New material yarn quality detection system

Abstract

The invention discloses a new material yarn quality detection system, and relates to the technical field of new material yarn detection, the new material yarn quality detection system comprises a yarn quality detection platform, the yarn quality detection platform is in communication connection with a performance data acquisition module, a defect identification module, a yarn performance detection module, a comprehensive quality evaluation module and a visual display module, the modules are in electric signal connection; and the performance data acquisition module is used for acquiring physical and mechanical performance data of the new material yarn by using an intelligent sensing system. By integrating an intelligent sensing technology, a machine learning algorithm and multi-module cooperative work, high-precision and high-efficiency detection of the new material yarn is realized, appearance defects of the yarn are concerned in the detection process, the mechanical property and environmental adaptability of the yarn are deeply evaluated, and the detection accuracy is improved. The performance of the yarn under the mechanical performance and environmental conditions can be comprehensively analyzed, the use performance of the yarn can be deeply known, and the special requirements of different fields for the yarn performance are met.

Description

Technical Field

[0001] The present invention relates to the technical field of new material yarn detection, and particularly to a quality detection system for new material yarns. Background Art

[0002] With the continuous development of new material technologies, various new types of yarn materials have emerged, such as high-performance fibers, intelligent fibers, and environmentally friendly fibers. These new material yarns have unique properties and uses, posing higher requirements for quality detection. However, traditional quality detection methods are difficult to meet the detection needs of these new material yarns. Therefore, a more advanced and accurate quality detection system is required.

[0003] For example, a yarn quality detection system, method, and device with the Chinese patent publication number CN119147540A adjusts the shooting parameter information based on the yarn quality standard and external configuration information, and uses a high-speed camera corresponding to the shooting parameter information to collect the original image data of the yarn during the production process in real time, and processes the original image data to obtain the yarn feature information.

[0004] In the prior art, a variety of yarn feature information is detected through an image processing module, and the yarn defects are automatically classified and statistically analyzed, solving the problem of complex yarn analysis. However, due to the more complex structure and performance characteristics of new material yarns, and the need to evaluate multiple characteristics such as the high temperature resistance, ultraviolet resistance, and antibacterial properties of the yarn, the efficiency of defect identification and performance evaluation of new material yarns is greatly affected. Therefore, how to comprehensively analyze multiple data through an intelligent sensing system to comprehensively identify the defects and performance indicators of the yarn to improve the detection efficiency of new material yarns is the problem to be solved by the present invention. For this reason, a quality detection system for new material yarns is proposed herein. Summary of the Invention

[0005] The purpose of the present invention is to provide a quality detection system for new material yarns to solve the problems raised in the above background art.

[0006] To solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A quality detection system for new material yarns includes a yarn quality detection platform, which is communicatively connected to a performance data acquisition module, a defect identification module, a yarn performance detection module, a comprehensive quality evaluation module, and a visualization display module. Among them, the modules are electrically connected to each other;

[0008] The performance data acquisition module is used to collect the physical and mechanical performance data of the new material yarn by using an intelligent sensing system, and perform preprocessing and feature analysis to obtain a performance feature sequence;

[0009] The defect identification module is used to analyze the performance indicators in the performance feature sequence by using machine learning algorithms to identify defects on the surface of the new material yarn;

[0010] The yarn performance detection module is used to detect the mechanical properties and environmental adaptability of the new material yarn in combination with the performance characteristics of the performance feature sequence, and analyze the performance trends of the new material yarn in terms of mechanical properties and environmental adaptability;

[0011] The comprehensive quality assessment module is used to comprehensively analyze the defect identification and performance detection results, judge the quality grade of the new material yarn, form a complete yarn quality detection report, and provide comprehensive yarn quality information;

[0012] The visualization display module is used to display the detection results of the new material yarn in the form of charts, which is convenient for users to understand and view, improves the readability and understandability of the data, and is convenient for users to quickly master the quality status of the yarn.

[0013] A further improvement of the technical solution of the present invention is that the performance data acquisition module includes an intelligent sensor unit and a feature extraction unit;

[0014] Among them, the intelligent sensor unit is used to collect various performance data of the new material yarn through different deployed sensors, including yarn diameter, strength, elastic modulus, elongation, twist, tension, temperature, ultraviolet intensity, fiber morphology, and color change, and perform preprocessing operations such as cleaning, denoising, and normalization on the collected performance data;

[0015] The feature extraction unit is used to extract features related to yarn defects and performance indicators from the preprocessed performance data, and integrate them to obtain a performance feature sequence.

[0016] A further improvement of the technical solution of the present invention is that the intelligent sensor unit specifically includes:

[0017] According to the detection requirements and characteristics of the new material yarn, samples of the new material yarn to be detected are taken to obtain yarn samples, and the yarn samples are placed in a simulated environment. At the same time, a variety of sensors are deployed to collect the physical and mechanical performance data of the new material yarn samples. Among them, the sensors include a laser displacement sensor for measuring the yarn diameter, a tensile sensor for measuring the strength, a twist meter for measuring the twist, a tension sensor for measuring the tension, an infrared sensor for measuring the temperature, a ultraviolet sensor for measuring the ultraviolet intensity, and an industrial camera for observing the fiber morphology and color change. Then, according to the set sampling frequency, the diameter, strength, elastic modulus, elongation, twist, tension, temperature, ultraviolet intensity, fiber morphology images, and color change image data of the new material yarn are collected;

[0018] Preprocess the collected original performance data, including data cleaning, denoising, and normalization preprocessing operations;

[0019] Integrate the preprocessed performance data, align and merge the data collected by different sensors according to the time series, and then store it in the data warehouse for subsequent data analysis and mining.

[0020] A further improvement of the technical solution of the present invention lies in that: the feature extraction unit specifically includes:

[0021] Group and classify the preprocessed performance data. According to the physical meaning and detection objectives of the data, divide the performance data into different categories, namely mechanical property data, environmental adaptability data, and appearance feature data;

[0022] After completing the data grouping and classification, further divide different performance indicators according to the performance data categories of the yarn, including mechanical property indicators, environmental adaptability indicators, and appearance feature indicators;

[0023] Combined with the defect detection objectives of the new material yarn, determine the sub-features of each performance indicator, including the diameter change rate, strength volatility, elastic modulus, elongation rate, twist change rate, tension amplitude, temperature sensitive range, ultraviolet tolerance strength, and fiber morphology and color change rate. Among them, for the mechanical property indicators, its sub-features are strength volatility, twist change rate, tension amplitude, elastic modulus, and elongation rate; for the environmental adaptability indicators, its sub-features are temperature sensitive range and ultraviolet tolerance strength; for the appearance feature indicators, its sub-features are diameter change rate, fiber morphology, and color change rate;

[0024] According to the material characteristics of the new material yarn, set the allowable reference values of the sub-features of each performance indicator, and integrate the sub-features of each performance indicator and their allowable reference values to obtain a performance feature sequence.

[0025] A further improvement of the technical solution of the present invention lies in that: the defect identification module specifically includes:

[0026] Pre-collect a historical data set containing normal samples and defect samples of the new material yarn, and mark the appearance feature indicators of the new material yarn in the historical data set, including diameter, fiber morphology, and color;

[0027] Analyze the historical data set marked with appearance feature indicators, extract the sub-features of the appearance feature indicators including diameter change rate, fiber morphology, and color change rate, and integrate them to obtain a feature data set, and then divide the feature data set into a training set and a test set;

[0028] According to the identification requirements of surface defects of new material yarns, a neural network model is selected as the basic architecture of the surface defect identification model. The training set is input into the neural network model for model training. By adjusting the algorithm parameters and optimizing the model structure, the model can accurately identify the defects on the yarn surface. During the training process, the cross-validation method is adopted to evaluate the performance of the model to ensure the generalization ability and stability of the model. The trained model is evaluated and verified using the test set. The evaluation metrics include accuracy, precision, recall, and F1 score. Through the evaluation metrics, the performance of the model in defect identification and its performance on different categories are understood, and the parameters and structure of the model are adjusted to improve the performance of the model, thereby obtaining a trained surface defect identification model;

[0029] Deploy the surface defect identification model, input the performance feature sequence into the trained surface defect identification model to identify the surface defects of the new material yarn, determine whether there are defects on the surface of the new material yarn, and calculate the surface defect identification index by combining the allowable reference values of the sub-features of each appearance feature index, analyze the severity of the surface defects, and output the identification and analysis results;

[0030] The expression of the surface defect identification index is:

[0031]

[0032] In the formula, S is the surface defect identification index, F i is the actual value of the i-th sub-feature of the appearance feature index (diameter change rate, fiber morphology, and color change rate), B i is the allowable reference value of the i-th sub-feature of the appearance feature index, D i is the deviation value of the i-th sub-feature of the appearance feature index, that is, F i -B i , n is the total number of sub-features of the appearance feature index, and the value range of S is between 0 and 1.

[0033] A further improvement of the technical solution of the present invention is that the yarn performance detection module includes a mechanical property detection unit and an environmental adaptability detection unit;

[0034] Among them, the mechanical property detection unit is used to detect and analyze the yarn in combination with the mechanical property indexes of the new material yarn, evaluate the performance of the yarn under high stress conditions, and ensure the stability and reliability of the new material yarn in mechanical properties;

[0035] The environmental adaptability detection unit is used to analyze the changes in the temperature sensitive range and ultraviolet tolerance intensity in combination with the environmental adaptability indexes of the new material yarn, and evaluate the durability of the yarn.

[0036] A further improvement of the technical solution of the present invention lies in that: The mechanical property detection unit specifically includes:

[0037] Traverse the mechanical property indexes in the performance characteristic sequence, and extract the sub-characteristics of the mechanical property indexes including strength volatility, twist change rate, tension amplitude, elastic modulus, and elongation rate;

[0038] Compare each sub-characteristic of the mechanical property indexes of the new material yarn with the corresponding allowable reference value, calculate the deviation between each sub-characteristic of the mechanical property indexes and the allowable reference value, and evaluate the performance of the yarn under high stress conditions;

[0039] According to the results of the performance analysis, comprehensively evaluate the mechanical properties of the new material yarn, calculate the mechanical property trend index, evaluate the stability and reliability of the yarn in terms of mechanical properties, and determine whether it meets the design and use requirements;

[0040] The expression of the mechanical property trend index is:

[0041]

[0042] In the formula, M is the mechanical property trend index, F j is the actual value of the jth sub-characteristic of the mechanical property index (strength volatility, twist change rate, tension amplitude, elastic modulus, and elongation rate), B j is the allowable reference value of the jth sub-characteristic of the mechanical property index, m is the total number of sub-characteristics of the mechanical property index, and the value range of M is between 0 and 1.

[0043] A further improvement of the technical solution of the present invention lies in that: The environmental adaptability detection unit specifically includes:

[0044] Traverse the environmental adaptability index data of the new material yarn obtained in the simulated environment, and extract the sub-characteristics of the environmental adaptability index including the temperature sensitive range and the ultraviolet tolerance intensity;

[0045] Compare each sub-characteristic of the environmental adaptability index with its corresponding allowable reference value, and obtain the deviation between the actual value and the allowable reference value of the temperature sensitive range and the ultraviolet tolerance intensity;

[0046] Compare the change of the environmental adaptability index of the new material yarn in the simulated environment with the initial environmental adaptability index, calculate the environmental adaptability trend index, analyze the change trend of the environmental adaptability index of the new material yarn, and then evaluate the durability of the new material yarn;

[0047] The expression of the environmental adaptability trend index is:

[0048]

[0049] In the formula, E is the environmental adaptability trend index, Ts is the actual value of the temperature-sensitive range of the new material yarn in the simulated environment, T b is the allowable reference value of the temperature-sensitive range, U s is the actual value of the ultraviolet resistance intensity of the new material yarn in the simulated environment, U b is the allowable reference value of the ultraviolet resistance intensity, and the value range of E is between 0 and 1.

[0050] A further improvement of the technical solution of the present invention lies in that: the comprehensive quality evaluation module specifically includes:

[0051] Collect various types of data output by the defect identification module and the performance detection module, including defect identification results, mechanical property detection results, and environmental adaptability detection results, and organize the collected data to ensure the integrity and consistency of the data;

[0052] Assign weights to different types of detection results, determine the corresponding weights according to their influence on the yarn quality, and combine the surface defect identification index, mechanical property trend index, and environmental adaptability trend index to calculate the comprehensive yarn quality score;

[0053] According to the calculated comprehensive yarn quality score, determine the quality grade of the new material yarn, set different quality grades, including excellent quality grade, good quality grade, qualified quality grade, and unqualified quality grade, and determine the score range corresponding to each quality grade. Then, according to the calculated comprehensive yarn quality score, classify the new material yarn into the corresponding quality grade;

[0054] Integrate the defect identification, performance detection, and quality grade determination results to form a complete yarn quality inspection report, which includes defect identification results, performance detection results, comprehensive yarn quality score, and quality grade information.

[0055] A further improvement of the technical solution of the present invention lies in that: the expression of the comprehensive yarn quality score is:

[0056]

[0057] In the formula, Y is the comprehensive yarn quality score, S is the surface defect identification index, reflecting the severity of surface defects of the yarn, M is the mechanical property trend index, reflecting the stability and reliability of the yarn in mechanical properties, E is the environmental adaptability trend index, reflecting the durability of the yarn under different environmental conditions, B S is the reference value of the surface defect identification index, R M is the reference value of the mechanical property trend index, B Eis the baseline value of the environmental adaptability tendency index, w1, w2, and w3 are the weights of surface defects, mechanical properties, and environmental adaptability respectively, and w1 + w2 + w3 = 1. The value range of Y is between 0 and 1;

[0058] Multiple said quality grades correspond one by one to multiple said scoring ranges, and the corresponding relationship is as follows:

[0059] The scoring range of the excellent quality grade is: Y yz <Y ≤ 1;

[0060] The scoring range of the good quality grade is: Y lz <Y ≤ Y yz ;

[0061] The scoring range of the qualified quality grade is: Y hz <Y ≤ Y lz ;

[0062] The scoring range of the unqualified quality grade is: 0 < Y ≤ Y hz ;

[0063] Among them, Y is the comprehensive score of yarn quality, and Y yz is the lower threshold of the excellent quality grade and the upper threshold of the good quality grade, and Y lz is the lower threshold of the good quality grade and the upper threshold of the qualified quality grade, and Y hz is the lower threshold of the qualified quality grade and the upper threshold of the unqualified quality grade, and Y yz = 0.9, Y lz = 0.8, Y hz = 0.7.

[0064] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is:

[0065] 1. The present invention provides a new material yarn quality detection system. By integrating intelligent sensing technology, machine learning algorithms, and multi-module collaborative work, it realizes high-precision and high-efficiency detection of new material yarns. Moreover, the detection process not only focuses on the appearance defects of the yarns but also deeply evaluates their mechanical properties and environmental adaptability, and can comprehensively analyze the performance of the yarns under mechanical properties and environmental conditions, which helps to deeply understand the use performance of the yarns and meet the special requirements for yarn performance in different fields.

[0066] 2. The present invention provides a quality inspection system for new material yarns. Through comprehensive analysis of defect identification and performance detection results, it can automatically judge the quality grade of new material yarns and generate a complete yarn quality inspection report, which helps to quickly understand the quality status of the yarns, timely adjust the production process or usage plan. At the same time, the detailed data and analysis results in the quality inspection report provide a strong basis for the quality control and improvement of the yarns, contributing to the continuous improvement of the quality of new material yarns. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0068] Figure 1 It is a schematic diagram of the system function modules of the present invention;

[0069] Figure 2 It is a schematic diagram of the working process of the comprehensive quality assessment module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0071] Example 1, as Figure 1 、 Figure 2 shown, the present invention provides a quality inspection system for new material yarns, including a yarn quality inspection platform. The yarn quality inspection platform is communicatively connected to a performance data acquisition module, a defect identification module, a yarn performance detection module, a comprehensive quality assessment module, and a visualization display module. Among them, the modules are electrically connected to each other;

[0072] The performance data acquisition module is used to collect the physical and mechanical performance data of new material yarns using an intelligent sensing system, perform preprocessing and feature analysis, and obtain a performance feature sequence. The performance data acquisition module includes an intelligent sensor unit and a feature extraction unit;

[0073] Among them, the intelligent sensor unit is used to collect various performance data of the new material yarn through different deployed sensors, including yarn diameter, strength, elastic modulus, elongation, twist, tension, temperature, ultraviolet intensity, fiber morphology, and color change. It also performs preprocessing operations such as data cleaning, denoising, and normalization on the collected performance data to ensure data accuracy and consistency, improve data quality, and reduce errors. According to the detection requirements and characteristics of the new material yarn, samples of the new material yarn to be detected are taken to obtain yarn samples, and the yarn samples are placed in a simulated environment. At the same time, multiple sensors are deployed to collect physical and mechanical performance data of the new material yarn samples. Among them, the sensors include a laser displacement sensor for measuring yarn diameter, a tensile sensor for measuring strength, a twist meter for measuring twist, a tension sensor for measuring tension, an infrared sensor for measuring temperature, a ultraviolet sensor for measuring ultraviolet intensity, and an industrial camera for observing fiber morphology and color change. Furthermore, according to the set sampling frequency, data on the diameter, strength, elastic modulus, elongation, twist, tension, temperature, ultraviolet intensity, fiber morphology images, and color change images of the new material yarn are collected. Preprocessing is performed on the collected original performance data, including data cleaning, denoising, and normalization preprocessing operations. Among them, outliers, duplicate values, or invalid data in the collected data are removed through data cleaning, and a filtering algorithm is used to denoise the collected signals to improve data accuracy. Data with different dimensions and value ranges are converted into a unified scale for subsequent data analysis and processing. The preprocessed performance data is integrated, and the data collected by different sensors is aligned and merged according to the time series, and then stored in the data warehouse for subsequent data analysis and mining;

[0074] A feature extraction unit is used to extract features related to yarn defects and performance indicators from the preprocessed performance data, and integrate them to obtain a performance feature sequence. The preprocessed performance data is grouped and classified. According to the physical meaning and detection objectives of the data, the performance data is divided into different categories, namely mechanical performance data, environmental adaptability data, and appearance feature data. After completing the data grouping and classification, according to the performance data category of the yarn, different performance indicators are further divided, including mechanical performance indicators, environmental adaptability indicators, and appearance feature indicators. Combining the defect detection objectives of the new material yarn, the sub-features of each performance indicator are determined, including the diameter change rate, strength volatility, elastic modulus, elongation rate, twist change rate, tension amplitude, temperature sensitive range, ultraviolet tolerance strength, and fiber morphology and color change rate. Among them, for the mechanical performance indicators, the sub-features are strength volatility, twist change rate, tension amplitude, elastic modulus, and elongation rate; for the environmental adaptability indicators, the sub-features are temperature sensitive range and ultraviolet tolerance strength; for the appearance feature indicators, the sub-features are diameter change rate, fiber morphology, and color change rate. According to the material characteristics of the new material yarn, the allowable reference values of the sub-features of each performance indicator are set, and the sub-features of each performance indicator and their allowable reference values are integrated to obtain a performance feature sequence;

[0075] A defect recognition module is used to analyze the performance metrics in the performance feature sequence using machine learning algorithms to identify defects on the surface of new material yarns. It pre-collects a historical dataset containing normal samples and defect samples of new material yarns, and marks the appearance feature metrics of the new material yarns in the historical dataset, including diameter, fiber morphology, and color. It analyzes the historical dataset with marked appearance feature metrics, extracts sub-features of appearance feature metrics including diameter change rate, fiber morphology, and color change rate, and integrates them to obtain a feature dataset. Then, the feature dataset is divided into a training set and a test set. According to the identification requirements of surface defects of new material yarns, a neural network model is selected as the basic architecture of the surface defect recognition model. The training set is input into the neural network model for model training. By adjusting algorithm parameters and optimizing the model structure, the model can accurately identify defects on the yarn surface. During the training process, a cross-validation method is used to evaluate the performance of the model to ensure the generalization ability and stability of the model. The test set is used to evaluate and verify the trained model. The evaluation metrics include accuracy, precision, recall, and F1 score. Through the evaluation metrics, understand the performance of the model in defect identification and its performance on different categories, and adjust the parameters and structure of the model to improve the performance of the model, and then obtain a trained surface defect recognition model. Deploy the surface defect recognition model, input the performance feature sequence into the trained surface defect recognition model to identify surface defects of new material yarns, determine whether there are defects on the surface of new material yarns, and calculate the surface defect recognition index in combination with the allowable benchmark values of each sub-feature of appearance feature metrics, analyze the severity of surface defects, and output the recognition and analysis results;

[0076] The expression of the surface defect recognition index is:

[0077]

[0078] In the formula, S is the surface defect recognition index, F i is the actual value of the i-th sub-feature of appearance feature metrics (diameter change rate, fiber morphology, and color change rate), B i is the allowable benchmark value of the i-th sub-feature of appearance feature metrics, D i is the deviation value of the i-th sub-feature of appearance feature metrics, that is, F i -B i , n is the total number of sub-features of appearance feature metrics, and the value range of S is between 0 and 1. When F i is close to B i , D i is smaller, and the S value is larger, indicating that the surface defect is lighter. When F i is far from B i , D i is larger, and the S value is smaller, indicating that the surface defect is more serious;

[0079] A yarn performance detection module, which is used to detect the mechanical properties and environmental adaptability of new material yarns by combining the performance characteristics of the performance characteristic sequence, and analyze the performance trends of new material yarns in terms of mechanical properties and environmental adaptability;

[0080] A comprehensive quality assessment module, which is used to comprehensively analyze the defect identification and performance detection results, judge the quality grade of the new material yarn, form a complete yarn quality inspection report, and provide comprehensive yarn quality information;

[0081] A visualization display module, which is used to display the detection results of the new material yarn in the form of charts, facilitate users to understand and view, improve the readability and understandability of the data, and facilitate users to quickly grasp the quality status of the yarn.

[0082] Example 2, as Figure 1 、 Figure 2 shown, on the basis of Example 1, the present invention provides a technical solution: Preferably, the yarn performance detection module includes a mechanical property detection unit and an environmental adaptability detection unit;

[0083] Among them, the mechanical property detection unit is used to detect and analyze the yarn by combining the mechanical property indexes of the new material yarn, evaluate the performance of the yarn under high stress conditions, ensure the stability and reliability of the new material yarn in terms of mechanical properties, traverse the mechanical property indexes in the performance characteristic sequence, extract the mechanical property index sub-characteristics including strength volatility, twist change rate, tension amplitude, elastic modulus and elongation rate, compare each mechanical property index sub-characteristic of the new material yarn with the corresponding allowable reference value, calculate the deviation between each mechanical property index sub-characteristic and the allowable reference value, evaluate the performance of the yarn under high stress conditions, comprehensively evaluate the mechanical properties of the new material yarn according to the results of the performance analysis, calculate the mechanical property trend index, evaluate the stability and reliability of the yarn in terms of mechanical properties, and judge whether it meets the design and use requirements;

[0084] The expression of the mechanical property trend index is:

[0085]

[0086] In the formula, M is the mechanical property trend index, F j is the actual value of the jth mechanical property index sub-characteristic (strength volatility, twist change rate, tension amplitude, elastic modulus and elongation rate), B j is the allowable reference value of the jth mechanical property index sub-characteristic, m is the total number of mechanical property index sub-characteristics, the value range of M is between 0 and 1, when F j is close to B j , the value of M is larger, indicating that the mechanical property trend is good, and the yarn has higher stability and reliability in terms of mechanical properties. When Fj Away from B j When it is away from B, the value of M is small, indicating that the mechanical properties tend to be poor, and the yarn may be unstable or unreliable in mechanical properties;

[0087] The environmental adaptability detection unit is used to analyze the changes in the temperature-sensitive range and ultraviolet tolerance intensity in combination with the environmental adaptability index of the new material yarn, evaluate the durability of the yarn, ensure that the new material yarn can maintain stable performance for a long time under different environmental conditions, meet special application requirements, traverse the environmental adaptability index data of the new material yarn obtained in the simulated environment, extract the sub-characteristics of the environmental adaptability index including the temperature-sensitive range and ultraviolet tolerance intensity, compare each sub-characteristic of the environmental adaptability index with its corresponding allowable reference value, obtain the deviation between the actual value and the allowable reference value of the temperature-sensitive range and ultraviolet tolerance intensity, compare the changes in the environmental adaptability index of the new material yarn in the simulated environment with the initial environmental adaptability index, calculate the environmental adaptability trend index, analyze the change trend of the environmental adaptability index of the new material yarn, and then evaluate the durability of the new material yarn;

[0088] The expression of the environmental adaptability trend index is:

[0089]

[0090] In the formula, E is the environmental adaptability trend index, T s is the actual value of the temperature-sensitive range of the new material yarn in the simulated environment, T b is the allowable reference value of the temperature-sensitive range, U s is the actual value of the ultraviolet tolerance intensity of the new material yarn in the simulated environment, U b is the allowable reference value of the ultraviolet tolerance intensity, and the value range of E is between 0 and 1. When T s is close to T b and U s is close to U b , the value of E is close to 1, indicating that the change in the environmental adaptability index of the new material yarn in the simulated environment is small and the durability is good. When T s or U s deviates from T b or U b is large, the value of E is close to 0, indicating that the change in the environmental adaptability index of the new material yarn in the simulated environment is large and the durability is poor;

[0091] The comprehensive quality evaluation module specifically includes:

[0092] Collect various data output by the defect identification module and the performance detection module, including defect identification results, mechanical property detection results, and environmental adaptability detection results, and organize the collected data to ensure data integrity and consistency. Assign weights to different types of detection results, determine the corresponding weights according to their impact on yarn quality, and combine the surface defect identification index, mechanical property trend index, and environmental adaptability trend index to calculate the comprehensive yarn quality score. Determine the quality grade of the new material yarn according to the calculated comprehensive yarn quality score. Set different quality grades, including excellent quality grade, good quality grade, qualified quality grade, and unqualified quality grade, and determine the score range corresponding to each quality grade. Then, divide the new material yarn into the corresponding quality grades according to the calculated comprehensive yarn quality score. Integrate the defect identification, performance detection, and quality grade determination results to form a complete yarn quality inspection report. The yarn quality inspection report includes defect identification results, performance detection results, comprehensive yarn quality score, and quality grade information;

[0093] The expression for the comprehensive yarn quality score is:

[0094]

[0095] In the formula, Y is the comprehensive yarn quality score, S is the surface defect identification index, reflecting the severity of surface defects of the yarn, M is the mechanical property trend index, reflecting the stability and reliability of the yarn in mechanical properties, E is the environmental adaptability trend index, reflecting the durability of the yarn under different environmental conditions, B S is the reference value of the surface defect identification index, B M is the reference value of the mechanical property trend index, B E is the reference value of the environmental adaptability trend index, w1, w2, and w3 are the weights of surface defects, mechanical properties, and environmental adaptability respectively, and w1 + w2 + w3 = 1. The value range of Y is between 0 and 1. When S, M, and E are close to their respective reference values B S 、B M and B E ,Y has a larger value, indicating better yarn quality. When S, M, or E is far from their respective reference values, Y has a smaller value, indicating poorer yarn quality;

[0096] Multiple quality grades correspond one-to-one with multiple score ranges, and the corresponding relationship is as follows:

[0097] The score range for the excellent quality grade is: Y yz <Y ≤ 1;

[0098] The score range for the good quality grade is: Y lz <Y ≤ Y yz ;

[0099] The scoring range for the qualified quality level is: Y hz <Y ≤ Y lz ;

[0100] The scoring range for the unqualified quality level is: 0 < Y ≤ Y hz ;

[0101] Wherein, Y is the comprehensive yarn quality score, Y yz is the lower threshold of the excellent quality level and the upper threshold of the good quality level, Y lz is the lower threshold of the good quality level and the upper threshold of the qualified quality level, Y hz is the lower threshold of the qualified quality level and the upper threshold of the unqualified quality level, Y yz = 0.9, Y lz = 0.8, Y hz = 0.7.

[0102] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

Claims

1. A new material yarn quality detection system, including a yarn quality detection platform, is characterized in that: The yarn quality detection platform is communicatively connected to a performance data acquisition module, a defect identification module, a yarn performance detection module, a comprehensive quality assessment module, and a visualization display module. Among them, the modules are electrically connected to each other; The performance data acquisition module is used to collect the physical and mechanical performance data of the new material yarn by using an intelligent sensing system, and perform preprocessing and feature analysis to obtain a performance feature sequence; The defect identification module is used to analyze the performance indicators in the performance feature sequence by using machine learning algorithms to identify the defects on the surface of the new material yarn; The yarn performance detection module is used to detect the mechanical performance and environmental adaptability of the new material yarn in combination with the performance features of the performance feature sequence, and analyze the performance trend of the new material yarn in terms of mechanical performance and environmental adaptability; The comprehensive quality assessment module is used to comprehensively analyze the defect identification and performance detection results, judge the quality grade of the new material yarn, and form a yarn quality detection report; The visualization display module is used to display the detection results of the new material yarn in the form of charts.

2. The quality inspection system for a new material yarn according to claim 1, characterized in that: The performance data acquisition module includes an intelligent sensor unit and a feature extraction unit; Among them, the intelligent sensor unit is used to collect various performance data of the new material yarn through different deployed sensors, and perform preprocessing operations on the collected performance data; The feature extraction unit is used to extract the features related to yarn defects and performance indicators from the preprocessed performance data, and integrate them to obtain a performance feature sequence.

3. The quality inspection system for a new material yarn according to claim 2, characterized in that: The intelligent sensor unit specifically includes: According to the detection requirements and characteristics of the new material yarn, samples of the new material yarn to be detected are taken to obtain yarn samples, and the yarn samples are placed in a simulated environment. At the same time, a variety of sensors are deployed to collect the physical and mechanical performance data of the new material yarn samples. Among them, the sensors include a laser displacement sensor for measuring the yarn diameter, a tensile sensor for measuring the strength, a twist meter for measuring the twist, a tension sensor for measuring the tension, an infrared sensor for measuring the temperature, a ultraviolet sensor for measuring the ultraviolet intensity, and an industrial camera for observing the fiber morphology and color changes. Then, according to the set sampling frequency, the diameter, strength, elastic modulus, elongation, twist, tension, temperature, ultraviolet intensity, fiber morphology image, and color change image data of the new material yarn are collected; Perform preprocessing on the collected original performance data, including preprocessing operations such as data cleaning, denoising, and normalization; Integrate the preprocessed performance data, align and merge the data collected by different sensors according to the time series, and then store them in the data warehouse.

4. The quality inspection system for a new material yarn according to claim 3, characterized in that: The feature extraction unit specifically includes: Group and classify the preprocessed performance data. According to the physical meaning and detection objectives of the data, the performance data is divided into different categories, namely mechanical performance data, environmental adaptability data, and appearance feature data; After completing the data grouping and classification, according to the performance data category of the yarn, further divide different performance indicators, including mechanical performance indicators, environmental adaptability indicators, and appearance feature indicators; Combined with the defect detection objectives of the new material yarn, determine the sub-features of each performance index, including the diameter change rate, strength volatility, elastic modulus, elongation rate, twist change rate, tension amplitude, temperature sensitive range, ultraviolet resistance strength, and fiber morphology and color change rate. Among them, for the mechanical property index, its sub-features are strength volatility, twist change rate, tension amplitude, elastic modulus, and elongation rate; for the environmental adaptability index, its sub-features are temperature sensitive range and ultraviolet resistance strength; for the appearance feature index, its sub-features are diameter change rate, fiber morphology, and color change rate; According to the material characteristics of the new material yarn, set the allowable reference values of the sub-features of each performance index, and integrate the sub-features of each performance index and their allowable reference values to obtain a performance feature sequence.

5. A new material yarn quality detection system according to claim 4, characterized in that: The defect identification module specifically includes: Pre-collect a historical data set containing normal samples and defect samples of the new material yarn, and mark the appearance feature indexes of the new material yarn in the historical data set, including diameter, fiber morphology, and color; Analyze the historical data set with marked appearance feature indexes, extract the sub-features of the appearance feature indexes including diameter change rate, fiber morphology, and color change rate, and integrate them to obtain a feature data set. Then divide the feature data set into a training set and a test set; According to the identification requirements of the surface defects of the new material yarn, select a neural network model as the basic architecture of the surface defect identification model, input the training set into the neural network model for model training, use the test set to evaluate and verify the trained model, and adjust the parameters and structure of the model to obtain a trained surface defect identification model; Deploy the surface defect identification model, input the performance feature sequence into the trained surface defect identification model to identify the surface defects of the new material yarn, judge whether there are defects on the surface of the new material yarn, calculate the surface defect identification index in combination with the allowable reference values of the sub-features of each appearance feature index, analyze the severity of the surface defects, and output the identification and analysis results; The expression of the surface defect identification index is: Wherein, S is the surface defect recognition index, F i is the actual value of the i-th sub-feature of the appearance feature index, B i is the allowable reference value of the i-th sub-feature of the appearance feature index, D i is the deviation value of the i-th sub-feature of the appearance feature index, that is, F i -B i , n is the total number of sub-features of the appearance feature index, and the value range of S is between 0 and 1.

6. The quality inspection system for a new material yarn according to claim 1, wherein: The yarn performance detection module includes a mechanical property detection unit and an environmental adaptability detection unit; Among them, the mechanical property detection unit is used to detect and analyze the yarn in combination with the mechanical property indexes of the new material yarn, and evaluate the performance of the yarn under high stress conditions; The environmental adaptability detection unit is used to analyze the changes in the temperature sensitive range and ultraviolet resistance strength in combination with the environmental adaptability indexes of the new material yarn, and evaluate the durability of the yarn.

7. The quality inspection system for a new material yarn according to claim 6, characterized in that: The mechanical property detection unit specifically includes: Traverse the mechanical property indexes in the performance feature sequence, and extract the sub-features of the mechanical property indexes including strength volatility, twist change rate, tension amplitude, elastic modulus, and elongation rate; Compare the sub-features of each mechanical property index of the new material yarn with the corresponding allowable reference values, calculate the deviation between the sub-features of each mechanical property index and the allowable reference values, and evaluate the performance of the yarn under high stress conditions; Based on the results of performance analysis, comprehensively evaluate the mechanical properties of the new material yarn, calculate the mechanical property trend index, evaluate the stability and reliability of the yarn in terms of mechanical properties, and determine whether it meets the design and usage requirements; The expression of the mechanical property trend index is: Where M is the mechanical property tendency index, F j is the actual value of the j-th sub-feature of the mechanical property index, B j is the allowable reference value of the j-th sub-feature of the mechanical property index, m is the total number of sub-features of the mechanical property index, and the value range of M is between 0 and 1.

8. The quality inspection system for a new material yarn according to claim 6, characterized in that: The environmental adaptability detection unit specifically includes: Traverse the environmental adaptability index data of the new material yarn obtained in the simulated environment, and extract the sub-features of the environmental adaptability index including the temperature sensitive range and the ultraviolet tolerance intensity; Compare each sub-feature of the environmental adaptability index with its corresponding allowable reference value to obtain the deviation between the actual value and the allowable reference value of the temperature sensitive range and the ultraviolet tolerance intensity; Compare the change of the environmental adaptability index of the new material yarn in the simulated environment with the initial environmental adaptability index, calculate the environmental adaptability trend index, analyze the change trend of the environmental adaptability index of the new material yarn, and then evaluate the durability of the new material yarn; The expression of the environmental adaptability trend index is: Where E is the environmental adaptability tendency index, T s is the actual value of the temperature-sensitive range of the new material yarn in the simulated environment, T b is the allowable reference value of the temperature-sensitive range, U s is the actual value of the ultraviolet tolerance intensity of the new material yarn in the simulated environment, U b is the allowable reference value of the ultraviolet tolerance intensity, and the value range of E is between 0 and 1.

9. A quality inspection system for a new material yarn, according to claim 8, characterized in that: The comprehensive quality evaluation module specifically includes: Collect various data output by the defect identification module and the performance detection module, including defect identification results, mechanical property detection results and environmental adaptability detection results, and organize the collected data; Assign weights to different types of detection results, determine the corresponding weights according to their influence on the yarn quality, and combine the surface defect identification index, the mechanical property trend index and the environmental adaptability trend index to calculate the comprehensive yarn quality score; Based on the calculated comprehensive yarn quality score, determine the quality grade of the new material yarn, set different quality grades, including excellent quality grade, good quality grade, qualified quality grade and unqualified quality grade, and determine the score range corresponding to each quality grade. Then, according to the calculated comprehensive yarn quality score, classify the new material yarn into the corresponding quality grade; Integrate the defect identification, performance detection and quality grade determination results to form a complete yarn quality inspection report, which includes defect identification results, performance detection results, comprehensive yarn quality score and quality grade information.

10. A new material yarn quality detection system according to claim 9, characterized in that: The expression of the comprehensive yarn quality score is: Wherein, Y is the comprehensive score of yarn quality, S is the surface defect recognition index, M is the mechanical property trend index, E is the environmental adaptability trend index, B S is the reference value of the surface defect recognition index, B M is the reference value of the mechanical property trend index, B E is the reference value of the environmental adaptability trend index, w1, w2, and w3 are the weights of surface defects, mechanical properties, and environmental adaptability respectively, and w1 + w2 + w3 = 1, and the value range of Y is between 0 and 1; Multiple said quality grades correspond one by one to multiple said score ranges, and the corresponding relationship is as follows: The scoring range for the high-quality level is: Y yz <Y ≤ 1; The scoring range for the good quality level is: Y lz <Y ≤ Y yz ; The scoring range of the qualified quality level is: Y hz <Y ≤ Y lz ; The scoring range of the unqualified quality level is: 0 < Y ≤ Y hz ; Among them, Y is the comprehensive score of yarn quality, Y yz is the lower threshold of the excellent quality level and the upper threshold of the good quality level, Y lz is the lower threshold of the good quality level and the upper threshold of the qualified quality level, Y hz is the lower threshold of the qualified quality level and the upper threshold of the unqualified quality level, Y yz = 0.9, Y lz = 0.8, Y hz = 0.7.

Images