Air-textured yarn device and its preparation process

Abstract

The present invention relates to an air-deformation device for wool-like air-textured yarn and a preparation process thereof, belonging to the field of textile technology. The air-deformation device improves the uniformity of the air-deformed yarn through a two-stage air-deformation structure. The arc-shaped trumpet-shaped yarn outlet reduces occasional unevenness caused by the yarn colliding with sharp cross-sections. The new tile-shaped baffle has a certain degree of freedom and slight vibration. Incomplete loops can be further fluffed here, making the yarn surface loop distribution more uniform. It also effectively reduces the surface loop collapse caused by the yarn contacting the baffle body and bending, reducing the loss of wool-like effect. At the same time, it can also reduce the strength loss caused by the high-speed airflow carrying the yarn to impact the baffle body. In terms of the preparation process, it combines advanced chaotic neural network optimization technology and achieves a high degree of automation and intelligence in the preparation process by accurately optimizing and controlling multiple process parameters such as the original yarn characteristics, overfeed rate, and air intake parameters.

Description

Technical Field

[0001] The invention relates to an air-deformation device for wool-like air-deformed yarn and a preparation process thereof, belonging to the technical field of textiles. Background Art

[0002] Air-textured yarn is a type of yarn produced by intertwining yarn bundles using air jet technology to form irregularly twisted loops, giving the bundle a fluffy, terry-like appearance. The process can be summarized as follows: The raw monofilament or multifilament yarn is fed from a creel through a feed roller and enters a nozzle at the same or varying speeds. The turbulent airflow within the nozzle disperses the individual fibers in the bundle, causing them to entangle and deform laterally, creating loops and arcs. The bulkiness of air-textured yarn has led to its widespread application in clothing, home textiles, and other fields.

[0003] However, different application scenarios have different requirements for the bulkiness of air-textured yarns, and traditional air-textured devices for producing air-textured yarns can only produce yarns with a single bulkiness. Chinese patent publication number CN113755979A discloses an air-textured device for producing air-textured yarns. In order to solve the problem that the size of the air inlet channel of the existing air-textured device is difficult to adjust, resulting in difficulty in adjusting the bulkiness of the yarn, the size of the air inlet channel is adjustable by setting the mother seat and the nozzle housing to be threadedly connected, thereby achieving the adjustment of the bulkiness of the yarn. However, this solution requires manual adjustment, and the size of the air inlet channel can only be adjusted based on experience.

[0004] In addition, the current preparation technologies for producing air-textured yarns do not comprehensively consider the impact of processing parameters on yarn bulkiness. Therefore, it is necessary to develop an air-textured yarn preparation device and process that can comprehensively consider the impact of various processing parameters on yarn bulkiness. Summary of the Invention

[0005] In order to solve the existing technical problems of optimizing processing parameters and poor single-channel fluffy effect, the present invention provides an air-textured yarn device and a preparation process thereof. The technical solution is as follows:

[0006] The present invention provides an air-textured device for wool-like air-textured yarn, comprising:

[0007] A first yarn guide core body 4;

[0008] The yarn feeding hole 1 is provided in the first yarn guide core body 4;

[0009] A first yarn guide channel 3 is connected to the yarn inlet hole 1; the first yarn guide channel 3 is connected to a first turbulent cavity 5, a first air inlet channel 201 is connected to one side of the first turbulent cavity 5, and the first air inlet channel 201 is connected to the first air inlet hole 2;

[0010] The second yarn guide core body 8 is installed on one side of the first yarn guide core body 4;

[0011] A second yarn guide channel 7 is connected to the first yarn guide channel 3 and is disposed in the second yarn guide core body 8. A second turbulent flow chamber 9 is connected thereto. One side of the second turbulent flow chamber 9 is connected to a second air inlet channel 601. One end of the second air inlet channel 601 is connected to a second air inlet hole 6. The other side of the second turbulent flow chamber 9 is connected to a yarn outlet hole 10.

[0012] The blocking body 11 is provided on one side of the second yarn guide core body 8;

[0013] The first yarn guide core body 4 and the second yarn guide core body 8 are an integral structure.

[0014] Optionally, the blocking body 11 is a tile-shaped blocking body.

[0015] Optionally, the tile-shaped baffle is a rotatable structure.

[0016] Optionally, the first air inlet hole 2 passes through the side wall of the first yarn guide core body 4, and the second air inlet hole 6 passes through and is connected to the side wall 8 of the second yarn guide core body.

[0017] Optionally, the yarn inlet hole 1 and the yarn outlet hole 10 are designed to be trumpet-shaped.

[0018] A second object of the present invention is to provide a process for preparing wool-like air-textured yarn, which is based on the above-mentioned air-textured yarn device and includes the following steps:

[0019] The first step is to moisten the wool-like air-textured yarn before it enters the air-textured yarn device;

[0020] The second step is to preliminarily set the equipment parameters of the air-textured yarn device, including: the distance D between the baffle 11 and the yarn outlet 10, the overfeed rate SR, the original yarn property influencing parameter YF, the airflow influencing parameter NP of the first air inlet 2, and the airflow influencing parameter N2P of the second air inlet 6; based on the preliminarily set equipment parameters, the air-textured yarn is preliminarily obtained and its performance is characterized by testing;

[0021] In the third step, the chaotic neural network with logistic mapping is used to optimize the equipment parameters;

[0022] Step 4: Set D, SR, YF, NP, and N2P according to the optimized parameters;

[0023] The fifth step is to place the yarn into the air-changing device for processing.

[0024] Optionally, optimizing device parameters using a chaotic neural network with Logistic mapping in the third step includes:

[0025] Step 1, data preparation;

[0026] Step 2, data preprocessing;

[0027] Step 3: Network architecture design;

[0028] The network architecture design includes an input layer, a hidden layer and an output layer;

[0029] The specific expression is:

[0030]

[0031] where v jk is the weight from the jth neuron in the hidden layer to the kth neuron in the output layer; r is the control parameter of the chaotic map; n is the number of input nodes in the input layer; m is the number of hidden nodes in the hidden layer; w ij represents the weight from the i-th neuron in the input layer to the j-th neuron in the hidden layer; x i represents the i-th input of the input layer; b j is the bias of the jth neuron in the hidden layer; c k is the bias of the kth neuron in the output layer.

[0032] Optionally, the value of the control parameter r of the chaotic mapping is 3.58.

[0033] Optionally, the data preprocessing in step 2 includes:

[0034] Step 2.1, data outlier detection;

[0035] Step 2.2, standardize and normalize the data;

[0036] The standardized expression is:

[0037]

[0038] Among them, x i ′ is the standardized data, x i is the input data, μ is the mean of the input data, and σ is the variance of the input data; the normalized expression is:

[0039]

[0040] where x max and x min are the maximum and minimum values ​​of the normalized data.

[0041] Optionally, the data outlier detection in step 2.1 includes the following steps:

[0042]

[0043] If |Z|>Z th , then the data point is considered an outlier if |Z|≤Z th , then the data point is considered a normal data point, Z th is a pre-set threshold.

[0044] The beneficial effects of the present invention are:

[0045] Based on the above technical solution, the air-changing device for wool-like air-textured yarn of the present invention realizes efficient processing of wool-like air-textured yarn through ingenious structural design and process optimization; first, the air-changing device improves the uniformity of the air-textured yarn by setting a two-stage air-changing structure. The trumpet-shaped yarn outlet hole with arc treatment can reduce occasional unevenness caused by collision with sharp cross-sections. The new tile-shaped baffle has a certain degree of freedom and has slight vibration. Incomplete loops can be further fluffed here, making the distribution of loops on the yarn surface more uniform. When the yarn passes through the tile-shaped baffle and enters the drafting area, the tile-shaped baffle can effectively reduce the surface loops caused by the bending of the yarn after contacting the baffle due to its smooth surface and movable design, thereby reducing the loss of wool-like effect. At the same time, it can reduce the strength loss caused by the high-speed airflow carrying the yarn to impact the baffle, and has a diversion effect to ensure the stability of the finished product.

[0046] Furthermore, the present invention incorporates advanced chaotic neural network optimization technology to achieve a highly automated and intelligent production process by precisely optimizing and controlling multiple process parameters, including raw yarn properties, overfeed ratio, and air intake parameters. The chaotic neural network can learn the optimal configuration from complex parameter combinations, ensuring consistent quality and process stability for each batch of yarn, resolving the complex parameter adjustments and unpredictable results inherent in traditional methods.

[0047] Through this series of technical improvements, the present invention not only improves the processing efficiency and product quality of wool-like air-textured yarn, but also achieves breakthroughs in process control precision and equipment versatility, bringing more advanced technical solutions to the textile industry. In particular, in the processing of wool-like yarn, the present invention significantly improves the yarn's feel and appearance, bringing it closer to that of natural wool yarn, thereby expanding the application areas and market competitiveness of wool-like yarn. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 This is a side view of the internal structure of an air-textured device for wool-like air-textured yarn provided by the present invention;

[0050] Figure 2 This is a top view of the internal structure of an air-textured device for wool-like air-textured yarn provided by the present invention;

[0051] 1. Yarn inlet hole; 2. First air inlet hole; 3. First yarn guide channel; 4. First yarn guide core body; 5. First turbulent flow chamber; 6. Second air inlet hole; 7. Second yarn guide channel; 8. Second yarn guide core body; 9. Second turbulent flow chamber; 10. Yarn outlet hole; 11. Tile-type baffle; 201. First air inlet channel; 601. Second air inlet channel; 1101. Rotating shaft.

[0052] Figure 3 This is a microscope image of yarn produced using an existing wool-like air-textured yarn air-textured yarn device.

[0053] Figure 4 The figure shows a microscope image of yarn produced by using the wool-like air-textured yarn air-textured yarn device provided by the present invention. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0055] Example 1:

[0056] like Figure 1 and Figure 2 As shown, this embodiment provides an air-variable device for wool-like air-textured yarn, which includes a two-stage air-variable structure, specifically comprising:

[0057] A first yarn guide core body 4, a second yarn guide core body 8 and a blocking body 11; wherein, the first yarn guide core body 4 is provided with a yarn feed hole 1, a first yarn guide channel 3, a first turbulent cavity 5, a first air inlet channel 201 and a first air inlet hole 2; the yarn feed hole 1 is arranged at the front end inside the first yarn guide core body 4, and the first yarn guide channel 3 is connected to the yarn feed hole 1; the first yarn guide channel 3 is connected to the first turbulent cavity 5, and a first air inlet channel 201 is passed through one side of the first turbulent cavity 5, and the first air inlet channel 201 is connected to the first air inlet hole 2.

[0058] The second yarn guide core body 8 is installed on one side of the first yarn guide core body 4; the second yarn guide core body 8 is provided with a second yarn guide channel 7, a second turbulent cavity 9, a second air inlet channel 601, a second air inlet hole 6 and a yarn outlet hole 10; wherein, the second yarn guide channel 7 is connected to the first yarn guide channel 3 in the first yarn guide core body, the second yarn guide channel 7 is connected to the second turbulent cavity 9, one side of the second turbulent cavity 9 is connected to the second air inlet channel 601, one end of the second air inlet channel 601 is connected to the second air inlet hole 6, and the other side of the second turbulent cavity 9 is connected to the yarn outlet hole 10, and the yarn outlet hole 10 is designed to be trumpet-shaped to reduce occasional unevenness caused by collision with sharp sections.

[0059] The baffle 11 of the air change device is a tile-type baffle, which is arranged on the side of the second yarn guide core body where the yarn outlet hole is provided, and a movable rotating shaft 1101 is provided in the middle part of the tile-type baffle. The tile-type baffle can rotate around the rotating shaft 1101 at a certain angle, and the incomplete arc can be further fluffed here, so that the arc distribution on the surface of the yarn is more even. At the same time, the rotatable design can reduce the strength loss caused by the high-speed airflow carrying the yarn to impact the baffle, and has a diversion effect. In actual application, a limiting structure is set to ensure that the tile-type baffle only rotates within a certain angle range.

[0060] Preferably, the first air inlet hole 2 passes through the side wall of the first yarn guide core body 4 , and the second air inlet hole 6 passes through and is connected to the side wall of the second yarn guide core body 8 .

[0061] Preferably, the yarn inlet hole 1 and the yarn outlet hole 10 are designed to be conical, and the inner walls are arc-shaped.

[0062] Based on the above technical solution, the wool-like air-textured yarn air-textured device of the present invention introduces compressed air into the first turbulence chamber 5 and the second turbulence chamber 9 via the first air inlet channel 201 and the second air inlet channel 601, respectively, creating intense turbulence and effectively air-texturing the yarn. This two-stage air-texturing ensures a uniform wool-like effect on the yarn, thereby improving yarn quality. The tapered design of the yarn inlet and outlet further optimizes yarn introduction and output, ensuring the stability and efficiency of the entire texturizing process. The tile-shaped baffle, which can rotate within a certain angle range, reduces strength loss caused by high-speed airflow carrying yarn and impacting the baffle, and also provides a flow-guiding effect.

[0063] Example 2

[0064] This embodiment provides a preparation process of wool-like air-textured yarn, the preparation process comprising:

[0065] The first step is to moisten the wool-like air-textured yarn before it enters the air-textured yarn device;

[0066] The second step is to preliminarily set the equipment parameters of the air-textured yarn device, including: the distance D between the baffle 11 and the yarn outlet 10, the overfeed rate SR, the original yarn property influencing parameter YF, the airflow influencing parameter NP of the first air inlet 2, and the airflow influencing parameter N2P of the second air inlet 6; based on the preliminarily set equipment parameters, the air-textured yarn is preliminarily obtained and its performance is characterized by testing;

[0067] The third step is to optimize the equipment parameters using a chaotic neural network with Logistic mapping.

[0068] Step 4: Set D, SR, YF, NP, and N2P according to the optimized parameters;

[0069] The fifth step is to place the yarn into the air-changing device for processing.

[0070] In the third step, the optimization of equipment parameters using a chaotic neural network using a Logistic map specifically includes the following steps:

[0071] Step 1, data preparation;

[0072] The different equipment parameters of the above-mentioned air-deformed device and the corresponding performance parameters of the air-deformed yarn are collected, wherein the equipment parameters can be expanded on the basis of empirical values. For example, the distance D between the baffle 11 and the yarn outlet hole 10 can be added or subtracted based on the optimal empirical value, which can be determined by technical personnel.

[0073] The performance parameters of air-textured yarn include breaking strength, linear density, twist, uniformity, hairiness index, rebound index, moisture regain, and bulkiness. The bulkiness is directly measured using a fiber bulkiness meter.

[0074] The yarn quality score Q can be obtained based on the performance parameters of the above-mentioned air-textured yarn. Specifically, it is calculated using the weighted comprehensive scoring method:

[0075] Q=q1×P1+q2×P2+…+qn×Pn

[0076] qi is the weight of the i-th performance parameter, Pi is the score of the i-th performance parameter, and the score of each performance parameter is determined by technicians based on experience.

[0077] Step 2, data preprocessing;

[0078] Data preprocessing operations include outlier detection and standardization and normalization. Outlier detection is performed by setting a threshold and removing data that exceeds the threshold as outliers. In this embodiment, the threshold is denoted as Z th , calculate the Z corresponding to each data according to the following formula:

[0079]

[0080] If |Z|>Z th , then the data point is considered an outlier if |Z|≤Z th , then the data point is considered a normal data point; μ is the mean of the input data, and σ is the variance of the input data.

[0081] In data standardization and normalization operations, the standardized expression is:

[0082]

[0083] Among them, x i ′ is the standardized data, x i For input data;

[0084] The normalized expression is:

[0085]

[0086] where x max and x min are the maximum and minimum values ​​of the normalized data.

[0087] Step 3: Network architecture design;

[0088] The architecture design of the chaotic neural network using Logistic mapping includes input layer, hidden layer and output layer;

[0089] The specific expression is:

[0090]

[0091] where v jk is the weight from the jth neuron in the hidden layer to the kth neuron in the output layer; r is the control parameter of the chaotic map; n is the number of input nodes in the input layer; m is the number of hidden nodes in the hidden layer; w ij represents the weight from the i-th neuron in the input layer to the j-th neuron in the hidden layer; x i represents the i-th input of the input layer; b j is the bias of the jth neuron in the hidden layer; c k is the bias of the kth neuron in the output layer.

[0092] In this embodiment, the value of the control parameter r of the chaotic mapping is 3.58.

[0093] Specific preparation process:

[0094] Step 1: wet treatment;

[0095] The wool-like air-textured yarn is properly moistened before entering the air-textured device, with the humidity controlled at around 8%. This step aims to improve the plasticity of the yarn in subsequent processing, making it easier to be processed into the desired wool-like effect.

[0096] Step 2: Preliminary setting of key parameters;

[0097] Before the air-textured yarn enters the air-textured device, the following key process parameters are preliminarily set:

[0098] The distance D between the movable tile-shaped baffle 11 and the second body is initially set to 5.5 mm to control the flow path of the yarn during processing.

[0099] Overfeed rate SR: initially set to 12% to adjust the ratio between the yarn feed speed and the yarn discharge speed and control the yarn curl and looseness.

[0100] Original yarn property influencing parameter YF: Based on the elasticity and diameter of the yarn, it is initially set to 0.85.

[0101] The airflow influencing parameter NP of the first air inlet 2 is set to 20 m / s to control the curl of the yarn during the deformation process.

[0102] The airflow influencing parameter N2P of the second air inlet 6 is set to 18 m / s to further adjust the deformation effect of the yarn.

[0103] The air-textured yarn was obtained through the above preliminary settings, and its performance was tested and characterized.

[0104] Step 3: Chaotic neural network optimization;

[0105] The chaotic neural network is used to optimize the parameters set above, including:

[0106] Optimization parameters include the distance D between the movable tile-shaped baffle 11 and the yarn outlet hole 10, the overfeed rate SR, the original yarn characteristic influencing parameter YF, the airflow influencing parameter NP of the first air inlet 2, and the airflow influencing parameter N2P of the second air inlet 6.

[0107] Optimization process:

[0108] 1. Data preparation: Collect experimental data. In this embodiment, 1000 sets of yarn performance test results under different parameter settings were collected.

[0109] As shown in Table 1 below, the yarn is quantitatively scored based on the proportion of loop pile on the yarn surface.

[0110] Table 1 Yarn quality score table

[0111]

[0112]

[0113] 2. Data preprocessing:

[0114] Data outlier detection: The threshold Z set in this example is th is 3.

[0115] If the Z of a data point exceeds 3, it is considered an outlier and processed.

[0116] Data standardization and normalization:

[0117] Standardization formula: The mean of D is 5.0 mm and the standard deviation is 0.5 mm.

[0118] Normalization formula: where x max and x min 6 mm and 4 mm respectively.

[0119] 3. Network architecture design:

[0120] Input layer: Input parameters are D, SR, YF, NP, and N2P.

[0121] Hidden layer: The number of hidden layer nodes is 10, and chaos map is used as the activation function, where the value of chaos map control parameter r is 3.58.

[0122] Output layer: outputs optimized yarn performance parameters.

[0123] Table 2 Weight matrix from input layer to hidden layer

[0124]

[0125] Table 3 Bias of hidden layer

[0126]

[0127]

[0128] Table 4 Weight matrix from hidden layer to output layer

[0129]

[0130] Table 5 Bias of the output layer

[0131] c_k k1 -0.326626405

[0132] Step 4: Parameter optimization and setting

[0133] According to the parameters optimized by the chaotic neural network, key parameters such as D, SR, YF, NP, and N2P are adjusted and set. The optimized parameter settings are as follows:

[0134] D: 5.2 mm;

[0135] SR: 11%;

[0136] YF: 0.82;

[0137] NP: 21 m / s;

[0138] N2P: 19 m / s;

[0139] Step 5: Yarn processing;

[0140] The yarn is placed in an air-textured device and processed according to optimized parameters to finally produce wool-like air-textured yarn.

[0141] Figure 3 The wool-like air-textured yarn is produced by using an existing single-stage air-change structure air-change device. Figure 4 The wool-like air-textured yarn produced by the air-variation device provided by the present invention can be seen. It can be seen that the air-variation device with a two-stage air-variation structure of the present invention can make the incomplete loops further fluffy, and the loops on the yarn surface are more evenly distributed. The uniformly fluffy loops on the yarn surface can effectively simulate the fluffy feel of wool yarn. The yarn has a certain felting effect and is used to prepare wool-type fabrics with an excellent feel.

[0142] This example successfully produced high-quality wool-like air-textured yarn through preliminary parameter setting, chaotic neural network optimization, and final processing steps. By optimizing the parameter settings, the yarn's crimp, strength, and consistency were significantly improved, achieving the desired wool-like effect.

[0143] Some steps in the embodiments of the present invention may be implemented using software, and the corresponding software program may be stored in a readable storage medium, such as a CD or a hard disk.

[0144] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A wool-like air-textured yarn air-textured device, characterized in that: include: A first yarn guide core body (4); A yarn feeding hole (1) is provided in the first yarn guide core body (4); A first yarn guide channel (3) is connected to the yarn inlet hole (1); the first yarn guide channel (3) is connected to a first turbulence chamber (5); a first air inlet channel (201) is connected to one side of the first turbulence chamber (5); and the first air inlet channel (201) is connected to the first air inlet hole (2); A second yarn guide core body (8) is installed on one side of the first yarn guide core body (4); A second yarn guide channel (7) is connected to the first yarn guide channel (3), and the second yarn guide channel (7) is arranged in the second yarn guide core body (8); the second yarn guide channel (7) is connected to a second turbulent cavity (9); one side of the second turbulent cavity (9) is connected to a second air inlet channel (601); one end of the second air inlet channel (601) is connected to a second air inlet hole (6); the other side of the second turbulent cavity (9) is connected to a yarn outlet hole (10); A blocking body (11) is provided on one side of the second yarn guide core body (8); The first yarn guide core body (4) and the second yarn guide core body (8) are an integrated structure; The blocking body (11) is a tile-shaped blocking body; The tile-shaped baffle is a rotatable structure.

2. The air-textured yarn device of wool-like air-textured yarn according to claim 1, characterized in that: The first air inlet hole (2) passes through the side wall of the first yarn guide core body (4), and the second air inlet hole (6) passes through and is connected to the side wall of the second yarn guide core body (8).

3. The air-textured device for wool-like air-textured yarn according to claim 1, characterized in that: The yarn inlet hole (1) and the yarn outlet hole (10) are designed to be trumpet-shaped.

4. A process for preparing wool-like air-textured yarn, which is realized based on the air-textured yarn device of any one of claims 1 to 3, and is characterized in that: The following steps are involved: The first step is to moisten the wool-like air-textured yarn before it enters the air-textured yarn device; The second step is to preliminarily set the equipment parameters of the air-deformed yarn device, including: the distance D between the baffle (11) and the yarn outlet (10), the overfeed rate SR, the original yarn characteristic influencing parameter YF, the air flow influencing parameter NP of the first air inlet (2), and the air flow influencing parameter N2P of the second air inlet (6); based on the preliminarily set equipment parameters, the air-deformed yarn is preliminarily obtained, and its performance is characterized by testing; The third step is to optimize the equipment parameters using chaotic neural network; Step 4: Set D, SR, YF, NP, and N2P according to the optimized parameters; The fifth step is to place the yarn into the air-changing device for processing; The third step of optimizing equipment parameters by using a chaotic neural network includes: Step 1, data preparation; Step 2, data preprocessing; Step 3: Network architecture design; The network architecture design includes an input layer, a hidden layer and an output layer; The specific expression is: where v jk is the weight from the jth neuron in the hidden layer to the kth neuron in the output layer; r is the control parameter of the chaotic map; n is the number of input nodes in the input layer; m is the number of hidden nodes in the hidden layer; w ij represents the weight from the i-th neuron in the input layer to the j-th neuron in the hidden layer; x i represents the i-th input of the input layer; b j is the bias of the jth neuron in the hidden layer; c k is the bias of the kth neuron in the output layer.

5. The process for preparing wool-like air-textured yarn according to claim 4, characterized in that: The value of the control parameter r of the chaotic mapping is 3.

58.

6. The process for preparing wool-like air-textured yarn according to claim 4, characterized in that: The data preprocessing in step 2 includes: Step 2.1, data outlier detection; Step 2.2, standardize and normalize the data; The standardized expression is: Among them, x i ′ is the standardized data, x i is the input data, μ is the mean of the input data, and σ is the variance of the input data; The normalized expression is: where x max and x min are the maximum and minimum values ​​of the normalized data.

7. The process for preparing wool-like air-textured yarn according to claim 6, characterized in that: The data outlier detection in step 2.1 includes the following steps: If |Z|>Z th , then the data point is considered an outlier if |Z|≤Z th , then the data point is considered a normal data point, Z th is a pre-set threshold.

Images