Recommended methods for production process parameters and related equipment, program products and storage media

Abstract

This application provides a method for recommending production process parameters based on abnormal operating conditions, along with related equipment, program products, and storage media. The method includes: determining a first adjustment range for a first process parameter, where the first process parameter is an adjustable process parameter affecting product performance indicators during production; selecting N+1 process parameter values ​​from the first adjustment range; inputting the N+1 process parameter values ​​into a first mathematical model to obtain N+1 sets of predicted values ​​for product performance indicators; inputting the N+1 sets of predicted values ​​for product performance indicators into an indicator evaluation model to obtain N+1 indicator evaluation values; determining a first adjustment value among the N+1 process parameter values ​​based on the N+1 indicator evaluation values; and determining a recommended value for the first process parameter of the product based on the first adjustment value. Using this application embodiment, recommended values ​​for adjustable process parameters can be obtained through a prediction algorithm, improving production performance indicators and efficiency.

Description

Technical Field

[0001] This application relates to the field of manufacturing processes, and in particular to a method for recommending manufacturing process parameters based on abnormal operating conditions, as well as related equipment, program products, and storage media. Background Technology

[0002] With the development of science and technology, the requirements and demands for production processes are becoming increasingly stringent. Numerous factors influencing production lead to complex operating conditions and a large number of process parameters. When any process parameter (such as pressure or hydrogen content) undergoes abnormal changes due to uncontrollable factors like equipment load, continued production will negatively impact production indicators. To address these parameter variations, production personnel typically adjust the parameters based on their accumulated experience under complex conditions. However, this often results in inaccurate, inefficient, and untimely adjustments, ultimately affecting both the quality and efficiency of the production process. Summary of the Invention

[0003] This application discloses a method for recommending production process parameters based on abnormal operating conditions, as well as related equipment, program products, and storage media. It can obtain recommended values ​​of production equipment process parameters through prediction algorithms when abnormal changes occur in process parameters, thereby improving product performance indicators and production efficiency.

[0004] In a first aspect, embodiments of this application provide a method for recommending production process parameters based on abnormal operating conditions, characterized in that it includes:

[0005] A first adjustment range is determined for the first process parameter, wherein the first process parameter is an adjustable process parameter that affects the product performance indicators in production, and the first adjustment range is an adjustment range determined based on the first upper limit and the first lower limit of the first process parameter in the design scorecard.

[0006] Select N+1 process parameter values ​​from the first adjustment range, where N is an integer greater than 1;

[0007] The N+1 process parameter values ​​are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators. The predicted values ​​of the N+1 sets of product performance indicators are then input into the indicator evaluation model to obtain N+1 indicator evaluation values. The indicator evaluation values ​​are used to evaluate the overall closeness of the predicted value of each set of product performance indicators in the multiple sets of predicted values ​​of product performance indicators corresponding to the N+1 process parameter values ​​to the corresponding set of product performance target values.

[0008] The first adjustment value among the N+1 process parameter values ​​is determined based on the N+1 index evaluation values, wherein the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 index evaluation values.

[0009] The recommended values ​​for the first process parameters of the product are determined based on the first adjustment value.

[0010] In the above method, when process parameters change abnormally, a recommended value for the first process parameter (i.e., the adjustable process parameter that needs adjustment) is predicted. Specifically, the process parameter with the highest evaluation value within the first adjustment range is selected as the recommended value for the first process parameter, rather than relying on production personnel manually adjusting the process parameters based on accumulated experience and using the manually adjusted parameter as the recommended value. This method enables timely and accurate acquisition of recommended values ​​for the adjustable process parameters that need adjustment, even when production conditions undergo complex changes and multiple adjustable process parameters require adjustment. Production personnel can then adjust the process parameters based on these recommended values, improving product performance and adjustment efficiency.

[0011] It should be noted that under complex operating conditions, for adjustable process parameters (the first process parameter) that need adjustment, the recommended value of the first process parameter is obtained through a prediction method; for non-adjustable process parameters that need adjustment, they are usually treated as abnormal parameters, and the predicted value of the abnormal parameters is used for production; for parameters that do not need adjustment, they can be understood as parameters under normal operating conditions, and the target value of the process parameter in the benchmark operating condition scorecard is used for production (i.e., the process parameter value corresponding to the optimal product performance index).

[0012] It should be noted that the index evaluation value is used to evaluate the overall closeness between the predicted value of each set of product performance indicators and the corresponding set of product performance target values ​​among the predicted values ​​of multiple sets of product performance indicators corresponding to the process parameters. It can be understood as comparing the closeness between the predicted value of each set of product performance indicators and the target value of each set of product performance indicators, and finally taking the results of multiple comparisons as the overall closeness. The closer the closeness, the higher the corresponding index evaluation value.

[0013] In another possible implementation of the first aspect, the step of inputting the N+1 process parameter values ​​into the first mathematical model to obtain N+1 sets of predicted product performance indicators includes:

[0014] Determine a first reference value for the second process parameter, wherein the first reference value is the target value of the second process parameter in the benchmark scorecard;

[0015] Determine a second reference value for a third process parameter and an abnormal predicted value for a fourth process parameter, wherein the type of the third process parameter is an adjustable process parameter, the type of the fourth process parameter value is a non-adjustable process parameter, and the second process parameter, the third process parameter, the fourth process parameter, and the first process parameter belong to the set of independent variables of the first mathematical model;

[0016] If the recommended value exists for the third process parameter, then the second reference value is the recommended value for the third process parameter. If the recommended value does not exist for the third process parameter, then the second reference value is the target value for the third process parameter, wherein the target value for the third process parameter is the target value for the third process parameter in the benchmark working condition scorecard.

[0017] The N+1 process parameter values, the first reference value, the second reference value, and the abnormal prediction value of the fourth process parameter are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators.

[0018] In the above method, when complex operating conditions occur, the types of process parameters may include parameters that do not need adjustment under normal operating conditions, adjustable process parameters that need adjustment under abnormal operating conditions, and non-adjustable process parameters that need adjustment under abnormal operating conditions. Among them, the first process parameter is the process parameter for which the predicted value of product performance index is being calculated; the second process parameter is the process parameter that does not need adjustment under normal operating conditions; the third process parameter is the recommended value of the first process parameter that has completed the recommended value algorithm or the default value of the first process parameter that has not completed the recommended value algorithm (the target value of the benchmark operating condition scorecard) when abnormal operating conditions occur. At this time, the third process parameter is judged. If a recommended value exists, the recommended value is used; if no recommended value exists, the target value is used; the fourth process parameter is the non-adjustable process parameter under abnormal operating conditions.

[0019] Specifically, the set of independent variables in the first mathematical model is typically a set of first, second, third, and fourth process parameters. When calculating the predicted value of the product performance index for N+1 process parameter values ​​within the first adjustment range of a given first process parameter, it is necessary to first determine the initial values ​​for the remaining process parameters in the independent variable set, excluding the first process parameter. This can be understood as follows: if a recommended value exists for the third process parameter, it is used as the initial value; if no recommended value exists for the remaining third process parameters, the target value is used as the initial value. The second process parameter uses the target value from the benchmark scorecard as its initial value; and the fourth process parameter uses the abnormal predicted value as its initial value. This method considers that the predicted value of the product performance index is affected by all process parameters of the product. When calculating the predicted value of the product performance index for multiple process parameter values ​​within the adjustment range, the values ​​of the remaining process parameters are also pre-set, making the predicted value of the product performance index more accurate.

[0020] In another possible implementation of the first aspect, a parameter calculation operation for the predicted value of the product performance index is performed on the first process parameter in the set of independent variables of the first mathematical model. If the second reference value of the third process parameter does not have a recommended value, then the parameter calculation operation for the predicted value of the product performance index is performed on the third process parameter for which no recommended value exists. The parameter calculation operation for the third process parameter is the same as that for the first process parameter. It should be noted that for each third process parameter in the set of independent variables that does not yet have a recommended value, a parameter calculation operation for the predicted value of the product performance index is performed, and this parameter calculation operation is the same as that for the first process parameter, until every adjustable process parameter in the set of independent variables has a recommended value.

[0021] In another possible implementation of the first aspect, selecting N+1 process parameter values ​​from the first adjustment range includes: determining N-1 equal division points from the first adjustment range; and determining the N-1 equal division points and the first upper limit and the first lower limit of the first adjustment range as N+1 process parameter values.

[0022] It should be noted that after obtaining the first adjustment range of the adjustable process parameter (i.e., the first process parameter), N-1 equal division points (N is a positive integer greater than 1) need to be determined within the first adjustment range. The N-1 equal division points, the first upper limit value and the first lower limit value of the first adjustment range are determined as N+1 process parameter values. The process parameter value with the largest index evaluation value among the N+1 process parameter values ​​can be used as the first adjustment value. The recommended value of the first process parameter is further selected based on the first adjustment value.

[0023] In another possible implementation of the first aspect, determining the recommended value of the first process parameter of the product based on the first adjustment value includes:

[0024] If the first adjustment value is the first upper limit value or the first lower limit value, then the first adjustment value shall be used as the recommended value of the first process parameter;

[0025] If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value is optimized to obtain a second adjustment value, and the recommended value of the first process parameter is determined based on the second adjustment value.

[0026] In the above method, the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 process parameter values ​​within the first adjustment range. If the first adjustment value is the first upper limit or the first lower limit of the first adjustment range, then the first adjustment value is used as the recommended value of the first process parameter. If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value needs to be further optimized to obtain the second adjustment value. Then, the recommended value of the first process parameter is determined based on the second adjustment value. This method can further refine the first adjustment value based on the first adjustment value to obtain the second adjustment value.

[0027] In another possible implementation of the first aspect, optimizing the first adjustment value to obtain a second adjustment value, and determining the recommended value of the first process parameter based on the second adjustment value, includes:

[0028] The second adjustment range is formed by the process parameter values ​​corresponding to two adjacent equally divided points before and after the first adjustment value;

[0029] For the second adjustment range, perform the following operation M times:

[0030] The second adjustment range is divided into two sub-ranges;

[0031] The intermediate values ​​of the two sub-ranges are respectively input into the indicator evaluation model to obtain two indicator evaluation values;

[0032] Based on the evaluation values ​​of the two indicators, the sub-range with the highest evaluation value among the two sub-ranges is selected as the new second adjustment range;

[0033] The median value of the sub-range with the highest index evaluation value after M iterations is used as the second adjustment value;

[0034] The second adjustment value is used as the recommended value for the first process parameter.

[0035] In the above method, if the first adjustment value is not the first upper limit or the first lower limit, the first adjustment value is further optimized to obtain the second adjustment value. The specific process is as follows: Select the process parameter values ​​corresponding to the two adjacent equally divided points before and after the first adjustment value from the N+1 process parameter values ​​to form the second adjustment range. Divide the second adjustment range into two sub-ranges (usually two equal sub-ranges). The index evaluation value corresponding to the median value of each sub-range is used as the index evaluation value of that sub-range. Compare the index evaluation values ​​of the two sub-ranges and select the sub-range with the larger index evaluation value as the new second adjustment range. Continue to divide and compare the sub-ranges. The sum of the number of the second adjustment range and the new second adjustment range is M times (a total of M iterations).

[0036] It should be noted that the number of iterations M is adjustable. If a more accurate second process parameter is required, the value of M can be set larger. This method further refines the first adjustment value. By iterating M times, the size of the second adjustment range is continuously reduced. The middle value of the larger range of index evaluation values ​​obtained in the last iteration is selected as the second adjustment value, which can obtain a more accurate recommended value for the process parameter and improve the accuracy of the recommended value.

[0037] It should be noted that in this method, the condition for directly using the second adjustment value as the recommended value of the first process parameter is that the index evaluation value corresponding to the second adjustment value is greater than the index evaluation value corresponding to the first adjustment value and M reference evaluation values. Under complex working conditions, when multiple process parameters need to be adjusted, each adjustable process parameter corresponds to a first adjustment value. Among multiple first adjustment values, there may be a situation where a certain first adjustment value is the first lower limit or the first upper limit, or the index evaluation value corresponding to a certain first adjustment value is greater than the index evaluation value corresponding to the second adjustment value and M reference evaluation values, or other situations may occur. In the actual production process, when there are too many adjustable process parameters that need to be adjusted, the above-mentioned possibilities may occur on different process parameters throughout the entire production process. Therefore, in this method, directly using the second adjustment value as the recommended value of the first process parameter assumes that the index evaluation value corresponding to the second adjustment value will be the largest in the production process.

[0038] In yet another possible implementation of the first aspect, before using the second adjustment value as the recommended value for the first process parameter, the method further includes:

[0039] Compare the indicator evaluation value corresponding to the first adjustment value with the evaluation values ​​of M reference indicators, wherein each of the M reference indicator evaluation values ​​is the larger of the two indicator evaluation values ​​corresponding to the median value of the two sub-ranges obtained after one round of iteration, and the median value is the process parameter value in the middle of the sub-range.

[0040] If the index evaluation value corresponding to the second adjustment value is not the largest index evaluation value among the index evaluation value corresponding to the first adjustment value and the M reference index evaluation values, then the process parameter value corresponding to the largest index evaluation value shall be used as the recommended value of the first process parameter.

[0041] If the evaluation value of the indicator corresponding to the second adjustment value is the largest among the evaluation values ​​of the indicator corresponding to the first adjustment value and the evaluation values ​​of the M reference indicators, then the step of using the second adjustment value as the recommended value of the first process parameter is executed.

[0042] In the above method, if the indicator evaluation value corresponding to the second adjustment value is greater than the indicator evaluation value corresponding to the first adjustment value and the M reference evaluation values, then the second adjustment value is used as the recommended value of the first process parameter; if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values, then the process parameter value corresponding to the largest indicator evaluation value is used as the recommended value of the first process parameter. This method can further obtain specific recommended values ​​within the first adjustment range, ensuring that the product performance indicators corresponding to the recommended values ​​remain optimal, thus improving the accuracy of the recommended values ​​while simultaneously improving product quality.

[0043] In another possible implementation of the first aspect, determining the first adjustment value among the N+1 process parameter values ​​based on the N+1 index evaluation values ​​includes:

[0044] Determine the index evaluation value corresponding to each process parameter value in the N+1 process parameter values;

[0045] Select the process parameter value corresponding to the largest indicator evaluation value among N+1 indicator evaluation values ​​as the first adjustment value.

[0046] In the above method, the first adjustment value is the process parameter value with the largest index evaluation value among the N+1 process parameter values. It is necessary to first determine the index evaluation value corresponding to each process parameter value among the N+1 process parameter values, and then compare each index evaluation value to obtain the process parameter value corresponding to the largest index evaluation value. This allows for a preliminary selection of the N+1 process parameter values ​​and narrows down the range of the first adjustment.

[0047] It should be noted that product performance indicators are metrics used to measure product production, such as the final output of the product and the concentration of chemical substances in the product after production. The indicator evaluation value is determined based on the first mathematical model and the indicator evaluation model, and is used to measure the degree of influence of a certain process parameter value on the product performance indicator. That is, the indicator evaluation value is used to evaluate the comprehensive closeness of the predicted value of each set of product performance indicators in the multiple sets of predicted values ​​corresponding to the N+1 process parameter values ​​to the corresponding set of product performance target values. This comprehensive closeness can be understood as the closer the predicted value of the product performance indicator is to the target value of the product performance indicator, the better the impact on the final product performance indicator (the higher the indicator evaluation value).

[0048] Secondly, embodiments of this application provide an apparatus for recommending production process parameters based on abnormal operating conditions, the apparatus comprising:

[0049] An adjustment unit is used to determine a first adjustment range for a first process parameter, wherein the first process parameter is an adjustable process parameter that affects the product performance indicators in production, and the first adjustment range is an adjustment range determined based on the first upper limit and the first lower limit of the first process parameter in the design scorecard.

[0050] The selection unit is used to select N+1 process parameter values ​​from the first adjustment range, where N is an integer greater than 1;

[0051] The evaluation unit is used to input the N+1 process parameter values ​​into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators, and input the predicted values ​​of the N+1 sets of product performance indicators into the indicator evaluation model to obtain N+1 indicator evaluation values. The indicator evaluation values ​​are used to evaluate the overall closeness of the predicted value of each set of product performance indicators in the multiple sets of predicted values ​​of product performance indicators corresponding to the N+1 process parameter values ​​to the corresponding set of product performance target values.

[0052] The determining unit is used to determine a first adjustment value among the N+1 process parameter values ​​based on the N+1 index evaluation values; wherein the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 index evaluation values.

[0053] The first determining unit is configured to determine a recommended value for the first process parameter of the product based on the first adjustment value.

[0054] As can be seen, when process parameters change abnormally, the recommended value of the first process parameter (i.e., the adjustable process parameter that needs adjustment) is predicted by the recommended value prediction algorithm. Specifically, the process parameter with the highest evaluation value within the first adjustment range is selected as the first adjustment value of the first process parameter. Then, the recommended value of the first process parameter is obtained based on this first adjustment value. This method avoids relying on production personnel manually adjusting process parameters based on accumulated experience, and using the manually adjusted parameter as the recommended value of the first process parameter. This approach enables timely and accurate acquisition of the recommended values ​​of the adjustable process parameters that need adjustment, even when production conditions change complexly and multiple adjustable process parameters require adjustment. Production personnel can then adjust the process parameters based on these recommended values, improving product performance and adjustment efficiency.

[0055] It should be noted that, under complex operating conditions, for adjustable process parameters (the first process parameter) that need adjustment, a second adjustment value is selected as the recommended value of the first process parameter through a prediction method; for non-adjustable process parameters that need adjustment, they are usually treated as abnormal parameters, and the abnormal predicted value of the abnormal parameter is used for production; for parameters that do not need adjustment, they can be understood as parameters under normal operating conditions, and the target value of the process parameter in the benchmark operating condition scorecard is used for production (i.e., the process parameter value corresponding to the largest product performance index).

[0056] It should be noted that the index evaluation value is used to evaluate the overall closeness between the predicted value of each set of product performance indicators and the corresponding set of product performance target values ​​among the predicted values ​​of multiple sets of product performance indicators corresponding to the process parameters. It can be understood as comparing the closeness between the predicted value of each set of product performance indicators and the target value of each set of product performance indicators, and finally taking the results of multiple comparisons as the overall closeness. The closer the closeness, the higher the corresponding index evaluation value.

[0057] In one possible implementation of the second aspect, regarding the input of the N+1 process parameter values ​​into the first mathematical model to obtain N+1 sets of predicted product performance indicators, the evaluation unit is specifically used for:

[0058] Determine a first reference value for the second process parameter, wherein the first reference value is the target value of the second process parameter in the benchmark scorecard;

[0059] Determine a second reference value for a third process parameter and an abnormal prediction value for a fourth process parameter, wherein the type of the third process parameter is an adjustable process parameter, the type of the fourth process parameter is a non-adjustable process parameter, and the second process parameter, the third process parameter value, the fourth process parameter, and the first process parameter belong to the set of independent variables of the first mathematical model;

[0060] If the recommended value exists for the third process parameter, then the second reference value is the recommended value for the third process parameter; if the recommended value does not exist for the third process parameter, then the second reference value is the target value for the third process parameter, wherein the target value for the third process parameter is the target value for the third process parameter in the benchmark working condition scorecard.

[0061] The N+1 process parameter values, the first reference value, the second reference value, and the abnormal prediction value of the fourth process parameter are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators.

[0062] It can be seen that when complex operating conditions occur, the types of process parameters may include parameters that do not need to be adjusted under normal operating conditions, adjustable process parameters that need to be adjusted under abnormal operating conditions, and non-adjustable process parameters that need to be adjusted under abnormal operating conditions. Among them, the first process parameter is the process parameter for which the predicted value of product performance index is being calculated; the second process parameter is the process parameter that does not need to be adjusted under normal operating conditions; the third process parameter is the recommended value of the first process parameter that has completed the recommended value algorithm or the default value of the first process parameter that has not completed the recommended value algorithm (the target value of the operating condition scorecard) when abnormal operating conditions occur. At this time, the third process parameter is judged. If a recommended value exists, the recommended value is used; if no recommended value exists, the target value is used; the fourth process parameter is the non-adjustable process parameter under abnormal operating conditions.

[0063] Specifically, the set of independent variables in the first mathematical model is typically a set of first, second, third, and fourth process parameters. When calculating the predicted value of the product performance index for N+1 process parameter values ​​within the first adjustment range of a given first process parameter, it is necessary to first determine the initial values ​​for the remaining process parameters in the independent variable set, excluding the first process parameter. This can be understood as follows: if a recommended value exists for the third process parameter, it is used as the initial value; if no recommended value exists for the remaining third process parameters, the target value is used as the initial value. The second process parameter uses the target value from the benchmark scorecard as its initial value; and the fourth process parameter uses the abnormal predicted value as its initial value. This method considers that the predicted value of the product performance index is affected by all process parameters of the product. When calculating the predicted value of the product performance index for a given process parameter value within the adjustment range, the values ​​of the remaining process parameters are also pre-set, making the calculation of the predicted value of the product performance index more accurate.

[0064] In another possible implementation of the second aspect, the parameter calculation operation for the predicted value of the product performance index is performed on the first process parameter in the set of independent variables of the first mathematical model. If the second reference value of the third process parameter does not have a recommended value, then the parameter calculation operation for the predicted value of the product performance index is performed on the third process parameter for which no recommended value exists. The parameter calculation operation process for the third process parameter is the same as that for the first process parameter. It should be noted that the parameter calculation operation for the predicted value of the product performance index is performed on each third process parameter in the set of independent variables that does not yet have a recommended value. This parameter calculation operation is the same as that for the first process parameter, until every adjustable process parameter in the set of independent variables has a recommended value.

[0065] In another possible implementation of the second aspect, the selection unit is specifically used for:

[0066] Determine N-1 equal division points from the first adjustment range;

[0067] The N-1 equal division points and the first upper limit and the first lower limit of the first adjustment range are determined as N+1 process parameter values.

[0068] It should be noted that after obtaining the first adjustment range of the adjustable process parameter (i.e., the first process parameter), N-1 equal division points (N is a positive integer greater than 1) need to be determined within the first adjustment range. The N-1 equal division points, the first upper limit value and the first lower limit value of the first adjustment range are determined as N+1 process parameter values. The process parameter value with the largest index evaluation value among the N+1 process parameter values ​​can be taken as the first adjustment value. The recommended value of the first process parameter is further determined based on the first adjustment value.

[0069] In one possible implementation of the second aspect, the first determining unit is specifically used for:

[0070] If the first adjustment value is the first upper limit value or the first lower limit value, then the first adjustment value shall be used as the recommended value of the first process parameter value.

[0071] If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value is optimized to obtain a second adjustment value, and the recommended value of the first process parameter is determined based on the second adjustment value.

[0072] It can be seen that the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 process parameter values ​​within the first adjustment range. If the first adjustment value is the first upper limit or the first lower limit of the first adjustment range, then the first adjustment value is used as the recommended value of the first process parameter. If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value needs to be further optimized to obtain the second adjustment value. Then, the recommended value of the first process parameter is determined based on the second adjustment value. This method can further refine the first adjustment value based on the first adjustment value to obtain the second adjustment value.

[0073] In one possible implementation of the second aspect, in the step of optimizing the first adjustment value to obtain a second adjustment value, and determining a recommended value for the first process parameter based on the second adjustment value, the first determining unit is specifically used for:

[0074] The second adjustment range is formed by the process parameter values ​​corresponding to two adjacent equally divided points before and after the first adjustment value;

[0075] For the second adjustment range, perform the following operation M times:

[0076] The second adjustment range is divided into two sub-ranges;

[0077] The intermediate values ​​of the two sub-ranges are respectively input into the indicator evaluation model to obtain two indicator evaluation values;

[0078] Based on the evaluation values ​​of the two indicators, the sub-range with the highest evaluation value among the two sub-ranges is selected as the new second adjustment range;

[0079] The median value of the sub-range with the highest index evaluation value after M iterations is used as the second adjustment value;

[0080] The second adjustment value is used as the recommended value for the first process parameter.

[0081] It can be seen that if the first adjustment value is not the first upper limit or the first lower limit, the first adjustment value is further optimized to obtain the second adjustment value. The specific process is as follows: Select the process parameter values ​​corresponding to the two adjacent equally divided points before and after the first adjustment value from the N+1 process parameter values ​​to form the second adjustment range. Divide the second adjustment range into two sub-ranges (usually two equal sub-ranges). The index evaluation value corresponding to the median value of each sub-range is used as the index evaluation value of that sub-range. Compare the index evaluation values ​​of the two sub-ranges and select the sub-range with the larger index evaluation value as the new second adjustment range. Continue to divide and compare the sub-ranges. The sum of the number of the second adjustment range and the new second adjustment range is M times (a total of M iterations).

[0082] It should be noted that the number of iterations M is adjustable. If a more accurate second process parameter is required, the value of M can be set larger. This method further refines the first adjustment value. By iterating M times, the size of the second adjustment range is continuously reduced. The middle value of the larger range of index evaluation values ​​obtained in the last iteration is selected as the second adjustment value, which can obtain a more accurate recommended value for the process parameter and improve the accuracy of the recommended value.

[0083] It should be noted that in this method, the condition for directly using the second adjustment value as the recommended value of the first process parameter is that the index evaluation value corresponding to the second adjustment value is greater than the index evaluation value corresponding to the first adjustment value and M reference evaluation values. Under complex working conditions, when multiple process parameters need to be adjusted, each adjustable process parameter corresponds to a first adjustment value. Among multiple first adjustment values, there may be a situation where a certain first adjustment value is the first lower limit or the first upper limit, or the index evaluation value corresponding to a certain first adjustment value is greater than the index evaluation value corresponding to the second adjustment value and M reference evaluation values, or other situations may occur. In the actual production process, when there are too many adjustable process parameters that need to be adjusted, the above-mentioned possibilities may occur on different process parameters throughout the entire production process. Therefore, in this method, the second adjustment value is directly used as the recommended value of the first process parameter, which is assumed by default that the product performance index corresponding to the second adjustment value will be optimal in this production process.

[0084] In yet another possible implementation of the second aspect, the apparatus further includes:

[0085] The comparison unit is used to compare the index evaluation value corresponding to the first adjustment value with M reference index evaluation values ​​before the second adjustment value is used as the recommended value of the first process parameter. Each of the M reference index evaluation values ​​is the larger of the two index evaluation values ​​corresponding to the median value of two sub-ranges obtained after one round of iteration. The median value is the process parameter value in the middle of the sub-range.

[0086] The second determining unit is used to determine the process parameter value corresponding to the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values ​​if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values.

[0087] The first determining unit is specifically used to execute the step of using the second adjustment value as the recommended value of the first process parameter if the indicator evaluation value corresponding to the second adjustment value is the largest among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values.

[0088] It can be seen that if the indicator evaluation value corresponding to the second adjustment value is greater than the indicator evaluation value corresponding to the first adjustment value and the M reference evaluation values, then the second adjustment value is used as the recommended value of the first process parameter; if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values, then the process parameter value corresponding to the largest indicator evaluation value is used as the recommended value of the first process parameter. This method can further obtain specific recommended values ​​within the first adjustment range, ensuring that the product performance indicators corresponding to the recommended values ​​remain optimal, thus improving the accuracy of the recommended values ​​while simultaneously improving product quality.

[0089] Thirdly, embodiments of this application provide an electronic device, including a transceiver, a processor, and a memory. The memory is used to store a computer program, and the processor calls the computer program to execute the first aspect of the embodiments of this application or any one of the production process parameter recommendation methods based on abnormal operating conditions.

[0090] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a processor, implements the method of recommending production process parameters based on abnormal operating conditions in the first aspect of the embodiments of this application or any one of the methods in the first aspect.

[0091] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to execute the method of recommending production process parameters based on abnormal operating conditions, according to the first aspect of the embodiments of this application or any one of the first aspects.

[0092] Sixthly, embodiments of this application provide an electronic device that includes the methods or apparatus described in any embodiment of this application. The electronic device is, for example, a chip.

[0093] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0094] The accompanying drawings used in the embodiments of this application are described below.

[0095] Figure 1 This is a schematic diagram of the structure of an apparatus 10 for a method of recommending production process parameters based on abnormal operating conditions, provided in an embodiment of this application.

[0096] Figure 2 This is a flowchart illustrating a method for recommending production process parameters based on abnormal operating conditions, provided in an embodiment of this application.

[0097] Figure 3 A schematic diagram illustrating a scenario for obtaining first process parameters, provided as an embodiment of this application;

[0098] Figure 4 A schematic diagram of a scenario for determining N+1 process parameter values ​​within a first adjustment range of production time process parameters, provided in an embodiment of this application;

[0099] Figure 5 A schematic diagram of a scenario for determining 11 process parameter values ​​within a first adjustment range of production time process parameters, provided in an embodiment of this application;

[0100] Figure 6 This application provides a schematic diagram illustrating a scenario where product data is stored using blockchain.

[0101] Figure 7 A schematic diagram of a scenario for the second adjustment range corresponding to the first iteration of the loop, provided in an embodiment of this application;

[0102] Figure 8 A schematic diagram of a scenario where the second adjustment range corresponds to the second iteration of the loop is provided in an embodiment of this application;

[0103] Figure 9 A schematic diagram of a scenario corresponding to the second adjustment range when the loop count is 3, provided in an embodiment of this application;

[0104] Figure 10 This is a schematic diagram of the structure of an apparatus 100 for a method of recommending production process parameters based on abnormal operating conditions, provided in an embodiment of this application. Detailed Implementation

[0105] The technical solutions in the embodiments of this application will now be described clearly and in more detail with reference to the accompanying drawings. The terminology used in the implementation section of this application is only for explaining specific embodiments of this application and is not intended to limit this application.

[0106] Please see Figure 1 , Figure 1This is a schematic diagram of an apparatus 10 for a production process parameter recommendation method based on abnormal operating conditions, provided in an embodiment of this application. The apparatus 10 includes a processor 101, a memory 102, a scorer 103, an index evaluator 104, and a parameter recommender 105. The memory 102 of the production equipment typically stores computer stored programs or data, such as the values ​​of various parameters during production and related data cached during runtime. The processor 101 calls the computer programs or data stored in the memory 102 to perform production, typically selecting the target value of the process parameters (the process parameters corresponding to the optimal product performance index) for production, thereby maintaining the optimal performance index of the produced product.

[0107] However, under complex production conditions, process parameters can change due to abnormal fluctuations in these conditions. This can cause some parameters to no longer be used at their target values, resulting in a decrease in product performance. Continuing to use the changed process parameter values ​​may lead to lower product performance. To maintain high performance levels, production personnel typically adjust these parameters manually based on their accumulated experience. However, this often results in untimely and inaccurate adjustments, reducing production efficiency. Furthermore, some process parameters requiring adjustment cannot be used with their original target values. These adjusted process parameters include the adjustable process parameter X. m (m is a positive integer greater than or equal to 1) and non-adjustable process parameter X n (n is a positive integer greater than or equal to 1), where non-adjustable process parameters are abnormal parameters, and production can only be carried out using the abnormal predicted values ​​of these abnormal parameters. If production personnel forcibly adjust the parameters that need adjustment to the target values ​​of the process parameters (the target values ​​in the benchmark scorecard), it may lead to production being unable to continue or dangerous accidents, or a decrease in the performance indicators of the produced products. In addition, if production personnel arbitrarily assign values ​​to adjustable process parameters based on their own experience, it may lead to a decrease in the performance indicators of the produced products. Therefore, this application embodiment improves upon the above method, and the specific process is as follows:

[0108] Suppose the production process has e steps (e is a positive integer greater than 1), where any one of the e steps can be represented as step P. b (1≤b≤e). When the production schedule reaches process P... k When (1≤k≤e), if process P k The process parameters are abnormal (k is an integer within the range of e), and the process flow that needs to adjust the process parameters is P. i (k≤i≤e), process P that is confirmed to be running normally and does not require optimization. f (1≤f≤k-1). For example... Figure 1As shown, the memory 102 can store relevant data or programs cached during product production. The processor 101 calls the relevant programs or data stored in the memory 102 to perform production. Meanwhile, the scorer 103 includes a benchmark operating condition scorecard and a design scorecard. The design scorecard stores the first upper limit and the first lower limit of the first process parameter (i.e., the adjustable process parameter that needs to be adjusted) to obtain the first adjustment range of the first process parameter. The benchmark operating condition scorecard stores data such as the target value of the product performance index and the target value of the process parameter.

[0109] It should be noted that process P, which does not require optimization, f The parameter X that does not need to be adjusted a (where a is a positive integer greater than or equal to 1), meaning the parameter X that does not need to be adjusted. a Production is consistently carried out using the target values ​​of process parameters from the benchmark scorecard under normal operating conditions; however, in process P where process parameters need to be adjusted... i Among the process parameters that need to be adjusted for (k≤i≤e), the types of process parameters that need to be adjusted include non-adjustable process parameters X. n (n is a positive integer) and adjustable process parameter X m (m is a positive integer); if it is a non-adjustable process parameter X n Then use the non-adjustable process parameter X. n The non-adjustable process parameter X obtained through algorithmic prediction n Production is based on the predicted values ​​of abnormal parameters, for adjustable process parameters X. m (i.e., the first process parameter), it is necessary to obtain the adjustable process parameter X. m The corresponding process parameter value that optimizes product performance is used as the adjustable process parameter X. m Production will be based on the recommended values.

[0110] Select adjustable process parameter X m When determining the recommended value corresponding to the highest evaluation value, it is usually necessary to select multiple process parameter values ​​within the first adjustment range, such as... Figure 1As shown, the index evaluator 104 includes a first mathematical model and an index evaluation model. A recommendation algorithm is used to substitute each of the multiple process parameter values ​​into the first mathematical model to obtain a set of predicted values ​​for product performance indicators. The predicted values ​​and target values ​​of each set of product performance indicators are then substituted into the index evaluation model to obtain index evaluation values. A first adjustment value (i.e., the process parameter value corresponding to the largest index evaluation value) is selected. If the first adjustment value is a first upper limit or a first lower limit, the parameter recommender 105 uses the first adjustment value as the recommended value for the first process parameter. If the first adjustment value is not a first upper limit or a first lower limit, the first adjustment value is further optimized to obtain a second adjustment value. The index evaluation value corresponding to the second adjustment value, the index evaluation value corresponding to the first adjustment value, and the largest index evaluation value from each iteration in the optimization process are then compared to select the process parameter value with the largest index evaluation value. Figure 1 As shown, the process parameter with the highest evaluation value is used as the recommended value of the first process parameter by the parameter recommender 105. This method can recommend the process parameter with the highest evaluation value to the production equipment by the recommendation method, continuously narrowing the first adjustment range, making the recommended value more accurate, and ensuring the performance indicators and efficiency of product production.

[0111] The specific process of the method is described below:

[0112] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for recommending production process parameters based on abnormal operating conditions, provided in an embodiment of this application. This method can be based on... Figure 1 The method may be implemented using the device 10 shown, or based on other architectures, and includes, but is not limited to, the following steps:

[0113] S201: Determine the first adjustment range of the first process parameter.

[0114] Determine the first adjustment range of the first process parameter (the adjustable process parameter that needs to be adjusted), which is to determine the specific range of the optional process parameter values ​​of the first process parameter. The first adjustment range is the adjustment range used to determine the recommended value of the first process parameter.

[0115] In some embodiments, under normal operating conditions, the initial setting value of the process parameters is the target value set to achieve the optimal product performance index. The actual value is the value of the process parameters that deviates from the target value due to the influence of complex operating conditions during production. Here, the product performance index can be understood as the product concentration or product yield after production, etc., and the initial setting value can be understood as the target value of the process parameters, that is, the value of the process parameters that corresponds to the optimal product performance index in the benchmark operating condition scorecard. As shown in Table 1, Table 1 is a parameter table for the change data of multiple process parameters during the production process provided by an embodiment of this application. For example, when the process parameter is production time, under normal operating conditions, the initial setting value is 712.526 (the unit can be minutes or seconds, etc.); when the process parameter is the amount of soybean oil added, the initial setting value is 107.960 (the unit can be kilograms or grams, etc.), and the setting values ​​for other process parameters are similar and will not be elaborated further.

[0116] As the operating conditions change in a complex manner, the actual values ​​of various process parameters will change. For example, when the process parameter is production time, the actual value becomes 714.991 (the unit can be minutes or seconds, etc.); when the process parameter is the amount of soybean oil added, the actual value is 107.992 (the unit can be kilograms or grams, etc.). The actual values ​​of other process parameters can be deduced in the same way, and will not be elaborated further.

[0117]

[0118] Table 1

[0119] The first process parameter (adjustable process parameter) is explained below:

[0120] In some embodiments, a first process parameter is determined from the process that needs adjustment. That is, the process that needs adjustment includes adjustable process parameters (i.e., the first process parameter) and non-adjustable process parameters (i.e., the fourth process parameter), while the parameter value corresponding to the normal operating conditions of the process that does not require adjustment is the second parameter value. Typically, in production processes, when complex changes occur in operating conditions, the parameter configuration during production will display adjustable and non-adjustable process parameters. Referring to the hypothetical example above, the production process has P... e There are several processes (where e is a positive integer greater than 1), and the process that requires adjustment of process parameters is process P. i (k≤i≤e), for example, when P (e＝5) (The total process consists of 5 steps, namely p1, p2, p3, p4, and p5), when one of them P (k＝3)If the process parameters corresponding to the operating condition of process (i.e., p3) are abnormal, then the normal operating processes that have already been produced are p1 and p2. The parameter values ​​corresponding to the processes under normal operating conditions are the second parameter values, that is, the parameter values ​​corresponding to processes p1 and p2 are the target values ​​in the benchmark operating condition scorecard; the processes that need to be optimized are p3, p4, and p5. If the process parameters corresponding to the above three processes that need to be optimized are nine, specifically, as follows... Figure 3 As shown, the nine process parameters in the three production processes that need to be optimized may include: production time, amount of soybean oil added, amount of hydrogen added, amount of water added, hydrogen pressure, hydrogen time, hydrolysis temperature, hydrolysis oil-water ratio, and hydrolysis time.

[0121] It should be noted that if the actual value of a process parameter changes and is within the upper and lower limits of the process parameters in the benchmark operating condition database, the process parameter is usually regarded as an adjustable process parameter (the first process parameter); if the actual value of the process parameter is outside the upper and lower limits of the process parameters in the benchmark operating condition database, the process parameter is usually regarded as an abnormal parameter that exceeds the adjustment range, and the predicted value of the abnormal parameter is used for production. For example, the fourth process parameter can be the hydrogen pressure shown in Table 1, where the hydrogen pressure is 210 (in Pa). The corresponding benchmark operating condition range for the hydrogen pressure is [290.000, 298.000]. If the hydrogen pressure is below this range, it means that the hydrogen pressure is outside the benchmark operating condition range. In this case, the hydrogen pressure is determined by the production capacity of the infrastructure and cannot be adjusted by the production personnel. Usually, the pressure of the hydrogen production unit is continuously predicted over time to obtain the predicted pressure value of the hydrogen pressure during the production period of this batch. This value is then substituted into the model for calculation. It should be noted that the model here can be the first mathematical model, the second mathematical model optimized by the abnormal recommendation algorithm, or the third mathematical model relearned by abnormal recommendation value. The specific content of the second or third mathematical model is not described in detail in this embodiment of the application. For adjustable process parameters (first process parameters), there is usually an adjustable range, which is the upper and lower limits of the process parameters in the benchmark operating condition database. There are multiple process parameter values ​​within this adjustable range. The process parameter value corresponding to the optimal product performance index is selected as the first adjustment value of the first process parameter. Then, the recommended value of the first process parameter is obtained based on the first adjustment value.

[0122] Table 1 shows nine process parameters, including the adjustable process parameter X. m (i.e., the normal, variable first process parameter) and the non-adjustable process parameter X n (i.e., the abnormal, immutable fourth process parameter), such as Figure 3 As shown, Figure 3This application provides a schematic diagram of a scenario for obtaining a first process parameter, for an adjustable process parameter X. m (i.e., the first process parameter), such as production time, soybean oil dosage, hydrogenation amount, water dosage, hydrogenation time, hydrolysis temperature, hydrolysis oil-to-water ratio, hydrolysis time, etc.; non-adjustable process parameter X n (Fourth process parameter) refers to non-adjustable abnormal parameters, such as hydrogen pressure. For example, in a process that requires adjustment, the adjustable process parameter (i.e., the first process parameter) is X. m m∈[1,8], meaning there are 8 first process parameters. This can be understood as follows: when m=1, X1=production time; when m=2, X2=soybean oil production; when m=3, X3=hydrogenation amount; similarly, X4=water addition amount, X5=hydrogenation time, X6=hydrolysis temperature, X7=hydrolysis oil-water ratio, and X8=hydrolysis time. The recommended values ​​in this embodiment are obtained through a recommended value prediction algorithm. This process is carried out for the first process parameters and does not include unadjustable process parameters, parameters that do not need to be adjusted, or abnormal parameters.

[0123] The first adjustment range of the first process parameter is described below:

[0124] In some embodiments, a first upper spec limit (USL) and a first lower spec limit (LSL) of a first process parameter are selected using a design scorecard in the scorer 103 to determine a first adjustment range H corresponding to each first process parameter. m∈(LSL, USL), where m represents the total number of first process parameters. It can be understood that each first process parameter corresponds to an adjustable range (including a first upper limit value USL and a first lower limit value LSL). The adjustment ranges of different first process parameters can be the same or different; this embodiment does not limit this. It should be noted that the target value of the first process parameter is directly obtained from the design scorecard of the scorer 103, which is data already stored before production. It can also be obtained through other methods; this embodiment does not limit this. For example, as shown in Table 1, when the process parameter is production time, the adjustable range H1 can be [710.000, 715.000]; when the process parameter is the amount of soybean oil added, the adjustable range H2 can be [107.000, 108.000]; when the process parameter is the amount of hydrogenation, the adjustable range H3 can be [218.000, 220.000]; and when the process parameter is the amount of water added, the adjustable range H4 can be [75.000, 77].

[000] ; When the process parameter is hydrogen passage time, the adjustable range H5 can be [59.000, 59.600]; When the process parameter is hydrolysis temperature, the adjustable range H6 can be [89.000, 90.000]; When the process parameter is hydrolysis oil-water ratio, the adjustable range H7 can be [1.240, 1.270]; When the process parameter is hydrolysis time, the adjustable range H8 can be [664.000, 664.900].

[0125] The following method is analyzed when the first process parameter X1 equals the production time.

[0126] S202: Select N+1 process parameter values ​​from the first adjustment range.

[0127] When selecting a process parameter value within the first adjustment range, if the product performance index of the process parameter value is closer to the target value of the product performance index, it indicates that the production effect of the process parameter value is better, ensuring product performance during production. It should be noted that when selecting N+1 process parameter values ​​within the first adjustment range, they can be arbitrarily selected, or the first adjustment range can be divided into N-1 equal division points for selection, or other methods can be used. This application embodiment does not limit this. In this application embodiment, the method of dividing the first adjustment range into N-1 equal division points is selected for analysis.

[0128] In some embodiments, selecting N+1 process parameter values ​​from a first adjustment range includes: determining N-1 equal division points from the first adjustment range; and determining the N-1 equal division points and the first upper limit and first lower limit of the first adjustment range as N+1 process parameter values. Figure 4 As shown, Figure 4This is a schematic diagram illustrating a scenario for determining N+1 process parameter values ​​within a first adjustment range of a production time process parameter, as provided in an embodiment of this application. Within the first adjustment range of the first process parameter X1 (production time), N-1 equal division points are selected, namely 1, 2, 3, 4...N-3, N-2, N-1. The first lower limit value LSL and the first upper limit value USL of the first adjustment range, along with the process parameters corresponding to the N-1 equal division points, are collectively used as the N+1 process parameter values. These N+1 process parameter values ​​are d1, d2, d3, ..., d... N d N+1 When the first process parameter is production time, the adjustable range H1 can be [710.000, 715.000]. Figure 4 In this context, LSL = 710.000 and USL = 715.000. It should be noted that if the first process parameter is of other types, such as soybean oil production, the first lower limit and first upper limit of the first adjustment range are determined based on the first adjustment range H2 [107.000, 108.000] for soybean oil production, i.e., LSL = 107.000 and USL = 108.000. Similarly, the first adjustment range for soybean oil production is divided into N-1 equal division points; the specific process will not be elaborated further. It should be noted that the number of N-1 equal division points corresponding to different first process parameters can be different or the same; this embodiment does not limit this.

[0129] In this embodiment, the first process parameter is selected as production time, and the case of N=10 is analyzed.

[0130] For example, such as Figure 5 As shown, Figure 5 This is a schematic diagram illustrating a scenario for determining 11 process parameter values ​​within a first adjustment range of production time process parameters, as provided in an embodiment of this application. As shown in the figure, the two process parameters corresponding to the first lower limit and first upper limit of the first adjustment range of the production time process parameters are: d1 = 710.000 (i.e., LSL), d... 11 =715.000 (i.e., USL), and add 10-1=9 equal division points to divide the first adjustment range into 10 equal segments. The 9 process parameters corresponding to the 9 division points are: d2=710.500, d3=711.000, d4=711.500, d5=712.000, d6=712.500, d7=713.000, d8=713.500, d9=714.000, d... 10 =714.500. Therefore, the values ​​of 11 process parameters within the first adjustment range of the production time process parameters are obtained.

[0131] It should be noted that the 11 process parameter values ​​within the first adjustment range of the production time process parameters are optional. It is necessary to calculate the index evaluation value for each of the 11 process parameter values ​​to determine the process parameter value with the highest production index evaluation value. The calculation of the index evaluation values ​​for the process parameters is described below:

[0132] S203: Input the N+1 process parameter values ​​into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators. Input the predicted values ​​of N+1 sets of product performance indicators into the indicator evaluation model to obtain the evaluation values ​​of N+1 indicators.

[0133] For each of the N+1 process parameter values ​​within the first adjustment range, a corresponding indicator evaluation value needs to be calculated. This indicator evaluation value is used to assess the overall closeness between the predicted value of each product performance indicator and its corresponding target value. It can be understood as comparing the predicted value of each product performance indicator with its target value, and then using the results of these comparisons as the overall closeness. The closer the closeness, the higher the corresponding indicator evaluation value. It should be noted that for each of the first process parameters, the predicted value Ypredicted = Y1 ~ Y2 is the predicted value of the multiple product performance indicators. j Among them, the predicted value Y of each product performance index j Corresponding to a product performance Y j The target value for each product performance indicator can be the same or different, and this application embodiment does not limit this. It should be noted that the product performance target value is the product performance value corresponding to the state of production performance that achieves the best state (e.g., the highest output, the highest efficiency, the highest effective concentration, etc.). This product performance indicator value can be obtained from the benchmark working condition scorecard of the scorer 103, or it can be obtained through other means, and this application embodiment does not limit this.

[0134] The following is a detailed introduction to the evaluation values ​​of the calculated process parameters:

[0135] The predicted value of the product performance index is used to characterize the magnitude of the product performance index when one of the N+1 process parameter values ​​is selected as the first process parameter. Specifically, Y prediction = Y1 ~ Y jWhere j is a positive integer greater than or equal to 1, it is used to measure the number of product performance indicators. This can be understood as representing multiple product performance indicators. If the product performance indicators after production are product yield, sulfur concentration, oxygen concentration, and impurity mass, then j = 4, i.e., Y1 = product yield, Y2 = sulfur concentration, Y3 = oxygen concentration, and Y4 = impurity mass. It can also be understood that the number of target values ​​for each product performance indicator is also j, i.e., Y1 = product yield, Y2 = sulfur concentration, Y3 = oxygen concentration, and Y4 = impurity mass. These four product performance indicators correspond to the target values ​​for the four product performance indicators.

[0136] In some embodiments, N+1 process parameter values ​​are input into a first mathematical model to obtain N+1 sets of predicted product performance indicators. The specific process includes: determining a first reference value for a second process parameter, wherein the first reference value is the target value of the second process parameter in a benchmark scorecard; determining a second reference value for a third process parameter and an abnormal predicted value for a fourth process parameter, wherein the third process parameter is an adjustable process parameter and the fourth process parameter is a non-adjustable process parameter, and the second, third, fourth, and first process parameters belong to the set of independent variables of the first mathematical model; if a recommended value exists for the third process parameter, the second reference value is the recommended value of the third process parameter; if no recommended value exists for the third process parameter, the second reference value is the target value of the third process parameter, wherein the target value of the third process parameter is the target value of the third process parameter in the benchmark scorecard; and inputting the N+1 process parameter values, the first reference value, the second reference value, and the abnormal predicted value of the fourth process parameter into the first mathematical model to obtain N+1 sets of predicted product performance indicators.

[0137] Specifically, Y prediction = Y1 ~ Y j =F1(X1, X2, X3, ..., X m+n )~F j (X1, X2, X3, ..., X m+n ), where the independent variable within the parentheses of the F function is X1 to X. m+n The number of parameters (m+n) represents the total number of parameters that do not need adjustment, adjustable process parameters, and non-adjustable process parameters. In other words, when calculating F, the independent variable within the parentheses is the sum of all process parameters in the production process. F is the evaluation function in the first mathematical model. The specific formula for this function is not limited here. This function F is used to characterize the evaluation when the independent variables are X1, X2, X3, ..., X... m+nWhen the predicted value of a product performance indicator is F1, it can be understood that j is used to measure the number of product performance indicators, and also to measure the number of predicted values ​​of the product performance indicators. That is, the predicted value of Y1 is F1, the predicted value of Y2 is F2, and Y... j The predicted value is F j And so on, without further explanation.

[0138] Specifically, in calculating Y prediction = Y1 ~ Y j =F1(X1, X2, X3, ..., X m+n )~F j (X1, X2, X3, ..., X m+n When calculating the predicted value of a product performance index for a certain first process parameter, it is necessary to first set the initial values ​​for the remaining process parameters in the independent variable set of the first mathematical model. That is, if the process parameter for which the predicted value of the product performance index is being calculated is X1, then X2, X3, ..., X... m+n For parameters that require initial calculation values, it can be understood that at this time, the predicted value of the product performance index is calculated for a certain process parameter value among N+1 process parameters within the first adjustment range of X1 (the first process parameter). The N+1 process parameter values ​​are d1, d2, d3, ..., d... N d N+1 Specifically, for the first process parameter used in the calculation of predicted product performance indicators, N+1 process parameters are substituted into F for calculation, i.e., the first process parameter X1: Y prediction of process parameter d1 within the first adjustment range of production time = Y1 ~ Y j =F1(d1, X2, X3, ..., X m+n )~F j (d1, X2, X3, ..., X) m+n ), where X2, X3, ..., X m+n During the calculation of initial values ​​for multiple process parameters, for parameter X that does not require adjustment... a (i.e., the second process parameter) uses the target value in the benchmark scorecard to calculate the initial value setting, for the non-adjustable process parameter X. n (i.e., the fourth process parameter), then the original non-adjustable process parameter X is used. n The predicted values ​​of the abnormal parameters are calculated, and the adjustable parameter X is used for prediction. m(i.e., the third process parameter). The third process parameter is an adjustable process parameter. If a recommended value exists for the third process parameter, it is used for calculation. If no recommended value exists, the target value in the benchmark scorecard is used for prediction calculation. Therefore, we can obtain the prediction Y of the first process parameter X1: the process parameter d2 within the first adjustment range of the production time, Y = Y1 ~ Y2. j =F1(d2, X2, X3, ..., X m+n )~F j (d2, X2, X3, ..., X) m+n From this, N+1 process parameters d1, d2, d3, ..., d can also be obtained. N d N+1 The predicted Y value for each process parameter is obtained by following the same steps as in d1, and will not be repeated here.

[0139] For example, if there are nine process parameters corresponding to the three processes that need optimization mentioned above, such as... Figure 3 As shown, there are 8 first process parameters (normal parameters, variable parameters) (production time, soybean oil dosage, hydrogenation dosage, water dosage, hydrogenation time, hydrolysis temperature, hydrolysis oil-water ratio, hydrolysis time), and 1 non-adjustable process parameter (abnormal parameter, unchangeable parameter) (hydrogenation pressure). The formula for calculating the predicted product performance index for these 8 first process parameters is: Ypredicted = Y1 ~ Y2 j =F1(X1,X2,X3,...,X9)~F j (X1, X2, X3, ..., X9), where X1 to X8 are assumed to be the first process parameters, and X9 is a non-adjustable process parameter, such as... Figure 5 As shown, the 11 process parameter values ​​d1 to d2 within the first adjustment range of process parameter X1 and production time are calculated separately. 11 At this time, since the calculation of predicted product performance indicators is performed for multiple process parameter values ​​within the first adjustment range of production time X1, it is necessary to set initial values ​​for the calculation of parameters X2 to X9. Among the multiple process parameters X2 to X9, for the non-adjustable process parameter X9 (i.e., the fourth process parameter), the predicted value of the abnormal parameter of the original non-adjustable process parameter X9 is used for prediction calculation. For the adjustable process parameters X2 to X8 (i.e., the third process parameter), if the third process parameter has a recommended value, the second reference value of the third process parameter is calculated using the recommended value; if the third process parameter does not have a recommended value, the second reference value of the third process parameter is used for prediction calculation based on the target value of the process parameter stored in the benchmark working condition scorecard of the scorer 103. After assigning initial values ​​for the calculation of parameters X2 to X9, the 11 process parameter values ​​d1 to d2 within the first adjustment range of production time process parameter X1 are calculated respectively. 11Y prediction, the Y prediction of process parameters d1 within the first adjustment range of production time = Y1 ~ Y j =F1(d1,X2,X3,...,X9)~F j (d1, X2, X3, ..., X9); Y prediction of process parameter d2 within the first adjustment range of production time = Y1 ~ Y j =F1(d2,X2,X3,...,X9)~F j (d2, X2, X3, ..., X9), the specific steps for calculating the Y prediction of the remaining process parameter values ​​are similar to those for d1, and so on, and will not be repeated here.

[0140] It should be noted that blockchain is a chain-like data structure that combines data blocks sequentially according to time order. In the embodiments of this application, the independent variable set X1 to X2 in the first mathematical model... m+n In the middle, X1~X m+n This includes parameters that do not need adjustment (second process parameters), adjustable process parameters (first process parameters), and non-adjustable process parameters (fourth process parameters). Therefore, the data blocks corresponding to the first, second, and fourth process parameters can be combined in a chain-like data structure according to time order and in a sequentially connected manner. This chain-like data serves as the relevant data storage in the set of independent variables of the first mathematical model. When calculating the predicted value of the product performance index of a certain first process parameter, the initial values ​​of the other parameters can be set first, and then the predicted values ​​of the product performance index of N+1 process parameter values ​​within the first adjustment range of the first process parameter can be calculated. Multiple sets of independent variables do not affect each other, are stored in blocks, and have the characteristics of decentralization.

[0141] Specifically, such as Figure 6 As shown, Figure 6 This is a schematic diagram illustrating a scenario of using blockchain to store product data, provided in an embodiment of this application. When the number of independent variables in the first mathematical model is n+m=9, it is assumed that process parameter X1 is the first process parameter, i.e., an adjustable process parameter for calculating the predicted value of product performance indicators; X2 to X8 are the third process parameters, i.e., adjustable process parameters that require setting initial values ​​for calculation; and X9 is the fourth process parameter, i.e., a non-adjustable process parameter. In one possible case, it is assumed that X2 and X3 are process parameters with recommended values, and X4 to X8 are process parameters without recommended values. Then, the first data block stores 11 process parameter values ​​d1 to d2 within the first adjustment range of the first process parameter X1. 11The data blocks are as follows: the first data block contains recommended values ​​for the third process parameter X2 obtained using the recommended value algorithm; the second data block contains recommended values ​​for the third process parameter X3 obtained using the recommended value algorithm; the fourth data block contains N+1 process parameter values ​​within the first adjustment range of the third process parameter X4; the fifth data block contains N+1 process parameter values ​​within the first adjustment range of the third process parameter X5; the sixth data block contains N+1 process parameter values ​​within the first adjustment range of the third process parameter X6; the seventh data block contains N+1 process parameter values ​​within the first adjustment range of the third process parameter X7; the eighth data block contains N+1 process parameter values ​​within the first adjustment range of the third process parameter X8; and the ninth data block contains abnormal predicted values ​​for the abnormal parameters of the fourth process parameter X9. The first to ninth data blocks are a chain-like data structure that combines data blocks in chronological order. Multiple sets of data are stored in different data blocks without interfering with each other, and are stored separately without affecting each other, which has the characteristics of decentralization.

[0142] After determining the predicted product performance index value for each of the N+1 process parameter values ​​within the first adjustment range of the first process parameter (production time), the evaluation value of each process parameter value is determined. The specific steps are as follows:

[0143] In some embodiments, the predicted value of the product performance index corresponding to each first process parameter is calculated through a first mathematical model. The predicted value of the product performance index is then input into the index evaluation model to obtain the index evaluation value P. Specifically, the index evaluation value P is obtained based on the predicted value of each set of product performance indicators and the corresponding target value of each set of product performance indicators. This can be understood as calculating the predicted value of a set of product performance indicators for each process parameter, comparing the predicted value of this set of product performance indicators with the corresponding set of product performance target values. If the predicted value of a set of product performance indicators for a certain process parameter is closer to the corresponding set of product performance target values, then the index evaluation value of that process parameter is larger. Thus, the index evaluation value of each process parameter is obtained. The specific process is not described in detail here. The processor 101 obtains multiple target values ​​Y1 to Y2 for the product performance indicators through the benchmark operating condition scorecard of the scorer 103. j The targets, including multiple target values, are stored in the benchmark scoring card of the scorer 103 before production. These targets characterize the product performance indicators that achieve optimal performance (e.g., maximum output, minimum content of harmful substances). It should be noted that the formula for calculating the predicted value of a product performance indicator for a specific first process parameter is: Ypredicted = Y1 ~ Y2. j'j' is used to measure the number of product performance indicators, the number of predicted values ​​of product performance indicators, and the number of target values ​​of product performance indicators. That is, the predicted value of Y1 is F1, and the target value is Y1 target; the predicted value of Y2 is F2, and the target value is Y2 target; Y... j The predicted value is F j Y j The target value is Y j The objectives, and so on, will not be elaborated further.

[0144] Specifically, when calculating the index evaluation value P of a certain process parameter value within the first adjustment range, a set of predicted values ​​Y of the product performance index of that certain process parameter value is calculated as Y1 ~ Y2. j A set of target values ​​for product performance indicators = Y1 ~ Y j Comparing objectives can be understood as comparing the Y1 prediction with the Y1 objective, the Y2 prediction with the Y2 objective, and so on. j Prediction and Y j The target comparison yields a comprehensive result by comparing a set of predicted values ​​with a set of target values. If the predicted value of a set of product performance indicators for a certain process parameter is closer to the target value of the corresponding set of product performance indicators, then the index evaluation value of that process parameter is greater. The index evaluation value can be understood as an evaluation score (for example, it can be 0 to 100 points).

[0145] For example, such as Figure 5 As shown, for the index evaluation values ​​of 11 process parameter values ​​within the first adjustment range of production time, the Y prediction of process parameter d1 within the first adjustment range of production time is Y1~Y. j =F1(d1,X2,X3,...,X9)~F j (d1, X2, X3, ..., X9) and target Y = Y1 ~ Y j After comparing the targets, the evaluation value of index d1 is 89 points; if the Y prediction of process parameter d2 within the first adjustment range of production time is Y1~Y j =F1(d2,X2,X3,...,X9)~F j (d2, X2, X3, ..., X9) and target Y = Y1 ~ Y j After comparing the targets, the evaluation value of d2 was found to be 88 points. The evaluation values ​​of the other process parameters were consistent with the above process, and so on, without further explanation.

[0146] S204: Determine the first adjustment value among the N+1 process parameter values ​​based on the evaluation values ​​of N+1 indicators.

[0147] The first adjustment value is the process parameter value corresponding to the largest indicator evaluation value among N+1 indicator evaluation values. This can be understood as calculating the indicator evaluation value of each process parameter value within a first range of a certain first process parameter, comparing multiple indicator evaluation values, and selecting the process parameter value corresponding to the largest indicator evaluation value as the first adjustment value.

[0148] For example, such as Figure 5 As shown, for the index evaluation value P of 11 process parameter values ​​within the first adjustment range of production time, the Y prediction of process parameter d1 within the first adjustment range of production time is Y1~Y j =F1(d1,X2,X3,...,X9)~F j (d1, X2, X3, ..., X9) and Y target = Y1 target ~ Y j After comparing the targets, the evaluation value of index d1 is 89 points; if the Y prediction of process parameter d2 within the first adjustment range of production time is Y1~Y j =F1(d2,X2,X3,...,X9)~F j (d2, X2, X3, ..., X9) and Y target = Y1 target ~ Y j After comparing the targets, the evaluation score for d2 is 88 points. Similarly, the evaluation scores for process parameters d3, d4, d5, d6, d7, d8, d9, and d1 are 90, 90, 90, 90, 90, 90, 90, 90, 90, 90, 90, 90, 90, 80, 9 ... 10 The evaluation value of the process parameters can be 96 points, d 11 The evaluation value of the process parameter is 90 points, but other scores are also acceptable; this application does not limit this. After comparing the evaluation values ​​corresponding to the 11 process parameter values, the evaluation value of process parameter d5 is found to be 99 points, which is the highest. Therefore, d5 is determined as the first adjustment value.

[0149] S205: Determine the recommended values ​​for the first process parameters of the product based on the first adjustment value.

[0150] After selecting the first adjustment value corresponding to the largest index evaluation value among multiple process parameter values, this first adjustment value represents the process parameter value that optimizes the product performance index among N+1 process parameter values. It should be noted that if the first adjustment value is the first upper limit (USL) or the first lower limit (LSL), then the first adjustment value is used as the recommended value of the first process parameter. This completes the purpose of obtaining a recommended value for a certain first process parameter (adjustable process parameter) under complex operating conditions. If there are other first process parameters whose recommended values ​​are not yet determined, a prediction algorithm is used to obtain the recommended values ​​for the remaining first process parameters. At this point, the process steps S201 to S205 can continue to complete the prediction calculation of the recommended values ​​for the remaining first process parameters. If the first adjustment value is not the first upper limit (USL) or the first lower limit (LSL), then the first adjustment value is optimized to obtain a second adjustment value, and the recommended value of the first process parameter is determined based on the second adjustment value.

[0151] In one possible scenario, when the first process parameter is the production time in Table 1, the quantity of N+1 is 11, and the first adjustment range includes d1 to d2. 11 For each of the 11 process parameter values, an index evaluation value is calculated. The process parameter value with the highest index evaluation value is selected as the first adjustment value. If the first adjustment value is either the first upper limit or the first lower limit, then the first adjustment value is taken as the recommended value for the first process parameter. Figure 5 As shown, if the evaluation value of process parameter d1 (i.e., the first lower limit value LSL) or d 11 The evaluation values ​​of the process parameters (i.e., the first upper limit value USL) are d1 to d2. 11 The parameter with the highest value among the 11 evaluation indicators is selected as either d1 process parameter or d... 11 The recommended value for process parameter X1: production time is thus obtained. It should be noted that, in the above process, with the first process parameter being production time, the index evaluation values ​​of 11 process parameter values ​​within the first adjustment range were calculated, and the first adjustment value is d1 (the first lower limit value) or d... 11 In the case of (first upper limit value), the operation of obtaining the recommended value of the first process parameter when the production time is obtained by prediction method is completed. If there are other first process parameters whose recommended values ​​are not determined, the recommended value of the first process parameter is obtained by prediction algorithm for the first process parameter whose recommended value is not determined. At this time, the process of S201 to S205 can continue to complete the prediction calculation of the recommended value of the remaining first process parameters.

[0152] In some embodiments, determining the second adjustment value based on the first adjustment value can be understood as forming a second adjustment range based on the process parameters corresponding to two adjacent equally divided points before and after the first adjustment value, and iteratively performing the following operations M times on the second adjustment range: dividing the second adjustment range into two sub-ranges, inputting the median value of each sub-range into the index evaluation model to obtain two index evaluation values; selecting the sub-range with the highest index evaluation value from the two sub-ranges as the new second adjustment range; and using the median value of the sub-range with the highest index evaluation value after M iterations as the second adjustment value. It should be noted that the two sub-ranges can be of equal size (e.g., bisection) or unequal size. This embodiment selects the case where the ranges are equal for analysis. It is understood that after dividing the second adjustment range into two ranges, for a certain range, the index evaluation value corresponding to the median value of that range can be selected as the index evaluation value of that range, or other forms can be used. This embodiment does not limit this.

[0153] It should be noted that by iterating M times, the second adjustment range is continuously narrowed to obtain the second adjustment value corresponding to the largest indicator evaluation value within the narrowed second adjustment range. This allows for precise selection of the second adjustment value, thereby more accurately improving the performance indicators of the produced products.

[0154] The following explanation uses the case where process parameter X1 is production time and iteration count M = 3:

[0155] like Figure 5 As shown in the above analysis, d5 is the first adjustment value within the first adjustment range, which is not equal to the first upper limit or the first lower limit. Figure 7 As shown, Figure 7This is a schematic diagram illustrating a scenario of the second adjustment range corresponding to the first iteration of a cycle, as provided in an embodiment of this application. The second adjustment range ∈ [711.500, 712.500] needs to be formed by combining the two process parameter values ​​corresponding to the two adjacent equally spaced points d4 and d6 before and after d5. This second adjustment range is then divided into two sub-ranges, resulting in region S1 ∈ [711.500, 712.000] and region S2 ∈ [712.000, 712.500]. The index evaluation value corresponding to the median value f1 = 711.750 in region S1 is used as the index evaluation value for region S1, and the index evaluation value corresponding to the median value f2 = 712.750 in region S2 is used as the index evaluation value for region S2. For example... Input f1 into the first mathematical model to obtain the predicted value of the product performance index. Input the predicted value of the product performance index into the index evaluation model. Based on the predicted value and the target value of the product performance index, the index evaluation value is 95 points. Input f2 into the first mathematical model to obtain the predicted value of the product performance index. Input the predicted value of the product performance index into the index evaluation model. Based on the predicted value and the target value of the product performance index, the index evaluation value is 92 points. Comparison shows that the index evaluation value of f1 is larger. Therefore, region S1 is selected as the new second adjustment range, and the second iteration is performed. The specific steps are as follows:

[0156] like Figure 8 As shown, Figure 8 This is a schematic diagram illustrating a scenario of the second adjustment range corresponding to the second iteration of a cycle, as provided in an embodiment of this application. At this time, the new second adjustment range is the range formed by process parameters d4 to d5, which ∈ [711.500, 712.000]. The new second adjustment range is divided into two sub-ranges, resulting in region S1 ∈ [711.500, 711.750] and region S2 ∈ [711.750, 712.000]. The index evaluation value corresponding to the median value g1 = 711.625 in region S1 is used as the index evaluation value for region S1, and the median value g2 = 71... The indicator evaluation value corresponding to 1.825 is used as the indicator evaluation value for region S2. For example, g1 is input into the first mathematical model to obtain the predicted value of the product performance indicator. The predicted value of the product performance indicator is then input into the indicator evaluation model. Based on the predicted value and the target value of the product performance indicator, the indicator evaluation value is 92 points. Similarly, the indicator evaluation value of g2 is 97 points. Comparing the two, the indicator evaluation value of g2 is found to be larger. Therefore, region S2 is selected as the new second adjustment range, and the third iteration is performed. The specific steps are as follows:

[0157] like Figure 9 As shown, Figure 9This is a schematic diagram illustrating a scenario of the second adjustment range corresponding to the third iteration of a cycle, as provided in an embodiment of this application. At this time, the new second adjustment range is the range formed by process parameters f1 to d5, which ∈ [711.750, 712.000]. The new second adjustment range is divided into two sub-ranges, resulting in region S1 ∈ [711.750, 711.825] and region S2 ∈ [711.825, 712.000]. The index evaluation value corresponding to the median value q1 = 711.7875 in region S1 is used as the index evaluation value for region S1, and the median value q1 in region S2 is used as the index evaluation value for region S2. The index evaluation value corresponding to 2 = 711.9125 is used as the index evaluation value of region S2. For example, q1 is input into the first mathematical model to obtain the predicted value of the product performance index. The predicted value of the product performance index is input into the index evaluation model. Based on the predicted value of the product performance index and the target value of the product performance index, the index evaluation value is 93 points. Similarly, the index evaluation value of g2 is 98 points. It is found that the index evaluation value of q2 is larger. At this time, the iteration count ends after 3 times, and the process parameter q2 is the final second adjustment value.

[0158] It should be noted that the number of iterations M can be set by the user. The larger the number of iterations, the more accurate the final value of the second adjustment will be. Correspondingly, the number of steps will be more numerous and complex. The specific number of iterations can be set by the production operator, for example, it can be 8 times. This application embodiment does not limit this.

[0159] In some embodiments, the indicator evaluation value corresponding to the first adjustment value is compared with the evaluation values ​​of M reference indicators, wherein each of the M reference indicator evaluation values ​​is the larger of the two indicator evaluation values ​​corresponding to the median value of two sub-ranges obtained after one round of iteration, and the median value is the process parameter value in the middle of the sub-range; if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values, then the process parameter value corresponding to the largest indicator evaluation value is taken as the recommended value of the first process parameter; if the indicator evaluation value corresponding to the second adjustment value is the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values, then the step of taking the second adjustment value as the recommended value of the first process parameter is executed.

[0160] This can be understood as selecting the largest indicator evaluation value from the indicator evaluation value corresponding to the first adjustment value and the evaluation values ​​of M reference indicators. The process parameter value corresponding to the largest indicator evaluation value is then used as the recommended value of the first process parameter. For example, in the above example, the first adjustment value is d5, and the three reference evaluation values ​​in the M = 3 iterations are the three indicator evaluation values ​​corresponding to f1, g2, and q2, respectively. According to the example above, the indicator evaluation value of f1 is 95 points, the indicator evaluation value of g2 is 97 points, the indicator evaluation value of the second adjustment value q2 is 98 points, and the indicator evaluation value of the first adjustment value d5 is 99 points. That is, the indicator evaluation value corresponding to the second adjustment value q2 is less than the indicator evaluation value corresponding to the first adjustment value d5. Therefore, the first adjustment value d5 is used as the recommended value of the first process parameter. This concludes the calculation process for the recommended value of process parameter X1: production time. If it is necessary to calculate the recommended values ​​of other first process parameters, steps S201 to S205 can be continued.

[0161] exist Figure 2 In the method described, when process parameters change abnormally, a recommended value for the first process parameter (i.e., the adjustable process parameter that needs adjustment) is predicted. Specifically, the process parameter with the highest evaluation value within a first adjustment range is selected as the first adjustment value for the first process parameter. Then, a recommended value for the first process parameter is determined based on this first adjustment value. This method avoids relying on production personnel manually adjusting process parameters based on accumulated experience, and using the manually adjusted parameter as the recommended value for the first process parameter. This approach enables timely and accurate acquisition of recommended values ​​for the adjustable process parameters that need adjustment, even when production conditions undergo complex changes and multiple adjustable process parameters require adjustment. Production personnel can then adjust the process parameters based on these recommended values, improving product performance and adjustment efficiency.

[0162] Meanwhile, when complex operating conditions occur, the types of process parameters may include parameters that do not need adjustment under normal operating conditions, adjustable process parameters that need adjustment under abnormal operating conditions, and non-adjustable process parameters that need adjustment under abnormal operating conditions. Among them, the first process parameter is the process parameter for which the predicted value of product performance index is being calculated; the second process parameter is the process parameter that does not need adjustment under normal operating conditions; the third process parameter is the recommended value of the first process parameter that has completed the recommended value algorithm or the default value of the first process parameter that has not completed the recommended value algorithm (the target value of the operating condition scorecard) when an abnormal operating condition occurs. At this time, the third process parameter is judged. If a recommended value exists, the recommended value is used; if no recommended value exists, the target value is used; the fourth process parameter is the non-adjustable process parameter under abnormal operating conditions.

[0163] Meanwhile, if the first adjustment value is not the first upper limit or the first lower limit, the first adjustment value is further optimized to obtain the second adjustment value. The specific process is as follows: Select the process parameter values ​​corresponding to the two adjacent equally divided points before and after the first adjustment value from the N+1 process parameter values ​​to form the second adjustment range. Divide the second adjustment range into two sub-ranges (usually two equal sub-ranges). The index evaluation value corresponding to the median value of each sub-range is used as the index evaluation value of that sub-range. Compare the index evaluation values ​​of the two sub-ranges and select the sub-range with the larger index evaluation value as the new second adjustment range. Continue to divide and compare the sub-ranges. The sum of the number of the second adjustment range and the new second adjustment range is M times (a total of M iterations).

[0164] Simultaneously, if the indicator evaluation value corresponding to the second adjustment value is greater than the indicator evaluation value corresponding to the first adjustment value and the M reference evaluation values, then the second adjustment value is used as the recommended value for the first process parameter; if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values, then the process parameter value corresponding to the largest indicator evaluation value is used as the recommended value for the first process parameter. This method can further obtain specific recommended values ​​within the first adjustment range, ensuring that the product performance indicators corresponding to the recommended values ​​remain optimal, thus improving the accuracy of the recommended values ​​while simultaneously improving product quality.

[0165] The above describes a method for recommending production process parameters based on abnormal operating conditions. The following describes the apparatus used in this method.

[0166] like Figure 10 As shown, Figure 10 This is a schematic diagram of an apparatus 100 for recommending production process parameters based on abnormal operating conditions, provided in an embodiment of this application. The apparatus 100 includes: an adjustment unit 1001, a selection unit 1002, an evaluation unit 1003, a determination unit 1004, and a first determination unit 1005. This apparatus can be the aforementioned equipment or a device or module within the equipment. Each of the aforementioned units (or modules) is a functional module divided according to its function. In specific implementations, some functional blocks may be further subdivided into more smaller functional modules, and some functional modules may be combined into a single functional module. However, regardless of whether these functional modules are subdivided or combined, the general process executed during the calculation of recommended values ​​for production process parameters under abnormal operating conditions is the same. Typically, each functional module corresponds to its own program code (i.e., a computer program stored in the device's memory). When the program code corresponding to each functional module runs on the processor, it causes the functional module to execute the corresponding process to achieve the corresponding function. The descriptions of each unit are as follows:

[0167] The adjustment unit 1001 is used to determine a first adjustment range of the first process parameter, wherein the first process parameter is an adjustable process parameter that affects the product performance index in production, and the first adjustment range is an adjustment range determined according to the first upper limit value and the first lower limit value of the first process parameter in the design scorecard.

[0168] Selection unit 1002 is used to select N+1 process parameter values ​​from the first adjustment range, where N is an integer greater than 1;

[0169] Evaluation unit 1003 is used to input the N+1 process parameter values ​​into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators, and input the predicted values ​​of the N+1 sets of product performance indicators into the indicator evaluation model to obtain N+1 indicator evaluation values. The indicator evaluation values ​​are used to evaluate the overall closeness of the predicted value of each set of product performance indicators in the multiple sets of predicted values ​​of product performance indicators corresponding to the N+1 process parameter values ​​to the corresponding set of product performance target values.

[0170] The determining unit 1004 is used to determine a first adjustment value among the N+1 process parameter values ​​based on the N+1 index evaluation values; wherein, the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 index evaluation values.

[0171] The first determining unit 1005 is used to determine the recommended value of the first process parameter of the product based on the first adjustment value.

[0172] As can be seen, when process parameters change, the recommended value of the first process parameter (i.e., the adjustable process parameter that needs adjustment) is predicted. This involves selecting the process parameter with the highest evaluation value within the first adjustment range as the first adjustment value, and then further determining the recommended value based on this first adjustment value. This method avoids relying on production personnel manually adjusting process parameters based on accumulated experience, using the manually adjusted parameter as the recommended value for the first process parameter. This approach enables timely and accurate acquisition of the recommended values ​​for the adjustable process parameters when production conditions change complexly and multiple adjustable process parameters need adjustment. Production personnel can then adjust the process parameters based on these recommended values, improving product performance and adjustment efficiency.

[0173] It should be noted that, under complex operating conditions, for adjustable process parameters (the first process parameter) that need adjustment, a second adjustment value is selected as the recommended value of the first process parameter through a prediction method; for non-adjustable process parameters that need adjustment, they are usually treated as abnormal parameters, and the abnormal predicted value of the abnormal parameter is used for production; for parameters that do not need adjustment, they can be understood as parameters under normal operating conditions, and the target value of the process parameter in the benchmark operating condition scorecard is used for production (i.e., the process parameter value corresponding to the largest product performance index).

[0174] It should be noted that the index evaluation value is used to evaluate the overall closeness between the predicted value of each set of product performance indicators and the corresponding set of product performance target values ​​among the predicted values ​​of multiple sets of product performance indicators corresponding to the process parameters. It can be understood as comparing the closeness between the predicted value of each set of product performance indicators and the target value of each set of product performance indicators, and finally taking the results of multiple comparisons as the overall closeness. The closer the closeness, the higher the corresponding index evaluation value.

[0175] In one possible implementation, regarding the input of the N+1 process parameter values ​​into the first mathematical model to obtain N+1 sets of predicted product performance indicators, the evaluation unit 1003 is specifically used for:

[0176] Determine a first reference value for the second process parameter, wherein the first reference value is the target value of the second process parameter in the benchmark scorecard;

[0177] Determine a second reference value for a third process parameter and an abnormal prediction value for a fourth process parameter, wherein the type of the third process parameter is an adjustable process parameter, the type of the fourth process parameter is a non-adjustable process parameter, and the second process parameter, the third process parameter value, the fourth process parameter, and the first process parameter belong to the set of independent variables of the first mathematical model;

[0178] If the recommended value exists for the third process parameter, then the second reference value is the recommended value for the third process parameter; if the recommended value does not exist for the third process parameter, then the second reference value is the target value for the third process parameter, wherein the target value for the third process parameter is the target value for the third process parameter in the benchmark working condition scorecard.

[0179] The N+1 process parameter values, the first reference value, the second reference value, and the abnormal prediction value of the fourth process parameter are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators.

[0180] It can be seen that when complex operating conditions occur, the types of process parameters may include parameters that do not need to be adjusted under normal operating conditions, adjustable process parameters that need to be adjusted under abnormal operating conditions, and non-adjustable process parameters that need to be adjusted under abnormal operating conditions. Among them, the first process parameter is the process parameter for which the predicted value of product performance index is being calculated; the second process parameter is the process parameter that does not need to be adjusted under normal operating conditions; the third process parameter is the recommended value of the first process parameter that has completed the recommended value algorithm or the default value of the first process parameter that has not completed the recommended value algorithm (the target value of the benchmark operating condition scorecard) when abnormal operating conditions occur. At this time, the third process parameter is judged. If a recommended value exists, the recommended value is used; if no recommended value exists, the target value is used; the fourth process parameter is the non-adjustable process parameter under abnormal operating conditions.

[0181] Specifically, the set of independent variables in the first mathematical model is typically a set of first, second, third, and fourth process parameters. When calculating the predicted value of the product performance index for N+1 process parameter values ​​within the first adjustment range of a given first process parameter, it is necessary to first determine the initial values ​​for the remaining process parameters in the independent variable set, excluding the first process parameter. This can be understood as follows: if a recommended value exists for the third process parameter, it is used as the initial value; if no recommended value exists for the remaining third process parameters, the target value is used as the initial value. The second process parameter uses the target value from the benchmark scorecard as its initial value; and the fourth process parameter uses the abnormal predicted value as its initial value. This method considers that the predicted value of the product performance index is affected by all process parameters of the product. When calculating the predicted value of the product performance index for process parameter values ​​within the adjustment range, the values ​​of the remaining process parameters are also pre-set, making the predicted value of the product performance index more accurate.

[0182] In one possible implementation, for the first process parameter in the set of independent variables in the first mathematical model, a parameter calculation operation for the predicted value of the product performance index is performed. If the second reference value of the third process parameter does not have a recommended value, then the third process parameter without a recommended value undergoes the parameter calculation operation process for the predicted value of the product performance index. The parameter calculation operation process for the third process parameter is the same as that for the first process parameter. It should be noted that for each third process parameter in the set of independent variables that does not yet have a recommended value, a parameter calculation operation for the predicted value of the product performance index is performed, which is the same as that for the first process parameter, until every adjustable process parameter in the set of independent variables has a recommended value.

[0183] In one possible implementation, the selection unit 1002 is specifically used for:

[0184] Determine N-1 equal division points from the first adjustment range;

[0185] The N-1 equal division points and the first upper limit and the first lower limit of the first adjustment range are determined as N+1 process parameter values.

[0186] It should be noted that after obtaining the first adjustment range of the adjustable process parameter (i.e. the first process parameter) that needs to be adjusted, when selecting several process parameters, N-1 equal division points (N is a positive integer greater than 1) can usually be determined within the first adjustment range. The N-1 equal division points, as well as the first upper limit and the first lower limit of the first adjustment range, are determined as N+1 process parameter values, and the index evaluation values ​​of the N+1 process parameter values ​​are calculated respectively.

[0187] In one possible implementation, the first determining unit 1005 is specifically used for:

[0188] If the first adjustment value is the first upper limit value or the first lower limit value, then the first adjustment value shall be used as the recommended value of the first process parameter value.

[0189] If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value is optimized to obtain a second adjustment value, and the recommended value of the first process parameter is determined based on the second adjustment value.

[0190] It can be seen that the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 process parameter values ​​within the first adjustment range. If the first adjustment value is the first upper limit or the first lower limit of the first adjustment range, then the first adjustment value is used as the recommended value of the first process parameter. If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value needs to be further optimized to obtain the second adjustment value. Then, the recommended value of the first process parameter is determined based on the second adjustment value. This method can further refine the first adjustment value based on the first adjustment value to obtain the second adjustment value.

[0191] In one possible implementation of the second aspect, in the step of optimizing the first adjustment value to obtain a second adjustment value and determining a recommended value for the first process parameter based on the second adjustment value, the first determining unit 1005 is specifically used for:

[0192] The second adjustment range is formed by the process parameter values ​​corresponding to two adjacent equally divided points before and after the first adjustment value;

[0193] For the second adjustment range, perform the following operation M times:

[0194] The second adjustment range is divided into two sub-ranges;

[0195] The intermediate values ​​of the two sub-ranges are respectively input into the indicator evaluation model to obtain two indicator evaluation values;

[0196] Based on the evaluation values ​​of the two indicators, the sub-range with the highest evaluation value among the two sub-ranges is selected as the new second adjustment range;

[0197] The median value of the sub-range with the highest index evaluation value after M iterations is used as the second adjustment value;

[0198] The second adjustment value is used as the recommended value for the first process parameter.

[0199] It can be seen that if the first adjustment value is not the first upper limit or the first lower limit, the first adjustment value is further optimized to obtain the second adjustment value. The specific process is as follows: Select the process parameter values ​​corresponding to the two adjacent equally divided points before and after the first adjustment value from the N+1 process parameter values ​​to form the second adjustment range. Divide the second adjustment range into two sub-ranges (usually two equal sub-ranges). The index evaluation value corresponding to the median value of each sub-range is used as the index evaluation value of that sub-range. Compare the index evaluation values ​​of the two sub-ranges and select the sub-range with the larger index evaluation value as the new second adjustment range. Continue to divide and compare the sub-ranges. The sum of the number of the second adjustment range and the new second adjustment range is M times (a total of M iterations).

[0200] It should be noted that the number of iterations M is adjustable. If a more accurate second process parameter is required, the value of M can be set larger. This method further refines the first adjustment value. By iterating M times, the size of the second adjustment range is continuously reduced. The middle value of the larger range of index evaluation values ​​obtained in the last iteration is selected as the second adjustment value, which can obtain a more accurate recommended value for the process parameter and improve the accuracy of the recommended value.

[0201] It should be noted that in this method, the condition for directly using the second adjustment value as the recommended value of the first process parameter is that the index evaluation value corresponding to the second adjustment value is greater than the index evaluation value corresponding to the first adjustment value and M reference evaluation values. Under complex working conditions, when multiple process parameters need to be adjusted, each adjustable process parameter corresponds to a first adjustment value. Among multiple first adjustment values, there may be a situation where a certain first adjustment value is the first lower limit or the first upper limit, or the index evaluation value corresponding to a certain first adjustment value is greater than the index evaluation value corresponding to the second adjustment value and M reference evaluation values, or other situations may occur. In the actual production process, when there are too many adjustable process parameters that need to be adjusted, the above-mentioned possibilities may occur on different process parameters throughout the entire production process. Therefore, in this method, the second adjustment value is directly used as the recommended value of the first process parameter, which is assumed by default that the product performance index corresponding to the second adjustment value will be optimal in this production process.

[0202] In one possible implementation, the device 100 further includes:

[0203] The comparison unit is used to compare the index evaluation value corresponding to the first adjustment value with M reference index evaluation values ​​before the second adjustment value is used as the recommended value of the first process parameter. Each of the M reference index evaluation values ​​is the larger of the two index evaluation values ​​corresponding to the median value of two sub-ranges obtained after one round of iteration. The median value is the process parameter value in the middle of the sub-range.

[0204] The second determining unit is used to determine the process parameter value corresponding to the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values ​​if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values.

[0205] The first determining unit 1005 is specifically used to execute the step of using the second adjusting value as the recommended value of the first process parameter if the indicator evaluation value corresponding to the second adjustment value is the largest among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values.

[0206] It can be seen that if the indicator evaluation value corresponding to the second adjustment value is greater than the indicator evaluation value corresponding to the first adjustment value and the M reference evaluation values, then the second adjustment value is used as the recommended value of the first process parameter; if the indicator evaluation value corresponding to the second adjustment value is not the largest indicator evaluation value among the indicator evaluation value corresponding to the first adjustment value and the M reference indicator evaluation values, then the process parameter value corresponding to the largest indicator evaluation value is used as the recommended value of the first process parameter. This method can further obtain specific recommended values ​​within the first adjustment range, ensuring that the product performance indicators corresponding to the recommended values ​​remain optimal, thus improving the accuracy of the recommended values ​​while simultaneously improving product quality.

[0207] This application also provides a computer-readable storage medium storing a computer program that, when run on a processor, implements... Figure 2 This paper presents a method for recommending production process parameters based on abnormal operating conditions.

[0208] This invention also provides a computer program product that, when run on a processor, implements... Figure 2 This paper presents a method for recommending production process parameters based on abnormal operating conditions.

[0209] In summary, by implementing the embodiments of this application, when process parameters undergo abnormal changes, the recommended value of the first process parameter (i.e., the adjustable process parameter that needs adjustment) is predicted. Specifically, the process parameter with the highest evaluation value within a first adjustment range is selected as the first adjustment value of the first process parameter. Then, a recommended value is obtained based on this first adjustment value. This method avoids relying on production personnel manually adjusting process parameters based on accumulated experience, and using the manually adjusted parameter as the recommended value of the first process parameter. This approach enables timely and accurate acquisition of the recommended values ​​of the adjustable process parameters that need adjustment, even when production conditions undergo complex changes and multiple adjustable process parameters require adjustment. Production personnel can then adjust the process parameters based on these recommended values, improving product performance and adjustment efficiency.

[0210] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program using computer program-related hardware. The computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing computer program code, such as read-only memory (ROM) or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for recommending production process parameters based on abnormal operating conditions, characterized in that, include: Select N+1 process parameter values ​​from the first adjustment range of the first process parameter, where N is an integer greater than 1. The first process parameter is an adjustable process parameter that affects the product performance index in production. The first adjustment range is the adjustment range determined according to the first upper limit and the first lower limit of the first process parameter in the design scorecard. The N+1 process parameter values ​​are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators. The predicted values ​​of the N+1 sets of product performance indicators are then input into the indicator evaluation model to obtain N+1 indicator evaluation values. The indicator evaluation values ​​are used to evaluate the overall closeness of the predicted value of each set of product performance indicators in the multiple sets of predicted values ​​of product performance indicators corresponding to the N+1 process parameter values ​​to the corresponding set of product performance target values. The first adjustment value among the N+1 process parameter values ​​is determined based on the N+1 index evaluation values, wherein the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 index evaluation values. The recommended values ​​for the first process parameters of the product are determined based on the first adjustment value; The step of inputting the N+1 process parameter values ​​into the first mathematical model to obtain N+1 sets of predicted product performance indicators includes: Determine a first reference value for the second process parameter, wherein the first reference value is the target value of the second process parameter in the benchmark scorecard; Determine a second reference value for a third process parameter and an abnormal prediction value for a fourth process parameter, wherein the type of the third process parameter is an adjustable process parameter, the type of the fourth process parameter is a non-adjustable process parameter, and the second process parameter, the third process parameter, the fourth process parameter, and the first process parameter belong to the set of independent variables of the first mathematical model; If the recommended value exists for the third process parameter, then the second reference value is the recommended value for the third process parameter. If the recommended value does not exist for the third process parameter, then the second reference value is the target value for the third process parameter, wherein the target value for the third process parameter is the target value for the third process parameter in the benchmark working condition scorecard. The N+1 process parameter values, the first reference value, the second reference value, and the abnormal prediction value of the fourth process parameter are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators; wherein, the data blocks corresponding to the first process parameter, the second process parameter, and the fourth process parameter are combined in a chain-like data structure in chronological order and in a sequentially connected manner. The first process parameter is the process parameter for which the predicted value calculation of product performance indicators is being performed; the second process parameter is the process parameter that does not need to be adjusted under normal operating conditions; and the third process parameter is the recommended value of the first process parameter that has completed the recommended value algorithm or the default value of the first process parameter that has not completed the recommended value algorithm when abnormal operating conditions occur.

2. The method according to claim 1, characterized in that, For the first process parameter in the set of independent variables in the first mathematical model, the parameter calculation operation for the predicted value of the product performance index is performed. If the second reference value of the third process parameter does not have a recommended value, then the parameter calculation operation for the predicted value of the product performance index is performed for the third process parameter that does not have a recommended value. The parameter calculation operation process for the third process parameter is the same as that for the first process parameter.

3. The method according to any one of claims 1 to 2, characterized in that, The step of selecting N+1 process parameter values ​​from the first adjustment range of the first process parameter includes: Determine N-1 equal division points from the first adjustment range; The N-1 equal division points and the first upper limit and the first lower limit of the first adjustment range are determined as N+1 process parameter values.

4. The method according to claim 3, characterized in that, Determining the recommended value of the first process parameter of the product based on the first adjustment value includes: If the first adjustment value is the first upper limit value or the first lower limit value, then the first adjustment value shall be used as the recommended value of the first process parameter; If the first adjustment value is not the first upper limit or the first lower limit, then the first adjustment value is optimized to obtain a second adjustment value, and the recommended value of the first process parameter is determined based on the second adjustment value.

5. The method according to claim 4, characterized in that, The step of optimizing the first adjustment value to obtain a second adjustment value, and determining the recommended value of the first process parameter based on the second adjustment value, includes: The second adjustment range is formed by the process parameter values ​​corresponding to two adjacent equally divided points before and after the first adjustment value; For the second adjustment range, perform the following operation M times: The second adjustment range is divided into two sub-ranges; The intermediate values ​​of the two sub-ranges are respectively input into the indicator evaluation model to obtain two indicator evaluation values; Based on the evaluation values ​​of the two indicators, the sub-range with the highest evaluation value among the two sub-ranges is selected as the new second adjustment range; The median value of the sub-range with the highest index evaluation value after M iterations is used as the second adjustment value; The second adjustment value is used as the recommended value for the first process parameter.

6. A device for recommending production process parameters based on abnormal operating conditions, characterized in that, include: The selection unit is used to select N+1 process parameter values ​​from the first adjustment range of the first process parameter, where N is an integer greater than 1. The first process parameter is an adjustable process parameter that affects the product performance index in production, and the first adjustment range is an adjustment range determined according to the first upper limit value and the first lower limit value of the first process parameter in the design scorecard. The evaluation unit is used to input the N+1 process parameter values ​​into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators, and input the predicted values ​​of the N+1 sets of product performance indicators into the indicator evaluation model to obtain N+1 indicator evaluation values. The indicator evaluation values ​​are used to evaluate the overall closeness of the predicted value of each set of product performance indicators in the multiple sets of predicted values ​​of product performance indicators corresponding to the N+1 process parameter values ​​to the corresponding set of product performance target values. The determining unit is used to determine a first adjustment value among the N+1 process parameter values ​​based on the N+1 index evaluation values; wherein the first adjustment value is the process parameter value corresponding to the largest index evaluation value among the N+1 index evaluation values. The first determining unit is configured to determine a recommended value for the first process parameter of the product based on the first adjustment value; The step of inputting the N+1 process parameter values ​​into the first mathematical model to obtain N+1 sets of predicted product performance indicators includes: Determine a first reference value for the second process parameter, wherein the first reference value is the target value of the second process parameter in the benchmark scorecard; Determine a second reference value for a third process parameter and an abnormal prediction value for a fourth process parameter, wherein the type of the third process parameter is an adjustable process parameter, the type of the fourth process parameter is a non-adjustable process parameter, and the second process parameter, the third process parameter, the fourth process parameter, and the first process parameter belong to the set of independent variables of the first mathematical model; If the recommended value exists for the third process parameter, then the second reference value is the recommended value for the third process parameter. If the recommended value does not exist for the third process parameter, then the second reference value is the target value for the third process parameter, wherein the target value for the third process parameter is the target value for the third process parameter in the benchmark working condition scorecard. The N+1 process parameter values, the first reference value, the second reference value, and the abnormal prediction value of the fourth process parameter are respectively input into the first mathematical model to obtain the predicted values ​​of N+1 sets of product performance indicators; wherein, the data blocks corresponding to the first process parameter, the second process parameter, and the fourth process parameter are combined in a chain-like data structure in chronological order and in a sequentially connected manner. The first process parameter is the process parameter for which the predicted value calculation of product performance indicators is being performed; the second process parameter is the process parameter that does not need to be adjusted under normal operating conditions; and the third process parameter is the recommended value of the first process parameter that has completed the recommended value algorithm or the default value of the first process parameter that has not completed the recommended value algorithm when abnormal operating conditions occur.

7. An electronic device, characterized in that, It includes a transceiver, a processor, and a memory, wherein the memory is used to store a computer program, and the processor invokes the computer program to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program that, when executed by a processor, performs the method according to any one of claims 1-5.

9. A computer program product, characterized in that, When the computer program in the computer program product is executed by a processor, it performs the method described in any one of claims 1-5.

Images