A yarn texturing process

Abstract

The application relates to the technical field of chemical fibers, and particularly discloses a yarn elasticizing process, which comprises the following steps: before twisting, feeding the raw yarn through multiple heating sections in sequence; collecting yarn tension data at the inlet and outlet of each heating section, temperature data of each heating section and yarn deformation data in real time; and adjusting the heating parameters of the heating sections in real time according to the yarn tension data, the temperature data and the yarn deformation data. The yarn tension, the temperature and the deformation of the raw yarn during actual heating are controlled in real time, the heating effect of the raw yarn is improved, the temperature of each heating section is strictly controlled while the internal stress of the raw yarn is eliminated by gradually increasing the temperature, and the strength and the elasticity of the fiber are further improved.

Description

Technical Field

[0001] This invention relates to the field of chemical fiber technology, and more specifically, to a yarn texturing process. Background Technology

[0002] Texturing is a process of processing thermoplastic chemical fiber filaments into elastic yarns. The process mainly includes heating, false twisting (or twisting), and setting. The temperature, time, tension, and degree of twisting deformation during processing are the main process parameters of texturing. These parameters vary depending on the composition, linear density, and product characteristics of the raw yarn fed in, and are closely related to product quality.

[0003] Among them, the heating temperature affects the plasticity and deformation effect of the fiber. Too high a temperature may cause the fiber to break or its performance to decline, while too low a temperature will not achieve the desired texturing effect. In the existing technology, the heating temperature is usually static and cannot be dynamically adjusted according to the situation of the yarn during heating.

[0004] Therefore, it is necessary to propose a yarn texturing process to at least partially solve the problems existing in the prior art. Summary of the Invention

[0005] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this invention is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0006] To at least partially solve the above problems, the present invention provides a yarn texturing process, comprising:

[0007] Before twisting, the raw yarn is passed through multiple heating sections in sequence;

[0008] Real-time data collection of yarn tension at the inlet and outlet of each heating section, temperature data of each heating section, and yarn deformation data;

[0009] The heating parameters of the heating section are adjusted in real time based on yarn tension data, temperature data, and yarn deformation data.

[0010] Preferably, the yarn deformation data includes: yarn diameter and surface microcrack characteristics.

[0011] Preferably, the heating parameters of the heating section are adjusted in real time based on yarn tension data, temperature data, and yarn deformation data, including:

[0012] Based on yarn tension data, temperature data, and yarn deformation data, the future state of the yarn is predicted;

[0013] Based on the prediction results of the future state of the yarn, the heating parameters of the heating section are adjusted in real time.

[0014] Preferably, the future state of the yarn includes: crimp shrinkage and breaking elongation.

[0015] Preferably, the heating parameters of the heating section are adjusted in real time based on the prediction of the future state of the yarn, including:

[0016] If the predicted future state of the yarn is that the crimp shrinkage and breaking elongation are within the corresponding set range and neither shows a downward trend, then each heating section will operate according to the current heating parameters.

[0017] If the future state prediction of the yarn shows that at least one of the crimp shrinkage and breaking elongation is decreasing, then an adjustment instruction is generated;

[0018] The heating parameters of the heating section that needs adjustment are adjusted according to the control instructions.

[0019] Preferably, it also includes:

[0020] Before the raw filament passes through multiple heating sections, the corresponding initial heating parameters are selected based on the material of the raw filament;

[0021] Multiple heating sections operate according to their corresponding initial heating parameters.

[0022] Preferably, it also includes:

[0023] When the raw filament of the current material passes through multiple heating sections in sequence, the optimal heating parameters of the multiple heating sections during operation are obtained;

[0024] The optimal heating parameters are used as the initial heating parameters for the corresponding material's precursor fiber in the next heating cycle.

[0025] Preferably, the optimal heating parameters satisfy the condition that the prediction of the future state of the yarn has the highest degree of ideality.

[0026] Preferably, the optimal heating parameters are obtained by the following method:

[0027] The predicted curl shrinkage and elongation at break were standardized to obtain standard values ​​for curl shrinkage and elongation at break.

[0028] The standardized formula used to calculate the standard value is as follows:

[0029]

[0030] X′ is the standard value of the curl shrinkage rate, and X is the curl shrinkage rate. min and X max These are the minimum and maximum values ​​within the set range corresponding to the curl shrinkage rate;

[0031]

[0032] Y′ is the standard value of elongation at break, and Y is the elongation at break. min and Y max These are the minimum and maximum values ​​of the set range corresponding to the elongation at break;

[0033] Based on the standard values ​​of crimp shrinkage and breaking elongation, the ideality of the yarn future condition prediction results is obtained;

[0034] The ideality is calculated as follows:

[0035]

[0036] Where P is the degree of ideality, d + The distance from the standard values ​​of curl shrinkage and elongation at break to the positive target values:

[0037]

[0038] d - The distance from the standard values ​​of curl shrinkage and elongation at break to the negative target values:

[0039]

[0040] X′ + and X′ - Y′ represents the positive and negative target values ​​corresponding to the curl shrinkage rate, respectively. + and Y′ - These are the positive and negative target values ​​corresponding to the curling shrinkage rate, respectively;

[0041] The heating parameters that correspond to the highest degree of ideality are taken as the optimal heating parameters.

[0042] Preferably, it also includes:

[0043] Based on the yarn tension data of each heating section, obtain the yarn tension fluctuation parameters within a set time period;

[0044] Based on the yarn tension fluctuation parameters within a set time period, determine whether there is a risk of yarn breakage. If there is a risk of yarn breakage, issue an alarm.

[0045] Compared with the prior art, the present invention has at least the following beneficial effects:

[0046] The yarn texturing process described in this invention controls the temperature in real time by measuring the tension, temperature, and deformation of the raw yarn during actual heating. This improves the heating effect of the raw yarn, gradually increasing the temperature to eliminate internal stress while strictly controlling the temperature of each heating section, thereby further enhancing the strength and elasticity of the fiber.

[0047] By predicting the crimp shrinkage and breaking elongation of the yarn, the heating parameters can be adjusted before they exceed the corresponding set range. This allows for early prediction of the future impact of the heating parameters on the raw yarn, enabling timely adjustments and ensuring the stability of the raw yarn heating.

[0048] The yarn texturing process described in this invention, other advantages, objectives and features of this invention will be partly apparent from the following description, and partly understood by those skilled in the art through study and practice of this invention. Attached Figure Description

[0049] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0050] Figure 1 This is a flowchart of the yarn texturing process described in this invention;

[0051] Figure 2 This is a flowchart of step S3 in the yarn texturing process described in this invention;

[0052] Figure 3 This is a flowchart of step S32 in the yarn texturing process described in this invention;

[0053] Figure 4 This is a flowchart illustrating the selection of initial heating parameters in the yarn texturing process described in this invention;

[0054] Figure 5 This is a flowchart of step S4 in the yarn texturing process described in this invention. Detailed Implementation

[0055] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments, so that those skilled in the art can implement it based on the description.

[0056] It should be understood that terms such as “having,” “comprising,” and “including” as used herein do not exclude the presence or addition of one or more other elements or combinations thereof.

[0057] like Figure 1 As shown, the present invention provides a yarn texturing process, including:

[0058] S1. Before twisting, the raw yarn is passed through multiple heating sections in sequence;

[0059] S2. Real-time acquisition of yarn tension data at the inlet and outlet of each heating section, temperature data of each heating section, and yarn deformation data;

[0060] S3. Adjust the heating parameters of the heating section in real time based on yarn tension data, temperature data, and yarn deformation data.

[0061] After twisting, the yarn is texturized through processes such as blowing and forming. The heating process in yarn texturizing is completed by the above methods, which can effectively eliminate the internal stress of the raw yarn, reduce the stress unevenness caused by temperature change, and effectively improve elasticity.

[0062] Piezoelectric tension sensors are installed on the components (e.g., rollers) at the inlet and outlet of each heating section used for conveying and contacting the raw yarn to acquire yarn tension data in real time; multiple temperature sensors are distributed on each heating section to sample and monitor the temperature data of each heating section at 0.1 seconds; high-speed linear array cameras (e.g., 5000 frames / second) are deployed at key nodes of the heating section to acquire yarn images and extract yarn deformation data; then, based on the yarn tension data, the temperature data of each heating section, and the yarn deformation data, the heating parameters (e.g., temperature) of the heating section are adjusted in real time;

[0063] The temperature of each heating section increases sequentially. Since the heating temperature of each section has a significant impact on the yarn tension and deformation, if the temperature of each heating section is set to a fixed value, it cannot be dynamically adjusted based on the actual changes in the raw yarn after heating. For example, if the temperature difference between two adjacent heating sections is not designed properly, although the heating temperature of the raw yarn will not produce a large sudden change, even a small change will lead to uneven stress. Therefore, in the above process, by controlling the temperature in real time based on the actual tension, temperature, and deformation of the raw yarn during heating, the heating effect of the raw yarn can be improved. While gradually increasing the temperature to eliminate the internal stress of the raw yarn, the temperature of each heating section is strictly controlled to further improve the strength and elasticity of the fiber.

[0064] Furthermore, the yarn deformation data includes: yarn diameter and surface microcrack characteristics.

[0065] When raw yarn (such as chemical fiber) is heated to a certain temperature, the mobility of the molecular chains increases, resulting in thermal expansion and an increase in yarn diameter. When the temperature exceeds a certain level, the raw yarn may deform under external force, causing a change in diameter. Therefore, the change in yarn diameter is temperature-dependent. Since the raw yarn is subjected to external forces during transportation, its properties change during heating. When subjected to large external forces or when the heating temperature is unreasonable, microcracks may appear on the surface, thus affecting the breaking elongation of the yarn. Therefore, by acquiring yarn images through a high-speed linear array camera and extracting features such as yarn diameter and surface microcracks, it is possible to understand the impact of heating temperature on the performance of the raw yarn.

[0066] like Figure 2 As shown, in one embodiment, S3, adjusting the heating parameters of the heating section in real time based on yarn tension data, temperature data, and yarn deformation data includes:

[0067] S31. Based on yarn tension data, temperature data, and yarn deformation data, predict the future state of the yarn;

[0068] S32. Adjust the heating parameters of the heating section in real time based on the prediction results of the future state of the yarn.

[0069] Furthermore, the future state of the yarn includes: crimp shrinkage and breaking elongation.

[0070] Furthermore, the future condition of the yarn also includes the risk of yarn breakage.

[0071] In this embodiment, a trained LSTM (Long Short-Term Memory) reinforcement learning hybrid model can be used. Yarn tension data, temperature data, and yarn deformation data are used as inputs (input layer) to the trained LSTM reinforcement learning hybrid model, and the future state of the yarn is used as the output (output layer) of the LSTM reinforcement learning hybrid model. The heating parameters of the heating section are adjusted accordingly using the output crimp shrinkage rate and breaking elongation rate to optimize the heating process.

[0072] The LSTM reinforcement learning hybrid model takes historical data as input, which includes historical data on yarn tension, temperature, and yarn deformation of different raw yarn materials during heating. It then outputs the crimp shrinkage rate and breaking elongation rate corresponding to the historical data. The LSTM reinforcement learning hybrid model is trained through the above process. In the actual raw yarn heating process, new data from actual production can also be input into this model in real time to update the LSTM reinforcement learning hybrid model in real time.

[0073] like Figure 3 As shown, further, S32, based on the prediction results of the future state of the yarn, the heating parameters of the heating section are adjusted in real time, including:

[0074] S321. If the future state prediction of the yarn is that the crimp shrinkage rate and breaking elongation rate are both within the corresponding set range and there is no downward trend, then each heating section will work according to the current heating parameters.

[0075] S322. If the future state prediction of the yarn shows that at least one of the crimp shrinkage rate and breaking elongation rate is decreasing, then an adjustment instruction is generated.

[0076] S323. Adjust the heating parameters of the heating section that needs to be adjusted according to the control instructions.

[0077] The main purpose of heating the raw yarn is to increase the crimp shrinkage and breaking elongation of the yarn. Of course, the crimp shrinkage and breaking elongation of the yarn are also related to the subsequent processes. In this invention, assuming that the subsequent processes are the same and stable, the goal is to optimize the heating parameters of the raw yarn to increase the crimp shrinkage and breaking elongation of the yarn.

[0078] When the crimp shrinkage and breaking elongation are within their respective set ranges and neither shows a decreasing trend, it indicates that the current heating parameters can meet the process requirements of yarn texturing. If at least one of the crimp shrinkage and breaking elongation shows a decreasing trend, the heating parameters should be adjusted before it actually exceeds the corresponding set range. This allows for early prediction of the future impact of the heating parameters on the raw yarn and timely adjustments to ensure the stability of the raw yarn heating.

[0079] In addition, in step S32, the heating parameters of the heating section can be optimized based on the yarn future state prediction results through the reinforcement learning module of the LSTM reinforcement learning hybrid model. Specifically, the reward function in the reinforcement learning module guides the model to dynamically optimize the heating parameters, ultimately achieving the optimal crimp shrinkage rate and breaking elongation, as well as the lowest risk of yarn breakage.

[0080] The reward function transforms the process objective into a computable numerical signal as follows:

[0081] R = α·curling shrinkage rate + β·breaking elongation rate - γ·fiber breakage risk

[0082] R is the reward value, and α, β, and γ are the weight values ​​for crimp shrinkage rate, breaking elongation rate, and breakage risk, respectively. For example, α = 0.4, β = 0.4, and γ = 0.2. The specific weight values ​​can be allocated according to the actual importance.

[0083] If adjusting the heating parameters of the heating section increases the crimp shrinkage rate, or increases the breaking elongation rate, or reduces the risk of filament breakage, the reward value will increase, thus encouraging similar adjustments in the future.

[0084] If adjusting the heating parameters of the heating section increases the risk of wire breakage, the reward value will decrease, thereby suppressing this high-risk adjustment strategy.

[0085] In another embodiment, a process objective with the lowest energy consumption can be added to the process objectives, and the reward function is as follows:

[0086]

[0087] R is the reward value, and α, β, γ, and δ are the weight values ​​for curl shrinkage rate, breaking elongation rate, filament breakage risk, and heating section energy consumption, respectively. For example, α = 0.4, β = 0.4, γ = 0.1, γ = 0.1. The specific weight values ​​can be allocated according to the actual importance. Among them, the heating section energy consumption is encouraged to save energy in the form of a reciprocal.

[0088] In this embodiment, energy-saving requirements can be increased by adjusting the heating parameters of the heating section while reducing energy consumption.

[0089] In one embodiment, it also includes:

[0090] Before the raw filament passes through multiple heating sections, the corresponding initial heating parameters are selected based on the material of the raw filament;

[0091] Multiple heating sections operate according to their corresponding initial heating parameters.

[0092] Because different raw yarn materials are used, the corresponding heating parameters also differ. Therefore, it is necessary to select the corresponding initial heating parameters according to the raw yarn material. Then, during the heating process, the initial heating parameters of each heating section are adjusted based on the real-time collected yarn tension data at the inlet and outlet of each heating section, the temperature data of each heating section, and the yarn deformation data, in order to improve the performance of the yarn.

[0093] like Figure 4 As shown, in one embodiment, it further includes:

[0094] S4. When the raw filament of the current material passes through multiple heating sections in sequence, obtain the optimal heating parameters when the multiple heating sections are working.

[0095] S5. Use the optimal heating parameters as the initial heating parameters for the corresponding material's precursor fiber in the next heating cycle.

[0096] Furthermore, the optimal heating parameters satisfy the condition that the prediction of the future state of the yarn has the highest degree of ideality.

[0097] In this embodiment, the main purpose is to update the initial heating parameters. For example, each time the raw yarn is heated, the future state of the yarn is predicted multiple times, and the heating parameters corresponding to the prediction results are recorded. Then, in the historical prediction results, the heating parameters of multiple heating segments corresponding to the prediction results with the highest ideality are selected as the initial heating parameters for the raw yarn of the corresponding material next time. In this way, the heating process can be carried out with the optimal heating parameters each time the raw yarn is heated, reducing the frequency of adjusting the heating parameters, improving the stability of the raw yarn heating, and enabling the yarn to achieve the ideal texturing effect.

[0098] like Figure 5 As shown, the optimal heating parameters are further obtained by the following method:

[0099] S41. Standardize the predicted curl shrinkage and elongation at break to obtain standard values ​​for curl shrinkage and elongation at break.

[0100] The standardized formula used to calculate the standard value is as follows:

[0101]

[0102] X′ is the standard value of the curl shrinkage rate, and X is the curl shrinkage rate. min and X max These are the minimum and maximum values ​​within the set range corresponding to the curl shrinkage rate;

[0103]

[0104] Y′ is the standard value of elongation at break, and Y is the elongation at break. min and Y max These are the minimum and maximum values ​​of the set range corresponding to the elongation at break;

[0105] S42. Based on the standard values ​​of crimp shrinkage and breaking elongation, obtain the ideality of the yarn future state prediction results;

[0106] Since both curl shrinkage and elongation at break are better the higher they are, we set positive target values ​​(e.g., 1) and negative target values ​​(e.g., 0) for curl shrinkage and positive target values ​​(e.g., 1) and negative target values ​​(e.g., 0) for elongation at break. The ideality is then calculated as follows:

[0107]

[0108] Where P is the degree of ideality, d + The distance from the standard values ​​of curl shrinkage and elongation at break to the positive target values:

[0109]

[0110] d - The distance from the standard values ​​of curl shrinkage and elongation at break to the negative target values:

[0111]

[0112] X′ + and X′ - Y′ represents the positive and negative target values ​​corresponding to the curl shrinkage rate, respectively. + and Y′ - These are the positive and negative target values ​​corresponding to the curl shrinkage rate, respectively;

[0113] S43. The heating parameters corresponding to the highest ideality are taken as the optimal heating parameters.

[0114] Each heating process yields multiple sets of predicted results, namely multiple sets of crimp shrinkage rate and breaking elongation rate. Both crimp shrinkage rate and breaking elongation rate have their corresponding set ranges. As long as the predicted results are within the set ranges, it indicates that the yarn texturing effect can be achieved. However, in order to further improve the effect, multiple sets of crimp shrinkage rate and breaking elongation rate within the corresponding set ranges are calculated to obtain the ideality. The heating parameters with the highest ideality are then selected as the optimal heating parameters.

[0115] In the above method, considering that different heating temperatures have different effects on crimp shrinkage and breaking elongation, for example, within the corresponding set range, when the crimp shrinkage is relatively high, the breaking elongation may be relatively low, or both may be relatively high or low, the calculation of ideality is introduced here. When the ideality is the highest, the crimp shrinkage and breaking elongation are relatively balanced, and the yarn performance is better.

[0116] In one embodiment, it also includes:

[0117] Based on the yarn tension data of each heating section, obtain the yarn tension fluctuation parameters within a set time period;

[0118] Based on the yarn tension fluctuation parameters within a set time period, determine whether there is a risk of yarn breakage. If there is a risk of yarn breakage, issue an alarm.

[0119] The tension of the raw yarn can be detected at the inlet and outlet of each heating section. Within a set time period, the tension fluctuation parameter at each position can be obtained. For example, the set time period can be set to 2 seconds. If the tension F2 at the end of the set time T2 (at 2 seconds) is lower than the preset percentage (e.g., 85%) of the tension F1 at the beginning of the set time T0 (at 0 seconds), that is, F2-0.85F1<0, where F2-0.85F1 is the tension fluctuation parameter, that is, when the tension fluctuation parameter is less than 0, it indicates that there is a risk of yarn breakage and an alarm is issued. This can help to predict the risk of yarn breakage in advance and take appropriate measures in time.

[0120] Although the reward function in the reinforcement learning module of the aforementioned embodiment takes into account the impact of temperature on the risk of wire breakage, it is still necessary to actually detect the tension in order to further reduce the risk of wire breakage.

[0121] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the present invention, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A yarn texturing process characterized by, include: Before twisting, the raw yarn is passed through multiple heating sections in sequence; Real-time data collection of yarn tension at the inlet and outlet of each heating section, temperature data of each heating section, and yarn deformation data; The heating parameters of the heating section are adjusted in real time based on yarn tension data, temperature data, and yarn deformation data. It includes: Based on yarn tension data, temperature data, and yarn deformation data, an LSTM reinforcement learning hybrid model is used to predict the future state of the yarn. Based on the prediction results of the future state of the yarn, the heating parameters of the heating section are adjusted in real time; Yarn deformation data includes: yarn diameter and surface microcrack characteristics; The future state of yarn includes: crimp shrinkage and breaking elongation; Among these measures, the heating parameters of the heating section are adjusted in real time based on the predicted future state of the yarn, including: If the predicted future state of the yarn is that the crimp shrinkage and breaking elongation are within the corresponding set range and neither shows a downward trend, then each heating section will operate according to the current heating parameters. If the future state prediction of the yarn shows that at least one of the crimp shrinkage and breaking elongation is decreasing, then an adjustment instruction is generated. Adjust the heating parameters of the heating section that needs adjustment according to the control instructions; Also includes: When the raw filament of the current material passes through multiple heating sections in sequence, the optimal heating parameters of the multiple heating sections during operation are obtained; The optimal heating parameters are used as the initial heating parameters for the corresponding material's precursor fiber in the next heating cycle. Among them, the optimal heating parameters satisfy the condition that the ideality of the yarn future state prediction result is the highest; The optimal heating parameters are obtained by the following method: The predicted curl shrinkage and elongation at break were standardized to obtain standard values ​​for curl shrinkage and elongation at break. Based on the standard values ​​of crimp shrinkage and breaking elongation, the ideality of the yarn future condition prediction results is obtained; The heating parameters that correspond to the highest degree of ideality are taken as the optimal heating parameters.

2. The yarn texturing process according to claim 1, characterized in that, Also includes: Before the raw filament passes through multiple heating sections, the corresponding initial heating parameters are selected based on the material of the raw filament; Multiple heating sections operate according to their corresponding initial heating parameters.

3. The yarn texturing process according to claim 1, characterized in that, Also includes: Based on the yarn tension data of each heating section, obtain the yarn tension fluctuation parameters within a set time period; Based on the yarn tension fluctuation parameters within a set time period, determine whether there is a risk of yarn breakage. If there is a risk of yarn breakage, issue an alarm.

Images