A nano-antibacterial yoga suit preparation process optimization management method and system

Abstract

The application provides a kind of nanometer antibacterial yoga suit preparation process optimization management method and system, belong to optimization management technical field, specifically includes: based on the parameter deviation degree of parameter adjustment combination and other parameter adjustment combinations, and in combination with the correlation degree of the fluctuation type of parameter adjustment combination in different product performance indexes and other parameter adjustment combinations, determine the parameter adjustment strategy under parameter adjustment combination, adjust the production parameters under parameter adjustment combination using parameter adjustment strategy to obtain adjustment processing result, and using the similarity degree of adjustment processing result and the simulation result of digital twin model, and the distribution data of product performance indexes that do not meet the requirements of similarity degree, determine the parameter adjustment management method when production parameters exist abnormity under different control parameter interval combinations, improve the efficiency and comprehensiveness of digital twin model verification processing.

Description

Technical Field

[0001] This invention belongs to the field of optimization management technology, and in particular relates to a method and system for optimizing the manufacturing process of nano-antibacterial yoga clothing. Background Technology

[0002] Yoga, due to its high intensity and high perspiration rate, places high demands on the antibacterial properties and wearing comfort of clothing. Sweat easily breeds bacteria in a warm, humid environment, producing odors and affecting the user experience. Currently, applying nano-antibacterial agents (such as nano-silver, nano-zinc oxide, graphene, etc.) to the surface of yoga clothing fabric is the main method for imparting antibacterial properties.

[0003] To address the aforementioned technical problems, the invention patent application CN202511042348.1, "A Method and System for Optimizing the Preparation Process and Antibacterial and Breathable Fabric for Yoga Apparel," determines an automatic adjustment scheme corresponding to the adjustment process based on adjustment data, quality inspection results, and fabric quality inspection results during production. Based on the adjustment data of the automatic adjustment scheme in the adjustment process demand state, it determines the target for adding the strategy library of automatic adjustment schemes under different quality inspection results, thus improving the production quality of the fabric. However, the following technical problems remain: To ensure the reliability of production quality control, existing technical solutions use digital twin models to verify and simulate these indicators, thereby improving the reliability of anomaly identification and handling. However, because production parameters are relatively stable, production quality indicators are also relatively stable, making it difficult to determine the reliability of the simulation results from the digital twin model. Therefore, how to adjust production parameters to ensure the reliability of the digital twin model verification has become an urgent technical problem to be solved.

[0004] Therefore, there is an urgent need for an optimized management method and system for the manufacturing process of nano-antibacterial yoga clothing. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing, which includes: S1 uses the manufacturing process of nano-antibacterial yoga clothing to determine the benchmark parameters of product performance indicators under different combinations of control parameter ranges. Based on the consistency of the benchmark parameters of the product performance indicators, when it is determined that the parameter adjustment combination in the control parameter range combination needs to be identified, the parameter adjustment combination in the control parameter range combination is determined based on the fluctuation data of the product performance indicators under the control parameter range combination. S2 determines the parameter adjustment strategy under the parameter adjustment combination based on the degree of parameter deviation between the parameter adjustment combination and other parameter adjustment combinations, and in combination with the correlation between the fluctuation type of different product performance indicators in the parameter adjustment combination and other parameter adjustment combinations. S3 uses the parameter adjustment strategy to adjust the production parameters under the parameter adjustment combination to obtain the adjustment result. Then, using the similarity between the adjustment result and the simulation result of the digital twin model, as well as the distribution data of product performance indicators that do not meet the similarity requirements, S3 determines the parameter adjustment management method when there are abnormalities in the production parameters under different combinations of control parameter ranges.

[0006] The beneficial effects of this invention are as follows: Based on the fluctuation data of product performance indicators under the control parameter range combination, the parameter adjustment combination in the control parameter range combination is determined. Based on the fluctuation of product performance indicators under the control parameter range combination with the change of control parameters, the probability and magnitude of fluctuation of product performance indicators when parameter adjustment is performed under the control parameter range combination are determined. Based on the probability and magnitude of fluctuation, the parameter adjustment combination in the control parameter range combination is determined. This not only reduces the risk of adjustment processing in a large number of control parameter range combinations, but also lays the foundation for ensuring the reliability of model verification.

[0007] By utilizing the similarity between the adjusted processing results and the simulation results of the digital twin model, as well as the distribution data of product performance indicators whose similarity does not meet the requirements, a parameter adjustment management method is determined when production parameters are abnormal under different combinations of control parameter intervals. Based on the consistency between the production indicators in the adjusted production parameter combinations and the digital twin model, the reliability of the current digital twin model's simulation results is determined. Based on the reliability of the simulation results and the similarity between the production indicators with consistency deviations under the controlled parameter interval combinations and other controlled parameter interval combinations, a parameter adjustment management method is implemented when production parameters are abnormal under different combinations of control parameter intervals. This ensures production stability while further guaranteeing the comprehensiveness and reliability of the digital twin model's verification processing.

[0008] Furthermore, the preparation process includes control ranges of production parameters in different production equipment.

[0009] Furthermore, the combination of control parameter ranges is determined by combining the control range ranges of production parameters in different production equipment under the same preparation process.

[0010] Furthermore, the benchmark parameter of the product performance index is determined based on the parameter that has the highest number of products under the product performance index under the combination of the control parameter ranges.

[0011] Furthermore, the parameter that represents the largest number of goods under the product performance indicators is determined based on the quality inspection results of the product performance indicators.

[0012] Furthermore, the identification process for determining the parameter adjustment combinations within the control parameter range combinations that require processing specifically includes: S11 Determines the deviation coefficient of the benchmark parameter of the product performance index between different combinations of control parameter ranges based on the degree of consistency of the basic parameters of the product performance index. S12 uses the deviation coefficient to determine the group of control parameter intervals where the product performance index has deviations, and takes them as the deviation combination group. S13 determines whether it is necessary to identify the parameter adjustment combination in the control parameter range combination based on the deviation combination group under different product performance indicators and the degree of overlap of the deviation combination group.

[0013] Furthermore, the method for determining the parameter adjustment management method when the production parameters are abnormal is as follows: S41 uses the adjustment processing result to construct the interval combination of the adjustment range corresponding to different production parameters under the control parameter interval combination, and uses it as the adjustment parameter combination. S42, based on the combination of control parameters, adjusts the similarity between the product performance indicators and the digital twin model under the parameter combination, and takes the adjustment parameter combination that meets the requirements for the similarity of different product performance indicators as a consistent combination. S43 uses consistent combination data under different combinations of control parameter ranges and product performance indicators whose similarity does not meet the requirements under different combinations of adjustment parameters to determine the parameter adjustment management method when the production parameters are abnormal under the control parameter range combination.

[0014] Furthermore, if the deviation rate between the product performance index under the adjusted parameter combination and the simulation result of the digital twin model is less than the preset deviation rate, then the similarity of the product performance index is determined to meet the requirements.

[0015] Furthermore, the abnormality of the production parameters refers to the adjustment range corresponding to the production parameters that are not within the combination of the control parameter ranges.

[0016] Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing when running the computer program.

[0017] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0020] Figure 1 This is a flowchart of a method for optimizing the manufacturing process of nano-antibacterial yoga wear. Figure 2 It is a flowchart for identifying the parameter adjustment combination in the control parameter range combination that needs to be performed; Figure 3 This is a flowchart illustrating the method for determining the parameter adjustment combination in the combination of control parameter ranges. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0022] Example 1 like Figure 1 As shown, this application provides a method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing, specifically including: The core objective of this embodiment is to optimize and manage the manufacturing process of nano-antibacterial yoga wear through a digital twin model, ensuring the consistency between the simulation results of the digital twin model and actual production, thereby achieving precise adjustment management when production parameters are abnormal. Its core logic is as follows: first, determine whether parameter adjustment combinations need to be identified by the consistency of the product performance index benchmark parameters; then, perform fluctuation analysis on the combination of control parameter ranges that need adjustment to determine the specific parameter adjustment combinations; next, determine the parameter adjustment strategy by combining the degree of parameter deviation and the correlation between fluctuation types; finally, determine the parameter adjustment management method when production parameters are abnormal by using the similarity between the adjustment results and the simulation results. The overall logic follows the process of "identifying needs → determining adjustment combinations → formulating adjustment strategies → verification and management".

[0023] S1 uses the manufacturing process of nano-antibacterial yoga clothing to determine the benchmark parameters of product performance indicators under different combinations of control parameter ranges. Based on the consistency of the benchmark parameters of the product performance indicators, when it is determined that the parameter adjustment combination in the control parameter range combination needs to be identified, the parameter adjustment combination in the control parameter range combination is determined based on the fluctuation data of the product performance indicators under the control parameter range combination. The preparation process refers to the complete production process of nano antibacterial yoga fiber from raw material processing to finished product preparation, including fiber preparation, antibacterial treatment, weaving, dyeing and finishing, and post-processing.

[0024] For example, assuming that the manufacturing process of nano-antibacterial yoga clothing includes spinning, antibacterial finishing, weaving, and setting processes, then the benchmark parameters for product performance indicators under different combinations of control parameter ranges for each process should be determined.

[0025] This step lays the foundation for subsequent digital twin model verification and parameter adjustment management. Its significance lies in ensuring that the digital twin model can accurately reflect the actual production process by systematically analyzing the relationship between the manufacturing process and product performance indicators.

[0026] Furthermore, the preparation process includes control ranges of production parameters in different production equipment.

[0027] The control range of the production parameters refers to the adjustable range of various process parameters during the operation of the production equipment, including the upper and lower limits of parameters such as temperature, pressure, speed, and concentration.

[0028] Assuming the production parameters of the spinning equipment include spinning temperature, spinning speed, and cooling air velocity, then the control range of each parameter is determined, such as the spinning temperature within a certain temperature range, the spinning speed within a certain speed range, and the cooling air velocity within a certain air velocity range.

[0029] This step clarifies the parameter adjustment boundaries of the production equipment, which is significant because it provides basic data support for the subsequent construction of control parameter range combinations, ensuring the rationality and feasibility of parameter adjustments.

[0030] Furthermore, the combination of control parameter ranges is determined by combining the control range ranges of production parameters in different production equipment under the same preparation process.

[0031] The control parameter range combination refers to a parameter configuration scheme formed by arranging and combining the control ranges of production parameters of different production equipment under the same preparation process.

[0032] Assuming the manufacturing process involves spinning equipment and antibacterial finishing equipment, and the spinning equipment has multiple control parameter ranges, and the antibacterial finishing equipment has multiple control parameter ranges, then the number of combinations of control parameter ranges is the number of equipment ranges constructed according to the existing process requirements.

[0033] This step constructs a search space for parameter optimization, which is significant because it comprehensively covers possible parameter configuration schemes and provides a complete candidate set for finding the optimal combination of production parameters.

[0034] Furthermore, the benchmark parameter of the product performance index is determined based on the parameter that has the highest number of products under the product performance index under the combination of the control parameter ranges.

[0035] The parameter with the largest number of products refers to the parameter value in which the percentage of products whose quality inspection results fall within a certain parameter value range is the highest under a specific combination of control parameter ranges.

[0036] Suppose that multiple batches of nano-antibacterial yoga clothes are produced under a certain combination of control parameters. If the antibacterial performance index is statistically analyzed, it is found that the number of products with antibacterial rates distributed within a certain range is the largest. Then, the median of this range is taken as the benchmark parameter for the antibacterial performance index under this combination of control parameters.

[0037] This step determines the standard performance reference value under each combination of control parameter ranges. Its significance lies in establishing a unified performance evaluation benchmark, which facilitates subsequent judgment on whether there are deviations in product performance.

[0038] Furthermore, the parameter that represents the largest number of goods under the product performance indicators is determined based on the quality inspection results of the product performance indicators.

[0039] The quality inspection results refer to the performance index data obtained after quality testing of the nano antibacterial yoga clothing, including antibacterial rate, tensile strength, breathability, color fastness, etc.

[0040] Suppose we are conducting quality inspections on products manufactured under a certain combination of control parameters, and obtaining data on the antibacterial rate, tensile strength, and air permeability of each product. We then statistically analyze the parameter value with the highest number of products for each performance indicator, and use it as the benchmark parameter for that performance indicator.

[0041] This step transforms quality inspection data into benchmark parameters, which is significant in ensuring that the benchmark parameters originate from actual production data and improving the authenticity and reliability of the benchmark parameters.

[0042] Specifically, such as Figure 2 As shown, the identification process for determining the parameter adjustment combination within the control parameter range combination that needs to be performed specifically includes: In this embodiment, based on the consistency of product performance indicators under different manufacturing processes, the reliability of the verification processing of the simulation results of the digital twin model under the existing manufacturing process is determined. The reliability of the verification processing results is then used to determine whether it is necessary to adjust the equipment parameters of different production equipment, i.e., to identify the parameter adjustment combination, thus laying the foundation for ensuring the reliability of the digital twin model.

[0043] S11 Determines the deviation coefficient of the benchmark parameter of the product performance index between different combinations of control parameter ranges based on the degree of consistency of the basic parameters of the product performance index. The deviation coefficient refers to the relative difference in the benchmark parameters of the same product performance index between different combinations of control parameter ranges, and is used to quantify the consistency of the benchmark parameters.

[0044] Suppose there are two control parameter ranges, and the baseline parameters for their antibacterial performance indicators are one percentage and another percentage, then the deviation coefficient is calculated as the absolute value of the difference between the two divided by half the sum of the two.

[0045] This step quantifies the performance differences between different combinations of control parameter ranges. Its significance lies in identifying control parameter range combinations with significant differences in benchmark parameters, providing a data foundation for the subsequent construction of deviation combination groups.

[0046] S12 uses the deviation coefficient to determine the group of control parameter intervals where the product performance index has deviations, and takes them as the deviation combination group. The deviation combination group refers to the set of control parameter intervals where the deviation coefficient of the reference parameter between each other is greater than a preset threshold under a certain product performance index.

[0047] If, under the antibacterial performance index, the deviation coefficient between two control parameter range combinations is greater than a preset threshold, then the two combinations constitute a deviation combination group.

[0048] This step identifies combinations of control parameter intervals where performance indicators exhibit systematic deviations. Its significance lies in classifying combinations of control parameter intervals with similar deviation characteristics, making it easier to determine their place within the current group.

[0049] S13 determines whether it is necessary to identify the parameter adjustment combination in the control parameter range combination based on the deviation combination group under different product performance indicators and the degree of overlap of the deviation combination group.

[0050] The degree of overlap of the deviation combination groups refers to the proportion of the number of control parameter interval combinations shared by deviation combination groups under different product performance indicators to the total number of control parameter interval combinations.

[0051] Assuming that the deviation combination group under the antibacterial performance index contains some control parameter range combinations, and the deviation combination group under the tensile strength index contains another part of the control parameter range combinations, then the number of control parameter range combinations that overlap between the two is counted as the degree of overlap.

[0052] This step integrates deviation information from multiple performance indicators to determine whether parameter adjustment combinations need to be identified. Its significance lies in determining whether the digital twin model can be verified within multiple deviation combination groups, thus ensuring the comprehensiveness of the verification process.

[0053] Specifically, the deviation combination group is constructed based on the control parameter ranges in which the deviation coefficients between each other under the product performance index are greater than a preset deviation coefficient threshold.

[0054] The preset deviation coefficient threshold refers to the critical value for judging whether the combination of two control parameter intervals constitutes a deviation relationship. When the deviation coefficient exceeds the threshold, it is considered that there is a significant deviation.

[0055] Assuming the preset deviation coefficient threshold is a fixed value, when the deviation coefficient of the antibacterial performance index benchmark parameter of the combination of two control parameter intervals is greater than this value, it is determined that there is a deviation relationship between the two and they are included in the same deviation combination group.

[0056] This step clarifies the rules for constructing deviation combination groups, and its significance lies in establishing an objective and unified standard for determining deviations, ensuring the scientific nature and consistency of deviation combination group division.

[0057] Furthermore, based on the deviation combination groups under different product performance indicators and the degree of overlap of the deviation combination groups, it is determined whether the parameter adjustment combination in the control parameter range combination needs to be identified, specifically including: S131 determines whether there are deviation combination groups under different product performance indicators. If yes, proceed to step S132. If no, the accuracy of the simulation results of the digital twin model cannot be determined at this time. That is, the product performance indicators change with the change of control parameters. Therefore, it is determined that the parameter adjustment combination in the control parameter range combination needs to be identified. The different product performance indicators refer to the key performance indicators of nano antibacterial yoga clothing, including antibacterial rate, tensile strength, breathability, color fastness, etc.

[0058] Assuming the product performance indicators include antibacterial rate and tensile strength, if there is a group of deviation combinations under the antibacterial rate indicator but no group of deviation combinations under the tensile strength indicator, then it is determined as no, and the identification process of the parameter adjustment combination is required.

[0059] This step determines whether there is a discrepancy in the consistency of multiple indicators. Its significance lies in identifying potential systemic verification defects in the digital twin model and ensuring the comprehensiveness of model verification.

[0060] S132 Obtain the number of deviation combination groups under the product performance index, and use the product performance index with the number of deviation combination groups greater than the preset deviation combination group number threshold as the identification and matching performance index of the simulation model. Determine whether the proportion of the identification and matching performance index under the product performance index is greater than the preset matching index proportion threshold. If yes, it is determined that no identification processing of parameter adjustment combination in the control parameter range combination is required. If no, proceed to step S133. The identification and matching performance index refers to the performance index in which the number of deviation combination groups exceeds a preset threshold, indicating that there are many deviation combinations that need attention under this index.

[0061] Assuming there are multiple product performance indicators, a preset threshold for the number of deviation combination groups is a fixed value, and a preset threshold for the proportion of matching indicators is a certain proportion value, if the number of deviation combination groups under some performance indicators is greater than the threshold, then the proportion of these identified matching performance indicators to the total number of performance indicators is calculated to determine whether it is greater than the preset proportion threshold.

[0062] This step assesses the prevalence of the deviation problem. Its significance lies in determining whether the simulation results of the digital twin model can be reliably verified under the current production process, thereby deciding whether parameter adjustment and combination identification processing is required.

[0063] S133 determines the number of deviation combination groups based on the degree of overlap of deviation combination groups under different product performance indicators, and determines whether the number of deviation combination groups is greater than the preset group number threshold. If yes, proceed to step S134; otherwise, determine that the identification processing of parameter adjustment combination in the control parameter range combination needs to be performed. The degree of overlap of the deviation combination groups is measured by counting the number of control parameter interval combinations that appear under different product performance indicators.

[0064] If, under multiple performance indicators, some control parameter range combinations all appear in their respective deviation combination groups, then these combinations are highly overlapping deviation combinations. Count the number of all such highly overlapping deviation combinations and determine whether it exceeds the preset group number threshold.

[0065] This step identifies consistency issues across multiple indicators. Its significance lies in the fact that if the degree of overlap is high, it is impossible to perform verification processing under a large number of control parameter ranges, thus failing to guarantee the comprehensiveness and reliability of the verification process. However, if the degree of overlap is low, the reliability of the verification is high, so it is necessary to proceed to the next step.

[0066] S134 removes the product performance index from the identification matching performance index as other performance indexes. Based on whether the average number of deviation combination groups under different other performance indexes is less than the preset deviation group number threshold, if so, it is determined that the identification processing of parameter adjustment combination in the control parameter range combination is required; otherwise, it is determined that the identification processing of parameter adjustment combination in the control parameter range combination is not required.

[0067] The other performance indicators refer to the remaining performance indicators that were not identified as matching performance indicators. The deviations under these indicators need to be analyzed separately.

[0068] Assuming that some of the multiple performance indicators are identification and matching performance indicators, and the rest are other performance indicators, we analyze the distribution of deviation combination groups under these indicators to determine the reliability of verification under the current production process, and then determine whether the conditions for identification processing are met.

[0069] This step involves supplementing the analysis of non-primary deviation indicators. Its significance lies in the fact that, given the existence of numerous deviation combination groups, if other performance indicators also have numerous deviation combination groups, all performance indicators can be effectively verified, thus eliminating the need for parameter adjustment combination identification.

[0070] This embodiment achieves a systematic evaluation of the reliability of digital twin model simulation results through steps S11 to S134. Its core value is reflected in three aspects: First, it quantifies the performance differences between different combinations of control parameter ranges through deviation coefficients; second, it identifies systematic deviations through the construction and overlap analysis of deviation combination groups; and third, it ensures the necessity and accuracy of parameter adjustment combination identification and processing through multi-level judgment logic.

[0071] The manufacturing process of nano-antibacterial yoga clothing includes four steps: spinning, antibacterial finishing, weaving, and setting. It involves four types of production equipment: spinning equipment, antibacterial finishing equipment, weaving equipment, and setting equipment.

[0072] The production parameters of the spinning equipment are controlled within the following ranges: spinning temperature 250℃ to 280℃ (range 1), 260℃ to 290℃ (range 2), 270℃ to 300℃ (range 3); spinning speed 800m / min to 1000m / min (range A), 1000m / min to 1200m / min (range B); cooling air velocity 0.5m / s to 1.0m / s (range X), 1.0m / s to 1.5m / s (range Y).

[0073] The production parameters of the antibacterial finishing equipment are controlled within the following ranges: antibacterial agent concentration 3% to 5% (range P), 5% to 7% (range Q); finishing temperature 40℃ to 60℃ (range M), 60℃ to 80℃ (range N).

[0074] Under the existing control process, there are a total of 20 possible combinations of control parameter ranges.

[0075] The product performance indicators include four aspects: antibacterial rate, tensile strength, air permeability, and color fastness.

[0076] The quality inspection results of each performance index under various combinations of control parameter ranges were statistically analyzed to determine the benchmark parameters: the benchmark parameters for antibacterial rate of combination 1 (temperature range 1, velocity range A, wind speed range X, concentration range P, temperature range M) are 92%, tensile strength is 45MPa, air permeability is 180mm / s, and color fastness is grade 4; the benchmark parameters for antibacterial rate of combination 2 are 88% and tensile strength is 43MPa; the benchmark parameters for antibacterial rate of combination 3 are 90% and tensile strength is 46MPa; and so on.

[0077] In S11, the deviation coefficient is calculated: Deviation coefficient = |Reference parameter 1 - Reference parameter 2| ÷ ((Reference parameter 1 + Reference parameter 2) ÷ 2); The antibacterial rate deviation coefficient between combination 1 and combination 2 = |92-88| ÷ ((92+88)÷2) = 4÷90 ≈0.044; The tensile strength deviation coefficient between combination 1 and combination 2 = |45-43| ÷ ((45+43)÷2) = 2÷44 ≈0.045; In S12, if the preset deviation coefficient threshold is 0.05, then the control parameter interval combinations with a deviation coefficient greater than 0.05 under the antibacterial rate index are: combination 4 and combination 7 (deviation coefficient 0.062), combination 5 and combination 9 (deviation coefficient 0.058), and combination 12 and combination 15 (deviation coefficient 0.071), forming 3 deviation combination groups: group 1 includes combination 4 and combination 7, group 2 includes combination 5 and combination 9, and group 3 includes combination 12 and combination 15.

[0078] In S131, there are deviation combinations under all four product performance indicators, which are judged as "yes" and proceed to S132.

[0079] In S132, there are 3 deviation combination groups under the antibacterial rate index, 2 under the tensile strength index, 2 under the air permeability index, and 1 under the color fastness index. Assuming a preset threshold for the number of deviation combination groups is 2, and a preset threshold for the matching index ratio is 0.60, then the identified matching performance index is antibacterial rate, which is 1. The ratio is 1 ÷ 4 = 0.25, which is less than 0.60, proceeding to S133.

[0080] In S133, the deviation combinations that appear under different performance indicators are statistically analyzed: combination 4 appears under both antibacterial rate and tensile strength indicators, combination 7 appears under both antibacterial rate and air permeability indicators, and combination 12 appears under both tensile strength and color fastness indicators, totaling 3 highly overlapping deviation combinations. Assuming a preset threshold of 2 groups, if 3 > 2, proceed to S134.

[0081] In S134, excluding the identification and matching performance index (antibacterial rate), the average value of the deviation combination group under other performance indexes is 1.6, which is less than 2. It is judged as "yes" and it is determined that the identification processing of the parameter adjustment combination needs to be performed.

[0082] Specifically, such as Figure 3 As shown, the method for determining the parameter adjustment combination in the control parameter range combination is as follows: In this embodiment, based on the fluctuation of product performance indicators under the control parameter range combination as the control parameters change, the probability and magnitude of fluctuation of product performance indicators when parameter adjustment is performed under the control parameter range combination are determined. Based on the probability and magnitude of fluctuation, the parameter adjustment combination in the control parameter range combination is determined. This not only reduces the risk of adjustment processing in a large number of control parameter range combinations, but also lays the foundation for ensuring the reliability of model verification.

[0083] Specifically, such as Figure 3 As shown, the method for determining the parameter adjustment combination in the control parameter range combination is as follows: In this embodiment, based on the fluctuation of product performance indicators under the control parameter range combination as the control parameters change, the probability and magnitude of fluctuation of product performance indicators when parameter adjustment is performed under the control parameter range combination are determined. Based on the probability and magnitude of fluctuation, the parameter adjustment combination in the control parameter range combination is determined. This not only reduces the risk of adjustment processing in a large number of control parameter range combinations, but also lays the foundation for ensuring the reliability of model verification.

[0084] S21 determines the parameter fluctuation range of the product performance index under the control parameter range combination based on the fluctuation data of the product performance index under the control parameter range combination.

[0085] The parameter fluctuation range refers to the range of actual measured values ​​of a product's performance indicators under a specific combination of control parameter ranges, which is determined by the minimum and maximum values.

[0086] If, under a certain combination of control parameters, antibacterial rate is tested on multiple batches of products and the antibacterial rate is found to be distributed within a certain percentage range, then this range is the parameter fluctuation range of the antibacterial rate.

[0087] This step determines the actual range of variation in product performance indicators. Its significance lies in quantifying the stability of product performance and providing basic data for subsequent fluctuation analysis.

[0088] S22 Based on the parameter fluctuation range, determine the mean of the absolute values ​​of the deviation rates between the endpoint values ​​of the parameter fluctuation range of the product performance index and the benchmark value, and take the mean of the absolute values ​​of the deviation rates between the endpoint values ​​of the parameter fluctuation range of the product performance index and the benchmark value as the fluctuation value of the product performance index.

[0089] The mean of the absolute values ​​of the deviation rates between the endpoint values ​​and the benchmark values ​​refers to the value obtained by taking the absolute values ​​of the deviation rates between the upper and lower limits of the parameter fluctuation range and the benchmark values, and then averaging them.

[0090] Assuming that the fluctuation range of a product's performance index parameter is a certain range and the benchmark value is a certain value, then calculate the absolute value of the upper limit deviation rate and the absolute value of the lower limit deviation rate, and then calculate the average value as the fluctuation value.

[0091] This step quantifies the average deviation of product performance indicators from the benchmark value. Its significance lies in comprehensively reflecting the fluctuation range of product performance, which facilitates comparative analysis between different indicators.

[0092] S23 determines whether the combination of control parameter ranges is a parameter adjustment combination based on the fluctuation values ​​of different product performance indicators and the proportion of products whose product performance indicators are not under the basic parameters.

[0093] The proportion of products whose performance indicators are not below the baseline parameters refers to the proportion of the number of products whose actual product performance parameter values ​​are not within the baseline parameter range to the total number of products.

[0094] Suppose that multiple batches of products are produced under a certain combination of control parameters, the proportion of products whose antibacterial rate is not within the baseline parameter range is the percentage of products whose antibacterial rate is not under the basic parameters.

[0095] This step combines two dimensions—fluctuation value and product ratio—to determine whether parameter adjustments are needed. Its significance lies in comprehensively evaluating the stability and consistency of the combination of control parameter ranges, avoiding one-sided judgments based on a single indicator.

[0096] In the above steps, based on the proportion of products whose product performance indicators are not under the basic parameters, if there are no product performance indicators whose proportion is greater than the preset product proportion threshold, then the changes in the product performance indicators in the control parameter range combination are small. Therefore, it is determined that the control parameter range combination does not belong to the parameter adjustment combination.

[0097] The preset product ratio threshold refers to the critical ratio value used to determine whether there is a significant deviation in the product performance indicators.

[0098] Assuming the preset product ratio threshold is a certain ratio value, when the product ratios of all product performance indicators that are not under the basic parameters are all less than or equal to this threshold, it is determined that there is no significant deviation.

[0099] This step serves as a preliminary screening mechanism, its significance being to quickly eliminate combinations of control parameter ranges that ensure stable product performance, thereby reducing the computational workload of subsequent analysis.

[0100] Additionally, it is understandable that if there are product performance indicators where the proportion of a product exceeds the preset product proportion threshold, the following content will be included.

[0101] S231 determines whether the average value of the product proportions of different product performance indicators not under the basic parameters is less than the preset value of the product proportion. If yes, it determines that the combination of control parameter intervals does not belong to the parameter adjustment combination. If no, it proceeds to step S232.

[0102] The product ratio preset value refers to the critical value for judging the overall product ratio level, and is used to assess the degree of deviation of multiple indicators.

[0103] Suppose there are multiple product performance indicators, and the proportion of products for each indicator that is not under the basic parameters are different values. Calculate the average value and compare it with the preset value of the product proportion.

[0104] This step assesses the product ratio level from a comprehensive perspective. Its significance lies in identifying situations where individual indicators may deviate but the overall level is controllable. In such cases, no adjustments are necessary, ensuring stable production.

[0105] S232 determines whether the fluctuation values ​​of different product performance indicators are all greater than the preset fluctuation threshold. If so, it is determined that the combination of control parameter ranges belongs to the parameter adjustment combination. If not, proceed to step S233.

[0106] The preset fluctuation threshold refers to the critical value used to determine whether the fluctuation of product performance indicators is significant.

[0107] Assuming that the fluctuation values ​​of each product's performance indicators are calculated differently, if the fluctuation values ​​of all indicators are greater than the preset fluctuation threshold, then the combination of control parameter ranges is determined to be a parameter adjustment combination.

[0108] This step, judging from the perspective of fluctuation range, is significant in identifying combinations of control parameter ranges with drastic fluctuations in product performance. These combinations usually require priority parameter adjustment.

[0109] S233 determines the fluctuation matching value of the product performance index based on the fluctuation values ​​of different product performance indicators and the proportion of products not under the basic parameters, and determines whether the number of product performance indicators with fluctuation matching values ​​greater than the preset matching threshold meets the requirements. If yes, it is determined that the control parameter range combination belongs to the parameter adjustment combination; otherwise, it is determined that the control parameter range combination does not belong to the parameter adjustment combination.

[0110] The fluctuation matching value refers to the comprehensive fluctuation index calculated by combining the comprehensive fluctuation value and the proportion of products not under the basic parameters. It is used to measure the overall severity of fluctuations in product performance indicators.

[0111] If the fluctuation value of a product's performance indicator is a certain value, and the proportion of products not under the basic parameters is a certain proportion, then the fluctuation matching value is the product of the two.

[0112] This step makes a final judgment using comprehensive indicators. Its significance lies in taking into account both the fluctuation range and the deviation ratio, ensuring the accuracy and comprehensiveness of the parameter adjustment combination identification.

[0113] This embodiment achieves accurate identification of whether a combination of control parameter ranges needs parameter adjustment through steps S21 to S233. Its core value is reflected in three aspects: First, it quantifies the degree of product performance fluctuation through parameter fluctuation ranges and fluctuation values; second, it gradually filters out the control parameter range combinations that truly need adjustment through multi-level judgment logic; and third, it ensures the accuracy and reliability of the identification results through comprehensive evaluation of fluctuation matching values.

[0114] Suppose that the identification process for parameter adjustment combinations is determined in S1. After analysis, the candidate control parameter range combinations are determined to be 20 combinations from combination 1 to combination 12.

[0115] The product performance indicators include four aspects: antibacterial rate, tensile strength, air permeability, and color fastness.

[0116] In S21, the parameter fluctuation range of product performance indicators for each combination is statistically analyzed: Combination 1: Antibacterial rate 88% to 94%, tensile strength 42MPa to 48MPa, air permeability 170mm / s to 190mm / s, color fastness grade 3.5 to 4.5.

[0117] In S22, the volatility values ​​of each indicator for each combination are calculated: Fluctuation value = (|upper limit deviation rate| + |lower limit deviation rate|) ÷ 2; Taking combination 1 as an example, the baseline parameters are: antibacterial rate 91%, tensile strength 45MPa, air permeability 180mm / s, color fastness grade 4.0. The antibacterial rate of combination 1 is: upper limit deviation rate = (94-91)÷91=0.033, lower limit deviation rate = (88-91)÷91=-0.033, and fluctuation value = 0.033.

[0118] And so on, calculate the volatility value for all combinations.

[0119] In S23, the proportion of products whose performance indicators are not below the baseline parameters under each combination is calculated: Combination 5: Antibacterial rate 40%, tensile strength 35%, air permeability 30%, color fastness 28%.

[0120] If the preset product ratio threshold is set to 0.10, then combination 5 (multiple indicators) has a value greater than the threshold, and proceeds to the next step of the judgment.

[0121] In S231, calculate the average value: The average value of combination 5 = (40 + 35 + 30 + 28) ÷ 4 = 33.25% > 10%, proceed to S232.

[0122] In S232, the preset fluctuation threshold is set to 0.08: Combination 5: Assuming the antibacterial rate fluctuation value is 0.065 < 0.08, it does not meet the requirement of "all greater than", so proceed to S233.

[0123] In S233, the volatility matching value is calculated (Volatility matching value = Volatility value × Proportion of products not under the benchmark parameters): Combination 5: Antibacterial rate 0.065×0.40=0.026, tensile strength 0.092×0.35=0.032, air permeability 0.078×0.30=0.023, color fastness 0.095×0.28=0.027. Assuming a preset matching threshold of 0.028, and requiring two values, combination 5 has two values ​​(tensile strength 0.032 and color fastness 0.027 are not met, but it is assumed that tensile strength and the other indicator are met). Since the requirements are met, it is determined to be a parameter adjustment combination.

[0124] There are a total of 10 final parameter adjustment combinations: combination 5, combination 7, combination 10, combination 13, combination 15, combination 17, combination 19, and the assumption that combination 8, combination 11, and combination 14 also satisfy the conditions.

[0125] S2 determines the parameter adjustment strategy under the parameter adjustment combination based on the degree of parameter deviation between the parameter adjustment combination and other parameter adjustment combinations, and in combination with the correlation between the fluctuation type of different product performance indicators in the parameter adjustment combination and other parameter adjustment combinations. Furthermore, the method for determining the parameter adjustment strategy under the parameter adjustment combination is as follows: In this embodiment, based on the adjacency of the endpoints of the parameter adjustment combination with other parameter adjustment combinations and the similarity of the product performance indicators with more drastic fluctuations with other parameter adjustment combinations, the requirement for parameter adjustment processing under the parameter adjustment combination is determined, that is, the requirement for verification processing of the digital twin model. The parameter adjustment strategy is determined by using the requirement for parameter adjustment processing under the parameter integration combination, which not only reduces the risk of parameter adjustment processing, but also provides data support for the verification of the digital twin model.

[0126] S31 determines the absolute value of the deviation between the control range of the production parameters in different production equipment and the endpoints of the control range of the other parameter adjustment combinations based on the degree of parameter deviation between the parameter adjustment combination and other parameter adjustment combinations, and determines the associated production parameters between the parameter adjustment combination and other parameter adjustment combinations based on the absolute value of the deviation.

[0127] The absolute value of the deviation at the endpoints refers to the absolute value of the difference between the upper or lower limit of the control range of the same production parameter when the two parameters are adjusted together.

[0128] Assuming the spinning temperature range of parameter adjustment combination 5 is 270℃ to 280℃ and the spinning temperature range of parameter adjustment combination 7 is 260℃ to 290℃, then the absolute value of the endpoint deviation is the minimum of |270-260|=10 and |280-290|=10.

[0129] This step quantifies the degree of parameter similarity between parameter adjustment combinations. Its significance lies in identifying production parameters with similar control ranges among parameter adjustment combinations, providing basic data for subsequent correlation analysis.

[0130] It is understood that the associated production parameter is a production parameter whose absolute value of the deviation from the adjustment combination with other parameters is less than a preset deviation value.

[0131] The preset deviation value refers to the critical value used to determine whether the adjustment combination of two parameters constitutes a correlation with a certain production parameter.

[0132] Assuming the preset value of the deviation is a certain temperature value, when the absolute value of the deviation at the endpoint of the spinning temperature range of the two parameter adjustment combinations is less than this value, the spinning temperature is determined to be a related production parameter.

[0133] This step clarifies the criteria for determining related production parameters. Its significance lies in establishing objective rules for judging correlation, ensuring the accuracy and consistency of identifying related production parameters.

[0134] Specifically, the above steps include the following.

[0135] S311 Determine whether there are other parameter adjustment combinations with related production parameters in the parameter adjustment combination. If yes, proceed to step S312. If no, the digital twin model cannot be continuously verified under the parameter adjustment combination. Therefore, the parameter adjustment strategy under the parameter adjustment combination is determined as the basic adjustment strategy.

[0136] The basic adjustment strategy refers to a conservative strategy that uses a preset step size to adjust parameters, and is suitable for isolated parameter adjustment combinations.

[0137] If the absolute value of the endpoint deviation of a certain parameter adjustment combination from all other parameter adjustment combinations is greater than the preset value of the deviation, then it is determined that there are no related parameter adjustment combinations, and the basic adjustment strategy is adopted.

[0138] This step determines whether the parameter adjustment combinations are related. Its significance lies in identifying isolated parameter adjustment combinations, which cannot continuously verify the digital twin model. Therefore, its verification processing requirements for the digital twin model are relatively low.

[0139] It should be noted that the basic adjustment strategy involves adjusting the production parameters within the control range of the parameter adjustment combination according to a preset step size.

[0140] The preset step size refers to the reference step size for parameter adjustment, which is determined based on the characteristics of the production parameters and process requirements.

[0141] Assuming the preset step size is a fixed value, the basic adjustment strategy will gradually adjust the production parameters within the control range according to this step size.

[0142] This step clarifies the execution method of the basic adjustment strategy. Its significance lies in providing a standardized adjustment method for isolated parameter adjustment combinations, ensuring the standardization and controllability of the adjustment.

[0143] S312 determines whether the maximum value of the number of associated production parameters between the parameter adjustment combination and other parameter adjustment combinations is greater than the preset production parameter number threshold. If yes, the parameter adjustment strategy under the parameter adjustment combination is determined to be an aggressive adjustment strategy. If no, proceed to step S32.

[0144] The aggressive adjustment strategy refers to an aggressive strategy that uses a large step size to adjust parameters, and is suitable for situations with multiple related parameter adjustment combinations.

[0145] If a certain parameter adjustment combination has related production parameters with multiple other parameter adjustment combinations, and the maximum number of related production parameters is greater than a preset threshold, then an aggressive adjustment strategy is adopted.

[0146] This step determines the aggressiveness of the adjustment strategy based on the degree of correlation. Its significance lies in making full use of the correlation between parameter adjustment combinations to achieve continuous verification of the digital twin model within multiple parameter ranges. By reducing the step size of parameter adjustment, the reliability and comprehensiveness of the verification process are guaranteed.

[0147] It should be noted that the basic adjustment strategy is to adjust the production parameters within the control range of the parameter adjustment combination according to the second preset step size, wherein the second preset step size is smaller than the preset step size.

[0148] The second preset step size refers to an adjustment range smaller than the preset step size, which is used for more precise parameter adjustment scenarios.

[0149] If the second preset step size is a certain percentage of the preset step size, then the basic adjustment strategy will be adjusted according to that step size.

[0150] This step distinguishes the step size settings for different basic adjustment strategies. Its significance lies in flexibly selecting the adjustment precision according to specific circumstances, balancing adjustment efficiency and adjustment precision.

[0151] S32 determines the product performance index with severe fluctuation type in the parameter adjustment combination by the fluctuation type of different product performance indicators in the parameter adjustment combination, and uses it as the matching fluctuation performance index. Based on the correlation between the matching fluctuation performance index and other parameter adjustment combinations, it determines that the matching performance index belongs to the parameter adjustment combination of the matching fluctuation performance index, and uses it as the associated adjustment combination.

[0152] The severe fluctuation type refers to the fluctuation type where the product performance index fluctuates beyond the preset fluctuation threshold, indicating that the performance index is highly sensitive to parameter changes.

[0153] If the fluctuation matching value of a certain product performance indicator is greater than a preset threshold, it is determined to be a severe fluctuation type and is used as the matching fluctuation performance indicator.

[0154] This step identifies performance metrics that are sensitive to parameter changes. Its significance lies in focusing on changes in these metrics to ensure that parameter adjustments do not cause drastic fluctuations in performance metrics.

[0155] In the above steps, the fluctuation type is determined based on the fluctuation matching value of the product performance index, specifically including severe fluctuation type and general fluctuation type.

[0156] The volatility matching value refers to a quantitative indicator of volatility calculated by combining the volatility value and the product ratio.

[0157] If the fluctuation matching value is greater than a certain threshold, it is determined to be a severe fluctuation type; if it is less than the threshold, it is determined to be a normal fluctuation type.

[0158] This step establishes criteria for determining the type of fluctuation, which is significant for classifying and managing product performance indicators and adopting different handling strategies for different types of fluctuations.

[0159] In the above steps, it is determined whether there is a matching volatility performance index under the parameter adjustment combination that does not have a related adjustment combination other than the parameter adjustment combination. If so, the parameter adjustment strategy under the parameter adjustment combination is determined to be an aggressive adjustment strategy. If not, proceed to step S33.

[0160] The matching volatility performance index that does not have an associated adjustment combination refers to a situation where the performance index is of the severe volatility type, but no similar volatility characteristics appear in other parameter adjustment combinations.

[0161] If a matching volatility performance index exists in a certain parameter adjustment combination, and this index does not belong to the matching volatility performance index in other parameter adjustment combinations, then it is determined to be true, and an aggressive adjustment strategy is adopted. This step identifies unique severe volatility indicators. Its significance lies in taking active adjustment strategies for these special indicators to fully explore their parameter characteristics and ensure the comprehensiveness and reliability of the verification process of the digital twin model.

[0162] S33 determines the parameter adjustment strategy under the parameter adjustment combination based on the deviation of the parameter adjustment combination from other parameter adjustment combinations and the associated adjustment combination in different matching fluctuation performance indicators.

[0163] The deviation production parameter refers to the production parameter where the absolute value of the endpoint deviation between the two parameter adjustment combinations is greater than the preset deviation value.

[0164] If a certain production parameter has a significantly different control range between two parameter adjustment combinations, it is determined to be a deviation production parameter.

[0165] This step takes into account the correlation between parameter deviation and fluctuation. Its significance lies in comprehensively evaluating the characteristics and correlations of the parameter adjustment combination, providing complete information for the final strategy determination.

[0166] Furthermore, based on the number of associated adjustment combinations in the matched volatility performance index, the matching weight value between the matched volatility performance index and the parameter adjustment combination is determined. It is then determined whether the sum of the matching weight values ​​of the matched volatility performance index under the parameter adjustment combination is greater than a preset weight threshold. If so, the parameter adjustment strategy under the parameter adjustment combination is determined to be an aggressive adjustment strategy; otherwise, the parameter adjustment strategy under the parameter adjustment combination is determined to be a lenient adjustment strategy.

[0167] The matching weight value refers to the weight coefficient calculated based on the number of associated adjustment combinations, reflecting the correlation strength between the matching volatility performance index and the parameter adjustment combinations.

[0168] If a certain matching volatility performance index appears in multiple related adjustment combinations, its matching weight value is low, which means that it matches the current parameter adjustment combination to a high degree, and its verification requirement is high.

[0169] This step determines the final strategy through weight calculation. Its significance lies in quantitatively evaluating the volatility correlation characteristics of the parameter adjustment combination, thereby achieving objectivity and precision in strategy selection.

[0170] It is understood that the loose adjustment strategy is to adjust the production parameters within the control range of the parameter adjustment combination according to the third preset step size, wherein the third preset step size is less than the preset step size and greater than the second preset step size.

[0171] The third preset step size refers to the adjustment range between the preset step size and the second preset step size.

[0172] If the third preset step size is a certain proportion of the preset step size, and this proportion is greater than the proportion of the second preset step size to the preset step size, then the easing adjustment strategy will adjust according to this step size.

[0173] This step clarifies the step size setting of the lenient adjustment strategy, which is significant in providing a moderate adjustment strategy for parameter adjustment combinations with a moderate degree of correlation, balancing adjustment efficiency and risk control.

[0174] This embodiment, through steps S31 to S33, achieves a comprehensive analysis of the characteristics of parameter adjustment combinations and precise determination of adjustment strategies. Its core value is reflected in three aspects: First, it establishes a network of relationships between parameter adjustment combinations by identifying associated production parameters; second, it identifies performance indicators sensitive to parameter changes by analyzing fluctuation types; and third, it achieves personalized customization of adjustment strategies through multi-dimensional judgment, thereby improving the pertinence and effectiveness of parameter adjustment.

[0175] Suppose that 10 parameter adjustment combinations are determined in S2: combination 5, combination 7, combination 10, combination 13, combination 15, combination 17, combination 19, combination 8, combination 11, and combination 14.

[0176] The production parameters involved in each combination include: spinning temperature, spinning speed, cooling air velocity, antibacterial agent concentration, and finishing temperature.

[0177] In S31, calculate the absolute value of the endpoint deviation between each combination and other combinations: Taking combination 5 as an example, its control range is as follows: spinning temperature 250℃ to 260℃, spinning speed 900m / min to 1000m / min, cooling wind speed 0.8m / s to 1.2m / s, antibacterial agent concentration 4% to 6%, and finishing temperature 50℃ to 60℃.

[0178] The control range of combination 7 is as follows: spinning temperature 255℃ to 265℃, spinning speed 950m / min to 1050m / min, cooling air velocity 1.0m / s to 1.4m / s, antibacterial agent concentration 5% to 7%, and finishing temperature 55℃ to 65℃.

[0179] Calculate the absolute values ​​of the endpoint deviations: Spinning temperature: |250-255|=5, |260-265|=5; Spinning speed: |900-950|=50, |1000-1050|=50; Cooling air velocity: |0.8-1.0|=0.2, |1.2-1.4|=0.2; Antibacterial agent concentration: |4-5|=1, |6-7|=1; Finishing temperature: |50-55|=5, |60-65|=5; The preset deviation values ​​are: spinning temperature 10℃, spinning speed 100m / min, cooling wind speed 0.3m / s, antibacterial agent concentration 2%, and finishing temperature 10℃.

[0180] The associated production parameters for combination 5 and combination 7 are: spinning temperature, spinning speed, cooling wind speed, antibacterial agent concentration, and finishing temperature (all 5 parameters are satisfied).

[0181] After comprehensive analysis, the correlation between the parameter adjustment combinations is as follows: Combination 5 is related to Combination 7 and Combination 10 (the number of related production parameters is 5 and 3 respectively).

[0182] In S311, all 10 parameter adjustment combinations have other parameter adjustment combinations with related production parameters, which is determined as "yes", and proceeds to S312.

[0183] In S312, the preset production parameter quantity threshold is set to 4: The maximum number of associated production parameters for combination 5 is 5 (with combination 7) > 4, therefore the parameter adjustment strategy is determined to be an aggressive adjustment strategy. The maximum number of associated production parameters for combination 7 is 5 (with combination 5) > 4, therefore the parameter adjustment strategy is determined to be an aggressive adjustment strategy. The maximum number of associated production parameters for combination 10 is 4 (with combination 13) = 4, which is not greater than 4, so proceed to S32.

[0184] In S32, the threshold value for the fluctuation matching value of the severe fluctuation type is set to 0.030: The fluctuation matching values ​​for combination 10 are: antibacterial rate 0.028, tensile strength 0.035, air permeability 0.032, and color fastness 0.025. Therefore, the tensile strength and air permeability are of the severe fluctuation type (matching fluctuation performance indicators).

[0185] Analysis of the associated adjustment combinations of the matching fluctuation performance indicators: The tensile strength of combination 10 also belongs to the severe fluctuation type in combinations 5 and 13, and there is an associated adjustment combination. There are no matching fluctuation performance indicators without associated adjustment combinations for any parameter adjustment combination, so it is judged as "No", proceed to S33.

[0186] In S33, the matching weight value is calculated (matching weight value = 1 - number of association adjustment combinations ÷ total number of association parameter adjustment combinations): Matching fluctuation performance indicators for combination 10: tensile strength (related to 2 adjustment combinations), air permeability (related to 1 adjustment combination). The total number of related parameter adjustment combinations is 2 (combination 5, combination 13). Tensile strength matching weight value = 2 ÷ 2 = 0, air permeability matching weight value = 1 - 1 ÷ 2 = 0.5. Sum of matching weight values ​​= 0.5 = 0.5.

[0187] Assuming the preset weight threshold is 1, and the 0.5 of combination 10 is less than 1 and not greater than 1, the parameter adjustment strategy is determined to be a lenient adjustment strategy.

[0188] The final strategy for adjusting the 10 parameters was determined as follows: Aggressive adjustment strategy: Combinations 5, 7, 13, 15, 8, 11, 17, and 19 (8 combinations). Relaxed adjustment strategy: Combinations 10 and 14 (2 combinations).

[0189] The preset step sizes are: 2℃ (temperature), 50m / min (velocity), 0.2m / s (wind speed), 1% (concentration), and 5℃ (finishing temperature). The second preset step size is: 1℃, 25m / min, 0.1m / s, 0.5%, and 2.5℃. The third preset step size is: 1.5℃, 37.5m / min, 0.15m / s, 0.75%, and 3.75℃.

[0190] S3 uses the parameter adjustment strategy to adjust the production parameters under the parameter adjustment combination to obtain the adjustment result. Then, using the similarity between the adjustment result and the simulation result of the digital twin model, as well as the distribution data of product performance indicators that do not meet the similarity requirements, S3 determines the parameter adjustment management method when there are abnormalities in the production parameters under different combinations of control parameter ranges.

[0191] The adjustment results refer to the actual production data and product performance indicators obtained after adjusting the production parameters according to the parameter adjustment strategy.

[0192] Assuming that parameter adjustment combination 5 is adjusted using an aggressive adjustment strategy, the adjusted product performance index data is obtained as the result of the adjustment process.

[0193] This step translates the strategy into actual adjustment actions, and its significance lies in verifying the effectiveness of the parameter adjustment strategy and obtaining data on the actual adjustment effects.

[0194] Furthermore, the method for determining the parameter adjustment management method when the production parameters are abnormal is as follows: In this embodiment, the reliability of the simulation results of the current digital twin model is determined based on the consistency between the production indicators in the combination of production parameter adjustments and the digital twin model. Based on the reliability of the simulation results and the similarity between the production indicators with consistency deviations under the control parameter interval combinations and other control parameter interval combinations, a parameter adjustment management method is implemented for production parameters when there are anomalies under different control parameter interval combinations. This ensures production stability while further guaranteeing the comprehensiveness and reliability of the verification process of the digital twin model.

[0195] S41 uses the adjustment processing result to construct the interval combination of the adjustment range corresponding to different production parameters under the control parameter interval combination, and uses it as the adjustment parameter combination.

[0196] The aforementioned combination of adjustment parameters refers to the multidimensional parameter space formed by the adjustment range of each production parameter under a specific combination of control parameter ranges.

[0197] Assuming that parameter adjustment combination 5 involves three production parameters—spinning temperature, spinning speed, and antibacterial agent concentration—and each parameter has multiple adjustment ranges, then the adjustment parameter combination is the Cartesian product of these adjustment ranges.

[0198] This step constructs the search space for parameter adjustment, which is significant because it comprehensively covers possible parameter adjustment schemes and provides a complete candidate set for finding the optimal adjustment parameters.

[0199] S42, based on the combination of control parameters, adjusts the similarity between the product performance indicators and the digital twin model under the parameter combination, and takes the adjustment parameter combination that meets the requirements for the similarity of different product performance indicators as a consistent combination.

[0200] The degree of similarity refers to the closeness between the adjusted processing result and the simulation result of the digital twin model, which is measured by indicators such as the deviation rate.

[0201] If the deviation rate between the actual and simulated values ​​of each product performance index under a certain combination of adjustment parameters is less than a preset threshold, then the combination is determined to be a consistent combination.

[0202] This step identifies parameter combinations that are highly consistent with the digital twin model. Its significance lies in verifying the accuracy of the digital twin model and determining a reliable parameter adjustment scheme.

[0203] S43 uses consistent combination data under different combinations of control parameter ranges and product performance indicators whose similarity does not meet the requirements under different combinations of adjustment parameters to determine the parameter adjustment management method when the production parameters are abnormal under the control parameter range combination.

[0204] The product performance indicators that do not meet the similarity requirements refer to performance indicators whose deviation rate between the actual value and the simulated value is greater than a preset threshold.

[0205] If the deviation rate between the actual and simulated antibacterial rate under a certain combination of adjustment parameters is greater than a preset threshold, then the antibacterial rate is determined to be an indicator that does not meet the requirements for similarity.

[0206] This step analyzes the reasons and distribution patterns of model inconsistencies. Its significance lies in formulating targeted anomaly handling strategies based on model validation results, thereby improving the validation reliability of digital twin models when production parameters are abnormal.

[0207] Specifically, if the deviation rate between the product performance index under the adjusted parameter combination and the simulation result of the digital twin model is less than the preset deviation rate, then the similarity of the product performance index is determined to meet the requirements.

[0208] The preset deviation rate refers to the critical deviation rate used to determine whether the actual value and the simulated value are consistent. Assuming the preset deviation rate is 5%, a similarity is considered to be satisfied when the deviation rate is less than 5%.

[0209] This step clarifies the criteria for determining the degree of similarity, and its significance lies in establishing objective model verification rules to ensure the consistency and comparability of verification results.

[0210] It should be noted that the abnormality of the production parameters refers to the adjustment range corresponding to the production parameters that are not within the combination of the control parameter ranges.

[0211] The adjustment range corresponding to the production parameter refers to the allowable adjustment range of the production parameter under a specific combination of control parameter ranges.

[0212] For example, assuming the spinning temperature is adjusted from 250°C to 260°C in parameter adjustment combination 5, when the actual spinning temperature is 245°C, it is determined that there is an abnormality in the production parameters.

[0213] This step clarifies the definition of abnormal production parameters, and its significance lies in accurately identifying abnormal production parameters that require intervention, thus avoiding misjudgment and omission.

[0214] It is understandable that, by utilizing consistent combination data under different combinations of control parameter ranges and product performance indicators whose similarity does not meet requirements under different combinations of adjustment parameters, a parameter adjustment management method under the aforementioned control parameter range combinations is determined, specifically including: The simulation matching factor under the control parameter range combination is determined based on the proportion of the consistent combination under all adjustment parameter combinations.

[0215] The simulated matching factor refers to the proportion of consistent combinations to the total number of combinations of adjustment parameters, reflecting the overall accuracy of the digital twin model under the combination of control parameters.

[0216] Suppose there are multiple combinations of adjustment parameters under a certain range of control parameters, some of which are consistent combinations. Then the simulation matching factor is the number of consistent combinations divided by the total number of adjustment parameter combinations.

[0217] This step quantifies the overall validation effect of the digital twin model, and its significance lies in providing a quantitative basis for decision-making in the selection of subsequent management methods.

[0218] Scenario 1: If the adjustment parameter combinations under different control parameter range combinations are all consistent combinations, then the consistency is relatively high. Therefore, the parameter adjustment management method is determined to be that adjustment is only required when the duration of abnormal production parameters exceeds the first duration, regardless of the control parameter range combination, thereby further verifying the consistency of the digital twin model.

[0219] The first duration refers to the time threshold for determining whether abnormal production parameters require immediate intervention.

[0220] For example, assuming the first duration is 30 minutes, adjustments will only be made when the abnormal production parameters last for more than 30 minutes.

[0221] This step is suitable when the model validation results are excellent. Its significance lies in making full use of the model's high accuracy, reducing unnecessary frequent adjustments, and further validating the model's comprehensiveness by delaying adjustments.

[0222] Scenario 2: If the adjustment parameter combinations under different control parameter range combinations are all consistent combinations, and if there is a control parameter range combination where the simulation matching factor is not greater than the preset matching factor threshold, then the parameter adjustment management method is determined to be that if there is an abnormality in the production parameters under any control parameter range combination, adjustment processing is required.

[0223] The preset matching factor threshold refers to the critical value used to determine whether the simulated matching factor meets the standard.

[0224] For example, assuming the preset matching factor threshold is 0.80, when the simulated matching factor of a certain control parameter range combination is less than or equal to 0.80, the determination of this situation is triggered.

[0225] This step is applicable when the model validation results are partially insufficient. In this case, the model has a certain degree of validation bias, and there is no need to perform further validation processing outside the parameter requirement range. Its value is small. Therefore, a more cautious management strategy should be adopted for all combinations of control parameter ranges to ensure production stability.

[0226] Scenario 3: If there is no control parameter interval combination where the simulated matching factor is not greater than the preset matching factor threshold, the product performance indicators whose similarity does not meet the requirements under different adjustment parameter combinations are used to determine the adjustment parameter combinations where the similarity of the product performance indicators does not meet the requirements, and these are used as associated deviation parameter combinations. The deviation weight value of the product performance indicator is determined by the number of control parameter interval combinations in which the associated deviation parameter combinations of the product performance indicators are located. If there are associated deviation parameter combinations of product performance indicators with a deviation weight value greater than the preset weight threshold under the control parameter interval combination, then the parameter adjustment management method is determined to require adjustment only when the duration of abnormal production parameters under the control parameter interval combination exceeds the first duration.

[0227] The aforementioned correlation deviation parameter combination refers to the combination of adjustment parameters for product performance indicators where the similarity does not meet the requirements.

[0228] If the similarity of the antibacterial rate does not meet the requirements under a certain combination of adjustment parameters, then this combination is the correlation deviation parameter combination of the antibacterial rate.

[0229] This step is applicable when the model has systematic deviations in specific performance indicators. Its significance lies in identifying the weak links in the model. If, under the combination of control parameter intervals, there are performance indicators with associated deviation parameter combinations under a very small number of control parameter interval combinations, in order to ensure the reliability of the digital twin model verification, a delayed adjustment strategy is adopted on the basis of a certain degree of verification matching of the digital twin model, so as to provide more data for model verification and further update processing of the model.

[0230] Scenario 4: If there is no associated deviation parameter combination of product performance indicators with a deviation weight value greater than the preset weight threshold under the control parameter interval combination, the verification requirement weight value of the control parameter interval combination is determined by the sum of the deviation weight values ​​of the product performance indicators belonging to the associated deviation parameter combination under the control parameter interval combination. It is then determined whether the verification requirement weight value of the control parameter interval combination is greater than the preset weight threshold. If so, the parameter adjustment management method is determined to require adjustment only when the duration of abnormal production parameters under the control parameter interval combination exceeds the first duration. If not, the parameter adjustment management method is determined to require adjustment only when there are no abnormal production parameters within the most recent preset duration under the control parameter interval combination, and the duration of abnormal production parameters exceeds the first duration.

[0231] The verification requirement weight value refers to the sum of the deviation weight values ​​of all product performance indicators under a certain combination of control parameter ranges, reflecting the overall model verification requirement of the combination.

[0232] Suppose that under a certain combination of control parameters, there are multiple product performance indicators with associated deviation parameter combinations, and each indicator has a corresponding deviation weight value, then the verification requirement weight value is the sum of these weight values.

[0233] This step is applicable when there are no production indicators that do not meet the consistency requirements only in a very few control parameter ranges. In this case, in order to screen control parameter ranges with a high degree of verification requirements, we combine multiple product performance indicators with related deviation parameters under the control parameter range combination. Each indicator has a corresponding deviation weight value. Its significance is that, according to the degree of verification requirements, we can flexibly select management strategies under different control parameter range combinations to balance production stability and model verification requirements.

[0234] This embodiment, through the analysis of S41 to S43 and four scenarios, achieves accurate determination of management methods when production parameters are abnormal. Its core value is reflected in four aspects: First, it fully verifies the digital twin model by adjusting parameter combinations and constructing consistent combinations; second, it quantifies the model verification effect by simulating matching factors; third, it achieves differentiated customization of management methods through the classification and processing of four scenarios; and fourth, it ensures the comprehensiveness and reliability of model verification while guaranteeing production stability.

[0235] Suppose that 10 parameter adjustment combinations and their strategies are determined in S3: Aggressive adjustment strategies: Combination 5, Combination 7, Combination 13, Combination 15, Combination 8, Combination 11, Combination 17, Combination 19. Relaxed adjustment strategies: Combination 10, Combination 14.

[0236] In S41, taking combination 5 as an example, the following parameter combinations are constructed: Spinning temperature adjustment range: 250℃ to 260℃ (step size 2℃, 6 adjustment points: 250, 252, 254, 256, 258, 260℃). Spinning speed adjustment range: 900m / min to 1000m / min (step size 50m / min, 3 adjustment points: 900, 950, 1000℃). Antibacterial agent concentration adjustment range: 4% to 6% (step size 1%, 3 adjustment points: 4, 5, 6℃). Total number of parameter combinations = 6 × 3 × 3 = 54.

[0237] In S42, the preset deviation rate is 5%. After testing, among the 54 combinations of adjustment parameters in combination 5, the actual values ​​of the four performance indicators of antibacterial rate, tensile strength, air permeability and color fastness are all less than 5% in 45 combinations. Therefore, there are 45 consistent combinations.

[0238] Similarly, the number of consistent combinations for other combinations is as follows: Combination 7: 48 combinations of adjustment parameters, 40 consistent combinations. Combination 13: 42 combinations of adjustment parameters, 35 consistent combinations. Combination 15: 50 combinations of adjustment parameters, 42 consistent combinations. Combination 8: 46 combinations of adjustment parameters, 38 consistent combinations. Combination 11: 44 combinations of adjustment parameters, 36 consistent combinations. Combination 17: 40 combinations of adjustment parameters, 30 consistent combinations. Combination 19: 38 combinations of adjustment parameters, 28 consistent combinations. Combination 10 (relaxed strategy): 36 combinations of adjustment parameters, 32 consistent combinations. Combination 14 (relaxed strategy): 34 combinations of adjustment parameters, 29 consistent combinations.

[0239] In S43, calculate the simulated matching factor for each combination: Combination 5: 45 ÷ 54 = 0.833. Combination 7: 40 ÷ 48 = 0.833. Combination 13: 35 ÷ 42 = 0.833. Combination 15: 42 ÷ 50 = 0.840. Combination 8: 38 ÷ 46 = 0.826. Combination 11: 36 ÷ 44 = 0.818. Combination 17: 30 ÷ 40 = 0.750. Combination 19: 28 ÷ 38 = 0.737. Combination 10: 32 ÷ 36 = 0.889. Combination 14: 29 ÷ 34 = 0.853.

[0240] Set the preset matching factor threshold to 0.85.

[0241] Judgment: Not all combinations of adjusted parameters are consistent combinations (there are inconsistent combinations among all combinations), so condition 1 is not met. There are combinations with a simulation matching factor not greater than 0.85: combination 8 (0.826), combination 11 (0.818), combination 17 (0.750), and combination 19 (0.737), which meet the condition of condition 2.

[0242] The parameter adjustment management method is as follows: regardless of any combination of control parameter ranges, if there are abnormalities in the production parameters, adjustments must be made to ensure the stability and reliability of production.

[0243] If we assume that the matching factor for all combinations is greater than 0.85, then we proceed to case 3.

[0244] Example of Case 3 (hypothetical scenario): Suppose that the simulated matching factor of combination 17 is 0.90>0.85, and analyze the 10 combinations of adjustment parameters that do not meet the similarity requirements: antibacterial rate does not meet the requirements in 6 combinations, tensile strength does not meet the requirements in 4 combinations, air permeability does not meet the requirements in 3 combinations, and color fastness does not meet the requirements in 2 combinations.

[0245] Determine the associated deviation parameter combinations for each product performance index: Antibacterial rate: 6 adjustment parameter combinations. Tensile strength: 4 adjustment parameter combinations. Air permeability: 3 adjustment parameter combinations. Color fastness: 2 adjustment parameter combinations.

[0246] The number of control parameter interval combinations in which the associated deviation parameter combinations of each product performance index fall was statistically analyzed: The associated deviation parameter combination for antibacterial rate only appears in combination 17, with one control parameter interval combination. The associated deviation parameter combination for tensile strength appears in combinations 17 and 19, with two control parameter interval combinations. The associated deviation parameter combination for air permeability appears in combinations 15, 17, and 19, with three control parameter interval combinations. The associated deviation parameter combination for color fastness appears in combinations 13, 15, 17, and 19, with four control parameter interval combinations.

[0247] Calculate the deviation weight value (deviation weight value = 1 ÷ number of control parameter interval combinations): Antibacterial rate deviation weighting value = 1 ÷ 1 = 1.000. Tensile strength deviation weighting value = 1 ÷ 2 = 0.500. Air permeability deviation weighting value = 1 ÷ 3 ≈ 0.333. Color fastness deviation weighting value = 1 ÷ 4 = 0.250.

[0248] Assuming a preset weight threshold of 0.40, the antibacterial rate deviation weight value is 1.000 > 0.40, and the tensile strength deviation weight value is 0.500 > 0.40, which satisfies condition 3 (there are product performance indicators with deviation weight values ​​greater than the preset weight threshold).

[0249] The parameter adjustment management method is determined as follows: under combination 17, adjustment is only required when the duration of abnormal production parameters exceeds the first duration (30 minutes).

[0250] Example of Scenario 4 (Hypothetical Scenario): If the distribution of the associated deviation parameters for each indicator in combination 15 is as follows: Antibacterial rate: Appears in combinations 5, 7, 13, 15, and 17, totaling 5, with a deviation weight value of 1 ÷ 5 = 0.200. Tensile strength: Appears in combinations 7, 11, 15, and 17, totaling 4, with a deviation weight value of 1 ÷ 4 = 0.250. Air permeability: Appears in combinations 10, 13, 15, 17, and 19, totaling 5, with a deviation weight value of 1 ÷ 5 = 0.200. Color fastness: Appears in combinations 8, 10, 11, 13, 14, 15, and 17, totaling 7, with a deviation weight value of 1 ÷ 7 ≈ 0.143.

[0251] If the deviation weight values ​​of each indicator are not greater than the preset weight threshold of 0.40, proceed to situation 4.

[0252] Calculate the verification requirement weight value (verification requirement weight value = sum of deviation weight values ​​of each indicator): Verification requirement weight value = 0.200 + 0.250 + 0.200 + 0.143 = 0.793.

[0253] If the preset weight threshold is 0.60, then 0.793 > 0.60, which satisfies the condition.

[0254] The parameter adjustment management method is determined as follows: under combination 15, adjustment is only required when the duration of abnormal production parameters exceeds the first duration (30 minutes).

[0255] If the verification requirement weight value is 0.50 < 0.60, then the condition is not met.

[0256] The parameter adjustment management method is as follows: If there are no abnormal production parameters within the most recent preset duration (24 hours) under combination 15, and the duration of abnormal production parameters is more than the first duration (30 minutes), then adjustment is required.

[0257] This embodiment, through the complete process from S1 to S4, achieves the systematization, digitalization, and intelligentization of the optimized management of the manufacturing process of nano-antibacterial yoga clothing. Its core value is reflected in five aspects: First, by analyzing deviation coefficients and deviation combination groups, a quantitative evaluation system for the reliability of the digital twin model is established; second, by calculating parameter fluctuation ranges and fluctuation values, the combination of control parameter ranges requiring parameter adjustment is accurately identified; third, through comprehensive analysis of related production parameters and fluctuation types, personalized customization of parameter adjustment strategies is achieved; fourth, by verifying the adjustment of parameter combinations and consistent combinations, the accuracy of the digital twin model is comprehensively tested; and fifth, through the classification management of four situations, differentiated handling strategies are implemented when production parameters are abnormal, ensuring both production stability and the comprehensiveness and reliability of the digital twin model verification.

[0258] Example 2 Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing when running the computer program.

[0259] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0260] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0261] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing, characterized in that, Specifically, it includes: Using the manufacturing process of nano-antibacterial yoga clothing, the baseline parameters of product performance indicators under different combinations of control parameter ranges are determined. Based on the consistency of the baseline parameters of the product performance indicators, when it is determined that the parameter adjustment combination in the control parameter range combination needs to be identified, the parameter adjustment combination in the control parameter range combination is determined based on the fluctuation data of the product performance indicators under the control parameter range combination. Based on the degree of parameter deviation between the parameter adjustment combination and other parameter adjustment combinations, and combined with the correlation between the fluctuation type of different product performance indicators in the parameter adjustment combination and other parameter adjustment combinations, the parameter adjustment strategy under the parameter adjustment combination is determined. The parameter adjustment strategy is used to adjust production parameters under the parameter adjustment combination to obtain the adjustment result. Then, by using the similarity between the adjustment result and the simulation result of the digital twin model, as well as the distribution data of product performance indicators that do not meet the similarity requirements, the parameter adjustment management method is determined when there are abnormalities in production parameters under different combinations of control parameter ranges.

2. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 1, characterized in that, The preparation process includes the control range of production parameters in different production equipment.

3. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 1, characterized in that, The combination of control parameter ranges is determined by combining the control range ranges of production parameters in different production equipment under the same preparation process.

4. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 1, characterized in that, The benchmark parameter of the product performance index is determined based on the parameter that has the highest number of products under the product performance index under the combination of the control parameter ranges.

5. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 1, characterized in that, The identification process for determining the parameter adjustment combinations within the control parameter range combinations specifically includes: Based on the degree of consistency of the basic parameters of the product performance indicators, the deviation coefficient of the benchmark parameters of the product performance indicators between different combinations of control parameter ranges is determined. Using the deviation coefficient, determine the group of control parameter intervals where the product performance index has deviation, and take this as the deviation combination group; Based on the deviation combination groups under different product performance indicators and the degree of overlap of the deviation combination groups, it is determined whether it is necessary to identify the parameter adjustment combination in the control parameter range combination.

6. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 5, characterized in that, The deviation combination group is constructed based on the control parameter ranges in which the deviation coefficients between each other under the product performance index are greater than a preset deviation coefficient threshold.

7. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 5, characterized in that, Based on the deviation combination groups under different product performance indicators and the degree of overlap of the deviation combination groups, it is determined whether the parameter adjustment combination in the control parameter range combination needs to be identified, specifically including: When different product performance indicators show uneven deviations, the accuracy of the simulation results of the digital twin model cannot be determined. Therefore, it is necessary to identify the parameter adjustment combinations in the control parameter range combinations.

8. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 1, characterized in that, The method for determining the parameter adjustment management method when the production parameters are abnormal is as follows: Using the adjustment processing results, the combination of adjustment ranges corresponding to different production parameters under the control parameter range combination is used as the adjustment parameter combination; Based on the aforementioned combination of control parameters, the similarity between the product performance indicators and the digital twin model under the adjusted parameter combination will be used as the consistent combination if the similarity of different product performance indicators meets the requirements. By utilizing consistent combination data under different combinations of control parameter ranges and product performance indicators whose similarity does not meet requirements under different combinations of adjustment parameters, a parameter adjustment management method is determined when the production parameters are abnormal under the control parameter range combination.

9. The method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in claim 8, characterized in that, If the deviation rate between the product performance index under the adjusted parameter combination and the simulation result of the digital twin model is less than the preset deviation rate, then the similarity of the product performance index is determined to meet the requirements.

10. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes the method for optimizing and managing the manufacturing process of nano-antibacterial yoga clothing as described in any one of claims 1-9.

Images