Process parameter determination method, electronic equipment and storage medium

Abstract

The invention discloses a process parameter determination method, electronic equipment and a storage medium, and the method comprises the steps: combining a plurality of first candidate parameter values of each process parameter item to obtain a plurality of first process parameter groups, and determining a first preference rate of a product corresponding to each first process parameter group, each first process parameter group comprises a first candidate parameter value corresponding to each process parameter item; a first coefficient corresponding to each process parameter item and a second coefficient between every two process parameter items are determined according to the first optimization rate, the first coefficient represents the influence degree of the parameter value of each process parameter item on the optimization rate, and the second coefficient represents the influence degree of every two process parameter items on the optimization rate under the interaction effect; according to the first coefficients and the second coefficients, determining an optimization rate regression relation of the process parameter items; and according to the optimization rate regression relationship and the plurality of second process parameter groups, determining the second process parameter group with the maximum second optimization rate of the corresponding product as a target process parameter group.

Description

Technical Field

[0001] The present invention relates to the technical field of preparation processes, and in particular to a method for determining process parameters, an electronic device, and a storage medium. Background Art

[0002] To convert raw materials with high moisture content into products with low or zero moisture content, the raw materials must be dried during the production process. Since there are many process factors that control the moisture content of the product, it is necessary to reasonably select and match the parameter values corresponding to each process factor.

[0003] In the existing manufacturing process, the parameter values corresponding to all process factors are traversed according to the production requirements to form multiple process parameter groups. Test products are then produced according to the parameter values corresponding to the process factors in these process parameter groups, and the quality of the test products is evaluated. Finally, based on the quality evaluation of the test products, the parameter values corresponding to the process factors in the target process parameter group are selected and the product is manufactured.

[0004] However, the above method of selecting the target process parameter group may affect the quality evaluation results of the product due to operational errors in the production of the test product or subjective factors during the quality evaluation, resulting in errors in the quality evaluation results, and further resulting in low accuracy of the selected target process parameter group. Summary of the Invention

[0005] The present invention provides a method for determining process parameters, an electronic device, and a storage medium, which solve the current problem of high cost and time consumed in selecting a target process parameter group. It eliminates the need to produce products corresponding to a second process parameter group, and evaluates the products to select the optimal target process parameter group. This reduces the cost of producing test products, quickly selects the target process parameter group, and reduces the time for determining the target process parameter group.

[0006] According to one aspect of the present invention, a method for determining process parameters is provided, the method comprising:

[0007] Multiple first candidate parameter values of each process parameter item are combined to obtain multiple first process parameter groups, and the first preference rate of the product corresponding to each first process parameter group is determined, wherein each first process parameter group includes a first candidate parameter value corresponding to each process parameter item.

[0008] According to the first optimization rate, the first coefficient corresponding to each process parameter item and the second coefficient between every two process parameter items are determined respectively, wherein the first coefficient is used to characterize the degree of influence of the parameter value of each process parameter item on the optimization rate, and the second coefficient is used to characterize the degree of influence of the interaction between every two process parameter items on the optimization rate.

[0009] According to each first coefficient and the second coefficient, the optimal rate regression relationship of the process parameter item is determined.

[0010] According to the regression relationship of the preference rate and multiple second process parameter groups, the second process parameter group with the largest second preference rate of the corresponding product is determined as the target process parameter group.

[0011] The method for determining process parameters provided by the embodiments of the present invention, on the one hand, combines multiple first candidate parameter values for each process parameter item to obtain multiple first process parameter groups, thereby achieving possible coverage of the quality of products produced under a small number of different parameter values for all process parameter items. This ensures that various quality conditions of products are covered when the parameter values of different process parameter items change, avoids incomplete evaluation caused by focusing only on the parameter values of some process parameter items, and improves the accuracy of product quality evaluation. On the other hand, determining the first coefficient corresponding to each process parameter item and determining the second coefficient corresponding to each process parameter item can quantify the impact of the process parameter item on the product's preference rate when the parameter value changes. Based on the first coefficient and the second coefficient, a basis is provided for the subsequent quantification of the impact of the change in the process parameter item value on the preference rate, quickly and accurately selecting the parameter value of the preferred process parameter item. Furthermore, based on the first coefficient and the second coefficient, the preference rate regression relationship of the process parameter item is determined, achieving adaptive analysis based on the parameters of all process parameter items, reducing the problem in the prior art of low accuracy in selecting the optimal process parameter group due to the influence of operational errors or subjective factors on the quality evaluation results of a certain test product. Furthermore, it facilitates the analysis of parameter values and provides a clearer analytical basis for accurately determining the process parameter group that gives the product the highest preference rate. Finally, the second preference rate of the product corresponding to each second process parameter group is determined using the preference rate regression relationship, and the second process parameter group with the largest second preference rate is determined as the target process parameter group. This solves the current problem of low accuracy in selecting the target process parameter group due to errors in the quality evaluation results of the test products. It eliminates the need to produce products corresponding to the second process parameter group and evaluate the products to select the optimal target process parameter group. While accurately determining the target process parameter group, it reduces the cost of producing the test product, quickly selects the target process parameter group, and reduces the time to determine the target process parameter group.

[0012] According to another aspect of the present invention, there is provided a device for determining process parameters, the device comprising:

[0013] A combination module is used to combine multiple first candidate parameter values of each process parameter item to obtain multiple first process parameter groups, and determine the first preference rate of the product corresponding to each first process parameter group, wherein each first process parameter group includes a first candidate parameter value corresponding to each process parameter item.

[0014] A determination module is used to determine the first coefficient corresponding to each process parameter item and the second coefficient between every two process parameter items according to the first optimization rate, wherein the first coefficient is used to characterize the degree of influence of the parameter value of each process parameter item on the optimization rate, and the second coefficient is used to characterize the degree of influence of the interaction between every two process parameter items on the optimization rate.

[0015] The calculation module is used to determine the optimal rate regression relationship of the process parameter items based on the first coefficients and the second coefficients.

[0016] The selection module is used to determine the second process parameter group with the largest second preference rate of the corresponding product as the target process parameter group based on the preference rate regression relationship and multiple second process parameter groups.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform the method for determining the process parameters of any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the method for determining process parameters of any embodiment of the present invention when executed.

[0022] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, which implements the method for determining the process parameters of any embodiment of the present invention when executed by a processor.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic flow chart of a method for determining process parameters provided by an embodiment of the present invention;

[0026] Figure 2 A schematic flow chart of another method for determining process parameters provided by an embodiment of the present invention;

[0027] Figure 3 A schematic structural diagram of a device for determining process parameters provided by an embodiment of the present invention;

[0028] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Figure 1The present invention provides a flowchart of a method for determining process parameters according to an embodiment of the present invention. This embodiment is applicable to the case of determining the optimal process parameters for producing a product during the process of controlling the moisture content of the product. The method can be executed by a process parameter determination device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. In this embodiment, the electronic device can be a master control device in the process of controlling the moisture content of the product, such as a computer device and a server. Figure 1 As shown, the method includes:

[0032] S101. Combine multiple first candidate parameter values of various process parameter items to obtain multiple first process parameter groups, and determine a first preference rate of a product corresponding to each first process parameter group.

[0033] Among them, the process parameter items are process factor items that affect the moisture content of the product during the production process of controlling the moisture content of the product; in this embodiment, the process parameter items can be steam flow rate and hot air speed, etc. The first candidate parameter value is the value of the process parameter corresponding to each process parameter item. In this embodiment, the first candidate parameter value of each process parameter item can be selected from several values within the parameter default range of the process parameter item. The parameter default range is the default or commonly used parameter range in the process, and the parameter requirement range is the maximum requirement range that can be selected for each process parameter item in the process. The parameter default range is smaller than the parameter requirement range. For example, the parameter default range is (50, 70) and the parameter requirement range is (30, 90). Each first process parameter group includes a first candidate parameter value corresponding to each process parameter item. The first preference rate is the preference probability obtained after preparing test samples based on the candidate parameter values in each group of first process parameter groups and performing sensory quality evaluation on the test samples corresponding to each group of first process parameter groups. In this embodiment, sensory quality evaluation is performed on the test samples corresponding to each first process parameter group, and the first preference rate can be obtained based on a pre-trained model, a product quality evaluation instrument or manual evaluation.

[0034] Specifically, when using raw materials with a higher water content to prepare products with a lower water content or a water content of zero, it is necessary to control the water content of the product during the preparation process. There are many process factors that control the water content of the product, such as steam flow, hot air speed, and processing time. Among these factors, changes in each factor or changes in two factors will affect the water content of the final product. Therefore, these factors can be used as process parameter items, and the default value corresponding to each process parameter item or several values within the default range of values, such as the maximum value and the middle value, are determined as multiple first candidate parameter values of the process parameter item. And, the multiple first candidate parameter values of each process parameter item are combined to obtain multiple first process parameter groups.

[0035] For example, in one implementation, a first candidate parameter value of a process parameter item is randomly selected each time to obtain a first process parameter group. In another implementation, a process parameter item is used as a reference process parameter item, and first a first candidate parameter value is selected. Then, combinations of the first candidate parameter value and multiple first candidate parameter values of other process parameter items are traversed to obtain multiple first process parameter groups that all contain the first candidate parameter value of the reference process parameter item. Then, another first candidate parameter value is selected, and the same method is performed until all first candidate parameter values of the reference process parameter item are traversed to obtain all first process parameter groups.

[0036] It is worth noting that the "product" in this embodiment can be a semi-finished product or a finished product obtained through the process corresponding to the process parameter item. The semi-finished product can be, for example, a component.

[0037] Alternatively, the product in this embodiment may be a plastic product obtained through an injection molding process. Alternatively, the product in this embodiment may be a product used in the tobacco industry. For example, the product in this embodiment may be a product obtained through a thin sheet drying process in the tobacco industry.

[0038] Specifically, after obtaining a plurality of first process parameter groups, the first optimization rate of the corresponding product can be determined for each first process parameter group.

[0039] Exemplarily, test products are prepared according to the first candidate parameter value of each process parameter item in the first process parameter group, and after preparation, these test products are evaluated and tested in turn. In one implementation method, a moisture content evaluation model is pre-trained to evaluate whether the moisture content of these test products meets the requirements, and the test products are put into the trained moisture content evaluation model to obtain the first preference rate of the products in each first process parameter group. In another implementation method, a moisture content detection instrument is directly used to place the test products into the detection instrument to obtain the moisture content of each test product, and then the first preference rate of the products in each first process parameter group is calculated according to the set moisture content requirements. In another implementation method, multiple people are organized to evaluate the test products, and the evaluation method is a ranking evaluation method, that is, each person ranks the test products, and after multiple people have finished ranking each test product, the first preference rate of the products in each first process parameter group is calculated according to the ranking results of different people obtained for the products in each first process parameter group.

[0040] In this embodiment, several parameter values within the default parameter range of each process parameter item are selected as first candidate parameter values, and multiple first candidate parameter values of each process parameter item are combined to obtain multiple first process parameter groups. This can achieve possible coverage of the quality of products produced under fewer and different parameter values for all process parameter items, ensure that various quality conditions of the product are covered when the parameter values of different process parameter items change, avoid incomplete evaluation due to focusing only on the parameter values of some process parameter items, and improve the accuracy of product quality evaluation.

[0041] S102. Determine, according to the first optimization ratio, the first coefficient corresponding to each process parameter item and the second coefficient between every two process parameter items.

[0042] The first coefficient is used to characterize the degree of influence of the parameter value of each process parameter item on the optimization rate, and the second coefficient is used to characterize the degree of influence of the interaction between every two process parameter items on the optimization rate.

[0043] Specifically, since the first preference rate of the product corresponding to each first process parameter group has been determined, the degree of influence of each process parameter item on the preference rate when the parameter value changes can be determined based on the first preference rate, and the degree of influence of the parameter values of each two process parameter items on the preference rate under the interaction of the parameter values of these two process parameter items when the parameter values of these two process parameter items change can be determined.

[0044] For example, for the first coefficient, based on the first preference rate of the product corresponding to each first process parameter group and the parameter value of the process parameter item in each first process parameter group, a correlation analysis, regression analysis, variance analysis, or other mathematical analysis can be performed on the process parameter items to obtain the first coefficient. Furthermore, for the second coefficient and two process parameter items, parameter groups in which one process parameter item has a constant parameter value while the other has a variable parameter value, and one process parameter item has a variable parameter value while the other has a constant parameter value, are selected in the first process parameter group, along with the first preference rates of the products corresponding to these first process parameter groups. Based on the above data, a two-way variance analysis, response analysis, marginal effect analysis, or other mathematical analysis can be performed on the two process parameter items to obtain the second coefficient.

[0045] In this embodiment, a first coefficient corresponding to each process parameter item is determined based on the first preference ratio, and a second coefficient corresponding to each pair of process parameter items is determined based on the first preference ratio. This allows for quantification of the impact of changes in the parameter value of each process parameter item, and of the interaction between each pair of process parameter items, on the product preference ratio. Based on the first and second coefficients, this provides a basis for quickly and accurately selecting optimal process parameter values based on the subsequent quantification of the impact of changes in the process parameter item values on the preference ratio.

[0046] S103. Determine the optimal rate regression relationship of the process parameter items based on the first coefficients and the second coefficients.

[0047] The optimization rate regression relationship is used to determine the optimization rate of the product corresponding to each process parameter group obtained after random combination of different parameter values of all process parameter items.

[0048] Specifically, since the first coefficient represents the degree of influence of the parameter value of each process parameter item on the preference rate, the first coefficient can be considered the "slope" of each process parameter item. That is, when the first coefficient is positive, the larger the first coefficient, the larger the parameter value of the process parameter item, the stronger the influence on the preference rate, and the higher the preference rate. When the first coefficient is negative, the smaller the first coefficient, the smaller the parameter value of the process parameter item, the stronger the influence on the preference rate, and the higher the preference rate. Furthermore, since the second coefficient represents the degree of influence of the interaction between each two process parameter items on the preference rate, the second coefficient can be considered the "slope" of the two process parameter items. That is, when the second coefficient is positive, the larger the second coefficient, the larger the product of the parameter values of the two process parameter items, the stronger the influence on the preference rate, and the higher the preference rate. When the second coefficient is negative, the smaller the second coefficient, the smaller the product of the parameter values of the two process parameter items, the stronger the influence on the preference rate, and the higher the preference rate. Based on the above, a preferred rate regression relationship including all process parameter items can be determined according to the first coefficient and the second coefficient. In this preferred rate regression relationship, all process parameter items and the relationship between each two process parameter items when they interact are included.

[0049] In this embodiment, the regression relationship for the optimal ratio of process parameters is determined based on the first and second coefficients. This implements adaptive analysis based on the parameters of all process parameters. This reduces the problem in the prior art of inaccurate selection of the optimal process parameter set due to operational errors or subjective factors affecting the quality evaluation results of a particular test product. Furthermore, this facilitates the analysis of parameter values and provides a clearer analytical basis for subsequently accurately determining the process parameter set that achieves the highest product optimal ratio.

[0050] S104. According to the regression relationship of the preference rate and multiple second process parameter groups, the second process parameter group with the largest second preference rate of the corresponding product is determined as the target process parameter group.

[0051] The second candidate parameter value corresponding to each process parameter item in the second process parameter group may partially coincide with the first candidate parameter value corresponding to the process parameter item in the first process parameter group. In this embodiment, the second candidate parameter value corresponding to each process parameter item in the second process parameter group may be the same as the first candidate parameter value, or may be a plurality of second candidate parameter values determined based on the required range of each process parameter item. In this embodiment, the target process parameter group is the optimal process parameter group determined when controlling the moisture content of the product.

[0052] Specifically, each second process parameter group is substituted into the optimization rate regression relationship. That is, the second candidate parameter value of each process parameter item in the second process parameter group is substituted into the corresponding process parameter item in the optimization rate regression relationship to obtain the second optimization rate of the product corresponding to the second process parameter group. The second optimization rates of all second process parameter groups are compared, and the second process parameter group with the largest second optimization rate is determined as the target process parameter group.

[0053] In this embodiment, the second preference rate regression relationship is used to determine the second preference rate of the product corresponding to each second process parameter group, and the second process parameter group with the largest second preference rate is determined as the target process parameter group, which solves the current problem of low accuracy in selecting the target process parameter group due to errors in the quality evaluation results of the test products. The second preference rate of the product corresponding to the second process parameter group is determined based on the preference rate regression relationship, which eliminates the need to produce the product corresponding to the second process parameter group and evaluate the product to select the optimal target process parameter group. While accurately determining the target process parameter group, it reduces the cost of producing the test product, quickly selects the target process parameter group, and reduces the time for determining the target process parameter group.

[0054] The method for determining process parameters provided by an embodiment of the present invention, on the one hand, selects several parameter values within the default parameter range of each process parameter item as the first candidate parameter value, combines multiple first candidate parameter values of each process parameter item, and obtains multiple first process parameter groups, which can achieve the possible coverage of the quality of products produced under fewer and different parameter values for all process parameter items, ensuring that various quality conditions of the product are covered when the parameter values of different process parameter items change, avoiding the incomplete evaluation caused by only focusing on the parameter values of some process parameter items, and improving the accuracy of product quality evaluation. On the other hand, determining the first coefficient corresponding to each process parameter item, and determining the second coefficient corresponding to each two process parameter items, can achieve the quantification of the degree of influence of each process parameter item when the parameter value changes and the interaction between each two process parameter items when the parameter value changes on the product preference rate. Based on the first coefficient and the second coefficient, a basis is provided for the subsequent quantification of the degree of influence of the change in the numerical value of the process parameter item on the preference rate, and the rapid and accurate selection of the parameter value of the better process parameter item. Furthermore, based on the first coefficient and the second coefficient, the regression relationship of the preference rate of the process parameter items is determined, which realizes the adaptive analysis based on the parameters of all process parameter items, reducing the problem of low accuracy in selecting the optimal process parameter group due to the influence of operational errors or subjective factors on the quality evaluation results of a certain test product in the prior art. Further, it facilitates the analysis of parameter values, and provides a clearer analysis basis for accurately determining the process parameter group that makes the product's preference rate the highest. Finally, the second preference rate of the product corresponding to each second process parameter group is determined by the regression relationship of the preference rate, and the second process parameter group with the largest second preference rate is determined as the target process parameter group, which solves the current problem of low accuracy in selecting the target process parameter group due to errors in the quality evaluation results of the test product, and realizes that there is no need to produce the product corresponding to the second process parameter group and evaluate the product to select the optimal target process parameter group. While accurately determining the target process parameter group, it reduces the cost of producing the test product, quickly selects the target process parameter group, and reduces the time to determine the target process parameter group.

[0055] Figure 2 This is a flow chart of another method for determining process parameters provided by an embodiment of the present invention. Based on the above embodiment and other examples, this embodiment provides a detailed description of the steps of "determining the first preference rate of the product corresponding to each first process parameter group", "determining the first coefficient corresponding to each process parameter item and the second coefficient between each two process parameter items according to the first preference rate", and "determining the regression relationship of the preference rate of the process parameter items according to each of the first coefficients and the second coefficients". Figure 2 As shown, the method includes:

[0056] S201 : Combine multiple first candidate parameter values of various process parameter items to obtain multiple first process parameter groups.

[0057] Specifically, several parameter values are selected from the default parameter range of each process parameter item as first candidate parameter values, and multiple first candidate parameter values of each process parameter item are combined. Each obtained first process parameter group will include a first candidate parameter value for all process parameter items.

[0058] S202: Classify the first process parameter group to obtain multiple first process parameter group classes.

[0059] The first candidate parameter values of the target process parameter items in each first process parameter group are the same.

[0060] Specifically, a process parameter item is taken as a target process parameter item, and parameter groups in the first process parameter group that all contain the same first candidate parameter value of the target process parameter item are taken as a first process parameter group class.

[0061] For example, assuming that the process parameter items are parameter item A and parameter item B, the first candidate parameter values corresponding to parameter item A are a1, a2, and a3, and the first candidate parameter values corresponding to parameter item B are b1, b2, and b3, then the first process parameter group can be obtained: (a1, b1), (a2, b2), (a3, b3), (a1, b2), (a2, b3), (a1, b3), (a2, b1), (a3, b1), (a3, b2). Taking parameter item A as the target process parameter item, the first process parameter group is classified according to the above classification method, and the first process parameter group classes can be obtained: [(a1, b1), (a1, b2), (a1, b3)], [(a2, b1), (a2, b2), (a2, b3)], [(a3, b1), (a3, b2), (a3, b3)].

[0062] S203 . For each first process parameter group class, obtain multiple ratings of products corresponding to each first process parameter group included therein.

[0063] Each rating is obtained by treating the first process parameter group as a group of evaluation groups and performing an intra-group evaluation on the products corresponding to all the first process parameter groups in the evaluation group.

[0064] Specifically, the multiple ratings of the products corresponding to each first process parameter group can be determined based on a pre-trained model, a product quality evaluation instrument, or manual evaluation.

[0065] For example, continuing with the above example, the first first process parameter group is [(a1, b1), (a1, b2), (a1, b3)]. In one implementation, the data of the first process parameter group in the first process parameter group is input into the model, and 10 model output ratings are obtained. Similarly, in another implementation, the test product corresponding to each first process parameter group in the first first process parameter group is input into the instrument, and 10 moisture content scores are obtained from the instrument. Based on the moisture content scores and the pre-set moisture content optimization index, 10 quality ratings corresponding to each first process parameter group in the first first process parameter group can be determined. Similarly, in another implementation, 10 experts are selected to score the test product corresponding to each first process parameter group in the first first process parameter group, and 10 ratings are obtained for each first process parameter group. In the above, all ratings are performed by comparing (a1, b1), (a1, b2), and (a1, b3). Each first process parameter group has 10 ratings.

[0066] S204 : Determine a first priority rate of the product corresponding to each first process parameter group according to the multiple ratings corresponding to each first process parameter group and the quantity of each rating.

[0067] Specifically, a weight is set for each rating. For each first process parameter group, the total number of identical ratings is determined and multiplied by the corresponding weight to obtain a score for the identical rating. The scores for the different ratings are added together and divided by the sum of the scores for all ratings of all first process parameter groups in the first process parameter group class to obtain the first priority rate for the product corresponding to the first process parameter group.

[0068] For example, continuing the above example, assume that the ratings are divided into three levels, with the weight of the first level being 1, the weight of the second level being 2, and the weight of the third level being 3. (a1, b1) received 3 first-level ratings, 5 second-level ratings, and 2 third-level ratings; (a1, b2) received 2 first-level ratings, 4 second-level ratings, and 4 third-level ratings; and (a1, b3) received 1 first-level rating, 2 second-level ratings, and 7 third-level ratings. Then the first priority rate of the product corresponding to (a1, b1) is: (3*1+5*2+2*3) / (3*1+5*2+2*3+2*1+4*2+4*3+1*1+2*2+7*3)*100%=28.36%; the first priority rate of the product corresponding to (a1, b2) is: (2*1+4*2+4*3) / (3*1+5*2+2*3+2*1+4*2+4*3+1*1+2*2+7*3)*100%=32.84%; the first priority rate of the product corresponding to (a1, b3) is: (1*1+2*2+7*3) / (3*1+5*2+2*3+2*1+4*2+4*3+1*1+2*2+7*3)*100%=38.81%.

[0069] Optionally, in actual implementation, the above steps S201 to S204 can be implemented based on a method of establishing an orthogonal test model, as follows:

[0070] First, enter each process parameter into the orthogonal test table. The first process parameter in the table is used as the target process parameter. All parameters with the same first candidate parameter value are grouped together to determine the first process parameter group. When the number of tests is an odd number, n, the number of groups is n / 3; when the number of tests is an even number, n, the number of groups is n / 2.

[0071] Taking the four-factor three-level orthogonal test table in Table 1 as an example, in 9 experiments, the three candidate parameter values of the process parameter item of steam flow rate, 250, 300 and 350, were divided into 3 groups for testing. Each process parameter group includes three candidate parameter values of steam flow rate, hot air speed, process parameter item 3 and process parameter item 4. Among them, the candidate parameter values of hot air speed include 0.25, 0.35 and 0.45. And, "(1)", "(2)" and "(3)" in the table represent the numbers of the three candidate parameter values corresponding to each process parameter item. According to the first process parameter group in the table, the test product was prepared, and the same number of judges of more than or equal to 8 people were organized to conduct product quality rating. The rating method adopted the method of intra-group ranking evaluation. After the rating of all judges was completed, the first preference rate of each first process parameter group can be calculated according to the above calculation method, and the following first preference rate results were obtained.

[0072] Table 1 Four-factor three-level orthogonal test table

[0073]

[0074] In this embodiment, the first process parameter groups are classified based on the first candidate parameter value of the target process parameter item to obtain a plurality of first process parameter group categories. The first process parameter group categories are then used as a group of evaluation groups. After the products corresponding to all the first process parameter groups in the evaluation group are evaluated within the group, a first preference rate is obtained. This realizes the evaluation of the control variables when rating each first process parameter group. The parameter value of one of the process parameter items is controlled to remain unchanged for evaluation, thereby reducing the interference of one variable and helping to determine whether all the process parameter items are independent of each other.

[0075] S205. According to the first optimization rate, determine the first coefficient corresponding to each process parameter item, the second coefficient between every two process parameter items, the center value of each process parameter item, and the half-spacing of each process parameter item.

[0076] The center value and half-spacing of each process parameter item are used to characterize the value range of the parameter value of the process parameter item.

[0077] Specifically, the first coefficient, the second coefficient, the center value, and the half-spacing may be determined according to the following steps:

[0078] (1) For each process parameter item, a plurality of first process parameter groups including the maximum values among the first candidate parameter values of the process parameter item are determined as the first target parameter group, and a first coefficient corresponding to the process parameter item is determined according to a first preference rate of the product corresponding to the first target parameter group.

[0079] For example, following the above example, the three candidate parameter values of the process parameter item of steam flow are 250, 300 and 350. Therefore, the first process parameter group containing the candidate parameter values of steam flow of 250 and 350 can be determined as the first target parameter group, that is, the first process parameter group corresponding to the two groups of first process parameter group classes numbered 1 and 3 in Table 1 is determined as the first target parameter group.

[0080] And, the first coefficient can be determined as follows:

[0081] (1) Determine the first coefficient corresponding to the process parameter item based on the first preference rate of the product corresponding to the first target parameter group containing the maximum value of the process parameter item, the number of first target parameter groups containing the maximum value, the first preference rate of the product corresponding to the first target parameter group containing the minimum value of the process parameter item, and the number of first target parameter groups containing the minimum value.

[0082] Specifically, the formula for determining the first coefficient is: the first coefficient corresponding to the process parameter item = (the sum of the first preference rates of the products corresponding to the first target parameter group containing the maximum value of the process parameter item / the number of first target parameter groups containing the maximum value - the sum of the first preference rates of the products corresponding to the first target parameter group containing the minimum value of the process parameter item / the number of first target parameter groups containing the minimum value) / 2.

[0083] For example, continuing with the above example, taking steam flow as an example, the first coefficient corresponding to steam flow = [(34.4+28.8+33.3) / 3-(31.8+36.5+33.3) / 3)] / 2 = -0.85. Among them, 34.4, 28.8, and 33.3 correspond to the first optimization ratios of the first target parameter group with the first process parameter group numbers 7, 8, and 9, that is, the first process parameter group with the maximum steam flow. 31.8, 36.5, and 33.3 correspond to the first optimization ratios of the first target parameter group with the first process parameter group numbers 1, 2, and 3, that is, the first process parameter group with the minimum steam flow.

[0084] Similarly, taking the hot air speed as an example, the first coefficient corresponding to the hot air speed = [(36.5+34.9+28.8) / 3-(31.8+31.5+34.4) / 3] / 2≈0.42. The result can be rounded according to the preset accuracy.

[0085] In this embodiment, the first process parameter group including the maximum and minimum values of the process parameter items is used as the first target parameter group, and the first coefficient of the process parameter items is calculated according to the above method, thereby realizing the quantification of the degree of influence of each process parameter item on the final optimization rate when the value changes.

[0086] (2) For every two process parameter items, a plurality of first process parameter groups including the maximum values of the first candidate parameter values of the two process parameter items are determined as second target parameter groups, and a second coefficient between the two process parameter items is determined based on the first preference rate of the product corresponding to the second target parameter group.

[0087] For example, following the above example, taking steam flow rate and hot air speed as examples, the maximum values of the candidate parameter values of steam flow rate are 250 and 350, and the maximum values of the candidate parameter values of hot air speed are 0.25 and 0.45. Therefore, the first process parameter group numbered 1, 2, 7 and 8 in Table 1 can be selected as the second target parameter group.

[0088] And, the second coefficient can be determined as follows:

[0089] (1) Determine the second coefficient between the two process parameter items based on the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items, the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item, the first preference rate of the product corresponding to the second target parameter group containing the minimum values of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item.

[0090] Specifically, the formula for determining the second coefficient is: the second coefficient between two process parameter items = [(the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items - the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item) - (the first preference rate of the product corresponding to the second target parameter group containing the minimum value of each of the two process parameter items - the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item)] / 4.

[0091] For example, continuing with the above example, the second coefficient between steam flow and hot air speed = [(28.8-36.5)-(34.4-31.8)] / 4 = -2.575. Here, 28.8 is the first preferred ratio corresponding to the second target parameter group with the first process parameter group number being 8, 36.5 is the first preferred ratio corresponding to the second target parameter group with the first process parameter group number being 2, 34.4 is the first preferred ratio corresponding to the second target parameter group with the first process parameter group number being 7, and 31.8 is the first preferred ratio corresponding to the second target parameter group with the first process parameter group number being 1.

[0092] In this embodiment, the first process parameter group containing the maximum and minimum values of two process parameter items is used as the second target parameter group, and the second coefficient of the process parameter item is calculated according to the above method, so that when the parameter values of the two process parameter items change at the same time, the impact of the interaction between the numerical changes of the two process parameter items on the final optimization rate is quantified.

[0093] Optionally, before determining the second coefficient between two process parameter items, it is also possible to first determine whether there is an interactive relationship between the two process parameter items. The details are as follows:

[0094] (1) Determine whether there is an interactive relationship between two process parameter items based on the first data and the second data.

[0095] Among them, the first data is a value determined by the first preference rate of the product corresponding to the second target parameter group containing the maximum values of two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item; the second data is a value determined by the first preference rate of the product corresponding to the second target parameter group containing the minimum values of two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item.

[0096] Specifically, calculate whether [(the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items - the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item) - (the first preference rate of the product corresponding to the second target parameter group containing the minimum values of each of the two process parameter items - the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item)] / 2 is equal to 0. If it is equal to 0, it means that there is no interaction relationship between the two process parameter items; if it is not equal to 0, it means that there is an interaction relationship between the two process parameter items.

[0097] Among them, (the first preference rate of the product corresponding to the second target parameter group containing the maximum values of two process parameter items - the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item) is the first data; (the first preference rate of the product corresponding to the second target parameter group containing the minimum values of two process parameter items - the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item) is the second data.

[0098] (2) If there is no interaction relationship between the two process parameter items, the second coefficient between the two process parameter items is determined to be zero.

[0099] Specifically, if the calculated result is zero, it indicates that there is no interaction relationship between the two process parameter items. In this case, the second coefficient between the two process parameter items can be directly determined to be zero.

[0100] (3) If there is an interactive relationship between the two process parameter items, determine and execute the step of "determining the second coefficient between the two process parameter items based on the first preferred rate of the product corresponding to the second target parameter group."

[0101] In this embodiment, before calculating the second coefficients of the two process parameter items, it is first determined whether the two process parameter items have an interactive relationship. This can clarify whether the interaction brought about by the simultaneous changes of the two process parameter items will affect the final optimization rate, providing a basis for establishing a regression relationship for the optimization rate.

[0102] (3) Determine the center value and half spacing of the process parameter item according to the maximum value among the first candidate parameter values of each process parameter item.

[0103] Specifically, the center value and half spacing of the process parameter items can be determined according to the following steps:

[0104] (1) Determine the maximum and minimum values of the first candidate parameter values of the process parameter item.

[0105] For example, taking hot air speed as an example, the maximum value of the first candidate parameter value of hot air speed is 0.45 and the minimum value is 0.25. Taking steam flow as an example, the maximum value of the first candidate parameter value of steam flow is 350 and the minimum value is 250.

[0106] (2) Add the maximum value to the minimum value and divide by two to obtain the value that is the center value.

[0107] For example, following the above example, it is possible to determine that the central value of the hot air velocity is (0.45+0.25) / 2=0.35, and the central value of the steam flow rate is (350+250) / 2=300.

[0108] (3) Subtract the minimum value from the maximum value and divide by two to obtain the value that is the half span.

[0109] For example, based on the above example, the half-spacing of the hot air velocity can be determined as (0.45-0.25) / 2=0.1, and the half-spacing of the steam flow rate can be determined as (350-250) / 2=50.

[0110] In this embodiment, the center value and half-spacing of each process parameter item are determined. In addition to clarifying the degree of deviation and the acceptable fluctuation range of the parameter value of each process parameter item, it also provides a linear adaptive analysis for subsequently establishing a regression relationship for the preferred rate. It also provides an acceptable fluctuation range for determining the extended value of each process parameter item based on the first candidate parameter value, which is conducive to the accurate selection of the extended value.

[0111] S206. Determine the optimal rate regression relationship of the process parameter items according to the first coefficient, the second coefficient, the center value, and the half spacing.

[0112] Specifically, the optimal rate regression relationship of the process parameter items can be determined according to the following steps:

[0113] (1) Determine a constant coefficient based on the first preferred ratios of the products corresponding to all first process parameter groups and the number of first process parameter groups.

[0114] For example, taking Table 1 as an example, the constant coefficient is the sum of all the first preference ratios in Table 1 divided by the number of first process parameter groups. That is, constant coefficient = (31.8 + 36.5 + 33.3 + 31.5 + 34.9 + 29.6 + 34.4 + 28.8 + 33.3) / 9 ≈ 32.68.

[0115] (2) Determine the optimal rate regression relationship of the process parameter items based on the constant coefficient, each first coefficient, second coefficient, center value and half spacing.

[0116] Specifically, the optimal rate regression relationship can be determined according to the following formula:

[0117] Pr=c+w1*[(x1-M1) / D1]+…+w i *[(x i -M i ) / D i ]+…+w N *[(x N -M N ) / D N ]+w 12 *{[(x1-M1) / D1]*[(x2-M2) / D2]}+...w ij *{[(x i -M i ) / D i ]*[(x j -M j ) / D j}+…+w (N-1)N * {[(x N-1 -M N-1 ) / D N-1 ]*[(x N -M N ) / D N ]}

[0118] Wherein, Pr is the second preferred ratio; c is a constant coefficient; N represents the number of process parameter items, i is an integer between 1 and N, j is an integer between 1 and N, and i and j are not equal; w i is the first coefficient corresponding to the i-th process parameter item; x i Indicates the parameter value of the i-th process parameter item, which is an unknown quantity; M i is the central value corresponding to the i-th process parameter item; D i is the half spacing corresponding to the i-th process parameter item; w ijis the second coefficient between the i-th process parameter item and the j-th process parameter item.

[0119] In this embodiment, the center value and half-spacing are introduced into the determination of the optimization rate regression relationship, achieving a linear adaptability analysis of the parameter values of the process parameter items. Furthermore, based on the effect of "clarifying the degree of deviation and acceptable fluctuation range of the parameter values of each process parameter item" brought about by the center value and half-spacing, the final optimization rate regression relationship can not only accurately calculate the optimization rate corresponding to each process parameter group when the process parameter item values are within the default range, but also accurately calculate the optimization rate corresponding to each process parameter group within the required range of values outside the default range of the process parameter item.

[0120] S207 , for each process parameter item, determine an expansion value corresponding to the process parameter item according to the center value of the process parameter item and the half spacing of the process parameter item, and combine the expansion values corresponding to the various process parameter items to obtain a third process parameter group.

[0121] The expanded value is the parameter value of the process parameter item selected after reasonably expanding the range corresponding to the first candidate parameter value of the process parameter item. The third process parameter group is the process parameter group obtained by combining the expanded values corresponding to each process parameter item.

[0122] Specifically, since there are certain limitations when only using the first candidate parameter value to select the target process parameter group, it is necessary to appropriately expand the range corresponding to the first candidate parameter value of the process parameter item to ensure that more parameter values can be selected within the required range of the process parameter item to determine the target process parameter group.

[0123] Therefore, before calculating the expansion value, the expansion benchmark can be determined based on the number of process parameter items. For example, the expansion benchmark = 2^(number of process parameter items / 4). That is, when the number of process parameter items is 2, the expansion benchmark is 1.414; when the number of process parameter items is 3, the expansion benchmark is 1.628; when the number of process parameter items is 4, the expansion benchmark is 2; and when the number of process parameter items is 5, the expansion benchmark is 2.378.

[0124] After that, the expansion value corresponding to the process parameter item can be determined based on the center value, half-spacing, and expansion benchmark of the process parameter item. For example, if the process parameter items are steam flow and hot air speed, the number is 2, and the expansion benchmark is 1.414. At this time, the expansion value corresponding to the steam flow = the center value corresponding to the steam flow ± half-spacing * expansion benchmark = 300 ± 50 * 1.414 ≈ {243; 357}. The expansion value corresponding to the hot air speed = the center value corresponding to the hot air speed ± half-spacing * expansion benchmark = 0.35 ± 0.1 * 1.414 ≈ {0.21; 0.49}. That is, the expansion values corresponding to the steam flow are 243 and 357, and the expansion values corresponding to the hot air speed are 0.21 and 0.49.

[0125] Finally, after obtaining the expansion value corresponding to each process parameter item, the expansion values corresponding to each process parameter item can be combined to obtain a third process parameter group. For example, continuing the above example, after obtaining the expansion values 243 and 357 corresponding to steam flow, and the expansion values 0.21 and 0.49 corresponding to hot air speed, the third process parameter group can be obtained: (243, 0.21), (243, 0.49), (357, 0.21), and (357, 0.49).

[0126] In this embodiment, the parameter value of each process parameter item is expanded based on the center value and half spacing of each process parameter item, which solves the problem of limitations in obtaining the target process parameter group by only using the parameters in the default parameter range of each process parameter item for testing, and realizes the reasonable expansion of the parameter range of each process parameter item.

[0127] S208 , determining all the first process parameter groups and the third process parameter groups as the second process parameter group.

[0128] Specifically, all first process parameter groups and third process parameter groups are combined to form a second process parameter group.

[0129] S209. Determine the second optimization rate of the product corresponding to the second process parameter group based on each second process parameter group and the optimization rate regression relationship.

[0130] Specifically, the parameter value corresponding to each process parameter item in the second process parameter group is substituted into the corresponding "x i ", the second optimization rate of the product corresponding to each second process parameter group can be determined.

[0131] For example, taking the second process parameter group (steam flow rate 243, hot air speed 0.21) as an example, the optimal rate regression relationship is as follows:

[0132] Pr=32.68-0.85*[(x1-300) / 50]+0.42*[(x2-0.35) / 0.1]-2.575*{[(x1-300) / 50]*[[(x2-0.35) / 0.1]}

[0133] =32.68-0.85*[(243-300) / 50]+0.42*[(0.21-0.35) / 0.1];-2.575*{[(243-300) / 50]*[(0.21-0.35) / 0.1]}

[0134] =28.95

[0135] Therefore, it can be known that the second preferred rate of the product corresponding to (steam flow rate 243, hot air speed 0.21) is 28.95.

[0136] For example, only the parameter values corresponding to the steam flow rate and hot air speed in Table 1 are used as the first candidate parameter values. After combining them, the first process parameter group is obtained, and the above-mentioned third process parameter group is added to obtain the second process parameter group as shown in Table 2, which also shows the second preferred rate of the product corresponding to each second process parameter group obtained after all the second process parameter groups are substituted into the preferred rate regression relationship.

[0137] Table 2 Example of the second optimization rate of products corresponding to the second process parameter group

[0138]

[0139]

[0140] In this embodiment, the expanded extended values are grouped and combined with the first process parameters to obtain a second process parameter group, which not only broadens the range of parameter values corresponding to each process parameter item, but also provides more and richer possibilities for selecting the target process parameter group.

[0141] S210. Determine the target process parameter group by taking the process parameter group corresponding to the largest second preferred rate among the second preferred rates of the products corresponding to the second process parameter groups.

[0142] Specifically, the second preference rates of the products corresponding to all second process parameter groups are compared, and the process parameter group corresponding to the largest preference rate is selected as the target process parameter group, that is, the parameter value corresponding to each process parameter item in the target process parameter group is the most preferred process parameter.

[0143] For example, in Table 2, the maximum second preferred ratio is 38.35, and its corresponding second process parameter set (steam flow rate 243, hot air speed 0.49) is the target process parameter set. Therefore, it can be seen that the production process is optimal when the steam flow rate is 243 kg / h and the hot air speed is 0.49 m / s.

[0144] In this embodiment, the process parameter group corresponding to the largest second preferred rate is selected as the target process parameter group, thereby determining the optimal process parameter group when controlling the moisture content of the product.

[0145] Figure 3 Schematic diagram of the structure of the device for determining process parameters provided by the embodiment of the present invention. Figure 3 As shown, the device includes:

[0146] The combination module 301 is used to combine multiple first candidate parameter values of each process parameter item to obtain multiple first process parameter groups, and determine the first preference rate of the product corresponding to each first process parameter group, wherein each first process parameter group includes a first candidate parameter value corresponding to each process parameter item.

[0147] Determination module 302 is used to determine the first coefficient corresponding to each process parameter item and the second coefficient between every two process parameter items based on the first optimization rate, wherein the first coefficient is used to characterize the degree of influence of the parameter value of each process parameter item on the optimization rate, and the second coefficient is used to characterize the degree of influence of the interaction between every two process parameter items on the optimization rate.

[0148] The calculation module 303 is used to determine the optimal rate regression relationship of the process parameter items based on the first coefficients and the second coefficients.

[0149] The selection module 304 is used to determine the second process parameter group with the largest second preference rate of the corresponding product as the target process parameter group based on the preference rate regression relationship and multiple second process parameter groups.

[0150] Optionally, to determine a first optimization rate of a product corresponding to each first process parameter group, the combination module 301 is specifically configured to:

[0151] The first process parameter group is classified to obtain multiple first process parameter group classes, wherein the first candidate parameter value of the target process parameter item in each first process parameter group class is the same; for each first process parameter group class, multiple ratings of the products corresponding to each first process parameter group included therein are obtained, wherein each rating is obtained by treating the first process parameter group class as a group of evaluation groups and performing an intra-group evaluation on all products corresponding to the first process parameter groups in the evaluation group; based on the multiple ratings corresponding to each first process parameter group and the number of each rating, the first priority rate of the products corresponding to the first process parameter group is determined.

[0152] Optionally, the second candidate parameter value corresponding to each process parameter item in the second process parameter group is partially identical to the first candidate parameter value corresponding to the process parameter item in the first process parameter group; and according to the first preference ratio, the first coefficient corresponding to each process parameter item and the second coefficient between every two process parameter items are determined respectively. The determination module 302 is specifically configured to:

[0153] According to the first optimization rate, determining the first coefficient corresponding to each process parameter item, the second coefficient between every two process parameter items, the center value of each process parameter item, and the half-spacing of each process parameter item, respectively. The center value and half-spacing of each process parameter item are used to characterize the value range of the parameter value of the process parameter item;

[0154] Based on the first coefficients and the second coefficients, the optimal rate regression relationship of the process parameter items is determined. The calculation module 303 is specifically used to:

[0155] The optimal rate regression relationship of the process parameter items is determined based on the first coefficient, the second coefficient, the center value and the half spacing.

[0156] Optionally, the determining module 302 is specifically configured to:

[0157] For each process parameter item, multiple first process parameter groups including the maximum values among the first candidate parameter values of the process parameter item are determined as the first target parameter group, and the first coefficient corresponding to the process parameter item is determined according to the first preference rate of the product corresponding to the first target parameter group; for every two process parameter items, multiple first process parameter groups including the maximum values among the first candidate parameter values of the two process parameter items are determined as the second target parameter group, and the second coefficient between the two process parameter items is determined according to the first preference rate of the product corresponding to the second target parameter group; according to the maximum value among the first candidate parameter values of each process parameter item, the center value and half spacing of the process parameter item are determined.

[0158] Optionally, according to the first optimization rate of the product corresponding to the first target parameter group, a first coefficient corresponding to the process parameter item is determined, and the determination module 302 is specifically configured to:

[0159] The first coefficient corresponding to the process parameter item is determined based on the first preference rate of the product corresponding to the first target parameter group containing the maximum value of the process parameter item, the number of first target parameter groups containing the maximum value, the first preference rate of the product corresponding to the first target parameter group containing the minimum value of the process parameter item, and the number of first target parameter groups containing the minimum value.

[0160] Optionally, according to the first optimization rate of the product corresponding to the second target parameter group, a second coefficient between two process parameter items is determined, and the determination module 302 is specifically configured to:

[0161] The second coefficient between the two process parameter items is determined based on the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items, the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item, the first preference rate of the product corresponding to the second target parameter group containing the minimum value of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item.

[0162] Optionally, the determining module 302 is further configured to:

[0163] Determine whether there is an interactive relationship between two process parameter items based on the first data and the second data; wherein the first data is a value determined based on the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item; the second data is a value determined based on the first preference rate of the product corresponding to the second target parameter group containing the minimum values of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item; if there is no interactive relationship between the two process parameter items, determine that the second coefficient between the two process parameter items is zero; if there is an interactive relationship between the two process parameter items, determine to execute the step of "determining the second coefficient between the two process parameter items based on the first preference rate of the product corresponding to the second target parameter group".

[0164] Optionally, according to the maximum value among the first candidate parameter values of each process parameter item, the center value and the half spacing of the process parameter item are determined. The determination module 302 is specifically configured to:

[0165] Determine the maximum and minimum values among the first candidate parameter values of the process parameter item; take the value obtained by adding the maximum value to the minimum value and dividing it by two as the center value; and take the value obtained by subtracting the minimum value from the maximum value and dividing it by two as the half span.

[0166] Optionally, based on the first coefficient, the second coefficient, the center value, and the half-spacing, a regression relationship of the optimization rate of the process parameter items is determined, and the calculation module 303 is specifically used to:

[0167] The constant coefficient is determined based on the first optimization rate of the products corresponding to all first process parameter groups and the number of first process parameter groups; the optimization rate regression relationship of the process parameter items is determined based on the constant coefficient, each first coefficient, second coefficient, center value and half spacing.

[0168] Optionally, the optimization rate regression relationship of the process parameter items is determined according to the constant coefficient, each first coefficient, the second coefficient, the center value, and the half spacing. The calculation module 303 is specifically used to:

[0169] The optimal rate regression relationship is determined according to the following formula:

[0170] Pr=c+w1*[(x1-M1) / D1]+…+w i *[(x i -M i ) / D i ]+…+w N *[(x N -M N ) / D N ]+w 12 *{[(x1-M1) / D1]*[(x2-M2) / D2]}+...w ij *{[(x i -M i ) / D i ]*[(x i -M j ) / D j ]}+…+w (N-1)N *{[(x N-1 -M N-1 ) / D N-1 ]*[(x N -M N ) / D N ]}

[0171] Wherein, Pr is the second preferred ratio; c is a constant coefficient; N represents the number of process parameter items, i is an integer between 1 and N, j is an integer between 1 and N, and i and j are not equal; w i is the first coefficient corresponding to the i-th process parameter item; x i Indicates the parameter value of the i-th process parameter item, which is an unknown quantity; M i is the central value corresponding to the i-th process parameter item; D i is the half spacing corresponding to the i-th process parameter item; w ijis the second coefficient between the i-th process parameter item and the j-th process parameter item.

[0172] Optionally, before determining the second process parameter group with the highest second preference rate for the corresponding product as the target process parameter group based on the preference rate regression relationship and the multiple second process parameter groups, the selection module 304 is further configured to:

[0173] For each process parameter item, determine an expansion value corresponding to the process parameter item according to the center value of the process parameter item and the half spacing of the process parameter item, combine the expansion values corresponding to the various process parameter items to obtain a third process parameter group; and determine all the first process parameter groups and the third process parameter group as a second process parameter group;

[0174] The selection module 304 is specifically used for:

[0175] According to each second process parameter group and the regression relationship between the optimization rate, the second optimization rate of the product corresponding to the second process parameter group is determined; the process parameter group corresponding to the largest second optimization rate among the second optimization rates of the products corresponding to the second process parameter groups is determined as the target process parameter group.

[0176] The device for determining process parameters provided in the embodiment of the present invention can execute the method for determining process parameters provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0177] Figure 4 Schematic diagram of the structure of an electronic device 4 provided for an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0178] like Figure 4As shown, the electronic device 4 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 4. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0179] Multiple components in the electronic device 4 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 4 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0180] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining process parameters.

[0181] In some embodiments, the method for determining process parameters can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 4 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining process parameters described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the method for determining process parameters in any other appropriate manner (e.g., by means of firmware).

[0182] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0183] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0184] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0186] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0187] A computing system may include a client and a server. The client and server are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0188] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining process parameters provided in any embodiment of the present invention.

[0189] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0190] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0191] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining process parameters, characterized in that: The method comprises: Combining multiple first candidate parameter values for each process parameter item to obtain multiple first process parameter groups, and determining a first preference rate for the product corresponding to each first process parameter group, wherein each first process parameter group includes a first candidate parameter value corresponding to each process parameter item; Determine, based on the first optimization ratio, a first coefficient corresponding to each process parameter item and a second coefficient between every two process parameter items, wherein the first coefficient is used to characterize the degree of influence of the parameter value of each process parameter item on the optimization ratio, and the second coefficient is used to characterize the degree of influence of the interaction between every two process parameter items on the optimization ratio; Determining a regression relationship of an optimization rate of a process parameter item based on each of the first coefficients and the second coefficients; According to the optimization rate regression relationship and multiple second process parameter groups, the second process parameter group with the largest second optimization rate for the corresponding product is determined as the target process parameter group.

2. The method for determining process parameters according to claim 1, wherein: Determining the first optimization rate of the product corresponding to each first process parameter group includes: Classifying the first process parameter group to obtain a plurality of first process parameter group classes, wherein the first candidate parameter value of the target process parameter item in each first process parameter group class is the same; For each first process parameter group class, obtain multiple ratings of products corresponding to each first process parameter group included therein, wherein each rating is obtained by treating the first process parameter group class as an evaluation group and performing an intra-group evaluation on the products corresponding to all first process parameter groups within the evaluation group; A first priority rate of the product corresponding to each first process parameter group is determined according to the multiple ratings corresponding to each first process parameter group and the number of each rating.

3. The method for determining process parameters according to claim 1, wherein: The second candidate parameter value corresponding to each process parameter item in the second process parameter group is partially identical to the first candidate parameter value corresponding to the process parameter item in the first process parameter group; Determining the first coefficient corresponding to each process parameter item and the second coefficient between every two process parameter items according to the first optimization rate includes: Determine, according to the first optimization rate, a first coefficient corresponding to each process parameter item, a second coefficient between every two process parameter items, a center value of each process parameter item, and a half-spacing of each process parameter item, respectively. The center value and half-spacing of each process parameter item are used to represent a value range of the parameter value of the process parameter item. Determining the optimal rate regression relationship of the process parameter items according to the first coefficients and the second coefficients includes: The optimization rate regression relationship of the process parameter items is determined based on the first coefficient, the second coefficient, the center value and the half spacing.

4. The method for determining process parameters according to claim 3, wherein: Determining, according to the first optimization rate, the first coefficient corresponding to each process parameter item, the second coefficient between every two process parameter items, the center value of each process parameter item, and the half spacing of each process parameter item, respectively, includes: For each process parameter item, determining a plurality of first process parameter groups including the maximum value among the first candidate parameter values of the process parameter item as a first target parameter group, and determining a first coefficient corresponding to the process parameter item according to a first preference rate of the product corresponding to the first target parameter group; For every two process parameter items, determine multiple first process parameter groups that each include the maximum values of the first candidate parameter values of the two process parameter items as second target parameter groups, and determine a second coefficient between the two process parameter items based on a first preference rate of the product corresponding to the second target parameter group; According to the maximum value of the first candidate parameter values of each process parameter item, the center value and the half spacing of the process parameter item are determined.

5. The method for determining process parameters according to claim 4, characterized in that: The determining of the first coefficient corresponding to the process parameter item according to the first optimization rate of the product corresponding to the first target parameter group includes: The first coefficient corresponding to the process parameter item is determined based on the first preference rate of the product corresponding to the first target parameter group containing the maximum value of the process parameter item, the number of first target parameter groups containing the maximum value, the first preference rate of the product corresponding to the first target parameter group containing the minimum value of the process parameter item, and the number of first target parameter groups containing the minimum value.

6. The method for determining process parameters according to claim 4, wherein: The determining of the second coefficient between the two process parameter items according to the first optimization rate of the product corresponding to the second target parameter group includes: The second coefficient between the two process parameter items is determined based on the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items, the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item, the first preference rate of the product corresponding to the second target parameter group containing the minimum value of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item.

7. The method for determining process parameters according to claim 6, wherein: The method further comprises: Determining whether there is an interactive relationship between two process parameter items based on the first data and the second data; wherein the first data is a value determined based on the first preference rate of the product corresponding to the second target parameter group containing the maximum values of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the minimum value of one process parameter item and the maximum value of another process parameter item; and the second data is a value determined based on the first preference rate of the product corresponding to the second target parameter group containing the minimum values of each of the two process parameter items, and the first preference rate of the product corresponding to the second target parameter group containing the maximum value of one process parameter item and the minimum value of another process parameter item; If there is no interaction relationship between the two process parameter items, then the second coefficient between the two process parameter items is determined to be zero; If there is an interactive relationship between the two process parameter items, the step of "determining the second coefficient between the two process parameter items based on the first preference rate of the product corresponding to the second target parameter group" is determined to be executed.

8. The method for determining process parameters according to claim 4, wherein: The determining of the center value and the half spacing of each process parameter item according to the maximum value among the first candidate parameter values of each process parameter item includes: Determining a maximum value and a minimum value among first candidate parameter values of the process parameter item; The value obtained by adding the maximum value to the minimum value and dividing by two is used as the central value; A value obtained by subtracting the minimum value from the maximum value and dividing the result by two is used as the half span.

9. The method for determining process parameters according to claim 3, wherein: Determining the optimal rate regression relationship of the process parameter items according to the first coefficient, the second coefficient, the center value, and the half spacing includes: Determining a constant coefficient according to the first optimization rates of the products corresponding to all the first process parameter groups and the number of the first process parameter groups; The optimization rate regression relationship of the process parameter items is determined according to the constant coefficient, each of the first coefficients, the second coefficient, the center value and the half spacing.

10. The method for determining process parameters according to claim 9, wherein: Determining the optimal rate regression relationship of the process parameter item according to the constant coefficient, each of the first coefficients, the second coefficient, the center value, and the half spacing includes: The optimization rate regression relationship is determined according to the following formula: Pr=c+w1*[(x1-M1) / D1]+...+w i *[(x i -M i ) / D i |+...+w N *[(x N -M N ) / D N ]+w2*}[(x1-M1) / D1]*[(x2-M2) / D2]}+...w ij *{[(x i -M i ) / D i ]*[(x j -M j ) / D j ]}+...+w (N-1)N *{[(x N-1 -M N-1 ) / D N-1 ]*[(x N -M N ) / D N ]} Wherein, Pr is the second preferred ratio; c is a constant coefficient; N represents the number of process parameter items, i is an integer between 1 and N, j is an integer between 1 and N, and i and j are not equal; w i is the first coefficient corresponding to the i-th process parameter item; x i Indicates the parameter value of the i-th process parameter item, which is an unknown quantity; M i is the central value corresponding to the i-th process parameter item; D i is the half spacing corresponding to the i-th process parameter item; w ij is the second coefficient between the i-th process parameter item and the j-th process parameter item.

11. The method for determining process parameters according to claim 3, wherein: Before determining the second process parameter group with the largest second preference rate of the corresponding product as the target process parameter group based on the preference rate regression relationship and the plurality of second process parameter groups, the method includes: For each process parameter item, determine an extension value corresponding to the process parameter item according to a center value of the process parameter item and a half-spacing of the process parameter item, and combine the extension values corresponding to the respective process parameter items to obtain a third process parameter group; Determining all the first process parameter groups and the third process parameter group as the second process parameter group; The step of determining the second process parameter group with the highest second preference rate for the corresponding product as the target process parameter group based on the preference rate regression relationship and the plurality of second process parameter groups includes: Determining a second preferred rate of the product corresponding to each second process parameter group according to the preferred rate regression relationship; The target process parameter group is determined as the process parameter group corresponding to the largest second preferred rate among the second preferred rates of the products corresponding to the second process parameter groups.

12. The method for determining process parameters according to any one of claims 1 to 11, characterized in that: The target process parameter group is the optimal process parameter group determined when controlling the moisture content of the product.

13. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the process parameters according to any one of claims 1 to 12.

14. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the process parameters according to any one of claims 1 to 12 is implemented.

Images