij represents the comprehensive efficacy coefficient of product specification parameters and process control parameters, ‖ΔY i ‖ represents the modulus of the change amount of the i-th product specification parameter; ||ΔX j || represents the modulus of the change amount of the j-th process control parameter; a j represents the weight of the j-th process control parameter.

[0014] Furthermore, the grading of product specification parameters according to historical product specification parameters includes:

[0015] Obtain historical product specification parameters and perform anomaly filtering on them;

[0016] According to the filtered historical product specification parameters, calculate the confidence interval of each product specification parameter and the sigma level of each product specification parameter;

[0017] Take the maximum value of the absolute values of the upper and lower limits of the confidence intervals of all product specification parameters as the grading upper limit of the product specification parameters, and take the maximum value of the sigma levels of all product specification parameters as the grading interval of the product specification parameters;

[0018] Calculate the grading number of product specification parameters and the upper and lower limits of each grade of product specification parameters according to the grading upper limit and grading interval, and the corresponding formulas include:

[0019]

[0020] LL n =(z - 1)·d

[0021] LH n =z·d

[0022] Among them, C represents the grading number; floor represents the floor function; H MAX represents the grading upper limit; d represents the grading interval; LL n represents the lower limit of the product specification parameter grade; LH n represents the upper limit of the product specification parameter grade; z represents the grade number.

[0023] Furthermore, determining the process control parameter clusters corresponding to each grade of product specification parameters and calculating the weight distribution ratio of each grade of process control parameter clusters includes:

[0024] Calculate the number of types of process control parameters corresponding to each grade of product specification parameters;

[0025] Select process control parameter clusters equal to the number of types of process control parameters for each grade of product specifications in descending order of the comprehensive efficacy coefficient;

[0026] Calculate the weight distribution ratio of the process control parameter clusters for each grade;

[0027] Among them, the calculation formula corresponding to the weight distribution ratio includes:

[0028]

[0029] Among them, ρ if is the comprehensive efficacy coefficient value of the f-th cluster center point of the i-th specification; λ kf represents the weight distribution ratio, k ∈ [1, K], K represents the number of types of process control parameters corresponding to the product specification parameters; the calculation formula for the number of types of process control parameters includes:

[0030]

[0031] Among them, M m represents the number of clustering types of the m-th product specification parameter.

[0032] Furthermore, adjusting the profile product specifications according to the specification control matrix and the weight distribution ratio includes:

[0033] Take the difference between the profile product specification parameters and the standard parameters as the specification parameter error amount;

[0034] Process each specification parameter error amount in turn according to the descending order of the comprehensive efficacy coefficient, including: when it is determined that the specification parameter error amount is greater than the threshold, determine the level of the specification parameter error amount and the corresponding weight distribution ratio, and calculate the process control parameter value according to the boundary conditions of the process control parameters and the specification control matrix;

[0035] Predict the product specification parameter error amount according to the calculated process control parameter value, and calculate the predicted product specification and the specification parameter residual amount;

[0036] Repeat the above method until all specification parameter error amounts are less than the threshold or the traversal ends;

[0037] When all specification parameter error amounts are less than the threshold, adjust the profile product specifications according to the current process control parameter value; when the traversal ends, adjust the profile product specifications according to the process control parameter value corresponding to the minimum specification parameter residual amount.

[0038] The present disclosure also proposes a profile product specification control system, including:

[0039] A matrix construction module for constructing a specification control matrix according to product specification parameters and process control parameters;

[0040] A hierarchical clustering module for using the comprehensive efficacy coefficients of product specification parameters and process control parameters as clustering parameters to perform hierarchical clustering on the specification control matrix to obtain several process control parameter clusters corresponding to each product specification parameter in the specification control matrix;

[0041] A parameter grading module for grading product specification parameters according to historical product specification parameters;

[0042] A weight calculation module for determining the process control parameter clusters corresponding to product specification parameters of each grade and calculating the weight distribution ratio of the process control parameter clusters of each grade;

[0043] A specification adjustment module for adjusting the profile product specification according to the specification control matrix and the weight distribution ratio.

[0044] The present disclosure also provides an electronic device, including a memory and a processor, wherein a computer program / instructions are stored in the memory; the processor is used to execute the computer program / instructions; when the computer program / instructions are executed by the processor, it is at least used to implement the above-mentioned profile product specification control method.

[0045] The present disclosure also provides a computer-readable storage medium, wherein a computer program / instructions are stored in the computer-readable storage medium, and when the computer program / instructions are executed by a processor, it is at least used to implement the above-mentioned profile product specification control method.

[0046] Compared with the prior art, the beneficial effects of the present disclosure are:

[0047] The profile product specification control method provided by the present disclosure can solve the problems of low qualification rate of the first adjustment of profile rolling and low calculation efficiency of manual adjustment by constructing a specification control matrix based on historical product data, quantifying and evaluating the relationship between profile product specification parameters and process control parameters, improving the adjustment timeliness, reducing the accidental error of manual calculation, and at the same time improving the standardization of steel rolling adjustment and effectively reducing the product specification control fluctuation between teams.

[0048] Other features and advantages of the present disclosure will be described in the following specification, and some of them will become obvious from the specification, or be understood by implementing the present disclosure. The objectives and other advantages of the present disclosure can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0049] The technical solutions of the present disclosure will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0050] The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation to the present disclosure. In the accompanying drawings:

[0051] Figure 1 It is a schematic diagram of the profile product specification control method given by the embodiment of the present disclosure;

[0052] Figure 2 It is a schematic diagram of the profile product specification control system given by the embodiment of the present disclosure;

[0053] Figure 3 It is a schematic diagram of the electronic device given by the embodiment of the present disclosure;

[0054] Figure 4 It is a schematic diagram of the computer-readable storage medium given by the embodiment of the present disclosure. Detailed implementation manners

[0055] The following describes the preferred embodiments of the present disclosure with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present disclosure and are not used to limit the present disclosure.

[0056] Figure 1 The profile product specification control method given by the present disclosure includes:

[0057] S101. Construct a specification control matrix according to product specification parameters and process control parameters;

[0058] S102. Use the comprehensive efficacy coefficient of product specification parameters and process control parameters as the clustering parameter, perform hierarchical clustering on the specification control matrix, and obtain several process control parameter clusters corresponding to each product specification parameter in the specification control matrix;

[0059] S103. Grade the product specification parameters according to historical product specification parameters;

[0060] S104. Determine the process control parameter clusters corresponding to each grade of product specification parameters, and calculate the weight distribution ratio of each grade of process control parameter clusters;

[0061] S105. Adjust the profile product specifications according to the specification control matrix and the weight distribution ratio.

[0062] According to some embodiments of the present disclosure, constructing a specification control matrix based on product specification parameters and process control parameters includes: selecting a target historical product with the smallest difference degree from the target specification parameters among several historical products, constructing a specification control matrix according to the specification parameters and process control parameters of the target historical product, and adjusting the matrix elements of the specification control matrix based on the subjective weighting method. In some other embodiments of the present disclosure, constructing a specification control matrix according to product specification parameters and process control parameters includes:

[0063] (1) According to the production data of specification control for each work team, statistically obtain a historical specification control ranking table, and select the work team with the best specification control as the object.

[0064] (2) According to the actual production data of this work team, establish a specification control matrix, and give a specification control matrix table Am*n, where m represents the number of product specification parameters, and n represents the number of process control parameters. For example, as shown in Table 1 below:

[0065] Table 1

[0066] Rail height Web thickness Fullness Top width Bottom width Base width E1 first pass rolling line offset 0.0 0.0 0.0 0.0 0.0 0.0 E1 first pass horizontal roll gap 0.0 0.1 0.0 0.2 0.2 0.4 E1 first pass upper roll tilt 0.0 0.0 0.0 0.0 0.0 0.0 E1 second pass rolling line offset 0.0 0.0 0.0 0.0 0.0 0.0 E1 second pass horizontal roll gap 0.1 0.1 0.0 0.2 0.2 0.4 E1 second pass upper roll tilt 0.0 0.0 0.0 0.0 0.0 0.0 E1 lower roll axial offset 0.0 0.0 0.0 0.0 0.0 0.0 E1 third pass rolling line offset 0.0 0.0 0.0 0.0 0.0 0.0 E1 third pass horizontal roll gap 0.1 0.1 0.0 0.2 0.2 0.5 E1 third pass upper roll tilt 0.0 0.0 0.0 0.0 0.0 0.0

[0067] (3) Based on the above specification control matrix table, in the form of a meeting interview, adjust the matrix elements of the specification control matrix according to the subjective weighting method.

[0068] In some other embodiments of the present disclosure, after obtaining the specification control matrix, it further includes:

[0069] (1) Based on historical production data, that is, the data on the change of product specification data after each change of process control parameters, calculate the comprehensive efficacy coefficient between the change amount of each specification parameter and the adjustment amount of the process control parameter in each adjustment data, that is, the comprehensive efficacy coefficient.

[0070] (2) Sort the comprehensive efficacy coefficients in descending order. The product specification parameters with equal comprehensive efficacy coefficients are randomly sorted at adjacent positions, and finally a product specification parameter adjustment order table is obtained. For example, as shown in Table 2 below:

[0071] Table 2

[0072] Adjustment sequence 1 2 3 4 5 6 Specification parameters Web thickness Top width Bottom width Fullness Base width Rail height Efficiency coefficient 0.8 0.6 0.6 0.5 0.5 0.4

[0073] According to some embodiments of the present disclosure, the calculation formula for the comprehensive efficacy coefficient of product specification parameters and process control parameters includes:

[0074]

[0075] Among them, ρ ij represents the comprehensive efficacy coefficient of product specification parameters and process control parameters, ‖ΔY i‖ represents the modulus value of the change in the i-th product specification parameter; ||ΔX j || represents the modulus value of the change in the j-th process control parameter; a j represents the weight of the j-th process control parameter, ∑a j = 1, where a j can take the Poisson comprehensive efficacy coefficient.

[0076] According to some embodiments of the present disclosure, hierarchical clustering of the specification control matrix is performed, including: based on historical production data, calculating the comprehensive efficacy coefficient ρ of the product specification parameters and the process control parameters ij , establishing an index table of the process control parameters and the comprehensive efficacy coefficient for each product specification parameter, and according to the clustering algorithm, using the ρ of each specification ij as the clustering parameter, the number of clustering categories of each product specification parameter is M i , M i ∈[1,n], performing hierarchical clustering on the data in the index table to form an index table with clustering labels, and sorting the index table according to the size of ρ ig to form a process control parameter clustering table for each product specification parameter, ρ ig is the comprehensive efficacy coefficient value of the g-th cluster center point of the i-th specification, g ∈[1,M i , the number of adjustment factors contained in each category is T g , T g ∈[1,n], for example, as shown in Table 3 below, the process control parameter clustering table for some specification parameters of the rail. Taking the rail height as an example, M1 = 5, and the first process control parameter cluster contains the U2 drive side roll gap, whose comprehensive efficacy coefficient is 0.8, and the UF operation side roll gap, whose comprehensive efficacy coefficient is 1.

[0077] Table 3

[0078]

[0079] According to some embodiments of the present disclosure, grading of the product specification parameters is performed according to the historical product specification parameters, including: obtaining historical product specification parameter data and filtering out anomalies therefrom; according to the filtered historical product specification parameters, calculating the confidence interval [L, H] of each product specification parameter, where L is the lower confidence limit and H is the upper confidence limit, and calculating the sigma level σ of each product specification parameter i ; taking the maximum value of the absolute values of the upper and lower limits of the confidence intervals of all product specification parameters as the grading upper limit H MAX of the product specification parameters, that is, the expression of H MAX is H MAX = MAX[MAX[|L1|, H1],..., MAX[|L m |, H m, the maximum value among the sigma levels of all product specification parameters is used as the grading interval of the product specification parameters. That is, the expression for d is d = MAX[σ1,..., σ m ; Calculate the number of grading levels of the product specification parameters and the upper and lower limits of each grade of product specification parameters according to the grading upper limit and the grading interval. The corresponding formulas include:

[0080]

[0081] LL n =(z - 1)·d

[0082] LH n =z·d

[0083] Among them, C represents the number of grading levels; floor represents the floor function; H MAX represents the grading upper limit; d represents the grading interval; LL n represents the lower limit of the product specification parameter grade; LH n represents the upper limit of the product specification parameter grade; z represents the grade number.

[0084] Taking some specification parameters of the rail as an example, the confidence interval of the rail height increment is [-0.5 mm, 0.5 mm], the bottom width is [-0.7 mm, 0.7 mm], the sigma level of the rail height is 0.3 mm, and the sigma level of the bottom width is 0.4 mm. Therefore, the grading upper limit HMAX = 0.7 mm, the grading interval d = 0.4 mm, the number of grading levels C = 2, the lower limit of the first level LLn = 0 mm, the upper limit of the first level LLn = 0.4 mm, the lower limit of the second level LLn = 0.4 mm, and the upper limit of the second level LLn = 0.8 mm.

[0085] In the actual production process, according to the control of the finishing mill with small adjustment amount, the combined control of multiple rolling mills before and after large adjustment amount, and the fact that the grade adjustment factor of small adjustment amount is less and the grade adjustment factor of large adjustment amount is more, it is necessary to select the process control parameters that have a greater impact on the product specification parameters during adjustment. Therefore, according to some embodiments of the present disclosure, determine the process control parameter clusters corresponding to each grade of product specification parameters, and calculate the weight distribution ratio of each grade of process control parameter clusters, including: calculating the number of types of process control parameters corresponding to each grade of product specification parameters; selecting the process control parameter clusters equal to the number of types of process control parameters for each grade of product specification parameters in the order from large to small of the comprehensive efficacy coefficient, that is, the product specification parameter adjustment order table above; calculating the weight distribution ratio of each grade of process control parameter clusters; among them, the calculation formula corresponding to the weight distribution ratio includes:

[0086]

[0087] Among them, ρ ifis the comprehensive efficacy coefficient value of the f-th cluster center point for the i-th specification; λ kf represents the weight distribution ratio, k ∈ [1, K], where K represents the number of types of process control parameters corresponding to the product specification parameters; the calculation formula for the number of types of process control parameters includes:

[0088]

[0089] where M m represents the number of clustering types of the m-th product specification parameter.

[0090] Exemplarily, the weight coefficient distribution table obtained according to the above process is shown in Table 4:

[0091] Table 4

[0092] Grade Grade lower limit Grade upper limit The first cluster The second cluster The third cluster The fourth cluster The fifth cluster 1 0 0.1 1 0 0 0 0 2 0.1 0.2 0.5 0.5 0 0 0 3 0.2 0.3 0.4 0.3 0.3 0 0 4 0.3 0.5 0.3 0.3 0.2 0.2 0 5 0.5 0.7 0.2 0.2 0.2 0.2 0.2

[0093] According to some embodiments of the present disclosure, adjusting the profile product specifications according to the specification control matrix and the weight distribution ratio includes:

[0094] Taking the difference between the profile product specification parameter and the standard parameter as the specification parameter error amount; according to the order from large to small of the comprehensive efficacy coefficient, that is, traversing the specification adjustment sequence index table, processing each specification parameter error amount in turn, including:

[0095] When it is determined that the specification parameter error amount is greater than the threshold, determining the level of the specification parameter error amount and the corresponding weight distribution ratio, and calculating the process control parameter value according to the boundary conditions of the process control parameters and the specification control matrix;

[0096] Predicting the product specification parameter error amount according to the calculated process control parameter value, and calculating the predicted product specification parameter and the specification parameter residual amount;

[0097] Repeating the above method until all specification parameter error amounts are less than the threshold or the traversal ends;

[0098] When all specification parameter error amounts are less than the threshold, adjusting the profile product specifications according to the current process control parameter value; when the traversal ends, adjusting the profile product specifications according to the process control parameter value corresponding to the minimum specification parameter residual amount.

[0099] In some other embodiments of the present disclosure, the process of optimizing the adjustment of the process control parameters includes: calculating the actual adjustment amount of each specification {ΔY i} according to the difference between the actual value of the specification and the control standard value; traversing the specification adjustment sequence index table, if the current specification parameter adjustment amount is greater than a certain threshold, then taking this specification as the adjustment object; according to the weight distribution ratio table, selecting the process control parameter and the weight ratio of the specification parameter to be adjusted, calculating the value of the adjustment factor using the specification control matrix, and the calculation equation is for example {ΔYi} = A m*n *λ*{ΔX j}, where λ is the weight distribution ratio matrix, and λ is composed of λ kf The approximate solution {ΔX j} is obtained by using the simplex method, and a process control parameter adjustment scheme is obtained. At the same time, the approximate solution is substituted into the previous equation to obtain the predicted {ΔY i}. At the same time, the process control parameter adjustment scheme and the specification residual ||ΔYi|| are recorded, and the adjustment amount {ΔY i} of each product specification parameter is calculated according to the specification predicted value and the control standard; then return to the step of traversing the specification adjustment order index table. If the specification needs to be adjusted, the traversal ends, and the current process control parameter adjustment scheme is given. If there is still no solution after the traversal ends, the adjustment scheme with the smallest corresponding specification residual in the traversal record is given as the recommended adjustment scheme. In some other embodiments, the simulated annealing algorithm or the dynamic programming algorithm can also be used to solve the adjustment scheme.

[0100] Figure 2 The profile product specification control system provided by the present disclosure includes: a matrix construction module 201 for constructing a specification control matrix according to product specification parameters and process control parameters; a hierarchical clustering module 202 for using the comprehensive efficacy coefficient of product specification parameters and process control parameters as clustering parameters to perform hierarchical clustering on the specification control matrix to obtain several process control parameter clusters corresponding to each product specification parameter in the specification control matrix; a parameter grading module 203 for grading product specification parameters according to historical product specification parameters; a weight calculation module 204 for determining the process control parameter clusters corresponding to each level of product specification parameters and calculating the weight distribution ratio of each level of process control parameter clusters; a specification adjustment module 205 for adjusting the profile product specification according to the specification control matrix and the weight distribution ratio.

[0101] Figure 3 The schematic diagram of the electronic device 1000 provided by the present disclosure, the electronic device 1000 includes a memory 1002 and a processor 1001, and a computer program / instructions are stored in the memory 1002; the processor 1001 is used to execute the computer program / instructions; when the computer program / instructions are executed by the processor 1001, it is at least used to implement the above-mentioned profile product specification control method.

[0102] Figure 4 The present disclosure provides a computer-readable storage medium 1100, in which computer program / instructions are stored, and when the computer program / instructions are executed by a processor, it is at least used to implement the above-mentioned profile product specification control method.

[0103] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalent technologies, the present disclosure also intends to include these changes and modifications therein.

Claims

1. A profile product specification control method, characterized in that, Including: Construct a specification control matrix based on product specification parameters and process control parameters; Using the comprehensive efficacy coefficient of product specification parameters and process control parameters as the clustering parameter, perform hierarchical clustering on the specification control matrix to obtain several process control parameter clusters corresponding to each product specification parameter in the specification control matrix; Grade the product specification parameters according to historical product specification parameters; Determine the process control parameter clusters corresponding to each grade of product specification parameters, and calculate the weight distribution ratio of each grade of process control parameter clusters; Adjust the profile product specifications according to the specification control matrix and the weight distribution ratio.

2. The method according to claim 1, wherein The constructing of the specification control matrix according to product specification parameters and process control parameters includes: selecting the target historical product with the smallest difference degree from the target specification parameters among several historical products, and constructing the specification control matrix according to the specification parameters and process control parameters of the target historical product.

3. The method according to claim 2, wherein After constructing the specification control matrix according to the specification parameters and process control parameters of the target historical product, it further includes: adjusting the matrix elements of the specification control matrix based on the subjective weighting method.

4. The method according to claim 1, characterized in that, The calculation formula of the comprehensive efficacy coefficient of product specification parameters and process control parameters includes: Among them, ρ ij represents the comprehensive efficacy coefficient of product specification parameters and process control parameters, ‖ΔY i ‖ represents the modulus of the change amount of the i-th product specification parameter; ||ΔX j || represents the modulus of the change amount of the j-th process control parameter; a j represents the weight of the j-th process control parameter.

5. The method according to claim 1, characterized in that, The grading of product specification parameters according to historical product specification parameters includes: Obtain historical product specification parameters and filter out anomalies; According to the filtered historical product specification parameters, calculate the confidence interval of each product specification parameter and the sigma level of each product specification parameter; Take the maximum value of the absolute values of the upper and lower limits of the confidence intervals of all product specification parameters as the grading upper limit of the product specification parameters, and take the maximum value of the sigma levels of all product specification parameters as the grading interval of the product specification parameters; Calculate the grading number of product specification parameters and the upper and lower limits of each grade of product specification parameters according to the grading upper limit and grading interval, and the corresponding formulas include: LL n =(z - 1)·d LH n = z·d Among them, C represents the fixed number of levels; floor represents the floor function; H MAX represents the upper limit of level determination; d represents the level determination interval; LL n represents the lower limit of the product specification parameter level; LH n represents the upper limit of the product specification parameter level; z represents the level number.

6. The method according to claim 5, characterized in that, The determining of the process control parameter clusters corresponding to each grade of product specification parameters and the calculation of the weight distribution ratio of each grade of process control parameter clusters include: Calculate the number of types of process control parameters corresponding to each grade of product specification parameters; In the order from large to small of the comprehensive efficacy coefficient, select the number of process control parameter clusters equal to the number of types of process control parameters for each grade of product specification parameters; Calculate the weight distribution ratio of each grade of process control parameter clusters; Among them, the calculation formula corresponding to the weight distribution ratio includes: Among them, ρ if is the comprehensive efficacy coefficient value of the f-th cluster center point of the i-th specification; λ kf represents the weight distribution ratio, k ∈ [1, K], where K represents the number of types of process control parameters corresponding to the product specification parameters; the calculation formula for the number of types of process control parameters includes: Among them, M m represents the number of clustering categories of the m-th product specification parameter.

7. The method according to any one of claims 1 to 6, characterized in that Adjusting the profile product specifications according to the specification control matrix and the weight distribution ratio includes: Taking the difference between the profile product specification parameters and the standard parameters as the specification parameter error amount; Processing each specification parameter error amount in turn according to the order from large to small of the comprehensive efficacy coefficient, including: when it is determined that the specification parameter error amount is greater than the threshold, determining the grade of the specification parameter error amount and the corresponding weight distribution ratio, and calculating the process control parameter value according to the boundary conditions of the process control parameters and the specification control matrix; Predict the product specification parameter error amount according to the calculated process control parameter value, and calculate the predicted product specification parameter and the specification parameter residual amount; Repeat the above method until the error amounts of all specification parameters are less than the threshold value or the traversal ends; When the error amounts of all specification parameters are less than the threshold value, adjust the profile product specifications according to the current process control parameter values; when the traversal ends, adjust the profile product specifications according to the process control parameter values corresponding to the minimum specification parameter residual amounts.

8. A profile product specification control system, characterized in that, Including: A matrix construction module, configured to construct a specification control matrix according to product specification parameters and process control parameters; A hierarchical clustering module, configured to use the comprehensive efficacy coefficients of product specification parameters and process control parameters as clustering parameters to perform hierarchical clustering on the specification control matrix, and obtain several process control parameter clusters corresponding to each product specification parameter in the specification control matrix; A parameter grading module, configured to grade product specification parameters according to historical product specification parameters; A weight calculation module, configured to determine the process control parameter clusters corresponding to product specification parameters of each grade, and calculate the weight distribution ratios of the process control parameter clusters of each grade; A specification adjustment module, configured to adjust the profile product specifications according to the specification control matrix and the weight distribution ratios; 9. An electronic device, characterized in that, Including a memory and a processor, wherein a computer program / instructions are stored in the memory; the processor is configured to execute the computer program / instructions; when the computer program / instructions are executed by the processor, it is at least used to implement the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, A computer program / instructions are stored in the computer-readable storage medium, and when the computer program / instructions are executed by a processor, it is at least used to implement the method according to any one of claims 1-8.

Images