Yarn anti-winding method

Abstract

The invention provides a yarn anti-winding method which comprises the following steps: according to the relevance between yarn material characteristics and a processing technology, by optimizing the yarn raw material ratio and technological parameter setting, the generation of hairiness impurities on the surface of yarn is reduced, and the yarn uniformity and smoothness are improved, so that the friction adhesion risk between yarns is reduced; automatic quality detection devices are arranged among all procedures of yarn production, multi-source quality data such as yarn appearance and mechanics are collected, correlation analysis of the yarn quality data is achieved through a Kalman filtering algorithm, a yarn quality traceability chain is constructed, and when a yarn winding problem is found, a problem source is rapidly positioned and diagnosed, and the yarn winding problem is accurately detected. And a basis is provided for subsequent process adjustment.

Description

Technical Field

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

[0002] During the production process, yarns are prone to entanglement due to the influence of factors such as their own material properties, processing technology, and equipment status. When the yarns are running at high speed, the hairiness and impurities on the surface can easily cause friction and adhesion between the yarns, causing the yarns to be entangled together, forming quality defects such as yarn knots and broken ends. At the same time, when the parameters such as tension and speed of the yarn fluctuate, it is also easy to cause yarn entanglement problems, affecting production efficiency and product quality.

[0003] In order to solve the technical problem of yarn winding, it is necessary to analyze and optimize the material properties, production process, equipment status and other aspects of the yarn. First of all, it is necessary to select suitable yarn raw materials, reduce the hairiness and impurities on the yarn surface, and improve the uniformity and smoothness of the yarn. Secondly, it is necessary to optimize the production process of the yarn, such as using advanced processes such as air spinning and compact spinning to reduce the stress concentration and unevenness of the yarn during the production process. Thirdly, it is necessary to strengthen the maintenance and management of yarn production equipment, such as regular cleaning, lubrication, calibration, etc., to ensure the stability and reliability of equipment operation. Finally, it is necessary to establish a yarn quality monitoring and early warning mechanism, and timely discover and deal with quality problems such as yarn winding by online monitoring of the key parameters of the yarn to avoid the expansion of the problem.

[0004] In short, the yarn entanglement problem is a complex systemic problem that requires coordinated optimization and control of multiple links such as yarn raw materials, processes, equipment, and testing to effectively improve yarn quality, reduce the occurrence of entanglement problems, and improve the production efficiency and economic benefits of textile enterprises. Summary of the invention

[0005] The present invention provides a yarn anti-entanglement method, which mainly comprises: According to the correlation between yarn material characteristics and processing technology, by optimizing the yarn raw material ratio and process parameter settings, the generation of yarn surface hairiness impurities can be reduced, the yarn uniformity and smoothness can be improved, and the risk of friction and adhesion between yarns can be reduced. Specifically, it includes adjusting parameters such as fiber length distribution, fiber fineness, twist, and sizing agent formula; Use machine vision technology to perform real-time imaging analysis on the yarn surface morphology, extract key quality characteristic parameters such as the number of yarn hairiness impurities and length distribution, and combine with the preset quality threshold to judge in real time whether the yarn surface quality meets the standard. When yarn quality defects are detected, the alarm processing mechanism is automatically started, and the quality defect information is passed to subsequent processes; Install vibration sensors on yarn production equipment to collect vibration signals of the equipment in real time, perform time-frequency domain analysis on the collected vibration signals, extract abnormal vibration characteristics of the equipment, and judge whether the equipment operation status is normal according to the preset equipment health threshold. When signs of equipment failure are detected, the equipment maintenance management process is automatically started, and the relevant process parameters are adjusted to reduce the impact on yarn quality. At the same time, the equipment status information is associated with the yarn quality test results to analyze the impact of the equipment status on the yarn quality; In the yarn production process, key process parameters such as yarn tension, speed, temperature and humidity are collected in real time. The decision tree algorithm is used to analyze the correlation between yarn quality defects and process parameters, and a yarn quality prediction model based on random forest is established. When the process parameter fluctuation exceeds the preset range, an early warning signal is issued in time to automatically adjust the production process to avoid the occurrence of quality problems such as yarn winding. Laser speckle technology is used to precisely measure the surface morphology of the yarn, obtain microscopic morphological characteristic parameters such as yarn surface roughness and fuzz index, and use the support vector machine algorithm to build a yarn quality classification model to give early warning of the tendency of yarn winding. According to the warning results, the yarn production process is automatically optimized, such as adjusting the tension or speed to reduce the risk of yarn winding. The laser speckle measurement results are used as one of the inputs of the process parameter prediction model to improve the prediction accuracy. Automated quality detection devices are set up between each process of yarn production to collect multi-source quality data such as yarn appearance and mechanics. The Kalman filter algorithm is used to realize the correlation analysis of yarn quality data, and a yarn quality traceability chain is built. When a yarn winding problem is found, the source of the problem is quickly located and diagnosed, providing a basis for subsequent process adjustments. Establish a quality control system for the entire yarn production process, integrate multi-source heterogeneous data such as yarn raw materials, processes, equipment, and quality, use principal component analysis and neural network algorithms to explore the complex relationships between factors affecting yarn quality, and form a yarn quality optimization decision-making plan. According to the optimization plan, automatically adjust production parameters to continuously improve yarn quality, production efficiency, and economic benefits.

[0006] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: The present invention discloses a method for intelligent control of yarn production quality. The method reduces the hairiness and impurities on the yarn surface and improves the uniformity and smoothness by optimizing the raw material ratio and process parameters. The machine vision technology is used to analyze the surface morphology of the yarn in real time, and the vibration sensor is combined to monitor the equipment status, collect the process parameters in real time and establish a quality prediction model. The laser speckle technology is used to measure the microscopic morphology of the yarn, and a quality classification model is constructed for early warning. An automatic detection device is set between each process to realize the correlation analysis and traceability of quality data. The present invention integrates multi-source heterogeneous data, mines the complex correlation of quality influencing factors, forms an optimized decision-making plan and automatically adjusts the production parameters. Through the above-mentioned technical means, the present invention realizes the intelligent quality control of the whole process of yarn production, effectively reduces the occurrence of quality problems such as yarn winding, and improves product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 The present invention is a flow chart of a yarn anti-entanglement method.

[0008] Figure 2 It is a schematic diagram of a yarn anti-entanglement method of the present invention.

[0009] Figure 3 It is another schematic diagram of a yarn anti-entanglement method of the present invention. DETAILED DESCRIPTION

[0010] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0011] like Figure 1-3 In this embodiment, a yarn anti-entanglement method may specifically include: Step S101, based on the correlation between yarn material properties and processing technology, by optimizing the yarn raw material ratio and process parameter settings, the generation of yarn surface hairiness impurities is reduced, the yarn uniformity and smoothness are improved, and thus the risk of friction and adhesion between yarns is reduced. Specifically, it includes adjusting parameters such as fiber length distribution, fiber fineness, twist, and sizing agent formula.

[0012] According to the material characteristics of yarn, a yarn raw material ratio optimization model is established, and the optimal raw material ratio scheme is determined by genetic algorithm to reduce the probability of yarn surface hairiness and impurities. Image processing technology is used to detect and analyze the surface morphology of yarn, extract key parameters such as fiber length distribution and fineness, and combine with expert knowledge base to optimize the spinning process parameter settings using decision tree algorithm. The yarn production process data is collected in real time through online sensors, and the yarn uniformity and smoothness are predicted using support vector machine algorithm. When the predicted value is lower than the preset threshold, the twist and sizing agent formula are dynamically adjusted to ensure the stability of yarn quality. A yarn quality evaluation index system is constructed, comprehensively considering factors such as hairiness index, impurity content, uniformity, etc., and the fuzzy comprehensive evaluation method is used to quantitatively evaluate the yarn quality to provide a decision-making basis for production optimization. The whole process data of yarn production is collected, including raw material properties, process parameters, quality inspection results, etc. Based on big data analysis technology, the key factors affecting yarn quality are excavated to form a quality optimization knowledge base to guide production practice. Develop a yarn production expert system that integrates intelligent modules such as raw material ratio, process optimization, and quality prediction to achieve intelligent control of the entire yarn production process, improve production efficiency and product quality stability. Establish a yarn quality traceability system to track the entire life cycle of raw materials, semi-finished products, and finished products through the Internet of Things technology. When quality problems occur, the cause of the problem can be quickly located, closed-loop management of quality problems can be achieved, and the production process can be continuously optimized.

[0013] Specifically, in order to optimize the raw material ratio of yarn, the attribute data of fiber length, fineness, strength and other properties of different raw materials can be collected to establish a mathematical model of raw material attributes and yarn quality. Using genetic algorithm, with the minimum hairiness index and impurity content as the optimization target, the range of raw material ratio is set as the constraint condition, iterate 500 generations, crossover probability 8, mutation probability 1, and get the optimal raw material ratio scheme, cotton ratio 60%, modal 30%, spandex 10%. The image of the yarn surface morphology is collected with a resolution of 800×600, grayed and binarized, the fiber contour is extracted, and the average fiber length is calculated to be 15mm and the fineness is 2dtex. The extracted attribute parameters are input into the decision tree model, and the spinning process parameters are set according to the expert knowledge base, including spinning speed 800m / min, ring speed 12000r / min, etc. An online sensor is installed on the spinning frame with a sampling frequency of 1kHz to collect parameters such as yarn tension and hairiness index in real time. The quality prediction model was established using the support vector machine algorithm, with 2,000 samples in the training set and 500 samples in the test set, and the prediction accuracy reached 90%. When the predicted value of yarn uniformity is lower than 85%, the twist is dynamically adjusted to 800 tpm, and the sizing agent ratio is PVA 5% and acrylic 3% to improve the strength and smoothness of the yarn. A fuzzy comprehensive evaluation model was constructed based on five indicators, including hairiness index, impurity content, and strength. The membership function uses a Gaussian function, and the weight vector is determined by the AHP method. The yarn quality score is 85, which is at a good level. A total of 100,000 yarn production process parameters and quality inspection data were collected. The association rule mining algorithm was used with a support of 0.5 and a confidence of 8. The positive correlation between spinning speed and yarn strength was found, and 50 quality optimization rules were generated. A yarn production expert system based on B / S architecture was developed. The knowledge base covers 200 rules such as raw material selection, process optimization, and quality prediction. The inference engine uses forward chain reasoning to achieve intelligent control of the entire process. By applying RFID technology, electronic tags are attached to raw materials, semi-finished products and finished products, and quality traceability is achieved through the Internet of Things. When the yarn breakage rate exceeds 5%, the system automatically locates the process where the problem occurs, optimizes the spinning process parameters, and realizes closed-loop quality control.

[0014] Step S102, using machine vision technology to perform real-time imaging analysis on the yarn surface morphology, extracting key quality characteristic parameters such as the number of yarn hairiness impurities and length distribution, and combining with the preset quality threshold, to determine in real time whether the yarn surface quality meets the standard. When a yarn quality defect is detected, the alarm processing mechanism is automatically activated, and the quality defect information is passed to the subsequent process.

[0015] A high-resolution industrial camera is used to continuously image the yarn surface to obtain a high-definition digital image of the yarn surface. The acquired yarn surface image is preprocessed, including image denoising, enhancement and segmentation, to improve the image quality and the accuracy of feature extraction. Image feature extraction algorithms, such as texture analysis and edge detection, are used to extract key quality characteristic parameters such as hairiness impurities and fiber breakage from the preprocessed yarn surface image. According to the extracted yarn surface quality characteristic parameters, machine learning algorithms such as support vector machines are used to construct a yarn surface quality evaluation model to achieve quantitative evaluation of yarn surface quality. The yarn surface quality evaluation result is compared with the preset quality threshold. If the evaluation result is lower than the threshold, it is judged as a quality defect and the alarm processing mechanism is triggered. When a quality defect is detected, the defect type, location, severity and other information are transmitted to the workshop management system and subsequent processes in real time through the industrial bus communication protocol for timely processing and quality traceability. Big data analysis technology is used to statistically analyze the collected yarn surface quality data, explore the laws and influencing factors of quality defects, and provide data support for optimizing spinning process parameters and improving equipment performance.

[0016] Specifically, an industrial camera with a resolution of 4096×3072 pixels was used to continuously image the yarn surface at a speed of 100 frames per second to obtain a high-definition digital image of the yarn surface. The obtained yarn surface image was preprocessed by median filtering denoising, histogram equalization enhancement and threshold segmentation to improve the image quality and the accuracy of feature extraction. Grayscale co-occurrence matrix texture analysis and Canny edge detection algorithms were used to extract 10 key quality characteristic parameters such as hairiness density, impurity area, and fiber breakage number from the preprocessed yarn surface image. According to the extracted yarn surface quality characteristic parameters, the support vector machine algorithm was used to construct a yarn surface quality evaluation model with radial basis kernel function. Through 5-fold cross validation, the model accuracy reached more than 95%, realizing the quantitative evaluation of yarn surface quality. The yarn surface quality evaluation result was compared with the preset quality threshold. If the evaluation result was lower than the threshold of 8, it was judged as a quality defect, triggering the sound and light alarm processing mechanism. When quality defects are detected, the defect type, location coordinates, severity and other information are transmitted to the MES workshop management system and subsequent drawing process in real time through the EtherCAT industrial bus communication protocol for timely processing and quality traceability. Big data analysis technology is used to conduct statistical analysis on the collected yarn surface quality data. Through correlation analysis and data mining, the association between yarn quality defects and spinning process parameters is discovered, and a decision tree algorithm is used to build an analysis model of factors affecting quality defects, providing data support and decision-making basis for optimizing spinning process parameters and improving equipment performance.

[0017] Step S103, install a vibration sensor on the yarn production equipment to collect the vibration signal of the equipment in real time. Perform time-frequency domain analysis on the collected vibration signal to extract the abnormal vibration characteristics of the equipment. According to the preset equipment health threshold, judge whether the equipment operation status is normal. When the sign of equipment failure is detected, automatically start the equipment maintenance management process, and adjust the relevant process parameters to reduce the impact on the yarn quality. At the same time, associate the equipment status information with the yarn quality test results to analyze the impact of the equipment status on the yarn quality.

[0018] By installing vibration sensors on yarn production equipment, the vibration signal data of the equipment is collected in real time. The collected vibration signal data is preprocessed, including denoising, normalization and other operations to improve data quality. The time-frequency domain analysis method, such as wavelet transform or Fourier transform, is used to extract the features of the preprocessed vibration signal to obtain the abnormal vibration features of the equipment. According to the preset equipment health threshold, it is judged whether the extracted abnormal vibration features exceed the normal range. If they exceed, it is considered that the equipment operation state is abnormal and there are signs of failure. When the signs of equipment failure are detected, the equipment maintenance management process is automatically triggered, and the impact of the abnormal state of the equipment on the yarn quality is reduced by adjusting relevant process parameters such as speed and tension. The equipment status information is correlated with the yarn quality test results, and a prediction model between the equipment status and the yarn quality is established by using machine learning algorithms, such as support vector machines or decision trees. The established prediction model is used to predict the quality of the yarn produced in the current state of the equipment in real time. When the predicted quality is lower than the standard, the process parameters are adjusted in time or the equipment is maintained to ensure that the yarn production quality is stable within the qualified range.

[0019] Specifically, a piezoelectric vibration sensor of model PCB 603C01 is installed on the yarn production equipment, and the sampling frequency is set to 5000Hz. The vibration data is transmitted to the data acquisition terminal in real time through the RS-485 bus. The collected vibration signal data is subjected to wavelet denoising, and the Daubechies4 wavelet basis function is used to perform a 5-layer decomposition of the signal to remove the high-frequency noise components in the vibration signal. The Z-score normalization method is then used to normalize the amplitude of the denoised signal so that the signal amplitude is distributed in the range of 0-1. Short-time Fourier transform is used to perform time-frequency analysis on the pre-processed vibration signal, and the spectrum energy value of the signal in the 0-500Hz frequency band is extracted as the abnormal vibration feature. By comparing the spectrum energy threshold under the normal operation of the equipment, it is judged whether the current equipment is abnormal. When an equipment abnormality is detected, the equipment speed is automatically reduced by 10%, and the tension setting value is increased by 5N to reduce the impact of the abnormal state of the equipment on the yarn quality. The equipment vibration characteristics and yarn quality test results are correlated and analyzed, and the support vector machine regression algorithm is used to establish a prediction model for equipment vibration energy value and quality indicators such as yarn strength and elongation at break. The model input is the equipment vibration spectrum energy value, and the output is the predicted value of various yarn quality indicators. When the quality prediction value is lower than the national standard requirement, the system automatically alarms and optimizes the equipment process parameters, and at the same time triggers the equipment maintenance management process to inspect and repair the equipment, thereby ensuring that the yarn quality is continuously stable and qualified.

[0020] Step S104: In the yarn production process, key process parameters such as yarn tension, speed, temperature and humidity are collected in real time. The decision tree algorithm is used to analyze the association between yarn quality defects and process parameters, and a yarn quality prediction model based on random forest is established. When the process parameter fluctuation exceeds the preset range, an early warning signal is issued in time to automatically adjust the production process to avoid the occurrence of quality problems such as yarn entanglement.

[0021] Real-time data of key process parameters such as yarn tension, yarn speed, ambient temperature and ambient humidity in the yarn production process are obtained, and the data are transmitted to the data processing module. The data processing module preprocesses the obtained process parameter data, including data cleaning, data normalization and other operations, to obtain a standardized process parameter data set. The standardized process parameter data set is input into the association rule analysis module based on the decision tree algorithm, and the association rules between yarn quality defects and various process parameters are mined through the decision tree algorithm to obtain an association rule set. According to the association rule set and combined with the random forest algorithm, a yarn quality prediction model is established, and the standardized process parameter data set is used as the input of the model to train and obtain the yarn quality prediction model. In the yarn production process, the data of each process parameter is collected in real time, and the data is input into the yarn quality prediction model to obtain the yarn quality prediction result under the current process parameters. It is judged whether the yarn quality prediction result exceeds the preset quality threshold range. If it exceeds the threshold range, an early warning signal is triggered and the early warning signal is transmitted to the production control system. The production control system automatically adjusts the yarn production process parameters, such as yarn tension and yarn speed, based on the early warning signals and the preset process parameter adjustment strategy, to avoid yarn quality problems and ensure yarn production quality.

[0022] Specifically, in the yarn production process, the key process parameter data such as yarn tension, yarn speed, ambient temperature and ambient humidity are collected in real time through sensors, collected 10 times per second, and the collected data are transmitted to the data processing module through industrial Ethernet. The data processing module uses Python's Pandas library to clean the acquired process parameter data, remove missing values ​​and outliers, and then use the minimum-maximum normalization method to normalize the data, map the data to the [0,1] interval, and obtain a standardized process parameter data set. The standardized data set is input into the association rule analysis module based on the C5 decision tree algorithm. By calculating the information gain ratio of each attribute, the attribute with the largest information gain ratio is selected as the root node of the decision tree, and the decision tree is recursively constructed to mine the association rules between yarn quality defects and various process parameters. For example, when the yarn tension exceeds 10N and the yarn speed exceeds 200m / min, it is easy to cause yarn breakage. According to the association rule set, combined with the random forest algorithm, the yarn quality prediction model is established using the sklearn library. The standardized process parameter data set is divided into a training set and a test set with a ratio of 8:2. The model hyperparameters are optimized using grid search and cross-validation methods. The yarn quality prediction model is trained and the model accuracy reaches more than 95%. During the yarn production process, the process parameter data is collected every 5 seconds, and the data is input into the yarn quality prediction model to obtain the yarn quality prediction result under the current process parameters. If the prediction result exceeds the preset quality threshold range (such as yarn strength is lower than 10cN / tex), the warning signal is triggered and transmitted to the production control system through the OPC UA protocol. According to the warning signal, the production control system combines the preset process parameter adjustment strategy (such as when the yarn strength is lower than the threshold, reduce the yarn speed and increase the yarn tension), and automatically adjusts the process parameters of the yarn production equipment through the PLC controller, such as reducing the yarn speed from 200m / min to 180m / min and increasing the yarn tension from 10N to 12N, so as to ensure that the yarn quality is stable within the qualified range. Through this intelligent yarn quality prediction and control system, real-time monitoring and optimization control of the yarn production process can be achieved, effectively improving yarn quality and production efficiency.

[0023] Step S105, laser speckle technology is used to precisely measure the yarn surface morphology to obtain microscopic morphological characteristic parameters such as yarn surface roughness and fuzz index. A yarn quality classification model is constructed using the support vector machine algorithm to provide early warning of yarn winding tendency. Based on the warning results, the yarn production process is automatically optimized, such as adjusting tension or speed to reduce the risk of yarn winding. The laser speckle measurement results are used as one of the inputs of the process parameter prediction model to improve the prediction accuracy.

[0024] A high-resolution laser speckle meter is used to scan the yarn surface to obtain the three-dimensional morphological data of the yarn surface. The acquired speckle image is processed to extract the microscopic morphological characteristic parameters such as the yarn surface roughness and fuzz index. According to the yarn quality standard, the extracted morphological characteristic parameters are analyzed to determine whether the yarn surface quality meets the requirements. If the yarn surface quality does not meet the requirements, the morphological characteristic parameters are input into the pre-built support vector machine quality classification model to predict the yarn winding tendency. According to the prediction results of the support vector machine model, it is determined whether the yarn has a winding risk. If there is a winding risk, an early warning is triggered. When the yarn is monitored to have a winding risk, the tension and drafting speed parameters of the yarn production equipment are automatically adjusted to optimize the production process and reduce the probability of yarn winding. The yarn surface morphological characteristic parameters obtained by laser speckle measurement are used together with the production equipment parameters as the input of the process parameter prediction model. The model is continuously optimized through the machine learning algorithm to improve the accuracy of process parameter prediction.

[0025] Specifically, a high-resolution laser speckle meter with a resolution of 1 μm was used to scan the yarn surface at a scanning frequency of 1 kHz to obtain the three-dimensional morphological data of the yarn surface. The acquired speckle image was denoised using the Gaussian filter algorithm, and then the yarn surface profile was extracted using the Otsu threshold segmentation algorithm. The microscopic morphological characteristic parameters such as the yarn surface roughness Ra and the fuzz index HI were extracted based on the profile. According to the GB / T 398-2008 yarn quality standard, when the yarn surface roughness Ra is greater than 5 μm or the fuzz index HI is greater than 2, the yarn surface quality is judged to be unqualified. The extracted morphological characteristic parameters are input into the support vector machine quality classification model based on the RBF kernel function, and the yarn winding tendency is predicted by the one-to-many multi-classification algorithm. When the yarn winding probability is greater than 65%, it is judged that there is a winding risk and an early warning is triggered. After the yarn winding risk is detected, the tension and drafting speed parameters of the yarn production equipment are automatically adjusted based on the fuzzy PID control algorithm. The production process is optimized by reducing the tension by 10% and increasing the drafting speed by 5%, and the yarn winding probability is reduced. The yarn surface roughness, fuzzing index and other morphological characteristic parameters obtained by laser speckle measurement are used together with production equipment parameters such as tension and drafting speed as the input of the BP neural network process parameter prediction model. The model is trained using the error back propagation algorithm. When the prediction error is less than 5%, the iteration is stopped and the model is continuously optimized to improve the accuracy of process parameter prediction.

[0026] Step S106, set up an automated quality inspection device between each process of yarn production to collect multi-source quality data such as yarn appearance and mechanics. Use the Kalman filter algorithm to realize the correlation analysis of yarn quality data and build a yarn quality traceability chain. When a yarn winding problem is found, quickly locate the source of the problem and diagnose it, providing a basis for subsequent process adjustments.

[0027] According to the characteristics of each process of yarn production, the location and detection parameters of the quality detection point are determined, and an automated quality detection device is installed at each detection point to collect yarn appearance image data and mechanical property data in real time. The collected yarn appearance image data is image preprocessed to extract the yarn surface defect characteristics, and the defects are identified and classified according to the preset defect type and threshold to obtain the yarn appearance quality evaluation results. The collected yarn mechanical property data is feature extracted and statistically analyzed, and the quality is evaluated according to the preset mechanical property index and threshold to obtain the yarn mechanical quality evaluation results. The yarn appearance quality evaluation results and mechanical quality evaluation results are fused to construct a multi-source quality data set. The Kalman filter algorithm is used to perform correlation analysis and fusion on the multi-source quality data to obtain the comprehensive quality evaluation results. According to the yarn production process and the sequence of each process, the comprehensive quality evaluation results are arranged in chronological order to construct a yarn quality traceability chain to achieve full-process tracking and management of yarn quality. When a yarn winding problem is detected, the time point when the problem occurred is traced through the quality traceability chain, and the machine learning algorithm is used to perform root cause analysis based on the quality data and process parameters at that time point to locate the key factors that lead to the yarn winding problem. According to the location results of the yarn winding problem, the process parameters of the corresponding process are optimized and adjusted, and the adjusted process parameters are verified and evaluated, and the optimization is continuously iterated until the yarn winding problem is eliminated to ensure that the yarn quality is stable and controllable.

[0028] Specifically, quality inspection points are set up in key processes such as spinning and winding in yarn production, and high-speed cameras and tension sensors are installed to collect yarn surface images at a speed of 100 frames per second, and yarn tension data is collected at a frequency of 1kHz. The Canny algorithm is used to detect the edges of yarn images, extract characteristic parameters such as roundness and hairiness index of yarn cross-section, and classify defects based on the grayscale and morphological differences of yarn defects using the support vector machine (SVM) algorithm, with a recognition rate of more than 95%. The yarn tension data is analyzed in the frequency domain to extract characteristic values ​​such as spectrum entropy and harmonic distortion rate, set thresholds for mechanical defects such as yarn breakage and knots, and realize real-time evaluation of yarn mechanical properties. The Kalman filter algorithm is used to fuse yarn surface quality data and mechanical property data, establish state equations and observation equations, and realize dynamic tracking of data through two steps of prediction and update. The accuracy of fused data at each quality inspection point reaches more than 98%. The quality inspection results of each batch of yarn are recorded in the production execution system MES, and the yarn quality traceability chain is constructed through timestamps, batch numbers and other information to achieve step-by-step traceability from finished yarn to raw materials. When the yarn winding problem occurs, the winding process where the winding occurs is located through the quality traceability chain, and the quality data of the spinning process of the batch is taken out. The decision tree algorithm is used to analyze the association rules between yarn winding and spinning quality parameters, and it is determined that the yarn hairiness content is the key factor causing winding. By adjusting the process parameters such as the spinning machine draft ratio and airflow pressure, the yarn hairiness index is optimized, and the quality data of the spinning process is monitored. After three iterative optimizations, the yarn winding rate is finally reduced to below 5%, achieving stable control of yarn quality.

[0029] Step S107, establish a yarn production full-process quality control system, integrate multi-source heterogeneous data such as yarn raw materials, processes, equipment, and quality. Use principal component analysis and neural network algorithms to explore the complex relationships between factors affecting yarn quality and form a yarn quality optimization decision plan. According to the optimization plan, automatically adjust production parameters to continuously improve yarn quality, production efficiency, and economic benefits.

[0030] Obtain multi-source heterogeneous data such as raw materials, processes, equipment and quality in the yarn production process, and convert them into structured data through data cleaning, conversion and integration. For the integrated structured data, the principal component analysis algorithm is used to extract the main influencing factors of yarn quality and reduce the data dimension. According to the results of principal component analysis, a neural network model is constructed to deeply explore the complex nonlinear relationship between various influencing factors and yarn quality. Through the trained neural network model, the yarn quality under different production parameter combinations is predicted, and the optimal parameter combination is selected as the quality optimization plan. The quality optimization plan is converted into control instructions that can be executed by the production equipment, and the production parameters are adjusted in real time through the automatic control system. Continuously collect optimized production data, regularly update the principal component analysis and neural network model, and form a closed-loop control for continuous optimization of yarn quality. Establish a visual platform for yarn quality control and management, monitor the key quality indicators of each production link in real time, and provide data support for management decisions.

[0031] Specifically, firstly, the raw material parameters (such as cotton length, micronaire value, etc.), process parameters (such as combing process, spinning process, etc.), equipment parameters (such as spindle speed, draft ratio, etc.) and quality data (such as yarn uniformity, breaking strength, etc.) in the yarn production process are obtained through the data acquisition system, and the ETL tool is used to clean, convert and integrate the multi-source heterogeneous data to form a structured data table. Then, the principal component analysis algorithm is used to reduce the dimension of the integrated structured data, and the main factors that have a greater impact on yarn quality, such as fiber length and spinning fineness, are extracted by calculating the variance contribution rate of each variable. On this basis, a three-layer BP neural network model is constructed, with the number of input layer nodes being the number of main influencing factors, the number of hidden layer nodes being 5 times the number of input layer nodes, and the number of output layer nodes being the number of yarn quality indicators. By setting the learning rate to 01 and the number of iterations to 1000 times, the nonlinear relationship between each influencing factor and yarn quality is mined. The trained neural network model is used to predict the yarn quality under different production parameters (such as spinning frame spindle speed of 12000 rpm, draft ratio of 5, etc.), and the parameter combination is optimized by genetic algorithm to obtain the optimal quality solution (such as spinning frame spindle speed of 11500 rpm, draft ratio of 2, etc.). The optimization solution is converted into PLC control instructions to adjust the parameters such as spinning frame spindle speed and draft ratio in real time. At the same time, the optimized production data is continuously collected, and the principal component analysis and neural network model are updated once a week to continuously improve the accuracy of yarn quality prediction. Finally, a web-based yarn quality control platform is developed to display the changing trends of key quality indicators such as yarn uniformity and breaking strength in real time through a line chart, and set a quality warning threshold. When the indicator exceeds the threshold, an automatic alarm is triggered to provide a basis for managers' decision-making.

[0032] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A yarn anti-entanglement method, characterized in that: The method comprises: According to the correlation between yarn material characteristics and processing technology, by optimizing the yarn raw material ratio and process parameter settings, the generation of yarn surface hairiness impurities can be reduced, the yarn uniformity and smoothness can be improved, and the risk of friction and adhesion between yarns can be reduced. Specifically, it includes adjusting parameters such as fiber length distribution, fiber fineness, twist, and sizing agent formula; Use machine vision technology to perform real-time imaging analysis on the yarn surface morphology, extract key quality characteristic parameters such as the number of yarn hairiness impurities and length distribution, and combine with the preset quality threshold to judge in real time whether the yarn surface quality meets the standard. When yarn quality defects are detected, the alarm processing mechanism is automatically started, and the quality defect information is passed to subsequent processes; Install vibration sensors on yarn production equipment to collect vibration signals of the equipment in real time, perform time-frequency domain analysis on the collected vibration signals, extract abnormal vibration characteristics of the equipment, and judge whether the equipment operation status is normal according to the preset equipment health threshold. When signs of equipment failure are detected, the equipment maintenance management process is automatically started, and the relevant process parameters are adjusted to reduce the impact on yarn quality. At the same time, the equipment status information is associated with the yarn quality test results to analyze the impact of the equipment status on the yarn quality; In the yarn production process, key process parameters such as yarn tension, speed, temperature and humidity are collected in real time. The decision tree algorithm is used to analyze the correlation between yarn quality defects and process parameters, and a yarn quality prediction model based on random forest is established. When the process parameter fluctuation exceeds the preset range, an early warning signal is issued in time to automatically adjust the production process to avoid the occurrence of quality problems such as yarn winding. Laser speckle technology is used to precisely measure the surface morphology of the yarn, obtain microscopic morphological characteristic parameters such as yarn surface roughness and fuzz index, and use the support vector machine algorithm to build a yarn quality classification model to give early warning of the tendency of yarn winding. According to the warning results, the yarn production process is automatically optimized, such as adjusting the tension or speed to reduce the risk of yarn winding. The laser speckle measurement results are used as one of the inputs of the process parameter prediction model to improve the prediction accuracy. Automated quality detection devices are set up between each process of yarn production to collect multi-source quality data such as yarn appearance and mechanics. The Kalman filter algorithm is used to realize the correlation analysis of yarn quality data, and a yarn quality traceability chain is built. When a yarn winding problem is found, the source of the problem is quickly located and diagnosed, providing a basis for subsequent process adjustments. Establish a quality control system for the entire yarn production process, integrate multi-source heterogeneous data such as yarn raw materials, processes, equipment, and quality, use principal component analysis and neural network algorithms to explore the complex relationships between factors affecting yarn quality, and form a yarn quality optimization decision-making plan. According to the optimization plan, automatically adjust production parameters to continuously improve yarn quality, production efficiency, and economic benefits.

2. A yarn anti-entanglement method according to claim 1, characterized in that: According to the correlation between yarn material properties and processing technology, by optimizing the yarn raw material ratio and process parameter settings, the generation of hairiness impurities on the yarn surface is reduced, the yarn uniformity and smoothness are improved, and the risk of friction and adhesion between yarns is reduced; specifically, it includes adjusting parameters such as fiber length distribution, fiber fineness, twist, sizing agent formula, etc., including: According to the material characteristics of yarn, a yarn raw material ratio optimization model is established, and the optimal raw material ratio scheme is determined through genetic algorithm to reduce the probability of hairiness and impurities on the yarn surface; Image processing technology is used to detect and analyze the surface morphology of the yarn, extract key parameters such as fiber length distribution and fineness, and combined with the expert knowledge base, the decision tree algorithm is used to optimize the setting of spinning process parameters; The yarn production process data is collected in real time through online sensors, and the support vector machine algorithm is used to predict the uniformity and smoothness of the yarn. When the predicted value is lower than the preset threshold, the twist and sizing agent formula are dynamically adjusted to ensure stable yarn quality. Construct a yarn quality evaluation index system, comprehensively consider factors such as hairiness index, impurity content and uniformity, and use fuzzy comprehensive evaluation method to quantitatively evaluate yarn quality, providing a decision-making basis for production optimization; Collect data from the entire yarn production process, including raw material properties, process parameters, and quality test results. Based on big data analysis technology, explore the key factors affecting yarn quality, form a quality optimization knowledge base, and guide production practice; Develop a yarn production expert system that integrates intelligent modules such as raw material ratio, process optimization and quality prediction to achieve intelligent control of the entire yarn production process, improve production efficiency and product quality stability; Establish a yarn quality traceability system and use Internet of Things technology to achieve full life cycle tracking of raw materials, semi-finished products and finished products. When quality problems occur, the cause of the problem can be quickly located, closed-loop management of quality problems can be achieved, and production processes can be continuously optimized.

3. A yarn anti-entanglement method according to claim 1, characterized in that: The machine vision technology is used to perform real-time imaging analysis on the yarn surface morphology, extract key quality characteristic parameters such as the number of yarn hairiness impurities and length distribution, and combine the preset quality threshold to judge in real time whether the yarn surface quality meets the standard; when the yarn quality defect is detected, the alarm processing mechanism is automatically started, and the quality defect information is passed to the subsequent process, including: Use a high-resolution industrial camera to continuously image the yarn surface and obtain high-definition digital images of the yarn surface; Perform image preprocessing on the acquired yarn surface images, including image denoising, enhancement and segmentation, to improve image quality and the accuracy of feature extraction; Using image feature extraction algorithms, such as texture analysis and edge detection, key quality feature parameters such as hairiness and fiber breakage are extracted from the pre-processed yarn surface image; According to the extracted yarn surface quality characteristic parameters, machine learning algorithms such as support vector machine are used to build a yarn surface quality evaluation model to achieve quantitative evaluation of yarn surface quality. The yarn surface quality evaluation result is compared with the preset quality threshold. If the evaluation result is lower than the threshold, it is judged as a quality defect and the alarm processing mechanism is triggered; When quality defects are detected, information such as defect type, location, severity, etc. is transmitted to the workshop management system and subsequent processes in real time through the industrial bus communication protocol for timely processing and quality traceability; Big data analysis technology is used to conduct statistical analysis on the collected yarn surface quality data, explore the laws and influencing factors of quality defects, and provide data support for optimizing spinning process parameters and improving equipment performance.

4. A yarn anti-entanglement method according to claim 1, characterized in that: The vibration sensor is installed on the yarn production equipment to collect the vibration signal of the equipment in real time; the collected vibration signal is analyzed in the time and frequency domain to extract the abnormal vibration characteristics of the equipment; According to the preset equipment health threshold, determine whether the equipment is operating normally; when signs of equipment failure are detected, automatically start the equipment maintenance management process and adjust the relevant process parameters to reduce the impact on yarn quality; at the same time, associate the equipment status information with the yarn quality test results to analyze the impact of the equipment status on the yarn quality, including: By installing vibration sensors on yarn production equipment, the vibration signal data of the equipment can be collected in real time; Preprocess the collected vibration signal data, including denoising and normalization, to improve data quality; Use time-frequency domain analysis methods, such as wavelet transform or Fourier transform, to extract features from the preprocessed vibration signal to obtain abnormal vibration features of the equipment; According to the preset equipment health threshold, determine whether the extracted abnormal vibration characteristics exceed the normal range. If exceeded, it is considered that the equipment operation status is abnormal and there are signs of failure; When signs of equipment failure are detected, the equipment maintenance management process is automatically triggered to reduce the impact of abnormal equipment status on yarn quality by adjusting relevant process parameters such as speed and tension; Correlation analysis is performed between equipment status information and yarn quality test results, and a prediction model between equipment status and yarn quality is established using machine learning algorithms, such as support vector machines or decision trees; The established prediction model is used to predict the quality of yarn produced under the current state of the equipment in real time. When the predicted quality is lower than the standard, the process parameters are adjusted or equipment maintenance is performed in time to ensure that the yarn production quality is stable within the qualified range.

5. A yarn anti-entanglement method according to claim 1, characterized in that: In the yarn production process, key process parameters such as yarn tension, speed, temperature and humidity are collected in real time; the association between yarn quality defects and process parameters is analyzed using a decision tree algorithm, and a yarn quality prediction model based on a random forest is established; when the process parameter fluctuation exceeds a preset range, an early warning signal is issued in time, and the production process is automatically adjusted to avoid the occurrence of quality problems such as yarn entanglement, including: Obtain real-time data of key process parameters such as yarn tension, yarn speed, ambient temperature and ambient humidity during yarn production, and transmit the data to the data processing module; The data processing module pre-processes the acquired process parameter data, including data cleaning and data normalization, to obtain a standardized process parameter data set; The standardized process parameter data set is input into the association rule analysis module based on the decision tree algorithm, and the association rules between yarn quality defects and various process parameters are mined through the decision tree algorithm to obtain the association rule set; According to the association rule set and combined with the random forest algorithm, a yarn quality prediction model is established, and the standardized process parameter data set is used as the input of the model to train the yarn quality prediction model; During the yarn production process, the data of various process parameters are collected in real time, and the data is input into the yarn quality prediction model to obtain the yarn quality prediction results under the current process parameters; Determine whether the yarn quality prediction result exceeds the preset quality threshold range. If it exceeds the threshold range, trigger an early warning signal and transmit the early warning signal to the production control system; The production control system automatically adjusts the yarn production process parameters, such as yarn tension and yarn speed, based on the early warning signals and the preset process parameter adjustment strategy, to avoid yarn quality problems and ensure yarn production quality.

6. A yarn anti-entanglement method according to claim 1, characterized in that: The laser speckle technique is used to precisely measure the yarn surface morphology to obtain microscopic morphological characteristic parameters such as yarn surface roughness and fuzz index; The support vector machine algorithm is used to build a yarn quality classification model to provide early warning of yarn entanglement tendency; According to the early warning results, the yarn production process is automatically optimized, such as adjusting the tension or speed to reduce the risk of yarn entanglement; the laser speckle measurement results are used as one of the inputs of the process parameter prediction model to improve the prediction accuracy, including: A high-resolution laser speckle analyzer is used to scan the yarn surface to obtain the three-dimensional morphology data of the yarn surface; The acquired speckle images are processed to extract microscopic morphological characteristic parameters such as yarn surface roughness and fuzz index; According to the yarn quality standard, the extracted morphological characteristic parameters are analyzed to determine whether the yarn surface quality meets the requirements; If the yarn surface quality does not meet the requirements, the morphological feature parameters are input into the pre-built support vector machine quality classification model to predict the yarn winding tendency; Based on the prediction results of the support vector machine model, it is determined whether the yarn has the risk of entanglement. If there is a risk of entanglement, an early warning is triggered; When the yarn is detected to be entangled, the tension and drafting speed parameters of the yarn production equipment are automatically adjusted to optimize the production process and reduce the probability of yarn entanglement; The yarn surface morphology characteristic parameters obtained by laser speckle measurement are used together with the production equipment parameters as the input of the process parameter prediction model. The model is continuously optimized through machine learning algorithms to improve the accuracy of process parameter prediction.

7. A yarn anti-entanglement method according to claim 1, characterized in that: The method includes setting up an automated quality inspection device between each process of yarn production to collect multi-source quality data such as yarn appearance and mechanics; implementing correlation analysis of yarn quality data through Kalman filtering algorithm to build a yarn quality traceability chain; and quickly locating the source of the problem and making a diagnosis when a yarn winding problem is found, providing a basis for subsequent process adjustments, including: According to the characteristics of each process of yarn production, the location and detection parameters of the quality detection points are determined, and automated quality detection devices are installed at each detection point to collect yarn appearance image data and mechanical properties data in real time; Perform image preprocessing on the collected yarn appearance image data, extract the yarn surface defect features, identify and classify the defects according to the preset defect types and thresholds, and obtain the yarn appearance quality evaluation results; Perform feature extraction and statistical analysis on the collected yarn mechanical property data, conduct quality evaluation based on preset mechanical property indicators and thresholds, and obtain the yarn mechanical quality evaluation results; The yarn appearance quality evaluation results and mechanical quality evaluation results are integrated to construct a multi-source quality data set. The Kalman filter algorithm is used to perform correlation analysis and integration on the multi-source quality data to obtain a comprehensive quality evaluation result. According to the yarn production process and the sequence of each process, the comprehensive quality evaluation results are arranged in chronological order to build a yarn quality traceability chain to achieve full-process tracking and management of yarn quality; When a yarn entanglement problem is detected, the time point when the problem occurred is traced through the quality traceability chain, and the machine learning algorithm is used to perform root cause analysis based on the quality data and process parameters at that time point to locate the key factors that lead to the yarn entanglement problem; According to the positioning results of the yarn entanglement problem, the process parameters of the corresponding process are optimized and adjusted, and the adjusted process parameters are verified and evaluated, and the optimization is continuously iterated until the yarn entanglement problem is eliminated to ensure that the yarn quality is stable and controllable.

8. A yarn anti-entanglement method according to claim 1, characterized in that: The yarn production whole process quality control system is established to integrate multi-source heterogeneous data such as yarn raw materials, processes, equipment, and quality; principal component analysis and neural network algorithms are used to explore the complex relationships between factors affecting yarn quality and form a yarn quality optimization decision-making plan; According to the optimization plan, production parameters are automatically adjusted to continuously improve yarn quality, production efficiency and economic benefits, including: Acquire multi-source heterogeneous data such as raw materials, processes, equipment and quality in the yarn production process, and convert them into structured data through data cleaning, conversion and integration; For the integrated structured data, the principal component analysis algorithm is used to extract the main influencing factors of yarn quality and reduce the data dimension; Based on the results of principal component analysis, a neural network model was constructed to deeply explore the complex nonlinear relationship between various influencing factors and yarn quality; Through the trained neural network model, the yarn quality under different production parameter combinations is predicted, and the optimal parameter combination is selected as the quality optimization solution; Convert quality optimization plans into control instructions that can be executed by production equipment, and adjust production parameters in real time through automated control systems; Continuously collect optimized production data, regularly update principal component analysis and neural network models, and form a closed-loop control for continuous optimization of yarn quality; Establish a visual platform for yarn quality control to monitor key quality indicators of each production link in real time and provide data support for management decisions.

Images