Yarn surface treatment method

Abstract

The invention provides a yarn surface treatment method which comprises the following steps: aiming at coated yarns, adopting an orthogonal test design method, preferably selecting the type and concentration of a rinsing agent, and determining the optimal rinsing temperature, time and bath ratio, so that residual polymers and impurities on the surfaces of the yarns are removed, the damage and discoloration of the yarns caused by the rinsing agent are reduced to the greatest extent, and the quality of the yarns is improved. The cleanliness and the dyeing uniformity of the yarns are improved; for the rinsed yarn, according to different yarn varieties and filling requirements, the variety and particle size of a filling material are screened, filling process parameters such as filling temperature, time and pressure are optimized, so that the filling material is uniformly dispersed in the yarn, the heat retention property and the bulkiness of the yarn are improved, and meanwhile, the mechanical property and the dyeing property of the yarn are considered.

Description

Technical Field

[0001] The invention relates to the field of information technology, and in particular to a yarn surface treatment method. Background Art

[0002] Background: Yarn surface treatment is an important process in the textile industry, and its purpose is to improve the performance and function of yarn and increase the added value of yarn. However, in actual production, yarn surface treatment often encounters some technical difficulties. For example, when polymerizing yarn, how to control the rate and degree of polymerization reaction to prevent the polymer from forming an uneven coating on the yarn surface, affecting the feel and appearance of the yarn; when rinsing the yarn, how to choose a suitable rinsing agent and rinsing process, both to fully remove impurities and grease on the yarn surface, and to avoid the rinsing agent from causing damage or discoloration to the yarn; when filling the yarn, how to choose a suitable filling material and filling process, so that the filling material can be evenly dispersed inside the yarn, while not affecting the mechanical properties and dyeing properties of the yarn. These problems need to be constantly explored and optimized in practice to find the best process parameters and operating conditions to ensure the quality and efficiency of yarn surface treatment. Summary of the invention

[0003] The present invention provides a yarn surface treatment method, which mainly comprises: According to the type and performance requirements of the yarn, suitable polymerization monomers and initiators are selected, and the polymerization reaction rate and degree are adjusted by controlling the polymerization reaction temperature, time and catalyst dosage, so that the polymer forms a uniform and dense coating on the yarn surface, thereby improving the wear resistance and anti-pilling performance of the yarn, while maintaining the feel and appearance of the yarn; for the coated yarn, the orthogonal experimental design method is used to optimize the type and concentration of the rinsing agent, determine the optimal rinsing temperature, time and bath ratio, and remove the residual polymer and impurities on the yarn surface while minimizing the damage and discoloration of the yarn by the rinsing agent, thereby improving the cleanliness and uniformity of the yarn dyeing. After rinsing, the type and particle size of the filling material are screened according to different yarn varieties and filling requirements. By optimizing the filling process parameters, such as filling temperature, time and pressure, the filling material is evenly dispersed inside the yarn to improve the warmth retention and fluffiness of the yarn, while taking into account the mechanical properties and dyeing properties of the yarn. A mathematical model of the yarn surface treatment process is established, including polymerization, rinsing and filling. The model adopts a multivariate nonlinear regression equation, with polymerization temperature, time, catalyst dosage, rinsing temperature, time, bath ratio, filling temperature, time and pressure as independent variables, and yarn wear resistance, anti-pilling, cleanliness as the main parameters. , dyeing uniformity, warmth retention and fluffiness as dependent variables, and the response surface method and neural network algorithm are used to study the influence of various process parameters on yarn performance, optimize the combination of process parameters, realize intelligent control and prediction of yarn surface treatment process, and improve production efficiency and product quality stability; develop an online detection and feedback control system to monitor the key parameters in the yarn surface treatment process in real time, such as degree of polymerization, coating thickness, residual impurity amount, filling material distribution, etc. The system consists of sensors, data acquisition units, central processing units and actuators. The sensors collect real-time data, the data acquisition unit performs signal processing and conversion, and the central processing unit performs signal processing and conversion. The unit makes calculations and decisions based on the mathematical model, and the actuator adjusts the process parameters according to the instructions. Through this closed-loop control, the consistency and reliability of the yarn surface treatment quality are ensured; based on the mathematical model and the data of the online detection system, a standardized operating procedure and quality evaluation system for yarn surface treatment are established. The procedure includes four aspects: raw material selection, process parameter setting, equipment operation and quality inspection. The quality evaluation system covers the physical properties, chemical properties and appearance performance indicators of the yarn, and conducts refined management and control of the entire production process, improves the automation level and production efficiency of the equipment, and ensures the standardization and standardization of the yarn surface treatment process;Based on standardized operating procedures and quality evaluation systems, strengthen basic research and applied research on yarn surface treatment, deeply explore the mechanism of yarn surface modification, including the interface interaction between polymers and fibers, the dispersion mechanism of filling materials and the law of yarn structure change, develop new environmentally friendly surface treatment additives, such as bio-based polymers and nano-filling materials, study intelligent surface treatment equipment, such as plasma treatment devices and supercritical fluid treatment devices, expand the application scope and functions of yarn surface treatment, such as developing functional yarns such as antibacterial, flame retardant, and conductive, and enhance the market competitiveness and added value of yarn products. ;

[0004] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: The present invention discloses a yarn surface treatment method, which forms a uniform coating on the yarn surface by selecting suitable polymerization monomers and initiators, controlling polymerization reaction parameters; optimizing the rinsing process by orthogonal test, removing residues and protecting the yarn at the same time; screening filling materials and optimizing the filling process to improve yarn performance. The present invention establishes a mathematical model including three stages of polymerization, rinsing and filling, and optimizes the process parameters by using response surface method and neural network algorithm. At the same time, an online detection and feedback control system is developed to monitor key parameters in real time and automatically adjust the process. Based on this, a standardized operating procedure and a quality evaluation system are established to achieve refined management of the entire process. The present invention also conducts in-depth research on the surface modification mechanism, develops new environmentally friendly additives and intelligent equipment, expands the functional application of yarn, and improves product quality and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Figure 1 The present invention is a flow chart of a yarn surface treatment method.

[0006] Figure 2 It is a schematic diagram of a yarn surface treatment method of the present invention.

[0007] Figure 3 It is another schematic diagram of a yarn surface treatment method of the present invention. DETAILED DESCRIPTION

[0008] The technical scheme of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0009] like Figure 1-3 In this embodiment, a yarn surface treatment method may specifically include: S101. According to the type and performance requirements of the yarn, select appropriate polymerization monomers and initiators, and adjust the rate and degree of the polymerization reaction by controlling the temperature, time and catalyst dosage of the polymerization reaction so that the polymer forms a uniform and dense coating on the yarn surface, thereby improving the wear resistance and anti-pilling performance of the yarn while maintaining the feel and appearance of the yarn.

[0010] According to the yarn type and performance requirements, a suitable polymerization monomer is selected from the polymerization monomer database, and according to the characteristics of the polymerization monomer, a matching initiator is selected from the initiator database. The selected polymerization monomer and initiator are input into the polymerization reaction control system, and the temperature, time and catalyst dosage of the polymerization reaction are predicted and optimized by the neural network algorithm and the historical polymerization reaction data. According to the optimized polymerization reaction conditions, the polymerization reaction is carried out in the reactor, and the polymerization reaction process is monitored in real time by an infrared spectrometer to obtain the structure and performance data of the polymer. The data obtained during the polymerization reaction is input into the polymer performance prediction model, and the uniformity and density of the polymer coating are predicted by the support vector machine algorithm. If the prediction result meets the yarn performance requirements, the polymer is coated on the yarn surface to form a uniform and dense coating; if the prediction result does not meet the requirements, return to step 2 and adjust the polymerization reaction conditions until the requirements are met. The wear resistance of the coated yarn is tested by a friction tester, and the pilling condition on the yarn surface is analyzed by image recognition technology to obtain the wear resistance and anti-pilling performance data of the yarn. The yarn performance test data is compared with the preset performance threshold. If the test results meet the performance requirements, the yarn is output as a qualified product; if the test results do not meet the requirements, the batch of yarn is marked as unqualified, and returns to step 1 to reselect the polymerization monomer and initiator to start a new round of production optimization process.

[0011] For example, according to the yarn type and performance requirements, 10 optimal polymerization monomers are selected from a database containing 1,000 polymerization monomers by a support vector machine algorithm, and then 5 optimal initiators are matched from a database of 500 initiators according to the polarity, solubility and other characteristics of the polymerization monomers. The selected polymerization monomers and initiators are input into the polymerization reaction control system, and the three-layer feedforward neural network algorithm is used to train the optimization model in combination with 2,000 batches of historical polymerization data to predict the optimal polymerization temperature of 80°C, the time of 2 hours, and the amount of catalyst of 5% of the monomer mass. The polymerization reaction is carried out in a 5L reactor, and the spectral data of the reactants are collected every 5 minutes by a Fourier transform infrared spectrometer to monitor the polymerization reaction conversion rate and product molecular weight distribution in real time. The collected spectral data are input into the support vector machine model based on the Gaussian kernel function. By analyzing the chemical bond vibration peak intensity ratio of the polymer, it is predicted that the uniformity of the coating can reach more than 95% and the density can reach 95 g / cm³. The coating process was carried out at room temperature and pressure. The polymer was coated on the yarn surface by roller pressing method, and the coating thickness was controlled at about 50 μm. The wear resistance of the coated yarn was tested by a linear friction tester. The friction head used P1500 metallographic sandpaper, the pressure was 10 N, and the reciprocating motion was 100 times. The surface morphology of the yarn was photographed by a high-speed camera, and the proportion of the pilling area on the yarn surface was analyzed by using the convolutional neural network image segmentation algorithm. The wear resistance reached level 4, and the pilling area was less than 5%. The test results were compared with the preset performance index thresholds for a t-test, and P<0.5 was used as the significant difference standard to determine whether the yarn performance was qualified. The root cause analysis of the production data of the unqualified batches was carried out, and the association rule mining algorithm was used to find out the key factors that led to the substandard performance, and then optimize and adjust the production parameters to achieve continuous improvement of product performance.

[0012] S102. For the coated yarn, the orthogonal experimental design method is used to optimize the type and concentration of the rinsing agent, determine the optimal rinsing temperature, time and bath ratio, and minimize the damage and discoloration of the yarn caused by the rinsing agent while removing the residual polymers and impurities on the yarn surface, thereby improving the cleanliness and dyeing uniformity of the yarn.

[0013] According to the type and coating material of coated yarn, a set of alternative schemes for the type and concentration of rinsing agent was established, and the combination of each alternative scheme was determined through orthogonal experimental design. For each combination of rinsing agent type and concentration, different rinsing temperature, time and bath ratio parameters were set to form multiple groups of orthogonal experimental schemes. Rinse experiments were carried out on each group of orthogonal experimental schemes, and the rinsing effect was evaluated by detecting the content of yarn surface residues, and the damage degree and color difference change of the yarn were tested. A rinsing effect evaluation index system was constructed, and the comprehensive score of each orthogonal experimental scheme was calculated by comprehensively considering factors such as yarn surface residue removal rate, yarn damage degree and color difference change. The orthogonal experimental results were analyzed by data mining algorithm, and the association rules between the type and concentration of rinsing agent and rinsing temperature, time and bath ratio were established to reveal the influence of various factors on the rinsing effect. Based on the results of association rule analysis, a multi-objective optimization algorithm was used to search for the optimal rinsing process parameter combination, which minimizes the damage and discoloration degree of the rinsing agent to the yarn while meeting the requirements of yarn surface residue removal rate and dyeing uniformity. Verify the optimized rinsing process parameter combination, confirm its improvement effect in improving the cleanliness and dyeing uniformity of coated yarn through comparative tests, and form a standardized coated yarn rinsing process procedure.

[0014] Exemplarily, according to the type of coated yarn and the coating material, a set of alternative solutions for the type and concentration of rinsing agent is established, such as the concentration of alkaline rinsing agent is 1%~5%, the concentration of neutral rinsing agent is 5%~2%, and the concentration of acidic rinsing agent is 2%~1%. Through orthogonal experimental design, the combination of each alternative solution is determined, and the rinsing temperature (30℃, 40℃, 50℃), time (10min, 20min, 30min) and bath ratio (1:10, 1:20, 1:30) parameters are set to form 9 groups of orthogonal experimental schemes. A rinsing experiment is carried out for each group of schemes, and the content of residues on the surface of the yarn is detected by gas chromatography-mass spectrometry, the breaking strength and elongation of the yarn are tested by an electronic universal testing machine, and the color difference value ΔE of the yarn is tested by a spectrophotometer. A rinsing effect evaluation index system is constructed, and weight coefficients are set, such as residue removal rate 4, yarn damage degree 3, and color difference change 3. The weighted summation method is used to calculate the comprehensive score of each scheme. The Apriori algorithm was used to mine association rules for the orthogonal test results, and association rules with a minimum support of 20% and a minimum confidence of 80% were obtained, such as "alkaline rinsing agent concentration ≥ 3% and temperature ≥ 40℃ → residue removal rate ≥ 95%". Based on the results of association rule analysis, the non-dominated sorting genetic algorithm II was used for multi-objective optimization. The residue removal rate and yarn damage degree were taken as optimization targets, and the optimal rinsing process parameter combination was searched as follows: alkaline rinsing agent concentration 3%, temperature 45℃, time 25min, bath ratio 1:20. Through comparative tests, compared with the conventional process, the optimized rinsing process increased the residue removal rate by 5%, reduced the yarn breaking strength loss by 10%, and reduced the color difference value ΔE by 5, which verified its improvement effect in improving the cleanliness and dyeing uniformity of coated yarns, and formed a standardized coated yarn rinsing process specification.

[0015] S103. For the rinsed yarn, the type and particle size of the filling material are screened according to different yarn varieties and filling requirements. By optimizing the filling process parameters, such as filling temperature, time and pressure, the filling material is evenly dispersed inside the yarn to improve the warmth retention and fluffiness of the yarn, while taking into account the mechanical properties and dyeing properties of the yarn.

[0016] According to the yarn variety and filling requirements, the selection rules of filling material type and particle size are established, and the optimal filling material parameters are automatically matched through the knowledge base or machine learning algorithm. The fuzzy logic control algorithm is used to adaptively adjust the filling temperature, time and pressure and other process parameters according to the input parameters such as yarn variety and filling material characteristics to realize the intelligent optimization control of the filling process. Through computer vision technology, the internal structure of the filled yarn is imaged and analyzed to determine the uniformity of the filling material dispersion. If the dispersion is uneven, the filling process parameters are adjusted by feedback. A prediction model for the mechanical properties and dyeing properties of the yarn is established. Through the input of the filling material parameters and process parameters, the yarn fluffiness, warmth retention, mechanical properties and dyeing properties are predicted, and multi-objective optimization is performed to determine the best filling solution. Machine learning algorithms such as support vector machines or neural networks are used to train intelligent decision-making models for filling material selection and process parameter optimization based on historical production data to realize the automatic control of the filling process. Through big data analysis technology, the optimal filling material formula and process parameter combination rules under different yarn varieties and filling requirements are excavated to form a knowledge base that is continuously updated and iterated to guide production practice. Integrate the filling intelligent optimization control system with the enterprise ERP, MES and other information systems to realize the automation and information management of the entire process from customer order to product production, and improve production efficiency and traceability of product quality.

[0017] For example, according to the yarn varieties such as cotton yarn, polyester, etc., and the filling requirements such as bulkiness and warmth retention, the system automatically matches the optimal filling materials such as hollow fibers and far-infrared powder from the knowledge base, and the particle size is controlled at 1-5μm. The fuzzy logic control algorithm is adopted, with the yarn variety and the thermal conductivity K of the filling material as input, and the filling temperature T=K*200, time t=d*300, and pressure P=F / S are adaptively adjusted through the membership function to optimize the filling effect. After filling, the high-speed CCD camera collects the yarn cross-section image, and the image processing system analyzes the material dispersion uniformity through the grayscale co-occurrence matrix. If the unevenness exceeds 5%, the filling pressure and time are adjusted. Based on the support vector machine regression model, the mapping relationship between the filling material particle size d, pressure P and the yarn bulkiness H and warmth retention W is established, and the multi-objective genetic algorithm optimizes the filling parameters;. The neural network learns 500 sets of production parameters and product performance data, trains the parameter selection model, and realizes automatic filling control. Big data analyzes 1,000 yarn formulas, clustering algorithms mine the best ratio of filling materials, and the knowledge base infers the relationship between filling temperature T, time t and yarn strength Y: Y=8*T+6*t, guiding process optimization. The filling system is integrated with ERP, automatically generates production tasks based on orders, collects material consumption, energy consumption and other data in real time, and the MES system statistically analyzes the product quality pass rate by 5%.

[0018] S104. Establish a mathematical model of the yarn surface treatment process, including three stages: polymerization, rinsing and filling. The model uses a multivariate nonlinear regression equation, with polymerization temperature, time, catalyst dosage, rinsing temperature, time, bath ratio, filling temperature, time and pressure as independent variables, and yarn wear resistance, pilling resistance, cleanliness, dyeing uniformity, warmth retention and fluffiness as dependent variables. Using the response surface method and neural network algorithm, study the influence of various process parameters on yarn performance, optimize the combination of process parameters, realize intelligent control and prediction of yarn surface treatment process, and improve production efficiency and product quality stability.

[0019] According to the process flow of yarn surface treatment, the three key stages of polymerization, rinsing and filling are determined, and the relevant process parameters and performance index data are collected for each stage. The collected data are preprocessed to remove outliers, and the key process parameters closely related to yarn performance are screened out through correlation analysis. The multivariate nonlinear regression method is used to establish a mathematical model of the three stages of polymerization, rinsing and filling with the selected key process parameters as independent variables and yarn performance indicators as dependent variables. On the basis of the established regression model, the response surface analysis method is used to study the quantitative relationship between each process parameter and the yarn performance index, and the response surface diagram is drawn to intuitively analyze the influence of the parameters. The experimental data are randomly divided into training sets and test sets. The artificial neural network algorithm is used to learn the training set data, and the yarn performance prediction model is established. The prediction accuracy of the model is verified by the test set data. Combining the response surface analysis results and the neural network prediction model, multi-objective optimization is carried out, and the comprehensive performance indicators of the yarn are taken as the optimization target, and the key process parameters are taken as the optimization variables to search for the optimal parameter combination. The optimized process parameters are set in the control system of the production line. By collecting parameter data of each process in real time and combining it with the prediction model, online prediction and intelligent closed-loop control of yarn performance can be achieved to improve the consistency and stability of product quality.

[0020] For example, according to the yarn surface treatment process, process parameters such as temperature, pressure, time and yarn performance indicators such as strength and fineness in the three key stages of polymerization, rinsing and filling are collected. The outliers exceeding the mean ± 3 times the standard deviation are eliminated, and the temperature and pressure with a correlation coefficient greater than 6 are selected as key parameters by the Pearson correlation coefficient method. With temperature and pressure as independent variables and strength as dependent variable, a multivariate quadratic regression model is established with a correlation coefficient of R = 85. A three-dimensional response surface diagram of temperature-pressure-strength is drawn, and the strength is highest when the temperature is 80°C and the pressure is 2MPa. The data is divided into training set and test set at 8:2, and a 3-layer BP neural network is used for learning, with 10 neurons in the hidden layer, and the mean square error of the predicted strength is 5. With the comprehensive indicators of strength and fineness weighted 6 and 4 as the target, the genetic algorithm is used to optimize the key parameters, and the optimal parameter combination of temperature 78°C and pressure 25MPa is obtained. The optimization parameters are set in the production line control system, real-time data collection and performance prediction are carried out, intelligent closed-loop control is realized, yarn quality consistency is improved, and the product acceptance rate is increased by 5%.

[0021] S105. Develop an online detection and feedback control system to monitor key parameters in the yarn surface treatment process in real time, such as degree of polymerization, coating thickness, residual impurities, and filling material distribution. The system consists of sensors, data acquisition units, central processing units, and actuators. The sensors collect real-time data, the data acquisition unit performs signal processing and conversion, the central processing unit performs calculations and decisions based on mathematical models, and the actuators adjust process parameters according to instructions. Through this closed-loop control, the consistency and reliability of the yarn surface treatment quality are ensured.

[0022] According to the requirements of the yarn surface treatment process, the key parameters that need to be monitored in real time are determined, such as degree of polymerization, coating thickness, residual impurity content and filling material distribution. For each key parameter, a suitable sensor is selected for real-time data acquisition, and the sensor transmits the collected analog signal to the data acquisition unit. The data acquisition unit receives the analog signal collected by the sensor and converts the analog signal into a digital signal through signal amplification, filtering, A / D conversion and other processing. The processed digital signal is transmitted to the central processing unit, which analyzes and calculates the digital signal based on the preset mathematical model and algorithm to obtain the real-time value of the key parameter. The central processing unit compares the real-time parameter value with the preset standard value. If the real-time value deviates from the standard value range, an adjustment instruction is issued to the actuator. The actuator receives the adjustment instruction from the central processing unit and realizes real-time feedback control of the yarn surface treatment process by adjusting the process parameters of the yarn surface treatment equipment, such as temperature, pressure, speed, etc. Through the closed-loop control of the online detection and feedback control system, the yarn surface treatment process is continuously monitored and adjusted to ensure that the key parameters are always within the standard range, thereby ensuring the consistency and reliability of the yarn surface treatment quality.

[0023] Exemplarily, according to the yarn surface treatment process requirements, key parameters such as degree of polymerization, coating thickness, residual impurities and filling material distribution need to be monitored in real time. For the degree of polymerization parameter, a viscosity polymerization meter is selected for real-time data collection, and the degree of polymerization is calculated by measuring the viscosity value of the yarn solution, with an accuracy of up to 1. For the coating thickness parameter, an inductive coating thickness gauge is selected for real-time data collection, and the coating thickness is calculated by measuring the inductance value between the coating and the substrate, with an accuracy of up to 1 micron. For the residual impurity parameter, an optical microscope is selected for real-time data collection, and the number of impurity particles is calculated by binarizing the yarn surface image, with an accuracy of up to 0.1 mg. For the filling material distribution parameter, an X-ray diffractometer is selected for real-time data collection, and the dispersion of the filling material is calculated by curve fitting the diffraction spectrum, with an accuracy of up to 1%. The sensor transmits the collected analog signal to the data acquisition unit, and converts the analog signal into a digital signal through 10 times signal amplification, 50 Hz low-pass filtering, 12-bit A / D conversion and other processing. The central processing unit analyzes and calculates the digital signal based on mathematical models and algorithms such as the least squares method and Gaussian fitting to obtain the real-time value of the key parameters. If the real-time value deviates from the standard value within ±5%, an adjustment instruction is issued to the actuator. The actuator adjusts the temperature, pressure, speed and other process parameters of the yarn surface treatment equipment through the PID control algorithm to achieve real-time feedback control of the yarn surface treatment process. Through the closed-loop control of the online detection and feedback control system, the yarn surface treatment process is continuously monitored and adjusted to ensure that the key parameters are always within the standard range, thereby ensuring the consistency and reliability of the yarn surface treatment quality.

[0024] S106. Based on the mathematical model and the data from the online detection system, a standardized operating procedure and quality evaluation system for yarn surface treatment are established. The procedure includes four aspects: raw material selection, process parameter setting, equipment operation and quality inspection. The quality evaluation system covers the physical properties, chemical properties and appearance performance indicators of the yarn. The entire production process is managed and controlled in a refined manner to improve the automation level and production efficiency of the equipment and ensure the standardization and standardization of the yarn surface treatment process.

[0025] According to the standardized operating procedures of the yarn surface treatment process, data information such as raw material selection, process parameter setting, equipment operation and quality inspection are obtained; by analyzing the obtained raw material selection data, it is determined whether the raw materials meet the requirements of the standardized operating procedures. If not, the raw materials are optimized; according to the process parameter setting data, the support vector machine algorithm is used to optimize the equipment operating parameters to obtain the optimal combination of equipment operating parameters; the optimized equipment operating parameters are input into the equipment control system, and the precise operation and adjustment of the equipment are achieved through automatic control technology; in the yarn production process, the physical properties, chemical properties and appearance performance data of the yarn are obtained by an online detection system; by analyzing the detection data, it is determined whether the yarn quality meets the requirements of the quality evaluation system. If not, the process parameters are optimized again; according to the optimized process parameters, the equipment operation is adjusted, and the yarn quality data is continuously monitored, and the production process is continuously optimized through closed-loop control to improve the yarn quality and production efficiency.

[0026] Exemplarily, according to the standardized operating procedures of the yarn surface treatment process, data information such as raw material selection, process parameter setting, equipment operation and quality inspection are obtained. By analyzing the raw material selection data, it is judged whether the length, strength, fineness and other indicators of the raw materials meet the standard requirements, such as the fiber length deviation does not exceed 5%, the strength variation coefficient is less than 6%, etc. If it does not meet the requirements, the fuzzy comprehensive evaluation method is used to select the best raw material from the alternative raw materials. According to the process parameter setting data, the support vector machine algorithm is used, and the yarn quality and production efficiency are optimized. The operating parameters such as equipment speed, draft ratio, processing temperature are optimized to obtain the optimal parameter combination, such as the speed is increased by 5%, the draft ratio is reduced by 2%, and the temperature is controlled at 60℃±5℃. The optimized parameters are input into the equipment control system, and the precise operation of the equipment is realized through the PID control algorithm. In the yarn production process, an online detection system is used to collect data every 30 seconds to obtain physical and appearance performance data such as yarn diameter, strength, and hairiness index. By comparing with the standard value in the quality evaluation system, the yarn quality is judged. If the diameter exceeds the tolerance by 5%, the strength is 10% lower than the standard value, etc., the genetic algorithm is used to optimize the process parameters again. According to the optimized process parameters, the equipment operation is adjusted, and the yarn quality data is continuously monitored. The data is analyzed every 2 minutes, and closed-loop optimization is achieved through adaptive control algorithms to continuously improve the yarn quality, ensure that the quality pass rate is stable at more than 99%, and increase production efficiency by more than 10%.

[0027] S107. Strengthen basic and applied research on yarn surface treatment based on standardized operating procedures and quality evaluation systems. Deepen the exploration of the mechanism of yarn surface modification, including the interface interaction between polymers and fibers, the dispersion mechanism of filler materials, and the law of yarn structure change. Develop new environmentally friendly surface treatment additives, such as bio-based polymers and nanofiller materials. Research intelligent surface treatment equipment, such as plasma treatment devices and supercritical fluid treatment devices. Expand the application scope and functions of yarn surface treatment, such as developing functional yarns such as antibacterial, flame retardant, and conductive yarns, to enhance the market competitiveness and added value of yarn products.

[0028] According to the quality evaluation system of yarn surface treatment, a machine learning algorithm is used to establish a prediction model between yarn surface performance and process parameters. By optimizing key process parameters such as filler dispersion and interface effect, modified yarn with excellent performance is obtained. Computer vision technology is used to detect the surface morphology of yarn online to obtain information on yarn structure changes. Combined with the chemical composition data of environmentally friendly additives, the yarn surface modification mechanism is analyzed through data mining algorithms to determine the optimal additive formula and process conditions. By establishing a digital twin model of intelligent surface treatment equipment, the simulation optimization algorithm is used to optimize the equipment operation parameters, improve equipment operation efficiency and product quality stability, and reduce energy consumption and costs. According to market demand and application scope, the knowledge graph technology is used to conduct correlation analysis on yarn product functions, performance indicators and application scenarios to determine the development direction and technical route of new functional yarns. By building an expert knowledge base and case library for yarn surface treatment, the case reasoning algorithm is used to make intelligent decisions and optimize the development process of new yarn products, shorten the product development cycle, and improve the success rate. Use natural language processing technology to conduct sentiment analysis and semantic mining on market feedback information of yarn products, obtain users' evaluation and improvement suggestions on product performance and functions, and provide a basis for product upgrades and market competition strategy formulation. By building a full life cycle management platform for yarn products and using blockchain technology to trace and verify product quality information, we can increase product added value and brand influence and enhance market competitive advantages.

[0029] For example, according to the quality evaluation system of yarn surface treatment, the support vector machine algorithm is used to establish a nonlinear prediction model between yarn surface performance and process parameters such as filler dispersion and interface bonding force. The model is trained by the particle swarm optimization algorithm to obtain a modified yarn process parameter optimization model with a prediction accuracy of more than 95%. The yarn surface morphology is collected online by a high-speed camera, and key characteristic parameters such as yarn surface roughness and hairiness index are extracted. Combined with the infrared spectrum, nuclear magnetic resonance and other characterization data of environmentally friendly additives, the yarn surface modification mechanism is analyzed by the association rule mining algorithm, and the optimal additive formula is determined to be 5% nano-silicon dioxide and 0% organic silicon modifier. The optimal process conditions are 60°C temperature and 30 minutes. By constructing a digital twin model of intelligent surface treatment equipment, a genetic algorithm is used to perform multi-objective optimization of key parameters such as equipment speed and pressure, which can improve the equipment operation efficiency by more than 10% and reduce energy consumption by more than 20%. The knowledge graph technology is used to conduct correlation mining on the antibacterial, flame retardant, and conductive functions of yarn products, and the development direction of new functional yarns is determined to be graphene-modified flame retardant yarns, and the sol-gel method is used to prepare the process route. By building a yarn surface treatment expert knowledge base and case library, a rule-based reasoning algorithm and an example-based reasoning algorithm are combined to make intelligent decisions on key links such as the selection of additives and process optimization for new yarn products, shortening the product development cycle by more than 20% on average. The sentiment analysis algorithm is used to analyze the user evaluation data of yarn products, extract user satisfaction with key attributes such as product feel and appearance, and combine semantic network analysis to extract user suggestions for product performance improvement, providing data support for product performance improvement. By building a yarn product quality traceability platform based on blockchain technology and using smart contracts to encrypt and store key quality data, the quality management of the product life cycle is realized, the product added value is increased by more than 20%, and the brand market competitiveness is effectively enhanced.

[0030] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for treating the surface of a yarn, characterized in that: The method comprises: According to the type and performance requirements of the yarn, suitable polymerization monomers and initiators are selected, and the polymerization reaction rate and degree are adjusted by controlling the polymerization reaction temperature, time and catalyst dosage, so that the polymer forms a uniform and dense coating on the yarn surface, thereby improving the wear resistance and anti-pilling performance of the yarn, while maintaining the feel and appearance of the yarn; for the coated yarn, the orthogonal experimental design method is used to optimize the type and concentration of the rinsing agent, determine the optimal rinsing temperature, time and bath ratio, and remove the residual polymer and impurities on the yarn surface while minimizing the damage and discoloration of the yarn by the rinsing agent, thereby improving the cleanliness and uniformity of the yarn dyeing. After rinsing, the type and particle size of the filling material are screened according to different yarn varieties and filling requirements. By optimizing the filling process parameters, such as filling temperature, time and pressure, the filling material is evenly dispersed inside the yarn to improve the warmth retention and fluffiness of the yarn, while taking into account the mechanical properties and dyeing properties of the yarn. A mathematical model of the yarn surface treatment process is established, including polymerization, rinsing and filling. The model adopts a multivariate nonlinear regression equation, with polymerization temperature, time, catalyst dosage, rinsing temperature, time, bath ratio, filling temperature, time and pressure as independent variables, and yarn wear resistance, anti-pilling, cleanliness as the main parameters. , dyeing uniformity, warmth retention and fluffiness as dependent variables, and the response surface method and neural network algorithm are used to study the influence of various process parameters on yarn performance, optimize the combination of process parameters, realize intelligent control and prediction of yarn surface treatment process, and improve production efficiency and product quality stability; develop an online detection and feedback control system to monitor the key parameters in the yarn surface treatment process in real time, such as degree of polymerization, coating thickness, residual impurity amount, filling material distribution, etc. The system consists of sensors, data acquisition units, central processing units and actuators. The sensors collect real-time data, the data acquisition unit performs signal processing and conversion, and the central processing unit performs signal processing and conversion. The unit makes calculations and decisions based on the mathematical model, and the actuator adjusts the process parameters according to the instructions. Through this closed-loop control, the consistency and reliability of the yarn surface treatment quality are ensured; based on the mathematical model and the data of the online detection system, a standardized operating procedure and quality evaluation system for yarn surface treatment are established. The procedure includes four aspects: raw material selection, process parameter setting, equipment operation and quality inspection. The quality evaluation system covers the physical properties, chemical properties and appearance performance indicators of the yarn, and conducts refined management and control of the entire production process, improves the automation level and production efficiency of the equipment, and ensures the standardization and standardization of the yarn surface treatment process;Based on standardized operating procedures and quality evaluation systems, strengthen basic research and applied research on yarn surface treatment, deeply explore the mechanism of yarn surface modification, including the interface interaction between polymers and fibers, the dispersion mechanism of filling materials and the law of yarn structure change, develop new environmentally friendly surface treatment additives, such as bio-based polymers and nano-filling materials, study intelligent surface treatment equipment, such as plasma treatment devices and supercritical fluid treatment devices, expand the application scope and functions of yarn surface treatment, such as developing functional yarns such as antibacterial, flame retardant, and conductive, and enhance the market competitiveness and added value of yarn products. ; 2. A yarn surface treatment method according to claim 1, characterized in that: The method comprises: selecting appropriate polymerization monomers and initiators according to the type and performance requirements of the yarn, and adjusting the rate and degree of the polymerization reaction by controlling the temperature, time and amount of the catalyst of the polymerization reaction, so that the polymer forms a uniform and dense coating on the surface of the yarn, thereby improving the wear resistance and anti-pilling performance of the yarn, and maintaining the feel and appearance of the yarn. According to the yarn type and performance requirements, a suitable polymerization monomer is selected from the polymerization monomer database, and according to the characteristics of the polymerization monomer, a matching initiator is selected from the initiator database; The selected polymerization monomers and initiators are input into the polymerization reaction control system, and the temperature, time, catalyst dosage and other condition parameters of the polymerization reaction are predicted and optimized by the neural network algorithm combined with the historical polymerization reaction data; According to the optimized polymerization reaction conditions, a polymerization reaction is carried out in a reactor, and the polymerization reaction process is monitored in real time by an infrared spectrometer to obtain the structure and performance data of the polymer; The data obtained during the polymerization reaction are input into the polymer performance prediction model, and the uniformity and density of the polymer coating are predicted through the support vector machine algorithm; If the predicted results meet the yarn performance requirements, the polymer is coated on the yarn surface to form a uniform and dense coating; If the prediction result does not meet the requirements, return to step 2 and adjust the polymerization reaction conditions until the requirements are met; The wear resistance of the coated yarn was tested using a friction tester, and the pilling on the yarn surface was analyzed using image recognition technology to obtain the wear resistance and anti-pilling performance data of the yarn; Compare the yarn performance test data with the preset performance threshold, and if the test result meets the performance requirement, the yarn is output as a qualified product; If the test results do not meet the requirements, the batch of yarn is marked as unqualified and returns to step 1 to reselect the polymerization monomer and initiator and start a new round of production optimization process.

3. A yarn surface treatment method according to claim 1, characterized in that: The method adopts an orthogonal test design method to select the type and concentration of the rinsing agent, determine the optimal rinsing temperature, time and bath ratio for the coated yarn, and minimize the damage and discoloration of the rinsing agent to the yarn while removing the residual polymer and impurities on the yarn surface, thereby improving the cleanliness and dyeing uniformity of the yarn, including: According to the type of coated yarn and coating material, a set of alternative solutions for the type and concentration of rinsing agent is established, and the combination of each alternative solution is determined through orthogonal experimental design; For each type and concentration combination of rinse agents, different rinse temperature, time and bath ratio parameters are set to form multiple groups of orthogonal test schemes; A rinsing experiment was conducted for each orthogonal test scheme. The rinsing effect was evaluated by detecting the residue content on the yarn surface, and the damage degree and color difference change of the yarn were tested. A rinsing effect evaluation index system was constructed, and the comprehensive scores of each orthogonal test scheme were calculated by comprehensively considering factors such as the removal rate of residues on the yarn surface, the degree of yarn damage and the change in color difference. The data mining algorithm was used to analyze the orthogonal test results, and the association rules between the type and concentration of rinsing agent and the rinsing temperature, time and bath ratio were established, revealing the influence of various factors on the rinsing effect. Based on the results of association rule analysis, a multi-objective optimization algorithm was used to search for the optimal rinsing process parameter combination, which could meet the requirements of yarn surface residue removal rate and dyeing uniformity while minimizing the damage and discoloration of the rinsing agent to the yarn. Verify the optimized rinsing process parameter combination, confirm its improvement effect in improving the cleanliness and dyeing uniformity of coated yarn through comparative tests, and form a standardized coated yarn rinsing process procedure.

4. A yarn surface treatment method according to claim 1, characterized in that: The rinsed yarn is screened for the type and particle size of the filling material according to different yarn varieties and filling requirements, and the filling material is uniformly dispersed inside the yarn by optimizing the filling process parameters, such as filling temperature, time and pressure, to improve the warmth retention and fluffiness of the yarn, while taking into account the mechanical properties and dyeing properties of the yarn, including: According to the yarn type and filling requirements, the selection rules of filling material type and particle size are established, and the optimal filling material parameters are automatically matched through the knowledge base or machine learning algorithm; Fuzzy logic control algorithm is used to adaptively adjust process parameters such as filling temperature, time and pressure according to input parameters such as yarn type and filling material characteristics, so as to realize intelligent optimization control of the filling process; Through computer vision technology, the internal structure of the yarn after filling is imaged and analyzed to determine the uniformity of the filling material dispersion. If the dispersion is uneven, feedback is provided to adjust the filling process parameters. Establish a prediction model for the mechanical and dyeing properties of yarns. By inputting the filling material parameters and process parameters, predict the yarn bulkiness, warmth retention, mechanical properties and dyeing properties. Perform multi-objective optimization and solve to determine the best filling solution. Use machine learning algorithms such as support vector machines or neural networks to train intelligent decision-making models for filling material selection and process parameter optimization based on historical production data to achieve automated control of the filling process; Through big data analysis technology, we can explore the optimal filling material formula and process parameter combination rules under different yarn varieties and filling requirements, form a knowledge base that is constantly updated and iterated to guide production practice; Integrate the filling intelligent optimization control system with enterprise information systems such as ERP and MES to realize automation and information management of the entire process from customer order to product production, and improve production efficiency and traceability of product quality.

5. A yarn surface treatment method according to claim 1, characterized in that: The mathematical model of the yarn surface treatment process is established, including three stages: polymerization, rinsing and filling; the model adopts a multivariate nonlinear regression equation, with polymerization temperature, time, catalyst dosage, rinsing temperature, time, bath ratio, filling temperature, time and pressure as independent variables, and yarn wear resistance, anti-pilling, cleanliness, dyeing uniformity, warmth retention and fluffiness as dependent variables; Using response surface methodology and neural network algorithm, we study the influence of various process parameters on yarn performance, optimize the combination of process parameters, realize intelligent control and prediction of yarn surface treatment process, and improve production efficiency and product quality stability, including: According to the process flow of yarn surface treatment, the three key stages of polymerization, rinsing and filling are determined, and relevant process parameters and performance index data are collected for each stage; Pre-process the collected data, remove outliers, and screen out key process parameters closely related to yarn performance through correlation analysis; The multivariate nonlinear regression method was used to establish the mathematical model of the three stages of polymerization, rinsing and filling, with the selected key process parameters as independent variables and yarn performance indicators as dependent variables. Based on the established regression model, the response surface analysis method is used to study the quantitative relationship between each process parameter and the yarn performance index, and the response surface diagram is drawn to intuitively analyze the influence of the parameters; The experimental data were randomly divided into training set and test set, and the training set data were studied by artificial neural network algorithm to establish the yarn performance prediction model, and the prediction accuracy of the model was verified by the test set data. Combining the response surface analysis results with the neural network prediction model, multi-objective optimization is performed, with the comprehensive performance index of the yarn as the optimization target and the key process parameters as the optimization variables, to search for the optimal parameter combination; The optimized process parameters are set in the control system of the production line. By collecting parameter data of each process in real time and combining it with the prediction model, online prediction and intelligent closed-loop control of yarn performance can be achieved to improve the consistency and stability of product quality.

6. A yarn surface treatment method according to claim 1, characterized in that: The online detection and feedback control system is developed to monitor key parameters in the yarn surface treatment process in real time, such as degree of polymerization, coating thickness, residual impurity amount, filling material distribution, etc. The system is composed of sensors, data acquisition units, central processing units and actuators; the sensors collect real-time data, the data acquisition unit performs signal processing and conversion, the central processing unit performs calculations and decisions based on mathematical models, and the actuators adjust process parameters according to instructions; Through this closed-loop control, the consistency and reliability of yarn surface treatment quality is ensured, including: According to the yarn surface treatment process requirements, determine the key parameters that need to be monitored in real time, such as degree of polymerization, coating thickness, residual impurities and filling material distribution; For each key parameter, a suitable sensor is selected for real-time data collection, and the sensor transmits the collected analog signal to the data acquisition unit; The data acquisition unit receives the analog signal collected by the sensor and converts the analog signal into a digital signal through signal amplification, filtering and A / D conversion. The processed digital signal is transmitted to the central processing unit, which analyzes and calculates the digital signal based on the preset mathematical model and algorithm to obtain the real-time value of key parameters; The central processing unit compares the real-time parameter value with the preset standard value. If the real-time value deviates from the standard value range, an adjustment instruction is issued to the actuator; The actuator receives the adjustment instructions from the central processing unit and realizes real-time feedback control of the yarn surface treatment process by adjusting the process parameters of the yarn surface treatment equipment, such as temperature, pressure and speed; Through the closed-loop control of the online detection and feedback control system, the yarn surface treatment process is continuously monitored and adjusted to ensure that key parameters are always within the standard range, thereby ensuring the consistency and reliability of the yarn surface treatment quality.

7. A yarn surface treatment method according to claim 1, characterized in that: According to the mathematical model and the data of the online detection system, a standardized operating procedure and a quality evaluation system for yarn surface treatment are established; the procedure includes four aspects: raw material selection, process parameter setting, equipment operation and quality detection; The quality evaluation system covers the physical, chemical and appearance performance indicators of the yarn; it conducts fine management and control over the entire production process, improves the automation level and production efficiency of the equipment, and ensures the standardization and standardization of the yarn surface treatment process, including: According to the standardized operating procedures of yarn surface treatment process, obtain data information such as raw material selection, process parameter setting, equipment operation and quality inspection; By analyzing the obtained raw material selection data, determine whether the raw materials meet the requirements of the standardized operating procedures. If not, optimize the raw material selection; According to the process parameter setting data, the support vector machine algorithm is used to optimize the equipment operating parameters to obtain the optimal equipment operating parameter combination; Input the optimized equipment operating parameters into the equipment control system, and realize precise operation and adjustment of the equipment through automatic control technology; During the yarn production process, an online detection system is used to obtain the physical, chemical and appearance properties of the yarn; By analyzing the test data, it is determined whether the yarn quality meets the requirements of the quality evaluation system. If not, the process parameters are optimized again; According to the optimized process parameters, equipment operation is adjusted, and yarn quality data is continuously monitored. Through closed-loop control, the production process is continuously optimized to improve yarn quality and production efficiency.

8. A yarn surface treatment method according to claim 1, characterized in that: Based on the standardized operating procedures and quality evaluation system, the basic research and applied research on yarn surface treatment will be strengthened; the mechanism of yarn surface modification will be explored in depth, including the interface interaction between polymers and fibers, the dispersion mechanism of filling materials and the law of yarn structure change; new environmentally friendly surface treatment additives will be developed, such as bio-based polymers and nano-filling materials; intelligent surface treatment equipment will be studied, such as plasma treatment devices and supercritical fluid treatment devices; the application scope and functions of yarn surface treatment will be expanded, such as the development of functional yarns such as antibacterial, flame retardant and conductive yarns, to enhance the market competitiveness and added value of yarn products, including: According to the quality evaluation system of yarn surface treatment, a prediction model between yarn surface performance and process parameters was established using machine learning algorithms. By optimizing key process parameters such as filler dispersion and interface effect, modified yarns with excellent performance were obtained. Computer vision technology is used to detect the yarn surface morphology online to obtain information on yarn structure changes. Combined with the chemical composition data of environmentally friendly additives, the yarn surface modification mechanism is analyzed through data mining algorithms to determine the optimal additive formula and process conditions. By establishing a digital twin model of intelligent surface treatment equipment and using simulation optimization algorithms to optimize equipment operating parameters, equipment operating efficiency and product quality stability can be improved, while energy consumption and costs can be reduced; According to market demand and application scope, knowledge graph technology is used to conduct correlation analysis on yarn product functions, performance indicators and application scenarios to determine the development direction and technical route of new functional yarns; By building an expert knowledge base and case library for yarn surface treatment, case-based reasoning algorithms are used to make intelligent decisions and optimize the development process of new yarn products, shortening the product development cycle and improving the success rate; Use natural language processing technology to conduct sentiment analysis and semantic mining on market feedback information of yarn products, obtain users' evaluation of product performance and functions and improvement suggestions, and provide a basis for product upgrades and market competition strategy formulation; By building a yarn product life cycle management platform and using blockchain technology to trace and verify product quality information, we can increase product added value and brand influence and enhance market competitive advantage.

Images