A method for preparing high-performance smart gloves

Abstract

The present invention discloses a method for preparing high-performance smart gloves in the field of information technology. The method comprises: performing a calendering treatment on a woven knitted fabric, reducing the thickness of the knitted fabric by 20% and increasing the air permeability by 30% from the initial value by controlling the calendering pressure to 2 MPa, the calendering temperature to 120 degrees Celsius, and the calendering speed to 20 meters per minute, thereby further improving the sensitivity and air permeability of the gloves; cutting the hydrophobic-finished knitted fabric into a glove shape, and using laser cutting technology to produce a honeycomb air permeable structure with a diameter of 3 mm and a depth of 1 mm on the palm and fingertips of the gloves, thereby further increasing the air permeability area and sensitivity of the gloves; and sewing an inner fabric with the honeycomb air permeable structure to an outer fabric using a double-needle chain sewing machine and high-strength sewing thread to ensure that the honeycomb air permeable structure precisely corresponds to the outer fabric, thereby producing a smart glove with high elasticity, air permeability and perspiration wicking properties, and a flexible feel.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a manufacturing process for gloves, and in particular to a method for preparing high-performance smart gloves. Background Art

[0002] The development of highly sensitive dispensing gloves presents a series of interrelated technical challenges. First, achieving both softness and antistatic properties requires precise control over fiber selection and blending ratios. However, while increasing the proportion of conductive fibers improves antistatic properties, this can compromise softness and dexterity. Second, achieving breathability and a snug fit requires a specialized knit structure and calendering, but this can compromise abrasion resistance and strength. Furthermore, to enhance slip resistance and abrasion resistance, a hydrophobic finish and dispensing treatment are used, but this can compromise breathability and sensitivity. Finally, creating a honeycomb-like breathable structure in the palm and fingertips improves sensitivity and breathability, but this can also compromise protective performance in these critical areas. These conflicting requirements necessitate finding the optimal balance between various properties to develop a smart glove that meets dispensing process requirements while also offering excellent feel and dexterity. Summary of the Invention

[0003] The present invention provides a method for preparing high-performance smart gloves, which comprises the following steps:

[0004] Step S1: Based on the requirements for glove flexibility and wear resistance, 120 denier / 48 fiber silk protein fiber is selected as the natural fiber, and 40 denier spandex coated with 200 denier conductive yarn is selected as the conductive fiber, and the two fibers are blended in a ratio of 30:70 to prepare a high-elastic blended yarn with both softness and antistatic properties;

[0005] Step S2: Using a double-sided weft knitting process, a mesh structure with a pore size of 2 mm is designed and woven using the aforementioned high-elasticity blended yarn. A 150-denier polyester moisture-absorbing and quick-drying yarn is woven into the inner layer of the knitted fabric to obtain a knitted fabric with excellent fit and breathability. The warp density is controlled at 40 threads / inch, the weft density is controlled at 38 threads / inch, and the surface density is controlled within the range of 200-250 grams / square meter to ensure the sensitivity and softness of the glove.

[0006] Step S3, calendering the knitted fabric. By controlling the calendering pressure to 2 MPa, the calendering temperature to 120 degrees Celsius, and the calendering speed to 20 meters per minute, the thickness of the knitted fabric is reduced by 20%, and the air permeability is increased by 30% from the initial value, thereby further improving the sensitivity and air permeability of the gloves.

[0007] Step S4: performing a hydrophobic finishing on the calendered knitted fabric surface by immersing the knitted fabric in an emulsion prepared with an environmentally friendly fluorocarbon resin, acrylate, and deionized water in a ratio of 1:2:7 at 25 degrees Celsius for 30 minutes to increase the contact angle of the fabric to 120 degrees, thereby improving the anti-slip and wear resistance of the gloves.

[0008] Step S5: Cut the hydrophobically finished knitted fabric into a glove shape, and use laser cutting technology to create a honeycomb-shaped breathable structure with a diameter of 3 mm and a depth of 1 mm on the palm and fingertips of the glove to further increase the breathable area and sensitivity of the glove;

[0009] Step S6: Sewing the inner fabric with the honeycomb breathable structure to the outer fabric using a double-needle chain stitch machine and high-strength sewing thread to ensure that the honeycomb breathable structure and the outer fabric are precisely aligned, thereby producing a smart glove with high elasticity, breathability and perspiration-wicking properties, and a flexible feel.

[0010] Step S7: Evaluate the performance of the finished smart gloves. Test the antistatic properties of the gloves using a surface resistance tester, test the air permeability of the gloves using a dynamic hot plate method, and test the perspiration and quick-drying properties of the gloves using an artificial climate chamber. When the surface resistance exceeds 1×10^9 ohms, increase the proportion of conductive fibers by 5%. When the air permeability is less than 80 mm / s, increase the pore size of the mesh structure by 0.5 mm or increase the density of the honeycomb structure by 10%. When the perspiration and quick-drying time exceeds 30 minutes, increase the content of polyester moisture-absorbing and quick-drying yarn by 10% or optimize the hydrophobic finishing process parameters.

[0011] In step S8, after adjusting the gloves according to the performance evaluation results, a uniform layer of glue is applied to the palm and fingertips of the smart gloves. By controlling the viscosity, coating speed, and coating pressure of the glue, the thickness of the glue layer is controlled to 0.1-0.2 mm to ensure the anti-slip and sensitivity of the gloves. A polyurethane glue with good flexibility and strong wear resistance is selected and cured with UV light to further improve the wear resistance and service life of the gloves. At the same time, precision-controlled glue dispensing equipment is used during the glue coating process to retain 30% of the uncoated microporous structure in the glued area to maintain the breathability and perspiration properties of the gloves.

[0012] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0013] The present invention discloses a method for preparing high-performance smart gloves. High-elastic yarn is prepared by blending silk protein fiber and conductive yarn, and a double-sided weft knitting process is used to weave a knitted fabric with a mesh structure. Moisture-absorbing and quick-drying yarn is woven into the inner layer. The knitted fabric is calendered and hydrophobically finished to improve the glove's sensitivity, breathability, and anti-slip properties. Laser cutting technology is used to create a honeycomb-shaped breathable structure on the palm and fingertips to further increase the breathable area. The gloves are optimized and adjusted through performance evaluation, and finally, a dispensing layer is applied to the palm and fingertips while retaining part of the microporous structure. The present invention addresses the comprehensive performance issues of smart gloves in terms of softness, antistatic properties, breathability and perspiration wicking, and sensitivity. Through the synergistic effect of multiple innovative processes and structural designs, the gloves achieve high elasticity, excellent fit, good breathability and perspiration wicking properties, and a flexible feel. At the same time, they have anti-slip and wear-resistant properties, meeting multiple performance requirements of smart gloves. DETAILED DESCRIPTION

[0014] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0015] The method for preparing a high-performance smart glove in this embodiment may specifically include:

[0016] Step S1: Based on the requirements of glove flexibility and wear resistance, 120 denier / 48 fiber silk protein fiber is selected as the natural fiber, and 40 denier spandex coated with 200 denier conductive yarn is selected as the conductive fiber, and they are blended in a ratio of 30:70 to prepare a high-elastic blended yarn with both softness and antistatic properties.

[0017] Step S1 includes: obtaining initial mixing ratio data for fibroin fibers and conductive fibers, setting the initial mixing ratio to 30:70 using a computer program, and obtaining an initial mixing ratio model. Data for 120 denier / 48 denier fibroin fibers and 40 denier spandex-coated 200 denier conductive fibers are obtained, and the fineness data are used as input parameters for the mixing ratio model to obtain a mixing ratio adjustment model for specific finenesses. The mixing ratio adjustment model is iteratively optimized based on yarn denier requirements. If the yarn denier does not meet a preset range, the finenesses of the fibroin fibers and conductive fibers are adjusted to obtain an optimal fineness combination that meets the yarn denier requirements. A preliminary blending test is conducted using this optimal fineness combination, and an electron microscope is used to observe the fiber distribution image after blending to obtain fiber distribution uniformity data. It is then determined whether the fiber distribution uniformity data meets a set threshold. Based on the fiber distribution uniformity data, blending process parameters are optimized. If the fiber distribution uniformity data falls below the set threshold, the blending process parameters are adjusted to obtain optimized blending process parameters and obtain new fiber distribution uniformity data. Sensors are used to detect the static electricity and elasticity of the blended yarn, obtaining yarn static electricity data and yarn elasticity data, and determining whether the yarn static electricity data and yarn elasticity data meet the performance requirements of the gloves. Based on the yarn static electricity data and yarn elasticity data, if the yarn static electricity data or yarn elasticity data does not meet the requirements, the ratio of the silk protein fiber to the conductive fiber is adjusted to obtain a highly elastic antistatic blended yarn that meets the flexibility and wear resistance requirements of the gloves.

[0018] Specifically, the blend ratio of silk protein fiber and conductive fiber is crucial for producing high-performance antistatic gloves. The initial blend ratio was set at 30:70, based on the excellent softness of silk protein fiber and the antistatic properties of conductive fiber. For example, a 30% silk protein fiber content provides adequate comfort, while a 70% conductive fiber ensures good static dissipation. Denier is a key factor influencing yarn performance. The silk protein fiber has a denier of 120 denier / 48 fiber, meaning each fiber is approximately 2.5 denier. The conductive fiber is constructed using a 40 denier spandex wrapped around a 200 denier spandex. This design ensures conductivity while enhancing the yarn's elasticity. Inputting this denier data into the blend ratio model allows for more accurate predictions of the final yarn's physical properties. Adjusting yarn denier is an iterative optimization process. For example, if the target yarn denier is 300 denier, the initial model might yield a denier of 280 denier. The desired yarn denier can be achieved by increasing the silk protein fiber fineness to 130 denier / 48 denier or adjusting the conductive fiber to 45 denier spandex coated with 220 denier. This process may require multiple adjustments until the optimal fineness combination is achieved. The choice of blending method significantly impacts fiber distribution uniformity. Airflow blending can be used for preliminary trials, as it effectively disperses different fiber types. Electron microscopy of the blended fiber cross-section provides quantitative fiber distribution data. For example, if the uniformity threshold is set at 90%, but observations show only 85% uniformity, the blending process parameters need to be optimized. These optimizations may include adjusting the airflow velocity and feed rate. For example, increasing the airflow velocity from an initial 20 m / s to 25 m / s may significantly improve fiber dispersion. At the same time, reducing the feed rate allows the fibers more time to fully mix. Through these adjustments, fiber distribution uniformity can be increased to 92%, exceeding the set threshold. Yarn static electricity and elasticity are important indicators for evaluating glove performance. The surface resistance of the yarn can be measured using an electrostatic tester. For example, the target value may be set at 10^6-10^9 ohms. If the measured resistance value is 10^10 ohms, it indicates that the static dissipation ability is insufficient. Elasticity testing can be performed through a stretch recovery experiment, such as setting the recovery rate at 50% elongation to be no less than 95%. If the actual measured recovery rate is only 90%, it indicates insufficient elasticity. If the static or elastic data does not meet the requirements, the fiber ratio needs to be readjusted. For example, to improve the static dissipation ability, the conductive fiber ratio can be increased to 75%. To improve elasticity, a more elastic spandex fiber can be selected, such as 50 denier spandex coated with 180 denier conductive fiber. This adjustment may affect other properties, so multiple iterations are required to find the optimal balance. The entire process embodies a closed-loop optimization system, where each step, from initial design to final product, is adjusted based on the results of the previous step.This method effectively balances multiple performance indicators, such as static dissipation, elasticity, and comfort, ultimately resulting in a highly elastic, antistatic blended yarn that meets the flexibility and abrasion resistance requirements of gloves. This systematic approach can significantly improve the efficiency and success rate of product development, reduce trial and error costs, and accelerate the time to market for new products.

[0019] In step S2, a double-sided weft knitting process is used to design a mesh structure with an aperture of 2 mm. The mesh is woven using the aforementioned high-elasticity blended yarn. A 150-denier polyester moisture-absorbing and quick-drying yarn is woven into the inner layer of the knitted fabric to obtain a knitted fabric with excellent fit and breathability. The warp density is controlled at 40 threads / inch, the weft density is controlled at 38 threads / inch, and the surface density is controlled within the range of 200-250 g / m2 to ensure the sensitivity and softness of the gloves.

[0020] Step S2 includes: obtaining real-time operating parameters of the double-sided weft knitting machine, the operating parameters including speed, yarn feeding amount and pulling tension data; constructing a high-elastic yarn tension feature vector set according to the operating parameters; judging whether the operating parameters exceed the preset range, and if so, triggering an alarm mechanism and controlling the equipment to stop running; according to the alarm mechanism, using a control system to adjust the yarn feeding amount and pulling tension to obtain operating parameters that meet the preset range, determining that the equipment is operating normally, and generating a normal operating equipment number; retrieving corresponding process parameters from a database through the equipment number, the process parameters including aperture size, warp density and weft density data; using a photoelectric sensor to detect actual weaving parameters, judging whether the deviation between the actual weaving parameters and the process parameters exceeds a threshold, and if so, generating deviation data; according to the deviation The method comprises the following steps: first, collecting the image information of the mesh structure, performing grayscale and binarization processing on the image information; extracting the mesh edge contour through the edge detection algorithm, calculating the area of ​​each mesh, and judging whether the mesh area is within the set range; if the mesh area is not within the set range, repeating steps 6 and 7 until the mesh area is qualified, obtaining a fabric with a qualified mesh structure, and generating a fabric number; extracting the fabric weight data from the database through the fabric number, scanning the fabric thickness with an infrared sensor, and obtaining the thickness data; fusing the thickness data and the weight data, calculating the fabric surface density, and obtaining the result that the fabric surface density data is within the preset range.

[0021] Specifically, double-sided weft knitting machines are key equipment for producing highly elastic mesh fabrics. Obtaining their real-time operating parameters is crucial for ensuring fabric quality. Rotational speed, yarn feed rate, and draw tension are three core parameters that collectively determine the fabric's structure and properties. For example, excessive rotational speed can cause yarn breakage, insufficient yarn feed rate can make the fabric too tight, and excessive draw tension can cause deformation. By constructing a feature vector set for these parameters, comprehensive monitoring of the machine's operating status is possible. Triggering an alarm and shutting down the machine when parameters exceed preset ranges is a protective measure. For example, if the yarn feed rate suddenly drops below 50% of the normal value, the system will immediately generate an alarm and shut down the machine, preventing the production of a large number of substandard products. Operators can then adjust parameters based on the alarm, such as increasing the yarn feed rate or reducing the draw tension, to restore them to the normal range. Each machine has a unique number associated with its corresponding process parameters. For example, a machine numbered WM001 might be configured to produce mesh fabric with a 2mm aperture, a warp density of 40 ends / cm, and a weft density of 35 ends / cm. Photoelectric sensors monitor these parameters in real time, enabling timely detection of deviations. If the warp density reaches 45 strands / cm, exceeding the preset range of 40 ± 2 strands / cm, the system generates deviation data. PID control algorithms are widely used in the textile industry for parameter adjustment. Through a combination of proportional, integral, and differential control, they enable rapid and accurate adjustment of machine conditions. For example, if the warp density is detected to be too high, the PID controller calculates the necessary reduction in warp let-off and, through an actuator, precisely adjusts the let-off motor speed to restore the warp density to the set value. The mesh structure is a key feature of high-elasticity gloves. Image processing techniques enable precise assessment of mesh quality. First, the captured image is grayscaled to eliminate color interference. Then, the image is binarized and converted to black and white to highlight the mesh outline. Edge detection algorithms, such as Canny, accurately extract mesh edges. By calculating the pixel area of ​​each mesh and comparing it to a preset standard, the mesh size can be determined. If the mesh area is found to be unacceptable, such as exceeding the preset range of 4 ± 0.5 square millimeters, process parameters must be adjusted. This may involve operations such as changing the yarn feed amount and adjusting the pulling tension. This process may require multiple iterations until a qualified mesh structure is produced. The surface density of the fabric is an important indicator for evaluating its quality. The thickness of the fabric is scanned by an infrared sensor, and the surface density can be calculated in combination with the known weight of the fabric. For example, if a 1 square meter piece of fabric weighs 220 grams and is 1 mm thick, then its surface density is 220 grams per square meter, which falls within the target range of 200 to 250 grams per square meter. The surface density in this range ensures that the fabric has sufficient strength without being too thick and affecting the flexibility of the gloves. Real-time data collection and analysis play a key role in the entire production process.From initial operating parameters to final fabric performance, every step requires precise data support. This data-driven production approach not only improves product quality but also significantly enhances production efficiency. By establishing a complete data chain, full traceability of the production process is possible, facilitating the rapid identification and resolution of problems. Furthermore, the vast amount of accumulated data provides a valuable foundation for future process optimization and product innovation.

[0022] In step S3, the knitted fabric is calendered. By controlling the calendering pressure to 2 MPa, the calendering temperature to 120 degrees Celsius, and the calendering speed to 20 meters per minute, the thickness of the knitted fabric is reduced by 20% and the air permeability is increased by 30% from the initial value, thereby further improving the sensitivity and air permeability of the gloves.

[0023] Specifically, fabric calendering is an important process to improve fabric performance. First, the initial state data of the fabric is collected, including thickness and air permeability. For example, the initial thickness of a piece of cotton fabric is 0.8mm and the air permeability is 150cm 3 / cm 2 / s. These data are recorded by the sensor network system to form the initial fabric performance data set. Based on the initial data, a priori knowledge base and mapping model are established. The support vector machine algorithm is used to establish the relationship between calendering parameters and fabric performance. For example, input thickness 0.8mm and air permeability 150cm 3 / cm 2 / s, the model may output a calendering pressure of 2MPa, a temperature of 120°C, and a speed of 5m / min. This model can predict the optimal calendering parameters for different fabric properties. After obtaining the target fabric performance data, the required performance improvement is calculated. Assuming the target thickness is 0.6mm and the target air permeability is 200cm 3 / cm 2 / s, the thickness needs to be reduced by 25% and the air permeability needs to be increased by 33%. These data are standardized and used for subsequent model adjustments. When the demand for performance improvement is large, the support vector machine model needs to be adjusted. For example, if the thickness reduction demand exceeds 20% and the air permeability improvement demand exceeds 30%, it may be necessary to increase the training samples or adjust the kernel function parameters to improve the prediction accuracy of the model. According to the updated calendering parameters, the lathe is controlled by the CNC system to perform calendering. For example, the system may set the calendering pressure to 2.5MPa, the temperature to 130℃, and the speed to 4m / min. These parameters are precisely controlled by the actuator to ensure the stability and consistency of the calendering process. After calendering, the fabric performance data is collected again. Assume that the thickness after treatment is 0.62mm and the air permeability is 195cm 3 / cm 2 / s. These data are conditioned by the data acquisition card and converted into digital signals for subsequent analysis and comparison. Finally, the processed data are compared with the target data. If the error between the thickness and air permeability after treatment and the target value is within an acceptable range (such as ±5%), the calendering parameters are considered to be the optimal parameters. These parameters will be recorded in the prior knowledge base to guide the calendering treatment of similar fabrics in the future. This process reflects the refined control and continuous optimization of the calendering process. Through data-driven and machine learning methods, the calendering effect can be continuously improved, material waste can be reduced, and production efficiency can be improved. At the same time, this method also provides the possibility for personalized treatment of different types of fabrics. According to the characteristics and target performance of different fabrics, the calendering parameters can be flexibly adjusted to achieve the best treatment effect.

[0024] In step S4, the calendered knitted fabric surface is subjected to a hydrophobic finishing process using an emulsion composed of an environmentally friendly fluorocarbon resin, acrylate, and deionized water in a ratio of 1:2:7. The treatment is performed by immersion at 25 degrees Celsius for 30 minutes to increase the contact angle of the fabric to 120 degrees, thereby improving the anti-slip and wear resistance of the gloves.

[0025] Step S4 includes: obtaining a knitted fabric after calendering as a base material for hydrophobic finishing. According to the formula ratio of 1:2:7, environmentally friendly fluorocarbon resin, acrylate and deionized water are mixed to prepare a hydrophobic finishing emulsion. The knitted fabric is immersed in the hydrophobic finishing emulsion, the immersion temperature is controlled to 25°C, and the immersion time is 30 minutes. The knitted fabric after immersion is taken out and deliquescence treatment is carried out to remove excess hydrophobic finishing emulsion. The knitted fabric after deliquescence is dried and shaped to ensure that the hydrophobic finishing agent is fully combined with the knitted fabric. A contact angle meter is used to measure the contact angle of the knitted fabric surface after hydrophobic finishing to determine whether it reaches the target value of 120°. If not, steps 3-5 are repeated until the requirements are met. The knitted fabric after hydrophobic finishing is used to make gloves, and the anti-slip and wear resistance of the gloves are evaluated through friction coefficient test and wear resistance test to ensure that the expected performance requirements are met.

[0026] Specifically, hydrophobic finishing is a key process for improving the water repellency of knitted fabrics. First, a calendered knitted fabric is used as the substrate. This ensures surface smoothness, facilitating the uniform adhesion of the subsequent hydrophobic agent. The hydrophobic finishing emulsion is formulated in a ratio of 1:2:7, with an environmentally friendly fluorocarbon resin as the primary hydrophobic component, an acrylate providing adhesion, and deionized water as the dispersion medium. This ratio ensures hydrophobicity while minimizing environmental impact. The impregnation process is controlled at a temperature of 25°C and a duration of 30 minutes, which allows the hydrophobic agent to fully penetrate the fabric fibers. For example, excessively high temperatures may cause the emulsion to become unstable, while too short a duration may result in insufficient penetration. The stripping process removes excess emulsion, avoiding waste and compromising the subsequent finishing effect. Drying and finishing is a critical step, not only ensuring the hydrophobic agent fully bonds to the fabric but also solidifying the hydrophobic layer, enhancing its durability. Contact angle measurement is a key indicator for evaluating hydrophobicity. A target value of 120° indicates good hydrophobicity; if this is not achieved, repeated treatments are required to improve the finish. For example, if the contact angle is 110° after the initial treatment, further dipping or adjustment of the emulsion ratio may be necessary to improve hydrophobicity. This iterative optimization ensures consistent performance in the final product. The treated knitted fabric is then used to make gloves for coefficient of friction and abrasion resistance testing. The coefficient of friction test assesses the glove's slip resistance, for example, by using the inclined plane method, measuring the angle at which the glove begins to slide. Abrasion resistance testing employs the Martindale method, recording the number of frictions before the fabric breaks. These test results directly correlate to the actual performance of the gloves. The entire hydrophobic finishing process embodies meticulous control and quality assurance. From raw material selection to process parameter setting to final performance evaluation, every step is meticulously designed. For example, the use of environmentally friendly fluorocarbon resin ensures a hydrophobic effect while reducing environmental impact. Precise control of dipping temperature and time ensures uniform distribution of the hydrophobic agent. This comprehensive quality control system not only improves product performance but also enhances the repeatability and stability of the production process. This systematic hydrophobic finishing process significantly enhances the water repellency and service life of knitted gloves. For example, treated gloves maintain excellent grip even in wet conditions, reducing the risk of slippage. Furthermore, the hydrophobic treatment reduces water absorption, reducing the weight of the gloves when wet, and improving wearer comfort. These improvements directly impact the practicality and safety of gloves in various work environments, particularly those requiring delicate work in wet conditions.

[0027] In step S5, the hydrophobically treated knitted fabric is cut into a glove shape, and a honeycomb breathable structure with a diameter of 3 mm and a depth of 1 mm is produced on the palm and fingertips of the glove using laser cutting technology to further increase the breathable area and sensitivity of the glove.

[0028] Specifically, a knitted fabric that has undergone a hydrophobic finish is first obtained. This surface exhibits excellent hydrophobicity, with a contact angle of 120 degrees, effectively preventing water penetration and forming the foundation for high-performance gloves. For example, in the medical field, doctors need to wear gloves during surgical procedures. If the gloves are not hydrophobic enough, blood or other body fluids may penetrate the glove interior and cause contamination. Using knitted fabric with a hydrophobic finish can effectively prevent this, ensuring safe and hygienic surgical procedures. After obtaining the hydrophobic-finished knitted fabric, the knitted fabric is cut according to a pre-designed glove template, such as a template for a standard glove with five separate fingers or a template for mittens designed for specific working environments. This step can be performed using automated cutting equipment, such as a computerized cutting machine. With a pre-programmed cutting path, the machine can precisely cut the knitted fabric to the desired shape, ensuring that each piece of knitted fabric conforms to the glove's desired shape and is ready for subsequent sewing. To enhance the gloves' breathability, laser cutting technology is used to create tiny honeycomb-shaped pores in the palm and fingertips. Laser cutting technology uses a high-energy-density laser beam to locally heat the material, melting or vaporizing it to achieve the desired cutting effect. This technology offers advantages such as high precision, smooth cuts, and a minimal heat-affected zone, making it ideal for processing delicate, breathable structures. For example, for workers who need to wear gloves for extended periods, breathability is crucial. Poor breathability can lead to sweating on the palms, compromising comfort and potentially reducing work efficiency. By creating honeycomb-shaped ventilation holes with a diameter of 3 mm and a depth of 1 mm on the palms and fingertips, the air permeability area is increased while maintaining structural strength, improving air circulation, reducing sweating, and enhancing wearer comfort. The knitted fabric, cut and processed with ventilation holes, is then sewn together. This sewing process can be automated using automated sewing equipment, which stitches the various sections of knitted fabric together according to a pre-set sewing template using various seaming methods, such as flat seams, overlock seams, and stretch seams, to complete the glove. This step requires ensuring that the seams are firm, uniform, and aesthetically pleasing, avoiding issues such as missed seams and skipped stitches to ensure glove durability. For example, in industrial production, workers need to wear gloves for handling, assembly, and other operations. Poor glove stitching can easily lead to problems such as thread unraveling and breakage, shortening the gloves' service life. High-quality stitching ensures the gloves' durability and extends their service life. After stitching, the finished gloves need to be evaluated for their breathability and sensitivity. This can be determined using a professional breathability tester. The instrument simulates air circulation, measuring the air flow through the gloves per unit time, thereby calculating the breathable area.For example, if the breathability threshold is set at 10 square centimeters, and the test results show that a particular glove has a breathability of 12 square centimeters, exceeding the threshold, the glove's breathability meets the requirements. Sensitivity can be assessed through experiments simulating a finger touching an object. For example, a sensor can be used to measure the pressure change generated when a finger touches an object through a glove to determine the degree to which the glove hinders tactile perception. For example, if the sensitivity threshold is set at 90%, and the test results show that a particular glove has a sensitivity of 95%, exceeding the threshold, the glove's sensitivity meets the requirements. Finally, finished gloves are sorted based on the breathability and sensitivity test results. Only when both breathability and sensitivity meet the requirements are they sent to the next process, such as packaging and disinfection. Unqualified gloves are sent to waste recycling to prevent substandard products from entering the market. For example, for electronic assembly workers who need to perform delicate operations, the sensitivity of gloves is very important. If the sensitivity of the gloves is poor, it will affect the accuracy of the operation, reduce work efficiency, and even cause product defects. Through strict quality testing, it can be ensured that only gloves that meet the sensitivity standards can be shipped, ensuring product quality.

[0029] In step S6, the inner fabric with the honeycomb breathable structure and the outer fabric are sewn together using a double-needle chain sewing machine and high-strength sewing thread to ensure that the honeycomb breathable structure precisely corresponds to the outer fabric, thereby producing a smart glove with high elasticity, breathable and perspiration-wicking properties, and flexible feel.

[0030] Step S6 includes: collecting three-dimensional image information of the outer layer fabric and determining the curvature distribution map of the outer layer fabric; identifying the area of ​​the outer layer fabric to be sewn through a deep learning algorithm based on the curvature distribution map of the outer layer fabric, and obtaining the contour of the area to be sewn; and matching a pre-established inner layer fabric database based on the contour of the area to be sewn to obtain three-dimensional model data of the inner layer fabric to be sewn.

[0031] Specifically, a high-resolution industrial camera is used to capture the cut outer fabric from multiple angles, such as from the front, side, and top. Each capture captures at least 100 images to ensure every detail of the fabric surface is captured. This image data forms a three-dimensional image of the outer fabric. Professional 3D reconstruction software then combines these two-dimensional images into a complete three-dimensional model. This model accurately reflects the spatial position information of the outer fabric surface, including the spatial coordinates (x, y, z) of each point. Using these coordinates, a curvature map of the outer fabric can be constructed. For example, by calculating the radius of curvature of the area surrounding each point, areas with a radius less than 5 cm are labeled as high curvature, typically corresponding to the fingertips and joints of the glove. Areas with a radius greater than 20 cm are labeled as low curvature, corresponding to flatter areas such as the palm of the glove. Based on this curvature map of the outer fabric, a deep learning algorithm is used to identify the areas to be stitched. For example, a convolutional neural network model can be trained that takes the curvature map as input and outputs the contours of the areas to be stitched. The training dataset contains 10,000 glove curvature distribution images with labeled areas to be stitched. Through this large number of training samples, the model learns the mapping relationship between different curvature features and the areas to be stitched. The trained model accurately identifies the areas to be stitched, such as the fingertip-palm junction and the finger-to-finger junction, and outputs the precise contours of these areas. After obtaining the contours of the areas to be stitched, an image matching algorithm is used to search for matches within a pre-established database of honeycomb-structured ventilated inner fabrics. This database contains 3D models of honeycomb-structured ventilated structures of various sizes and shapes. For example, the database might include models of glove inner fabrics in sizes S, M, and L for different hand shapes, with each size containing 10 models of different honeycomb-structured ventilated structures. By calculating the similarity between the contours of the areas to be stitched and the models in the database, the best matching model can be found. For example, a shape context-based matching algorithm can be used to calculate the shape features of each point on the contour and compare them. The model with the highest similarity is ultimately selected as the 3D model data for the inner fabric to be stitched. Based on the matched 3D model data of the inner fabric to be stitched, a 3D modeling algorithm is used to generate a spatial fitting model of the inner and outer fabrics. For example, the inner and outer fabric models can be spatially registered to achieve optimal fit in 3D space. Then, using finite element analysis, the fitting model is discretized into a large number of tiny cells. For example, the edge of each honeycomb structure can be divided into 10 cells, each approximately 0.3 mm in size. Mechanical analysis is performed on each cell to calculate the forces acting on it during stitching and determine the precise spatial coordinates of each stitching point.For example, the coordinates of a certain point to be stitched at the fingertip can be determined to be (10.2, 25.8, 5.3). Based on the spatial coordinates of each point to be stitched, the motion trajectory information of the sewing machine is generated by a path planning algorithm. For example, the A* algorithm can be used to take the point to be stitched as a path node and calculate a path from the starting point to the end point that passes through all the points to be stitched and has the shortest path. This path is the trajectory that the sewing machine needle needs to move. Then, this trajectory information is converted into a control signal, for example, the coordinates of each point to be stitched are converted into a motion instruction of the robotic arm, and the robotic arm is controlled to drive the sewing machine to move along the predetermined trajectory. During the sewing process, the robotic arm controls the double-needle chain sewing machine to move according to the generated control signal. At the same time, the position information of the sewing machine needle is obtained in real time through a high-precision position sensor, for example, the position coordinates of the needle are collected every 0.1 seconds. The real-time position is compared with the predetermined spatial coordinates of the stitching point. If the deviation exceeds a preset threshold, for example, greater than 0.5 mm, a PID control algorithm is used to adjust the robotic arm's motion parameters, such as its speed and angle, to precisely return the needle to the predetermined trajectory. Furthermore, during the sewing process, a tension sensor collects real-time tension data on the high-strength sewing thread, for example, every 0.05 seconds. A fuzzy control algorithm dynamically adjusts the thread tension based on the real-time tension data and a preset tension target. For example, if the tension is detected to be excessive, exceeding the preset target of 2 Newtons, the motor is controlled to loosen the thread, reducing the tension. If the tension is too low, the thread is tightened, increasing the tension. This method achieves the optimal thread tension and ensures stitching quality. This completes the stitching of the smart glove, ensuring its strength and durability while maintaining good breathability and sensitivity.

[0032] Step S7: Evaluate the performance of the completed smart gloves. The gloves' antistatic properties are tested using a surface resistance tester, their air permeability is tested using a dynamic hot plate method, and their perspiration and quick-drying properties are tested using an artificial climate chamber. If the surface resistance exceeds 1×10^9 ohms, the proportion of conductive fiber is increased by 5%. If the air permeability is less than 80 mm / s, the mesh size is increased by 0.5 mm or the density of the honeycomb structure is increased by 10%. If the perspiration and quick-drying time exceeds 30 minutes, the content of the polyester quick-drying yarn is increased by 10%, or the hydrophobic finishing process parameters are optimized.

[0033] Step S7 includes: obtaining a finished smart glove sample, and testing the surface resistance of the smart glove sample using a surface resistance tester; if the surface resistance exceeds a preset resistance threshold, increasing the proportion of conductive fiber by a preset proportion, and reproducing the smart glove sample until the surface resistance is less than or equal to the preset resistance threshold, thereby obtaining a smart glove sample that meets the antistatic performance requirements; testing the air permeability of the smart glove sample that meets the antistatic performance requirements using a dynamic hot plate method; if the air permeability is lower than the preset air permeability threshold, increasing the aperture of the mesh structure by a first preset length or the density of the honeycomb structure by a first preset density according to the structural characteristics of the smart glove sample, and reproducing the smart glove sample until the air permeability is greater than or equal to the preset air permeability threshold, thereby obtaining a smart glove sample that meets the antistatic performance and air permeability requirements; testing the perspiration wicking and quick-drying performance of the smart glove sample that meets the antistatic performance and air permeability requirements using an artificial climate chamber; if the surface humidity of the smart glove sample does not reach a preset dryness within a preset time, replacing the polyester moisture-absorbing quick-drying yarn with a polyester moisture-absorbing quick-drying yarn; The content of the hydrophobic finishing process is increased to a second preset ratio, or the temperature and time parameters of the hydrophobic finishing process are optimized, and the smart glove sample is remade until the preset dryness is reached within the preset time, thereby obtaining a smart glove sample that meets the requirements of antistatic performance, breathability, and perspiration-wicking and quick-drying performance. A support vector machine algorithm is used to train and optimize a smart glove performance prediction model with the conductive fiber ratio, mesh aperture, honeycomb density, and moisture-absorbing and quick-drying yarn content as input features and the antistatic, breathability, and perspiration-wicking and quick-drying test results of the smart glove sample as output. In the subsequent smart glove production process, the smart glove performance prediction model is used to predict whether the comprehensive performance of the smart glove meets the requirements based on the raw material characteristics and process parameters. If not, the material ratio and process parameters are adjusted with reference to the optimization suggestions provided by the smart glove performance prediction model. Actual performance test data of each batch of smart gloves is continuously collected for continuous optimization and iterative updating of the smart glove performance prediction model, thereby improving the generalization ability and prediction accuracy of the smart glove performance prediction model and guiding the formulation design and production of smart gloves.

[0034] Specifically, the performance testing and optimization of smart gloves is a multi-step, iterative process. First, the antistatic performance test uses a surface resistivity tester, which calculates resistance by applying voltage to the glove surface and measuring the current. For example, if the measured resistance is 2×10^9 ohms, exceeding the standard of 1×10^9 ohms, the conductive fiber content needs to be increased. The original 20% conductive fiber content can be increased to 25%, and samples can be re-produced and tested until the standard is met. The breathability test uses the dynamic hot plate method, which simulates the heat dissipation process of human skin and evaluates the material's breathability by measuring the heat transfer rate. If the measured air permeability is 60 mm / s, which is lower than the requirement of 80 mm / s, the glove structure needs to be optimized. For mesh structures, the original 2 mm pore size can be increased to 7 mm; for honeycomb structures, the density can be increased from 50 to 55 cells per square centimeter to improve breathability. The perspiration-wicking and quick-drying performance test uses an artificial climate chamber to simulate different environmental conditions to evaluate the glove's moisture absorption and perspiration wicking ability. For example, if the temperature is set to 35°C and the relative humidity is 80%, if the humidity on the surface of the gloves is still over 60% after 30 minutes, it is considered as not meeting the standard.

[0035] 40%, or increasing the hydrophobic finishing process temperature from 120°C to 130°C and the duration from 30 minutes to 40 minutes to enhance perspiration wicking and quick-drying. A support vector machine algorithm was used to develop a performance prediction model for smart gloves. This algorithm classifies data points by constructing hyperplanes in a high-dimensional space, making it suitable for multivariate nonlinear problems. Input features may include the proportion of conductive fibers (e.g., 25%), mesh size (e.g., 7 mm), cell density (e.g., 55 cells per square centimeter), and the content of moisture-wicking and quick-drying yarn (e.g., 40%). The output is a comprehensive performance score for the glove, such as a weighted average of antistatic properties, breathability, and perspiration wicking and quick-drying properties. In actual production, this model can pre-evaluate the effects of different material ratios and process parameters. For example, if the model predicts a comprehensive performance score of 85 out of 100 for a given formula, below the required score of 90, it might recommend increasing the conductive fiber proportion by 2% or the cell density by 5%. This predictive capability helps reduce trial-and-error costs and improve production efficiency. Continuous optimization of the model is key to ensuring its accuracy. Actual test data from each batch of products is used to update the model. For example, if the model predicts the air permeability of a batch of gloves to be 85 mm / s, but the actual test result is 82 mm / s, this error is used to fine-tune the model parameters and improve its prediction accuracy. As the amount of data increases, the model's generalization ability will continue to improve, allowing it to better adapt to changes in raw materials and process conditions. This data-driven approach makes the performance optimization process of smart gloves more scientific and efficient. It not only ensures the stability of product quality but also provides strong support for new product development and promotes the continuous advancement of smart glove technology.

[0036] In step S8, after adjusting the glove based on the performance evaluation results, a uniform layer of adhesive is applied to the palm and fingertips of the smart glove. By controlling the viscosity, coating speed, and coating pressure of the adhesive, the thickness of the adhesive layer is controlled to 0.1-0.2 mm, ensuring the glove's slip resistance and sensitivity. A flexible and wear-resistant polyurethane adhesive is selected and cured with UV light to further improve the glove's wear resistance and service life. Furthermore, during the adhesive application process, precision-controlled adhesive dispensing equipment is used to maintain a 30% uncoated microporous structure in the adhesive-coated area to maintain the glove's breathability and perspiration-wicking properties.

[0037] Step S8 includes: obtaining glove performance data, the glove performance data including the anti-slip property, sensitivity, wear resistance, air permeability and perspiration property of the gloves under different working conditions, and corresponding glue layer parameters, the glue layer parameters including glue viscosity, coating speed, coating pressure, micropore size and curing degree; training a smart glove performance prediction model based on the glove performance data using a support vector machine algorithm, the input of the smart glove performance prediction model being the glue layer parameters and the output being the predicted values ​​of the glove performance parameters; obtaining performance requirement data of the target glove, inputting the performance requirement data into the smart glove performance prediction model, and optimizing the model through a particle swarm algorithm to obtain the optimal glue layer parameters; configuring the glue viscosity, coating speed and coating pressure of the glue dispensing device based on the optimal glue layer parameters, controlling the glue dispensing device to apply glue on the palm and fingertips of the glove to form an initial glue layer, the thickness of the initial glue layer The method comprises the following steps: placing the primary glue layer with a microporous structure in an ultraviolet light curing device, controlling the intensity and irradiation time of the ultraviolet light according to the curing degree parameter in the optimal glue layer parameters, and obtaining a secondary glue layer after UV curing; collecting image information of the secondary glue layer by an image sensor, and extracting thickness and uniformity characteristics of the secondary glue layer; obtaining a final glue layer if the thickness and uniformity characteristics meet the preset range; and inputting the thickness and uniformity characteristics into the smart glove performance prediction model to re-optimize the glue layer parameters if the thickness and uniformity characteristics do not meet the preset range.

[0038] Specifically, building a glove performance database is a key step in the development of smart gloves. By collecting performance parameters under different working conditions, such as slip resistance and sensitivity, and recording the corresponding adhesive layer parameters, a comprehensive data foundation can be established. For example, the slip resistance of gloves can be tested in a low-temperature environment, and the friction coefficient of the gloves on slippery surfaces can be recorded. Parameters such as the adhesive viscosity and coating speed of the adhesive layer can also be recorded. This data collection process can cover a variety of working environments, such as high temperature, high humidity, and oily conditions, ensuring the comprehensiveness and representativeness of the database. Using a support vector machine algorithm to train a smart glove performance prediction model, it is possible to map adhesive layer parameters to glove performance. For example, given adhesive layer parameters of 500 cP, 10 mm / s coating speed, 0.5 MPa coating pressure, 50 μm pore size, and 95% curing degree, the model can predict a slip resistance of 0.8 (friction coefficient), 98% sensitivity, 5000 abrasions (number of abrasions), 85 mm / s air permeability, and 20 minutes of drying time. This predictive capability is invaluable for quickly evaluating the effectiveness of different dispensing parameter combinations. After obtaining target performance requirements, a particle swarm algorithm is used to optimize the dispensing layer parameters. Assuming the target requirements are slip resistance of 0.9, sensitivity of 99%, abrasion resistance of 6,000 times, air permeability of 90 mm / s, and perspiration wicking of 15 minutes, the algorithm might generate optimized dispensing layer parameters: adhesive viscosity of 550 cP, coating speed of 8 mm / s, coating pressure of 0.6 MPa, micropore size of 45 μm, and curing degree of 97%. This optimization process quickly finds the optimal parameter combination that meets the target requirements. Based on the optimized parameters, the dispensing equipment is configured to apply the adhesive to the palm and fingertips of the glove to form an initial dispensing layer. The initial dispensing layer thickness is controlled between 1 and 2 mm by adjusting the coating speed and pressure. For example, a coating speed of 8 mm / s and a pressure of 0.6 MPa might produce a uniform dispensing layer of 1.5 mm. Laser etching is used to create the microporous structure, with the laser power and scanning speed set based on the optimized micropore size of 45 μm. The uncoated microporous structure accounts for 30%, which can be achieved by controlling the density and distribution of laser etching. This microporous structure can significantly improve the breathability and perspiration wicking properties of the gloves while maintaining good anti-slip properties. UV curing is a key step to ensure the performance of the adhesive layer. According to the curing degree parameter of 97%, it may be necessary to set the UV light intensity to 500mW / cm 2 The irradiation time is 30 seconds. This precise control ensures that the dispensed layer achieves optimal physical and chemical properties. Finally, an image sensor captures image information of the secondary dispensed layer and extracts thickness and uniformity characteristics. If the characteristics do not meet the preset range, such as a thickness variation exceeding ±0.2 mm or a uniformity deviation exceeding 5%, the dispensed layer parameters must be re-optimized. This closed-loop control ensures the quality consistency of the final dispensed layer, thereby guaranteeing the overall performance of the smart glove.

[0039] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the concept of this application. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for preparing high-performance smart gloves, characterized in that: The method comprises the following steps: Step S1: Based on the requirements for glove flexibility and wear resistance, 120 denier / 48 fiber silk protein fiber is selected as the natural fiber, and 40 denier spandex coated with 200 denier conductive yarn is selected as the conductive fiber, and the two fibers are blended in a ratio of 30:70 to prepare a high-elastic blended yarn with both softness and antistatic properties; Step S2: Using a double-sided weft knitting process, a mesh structure with a pore size of 2 mm is designed and woven using the aforementioned high-elasticity blended yarn. A 150-denier polyester moisture-absorbing and quick-drying yarn is woven into the inner layer of the knitted fabric to obtain a knitted fabric with excellent fit and breathability. The warp density is controlled at 40 threads / inch, the weft density is controlled at 38 threads / inch, and the surface density is controlled within the range of 200-250 grams / square meter to ensure the sensitivity and softness of the glove. Step S3, calendering the knitted fabric. By controlling the calendering pressure to 2 MPa, the calendering temperature to 120 degrees Celsius, and the calendering speed to 20 meters per minute, the thickness of the knitted fabric is reduced by 20%, and the air permeability is increased by 30% from the initial value, thereby further improving the sensitivity and air permeability of the gloves. Step S4: performing a hydrophobic finishing on the calendered knitted fabric surface by immersing the knitted fabric in an emulsion prepared with an environmentally friendly fluorocarbon resin, acrylate, and deionized water in a ratio of 1:2:7 at 25 degrees Celsius for 30 minutes to increase the contact angle of the fabric to 120 degrees, thereby improving the anti-slip and wear resistance of the gloves. Step S5: Cut the hydrophobically finished knitted fabric into a glove shape, and use laser cutting technology to create a honeycomb-shaped breathable structure with a diameter of 3 mm and a depth of 1 mm on the palm and fingertips of the glove to further increase the breathable area and sensitivity of the glove; Step S6: Sewing the inner fabric with the honeycomb breathable structure to the outer fabric using a double-needle chain stitch machine and high-strength sewing thread to ensure that the honeycomb breathable structure and the outer fabric are precisely aligned, thereby producing a smart glove with high elasticity, breathability and perspiration-wicking properties, and a flexible feel. Step S7: Evaluate the performance of the finished smart gloves. Test the antistatic properties of the gloves using a surface resistance tester, test the air permeability of the gloves using a dynamic hot plate method, and test the perspiration and quick-drying properties of the gloves using an artificial climate chamber. When the surface resistance exceeds 1×10^9 ohms, increase the proportion of conductive fibers by 5%. When the air permeability is less than 80 mm / s, increase the pore size of the mesh structure by 0.5 mm or increase the density of the honeycomb structure by 10%. When the perspiration and quick-drying time exceeds 30 minutes, increase the content of polyester moisture-absorbing and quick-drying yarn by 10% or optimize the hydrophobic finishing process parameters. In step S8, after adjusting the gloves according to the performance evaluation results, a uniform layer of glue is applied to the palm and fingertips of the smart gloves. By controlling the viscosity, coating speed, and coating pressure of the glue, the thickness of the glue layer is controlled to 0.1-0.2 mm to ensure the anti-slip and sensitivity of the gloves. A polyurethane glue with good flexibility and strong wear resistance is selected and cured with UV light to further improve the wear resistance and service life of the gloves. At the same time, precision-controlled glue dispensing equipment is used during the glue coating process to retain 30% of the uncoated microporous structure in the glued area to maintain the breathability and perspiration properties of the gloves.

2. The method for preparing a high-performance smart glove according to claim 1, characterized in that: The step S1 comprises: Obtaining initial mixing ratio data of silk protein fibers and conductive fibers, setting the initial mixing ratio to 30:70 through a computer program, and obtaining an initial mixing ratio model; Obtain data on 120 denier / 48 denier silk protein fiber and 40 denier conductive fiber coated with 200 denier spandex, use the fineness data as input parameters for the mixing ratio model, and obtain a mixing ratio adjustment model for specific fineness; Iteratively optimizing the mixing ratio adjustment model according to the yarn denier requirement; if the yarn denier does not meet the preset range, adjusting the fineness of the silk protein fiber and the conductive fiber to obtain an optimal fineness combination that meets the yarn denier requirement; Conducting a preliminary blending test using the optimal fineness combination, observing the fiber distribution image after blending through an electron microscope to obtain fiber distribution uniformity data, and determining whether the fiber distribution uniformity data reaches a set threshold; Optimizing blending process parameters according to the fiber distribution uniformity data; if the fiber distribution uniformity data is lower than a set threshold, adjusting the blending process parameters to obtain optimized blending process parameters and obtain new fiber distribution uniformity data; detecting the yarn static electricity and yarn elasticity of the blended yarn by a sensor, obtaining yarn static electricity data and yarn elasticity data, and determining whether the yarn static electricity data and yarn elasticity data meet the performance requirements of the gloves; According to the yarn electrostatic data and the yarn elastic data, if the yarn electrostatic data or the yarn elastic data does not meet the requirements, the ratio of the silk protein fiber and the conductive fiber is adjusted to obtain a high-elasticity antistatic blended yarn that meets the flexibility and wear resistance requirements of the gloves.

3. The method for preparing a high-performance smart glove according to claim 1, characterized in that: Described step S2 comprises: Obtaining real-time operating parameters of a double-sided weft knitting machine, including speed, yarn feed amount, and drawing tension data; Constructing a set of high-elastic yarn tension feature vectors according to the operating parameters; Determine whether the operating parameters exceed a preset range. If so, trigger an alarm mechanism and control the device to stop operating. According to the alarm mechanism, the control system is used to adjust the yarn feeding amount and the pulling tension to obtain the operating parameters within the preset range, determine the normal operation of the equipment, and generate the normal operation equipment number; Retrieving corresponding process parameters from a database using the equipment number, the process parameters including aperture size, warp density, and weft density data; Using a photoelectric sensor to detect actual knitting parameters, determining whether a deviation between the actual knitting parameters and the process parameters exceeds a threshold, and generating deviation data if the deviation exceeds the threshold; According to the deviation data, a PID control algorithm is used to calculate an adjustment signal, and the machine operation state is adjusted through an actuator to obtain a mesh structure that meets the process parameters and determine image information of the mesh structure; collecting image information of the mesh structure, and performing grayscale and binarization processing on the image information; Extract the mesh edge contour through the edge detection algorithm, calculate the area of ​​each mesh, and determine whether the mesh area is within the set range; If the mesh area is not within the set range, repeat steps 6 and 7 until the mesh area is qualified, obtain a fabric with a qualified mesh structure, and generate a fabric number; Extracting fabric weight data from a database using the fabric number, scanning fabric thickness using an infrared sensor to obtain thickness data; The thickness data and the weight data are integrated to calculate the fabric surface density, and obtain a result that the fabric surface density data is within a preset range.

4. The method for preparing a high-performance smart glove according to claim 1, characterized in that: Described step S4 comprises: obtaining a knitted fabric after calendering treatment as a base material for hydrophobic finishing; Environmentally friendly fluorocarbon resin, acrylate and deionized water were mixed according to a formula ratio of 1:2:7 to prepare a hydrophobic finishing emulsion; Immerse the knitted fabric in the hydrophobic finishing emulsion, control the immersion temperature to be 25°C, and the immersion time to be 30 minutes; The impregnated knitted fabric is taken out and subjected to a deliquescence treatment to remove excess hydrophobic finishing emulsion; The knitted fabric after dehydration is dried and shaped to fully combine the hydrophobic finishing agent with the knitted fabric; Use a contact angle meter to measure the contact angle of the knitted fabric after hydrophobic finishing to determine whether it reaches the target value of 120°. If not, repeat steps 3-5 until the requirement is met. The hydrophobic-treated knitted fabric is used to make gloves. The friction coefficient test and abrasion resistance test are used to evaluate the anti-slip and abrasion resistance of the gloves to ensure that they meet the expected performance requirements.

5. The method for preparing a high-performance smart glove according to any one of claims 1 to 4, characterized in that: Described step S7 comprises: Obtaining a manufactured smart glove sample, and measuring the surface resistance value of the smart glove sample using a surface resistance tester; If the surface resistance value exceeds a preset resistance threshold, the proportion of the conductive fiber is increased by a preset ratio, and the smart glove sample is remade until the surface resistance value is less than or equal to the preset resistance threshold, thereby obtaining a smart glove sample that meets the antistatic performance requirements; For the smart glove samples that meet the antistatic performance requirements, the air permeability is tested using the dynamic hot plate method; If the air permeability is lower than the preset air permeability threshold, then, based on the structural characteristics of the smart glove sample, the pore size of the mesh structure is increased by a first preset length or the density of the honeycomb structure is increased by a first preset density, and the smart glove sample is remade until the air permeability is greater than or equal to the preset air permeability threshold, thereby obtaining a smart glove sample that meets the antistatic performance and air permeability requirements; For the smart glove samples that meet the antistatic and breathable performance requirements, the perspiration wicking and quick-drying performance is tested in an artificial climate chamber; If the surface humidity of the smart glove sample does not reach a preset dryness level within a preset time, the content of the polyester moisture-absorbing quick-drying yarn is increased by a second preset ratio, or the temperature and time parameters of the hydrophobic finishing process are optimized, and the smart glove sample is remade until the preset dryness level is reached within the preset time, thereby obtaining a smart glove sample that meets the requirements for antistatic performance, air permeability, and perspiration-wicking and quick-drying performance; A support vector machine algorithm was used to train and optimize the smart glove performance prediction model, using the conductive fiber ratio, mesh aperture, honeycomb density, and moisture-absorbing and quick-drying yarn content as input features and the antistatic, breathability, and perspiration-wicking and quick-drying test results of the smart glove samples as output; In the subsequent smart glove production process, the smart glove performance prediction model is used to predict whether the comprehensive performance of the smart gloves meets the requirements based on the raw material characteristics and process parameters; If not, adjust the material ratio and process parameters by referring to the optimization suggestions given by the smart glove performance prediction model; Continuously collect actual performance test data of each batch of smart gloves for continuous optimization and iterative update of the smart glove performance prediction model, improve the generalization ability and prediction accuracy of the smart glove performance prediction model, and guide the formulation design and production of smart gloves.

6. The method for preparing a high-performance smart glove according to any one of claims 1 to 4, characterized in that: Described step S8 comprises: Obtaining glove performance data, including the glove's anti-slip properties, sensitivity, wear resistance, air permeability, and perspiration wicking properties under different working conditions, and corresponding dispensing layer parameters, including adhesive viscosity, coating speed, coating pressure, micropore size, and curing degree; Based on the glove performance data, a support vector machine algorithm is used to train a smart glove performance prediction model, wherein the input of the smart glove performance prediction model is the dispensing layer parameters, and the output is the predicted value of the glove performance parameters; Obtaining performance requirement data of a target glove, inputting the performance requirement data into the smart glove performance prediction model, and optimizing the model through a particle swarm algorithm to obtain optimal dispensing layer parameters; According to the optimal dispensing layer parameters, the glue viscosity, coating speed and coating pressure of the dispensing device are configured, and the dispensing device is controlled to apply the glue on the palm and fingertips of the glove to form an initial dispensing layer, wherein the thickness of the initial dispensing layer is 1 to 2 mm; A microporous structure is created on the initial dispensing layer using laser etching technology, wherein the pore size and distribution of the microporous structure are determined according to the micropore size parameter in the optimal dispensing layer parameters, and the proportion of uncoated microporous structure is 30%, thereby obtaining a primary dispensing layer with a microporous structure; Placing the primary adhesive layer with the microporous structure in an ultraviolet curing device, and controlling the intensity and irradiation time of ultraviolet light according to the curing degree parameter in the optimal adhesive layer parameters to obtain a secondary adhesive layer after ultraviolet curing treatment; Collecting image information of the secondary dispensing layer through an image sensor to extract thickness and uniformity characteristics of the secondary dispensing layer; If the thickness and uniformity characteristics meet the preset ranges, a final dispensing layer is obtained; If the thickness and uniformity characteristics do not meet the preset range, the thickness and uniformity characteristics are input into the smart glove performance prediction model and the dispensing layer parameters are re-optimized.