Multi-level progressive parameter optimization method for complex process industry

Abstract

The invention discloses a complex process industry-oriented multi-level progressive parameter optimization method, which comprises the following steps of: analyzing the correlation between M process parameters and a quality index one by one to determine the importance degree of each process parameter to the quality index; sorting the importance degrees of the quality indexes in a descending order according to the process parameters to obtain the process parameters sorted according to the importance degrees; according to the sorted technological parameters, a technological parameter layering method based on correlation analysis is constructed, hierarchical division of the technological parameters is achieved, and a multi-level technological parameter combination is obtained through C times of division; modeling optimization is carried out in sequence from the Cth layer of technological parameter combination to the first layer of technological parameter combination, and the optimal solution of the first layer of technological parameter combination to the optimal solution of the Cth layer of technological parameter combination are obtained. According to the method, the problem of optimization difficulty caused by low modeling prediction precision and various process parameters in complex process manufacturing is effectively solved, and the method is of great significance in guaranteeing the process quality and improving the processing efficiency for process manufacturing enterprises.

Description

Technical Field

[0001] The invention relates to a multi-level progressive parameter optimization method for complex process industries, belonging to the technical field of complex process process parameter optimization. Background Art

[0002] Different from discrete manufacturing, process manufacturing mainly realizes continuous production through the coordinated operation of process parameters with different functions. Therefore, the key to the overall optimization of process technology lies in how to achieve the joint optimization of process parameters, that is, to quickly control and optimize product quality by adjusting process parameters when quality fluctuations occur. In addition, complex process manufacturing has the characteristics of complex process, serious mass-energy coupling between process parameters, and strong temporal nature of process data, which makes it difficult to optimize process parameters through statistical analysis methods. Therefore, how to achieve complex process modeling and prediction, and then quickly and efficiently optimize and control process parameters is the core issue of realizing intelligent optimization decision-making in process workshops. Summary of the invention

[0003] The present invention provides a multi-level progressive parameter optimization method for complex process industries, which is used to solve the optimization technical problem of numerous process parameters in process manufacturing.

[0004] The technical solution of the present invention is:

[0005] According to a first aspect of the present invention, a multi-level progressive parameter optimization method for complex process industries is provided, comprising the following steps:

[0006] S1. Preprocess the process data to obtain a preprocessed process data set. The preprocessed process data set consists of process parameters and quality indicators, expressed as D = {X mn ,Y n}, where X mn represents the mth process parameter of the nth sample, Y n Represents the quality indicator of the nth sample;

[0007] S2. Analyze the correlation between the M process parameters and the quality index one by one to determine the importance of each process parameter to the quality index;

[0008] S3. Sort the quality indicators in descending order of importance according to the process parameters to obtain the process parameters sorted by importance;

[0009] S4. According to the sorted process parameters, a process parameter stratification method based on correlation analysis is constructed to realize the hierarchical division of process parameters, and a multi-level process parameter combination is obtained through C-fold division;

[0010] S5. For the 1st to Cth layer process parameter combinations, modeling and optimization are performed in sequence from the Cth layer process parameter combination to the 1st layer process parameter combination to obtain the optimal solution of the 1st layer process parameter combination to the Cth layer process parameter combination.

[0011] Further, the S4 includes:

[0012] S4.1. Construct a hierarchical model;

[0013] S4.2. The process parameters sorted by importance are used as the process parameters to be layered; the process parameters to be layered are layered according to the layering model, and after each layering, the dividing point of the qth layer and the process parameters to be layered before the dividing point are used as the qth layer process parameter combination, and the qth layer process parameter combination is deleted from the process parameters to be layered to update the process parameters to be layered, until the termination condition is reached, and a multi-level process parameter combination is obtained.

[0014] Furthermore, in S4.2, the process parameters to be layered are layered according to the layered model, specifically:

[0015] The process parameter with the largest correlation among the process parameters to be stratified is selected as the initial process parameter for the qth stratification; the qth data set Qq1 is constructed based on the initial process parameters and quality indicators;

[0016] The data set Qq1 is used as the input of the first training of the hierarchical model, and the hierarchical model is iteratively trained to obtain the goodness of fit; during the pth iterative training process, in the data set Qq p-1 Add a process parameter to build a data set Qq p , the data set Qq p As the input of the hierarchical model trained for the pth time, to obtain the goodness of fit; and so on, until all the process parameters in the process parameters to be stratified participate in the iteration, to obtain the goodness of fit of all the process parameters in the process parameters to be stratified;

[0017] According to the goodness of fit of all process parameters to be layered, the stability index is calculated; according to the stability index, the demarcation point of the qth layering is determined from all process parameters to be layered; the demarcation point of the qth layering in the process parameters to be layered and the process parameters before the demarcation point are taken as the qth layer process parameter combination, and the qth layer process parameter combination is deleted from the process parameters to be layered to update the process parameters to be layered for the q+1th layering.

[0018] Furthermore, the termination condition is that the correlation corresponding to the process parameter ranked first among the process parameters to be layered is less than 0.5.

[0019] Furthermore, the stability index C i The calculation is as follows:

[0020] C i =S i ·M i

[0021] Among them, S i represents the slope change rate of the process parameter with the ranking number i in the current process parameters to be layered, i=1,2,3,....,I-3, I represents the total number of process parameters in the current process parameters to be layered; M i Indicates the degree of mutation of the process parameter with ranking number i among the process parameters to be layered.

[0022] Furthermore, the slope change rate is expressed as:

[0023]

[0024] Among them, E i It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i in the current process parameters to be stratified and the quality indicators.

[0025] Furthermore, the mutation degree is expressed as:

[0026]

[0027] Among them, E i It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i in the current process parameters to be stratified and the quality indicators.

[0028] Furthermore, the modeling and optimization are specifically as follows: for the first optimization: a nonlinear mapping model between the C-th layer process parameter combination and the quality index is established based on the random forest regression model, and the improved particle swarm algorithm is called for global optimization to obtain the optimal solution of the C-th layer process parameter combination; for the second optimization: a nonlinear mapping model between the optimal solution of the C-1-th layer process parameter combination + the C-th layer process parameter combination and the quality index is established based on the random forest regression model, and the improved particle swarm algorithm is called for global optimization to obtain the optimal solution of the C-1-th layer process parameter combination; and so on, until the optimal solution of the 1st layer process parameter combination is obtained, that is, after C times of modeling and optimization, the optimal solution of the 1st layer process parameter combination ~ the optimal solution of the C-th layer process parameter combination are obtained.

[0029] According to a second aspect of the present invention, a multi-level progressive parameter optimization system for complex process industries is provided, comprising a module for executing any of the multi-level progressive parameter optimization methods for complex process industries described above.

[0030] According to a third aspect of the present invention, there is provided a terminal device comprising a memory, a processor, and a program stored in the memory and executable by the processor, wherein when the processor executes the program, the multi-level progressive parameter optimization method for complex process industries as described in any one of the above is implemented.

[0031] The beneficial effects of the present invention are as follows: first, based on the concept of hierarchical progression, the present invention divides the process parameters into layers according to the importance of relative quality indicators; on this basis, modeling optimization is performed to obtain the optimal process parameter combination; during the modeling optimization process, the optimal parameter combination obtained by each optimization is input as a constant to the next modeling optimization, thereby realizing multi-level progressive optimization of process parameters. The present invention effectively solves the problem of low prediction accuracy of complex process manufacturing modeling and optimization difficulties caused by numerous process parameters, which is of great significance for process manufacturing enterprises to ensure process quality and improve processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the process structure of the present invention;

[0033] Figure 2 It is a schematic diagram of the principle of the process parameter stratification method based on correlation analysis of the present invention;

[0034] Figure 3 This is an example diagram of multi-level progressive modeling optimization in the present invention;

[0035] Figure 4 It is the fitness function curve of IPSO optimization algorithm; among them, Figure 4 (a) is the fitness function curve of the first layer. Figure 4 (b) is the fitness function curve of the second layer. Figure 4 (c) is the fitness function curve of the third layer;

[0036] Figure 5 Fitness function curve graph for extracting key parameters optimization;

[0037] Figure 6 This is the fitness function curve for overall optimization. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily without conflict.

[0039] Example 1: Figure 1-6 As shown, according to a first aspect of an embodiment of the present invention, a multi-level progressive parameter optimization method for complex process industries is provided, comprising the following steps:

[0040] S1. Collect process industrial data through sensors to construct a process technology data set; preprocess the process technology data to obtain a preprocessed process technology data set; the preprocessed process technology data set consists of process parameters and quality indicators, expressed as D = {X mn ,Y n}, where X mn represents the mth process parameter of the nth sample, Y n Represents the quality index of the nth sample; m = 1, 2, ...., M;

[0041] S2. Analyze the correlation between the M process parameters and the quality index one by one according to the Pearson correlation to determine the importance of each process parameter to the quality index. In view of the different effects of the process parameters on the quality index, there are not only key process parameters with great influence, but also redundant process parameters with small influence. Therefore, the present invention introduces a hierarchical idea to divide the process parameters into levels.

[0042] S3. Sort the quality indicators in descending order of importance according to the process parameters to obtain the process parameters sorted by importance;

[0043] S4. According to the sorted process parameters, a process parameter stratification method based on correlation analysis is constructed to realize the hierarchical division of process parameters, and a multi-level process parameter combination is obtained through C-fold division;

[0044] S5. For the 1st to Cth layer process parameter combinations, modeling and optimization are performed in sequence from the Cth layer process parameter combination to the 1st layer process parameter combination to obtain the optimal solution of the 1st layer process parameter combination to the Cth layer process parameter combination.

[0045] Further, the S4 includes:

[0046] S4.1. Using a random forest regression model as a hierarchical model; the random forest regression model can effectively capture complex nonlinear relationships and has excellent stability and robustness; therefore, the present invention uses the existing random forest regression model as a hierarchical model;

[0047] S4.2. The process parameters sorted by importance are used as the process parameters to be layered; the process parameters to be layered are layered according to the layering model, and after each layering, the dividing point of the qth layer and the process parameters to be layered before the dividing point are used as the qth layer process parameter combination, and the qth layer process parameter combination is deleted from the process parameters to be layered to update the process parameters to be layered, until the termination condition is reached, and a multi-level process parameter combination is obtained.

[0048] Furthermore, in S4.2, the process parameters to be layered are layered according to the layered model, specifically:

[0049] The process parameter with the greatest correlation among the process parameters to be stratified is selected as the initial process parameter for the qth stratification; the qth data set Qq1 is constructed based on the initial process parameters and quality indicators, and is divided into the qth training set Qq1 and the qth validation set Qq1;

[0050] The data set Qq1 is used as the input of the hierarchical model, and the hierarchical model is iteratively trained to obtain the goodness of fit; for the pth iterative training process, in the data set Qq p-1 Add a process parameter to build a data set Qq p , the data set Qq p As the input of the hierarchical model trained for the pth time, to obtain the goodness of fit; and so on, until all the process parameters in the process parameters to be stratified participate in the iteration, to obtain the goodness of fit of all the process parameters in the process parameters to be stratified;

[0051] According to the goodness of fit R of all process parameters to be layered 2 , calculate the stability index; according to the stability index, determine the demarcation point of the qth stratification from all the process parameters to be stratified; take the demarcation point of the qth stratification and the process parameters to be stratified before the demarcation point as the qth layer process parameter combination, delete the qth layer process parameter combination from the process parameters to be stratified to update the process parameters to be stratified for the q+1th stratification.

[0052] Furthermore, the termination condition is that the correlation corresponding to the process parameter ranked first among the process parameters to be layered is less than 0.5.

[0053] Furthermore, the stability index C i The calculation is as follows:

[0054] C i =S i ·M i

[0055] Among them, S irepresents the slope change rate of the process parameter with the ranking number i in the current process parameters to be layered, i=1,2,3,....,I-3, I represents the total number of process parameters in the current process parameters to be layered; M i It indicates the mutation degree of the process parameter with the ranking number i in the current process parameters to be layered. It should be noted that the ranking numbers of the current process parameters to be layered are numbered according to 1, 2, 3, .... I, and the correlation value of the process parameter with the higher ranking number is greater.

[0056] Furthermore, the slope change rate is expressed as:

[0057]

[0058] Among them, E i It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i in the current process parameters to be stratified. i+1 It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i+1 in the current process parameters to be stratified, E i+2 、E i+3 The meaning is the same;

[0059] Furthermore, the mutation degree is expressed as:

[0060]

[0061] Among them, E i It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i in the current process parameters to be stratified and the quality indicators.

[0062] In stability judgment, the slope change rate is used as the main indicator to evaluate the change range of the model's goodness of fit under adjacent parameter settings; at the same time, due to the correlation between certain parameters that may appear during the model training process, the model accuracy may fluctuate, and this fluctuation can be understood as a mutation. Therefore, on the basis of introducing the slope change rate, the mutation rate is further introduced as an auxiliary indicator to measure the degree of mutation at different parameter levels. By combining the above two indicators, a stability index is formed. This stability index quantitatively evaluates the overall stability of the model through the product of the slope change rate and the mutation rate. The smaller the value, the more stable the model's goodness of fit. Therefore, the stability index can more effectively identify the stability of the trend.

[0063] Furthermore, the modeling optimization is specifically as follows: for the first optimization: a nonlinear mapping model between the C-th layer process parameter combination and the quality index is established based on the random forest regression model, and the improved particle swarm algorithm is called for global optimization to obtain the optimal solution of the C-th layer process parameter combination; for the second optimization: a nonlinear mapping model between the optimal solution of the C-1-th layer process parameter combination to the C-th layer process parameter combination and the quality index is established based on the random forest regression model, and the improved particle swarm algorithm is called for global optimization to obtain the optimal solution of the C-1-th layer process parameter combination; and so on, until the optimal solution of the 1-th layer process parameter combination is obtained, that is, after C times of modeling optimization, the optimal solution of the 1-th layer process parameter combination to the C-th layer process parameter combination is obtained. From the above, it can be seen that the optimal solution obtained in each optimization is used as a constant input for the next modeling optimization.

[0064] Exemplarily, the present invention obtains the first-third layer process parameter combinations, establishes a nonlinear mapping model between the third layer process parameter combination and the quality index based on the random forest regression model, and calls the improved particle swarm algorithm for global optimization to obtain the optimal solution of the third layer process parameter combination; for the second optimization: establishes a nonlinear mapping model between the optimal solution of the second layer process parameter combination + the third layer process parameter combination and the quality index based on the random forest regression model, and calls the improved particle swarm algorithm for global optimization to obtain the optimal solution of the second layer process parameter combination; for the third optimization: establishes a nonlinear mapping model between the optimal solution of the first layer process parameter combination + the second layer process parameter combination + the optimal solution of the third layer process parameter combination and the quality index based on the random forest regression model, and calls the improved particle swarm algorithm for global optimization to obtain the optimal solution of the first layer process parameter combination; that is, after three modeling optimization searches, the optimal solution of the first layer process parameter combination to the optimal solution of the third layer process parameter combination are obtained.

[0065] The above-mentioned nonlinear mapping model between the optimal solution of the second-layer process parameter combination + the third-layer process parameter combination and the quality index based on the random forest regression model is specifically as follows: based on the preprocessed process data set of S1, a new data set is constructed using the "optimal solution and quality index of the second-layer process parameter combination + the third-layer process parameter combination", and the training set and the test set are divided into a ratio of 7:3 for training and testing the random forest regression model, and then the quality index prediction results of the test set are obtained to participate in the calculation of the fitness value in the optimization process. The same is true for other optimization processes.

[0066] The improved particle swarm optimization algorithm is improved in that the inertia weight is linearly decreased, the acceleration factor is adaptively changed, and the strategy of limiting the particle position is adopted.

[0067] The improved particle swarm optimization algorithm is called to reversely search for the optimal solution of process parameter combination. The specific steps are as follows:

[0068] (1) Randomly initialize the particle swarm. In this method, the particle swarm consists of h particles, each particle represents a process parameter combination solution, and the dimension of each particle is the number of process parameters. The initial position of the particle is randomly generated within the upper and lower boundaries of the search space, and the velocity vector is initialized to 0. In this embodiment, the size of the particle swarm is set to 100, and the search range of the process parameters is defined within the given upper and lower boundaries.

[0069] (2) Calculate the fitness of each particle. The fitness of each particle is measured by the root mean square error between the model prediction result and the true value. The particle swarm will minimize this fitness value during the optimization process, so that the particle swarm gradually approaches the global optimal solution.

[0070] (3) Update pbest and gbest. The position of each particle with the highest fitness value is the individual optimal position, and the position of the particle with the highest fitness value in the particle group is the global optimal position.

[0071] (4) updating the inertia weight according to the nonlinear reduction strategy of the inertia weight, and updating the acceleration factor according to the adaptive nonlinear change strategy of the acceleration factor;

[0072] (5) Update the particle's velocity and position;

[0073] (6) Strategy for limiting particle positions: used to check whether there are particles whose positions are beyond the search range and put the particles beyond the search range back into the search range;

[0074] (7) Determine whether the maximum number of iterations has been reached. If so, record the optimal process parameter combination for the layer. If not, repeat steps (3) to (7).

[0075] (8) Determine whether the upper limit of the number of layers has been reached. If so, output the overall optimal process parameter combination. If not, increase the number of layers by one, and perform model training and testing on the layer based on the optimization of the process parameter combination of the previous layer. Then repeat steps (3) to (8) until the upper limit of the number of layers is reached.

[0076] The inertia weight linear reduction strategy expression is:

[0077]

[0078] Where: (t) is the inertia weight at the tth iteration, ω max is the maximum inertia weight, ω min is the minimum inertia weight, T max is the maximum number of iterations.

[0079] The adaptive change strategy expression of the acceleration factor is:

[0080]

[0081] Where: is the individual and global acceleration factor for the tth iteration, c 1max 、c 2max is the individual and global maximum acceleration factor, c 1min 、c 2min is the individual and global minimum acceleration factor, and Tmax is the maximum number of iterations.

[0082] The search strategy expression in the strategy of limiting the particle position is:

[0083]

[0084] In the formula, represents the particle position, h min represents the particle search lower limit, h max Represents the upper limit of particle search.

[0085] Furthermore, in the above, the inertia weight is reduced from 0.9 to 0.2, gradually reducing the particle's dependence on the previous velocity and enhancing the convergence ability, that is, ω max Take 0.9, ω min Take 0.2; Individual learning coefficient: Reduce from 2 to 1, so that each particle gradually reduces its dependence on its own historical optimal position during the search process, that is, c 1max Take 2, c 1min Take 1; Global learning coefficient: Increase from 1 to 2, gradually enhance the ability of particles to follow the global optimal position, and promote the group to explore the global optimal solution, that is, c 2max Take 2, c 2min Take 1; the algorithm sets Tmax to 500.

[0086] According to a second aspect of an embodiment of the present invention, a multi-level progressive parameter optimization system for complex process industries is provided, specifically comprising: a first module for executing S1: preprocessing process process data to obtain a preprocessed process process data set; a second module for executing S2: analyzing the correlation between M process parameters and quality indicators one by one according to Pearson correlation to determine the importance of each process parameter to the quality indicator; a third module for executing S3: sorting the importance of the quality indicator according to the process parameters in descending order to obtain the process parameters sorted by importance; a fourth module for executing S4: constructing a process parameter stratification method based on correlation analysis according to the sorted process parameters to achieve hierarchical division of the process parameters, and obtaining a multi-level process parameter combination through C divisions; a fifth module for executing S5: for the 1st layer to the Cth layer process parameter combination, modeling and optimization are performed in sequence from the Cth layer process parameter combination to the 1st layer process parameter combination to obtain the optimal solution of the 1st layer process parameter combination to the Cth layer process parameter combination. As used above, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the system described in the above embodiment is preferably implemented by software, implementation by hardware, or a combination of software and hardware is also possible and conceivable. For parts that are not described in detail in each module, please refer to the relevant description of this embodiment.

[0087] According to a third aspect of an embodiment of the present invention, a terminal device is provided, comprising a memory, a processor, and a program stored in the memory and executable by the processor, wherein when the processor executes the program, the multi-level progressive parameter optimization method for complex process industries as described in any one of the above is implemented.

[0088] Embodiment 2: The optional implementation manner of the present invention is described in detail below in conjunction with the accompanying drawings.

[0089] In order to solve the computational complexity problem caused by high-dimensional parameter optimization in process industries, the present invention proposes a multi-level progressive parameter optimization method for complex process industries. The method first divides the process parameters into layers according to the importance of relative quality indicators based on the concept of hierarchical progression. On this basis, an improved particle swarm algorithm is used to perform global optimization to obtain the optimal combination of process parameters. In the process of constructing the mapping model, the optimal parameter combination obtained by optimizing each layer is input as a constant to the next layer, thereby realizing the layer-by-layer progressive optimization of the process parameters. This method effectively solves the optimization difficulties caused by the low prediction accuracy of complex process manufacturing modeling and the large number of process parameters, which is of great significance for process manufacturing companies to ensure process quality and improve processing efficiency. The following is an explanation in combination with simulation data:

[0090] 1) The sample data set comes from a production line of a process manufacturing enterprise. The thin plate drying process data for October 2022 is exported from the MES system of the process production line. The data table contains "batch number", "collection time", and also includes 26 process parameters such as "dehumidification air temperature", "dehumidification air humidity", and "inlet material temperature" and a quality indicator - as shown in Table 1. As shown in Table 2, some process data are shown, and the collection time interval of each process data is 1s; the process technology data set is preprocessed (removing the head and tail operations) to obtain the preprocessed process technology data set, totaling 239281 items; according to the preprocessed process technology data set, the steps S2-S5 described in Example 1 of the present invention are used to optimize parameters.

[0091] Table 1 Process parameter numbers and quality indicators

[0092]

[0093] Table 2 Process data

[0094]

[0095] 2) According to the Pearson correlation, the correlation between the 26 process parameters and the quality indicators is analyzed one by one to determine the importance of each process parameter to the quality indicators.

[0096] 3) Sort the quality indicators in descending order according to the process parameters, and obtain the process parameters sorted by importance. The specific sorting results are: X5, X 24 , X 21 , X 25 , X 26 , X6, X7, X8, X 22 , X 20 , X9, X 23 , X 19 , X1, X3, X2, X 18 , X 17 , X 16 , X 12 , X 14 , X 13 , X 11 , X 10 , X 15 , X4, serial numbers are 1-26, for example, the correlation value of process parameter X5 with serial number 1 is the largest, that is, the importance is the highest.

[0097] 4) According to the sorted process parameters, a process parameter stratification method based on correlation analysis is constructed to realize the hierarchical division of process parameters, thereby obtaining a multi-level process parameter combination, specifically:

[0098] Before stratification, there are 26 process parameters to be stratified, and then the first stratification is carried out, that is, first X5 and the quality index are used to construct the first data set Q11, and the first training set Q11 and the first validation set Q11 are divided according to 7:3; the first training set Q11 and the first validation set Q11 are used as inputs of the stratification model, and the stratification model is iteratively trained, that is, 26 iterations are performed; according to the obtained goodness of fit, the stability index is calculated; according to the stability index, the dividing point of the first stratification is determined as X6 from all the process parameters to be stratified; the dividing point of the first stratification in the process parameters to be stratified and the process parameters before the dividing point are used as the first layer process parameter combination, and then the first layer process parameter combination is deleted from the process parameters to be stratified to update the process parameters to be stratified for the second stratification, that is, the process parameters corresponding to the serial numbers 7-26 are used as the updated process parameters to be stratified.

[0099] Before the second stratification, there are 20 process parameters to be stratified, and then the second stratification is carried out, that is, first X7 and the quality index are used to construct the second data set Q21, and the second training set Q21 and the second validation set Q21 are divided according to 7:3; the second training set Q21 and the second validation set Q21 are divided according to 7:3; the second training set Q21 and the second validation set Q21 are used as the input of the stratification model, and the stratification model is iteratively trained, that is, 20 iterations are performed; according to the obtained goodness of fit, the stability index is calculated; according to the stability index, the cutoff point of the second stratification is determined as X from all the process parameters to be stratified 17 ; The dividing point of the second layer in the process parameters to be layered and the process parameters before the dividing point are used as the second layer process parameter combination, and then the second layer process parameter combination is deleted from the process parameters to be layered to update the process parameters to be layered for the third layer, that is, the process parameters corresponding to serial numbers 19-26 are used as the updated process parameters to be layered.

[0100] Before the third stratification, there are 8 process parameters to be stratified. The process parameter X ranked first among the process parameters to be stratified is 16 The corresponding correlation is less than 0.5, so the current process parameters to be layered are taken as the last layer, that is, the third layer.

[0101] According to the above, the first layer process parameter combination is: X5, X 24 , X 21 , X 25 , X 26 , X6; the second layer process parameter combination is: X7, X8, X 22 , X 20 , X9, X 23 , X 19 , X1, X3, X2, X 18 , X 17 ; Layer 3 process parameter combination: X16 , X 12 , X 14 , X 13 , X 11 , X 10 , X 15 , X4.

[0102] 5) For the 1st to 3rd layer process parameter combinations, modeling and optimization are performed in order from the 3rd layer process parameter combination to the 1st layer process parameter combination to obtain the optimal solution of the 1st layer process parameter combination to the 3rd layer process parameter combination. Among them, the 3rd layer process parameter combination X obtained in the first optimization is 16 , X 12 , X 14 , X 13 , X 11 , X 10 , X 15 The optimal solutions of , X4 are: 17.996, 113.285, 705.134, 3.806, 32.351, 11.000, 49.170, 89.622, respectively. The fitness curve is as follows Figure 4 (c) As shown in the figure, the second layer process parameter combinations X7, X8, X 22 , X 20 , X9, X 23 , X 19 , X1, X3, X2, X 18 , X 17 The optimal solutions are: 1178.358, 31.849, 121.223, 0.133, -7.825, 97.062, 112.757, 7.340, 50.912, 1002.612, 47.393, 0.235. The fitness curve is as follows Figure 4 (b) shows the first layer process parameter combination X5, X5 obtained by the third optimization. 24 , X 21 , X 25 , X 26 The optimal solutions of X6 are 17.218, 110.797, 112.587, 110.264, 113.299, and 5.963 respectively. The fitness curve is shown in Figure 4 (a) as shown; Figure 4 It can be seen that in each optimization process, the fitness tends to be stable after multiple rounds of iterations through the improved particle swarm optimization algorithm and the range is between 0 and 0.0001.

[0103] Furthermore, the multi-level progressive optimization of the present invention is compared with the key parameter extraction optimization method and the overall prediction optimization method by experimental analysis as shown in Table 3.

[0104] The present invention is compared with different comparative cases. Case 1 is to extract key parameters, that is, the first layer process parameter combination extracted by the present invention is used as the key parameters; Case 2 is overall optimization, that is, 26 process parameters without stratification are shown; the implementation process of the comparative case is: the process parameters and quality index data of Case 1 and Case 2 under the process data set preprocessed by the present invention are divided into a training set and a test set in a ratio of 7:3, and then the quality index prediction model is constructed layer by layer by adopting the RF regression model; then, the improved particle swarm optimization algorithm IPSO is used to reversely search for the optimal process parameter combination, and the fitness curves are as follows: Figure 5 , Figure 6 As shown in Table 3, it shows that the fitness of Cases 1 and 2 tends to be stable after multiple rounds of iterations through the improved particle swarm optimization algorithm and the range is between 0 and 0.0001.

[0105] Table 3 Comparison results of key parameter optimization and multi-level progressive optimization

[0106]

[0107] In this embodiment, the model evaluation indicators used include mean absolute error (MAE), mean square error (MSE) and goodness of fit (R 2 ).

[0108]

[0109] Where: s is the number of samples, y is 1,j Represents the true value of the quality indicator, y 2,j represents the predicted value of the quality indicator, Represents the mean.

[0110] It can be seen from Table 3 that since the key parameter extraction optimization only analyzes the key parameters and ignores the influence of other parameters on the quality indicators, the running time of the method proposed in the present invention is slightly higher than that of the key parameter extraction optimization method, but the R 2 It is 0.851507, MAE is 0.050028, and RMSE is 0.006945. It can be seen that the effect of extracting key parameter optimization is significantly lower than the multi-level progressive optimization of the present invention. In the case of the same number of optimizations, the number of iterations of the multi-level progressive optimization in the particle swarm optimization process is 154 times, and the running time is 213 seconds, which is 49% and 63% lower than the 301 times and 576 seconds of the overall optimization, respectively. Therefore, the effect of the present invention is significantly better than the overall optimization effect. In summary, the multi-level progressive optimization of the present invention not only improves the prediction accuracy and reduces the complexity of the optimization process relative to the overall optimization, but also makes up for the deficiency of single optimization that only considers key parameters.

[0111] The specific implementation modes of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above implementation modes, and various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention.

Claims

1. A multi-level progressive parameter optimization method for complex process industries, characterized in that: The following steps are involved: S1. Preprocessing the process technology data to obtain a preprocessed process technology data set; The preprocessed process data set consists of process parameters and quality indicators, expressed as D = {X mn ,Y n }, where X mn represents the mth process parameter of the nth sample, Y n Represents the quality indicator of the nth sample; S2. Analyze the correlation between the M process parameters and the quality index one by one to determine the importance of each process parameter to the quality index; S3. Sort the quality indicators in descending order of importance according to the process parameters to obtain the process parameters sorted by importance; S4. According to the sorted process parameters, a process parameter stratification method based on correlation analysis is constructed to realize the hierarchical division of process parameters, and a multi-level process parameter combination is obtained through C-fold division; S5. For the 1st to Cth layer process parameter combinations, modeling and optimization are performed in sequence from the Cth layer process parameter combination to the 1st layer process parameter combination to obtain the optimal solution of the 1st layer process parameter combination to the Cth layer process parameter combination.

2. The multi-level progressive parameter optimization method for complex process industries according to claim 1, characterized in that: The S4 comprises: S4.

1. Construct a hierarchical model; S4.

2. The process parameters sorted by importance are used as the process parameters to be layered; the process parameters to be layered are layered according to the layering model, and after each layering, the dividing point of the qth layer and the process parameters to be layered before the dividing point are used as the qth layer process parameter combination, and the qth layer process parameter combination is deleted from the process parameters to be layered to update the process parameters to be layered, until the termination condition is reached, and a multi-level process parameter combination is obtained.

3. The multi-level progressive parameter optimization method for complex process industries according to claim 2, characterized in that: In S4.2, the process parameters to be layered are layered according to the layered model, specifically: The process parameter with the largest correlation among the process parameters to be stratified is selected as the initial process parameter for the qth stratification; the qth data set Qq1 is constructed based on the initial process parameters and quality indicators; The data set Qq1 is used as the input of the first training of the hierarchical model, and the hierarchical model is iteratively trained to obtain the goodness of fit; during the pth iterative training process, in the data set Qq p-1 Add a process parameter to build a data set Qq p , the data set Qq p As the input of the hierarchical model trained for the pth time, to obtain the goodness of fit; and so on, until all the process parameters in the process parameters to be stratified participate in the iteration, to obtain the goodness of fit of all the process parameters in the process parameters to be stratified; Calculate the stability index based on the goodness of fit of all process parameters to be stratified; According to the stability index, the dividing point of the qth stratification is determined from all the process parameters to be stratified; The process parameters before and at the demarcation point of the qth stratification in the process parameters to be stratified are taken as the qth layer process parameter combination, and the qth layer process parameter combination is deleted from the process parameters to be stratified to update the process parameters to be stratified for the q+1th stratification.

4. The multi-level progressive parameter optimization method for complex process industries according to claim 2, characterized in that: The termination condition is that the correlation corresponding to the process parameter ranked first among the process parameters to be layered is less than 0.

5.

5. The multi-level progressive parameter optimization method for complex process industries according to claim 3, characterized in that: The stability index C i The calculation is as follows: C i =S i ·M i Among them, S i represents the slope change rate of the process parameter with the ranking number i in the current process parameters to be layered, i=1,2,3,....,I-3, I represents the total number of process parameters in the current process parameters to be layered; M i Indicates the degree of mutation of the process parameter with ranking number i among the process parameters to be layered.

6. The multi-level progressive parameter optimization method for complex process industries according to claim 5, characterized in that: The slope change rate is expressed as: Among them, E i It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i in the current process parameters to be stratified and the quality indicators.

7. The multi-level progressive parameter optimization method for complex process industries according to claim 5, characterized in that: The mutation degree is expressed as: Among them, E i It represents the goodness of fit value obtained by training and verifying the data set constructed by the process parameters with ranking number 1 to ranking number i in the current process parameters to be stratified and the quality indicators.

8. The multi-level progressive parameter optimization method for complex process industries according to claim 1, characterized in that: The modeling and optimization are specifically as follows: for the first optimization: a nonlinear mapping model between the C-th layer process parameter combination and the quality index is established based on the random forest regression model, and the improved particle swarm algorithm is called for global optimization to obtain the optimal solution of the C-th layer process parameter combination; for the second optimization: a nonlinear mapping model between the optimal solution of the C-1-th layer process parameter combination + the C-th layer process parameter combination and the quality index is established based on the random forest regression model, and the improved particle swarm algorithm is called for global optimization to obtain the optimal solution of the C-1-th layer process parameter combination; and so on, until the optimal solution of the 1st layer process parameter combination is obtained, that is, after C times of modeling and optimization, the optimal solution of the 1st layer process parameter combination ~ the optimal solution of the C-th layer process parameter combination are obtained.

9. A multi-level progressive parameter optimization system for complex process industries, characterized in that: The method comprises a module for executing the multi-level progressive parameter optimization method for complex process industries as claimed in any one of claims 1 to 8.

10. A terminal device, characterized in that: The method comprises a memory, a processor and a program stored in the memory and executable by the processor. When the processor executes the program, the method implements the multi-level progressive parameter optimization method for complex process industries as described in any one of claims 1 to 8.

Images