Spinning parameter adjusting method and platform for anti-wrinkle soft covering yarn

Abstract

The invention provides a spinning parameter adjusting method and platform for anti-wrinkle soft covering yarn, and relates to the technical field of spinning parameter adjusting.The spinning parameter adjusting method comprises the steps that application scene information of target covering yarn is obtained, multi-dimensional demand analysis is conducted, and spinning demand parameters, including anti-wrinkle demand parameters and softness demand parameters, of the covering yarn are obtained; performing fiber parameter configuration to establish a target yarn structure; a core spun yarn spinning process database is connected, spinning data mining is carried out, and a spinning process control space is constructed; taking the core spun yarn spinning demand parameters as optimization constraint conditions, performing optimization analysis in the spinning process control space, and determining target spinning control parameters; and quality feedback optimization is carried out, optimized spinning control parameters are obtained, and spinning control is carried out. The technical problems that in the core spun yarn production process in the prior art, selection of spinning parameters generally depends on experience, refined spinning process control is difficult to conduct according to specific application requirements, and the final product quality is poor are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of spinning parameter adjustment, and particularly to a method and platform for adjusting spinning parameters for anti-wrinkle and soft core-spun yarns. Background Art

[0002] In the production process of core-spun yarns, anti-wrinkle property and softness are two key performance indicators affecting the quality of the yarn. The anti-wrinkle property determines whether the yarn is prone to wrinkles during use, while the softness determines the comfort and usage experience of the yarn. With the increasing requirements of consumers for the comfort and durability of textiles, the market demand for anti-wrinkle and soft core-spun yarns is increasing.

[0003] However, there are still several technical problems in the existing spinning technology when dealing with the balance between anti-wrinkle property and softness. In the traditional production process of core-spun yarns, the selection of spinning parameters usually depends on experience, and it is difficult to achieve refined control of the spinning process according to specific application requirements. The requirements for anti-wrinkle property and softness are often contradictory, and adjusting one performance may affect the other. In the existing technology, core-spun yarns that meet the basic requirements can usually be produced only under certain fixed parameter combinations, lacking a systematic method for precisely optimizing various performances. Summary of the Invention

[0004] The present application provides a method and platform for adjusting spinning parameters for anti-wrinkle and soft core-spun yarns, aiming to solve the technical problem that in the production process of core-spun yarns in the existing technology, the selection of spinning parameters usually depends on experience, and it is difficult to perform refined control of the spinning process according to specific application requirements, resulting in poor quality of the final product.

[0005] In the first aspect disclosed by the present application, a method for adjusting spinning parameters for anti-wrinkle and soft core-spun yarns is provided. The method includes: obtaining application scenario information of the target core-spun yarn, performing multi-dimensional requirement analysis on the application scenario information to obtain core-spun yarn spinning requirement parameters, where the core-spun yarn spinning requirement parameters include anti-wrinkle property requirement parameters and softness requirement parameters; according to the core-spun yarn spinning requirement parameters, configuring fiber parameters of the core fiber and outer fiber of the yarn to establish a target yarn structure; connecting to a core-spun yarn spinning process database, and based on the target yarn structure, performing spinning data mining in the core-spun yarn spinning process database to construct a spinning process control space, where the core-spun yarn spinning process database includes a set of historical spinning control parameters and corresponding historical spinning effect sets within a preset time window; using the core-spun yarn spinning requirement parameters as optimization constraint conditions, performing optimization analysis in the spinning process control space to determine target spinning control parameters; performing quality feedback optimization on the target spinning control parameters to obtain optimized spinning control parameters, and using the optimized spinning control parameters to control the spinning of the target core-spun yarn.

[0006] The second aspect disclosed in this application provides a spinning parameter adjustment platform for anti-wrinkle soft core-spun yarn. The platform is used for the above-mentioned spinning parameter adjustment method for anti-wrinkle soft core-spun yarn. The platform includes: a multi-dimensional demand analysis module, which is used to obtain the application scenario information of the target core-spun yarn, conduct multi-dimensional demand analysis on the application scenario information, and obtain the core-spun yarn spinning demand parameters. Among them, the core-spun yarn spinning demand parameters include anti-wrinkle demand parameters and softness demand parameters; a fiber parameter configuration module, which is used to configure the fiber parameters of the core fiber and the outer fiber of the yarn according to the core-spun yarn spinning demand parameters, and establish the target yarn structure; a spinning data mining module, which is used to connect to the core-spun yarn spinning process database, and based on the target yarn structure, conduct spinning data mining in the core-spun yarn spinning process database to construct a spinning process control space. Among them, the core-spun yarn spinning process database includes a set of historical spinning control parameters and a corresponding set of historical spinning effects within a preset time window; an optimization analysis module, which is used to conduct optimization analysis in the spinning process control space with the core-spun yarn spinning demand parameters as the optimization constraint conditions to determine the target spinning control parameters; a spinning control module, which is used to conduct quality feedback optimization on the target spinning control parameters to obtain optimized spinning control parameters, and conduct spinning control of the target core-spun yarn with the optimized spinning control parameters.

[0007] One or more technical solutions provided in this application have at least the following beneficial effects: By obtaining the application scenario information of the target core-spun yarn and conducting multi-dimensional requirement analysis, the specific usage requirements of the yarn can be clarified, including wrinkle resistance and softness. This requirement analysis ensures that the parameters used in the spinning process can accurately match the usage requirements of the final product, avoiding deviations between the spinning parameters and the actual requirements. Based on the spinning requirement parameters obtained from the analysis, the core fibers and outer fibers of the yarn are precisely configured, and then the target yarn structure is established, realizing the customized design of the yarn structure, so that the produced core-spun yarn can better meet the requirements of wrinkle resistance and softness. By connecting to the core-spun yarn spinning process database and conducting spinning data mining based on the target yarn structure, the spinning control parameters related to the target yarn structure are extracted from the historical spinning data. This process uses historical data to provide guidance for the current spinning process, reducing the costs of experimentation and adjustment, and helping to quickly identify effective combinations of control parameters through data mining, making the control process of the spinning process more accurate and efficient. Taking the spinning requirement parameters of the core-spun yarn as the optimization constraint conditions, optimization analysis is carried out within the spinning process control space. Through the optimization analysis of multi-dimensional parameters, the most suitable spinning control parameters can be determined, and the spinning process is controlled according to the obtained spinning control parameters, maximizing the satisfaction of key requirements such as wrinkle resistance and softness. This ensures that the performance of the yarn can meet the expected goals and reduces the time and costs of multiple adjustments and experiments. The target spinning control parameters are adjusted in real time through the quality feedback optimization mechanism. Through the quality testing of the finished yarn during the production process, potential problems in the spinning process can be immediately diagnosed, and then the control parameters are adjusted to optimize the quality of the final product. This feedback optimization mechanism enhances the adaptability and flexibility of production, ensuring that it can respond and adjust in a timely manner during the production process and continuously improving the quality of the core-spun yarn.

[0008] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. Brief Description of the Drawings

[0009] Figure 1 It is a schematic flow chart of the method for adjusting the spinning parameters of the anti-wrinkle and soft core-spun yarn provided by the embodiment of this application.

[0010] Figure 2 It is a schematic structural diagram of the platform for adjusting the spinning parameters of the anti-wrinkle and soft core-spun yarn provided by the embodiment of this application.

[0011] Description of the reference numerals: Multi-dimensional requirement analysis module 10, fiber parameter configuration module 20, spinning data mining module 30, optimization analysis module 40, spinning control module 50. Detailed Description of the Embodiments

[0012] In the embodiments of the present application, by providing a method and platform for adjusting the spinning parameters of anti-wrinkle soft core-spun yarns, the technical problem in the prior art during the production of core-spun yarns is solved, where the selection of spinning parameters usually depends on experience, and it is difficult to carry out refined control of the spinning process according to specific application requirements, resulting in poor quality of the final product.

[0013] After introducing the basic principle of the present application, various non-limiting embodiments of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Example 1, as Figure 1 shown, the embodiments of the present application provide a method for adjusting the spinning parameters of anti-wrinkle soft core-spun yarns, and the method includes: Obtain the application scenario information of the target core-spun yarn, conduct a multi-dimensional requirement analysis on the application scenario information, and obtain the spinning requirement parameters of the core-spun yarn. Among them, the spinning requirement parameters of the core-spun yarn include anti-wrinkle requirement parameters and softness requirement parameters.

[0015] Obtaining the application scenario information of the target core-spun yarn includes obtaining the application field of the target core-spun yarn. The target core-spun yarn can be applied to different textile fields, such as clothing, household items, industrial fabrics, etc., and the requirements for core-spun yarns in each field are different; obtaining the usage environment of the target core-spun yarn, such as whether it needs to be high-temperature resistant, wash-resistant, etc.; obtaining the consumer requirements of the target core-spun yarn, for example, analyzing the specific requirements of consumers for the comfort, durability, etc. of textiles.

[0016] Conducting a multi-dimensional requirement analysis on the application scenario information includes anti-wrinkle requirement analysis and softness requirement analysis. Among them, anti-wrinkle refers to the ability of the yarn to effectively reduce or prevent the generation of wrinkles during use and maintain the flatness of the fabric. By analyzing the specific requirements for anti-wrinkle in the target application, for example, whether the clothing needs to be anti-wrinkle, the anti-wrinkle requirement parameters of the core-spun yarn are determined. The anti-wrinkle requirement parameters include factors such as the resilience of the yarn, the buckling degree of the fiber, and the spinning density, which will all affect the anti-wrinkle ability of the final fabric; softness refers to the comfort and feel of the core-spun yarn, which is usually related to the fiber structure, spinning process, etc. Consumers may require the textiles to be soft and comfortable in touch, especially in close-fitting clothing or household items. The softness can be quantified through physical tests, such as using standards such as elasticity and friction to evaluate the softness.

[0017] According to the spinning requirement parameters of the core-spun yarn, configure the fiber parameters of the core fiber and the outer fiber of the yarn, and establish the target yarn structure.

[0018] The core fiber is the central part of the core-spun yarn, providing the strength and toughness of the yarn. For higher wrinkle resistance requirement parameters, stronger and more elastic fiber materials (such as polyester, nylon, etc.) are selected. For softness requirements, softer and more comfortable fibers (such as cotton fiber or fine polyester) are chosen; the outer layer fiber wraps around the core fiber and mainly affects the touch and appearance of the yarn. The softness requirement determines the choice of the outer layer fiber. Common choices include natural fibers such as cotton and wool, or synthetic fibers such as polyester and nylon. The specific choice needs to be determined based on the softness requirement.

[0019] According to the above information, the parameter configuration of the core fiber of the yarn is carried out. Among them, the thickness, strength, elasticity, thermal stability, etc. of the core fiber are set according to the requirements of wrinkle resistance and softness; the parameter configuration of the outer layer fiber of the yarn is carried out. Among them, the fiber fineness, curvature, softness, etc. of the outer layer fiber are set according to the softness requirement. After configuring the fiber parameters of the core fiber and the outer layer fiber, a target yarn structure is established, including fiber parameters, the arrangement method of the core fiber, the wrapping method of the outer layer fiber, etc. Through these configurations, a yarn structure that meets the requirements of wrinkle resistance and softness can be obtained, which serves as the basis for subsequent process design.

[0020] Connect to the core-spun yarn spinning process database. Based on the target yarn structure, carry out spinning data mining in the core-spun yarn spinning process database to construct a spinning process control space. Among them, the core-spun yarn spinning process database includes a set of historical spinning control parameters and a corresponding set of historical spinning effects within a preset time window.

[0021] Connect to the core-spun yarn spinning process database. The core-spun yarn spinning process database contains a large amount of data in the historical spinning process. These data include various control parameters and corresponding spinning effects. When constructing the spinning process control space, connect to the database and query these data. These data come from the spinning process in the past period of time.

[0022] According to the target yarn structure, through data mining technology, analyze the historical data, and extract the key control parameters that affect the spinning effect, including spinning temperature, speed, tension, etc. These historical data include a set of historical spinning control parameters and a corresponding set of historical spinning effects, which will provide a reference for subsequent optimization. Among them, the set of historical spinning control parameters includes operating parameters such as the rotation speed of the spinning machine, spinning tension, and spinning temperature. The set of historical spinning effects is used to analyze the influence of different spinning control parameters on the yarn, such as wrinkle resistance, softness, strength, etc.

[0023] Taking the core-spun yarn spinning requirement parameters as the optimization constraint conditions, carry out optimization analysis in the spinning process control space to determine the target spinning control parameters.

[0024] Set evaluation indicators for spinning effect according to the requirements parameters of core-spun yarn spinning, such as wrinkle resistance, softness, etc. Optimize the indicators of these performances as the optimization constraints. Extract multiple spinning effect evaluation indicators from historical data. These indicators include wrinkle resistance, softness, strength, curvature, etc. Together, they constitute the criteria for evaluating yarn performance. Extract and quantify these indicators so as to evaluate different combinations of control parameters through a mathematical model. Based on the set of spinning effect evaluation indicators, perform function fitting on historical data to establish a fitness function, which can quantify the relationship between spinning control parameters and spinning effect. Through global optimization algorithms, such as particle swarm optimization, genetic algorithm, etc., conduct a comprehensive search within the spinning process control space to find a combination of control parameters that can maximize the spinning effect. Use the fitness function to evaluate the effect of each group of candidate parameter combinations, and find the set of control parameters that can best meet the spinning requirements as the target spinning control parameters.

[0025] Conduct quality feedback optimization on the target spinning control parameters to obtain optimized spinning control parameters, and use the optimized spinning control parameters to control the spinning of the target core-spun yarn.

[0026] Use the determined target spinning control parameters to carry out actual spinning production of core-spun yarn. Produce by implementing these control parameters on a spinning machine to obtain a preliminary finished core-spun yarn. Conduct a wrinkle resistance test on the finished core-spun yarn to evaluate whether it meets the standard of wrinkle resistance requirement parameters. For example, test the yarn under simulated daily use or washing conditions to check the degree of wrinkles generated; conduct a softness test on the finished product to check whether it meets the softness requirement, such as through physical tests like touch test, bending test, etc.

[0027] If the test results show that the wrinkle resistance or softness of the yarn does not meet the expected standard, conduct data diagnosis. By analyzing the test data, identify problems existing in the spinning process, such as too high tension, too fast spinning speed, etc. According to the diagnosis results, make appropriate adjustments to the spinning control parameters. For example, adjust the rotation speed, tension, temperature, etc. of the spinning machine, re-spin and conduct tests until the expected wrinkle resistance and softness requirements are met. After continuous optimization and meeting the quality standards, finally obtain a set of optimized spinning control parameters, and continue to use the optimized spinning control parameters in subsequent spinning processes to ensure that the quality of core-spun yarn in mass production meets the expectations.

[0028] Furthermore, connect to the core-spun yarn spinning process database, and based on the target yarn structure, conduct spinning data mining within the core-spun yarn spinning process database to construct a spinning process control space. The method includes: Extract the first spinning process data from the core-spun yarn spinning process database; perform feature analysis on the first yarn structure of the first spinning process data to obtain the first yarn structure feature set; perform feature analysis on the target yarn structure to obtain the target yarn structure feature set; perform similarity analysis on the first yarn structure feature set and the target yarn structure feature set to obtain the first yarn structure similarity coefficient; if the first yarn structure similarity coefficient meets the yarn structure similarity coefficient threshold, add the first historical spinning control parameters and the corresponding first historical spinning effect of the first spinning process data to the spinning process control space.

[0029] Randomly extract an analysis object from the core-spun yarn spinning process database as the first spinning process data. By randomly extracting the first spinning process data, the entire database can be traversed to avoid selection bias.

[0030] The first yarn structure includes parameter configurations, arrangement methods, etc. of the core fiber and the outer fiber. Analyze these structural features to extract key factors affecting yarn performance. For example, the type of core fiber, the material of the outer fiber, the thickness of the yarn, the twist, the arrangement method of the fiber, etc. all belong to the characteristics of the yarn structure. According to the above analysis, the first yarn structure feature set is obtained for subsequent analysis and comparison.

[0031] Similar to the first yarn structure, the target yarn structure also contains parameters of the core fiber and the outer fiber. For example, the target yarn may include a higher proportion of fibers with stronger softness, or the core fiber has better wrinkle resistance. Through the structural analysis of the target yarn, the corresponding feature set of the first yarn structure is extracted to form the target yarn structure feature set. These features are used for similarity analysis and final process optimization in the subsequent steps.

[0032] By comparing the first yarn structure feature set and the target yarn structure feature set, analyze the similarity between the two structures. For example, use the Pearson correlation coefficient. Calculate the Pearson correlation coefficient of the two sets of features to measure their linear correlation. A correlation coefficient close to +1 indicates a high similarity between the two, close to -1 indicates they are opposite, and close to 0 indicates no correlation. According to the similarity index calculated by the above method, the first yarn structure similarity coefficient is formed. The larger the similarity coefficient value, the closer the first yarn structure is to the target yarn structure.

[0033] Preset a similarity coefficient threshold in advance. Only when the yarn structure similarity coefficient exceeds this threshold can the corresponding data be included in the analysis. The setting of this threshold is usually based on experience or experimental data, aiming to ensure that only highly similar yarn structures are used for subsequent process optimization.

[0034] If the similarity coefficient of the first yarn structure is greater than the set threshold, it indicates that the similarity between the first yarn structure and the target yarn structure is relatively high, and it can be regarded as a suitable candidate structure. Under the condition of meeting the similarity threshold, the first spinning process data (including control parameters and corresponding historical effects) is added to the spinning process control space. The purpose of doing this is to use past successful experiences as potential optimization solutions and provide reference data for subsequent process optimization.

[0035] Furthermore, the similarity analysis of the first yarn structure feature set and the target yarn structure feature set to obtain the similarity coefficient of the first yarn structure includes: Obtain a preset label scheme; based on the preset label scheme, label the first yarn structure feature set to obtain a first label vector; based on the preset label scheme, label the target yarn structure feature set to obtain a target label vector; obtain the similarity coefficient of the first yarn structure according to the Pearson correlation coefficient between the first label vector and the target label vector.

[0036] Obtain a preset label scheme. The preset label scheme provides a framework for subsequent feature marking and similarity analysis. The scheme includes label types, feature classifications, and label assignment rules. Specifically, the label scheme usually consists of different types of labels, and each label represents a specific yarn structure feature. For example, labels include fiber type, twist, fiber fineness, arrangement method, etc.; each feature is divided into different categories according to its importance or influence in the yarn structure. For example, twist and fiber type can be regarded as structural features, while softness and wrinkle resistance can be regarded as performance features; for each feature, there are specific assignment rules. For example, the fineness of the fiber can be marked as fine, medium, or coarse through a numerical range, and the twist can be marked as low, medium, or high.

[0037] According to the preset label scheme, each feature in the first yarn structure feature set is marked as the corresponding label, and each yarn structure feature will be converted into a label value to form a label vector. Specifically, according to the parameters of the first yarn structure, such as fiber type, twist, arrangement method, etc., each feature is analyzed. For each analyzed feature, referring to the preset label scheme, a suitable label is selected and marked to form a multi-dimensional first label vector.

[0038] Similar to the first yarn structure feature set, the target yarn structure feature set is labeled to obtain a target label vector.

[0039] The Pearson correlation coefficient is used to calculate the similarity between the first label vector and the target label vector. The Pearson correlation coefficient is a statistical method for measuring the linear relationship between two sets of data. The value of the Pearson correlation coefficient serves as the first yarn structure similarity coefficient between the first yarn structure and the target yarn structure. The value ranges from -1 to +1. The closer it is to +1, the more similar the two are; the closer it is to -1, the greater the difference between the two.

[0040] Furthermore, with the core-spun yarn spinning requirement parameters as the optimization constraint conditions, an optimization analysis is carried out within the spinning process control space to determine the target spinning control parameters. The method includes: Based on the historical spinning effect set, extraction of spinning effect evaluation indicators is carried out to obtain a spinning effect evaluation indicator set; based on the spinning effect evaluation indicator set, function fitting is carried out to establish a spinning effect evaluation fitness function; with the core-spun yarn spinning requirement parameters as the optimization constraint conditions, global iterative optimization is carried out within the spinning process control space, and spinning effect evaluation and comparison are carried out through the spinning effect evaluation fitness function to determine the target spinning control parameters.

[0041] From the historical spinning effect set, performance data related to the spinning effect is collected. These data include the performance of the yarn in terms of wrinkle resistance, softness, strength, comfort, etc. Through the analysis of the historical spinning effects, the core evaluation indicators reflecting the yarn quality are extracted to obtain a spinning effect evaluation indicator set. These evaluation indicators not only reflect the comprehensive performance of the yarn but also provide a basis for optimizing the spinning control parameters.

[0042] Using the spinning effect evaluation indicator set and the corresponding spinning control parameters in the historical spinning dataset as the input data for function fitting, a suitable mathematical model is selected for fitting according to the actual situation. Common fitting methods include linear regression, non-linear regression, as well as support vector machines, decision trees, etc., for dealing with more complex non-linear relationships. The selected model is used to fit the historical data to establish a spinning effect evaluation fitness function. This fitness function models the relationship between the control parameters and the effect evaluation indicators, thus providing accurate predictions and being able to predict the spinning effect of the yarn through the input control parameters.

[0043] Determine the optimization objective, that is, optimize the control parameters of the spinning process (such as spinning speed, tension, temperature, etc.) according to the spinning requirement parameters of the core-spun yarn (such as wrinkle resistance, softness, etc.) so that the performance of the yarn meets the expectations. Use global optimization algorithms, such as genetic algorithms, particle swarm optimization, etc., to perform global optimal search in the spinning process control space, find a set of global optimal control parameter sets, and further perform local optimal search within the global optimal control parameter sets. In each iteration, use the fitness function to evaluate the current control parameter combination to obtain the corresponding spinning effect, compare the spinning effects under different control parameters, and select the control parameters that are closest to the spinning requirement parameters of the core-spun yarn. After multiple iterations, determine the target spinning control parameters, which can maximize the satisfaction of the requirements such as wrinkle resistance and softness of the core-spun yarn.

[0044] Furthermore, the method for determining the target spinning control parameters includes: Obtain the global search step size, perform global parameter search in the spinning process control space according to the global search step size to obtain a set of global spinning process control parameters; evaluate the set of global spinning process control parameters based on the spinning effect evaluation fitness function to obtain a set of global spinning effect evaluation fitness; sort the set of global spinning effect evaluation fitness in descending order, and obtain the optimal global spinning process control parameters corresponding to the maximum global spinning effect evaluation fitness based on the descending order result; obtain the local search step size, combine the local search step size and the spinning effect evaluation fitness function, and perform local parameter search based on the global spinning process control parameters until the preset number of iterations is reached, and output the target spinning control parameters.

[0045] The global search step size refers to the amplitude of adjusting the control parameters in each step of the optimization process. In global optimization, when the search step size is large, the parameter space covered by the search process is relatively wide, but it may not be fine enough; when the search step size is small, the search process is more detailed, but it may miss the optimization opportunities in a larger range. In the initial stage, usually a larger search step size is selected and refined step by step.

[0046] Based on the global search step size, perform global parameter search in the spinning process control space. The spinning process control space includes the value ranges of various control parameters, such as temperature, tension, spinning speed, etc. Each control parameter represents a solution. The search process attempts to find the parameters that can best meet the requirements of the target yarn by analyzing different control parameters. In the global search process, generate a set of candidate global spinning process control parameter sets, and each control parameter in this set will be used as a candidate solution for further evaluation and optimization.

[0047] For each set of spinning process control parameters obtained from the global search, a fitness function is used for evaluation. The fitness function will predict indexes such as the wrinkle resistance, softness, and strength of the yarn based on the input control parameters (such as spinning speed, tension, etc.). After evaluation, an effect evaluation value corresponding to each control parameter is output. This value reflects the quality of the yarn performance under this control parameter. Generally speaking, the higher the effect evaluation fitness value, the better the yarn performance and the better it can meet the target requirements. Integrate the evaluation results of all global control parameter sets into a fitness set. This set contains the fitness values corresponding to each set of control parameters and can help determine which control parameters are more superior.

[0048] Arrange the fitness values corresponding to all global spinning process control parameter sets in descending order, that is, arrange them from high to low according to the fitness values. The purpose is to find the control parameter combination with the best fitness. The higher the fitness value, the better the control parameter can meet the target requirements. After sorting, select the global control parameter with the highest fitness value as the preliminary optimal solution for local search in subsequent optimization.

[0049] The local search step size refers to the amplitude of adjusting the control parameter each time during local optimization. The local search step size is usually smaller than the global search step size, aiming at fine-tuning to further optimize the control parameter. By setting the local search step size, it is possible to avoid searching a too large parameter space and thus focus more on the area around the global optimal solution.

[0050] Based on the global optimal solution, finely adjust the global spinning process control parameters through local search. The goal of local search is to further improve the fitness of the global control parameter, finely optimize, and find the optimal control parameter. Specifically, based on the preliminary optimal solution, adjust one or more control parameters, such as temperature, tension, spinning speed, etc., and use the fitness function to evaluate the new control parameter combination. Through local adjustment, it is expected to find a control parameter combination that is better than the current solution. The local search process will continue until the preset number of iterations is reached. The setting of the number of iterations is usually to balance the search depth and calculation time. After local search is completed, output the finally optimized target spinning control parameter. This parameter is the optimal combination obtained through global search and local adjustment and can best meet the performance requirements of the core-spun yarn and will be used in the actual spinning process.

[0051] Furthermore, for quality feedback optimization of the target spinning control parameter to obtain an optimized spinning control parameter, the method includes: Based on the target spinning control parameters, carry out the spinning process of the target core-spun yarn to obtain the finished core-spun yarn; based on the wrinkle resistance requirement parameters and softness requirement parameters, generate wrinkle resistance test indicators and softness test indicators; based on the wrinkle resistance test indicators and softness test indicators, conduct a spinning effect test on the finished core-spun yarn. When the test result does not meet the required effect, conduct test data diagnosis, and optimize the target spinning control parameters according to the diagnosis result to obtain optimized spinning control parameters.

[0052] Apply the target spinning control parameters to the actual production process, input them into the spinning machine to adjust the machine settings, and conduct the actual processing of the core-spun yarn. Through the spinning process, finally obtain the finished core-spun yarn, and the performance of this finished core-spun yarn is close to the preset wrinkle resistance and softness requirements.

[0053] According to the wrinkle resistance requirement parameters, determine the appropriate test standards. For example, certain test conditions can be set, such as multiple washes, compression, bending, etc., and by measuring indicators such as the generation of wrinkles and the flatness of the yarn surface, evaluate the wrinkle resistance. The generated wrinkle resistance test indicators include wrinkle recovery rate, post-washing wrinkle resistance, etc.; according to the softness requirement parameters, determine the softness test standards. For example, evaluate the softness of the yarn through touch tests, flexibility tests or bending tests. The finally generated wrinkle resistance and softness test indicators are used for subsequent evaluation and inspection of the finished core-spun yarn.

[0054] Apply the generated wrinkle resistance test indicators and softness test indicators to the finished core-spun yarn for actual tests. For example, conduct wrinkle recovery tests after multiple washes and physical tests on softness such as bending degree and hand feel, and check whether the wrinkle resistance and softness of the finished core-spun yarn meet the required effects. If the test results show that the performance of the finished core-spun yarn does not reach the expected target, further optimization is required.

[0055] If the test result does not meet the requirements, conduct test data diagnosis. Data diagnosis and analysis can help identify the specific parameters that cause problems. Specifically, determine which control parameters in the spinning process, such as temperature, tension, spinning speed, etc., have an adverse impact on wrinkle resistance and softness, and analyze whether structural parameters such as specific fiber types, twist, and yarn density need to be adjusted. According to the test data diagnosis results, adjust the target spinning control parameters. For example, reduce the spinning speed, adjust the tension or change the temperature setting of the spinning machine. By optimizing the control parameters, the wrinkle resistance and softness of the finished core-spun yarn reach the expected standards. After optimization and adjustment, the new spinning control parameters form optimized spinning control parameters for subsequent spinning processes.

[0056] Furthermore, the method further includes: Configure a wrinkle detection device, where the wrinkle detection device includes an image sensor for traversing image acquisition; acquire the image of the finished core-spun yarn through the image sensor to obtain an image acquisition result; establish a reference pixel gray value, compare the pixel gray values of the image acquisition result based on the reference pixel gray value, and obtain a wrinkle area set according to the comparison result; perform wrinkle statistics based on the wrinkle area set and record the wrinkle data set; perform common clustering on the position and features of the wrinkle data set to generate a common clustering result; perform feedback tuning of the target spinning control parameters based on the common clustering result.

[0057] Configure a wrinkle detection device that can detect the wrinkles of the finished core-spun yarn through image acquisition. Specifically, it includes an image sensor for traversing image acquisition. The image sensor should have sufficient accuracy to clearly identify the wrinkles on the surface of the yarn. Common types of image sensors include CCD (Charge Coupled Device) and CMOS (Complementary Metal Oxide Semiconductor) sensors. Install the image sensor above the surface of the finished core-spun yarn to ensure that it can cover the entire surface area of the yarn. The image sensor should be able to perform traversing image acquisition, that is, gradually capture the image information of each part of the surface of the finished core-spun yarn, so as to perform comprehensive wrinkle detection.

[0058] Start the image sensor to scan the surface of the finished core-spun yarn and collect image data in real time. Each image includes the entire surface of the yarn, and the wrinkle area on the surface of the yarn should be clearly shown in the image as the basis for subsequent analysis.

[0059] Establish a reference pixel gray value for use as a reference for wrinkle detection in image processing. The reference gray value is usually calculated from the pixel gray values of the flat parts on the surface of the yarn. These areas should have no wrinkles. By statistically analyzing the pixel values in the flat areas of the image, a range of reference pixel gray values is calculated, and this range represents the normal state of the surface of the yarn.

[0060] Compare the pixel gray values of each image with the reference gray value and analyze the deviation of the pixel gray values. Among them, the wrinkle area usually shows a change in gray value because the wrinkle will change the reflection of light, resulting in fluctuations in the gray value in the image. By comparison, it can be determined whether these changes belong to the wrinkle area. According to the result of the pixel gray value comparison, extract the wrinkle area from the image and form a wrinkle area set to provide a basis for subsequent quality analysis and adjustment.

[0061] Count each area in the wrinkle area set to obtain the total number of wrinkles that appear, including the area, shape, distribution density, etc. of the wrinkle area, and generate a detailed wrinkle data set to provide information for subsequent clustering analysis and adjustment.

[0062] According to the information in the wrinkle dataset, select the features suitable for clustering analysis, including position features, size features, shape features, etc. Use clustering algorithms to analyze the wrinkle data. For example, adopt K-means clustering to divide the data points into k groups, and the data points in each group have similar features. According to the clustering results, the wrinkle regions in each cluster obtained have similar features such as position, size, or shape, which helps to analyze which spinning parameters lead to these common wrinkles.

[0063] Analyze the results of the commonality clustering, and identify which control parameters may lead to specific types of wrinkles. For example, certain wrinkles with specific shapes or positions may be related to factors such as too fast spinning speed and uneven tension. According to the features of different clusters, find the relationship between specific types of wrinkles and control parameters. According to the clustering analysis results, feedback and optimize the spinning control parameters. By adjusting the control parameters that affect wrinkle formation, improve the yarn quality and avoid or reduce the generation of wrinkles.

[0064] In summary, the spinning parameter adjustment method for anti-wrinkle soft core-spun yarn provided by the embodiments of the present application has the following technical effects: By obtaining the application scenario information of the target core-spun yarn and conducting multi-dimensional requirement analysis, the specific usage requirements of the yarn can be clarified, including wrinkle resistance and softness. This requirement analysis ensures that the parameters used in the spinning process can accurately match the usage requirements of the final product, avoiding deviations between the spinning parameters and the actual requirements. Based on the spinning requirement parameters obtained from the analysis, the core fibers and outer fibers of the yarn are precisely configured, and then the target yarn structure is established, realizing the customized design of the yarn structure, so that the produced core-spun yarn can better meet the requirements of wrinkle resistance and softness. By connecting to the core-spun yarn spinning process database and conducting spinning data mining based on the target yarn structure, the spinning control parameters related to the target yarn structure are extracted from the historical spinning data. This process uses historical data to provide guidance for the current spinning process, reducing the costs of experimentation and adjustment, and helping to quickly identify effective combinations of control parameters through data mining, making the adjustment of the spinning process more accurate and efficient. Taking the spinning requirement parameters of the core-spun yarn as the optimization constraint conditions, optimization analysis is carried out within the spinning process control space. Through the optimization analysis of multi-dimensional parameters, the most suitable spinning control parameters can be determined to maximize the satisfaction of key requirements such as wrinkle resistance and softness, ensuring that the performance of the yarn can meet the expected goals and reducing the time and costs of multiple adjustments and experiments. The target spinning control parameters are adjusted in real time through the quality feedback optimization mechanism. By testing the quality of the finished yarn during the production process, potential problems in the spinning process can be diagnosed immediately, and then the control parameters can be adjusted to optimize the quality of the final product. This feedback optimization mechanism enhances the adaptability and flexibility of production, ensuring that timely responses and adjustments can be made during the production process to continuously improve the quality of the core-spun yarn.

[0065] Embodiment 2. Based on the same inventive concept as the method for adjusting the spinning parameters of the wrinkle-resistant and soft core-spun yarn in the foregoing embodiment, as Figure 2 shown, the embodiment of the present application provides a platform for adjusting the spinning parameters of the wrinkle-resistant and soft core-spun yarn, and the platform includes: The multi-dimensional requirement analysis module 10 is used to obtain the application scenario information of the target core-spun yarn, conduct multi-dimensional requirement analysis on the application scenario information, and obtain the core-spun yarn spinning requirement parameters. Among them, the core-spun yarn spinning requirement parameters include wrinkle resistance requirement parameters and softness requirement parameters. The fiber parameter configuration module 20 is used to configure the fiber parameters of the core fiber and the outer fiber of the yarn according to the core-spun yarn spinning requirement parameters, and establish the target yarn structure. The spinning data mining module 30 is used to connect to the core-spun yarn spinning process database, and based on the target yarn structure, conduct spinning data mining in the core-spun yarn spinning process database to construct a spinning process control space. Among them, the core-spun yarn spinning process database includes a set of historical spinning control parameters and a corresponding set of historical spinning effects within a preset time window. The optimization analysis module 40 is used to conduct optimization analysis in the spinning process control space with the core-spun yarn spinning requirement parameters as the optimization constraint conditions, and determine the target spinning control parameters. The spinning control module 50 is used to perform quality feedback optimization on the target spinning control parameters to obtain optimized spinning control parameters, and conduct spinning control of the target core-spun yarn with the optimized spinning control parameters.

[0066] Furthermore, the spinning data mining module 30 includes: The first spinning process data extraction unit is used to extract the first spinning process data from the core-spun yarn spinning process database. The first feature analysis unit is used to conduct feature analysis on the first yarn structure of the first spinning process data to obtain the first yarn structure feature set. The second feature analysis unit is used to conduct feature analysis on the target yarn structure to obtain the target yarn structure feature set. The similarity analysis unit is used to conduct similarity analysis on the first yarn structure feature set and the target yarn structure feature set to obtain the first yarn structure similarity coefficient. The judgment unit is used to, if the first yarn structure similarity coefficient meets the yarn structure similarity coefficient threshold, add the first historical spinning control parameter and the corresponding first historical spinning effect of the first spinning process data to the spinning process control space.

[0067] Furthermore, the similarity analysis unit includes: The preset label scheme acquisition channel is used to acquire the preset label scheme. The first label marking channel is used to conduct label marking on the first yarn structure feature set based on the preset label scheme to obtain the first label vector. The second label marking channel is used to conduct label marking on the target yarn structure feature set based on the preset label scheme to obtain the target label vector. The similarity coefficient calculation channel is used to obtain the first yarn structure similarity coefficient according to the Pearson correlation coefficient of the first label vector and the target label vector.

[0068] Furthermore, the optimization analysis module 40 includes: An evaluation index extraction unit, configured to extract spinning effect evaluation indexes based on the historical spinning effect set to obtain a spinning effect evaluation index set; a function fitting unit, configured to perform function fitting based on the spinning effect evaluation index set to establish a spinning effect evaluation fitness function; a global iterative optimization unit, configured to use the core-spun yarn spinning requirement parameters as optimization constraint conditions, perform global iterative optimization in the spinning process control space, and evaluate and compare the spinning effects through the spinning effect evaluation fitness function to determine the target spinning control parameters.

[0069] Furthermore, the global iterative optimization unit includes: A local parameter search channel, configured to obtain a global search step size, perform global parameter search in the spinning process control space according to the global search step size to obtain a global spinning process control parameter set; an evaluation channel, configured to evaluate the global spinning process control parameter set based on the spinning effect evaluation fitness function to obtain a global spinning effect evaluation fitness set; a descending order arrangement channel, configured to perform a descending order arrangement on the global spinning effect evaluation fitness set, and obtain the optimal global spinning process control parameter corresponding to the maximum global spinning effect evaluation fitness based on the descending order arrangement result; a local parameter search channel, configured to obtain a local search step size, combine the local search step size and the spinning effect evaluation fitness function, and perform local parameter search based on the global spinning process control parameters until a preset number of iterations is reached, and output the target spinning control parameters.

[0070] Furthermore, the spinning control module 50 includes: A spinning processing unit, configured to perform spinning processing of the target core-spun yarn based on the target spinning control parameters to obtain a finished core-spun yarn; a test index generation unit, configured to generate a wrinkle resistance test index and a softness test index based on the wrinkle resistance requirement parameters and the softness requirement parameters; an optimization unit, configured to perform a spinning effect test on the finished core-spun yarn based on the wrinkle resistance test index and the softness test index, and when the test result does not meet the required effect, perform test data diagnosis, and optimize the target spinning control parameters according to the diagnosis result to obtain optimized spinning control parameters.

[0071] Furthermore, the spinning control module 50 further includes: A wrinkle detection device configuration unit for configuring a wrinkle detection device, wherein the wrinkle detection device includes an image sensor for traversing image acquisition; an image acquisition unit for acquiring an image of the finished core-spun yarn through the image sensor to obtain an image acquisition result; a pixel gray value comparison unit for establishing a reference pixel gray value, comparing the pixel gray values of the image acquisition result based on the reference pixel gray value, and obtaining a wrinkle area set according to the comparison result; a wrinkle statistics unit for performing wrinkle statistics based on the wrinkle area set and recording a wrinkle data set; a commonality clustering unit for performing commonality clustering on the position and features of the wrinkle data set to generate a commonality clustering result; and a feedback tuning unit for performing feedback tuning of the target spinning control parameters based on the commonality clustering result.

[0072] Through the foregoing detailed description of the method for adjusting the spinning parameters of the anti-wrinkle soft core-spun yarn in this specification, those skilled in the art can clearly know the spinning parameter adjustment platform for the anti-wrinkle soft core-spun yarn in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method section.

[0073] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn, characterized in that: The method comprises: Acquire application scenario information of the target core-spun yarn, perform multi-dimensional demand analysis on the application scenario information, and obtain the core-spun yarn spinning demand parameters, wherein the core-spun yarn spinning demand parameters include wrinkle resistance demand parameters and softness demand parameters; According to the required parameters of the core-spun yarn spinning, fiber parameters of the core fiber and the outer fiber of the yarn are configured to establish a target yarn structure; Connecting to a core-spun yarn spinning process database, and based on the target yarn structure, performing spinning data mining in the core-spun yarn spinning process database to construct a spinning process control space, wherein the core-spun yarn spinning process database includes a historical spinning control parameter set and a corresponding historical spinning effect set within a preset time window; Taking the core-spun yarn spinning requirement parameters as optimization constraints, performing optimization analysis in the spinning process control space to determine target spinning control parameters; The target spinning control parameters are subjected to quality feedback tuning to obtain optimized spinning control parameters, and the spinning control of the target core-spun yarn is performed with the optimized spinning control parameters.

2. The spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to claim 1, characterized in that: The method of connecting the core-spun yarn spinning process database and performing spinning data mining in the core-spun yarn spinning process database based on the target yarn structure to construct a spinning process control space includes: Extracting the first spinning process data from the core-spun yarn spinning process database; Performing feature analysis on the first yarn structure of the first spinning process data to obtain a first yarn structure feature set; Performing feature analysis on the target yarn structure to obtain a target yarn structure feature set; Performing a similarity analysis on the first yarn structure feature set and the target yarn structure feature set to obtain a first yarn structure similarity coefficient; If the first yarn structure similarity coefficient meets the yarn structure similarity coefficient threshold, the first historical spinning control parameter of the first spinning process data and the corresponding first historical spinning effect are added to the spinning process control space.

3. The spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to claim 2, characterized in that: The performing similarity analysis on the first yarn structure feature set and the target yarn structure feature set to obtain a first yarn structure similarity coefficient includes: Get the preset label scheme; Based on the preset labeling scheme, labeling the first yarn structure feature set to obtain a first label vector; Based on the preset labeling scheme, labeling the target yarn structure feature set to obtain a target label vector; The first yarn structure similarity coefficient is obtained according to the Pearson correlation coefficient between the first label vector and the target label vector.

4. The spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to claim 1, characterized in that: The method uses the core-spun yarn spinning requirement parameters as optimization constraints, performs optimization analysis in the spinning process control space, and determines the target spinning control parameters, and includes: Extracting spinning effect evaluation indicators based on the historical spinning effect set to obtain a spinning effect evaluation indicator set; Perform function fitting based on the spinning effect evaluation index set to establish a spinning effect evaluation fitness function; Taking the core-spun yarn spinning requirement parameters as optimization constraints, a global iterative optimization is performed in the spinning process control space, and the spinning effect is evaluated and compared through the spinning effect evaluation fitness function to determine the target spinning control parameters.

5. The spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to claim 4, characterized in that: The method for determining the target spinning control parameter comprises: Acquire a global search step length, perform a global parameter search in the spinning process control space according to the global search step length, and obtain a global spinning process control parameter set; Evaluate the global spinning process control parameter set based on the spinning effect evaluation fitness function to obtain a global spinning effect evaluation fitness set; Arrange the global spinning effect evaluation fitness set in descending order, and obtain the optimal global spinning process control parameter corresponding to the maximum global spinning effect evaluation fitness based on the descending order result; The local search step length is obtained, and the local search step length is combined with the spinning effect evaluation fitness function, and a local parameter search is performed based on the global spinning process control parameters until a preset number of iterations is reached, and the target spinning control parameters are output.

6. The spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to claim 1, characterized in that: The method of performing quality feedback tuning on the target spinning control parameters to obtain optimized spinning control parameters includes: Performing spinning processing on the target core-spun yarn based on the target spinning control parameters to obtain a finished core-spun yarn; Based on the wrinkle resistance requirement parameter and the softness requirement parameter, generating a wrinkle resistance test index and a softness test index; Based on the wrinkle resistance test index and the softness test index, the spinning effect of the finished core-spun yarn is tested. When the test result does not meet the required effect, the test data diagnosis is performed, and the target spinning control parameters are optimized according to the diagnosis result to obtain the optimized spinning control parameters.

7. The spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to claim 6, characterized in that: The method further comprises: Configuring a wrinkle detection device, wherein the wrinkle detection device includes an image sensor for performing traversal image acquisition; Capturing an image of the finished core-spun yarn by using the image sensor to obtain an image acquisition result; Establishing a reference pixel grayscale value, performing pixel grayscale value comparison of the image acquisition result based on the reference pixel grayscale value, and obtaining a wrinkle region set according to the comparison result; Performing wrinkle statistics based on the wrinkle area set and recording a wrinkle data set; Performing commonality clustering of positions and features on the wrinkle dataset to generate commonality clustering results; Feedback tuning of the target spinning control parameters is performed based on the commonality clustering results.

8. The spinning parameter adjustment platform for wrinkle-resistant soft core-spun yarn is characterized by: For implementing the spinning parameter adjustment method for wrinkle-resistant soft core-spun yarn according to any one of claims 1 to 7, the platform comprises: A multi-dimensional demand analysis module, used to obtain application scenario information of the target core-spun yarn, perform multi-dimensional demand analysis on the application scenario information, and obtain the core-spun yarn spinning demand parameters, wherein the core-spun yarn spinning demand parameters include wrinkle resistance demand parameters and softness demand parameters; A fiber parameter configuration module, used to configure the fiber parameters of the core fiber and the outer fiber of the yarn according to the required parameters of the core-spun yarn spinning, and establish a target yarn structure; A spinning data mining module, which is used to connect to a core-spun yarn spinning process database, and based on the target yarn structure, perform spinning data mining in the core-spun yarn spinning process database to construct a spinning process control space, wherein the core-spun yarn spinning process database includes a historical spinning control parameter set and a corresponding historical spinning effect set within a preset time window; An optimization analysis module is used to perform optimization analysis in the spinning process control space with the core-spun yarn spinning requirement parameters as optimization constraints to determine target spinning control parameters; The spinning control module is used to perform quality feedback tuning on the target spinning control parameters to obtain optimized spinning control parameters, and to perform spinning control of the target core-spun yarn with the optimized spinning control parameters.

Images