Methods and systems for controlling fiber uniformity during spandex spinning
Through precise raw material processing, intelligent spinning process optimization, and real-time monitoring and adjustment, the problem of poor fiber uniformity in spandex spinning has been solved, achieving efficient and stable fiber production to meet the demands of the high-end market.
Patent Information
- Application Number
- CN202510483657.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-17
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2045-04-17
AI Technical Summary
In existing spandex spinning technology, the raw material pretreatment is not precise, the spinning process parameters rely on experience, and the monitoring methods are limited, resulting in poor fiber uniformity, low production efficiency, and high defect rate.
Optical sorting technology combined with multispectral imaging analysis, vacuum drying equipment and fuzzy control algorithm, response surface optimization method and genetic algorithm are used to optimize process parameters. Real-time monitoring is carried out through fiber Bragg grating and distributed temperature sensor, combined with deep learning and adaptive control algorithm for feedback adjustment, and adaptive parameter correction and machine learning prediction are introduced to optimize the spinning environment and equipment status.
It has achieved a significant improvement in fiber uniformity, reduced defect rate, increased production efficiency and raw material utilization, reduced production costs, and met the needs of the high-end market.
Smart Images

Figure CN120401026B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of spinning fiber control technology, and in particular to a method and system for controlling fiber uniformity during spandex spinning. Background Technology
[0002] Spandex, as a highly elastic fiber, is widely used in the textile industry. In the early stages of spandex spinning, raw material pretreatment relied solely on simple sieving, which was insufficient to accurately remove fine impurities. Moisture control also lacked precision, resulting in unstable raw material quality and posing a risk to fiber uniformity. For example, in some small spinning mills, impurities often led to problems such as uneven fiber thickness and breakage.
[0003] Traditional spinning process parameters rely heavily on experience, making it difficult to adapt to the complex and ever-changing characteristics of raw materials and equipment conditions. Using fixed parameters for different batches of raw materials cannot simultaneously guarantee fiber strength, elasticity, and uniformity. For example, inappropriate spinning temperature can lead to internal structural defects in the fiber, affecting uniformity.
[0004] Monitoring methods for the spinning process are limited. Ordinary pressure and temperature sensors lack sufficient accuracy to capture subtle changes in real time. Manual sampling of fiber morphology is inefficient and cannot provide comprehensive coverage. In today's high-speed production environment, traditional monitoring methods cannot detect problems in time, delaying adjustments and resulting in a large number of defective products. Therefore, the development of advanced methods and systems for controlling the uniformity of spandex spinning fibers is urgently needed. Summary of the Invention
[0005] The present invention proposes a method and system for controlling fiber uniformity during spandex spinning to solve the problems mentioned in the prior art.
[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for controlling fiber uniformity during spandex spinning, comprising:
[0007] Spinning raw material pretreatment steps: The spandex spinning raw material is screened using optical sorting technology combined with multispectral imaging analysis to identify and remove impurities. The raw material is then placed in a temperature and humidity controlled vacuum drying device. A fuzzy control algorithm is used to dynamically adjust the drying temperature and vacuum level based on real-time humidity and temperature feedback of the raw material to remove moisture and prevent moisture from causing fiber defects during spinning. The dried raw material is then stirred and mixed using a stirring device equipped with variable frequency speed control and stirring mode switching functions. Inert gas is introduced during the stirring process to ensure uniform mixing of the raw material.
[0008] The optimization steps for spinning process parameters are as follows: Based on the characteristics of the spinning equipment and the raw material parameters, the spinning process parameters are determined using response surface methodology combined with a genetic algorithm; a mathematical model is constructed with spinning temperature, spinning pressure, screw speed, and spinning velocity as independent variables and fiber uniformity as the response value; through experimental design, fiber uniformity data under different parameter combinations are obtained, and regression analysis is used to obtain the relationship between fiber uniformity U and spinning temperature T, spinning pressure P, screw speed n, and spinning velocity v, expressed as U = aT. 2 +bP 2 +cn 2 +dv 2 +eT+fP+gn+hv+i, where a, b, c, d, e, f, g, h, and i are regression coefficients; at the same time, considering the differences between different batches of raw materials, an adaptive parameter correction mechanism is introduced to fine-tune the process parameters according to the initial characteristics of the raw materials;
[0009] Real-time monitoring steps of the spinning process: A pressure sensor is installed at the spinning nozzle, using fiber Bragg grating sensing technology to monitor the spinning pressure in real time and provide a high-frequency response to dynamic changes in pressure; a temperature sensor is installed in the spinning tunnel, using distributed fiber optic temperature sensing technology to measure the continuous spatial temperature during the spinning process; an online image acquisition device is used to acquire morphological images of the fibers during the spinning process, which are then analyzed using a deep learning convolutional neural network (CNN) algorithm, and fine-tuned in the actual spinning scenario;
[0010] Feedback adjustment steps: Real-time monitoring and acquisition of spinning pressure, temperature, and fiber morphology data are transmitted to the control system; when the spinning pressure deviates from the set value, the control system adjusts the metering pump speed n according to the pressure deviation ΔP. p Pressure adjustment is performed using the formula n. p =n p0 +k1ΔP+k 11 ΔP 2 , where n p0 The initial metering pump speed is given by k, and k1 is the primary pressure adjustment coefficient. 11 The secondary pressure adjustment coefficient was determined experimentally; when the temperature deviates from the set value, the power P of the heating or cooling device is adjusted. hc The adjustment formula is P hc =P hc0 +k2ΔT+k 22 ΔT 2 , where P hc0 k is the initial power, k2 is the primary temperature regulation coefficient, and k 22 The secondary temperature adjustment coefficient was determined experimentally. If the fiber diameter uniformity is lower than the set standard, it can be optimized by adjusting the stretch ratio R of the spinning nozzle. The adjustment formula is R = R0 + k3ΔU + k 33 ΔU2 Where R0 is the initial position-to-scaling ratio, k3 is the first uniformity adjustment coefficient, and k 33 The coefficient for adjusting the uniformity is determined experimentally. Simultaneously, a predictive feedback mechanism is introduced to fine-tune the process parameters in advance based on the prediction of future changes in process parameters using a machine learning model.
[0011] Furthermore, it also includes:
[0012] Real-time raw material characteristic detection steps: A near-infrared spectrometer is installed in the raw material conveying pipeline to detect the chemical composition and molecular weight distribution of the raw material in real time; a spectral fusion technology is used to combine near-infrared spectroscopy with Raman spectroscopy to obtain the molecular structure information of the raw material; by establishing a correlation model between the raw material characteristics and multispectral data, the support vector machine (SVM) algorithm is used to analyze the spectral data to obtain the characteristic parameters of the raw material.
[0013] Spinning environment control steps: Install a temperature and humidity control system in the spinning workshop, using a distributed temperature and humidity sensor network based on the Internet of Things to achieve real-time monitoring and control of temperature and humidity in the workshop; install air purification equipment, using electrostatic adsorption and filtration composite technology to remove dust and impurities in the workshop air; at the same time, use active noise reduction technology, through the principle of anti-phase sound wave cancellation, to reduce workshop noise and ensure that fiber uniformity is not affected by environmental fluctuations.
[0014] Furthermore, in the pretreatment step of the spinning raw materials, the screened raw materials are subjected to surface modification treatment; a low-temperature plasma and nano-coating composite treatment technology is used to introduce active groups on the surface of the raw materials and deposit a uniform nano-coating; through surface modification, not only is the flowability and compatibility with additives improved, but the raw materials are also endowed with certain antistatic and antibacterial properties.
[0015] Furthermore, in the optimization step of spinning process parameters, the aging and wear factors of spinning equipment are considered; by adopting the fusion technology based on acoustic emission detection and infrared thermal imaging sensors, a fuzzy relationship model between equipment wear and process parameter correction is established. When the wear of equipment components reaches a threshold, the spinning process parameters are automatically corrected to maintain fiber uniformity; at the same time, based on the prediction of the remaining service life of the equipment, equipment maintenance and replacement plans are arranged in advance.
[0016] Furthermore, in the feedback adjustment step, an adaptive control algorithm combined with a reinforcement learning algorithm is introduced; the control system automatically adjusts the adjustment coefficients k1, k2, k3, and k based on historical and real-time data from the spinning process. 11 k 22 k 33The reinforcement learning algorithm interacts with the spinning process and continuously tries different adjustment strategies to optimize the reward value for fiber uniformity. At the same time, a target optimization mechanism is introduced to balance spinning efficiency and energy consumption while ensuring fiber uniformity.
[0017] Furthermore, in the real-time monitoring step of the spinning process, machine learning algorithms are used to predict and analyze the monitoring data. An attention-based Long Short-Term Memory (LSTM) network model is employed, using historical monitoring data as input to automatically focus on key features and time-series information in the data, predicting future trends in spinning pressure, temperature, and fiber morphology.
[0018] A system for controlling fiber uniformity during spandex spinning, comprising:
[0019] Raw material pretreatment module: Equipped with a raw material screening device, using optical sorting equipment combined with a multispectral imaging analysis system to identify and remove impurities in the raw materials; vacuum drying equipment equipped with temperature and humidity control functions, using a fuzzy control algorithm to dynamically adjust drying parameters according to the real-time status of the raw materials; stirring equipment adopts variable frequency speed regulation and stirring mode switching technology, and inert gas is introduced during the stirring process. At the same time, it is also equipped with an additive dispensing device to add additives according to the characteristics of the raw materials and process requirements.
[0020] Process parameter optimization module: It incorporates response surface methodology software combined with a genetic algorithm solver to construct a mathematical model of fiber uniformity and spinning process parameters based on input spinning equipment parameters, raw material parameters, and experimental data. The genetic algorithm searches for optimal solutions in the solution space to obtain the spinning process parameters, which are then transmitted to the spinning equipment control system. It also features adaptive parameter correction, fine-tuning process parameters based on initial raw material characteristics. Furthermore, it connects to the equipment status monitoring module to adjust process parameters in real time based on equipment wear.
[0021] Real-time monitoring module: Includes a pressure sensor using fiber Bragg grating sensing technology to monitor spinning pressure in real time and respond to dynamic pressure changes at high frequency; a temperature sensor using distributed fiber optic temperature sensing technology to measure the temperature of the continuous space in the spinning tunnel; an online image acquisition device using a camera and matching light source, combined with a deep learning convolutional neural network (CNN) algorithm to detect fiber diameter changes, distribution, and surface defects; also equipped with an acoustic emission sensor and an infrared thermal imager to monitor the operating status of spinning equipment components;
[0022] Feedback adjustment module: Composed of the control system, it receives data transmitted from the real-time monitoring module; when the data deviates from the set value, it adjusts the spinning process by controlling the metering pump speed, the power of the heating or cooling device, and the spinning nozzle stretch ratio according to the adjustment formula; it adopts an adaptive control algorithm combined with a reinforcement learning algorithm to automatically adjust the adjustment coefficient, while introducing a target optimization mechanism to take into account fiber uniformity, spinning efficiency, and energy consumption; it also has a predictive feedback function to make fine adjustments in advance based on the prediction results of the machine learning model;
[0023] Raw material characteristic detection module: Near-infrared spectrometer and Raman spectrometer are installed in the raw material conveying pipeline. The molecular structure information of the raw materials is obtained by using spectral fusion technology. The data processing unit uses the support vector machine (SVM) algorithm to analyze the spectral data, obtain the raw material characteristic parameters, and feed the results back to the raw material pretreatment module to adjust the raw material processing method and the amount of additives.
[0024] Environmental control module: The temperature and humidity control system adopts an IoT-based distributed temperature and humidity sensor network to achieve real-time monitoring and control of temperature and humidity in the workshop; the air purification equipment adopts electrostatic adsorption and filtration composite technology, and the active noise reduction equipment adopts the principle of anti-phase sound wave cancellation to reduce workshop noise; it also has a laminar flow air supply system to optimize the airflow distribution in the workshop and achieve uniform and stable airflow in the spinning area.
[0025] Learning and prediction module: Based on the attention-based Long Short-Term Memory (LSTM) network model, it is trained using historical monitoring data; it predicts future changes in spinning pressure, temperature and fiber morphology, and transmits the prediction results to the feedback adjustment module and the process parameter optimization module to adjust the process parameters in advance.
[0026] Furthermore, it also includes:
[0027] Equipment Status Monitoring Module: This module monitors the operating status of the spinning equipment in real time using vibration sensors, displacement sensors, acoustic emission sensors, and infrared thermal imagers installed on the equipment components. Utilizing sensor fusion technology and fault diagnosis algorithms, it determines whether there are potential faults based on sensor data. When an abnormality is detected, an alarm is issued, and the equipment status data is transmitted to the process parameter optimization module for adjustment. Simultaneously, the module is equipped with a function to predict the remaining service life of the equipment, allowing for advance planning of equipment maintenance and replacement.
[0028] Human-computer interaction module: Provides a visual operation interface, using virtual reality and augmented reality technologies. Operators can input spinning task parameters, view real-time monitoring data, historical data, and system operating status. At the same time, they can set system parameters, including adjustment coefficients and alarm thresholds, to achieve convenient management and monitoring of the system. It also has a voice interaction function, which makes it convenient for operators to operate in the environment.
[0029] Compared with existing technologies, the beneficial effects of this invention are:
[0030] Regarding fiber quality improvement, precise control methods and intelligent systems enable real-time monitoring and adjustment of key parameters during the spinning process, effectively reducing fiber thickness unevenness and keeping the diameter deviation of spandex fibers within a very small range. This significantly improves fiber uniformity, resulting in more stable and consistent performance in key performance indicators such as strength and elasticity of the produced spandex fibers. This significantly enhances the overall quality of spandex products and meets the stringent requirements of the high-end market for fiber quality.
[0031] From a production efficiency perspective, the system possesses rapid response and automatic control capabilities, quickly reacting to and correcting abnormalities that occur during the spinning process. This avoids frequent downtime caused by fiber unevenness, effectively reducing production interruption time and enabling the spandex spinning production line to operate stably for extended periods. This significantly increases fiber output per unit time, reduces production costs, and enhances the company's competitiveness in the market. Regarding raw material utilization, the effective control of fiber uniformity reduces waste caused by fiber quality issues, improves raw material utilization, reduces resource waste, aligns with sustainable development principles, and saves the company substantial raw material procurement costs.
[0032] Furthermore, this control method and system have good compatibility and scalability, and can be effectively integrated with existing spandex spinning equipment without large-scale equipment replacement, reducing the cost and difficulty of enterprise technology upgrades. At the same time, it can also be functionally expanded and optimized according to enterprise production needs and technological development, providing strong support for the technological progress and industrial upgrading of the spandex spinning industry, and promoting the entire industry to develop in the direction of high quality and high efficiency. Attached Figure Description
[0033] Figure 1 This is a schematic block diagram of the fiber uniformity control system during the spandex spinning process proposed in this invention.
[0034] Figure 2 This is a schematic block diagram of the fiber uniformity control method in the spandex spinning process proposed in this invention.
[0035] Figure 3 This is a schematic diagram comparing the fiber uniformity of the fiber uniformity control method in the spandex spinning process proposed in this invention.
[0036] Figure 4 This is a schematic diagram comparing the spinning efficiency of the fiber uniformity control method proposed in this invention during the spandex spinning process. Detailed Implementation
[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0038] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.
[0039] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.
[0040] Reference Figures 1-4 : A method and system for controlling fiber uniformity during spandex spinning - detailed implementation method
[0041] I. System Overall Framework
[0042] This method and system for controlling fiber uniformity in spandex spinning encompasses multiple key modules, including raw material pretreatment, process parameter optimization, real-time monitoring, feedback adjustment, raw material characteristic detection, environmental control, machine learning prediction, equipment status monitoring, and human-machine interaction. These modules work closely together to precisely control the entire spinning process, starting from the raw material preparation stage, ensuring optimal uniformity of the spandex fibers.
[0043] II. Detailed Implementation Steps for Each Module
[0044] (I) Spinning Raw Material Pretreatment Module
[0045] 1. Raw material screening: High-precision optical sorting equipment is used in conjunction with a multispectral imaging analysis system. Based on the differences in light absorption and reflection of substances, impurities are identified by a multispectral camera and removed by high-speed air blowing with a precision of micron level. A magnetic separator is also set up to remove metal particles.
[0046] 2. Vacuum drying: The vacuum drying equipment has an intelligent temperature and humidity control system. It uses temperature and humidity sensors and fuzzy control algorithms to adjust the heating power and pumping rate in real time according to the humidity of the raw materials, maintaining 60-80℃ and 10-20Pa for 4-6 hours of drying.
[0047] 3. Stirring and mixing: The high-speed stirring equipment is equipped with a variable frequency motor, and the speed is adjusted to 800-1200 rpm according to the properties of the raw materials. Special blades are used to enhance the effect. Argon gas is passed through at 0.1-0.5L / min during stirring to prevent oxidation. Stir well for 15-25 minutes. Additives are added as required using a high-precision metering pump.
[0048] (II) Spinning Process Parameter Optimization Module
[0049] 1. Model Construction and Solution: The module incorporates response surface optimization software and a genetic algorithm solver. Operators input spinning equipment and raw material parameters, and through multiple sets of experiments, obtain fiber uniformity data under different parameter combinations, constructing U = aT. 2 +bP 2 +cn 2 +dv 2 The +eT+fP+gn+hv+i model uses a genetic algorithm to search for the optimal parameters.
[0050] 2. Adaptive parameter correction: Connected to the raw material characteristic detection and equipment status monitoring modules, parameters are adjusted according to the correlation model when the raw material characteristics change, and adjustments are made according to the fuzzy relation model when key equipment components are worn. For example, if the nozzle orifice diameter increases, the pressure is reduced and the rotation speed and speed combination are adjusted.
[0051] (III) Real-time monitoring module for the spinning process
[0052] 1. Pressure monitoring: A fiber Bragg grating pressure sensor is installed at the spinning nozzle. It transmits light signals by utilizing the wavelength variation of the fiber grating with pressure. The accuracy is ±0.005MPa, the sampling frequency is over 100Hz, and the fiber optic cable has strong anti-interference capabilities.
[0053] 2. Temperature monitoring: Sensors using distributed optical fiber temperature sensing technology are used in the spinning tunnel to measure the temperature of the continuous space based on the characteristics of backscattered light, with an accuracy of ±0.1℃.
[0054] 3. Fiber morphology monitoring: A high-resolution camera with a dedicated lens and light source is used to capture fiber morphology at a frame rate of 50-100fps. A pre-trained CNN algorithm is used to identify diameter, distribution, and microscopic defects.
[0055] 4. Equipment status monitoring: Install acoustic emission sensors to determine equipment faults based on signal characteristics, and use infrared thermal imagers to monitor equipment overheating and provide early warnings.
[0056] (iv) Feedback Adjustment Module
[0057] 1. Parameter Adjustment: The control system adjusts based on real-time monitoring data; when the pressure deviation ΔP occurs, adjust according to n. p =n p0 +k1ΔP+k 11 ΔP 2 Adjust the metering pump speed; when the temperature deviation ΔT is within the specified range, press P. hc =P hc0 +k2ΔT+k 22 ΔT 2 When adjusting heating and cooling power, the uniformity deviation ΔU is calculated as R = R0 + k3ΔU + k 33 ΔU 2 The nozzle stretch ratio was adjusted, and the coefficient was determined through numerous experiments.
[0058] 2. Application of intelligent algorithms: The combination of adaptive and reinforcement learning algorithms, the adaptive algorithm adjusts the coefficients, and the reinforcement learning optimizes the strategy based on the reward value, taking into account fiber uniformity, spinning efficiency and energy consumption, and setting weights for comprehensive optimization.
[0059] 3. Predictive feedback: Fine-tuning in advance based on machine learning predictions, such as reducing the metering pump speed in advance if pressure is predicted to rise.
[0060] (V) Raw Material Characteristic Testing Module
[0061] 1. Spectroscopic detection: The raw material delivery tube is equipped with near-infrared and Raman spectrometers. The former measures the vibration of hydrogen-containing groups, and the latter measures the molecular skeleton. Spectroscopic fusion technology integrates the data.
[0062] 2. Data processing and feedback: The data processing unit uses the SVM algorithm to collect multiple batches of raw material spectra and characteristic parameters to build a training set, train the correlation model, and provide feedback to the raw material pretreatment module in real time to adjust the processing method and additive dosage.
[0063] (vi) Environmental Control Module
[0064] 1. Temperature and humidity control: Using an IoT distributed temperature and humidity sensor network, the sensors wirelessly transmit data, and the central system controls the air conditioner, humidifier, and dehumidifier, controlling the temperature at 22-25℃ and the humidity at 50-60%RH, with an accuracy of ±0.5℃ and ±1%RH.
[0065] 2. Air purification: The air purification equipment uses a combination of electrostatic adsorption and filtration technology. Static electricity causes dust to become charged and is adsorbed. Multi-layer filtration removes fine particles, achieving a purification rate of 99.9%.
[0066] 3. Noise reduction and airflow optimization: The active noise reduction equipment emits anti-phase sound waves to reduce noise to 65dB(A), and the laminar flow air supply system is set with supply and return air vents to form a uniform laminar flow.
[0067] (vii) Machine Learning Prediction Module
[0068] 1. Model building and training: Using the LSTM-Attention model, historical monitoring data is collected and divided into training and test sets. During training, the model learns the rules by using the attention mechanism and adjusts the parameters.
[0069] 2. Prediction and Decision Making: Input real-time data to predict changes over 10-30 minutes, and transmit the results to the adjustment and process parameter optimization module for comprehensive decision-making in conjunction with the expert knowledge base.
[0070] (viii) Equipment Status Monitoring Module
[0071] 1. Multi-sensor monitoring: Multiple sensors such as vibration, displacement, acoustic emission, and infrared thermal imaging are installed on key components of the spinning equipment. Vibration and displacement sensors measure the operating status of the components, while acoustic emission and infrared thermal imaging monitor potential faults.
[0072] 2. Fault diagnosis and early warning: Data is integrated and analyzed using multi-sensor fusion technology and fault diagnosis algorithms to identify potential faults, issue alarms when abnormalities occur, transmit equipment status data to the process parameter optimization module to adjust parameters, and predict the remaining service life to arrange maintenance and replacement.
[0073] (ix) Human-Computer Interaction Module
[0074] 1. Visualized User Interface: Provides a visual interface using VR and AR technologies, allowing operators to immerse themselves in inputting task parameters, viewing real-time and historical data, and system status.
[0075] 2. Intelligent voice interaction: It has intelligent voice interaction function, which is convenient for operation in special environments. System parameters such as adjustment coefficients and alarm thresholds can also be set.
[0076] III. Characterization of Beneficial Effects Data
[0077] Evaluation indicators Traditional spinning system This patented spinning system Increase ratio Fiber uniformity (CV value) 8% 3% Reduced by 62.5% Defect rate 15% 5% Reduced by 66.7% Spinning efficiency (output / day) 10 tons 13 tons Increase by 30% Energy consumption (kWh / ton of fiber) 300 250 Reduced by 16.7%
[0078] As can be seen, this patented system significantly improves the uniformity of spandex spinning fibers, reduces the defect rate, increases efficiency, and reduces energy consumption, demonstrating clear advantages.
[0079] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.
Claims
1. A method for controlling fiber uniformity during spandex spinning, characterized in that, include: Spinning raw material pretreatment steps: The spandex spinning raw material is screened using optical sorting technology combined with multispectral imaging analysis to identify and remove impurities. The raw material is then placed in a temperature and humidity controlled vacuum drying device. A fuzzy control algorithm is used to dynamically adjust the drying temperature and vacuum level based on real-time humidity and temperature feedback of the raw material to remove moisture and prevent moisture from causing fiber defects during spinning. The dried raw material is then stirred and mixed using a stirring device equipped with variable frequency speed control and stirring mode switching functions. Inert gas is introduced during the stirring process to ensure uniform mixing of the raw material. The optimization steps for spinning process parameters are as follows: Based on the characteristics of the spinning equipment and the raw material parameters, the spinning process parameters are determined using response surface methodology combined with a genetic algorithm; a mathematical model is constructed with spinning temperature, spinning pressure, screw speed, and spinning velocity as independent variables and fiber uniformity as the response value; through experimental design, fiber uniformity data under different parameter combinations are obtained, and regression analysis is used to obtain the relationship between fiber uniformity U and spinning temperature T, spinning pressure P, screw speed n, and spinning velocity v. Where a, b, c, d, e, f, g, h, and i are regression coefficients; at the same time, considering the differences between different batches of raw materials, an adaptive parameter correction mechanism is introduced to fine-tune each process parameter according to the initial characteristics of the raw materials. In the step of optimizing spinning process parameters, considering the aging and wear factors of spinning equipment, a fusion technology based on acoustic emission detection and infrared thermal imaging sensors is adopted. By establishing a fuzzy relationship model between equipment wear and process parameter correction, when the wear of equipment parts reaches a threshold, the spinning process parameters are automatically corrected to maintain fiber uniformity. At the same time, based on the prediction of the remaining service life of the equipment, equipment maintenance and replacement plans are arranged in advance. Real-time monitoring steps of the spinning process: A pressure sensor is installed at the spinning nozzle, using fiber Bragg grating sensing technology to monitor the spinning pressure in real time and provide a high-frequency response to dynamic changes in pressure; a temperature sensor is installed in the spinning tunnel, using distributed fiber optic temperature sensing technology to continuously measure the spatial distribution of temperature during the spinning process; an online image acquisition device is used to acquire morphological images of the fibers during the spinning process, which are then analyzed using a deep learning convolutional neural network (CNN) algorithm, and fine-tuned in the actual spinning scenario; Feedback adjustment steps: Real-time monitoring and acquisition of spinning pressure, spinning temperature, and fiber morphology data are transmitted to the control system; when the spinning pressure deviates from the set value, the control system adjusts the control system based on the pressure deviation. By adjusting the metering pump speed Adjust the pressure using the following formula: ,in The initial metering pump speed, This is the primary pressure regulation coefficient. The secondary pressure adjustment coefficient was determined experimentally; when the temperature deviates from the set value, the power of the heating or cooling device is adjusted. The adjustment formula is ,in This represents the deviation value of the spinning temperature. For initial power, This is the primary temperature regulation coefficient. The secondary temperature adjustment coefficient was determined experimentally. When the fiber uniformity was lower than the set standard, optimization was achieved by adjusting the draw ratio R of the spinning nozzle. The adjustment formula is as follows: ,in This represents the deviation value for fiber uniformity. This is the initial stretch ratio. This is the uniformity adjustment coefficient. The coefficient for adjusting the uniformity is determined experimentally. At the same time, a predictive feedback mechanism is introduced to make fine adjustments in advance based on the prediction of changes in process parameters in the future time based on the machine learning model. Real-time raw material property detection steps: A near-infrared spectrometer is installed in the raw material conveying pipeline to detect the chemical composition and molecular weight distribution of the raw material in real time; a spectral fusion technology is used to combine near-infrared spectroscopy with Raman spectroscopy to obtain the molecular structure information of the raw material; by establishing a correlation model between raw material properties and multispectral data, the support vector machine (SVM) algorithm is used to analyze the spectral data to obtain the characteristic parameters of the raw material; In the feedback adjustment step, an adaptive control algorithm combined with a reinforcement learning algorithm is introduced; The control system automatically adjusts the adjustment coefficient based on historical and real-time data from the spinning process. ; Reinforcement learning algorithms interact with the spinning process and continuously adjust their control strategies based on reward values to optimize fiber uniformity. At the same time, a target optimization mechanism is introduced to balance spinning efficiency and energy consumption while ensuring fiber uniformity. It also includes: spinning environment control steps: installing a temperature and humidity control system in the spinning workshop, using a distributed temperature and humidity sensor network based on the Internet of Things to realize real-time monitoring and control of temperature and humidity in the workshop; By installing air purification equipment and using electrostatic adsorption and filtration composite technology, dust and impurities in the workshop air are removed. At the same time, active noise reduction technology is used to reduce workshop noise through the principle of anti-phase sound wave cancellation, ensuring that fiber uniformity is not affected by environmental fluctuations.
2. The method for controlling fiber uniformity during spandex spinning according to claim 1, characterized in that, In the pretreatment step of spinning raw materials, the screened raw materials are subjected to surface modification treatment; By employing a low-temperature plasma and nano-coating composite treatment technology, active groups are introduced onto the surface of the raw material while a uniform nano-coating is deposited. Through surface modification, not only is the flowability and compatibility with additives improved, but the raw material is also endowed with certain antistatic and antibacterial properties.
3. The method for controlling fiber uniformity during spandex spinning according to claim 1, characterized in that, In the real-time monitoring step of the spinning process, machine learning algorithms are used to predict and analyze the monitoring data; an attention-based Long Short-Term Memory (LSTM) network model is used for training with historical monitoring data; future changes in spinning pressure, temperature and fiber morphology are predicted, and the prediction results are transmitted to the feedback adjustment module and the process parameter optimization module to adjust the process parameters in advance.
4. A system for implementing the fiber uniformity control method in the spandex spinning process according to any one of claims 1-3, characterized in that, include: Raw material pretreatment module: Equipped with a raw material screening device, using optical sorting equipment combined with a multispectral imaging analysis system to identify and remove impurities in the raw materials; vacuum drying equipment equipped with temperature and humidity control functions, using a fuzzy control algorithm to dynamically adjust drying parameters according to the real-time status of the raw materials; stirring equipment adopts variable frequency speed regulation and stirring mode switching technology, and inert gas is introduced during the stirring process. At the same time, it is also equipped with an additive dispensing device to add additives according to the characteristics of the raw materials and process requirements. Process parameter optimization module: It incorporates response surface methodology software combined with a genetic algorithm solver to construct a mathematical model of fiber uniformity and spinning process parameters based on input spinning equipment parameters, raw material parameters, and experimental data. The genetic algorithm searches for optimal solutions in the solution space to obtain the spinning process parameters, which are then transmitted to the spinning equipment control system. It also features adaptive parameter correction, fine-tuning process parameters based on initial raw material characteristics. Furthermore, it connects to the equipment status monitoring module to adjust process parameters in real time based on equipment wear. Real-time monitoring module: Includes a pressure sensor using fiber Bragg grating sensing technology to monitor spinning pressure in real time and respond to dynamic pressure changes at high frequency; a temperature sensor using distributed fiber optic temperature sensing technology to continuously measure the spatial distribution of temperature within the spinning tunnel; an online image acquisition device using a camera and matching light source, combined with a deep learning convolutional neural network (CNN) algorithm to detect fiber diameter changes, distribution, and surface defects; also equipped with an acoustic emission sensor and an infrared thermal imager to monitor the operating status of spinning equipment components; Feedback adjustment module: Composed of the control system, it receives data transmitted from the real-time monitoring module; when the data deviates from the set value, it adjusts the spinning process by controlling the metering pump speed, the power of the heating or cooling device, and the spinning nozzle stretch ratio according to the adjustment formula; it adopts an adaptive control algorithm combined with a reinforcement learning algorithm to automatically adjust each adjustment coefficient, while introducing a target optimization mechanism to take into account fiber uniformity, spinning efficiency, and energy consumption; it also has a predictive feedback function to make fine adjustments in advance based on the prediction results of the machine learning model; Raw material characteristic detection module: Near-infrared spectrometer and Raman spectrometer are installed in the raw material conveying pipeline. The molecular structure information of the raw materials is obtained by using spectral fusion technology. The data processing unit uses the support vector machine (SVM) algorithm to analyze the spectral data, obtain the raw material characteristic parameters, and feed the results back to the raw material pretreatment module to adjust the raw material processing method and the amount of additives. Environmental control module: The temperature and humidity control system adopts an IoT-based distributed temperature and humidity sensor network to achieve real-time monitoring and control of temperature and humidity in the workshop; the air purification equipment adopts electrostatic adsorption and filtration composite technology, and the active noise reduction equipment adopts the principle of anti-phase sound wave cancellation to reduce workshop noise; it also has a laminar flow air supply system to optimize the airflow distribution in the workshop and achieve uniform and stable airflow in the spinning area. Learning and prediction module: Based on the attention mechanism, a long short-term memory network (LSTM) model is constructed and trained using historical monitoring data; it predicts future changes in spinning pressure, temperature and fiber morphology, and transmits the prediction results to the feedback adjustment module and the process parameter optimization module to adjust the process parameters in advance.
5. The system according to claim 4, characterized in that, Also includes: Equipment Status Monitoring Module: This module monitors the operating status of the spinning equipment in real time using vibration sensors, displacement sensors, acoustic emission sensors, and infrared thermal imagers installed on the equipment components. Utilizing sensor fusion technology and fault diagnosis algorithms, it determines whether there are potential faults based on sensor data. When an abnormality is detected, an alarm is issued, and the equipment status data is transmitted to the process parameter optimization module for adjustment. Simultaneously, the module is equipped with a function to predict the remaining service life of the equipment, allowing for advance planning of equipment maintenance and replacement.
6. The system according to claim 4, characterized in that, Also includes: Human-computer interaction module: Provides a visual operation interface, using virtual reality and augmented reality technologies. Operators can input spinning task parameters, view real-time monitoring data, historical data, and system operating status; at the same time, they can set system parameters, including adjustment coefficients and alarm thresholds, to achieve convenient management and monitoring of the system; it also has a voice interaction function to facilitate operation.
Citation Information
Patent Citations
Spinning parameter control method to improve the consistency of ultrafine fiber yarn
CN119758886A
