A process optimization method and system for manufacturing an antibacterial spandex fiber

Abstract

The present application relates to the technical field of fiber manufacturing, and specifically includes a manufacturing process optimization method and system for antibacterial spandex fiber, which comprises: according to the performance requirements of antibacterial spandex fiber raw materials, gradient proportion mixing dispersant and coupling agent, setting stirring and dispersion index; after vacuum drying of the obtained antibacterial master batch and spandex chip, through processes such as double screw extruder, multi-scale regulation and synergistic optimization of each parameter to determine the manufacturing process parameter combination. The technical problems of single or extensive temperature control mode, difficulty in according to the difference in thermal stability of antibacterial master batch and spandex chip, easy to appear local overheating degradation or insufficient melting, affect the mechanical properties of the fiber, and unable to guarantee the quality of the finished product are solved, the synergistic effect of segmented temperature control parameters and multi-stage stretching cold and hot cycle is realized, the material melting state and fiber molecular orientation are accurately controlled, and through the deep analysis of the coupling effect between parameters, the technical effects of improving the production process stability and the controllability of the finished product quality are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fiber manufacturing, and particularly relates to a manufacturing process optimization method and system for antibacterial spandex fibers. BACKGROUND

[0002] Spandex fibers have high elasticity, good extensibility and recovery, and on this basis, they are endowed with antibacterial properties, which can effectively inhibit bacterial growth and improve product safety and comfort, and have broad application prospects in the medical and health, sports clothing and other industries.

[0003] The current manufacturing process of antibacterial spandex fibers has many problems. In the raw material mixing stage, the proportion of dispersant and coupling agent is not appropriate, and the mixing stirring and ultrasonic dispersion index control is not good, which leads to uneven dispersion of antibacterial agents, affecting the antibacterial effect of the fibers. At the same time, the existing process parameter optimization is mostly based on experience or single variable adjustment, lacking systematic and collaborative optimization, and the quality monitoring and dynamic adjustment ability of the production process is insufficient, resulting in poor quality stability of the finished product, which is difficult to meet the large-scale industrial production demand.

[0004] In summary, the existing technology has the technical problems of single or extensive temperature control mode, which is difficult to adapt to the differences in thermal stability of antibacterial masterbatch and spandex chips, and is prone to local overheating degradation or insufficient melting, affecting the mechanical properties of the fibers and unable to guarantee the quality of the finished product. SUMMARY

[0005] The present application provides a manufacturing process optimization method and system for antibacterial spandex fibers, which aims to solve the technical problems of single or extensive temperature control mode in the prior art, which is difficult to adapt to the differences in thermal stability of antibacterial masterbatch and spandex chips, and is prone to local overheating degradation or insufficient melting, affecting the mechanical properties of the fibers and unable to guarantee the quality of the finished product.

[0006] In view of the above problems, the technical scheme of the present application is:

[0007] In one aspect of the present application, a method for optimizing the manufacturing process of antibacterial spandex fibers is provided, wherein the method comprises: mixing dispersants and coupling agents in gradient proportions according to the fiber performance requirements of antibacterial spandex fiber raw materials, setting mixing and stirring indexes and ultrasonic dispersion indexes; drying the antibacterial master batch and spandex chips prepared according to the mixing and stirring indexes and ultrasonic dispersion indexes in a vacuum environment, and then feeding them into a twin-screw extruder at a preset ratio, and setting segmented temperature control parameters; quantitatively feeding the material after melt blending to a spinning assembly through a metering pump to form a primary fiber, and adopting cold and hot cycle treatment during the multi-stage stretching process of the primary fiber to obtain antibacterial spandex fiber products; wherein the gradient proportions of dispersants and coupling agents are controlled in multiple scales in combination with the mixing and stirring indexes and ultrasonic dispersion indexes, and the segmented temperature control parameters and multi-stage stretching parameters are optimized in coordination to determine the manufacturing process parameter combination.

[0008] Preferably, the fiber performance requirements include fiber antibacterial rate and mechanical strength; a correlation database of the gradient proportions of dispersants and coupling agents and the fiber performance requirements is established to determine a multi-gradient ratio interval, and response surface optimization is performed in the multi-gradient ratio interval.

[0009] Preferably, the dispersant concentration and the coupling agent concentration are used as core variables, and effective variable intervals are screened under the boundary conditions of the correlation database; based on the effective variable intervals, interactive effect terms and quadratic terms are configured, and a fiber performance response surface is generated by comparing the multi-gradient ratio interval.

[0010] Preferably, the interactive effect terms include first interactive effect terms and second interactive effect terms; the first interactive effect terms under the coupling effect between parameters are determined based on the mixing and stirring speed of the mixing and stirring indexes in combination with the dispersant concentration; and the second interactive effect terms under the coupling effect between parameters are determined based on the ultrasonic dispersion time of the ultrasonic dispersion indexes in combination with the coupling agent concentration.

[0011] Preferably, the interactive effect terms and the quadratic terms are substituted into the fiber performance response surface to construct a multi-variable nonlinear model containing dispersant concentration, coupling agent concentration, mixing and stirring speed, and ultrasonic dispersion time; global optimization is performed on the multi-variable nonlinear model, the predicted fiber antibacterial rate and mechanical strength predicted values under different variable combinations are iterated through crossover operation and mutation operation; during the optimization process, a target function is formulated according to the predicted fiber antibacterial rate and mechanical strength predicted values to determine a multi-scale control parameter set.

[0012] Preferably, the twin-screw extruder is linked, historical temperature data of each heating section and corresponding material melting state images are collected, a convolutional neural network is used to extract temperature-melting state feature mapping relationship, temperature regulation constraint conditions are constructed based on the temperature-melting state feature mapping relationship and in combination with thermal stability parameters of the antibacterial master batch and spandex chips, and the segmented temperature control parameters are determined by searching under the temperature regulation constraint conditions.

[0013] Preferably, the molecular orientation and stress-strain parameters of the primary fiber in the stretching process are established, the stretching ratio range is determined in combination with the target mechanical property requirements of the antibacterial spandex fiber, the temperature variation gradient, the cycle number and the residence time of each temperature section of the cold-hot cycle are set as optimization variables, an orthogonal test scenario is drafted, and the fiber breaking strength and elongation at break under the orthogonal test scenario are used to perform collaborative optimization in the stretching ratio range to determine the manufacturing process parameter combination.

[0014] Preferably, a digital twin model associated with the manufacturing process of the antibacterial spandex fiber is constructed, the manufacturing process parameter combination is uploaded for simulation verification, meanwhile, fluctuation data of fiber quality indicators in the simulation running process are collected, key parameters affecting the quality stability of the antibacterial spandex fiber product are identified, and a dynamic compensation mechanism is set, which is used to adaptively adjust the key parameters according to the equipment running state and environmental changes.

[0015] Preferably, a fiber surface defect detection unit under machine vision is established, a YOLO model is trained to identify defects of the antibacterial spandex fiber product including fiber surface holes and uneven thickness, the antibacterial spandex fiber product defect identification information is associated with the key parameters for correlation analysis, a defect traceability fault tree is constructed, and the defect traceability fault tree is used to mark the position of the antibacterial spandex fiber product defect.

[0016] In another aspect, this application provides a manufacturing process optimization system for antibacterial spandex fibers. The system includes: a gradient proportion mixing module, used to add dispersants and coupling agents in gradient proportions according to the fiber performance requirements of the antibacterial spandex fiber raw materials, and setting mixing and stirring indices and ultrasonic dispersion indices; a drying module, used to dry the antibacterial masterbatch and spandex chips prepared according to the mixing and stirring indices and ultrasonic dispersion indices under vacuum, and then feed them into a twin-screw extruder according to a preset ratio, setting segmented temperature control parameters; a circulation module, used to quantitatively transport the melt-blended material to a spinning assembly via a metering pump, extrude it to form nascent fibers, and use a hot and cold cycle treatment during the multi-stage stretching process of the nascent fibers to obtain the finished antibacterial spandex fiber; and a synergistic optimization module, used to determine the combination of manufacturing process parameters by multi-scale control based on the gradient proportions of dispersants and coupling agents, combined with the mixing and stirring indices and ultrasonic dispersion indices, and in conjunction with the synergistic optimization of the segmented temperature control parameters and multi-stage stretching parameters.

[0017] In summary, one or more technical solutions provided in this application achieve the synergistic effect of segmented temperature control parameters and multi-stage stretching thermal cycling, precisely controlling the melting state of materials and fiber molecular orientation. Through in-depth analysis of the coupling effect between parameters, the technical effect of improving the stability of the production process and the controllability of finished product quality is enhanced. Attached Figure Description

[0018] Figure 1 This application provides a flowchart illustrating an optimized manufacturing process for antibacterial spandex fibers.

[0019] Figure 2 This application provides a schematic diagram of the structure of a manufacturing process optimization system for antibacterial spandex fibers.

[0020] Explanation of reference numerals in the attached diagram: Gradient ratio mixing module M100, drying processing module M200, circulation processing module M300, and collaborative optimization module M400. Detailed Implementation

[0021] Example 1

[0022] The present application will now be described in detail with reference to the accompanying drawings, such as... Figure 1 As shown, this application provides a method for optimizing the manufacturing process of antibacterial spandex fiber, wherein the method includes:

[0023] S1: According to the fiber performance requirements of antibacterial spandex fiber raw materials, dispersant and coupling agent are added in a gradient ratio, and mixing and stirring index and ultrasonic dispersion index are set; S2: The antibacterial masterbatch and spandex chips prepared with the mixing and stirring index and ultrasonic dispersion index are dried in a vacuum environment, and then fed into a twin-screw extruder according to a preset ratio, and segmented temperature control parameters are set.

[0024] Specifically, gradient ratio mixing refers to mixing dispersants and coupling agents according to specific gradient ratios based on fiber performance requirements to achieve uniform dispersion of antibacterial agents in fibers. The mixing method involves not only adjusting the ratio between dispersants and coupling agents, but also the synergistic effect with antibacterial spandex fiber raw materials. The mixing and stirring index and ultrasonic dispersion index refer to parameters such as rotation speed and time during the stirring process and parameters such as time and intensity of ultrasonic dispersion treatment, respectively, to ensure uniform distribution and full dispersion of dispersants and coupling agents in raw materials.

[0025] In one feasible implementation, according to the fiber performance requirements of the antibacterial spandex fiber raw material, such as antibacterial rate and mechanical strength, the dispersant and coupling agent are mixed and added in a gradient ratio, which can effectively improve the dispersibility of the antibacterial agent in the fiber. By setting the mixing speed, stirring time, and ultrasonic dispersion time, it is ensured that the dispersant and coupling agent are fully mixed with the antibacterial agent to form a uniform antibacterial masterbatch. The prepared antibacterial masterbatch and spandex chips are dried in a vacuum environment, for example, by setting the vacuum degree to -0.08MPa to -0.095MPa and the pre-drying temperature to 80-100℃, which can effectively remove moisture from the raw material and prevent the generation of bubbles or defects during subsequent extrusion.

[0026] The dried antibacterial masterbatch and spandex chips are fed into a twin-screw extruder according to a preset ratio. Segmented temperature control parameters are set, such as zone 1 temperature 200-220℃, zone 2 temperature 220-240℃, zone 3 temperature 240-260℃, zone 4 temperature 250-270℃, and zone 5 temperature 260-280℃. The screw speed is controlled at 150-250 r / min to ensure that the material stays in the extruder for a sufficient time (e.g., 8-12 min) to achieve full melt blending. This segmented temperature control can avoid local overheating and degradation or insufficient melting based on the difference in thermal stability between the antibacterial masterbatch and spandex chips, thereby improving the mechanical properties and quality stability of the fiber.

[0027] S3: The material after melt blending is quantitatively delivered to the spinning assembly by a metering pump and extruded to form nascent fibers. During the multi-stage stretching process of the nascent fibers, a hot and cold cycle treatment is adopted to obtain the antibacterial spandex fiber product; S4: The manufacturing process parameter combination is determined by multi-scale control based on the gradient ratio of dispersant and coupling agent, combined with the mixing and stirring index and ultrasonic dispersion index, and in conjunction with the synergistic optimization of the segmented temperature control parameters and multi-stage stretching parameters.

[0028] Specifically, metering the material to the spinning assembly via a metering pump means precisely controlling the pump's rotation speed to deliver the molten blended material to the spinning assembly at a stable flow rate, ensuring the continuity and stability of the extrusion process. Extrusion to form nascent fibers involves squeezing the molten material through the tiny pores of a spinneret to form filamentous nascent fibers, a crucial step in fiber formation. The use of hot and cold cycling during the multi-stage stretching of nascent fibers refers to alternating hot air circulation for heating and water bath cooling, causing the fibers to undergo temperature changes during stretching. This regulates molecular orientation and stress distribution, improving the fiber's mechanical properties. This hot and cold cycling process requires precise control of parameters such as temperature, air velocity, and water bath temperature to achieve optimal stretching results.

[0029] In one feasible implementation, a gear metering pump is used, with the rotation speed controlled at 30-60 r / min. This ensures stable material delivery and avoids the impact of flow fluctuations on fiber quality. Preferably, when the metering pump speed is set to 45 r / min, the fiber uniformity is optimal, and the breaking strength can reach above 1.8 cN / dtex. During the multi-stage stretching process of the nascent fiber, a hot and cold cycle treatment is used, which can significantly improve the mechanical properties of the fiber. For example, the nascent fiber is first stretched in a hot air circulation device at a temperature of 80℃-90℃ and a wind speed of 2-3 m / s, with a stretching ratio of 3-5 times. Then, it is quickly immersed in a water bath at a temperature of 20-30℃ for cooling and shaping, and then subjected to a second stretching at a temperature of 100-110℃, with a stretching ratio of 1.5-2.5 times.

[0030] By optimizing the temperature gradient and the number of cycles, the hot and cold cycling process can effectively regulate molecular orientation and stress-strain properties, thereby balancing the mechanical strength and antibacterial properties of the fiber. By controlling the gradient ratio of dispersants and coupling agents at multiple scales, combined with mixing and ultrasonic dispersion indicators, and with the synergistic optimization of segmented temperature control parameters and multi-level stretching parameters, the optimal combination of manufacturing process parameters can be determined.

[0031] Furthermore, the method of this application includes:

[0032] The fiber performance requirements include fiber antibacterial rate and mechanical strength; a correlation database is established between the gradient ratio of dispersant and coupling agent and the fiber performance requirements, and multiple gradient ratio ranges are determined, and response surface optimization is performed based on the multiple gradient ratio ranges.

[0033] Specifically, fiber performance requirements refer to performance indicators such as antibacterial rate and mechanical strength proposed for fibers based on specific application scenarios. Antibacterial rate usually refers to the fiber's ability to inhibit specific bacteria (such as Escherichia coli and Staphylococcus aureus), expressed as a percentage. Mechanical strength involves indicators such as fiber breaking strength and elongation, reflecting the fiber's durability and elasticity. Establishing a correlation database between the gradient ratio of dispersants and coupling agents and fiber performance requirements refers to constructing a database containing different ratios of dispersants and coupling agents, mixing and stirring indicators, ultrasonic dispersion indicators, and corresponding fiber antibacterial rates and mechanical strengths through experimental data collection and analysis. This correlation database can reflect the quantitative relationship between process parameters and fiber performance, providing data support for subsequent process optimization. Response surface methodology is a statistical analysis method used to determine the optimal combination of process parameters within a multi-gradient ratio range, predict fiber performance through mathematical models, and find the parameter combination that achieves the best performance.

[0034] In one feasible implementation, by varying the gradient ratio of dispersant and coupling agent (e.g., 0.5% to 1% dispersant and 0.3% to 0.8% coupling agent), and combining this with different mixing speeds (800-1200 r / min) and ultrasonic dispersion times (20-40 min), antibacterial spandex fiber samples with different antibacterial rates and mechanical strengths can be prepared. Preferably, when the dispersant concentration is 0.8%, the coupling agent concentration is 0.5%, the mixing speed is 1000 r / min, and the ultrasonic dispersion time is 30 min, the resulting fiber achieves an antibacterial rate of 99.5% and a breaking strength of 2.0 cN / dtex. By collecting a large amount of such experimental data and constructing a correlation database, it is possible to clearly reflect how the ratio of dispersant and coupling agent, as well as other process parameters, affects fiber properties.

[0035] Building upon this foundation, response surface methodology (RSM) optimization using multi-gradient mixing ratios allows for further refinement of process parameters. The RSM method constructs a mathematical model, using dispersant and coupling agent concentrations as core variables, considering the interaction effects of mixing speed and ultrasonic dispersion time. It predicts fiber performance under different parameter combinations and uses iterative calculations to find the optimal parameter combination for achieving the best fiber performance. This optimization method not only improves process precision but also significantly enhances production efficiency and product quality, enabling antibacterial spandex fibers to consistently meet the high standards required for large-scale industrial production.

[0036] Furthermore, the method of this application for response surface optimization using the aforementioned multi-gradient ratio range includes:

[0037] Using dispersant concentration and coupling agent concentration as core variables, effective variable intervals are selected based on the boundary conditions of the associated database. Based on the effective variable intervals, interaction effect terms and quadratic terms are configured, and fiber performance response surfaces are generated by comparing with the multi-gradient ratio intervals.

[0038] Specifically, the core variables refer to the key process parameters that significantly affect fiber performance, namely dispersant concentration and coupling agent concentration. Changes in these variables directly affect the dispersion effect of antibacterial agents in the spandex matrix and the final fiber performance. The boundary conditions of the associated database refer to the reasonable range of dispersant and coupling agent concentrations determined during the preliminary experiments and data collection process. These ranges are based on the acceptable range of fiber performance requirements (such as antibacterial rate and mechanical strength). Screening the effective variable range refers to further narrowing the range of dispersant and coupling agent concentrations within the boundary conditions through data analysis and statistical methods, so that they more accurately correspond to the optimal fiber performance. The interaction effect term refers to the influence of the interaction between two variables on fiber performance, such as the synergistic effect between dispersant concentration and mixing speed. The quadratic term refers to the square of the variable itself, used to describe the nonlinear influence of the variable on fiber performance. The fiber performance response surface is a visualization tool that uses mathematical models to present the complex relationship between multiple variables and fiber performance in the form of a three-dimensional surface, helping to identify the optimal combination of process parameters.

[0039] In one feasible implementation, using dispersant concentration and coupling agent concentration as core variables and screening effective variable ranges under boundary conditions in a correlation database is a key step in optimizing the process. For example, the boundary conditions for dispersant concentration in the correlation database are 0.5% to 1.5% and coupling agent concentration is 0.2% to 1.0%. Data analysis revealed that the fiber exhibits the best antibacterial rate and mechanical strength when the dispersant concentration is between 0.7% and 1.2% and the coupling agent concentration is between 0.3% and 0.8%.

[0040] Based on the aforementioned effective variable range, interaction terms and quadratic terms are configured to construct a fiber performance response surface. Furthermore, the interaction terms include the interaction between dispersant concentration and mixing speed, and the interaction between coupling agent concentration and ultrasonic dispersion time. The quadratic terms consider the squares of dispersant and coupling agent concentrations to capture their nonlinear effects on fiber performance. By generating a fiber performance response surface using the response surface methodology, the changing trends of fiber performance under different concentration combinations can be visually observed. Analyzing the response surface allows for the determination of the optimal parameter combination, thereby enabling the stable manufacturing of high-quality antibacterial spandex fibers in large-scale production.

[0041] Furthermore, the method of this application includes:

[0042] The interaction effect term includes a first interaction effect term and a second interaction effect term; based on the dispersant concentration and the mixing speed of the mixing index, the first interaction effect term under the parameter coupling effect is determined; based on the coupling agent concentration and the ultrasonic dispersion time of the ultrasonic dispersion index, the second interaction effect term under the parameter coupling effect is determined.

[0043] Specifically, the interaction effect term refers to the influence of the interaction between two or more process parameters on fiber properties. The first interaction effect term is based on the coupling effect between dispersant concentration and mixing speed in the mixing index. Specifically, changes in dispersant concentration affect the dispersion efficiency of antibacterial agents during mixing, while adjustments to the mixing speed also change the interaction effect between dispersant and antibacterial agents. The second interaction effect term is based on the coupling effect between coupling agent concentration and ultrasonic dispersion time in the ultrasonic dispersion index. Changes in coupling agent concentration affect the interfacial bonding between antibacterial agents and spandex chips during ultrasonic dispersion, while the duration of ultrasonic dispersion further affects the stability of this bonding.

[0044] In one feasible implementation, firstly, based on the interaction between dispersant concentration and mixing speed, a first interaction effect term is determined. For example, when the dispersant concentration is 0.8% and the mixing speed is 1000 r / min, the antibacterial agent exhibits optimal dispersion in the spandex matrix, achieving an antibacterial rate of 99.5% and a breaking strength of 2.0 cN / dtex. Through regression analysis of the experimental data, the linear and nonlinear relationships between dispersant concentration and mixing speed can be determined, thereby quantifying the magnitude of the first interaction effect term.

[0045] Secondly, based on the interaction between coupling agent concentration and ultrasonic dispersion time, a second interaction effect term is determined. For example, when the coupling agent concentration is 0.5% and the ultrasonic dispersion time is 35 min, the interfacial bonding strength between the antibacterial agent and the spandex chips reaches its maximum, and the mechanical properties of the fiber are significantly improved. Through similar regression analysis, the coefficient of the second interaction effect term can be determined. Introducing these interaction effect terms into the response surface model can more accurately predict the fiber properties under different combinations of process parameters.

[0046] Furthermore, based on the gradient ratio of dispersant and coupling agent, and combined with the mixing and stirring index and ultrasonic dispersion index, the method of this application includes multi-scale control:

[0047] Substituting the interaction effect term and the quadratic term into the fiber performance response surface, a multivariate nonlinear model is constructed, including dispersant concentration, coupling agent concentration, mixing speed, and ultrasonic dispersion time. Global optimization is performed on the multivariate nonlinear model, iterating the predicted fiber antibacterial rate and mechanical strength under different variable combinations through crossover and mutation operations. During the optimization process, an objective function is formulated based on the predicted fiber antibacterial rate and mechanical strength, and a set of multi-scale control parameters is determined.

[0048] Specifically, a multivariate nonlinear model refers to a mathematical model that comprehensively considers multiple process parameters (such as dispersant concentration, coupling agent concentration, mixing speed, and ultrasonic dispersion time) and their interaction effects and quadratic terms; this model is used to describe the nonlinear relationship between these complex process parameters and fiber properties (antibacterial rate and mechanical strength); global optimization refers to the process of finding the optimal combination of parameters to achieve the best fiber properties within the parameter space defined by the model.

[0049] Crossover and mutation are two key operations in genetic algorithms. Crossover generates new combinations by exchanging the values ​​of different parameter combinations, while mutation increases the diversity of the search by randomly changing the value of a parameter. The objective function is a standard function used to measure the quality of parameter combinations during the optimization process. It is constructed based on the predicted values ​​of fiber antibacterial rate and mechanical strength, and is formed by weighted summation or other combinations. The multi-scale control parameter set is a set of parameter values ​​determined after optimization. These parameters work together at different scales (such as molecular dispersion, interfacial bonding, and macroscopic performance) to achieve the best fiber performance.

[0050] In one feasible implementation, the interaction effect term and the quadratic term are substituted into the fiber performance response surface to construct a multivariate nonlinear model that includes dispersant concentration, coupling agent concentration, mixing speed, and ultrasonic dispersion time. When performing global optimization on the multivariate nonlinear model, a genetic algorithm is preferably used, with an initial population size of 50 and 100 generations. Single-point crossover is used with a crossover probability of 0.8, and uniform mutation is used with a mutation probability of 0.1. In each generation, the predicted fiber antibacterial rate is denoted as... The predicted mechanical strength value is denoted as The objective function value F is calculated based on the predicted fiber antibacterial rate and mechanical strength: F = w1 × +w2× In this study, w1 and w2 are the weighting coefficients for predicting the fiber antibacterial rate and mechanical strength, respectively. Through iterative optimization, a set of multi-scale control parameters is determined, the dispersion of the antibacterial agent is optimized, the binding force is enhanced at the interface scale, and the fiber performance is improved at the macro scale, thus achieving multi-scale synergistic control.

[0051] Furthermore, by coordinating the segmented temperature control parameters and multi-stage tensile parameters to determine the combination of manufacturing process parameters, the method of this application includes:

[0052] The twin-screw extruder is linked to collect historical temperature data and corresponding material melting state images of each heating section. A convolutional neural network is used to extract the temperature-melting state feature mapping relationship. Based on the temperature-melting state feature mapping relationship, combined with the thermal stability parameters of antibacterial masterbatch and spandex chips, temperature control constraints are constructed. Under the temperature control constraints, the segmented temperature control parameters are searched and determined.

[0053] Specifically, in the manufacturing process of antibacterial spandex fibers, linking the twin-screw extruder refers to connecting the temperature data acquisition system to the heating section of the twin-screw extruder to collect historical temperature data of each heating section in real time. Simultaneously, collecting historical temperature data and corresponding material melting state images of each heating section involves recording temperature changes in each heating section of the extruder and images of the material's melting state at different temperatures using temperature sensors and image acquisition equipment. Utilizing convolutional neural networks (CNNs), a deep learning technique, allows for the extraction of feature mapping relationships between temperature and the material's melting state through training a CNN model. This mapping relationship helps us understand the changing patterns of the material's melting state under different temperature conditions. Thermal stability parameters refer to the highest temperature that the antibacterial masterbatch and spandex chips can withstand during processing and the temperature range within which they maintain performance stability. These parameters are crucial for determining reasonable temperature control constraints.

[0054] In one feasible implementation, after linking the twin-screw extruder, collecting historical temperature data and corresponding material melting state images for each heating section forms the basis for constructing a temperature-melting state feature mapping relationship. By training a convolutional neural network on a large amount of data and images, the complex nonlinear relationship between temperature changes and the material melting state can be extracted.

[0055] Based on the melting characteristics of the materials, such as crystalline materials requiring temperatures slightly above their melting point and amorphous materials requiring temperatures above their glass transition temperature, and combining the thermal stability parameters of antibacterial masterbatch and spandex chips, temperature control constraints can be constructed. These constraints ensure that the temperature settings of each heating section of the extruder guarantee sufficient melting of the material while preventing material degradation due to excessively high temperatures. Under these temperature control constraints, a search is conducted, and an optimization algorithm is used to determine segmented temperature control parameters, enabling the material to achieve optimal melt blending during extrusion while preventing the decomposition of antibacterial components.

[0056] Furthermore, the method of this application includes:

[0057] The molecular orientation and stress-strain parameters of the nascent fiber during the stretching process are established. Combined with the target mechanical performance requirements of antibacterial spandex fiber, the stretching ratio range is determined. The temperature change gradient, number of cycles, and residence time at each temperature range are set as optimization variables to formulate an orthogonal test scenario. Through the fiber breaking strength and breaking elongation under the orthogonal test scenario, synergistic optimization is performed within the stretching ratio range to determine the combination of manufacturing process parameters.

[0058] Specifically, in the stretching process of nascent fibers, establishing molecular orientation and stress-strain parameters refers to determining the degree of orientation of polymer chain segments within the fiber during stretching and the relationship between stress and strain through experimental measurements and theoretical modeling. These parameters include Young's modulus, yield strength, elongation at break, and molecular orientation function. Target mechanical performance requirements refer to the mechanical performance indicators set according to the specific application scenarios of antibacterial spandex fibers (such as medical clothing), including breaking strength and elongation at break. The stretch ratio range is the range of multiples by which the length of the nascent fiber increases during stretching. The temperature gradient, number of cycles, and residence time at each temperature range during thermal cycling are important process parameters affecting fiber molecular orientation and crystallinity. Orthogonal testing scenarios are used to systematically vary these optimization variables to evaluate their impact on fiber performance.

[0059] In one feasible implementation, the molecular orientation and stress-strain parameters of the nascent fiber during the stretching process are established. Specifically, in a uniaxial tensile test, the stress-strain curve of the fiber can be measured, and the Young's modulus and elongation at break can be calculated. At the same time, the degree of orientation of the molecular chains can be observed using a polarizing microscope or X-ray diffraction technique, and a molecular orientation function can be established.

[0060] Based on the target mechanical property requirements of antibacterial spandex fiber (e.g., breaking strength ≥2.0 cN / dtex, breaking elongation ≥400%), the draw ratio range was determined to be 3-5 times through theoretical analysis and experimental verification. To optimize the thermal cycling parameters, an orthogonal test scenario was set up, selecting temperature change gradients (e.g., 20℃ / min, 30℃ / min, 40℃ / min), number of cycles (e.g., 1, 2, 3 times), and residence time at each temperature range (e.g., 1 min, 2 min, 3 min) as variables. Through the orthogonal test scenario, the influence of these variables on fiber properties can be efficiently evaluated, and the optimal combination of manufacturing process parameters within the draw ratio range was determined, thus achieving the best balance between mechanical and antibacterial properties in the antibacterial spandex fiber.

[0061] Furthermore, the method of this application also includes:

[0062] A digital twin model relating to the manufacturing process of antibacterial spandex fiber is constructed, and the manufacturing process parameters are combined and uploaded for simulation verification. At the same time, fluctuation data of fiber quality indicators are collected during the simulation operation to identify key parameters affecting the quality stability of the finished antibacterial spandex fiber. A dynamic compensation mechanism is set up to adaptively adjust the key parameters according to the equipment operating status and environmental changes.

[0063] Specifically, the digital twin model can construct a virtual mapping of the antibacterial spandex fiber manufacturing process to simulate and verify the effects of combinations of manufacturing process parameters. During the simulation verification process, the combination of manufacturing process parameters is uploaded to the digital twin model to simulate the fiber manufacturing process, thereby evaluating the effectiveness and quality impact of the parameters. Key parameters refer to process parameters that have a significant impact on the stability of the finished fiber quality; fluctuations in these parameters may lead to inconsistencies in fiber quality. The dynamic compensation mechanism is a real-time adjustment system that can adaptively adjust key parameters according to the actual operating status of the equipment and environmental changes (such as temperature, humidity, equipment load, etc.) to ensure the stability of the production process and the consistency of product quality.

[0064] In one feasible implementation, by uploading the combination of manufacturing process parameters to a digital twin model for simulation verification, the performance of the parameter combination in actual production can be evaluated in advance. For example, by simulating segmented temperature control parameters and multi-stage tensile parameters in the digital twin model, the molecular orientation and stress distribution during fiber forming can be observed, and the fiber's breaking strength and elongation at break can be predicted.

[0065] Meanwhile, collecting fluctuation data of fiber quality indicators during simulation operation, such as antibacterial rate, mechanical strength, and diameter uniformity, helps to identify key parameters affecting the stability of finished fiber quality. For example, the analysis found that the temperature in the fourth zone of the twin-screw extruder and the first-stage draw ratio of the nascent fiber have a significant impact on the fiber's breaking strength.

[0066] To address the uncertainties brought about by changes in equipment operating status and the environment, a dynamic compensation mechanism is implemented. By monitoring equipment parameters and environmental conditions in real time, and utilizing PID control or fuzzy control algorithms, key parameters are adaptively adjusted. For example, when increased ambient humidity causes fluctuations in fiber diameter, the dynamic compensation mechanism can automatically adjust the extrusion speed of the spinning assembly and the rotation speed of the metering pump to ensure the uniformity of fiber diameter. This real-time feedback and adjustment mechanism significantly improves the stability of the production process and the controllability of finished product quality.

[0067] Furthermore, the method of this application also includes:

[0068] A fiber surface defect detection unit under machine vision is established. By training a YOLO model, defects in antibacterial spandex fiber finished products, including fiber surface holes and uneven thickness, are identified. The defect identification information of the antibacterial spandex fiber finished products is correlated with the key parameters to construct a defect source fault tree. The defect source fault tree is used to locate and mark the defects in the antibacterial spandex fiber finished products.

[0069] Specifically, machine vision is a technology that uses optical equipment and computer vision algorithms to detect and analyze objects. In the manufacturing of antibacterial spandex fibers, establishing a fiber surface defect detection unit under machine vision refers to acquiring fiber surface images through a high-resolution camera and using the YOLO (You Only Look Once, a target detection algorithm) model for real-time defect detection, which can quickly and accurately identify specific targets in the image.

[0070] Surface pores and uneven fiber thickness are two common defects in antibacterial spandex fibers, which can affect the fiber's mechanical properties and antibacterial effect. Key parameters refer to process parameters that significantly affect fiber quality during manufacturing, such as dispersant concentration, mixing speed, and draw ratio. Correlation analysis uses statistical methods or data mining techniques to identify the relationship between fiber surface defects and key parameters to determine the main causes of defects. Fault tree analysis is a system analysis tool used to build causal relationship models of defects, helping to identify and locate the root causes of defects. Location marking refers to marking the identified defect locations on the finished fiber product for subsequent quality control and improvement.

[0071] In one feasible implementation, a machine vision-based fiber surface defect detection unit is established by training a YOLO model to identify defects such as pores and uneven thickness on the fiber surface. A large number of fiber surface images with defect annotations are collected as a training dataset. Data augmentation techniques (such as rotation, scaling, and cropping) are used to expand the dataset, and then the YOLO model is trained. The trained YOLO model can detect fiber surface defects in real time during actual production and output the location and type of the defects.

[0072] By correlating the identified defect information with key process parameters and constructing a defect source fault tree, the causes of defects can be systematically analyzed. For example, Pearson correlation analysis revealed that fiber surface pores are highly correlated with the temperature of the fourth zone of the twin-screw extruder and the vacuum drying time, while uneven thickness is closely related to the first-level draw ratio of the nascent fiber and the extrusion speed of the spinning assembly.

[0073] By utilizing fault tree analysis (FMA), identified defects can be located and marked, guiding parameter adjustments during production. For example, when surface pores are detected on fibers, FMA analysis suggests that the degradation may be due to excessively high temperatures in Zone 4. In this case, the pores are marked at the fiber defect location, and it is recommended to lower the Zone 4 temperature by 5-10°C and extend the vacuum drying time by 1-2 hours. This defect location and marking method can significantly improve the efficiency of quality control in the production process, reduce the defect rate, and enhance the overall quality level of antibacterial spandex fibers.

[0074] In summary, the beneficial effects of the embodiments of this application are:

[0075] Based on the fiber performance requirements of antibacterial spandex fiber raw materials, dispersants and coupling agents are added in gradient proportions, and mixing and ultrasonic dispersion indices are set. The antibacterial masterbatch and spandex chips prepared according to the mixing and ultrasonic dispersion indices are dried in a vacuum environment, and then fed into a twin-screw extruder according to a preset ratio, with segmented temperature control parameters set. The melt-blended material is quantitatively delivered to the spinning assembly by a metering pump, and extruded to form nascent fibers. During the multi-stage stretching process of the nascent fibers, a hot and cold cycle treatment is used to obtain the finished antibacterial spandex fiber. Among them, the combination of manufacturing process parameters is determined by multi-scale control based on the gradient proportions of dispersants and coupling agents, combined with mixing and ultrasonic dispersion indices, and synergistic optimization of segmented temperature control parameters and multi-stage stretching parameters. This application provides a manufacturing process optimization method and system for antibacterial spandex fibers, which achieves the synergistic effect of segmented temperature control parameters and multi-stage stretching thermal cycling, precisely controlling the melting state of materials and fiber molecular orientation. Through in-depth analysis of the coupling effect between parameters, it improves the technical effect of enhancing the stability of the production process and the controllability of finished product quality.

[0076] Example 2

[0077] Based on the same inventive concept as the manufacturing process optimization method for antibacterial spandex fiber in the foregoing embodiments, such as Figure 2 As shown in the figure, this application provides a manufacturing process optimization system for antibacterial spandex fibers, wherein the system includes:

[0078] The gradient proportion mixing module M100 is used to add dispersants and coupling agents in a gradient proportion according to the fiber performance requirements of antibacterial spandex fiber raw materials, and to set the mixing and stirring index and ultrasonic dispersion index.

[0079] The drying module M200 is used to dry the antibacterial masterbatch and spandex chips prepared with the mixing and stirring index and ultrasonic dispersion index in a vacuum environment. After that, the chips are fed into a twin-screw extruder according to a preset ratio and segmented temperature control parameters are set.

[0080] The recycling module M300 is used to quantitatively transport the melt-blended material to the spinning assembly via a metering pump, extrude it to form nascent fibers, and then use a hot and cold cycle treatment during the multi-stage stretching process of the nascent fibers to obtain antibacterial spandex fiber finished products.

[0081] The collaborative optimization module M400 is used to determine the combination of manufacturing process parameters by performing multi-scale control based on the gradient ratio of dispersant and coupling agent, combined with the mixing and stirring index and ultrasonic dispersion index, and in conjunction with the collaborative optimization of the segmented temperature control parameters and multi-level stretching parameters.

[0082] Furthermore, the gradient scaling mixing module M100 is also used to perform the following method:

[0083] The fiber performance requirements include fiber antibacterial rate and mechanical strength; a correlation database is established between the gradient ratio of dispersant and coupling agent and the fiber performance requirements, and multiple gradient ratio ranges are determined, and response surface optimization is performed based on the multiple gradient ratio ranges.

[0084] Furthermore, the gradient scaling mixing module M100 is also used to perform the following method:

[0085] Using dispersant concentration and coupling agent concentration as core variables, effective variable intervals are selected based on the boundary conditions of the associated database. Based on the effective variable intervals, interaction effect terms and quadratic terms are configured, and fiber performance response surfaces are generated by comparing with the multi-gradient ratio intervals.

[0086] Furthermore, the gradient scaling mixing module M100 is also used to perform the following method:

[0087] The interaction effect term includes a first interaction effect term and a second interaction effect term; based on the dispersant concentration and the mixing speed of the mixing index, the first interaction effect term under the parameter coupling effect is determined; based on the coupling agent concentration and the ultrasonic dispersion time of the ultrasonic dispersion index, the second interaction effect term under the parameter coupling effect is determined.

[0088] Furthermore, the collaborative optimization module M400 is used to perform the following method:

[0089] Substituting the interaction effect term and the quadratic term into the fiber performance response surface, a multivariate nonlinear model is constructed, including dispersant concentration, coupling agent concentration, mixing speed, and ultrasonic dispersion time. Global optimization is performed on the multivariate nonlinear model, iterating the predicted fiber antibacterial rate and mechanical strength under different variable combinations through crossover and mutation operations. During the optimization process, an objective function is formulated based on the predicted fiber antibacterial rate and mechanical strength, and a set of multi-scale control parameters is determined.

[0090] Furthermore, the collaborative optimization module M400 is also used to perform the following methods:

[0091] The twin-screw extruder is linked to collect historical temperature data and corresponding material melting state images of each heating section. A convolutional neural network is used to extract the temperature-melting state feature mapping relationship. Based on the temperature-melting state feature mapping relationship, combined with the thermal stability parameters of antibacterial masterbatch and spandex chips, temperature control constraints are constructed. Under the temperature control constraints, the segmented temperature control parameters are searched and determined.

[0092] Furthermore, the collaborative optimization module M400 is also used to perform the following methods:

[0093] The molecular orientation and stress-strain parameters of the nascent fiber during the stretching process are established. Combined with the target mechanical performance requirements of antibacterial spandex fiber, the stretching ratio range is determined. The temperature change gradient, number of cycles, and residence time at each temperature range are set as optimization variables to formulate an orthogonal test scenario. Through the fiber breaking strength and breaking elongation under the orthogonal test scenario, synergistic optimization is performed within the stretching ratio range to determine the combination of manufacturing process parameters.

[0094] Furthermore, the manufacturing process optimization system for the antibacterial spandex fiber is also used to perform the following methods:

[0095] A digital twin model relating to the manufacturing process of antibacterial spandex fiber is constructed, and the manufacturing process parameters are combined and uploaded for simulation verification. At the same time, fluctuation data of fiber quality indicators are collected during the simulation operation to identify key parameters affecting the quality stability of the finished antibacterial spandex fiber. A dynamic compensation mechanism is set up to adaptively adjust the key parameters according to the equipment operating status and environmental changes.

[0096] Furthermore, the manufacturing process optimization system for the antibacterial spandex fiber is also used to perform the following methods:

[0097] A fiber surface defect detection unit under machine vision is established. By training a YOLO model, defects in antibacterial spandex fiber finished products, including fiber surface holes and uneven thickness, are identified. The defect identification information of the antibacterial spandex fiber finished products is correlated with the key parameters to construct a defect source fault tree. The defect source fault tree is used to locate and mark the defects in the antibacterial spandex fiber finished products.

[0098] In summary, any step can be stored as a computer instruction or program in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor; no further restrictions are imposed here.

[0099] Furthermore, the above technical solutions only embody the preferred technical solutions of the embodiments of this application. Any changes that those skilled in the art may make to certain parts of these solutions embody the novel principles of the embodiments of this application. Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application.

Claims

1. An optimized manufacturing process for antibacterial spandex fiber, characterized in that, The method includes: Based on the fiber performance requirements of antibacterial spandex fiber raw materials, dispersants and coupling agents are added in gradient proportions, and mixing and stirring indicators and ultrasonic dispersion indicators are set. The antibacterial masterbatch and spandex chips prepared with the aforementioned mixing and ultrasonic dispersion index are dried in a vacuum environment, and then fed into a twin-screw extruder according to a preset ratio, with segmented temperature control parameters set. The material after being melted and blended is quantitatively delivered to the spinning assembly by a metering pump and extruded to form nascent fibers. During the multi-stage stretching process of the nascent fibers, a hot and cold cycle treatment is adopted to obtain antibacterial spandex fiber finished product. Among them, the manufacturing process parameter combination is determined by multi-scale control based on the gradient ratio of dispersant and coupling agent, combined with the mixing and stirring index and ultrasonic dispersion index, and in conjunction with the synergistic optimization of the segmented temperature control parameters and multi-level stretching parameters. The fiber performance requirements include fiber antibacterial rate and mechanical strength; Establish a database relating the gradient ratios of dispersants and coupling agents to the fiber performance requirements, determine multiple gradient ratio ranges, and perform response surface optimization based on these multiple gradient ratio ranges. The response surface optimization based on the multi-gradient ratio range includes: Using dispersant concentration and coupling agent concentration as core variables, the effective variable range is selected based on the boundary conditions of the associated database. Based on the effective variable range, the interaction effect term and the quadratic term are configured, and the fiber performance response surface is generated by referring to the multi-gradient ratio range.

2. The optimized manufacturing process method for antibacterial spandex fiber as described in claim 1, characterized in that, The interaction effect term includes a first interaction effect term and a second interaction effect term; Based on the dispersant concentration and the mixing speed of the mixing index, the first interaction effect term under the coupling effect between parameters is determined; Based on the coupling agent concentration and the ultrasonic dispersion time of the ultrasonic dispersion index, the second interaction effect term under the coupling effect between parameters is determined.

3. The optimized manufacturing process method for antibacterial spandex fiber as described in claim 2, characterized in that, Based on the gradient ratio of dispersant and coupling agent, and combined with the mixing and stirring index and ultrasonic dispersion index, multi-scale control is performed. The method includes: Substituting the interaction effect term and the quadratic term into the fiber performance response surface, a multivariate nonlinear model is constructed that includes dispersant concentration, coupling agent concentration, mixing speed, and ultrasonic dispersion time. The multivariate nonlinear model is globally optimized by using crossover and mutation operations to iterate the predicted fiber antibacterial rate and mechanical strength under different combinations of variables. During the optimization process, an objective function is formulated based on the predicted antibacterial rate and mechanical strength of the fiber, and a set of multi-scale control parameters is determined.

4. The optimized manufacturing process of antibacterial spandex fiber as described in claim 3, characterized in that, In conjunction with the synergistic optimization of the segmented temperature control parameters and multi-stage tensile parameters, the method for determining the combination of manufacturing process parameters includes: Link the twin-screw extruder, collect historical temperature data of each heating section and corresponding material melting state images, and use a convolutional neural network to extract the temperature-melting state feature mapping relationship; Based on the temperature-melting state characteristic mapping relationship, and combined with the thermal stability parameters of antibacterial masterbatch and spandex chips, temperature control constraints are constructed. The segmented temperature control parameters are determined by searching under the temperature regulation constraints.

5. The optimized manufacturing process method for antibacterial spandex fiber as described in claim 4, characterized in that, The method includes: The molecular orientation and stress-strain parameters of the nascent fiber during the stretching process are established, and the stretch ratio range is determined in combination with the target mechanical property requirements of antibacterial spandex fiber. The temperature change gradient of the hot and cold cycle, the number of cycles, and the dwell time in each temperature range are set as optimization variables to formulate an orthogonal test scenario. By using the fiber breaking strength and breaking elongation under the orthogonal test scenario, synergistic optimization is performed within the tensile ratio range to determine the combination of manufacturing process parameters.

6. The optimized manufacturing process method for antibacterial spandex fiber as described in claim 1, characterized in that, The method further includes: A digital twin model related to the manufacturing process of antibacterial spandex fiber was constructed, and the manufacturing process parameters were uploaded for simulation verification. Meanwhile, data on the fluctuation of fiber quality indicators during the simulation process were collected to identify key parameters affecting the quality stability of antibacterial spandex fiber finished products. A dynamic compensation mechanism is set up to adaptively adjust the key parameters according to the equipment operating status and environmental changes.

7. The optimized manufacturing process of antibacterial spandex fiber as described in claim 6, characterized in that, The method includes: A fiber surface defect detection unit under machine vision was established, and the YOLO model was trained to identify defects in finished antibacterial spandex fibers, including surface holes and uneven thickness. The defect identification information of the antibacterial spandex fiber finished product is correlated with the key parameters to construct a defect source fault tree; The aforementioned defect tracing fault tree is used to locate and mark defects in finished antibacterial spandex fiber products.

8. A manufacturing process optimization system for antibacterial spandex fiber, characterized in that, A method for optimizing the manufacturing process of an antibacterial spandex fiber according to any one of claims 1-7, the system comprising: The gradient ratio mixing module is used to add dispersants and coupling agents in a gradient ratio according to the fiber performance requirements of antibacterial spandex fiber raw materials, and to set the mixing and stirring index and ultrasonic dispersion index. The drying module is used to dry the antibacterial masterbatch and spandex chips prepared with the mixing and stirring index and ultrasonic dispersion index in a vacuum environment. After that, the chips are fed into a twin-screw extruder according to a preset ratio and segmented temperature control parameters are set. The recycling module is used to quantitatively transport the melted and blended material to the spinning assembly via a metering pump, and extrude it to form nascent fibers. During the multi-stage stretching process of the nascent fibers, a hot and cold cycle treatment is adopted to obtain antibacterial spandex fiber finished product. The collaborative optimization module is used to determine the combination of manufacturing process parameters by performing multi-scale control based on the gradient ratio of dispersant and coupling agent, combined with the mixing and stirring index and ultrasonic dispersion index, and in conjunction with the collaborative optimization of the segmented temperature control parameters and multi-level stretching parameters.

Images