Yarn twist measuring method and yarn twist measuring system

Abstract

The invention belongs to the technical field of yarn twist measurement, and discloses a yarn twist measurement method and a yarn twist measurement system. The system comprises a feature data processing module, a quality prediction value generation module, a prediction grading early warning module, an environment compensation mechanism module, a self-adaptive parameter adjustment module, a yarn self-calibration module and a user visualization module, a feature data set is analyzed to obtain a yarn quality prediction value, the yarn quality prediction value is analyzed to obtain a yarn quality prediction result, and the yarn quality prediction result is obtained. The method comprises the steps of obtaining a yarn quality decision report, processing the yarn quality decision report, obtaining an environment optimization compensation report, analyzing material type data, obtaining measurement matching parameters, processing a yarn quality predicted value based on a yarn quality standard value, and obtaining a yarn calibration report. The method has the remarkable advantages of being high in yarn twist measurement and prediction accuracy, good in working assisting effect of workers and large in influence factor feedback adjustment effect.

Description

Technical Field

[0001] This invention relates to the field of yarn twist measurement technology, and more specifically, to a yarn twist measurement method and a yarn twist measurement system. Background Technology

[0002] Yarn twist refers to the physical and mechanical properties of yarn, such as strength, elasticity, elongation, luster, and hand feel. Twisting is achieved by altering the fiber structure of cotton yarn. Essentially, it involves creating a relative angular displacement between the cross-sections of the cotton yarn, causing the originally straight and parallel fibers to tilt relative to the yarn axis, thus changing the yarn structure. During twisting, the sliver gradually narrows in width, folds over on both sides, and rolls into the center of the yarn, forming a twisting triangle. Within this triangle, the width and cross-sectional area of ​​the sliver change, transforming from a flat strip into a cylindrical yarn. With the rapid economic development and rising living standards in my country in recent years, yarn, as a crucial raw material for clothing, has received significant attention. The twist of the yarn directly determines the comfort and practicality of clothing.

[0003] Patent application CN107192712A discloses a method and system for measuring yarn twist. By using a software analysis device to analyze the image to be measured, the system obtains analytical data, which is then transmitted to a computing device. The computing device calculates the yarn twist in the fabric to be measured. Compared with the prior art, the provided yarn twist measurement system avoids damage to the fabric to be measured during the measurement process and can quickly and accurately measure its yarn twist, thereby further improving its practicality.

[0004] However, while the aforementioned yarn twist measurement method and system reduce the measurement costs associated with traditional methods that require damaging the fabric, the system still necessitates measuring the already twisted raw material. If the measurement results are unsatisfactory, rework and detwisting are required. Therefore, accurately predicting the quality and strength of the twisted yarn would significantly reduce rework and greatly improve enterprise efficiency. Furthermore, yarn twist is affected by factors such as temperature, humidity, and vibration in the processing environment. These environmental factors are dynamic and prone to low measurement accuracy. Moreover, existing systems struggle to adjust measurement parameters according to the yarn material type, leading to poor accuracy in basic parameter acquisition and further impacting measurement accuracy. Additionally, manual calibration of yarn quality not only significantly increases operating costs but also results in considerable fluctuations in accuracy.

[0005] In view of this, the present invention proposes a yarn twist measurement method and a yarn twist measurement system to solve the above problems. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution, including: The yarn data acquisition module is used to acquire yarn datasets, which include yarn diameter data, material type data, and twist coefficient data. The environmental data acquisition module is used to collect environmental datasets, which include ambient temperature data, ambient humidity data, and vibration intensity data. The feature data processing module is used to preprocess the yarn dataset and the environment dataset to obtain the feature dataset; Furthermore, methods for preprocessing the yarn dataset and environment dataset include: Q1. Data cleaning and normalization were performed on the yarn dataset and the environment dataset using outlier removal and normalization formulas. Q2, Twist feature extraction is performed using yarn diameter data and twist coefficient data. The specific calculation formula for twist feature extraction is as follows: ; Obtain twist characteristic data ,in, This is the yarn diameter data. This refers to the twist coefficient data; Q3. Stable features are extracted from ambient temperature and humidity data. The specific calculation formula for stable feature extraction is as follows: ; Obtain stable feature data ,in, For ambient temperature data, This refers to ambient humidity data. Q4. Pack twist characteristic data, stability characteristic data and vibration intensity data to obtain the characteristic dataset; The quality prediction value generation module is used to analyze the feature dataset to obtain the yarn quality prediction value; Furthermore, the steps for analyzing the feature dataset include: Step 1: Obtain a set of historical feature datasets stored in the database, compare them with the current time based on the timestamp, and group and label them in ascending order of time. The labeling results are L1, L2, L3, ..., Ln. Use the labeling results as the sample set. Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and build a yarn quality prediction model based on the sample set. Step 3: Based on the historical feature dataset, use a multi-layer heterogeneous sub-model to calculate and obtain the initial yarn quality prediction value set. The specific formula set for the calculation is as follows: ; Obtain the initial yarn quality prediction set ,in, , and These are the predicted values ​​for the first yarn quality, the second yarn quality, and the third yarn quality, respectively. For the Sigmoid function, For the size of the historical window data, The time decay coefficient, , and For nonlinear activation parameters, It is the hyperbolic tangent function. and For characteristic index parameters, Features The first difference, For Fourier transform, For frequency variables Integral infinitesimal element; Step 4: Calculate the predicted yarn quality value based on the initial yarn quality prediction set from Step 3. The specific formula for calculation is as follows: ; Obtain the predicted yarn quality value ,in, It is a weighted average function. For the first The model weighting factors for the yarn quality prediction values ​​in the initial set of yarn quality prediction values. A collection of historical feature datasets, Environmental sensitivity coefficient, For partial derivatives, For characteristic index parameters; Step 5: Based on the weighted average function in Step 4, perform... The value is re-verified when When, the output value is ;when When, the output value is Return and substitute into step four, where It is a median function; Step 6: Output the predicted yarn quality value to the prediction grading and early warning module; The prediction and grading early warning module is used to analyze the predicted values ​​of yarn quality and obtain a yarn quality decision report; Furthermore, methods for analyzing the predicted yarn quality include: Subtract the standard yarn quality value from the predicted yarn quality value, divide by the standard yarn quality value, and then multiply by 100% to obtain the quality deviation rate. A normal report is generated when the quality deviation rate is greater than or equal to -5%; a warning report is generated when the quality deviation rate is less than -5% but greater than or equal to -10%; and an alarm report is generated when the quality deviation rate is less than -10%. A normal report includes a statement indicating that the predicted yarn quality is normal, and requesting staff to continue monitoring production. The warning report includes a description of predicted low yarn quality, requesting staff to check and verify the production environment; The alarm report includes a description of predicted poor yarn quality, instructing staff to immediately stop the equipment and calibrate the yarn raw materials; Package normal reports, warning reports, and alarm reports to obtain a yarn quality decision report; The environmental compensation mechanism module is used to process the yarn quality decision report and obtain an environmental optimization compensation report. Furthermore, the methods for processing yarn quality decision reports include: When the yarn quality decision report is a warning report, adjust the ambient temperature data. The specific calculation formula for the adjustment is as follows: ; New ambient temperature data obtained ,in, This is an empirical coefficient. This refers to the quality deviation rate. Divide the ambient humidity data by 2 to obtain the new ambient humidity data; By packaging the new ambient temperature data and the new ambient humidity data, an environmental optimization and compensation report is obtained. The adaptive parameter adjustment module is used to analyze material type data to obtain measurement matching parameters; Furthermore, methods for analyzing material type data include: The material type data is tested, and measurement matching parameters are matched to the material type data through the parameter rule table; The specific rules of the parameter rule table are as follows: Cotton = (La=500, Lb=100), Polyester = (La=700, Lb=150), Nylon = (La=600, Lb=120), where La is the light source intensity and Lb is the sampling frequency; Input material type data, and output measurement matching parameters La and Lb; The yarn self-calibration module is used to process the predicted yarn quality value based on the standard yarn quality value to obtain a yarn calibration report; Furthermore, the methods for processing the predicted yarn quality value based on the standard yarn quality value include: Actual yarn quality values ​​were collected by randomly sampling sensors. The strength qualification value is obtained by calculating the absolute value of the difference between the actual value of yarn quality and the standard value of yarn quality; When the strength qualification value is greater than 0.5, a rework calibration report is generated; The rework calibration report includes the batch number of the yarn and states that the yarn strength of that batch is substandard. The prediction tolerance is obtained by subtracting the absolute value of the actual yarn quality from the predicted yarn quality value. When the prediction tolerance is less than or equal to the tolerance threshold, a prediction qualification report is generated; When the prediction tolerance exceeds the tolerance threshold, a prediction failure report is generated. The forecast report includes a statement indicating that the current yarn quality forecasting model has high accuracy. The report of unqualified prediction includes an explanation that the current yarn quality prediction model has low prediction accuracy, and asks staff to check whether all sensors are working properly. The yarn calibration report is obtained by packaging rework calibration reports, predicted pass reports, and predicted fail reports; The user visualization module is used to analyze yarn quality decision reports, implement corresponding measures based on the analysis results, display environmental optimization compensation reports and yarn calibration reports, and store the overall dataset. Furthermore, the methods for analyzing the yarn quality decision report and implementing corresponding measures based on the analysis results include: Decision-making report for identifying yarn quality; When the yarn quality decision report is a normal report, the normal report is displayed on the visualization panel and a green indicator light is constantly lit by the sound and light device. When the yarn quality decision report is a warning report, the warning report is displayed through the visualization panel, and a yellow light flashes and a buzzer is activated once every thirty seconds via the audio-visual equipment. When the yarn quality decision report is an alarm report, the alarm report is displayed on the visualization panel, and a red light flashes and a buzzer is continuously activated by the sound and light device. The overall dataset includes yarn dataset, environment dataset, feature dataset, yarn quality prediction values, yarn quality decision report, environmental optimization compensation report, measurement matching parameters, and yarn calibration report; Further, S1: Collect yarn dataset, which includes yarn diameter data, material type data, and twist coefficient data; S2: Collect environmental datasets, which include ambient temperature data, ambient humidity data, and vibration intensity data; S3: Preprocess the yarn dataset and environment dataset to obtain the feature dataset; S4: Analyze the feature dataset to obtain the predicted yarn quality value; S5: Analyze the predicted yarn quality values ​​to obtain a yarn quality decision report; S6: Process the yarn quality decision report to obtain an environmental optimization compensation report; S7: Analyze the material type data to obtain the measurement matching parameters; S8: Process the predicted yarn quality value based on the standard yarn quality value to obtain a yarn calibration report; S9: Analyze the yarn quality decision report, implement corresponding measures based on the analysis results, display the environmental optimization compensation report and yarn calibration report, and store the overall dataset.

[0007] The technical effects and advantages of the yarn twist measurement method and system of this invention are as follows: This invention collects a yarn dataset (including yarn diameter, material type, and twist coefficient data) and an environmental dataset (including ambient temperature, humidity, and vibration intensity data). Both datasets are preprocessed to obtain a feature dataset. This feature dataset is then analyzed to obtain a predicted yarn quality value. Further analysis of the predicted yarn quality value yields a yarn quality decision report. This decision report is then processed to generate an environmental optimization compensation report. Material type data is analyzed to obtain measurement matching parameters. Based on standard yarn quality values, the predicted yarn quality value is processed to generate a yarn calibration report. The decision report is analyzed, and corresponding measures are implemented based on the analysis results. The environmental optimization compensation report and yarn calibration report are displayed, and the overall dataset is stored. This allows the system to adapt to dynamic environmental conditions. This invention accurately predicts yarn twist under the influence of dynamic factors, significantly reducing the probability of yarn rework and effectively improving enterprise efficiency. Furthermore, by analyzing yarn quality, it reverse-calculates the environmental data required for yarn quality improvement, further reducing the risk of rework due to insufficient twist. Moreover, by differentiating various material types and applying matching measurement parameters to each, it greatly improves measurement accuracy, avoiding inaccurate yarn twist predictions caused by insufficient sensor data. Simultaneously, by comparing the actual twist quality of finished yarns, it assists workers in quickly calibrating the yarn and promptly adjusting related issues, further ensuring enterprise efficiency. Overall, this invention has significant advantages such as high accuracy in yarn twist measurement and prediction, excellent assistance to workers, and a strong feedback mechanism to adjust influencing factors. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of a yarn twist measurement system according to the present invention; Figure 2 This is a schematic diagram of a yarn twist measurement method according to the present invention. Detailed Implementation

[0009] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0010] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0011] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0012] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0013] In practice, the server-side equipment deployed by the yarn twist measurement system may consist of one or more devices. The aforementioned yarn twist measurement system can be implemented as a business instance, a virtual machine, or a hardware device. For example, the yarn twist measurement system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the yarn twist measurement system can be understood as software deployed on a cloud node, used to provide yarn twist measurement services to various user terminals. Alternatively, the yarn twist measurement system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Or, the yarn twist measurement system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide yarn twist measurement services to various user terminals.

[0014] In terms of implementation, the yarn twist measurement system and the user terminal are mutually compatible. That is, if the yarn twist measurement system is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the yarn twist measurement system is implemented as a website, then the user terminal is implemented as a webpage; or if the yarn twist measurement system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0015] like Figure 1 The figure shown is a system architecture diagram of a yarn twist measurement system provided in an embodiment of the present invention.

[0016] The yarn twist measurement system of this invention can be set up in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed into a website. Depending on the functions implemented, the yarn twist measurement system may include a yarn data acquisition module, an environmental data acquisition module, a feature data processing module, a quality prediction value generation module, a prediction grading and early warning module, an environmental compensation mechanism module, an adaptive parameter adjustment module, a yarn self-calibration module, and a user visualization module. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0017] In this embodiment of the invention, each of the above-mentioned modules in the yarn twist measurement system can be implemented independently and can call other modules. Here, "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. For example, the sharing and evaluation module can call the same information acquisition module to obtain information collected by that module. Based on the above characteristics, in the yarn twist measurement system provided by this embodiment of the invention, without modifying the program code, the applicable scope of the yarn twist measurement system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the yarn twist measurement system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0018] Example 1: Please refer to Figure 1 As shown in this embodiment, a yarn twist measurement system includes: The yarn data acquisition module is used to acquire yarn datasets, which include yarn diameter data, material type data, and twist coefficient data. It needs to be explained that the yarn diameter data is obtained by collecting the diameter values ​​of a specified batch of yarn using an industrial laser scanner; and the material type data is obtained by collecting the specific wavelength spectrum of the specified batch of yarn using a near-infrared spectrometer and matching it with the material type in the database. The specific formula for displaying the material type data is as follows: The actual twist of a specified batch of yarn is collected using an optical torque sensor and divided by the standard twist to obtain twist coefficient data. The environmental data acquisition module is used to acquire environmental datasets, which include environmental temperature data, environmental humidity data, and vibration intensity data. It should be explained that the ambient temperature data is obtained by collecting temperature values ​​within a specified area using a digital temperature sensor; the ambient humidity data is obtained by collecting humidity values ​​within a specified area using a capacitive humidity sensor; and the vibration intensity data is obtained by collecting vibration values ​​of a specified device using a triaxial accelerometer. The feature data processing module is used to preprocess the yarn dataset and the environment dataset to obtain the feature dataset; Furthermore, methods for preprocessing the yarn dataset and environment dataset include: Q1. Data cleaning and normalization were performed on the yarn dataset and the environment dataset using outlier removal and normalization formulas. It should be explained that the normalization formula is: ,in, For the first A data vector containing all sub-data items from the yarn dataset and the environment dataset. For the first The historical maximum value of each sub-data item For the first The historical minimum value of each sub-data item; Q2, Twist feature extraction is performed using yarn diameter data and twist coefficient data. The specific calculation formula for twist feature extraction is as follows: ; Obtain twist characteristic data ,in, This is the yarn diameter data. This refers to the twist coefficient data; Q3. Stable features are extracted from ambient temperature and humidity data. The specific calculation formula for stable feature extraction is as follows: ; Obtain stable feature data ,in, For ambient temperature data, This refers to ambient humidity data. Q4. Pack twist characteristic data, stability characteristic data and vibration intensity data to obtain the characteristic dataset; The quality prediction value generation module is used to analyze the feature dataset to obtain the yarn quality prediction value; Further steps in analyzing the feature dataset include: Step 1: Obtain a set of historical feature datasets stored in the database, compare them with the current time based on the timestamp, and group and label them in ascending order of time. The labeling results are L1, L2, L3, ..., Ln. Use the labeling results as the sample set. Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and build a yarn quality prediction model based on the sample set. Step 3: Based on the historical feature dataset, use a multi-layer heterogeneous sub-model to calculate and obtain the initial yarn quality prediction value set. The specific formula set for the calculation is as follows: ; Obtain the initial yarn quality prediction set ,in, , and These are the predicted values ​​for the first yarn quality, the second yarn quality, and the third yarn quality, respectively. For the Sigmoid function, For the size of the historical window data, The time decay coefficient, , and For nonlinear activation parameters, It is the hyperbolic tangent function. and For characteristic index parameters, Features The first difference, For Fourier transform, For frequency variables Integral infinitesimal element; It should be explained that the Sigmoid function is used to convert the output value immediately within the parentheses into a probability value of (0,1); the hyperbolic tangent function is used to compress the output value immediately within the parentheses into the interval [1,1]. Step 4: Calculate the predicted yarn quality value based on the initial yarn quality prediction set from Step 3. The specific formula for calculation is as follows: ; Obtain the predicted yarn quality value ,in, It is a weighted average function. For the first The model weighting factors for the yarn quality prediction values ​​in the initial set of yarn quality prediction values. A collection of historical feature datasets, Environmental sensitivity coefficient, For partial derivatives, For characteristic index parameters; Step 5: Based on the weighted average function in Step 4, perform... The value is re-verified when When, the output value is ;when When, the output value is Return and substitute into step four, where It is a median function; It should be explained that the median function is used to take the median of the data immediately preceding the parentheses; Step 6: Output the predicted yarn quality value to the prediction grading and early warning module; The prediction and grading early warning module is used to analyze the predicted yarn quality values ​​and obtain a yarn quality decision report. Furthermore, methods for analyzing predicted yarn quality values ​​include: Subtract the standard yarn quality value from the predicted yarn quality value, divide by the standard yarn quality value, and then multiply by 100% to obtain the quality deviation rate. A normal report is generated when the quality deviation rate is greater than or equal to -5%; a warning report is generated when the quality deviation rate is less than -5% but greater than or equal to -10%; and an alarm report is generated when the quality deviation rate is less than -10%. A normal report includes a statement indicating that the predicted yarn quality is normal, and requesting staff to continue monitoring production. The warning report includes a description of predicted low yarn quality, requesting staff to check and verify the production environment; The alarm report includes a description of predicted poor yarn quality, instructing staff to immediately stop the equipment and calibrate the yarn raw materials; Package normal reports, warning reports, and alarm reports to obtain a yarn quality decision report; The environmental compensation mechanism module is used to process the yarn quality decision report to obtain an environmental optimization compensation report; Furthermore, the methods for processing yarn quality decision reports include: When the yarn quality decision report is a warning report, adjust the ambient temperature data. The specific calculation formula for the adjustment is as follows: ; New ambient temperature data obtained ,in, This is an empirical coefficient. This refers to the quality deviation rate. Divide the ambient humidity data by 2 to obtain the new ambient humidity data; By packaging the new ambient temperature data and the new ambient humidity data, an environmental optimization and compensation report is obtained. The adaptive parameter adjustment module is used to analyze material type data to obtain measurement matching parameters; Furthermore, methods for analyzing material type data include: The material type data is tested, and measurement matching parameters are matched to the material type data through the parameter rule table; The specific rules of the parameter rule table are as follows: Cotton = (La=500, Lb=100), Polyester = (La=700, Lb=150), Nylon = (La=600, Lb=120), where La is the light source intensity and Lb is the sampling frequency; Input material type data, and output measurement matching parameters La and Lb; The yarn self-calibration module is used to process the predicted yarn quality value based on the standard yarn quality value to obtain a yarn calibration report; Furthermore, methods for processing yarn quality prediction values ​​based on yarn quality standard values ​​include: Actual yarn quality values ​​were collected by randomly sampling sensors. The strength qualification value is obtained by calculating the absolute value of the difference between the actual value of yarn quality and the standard value of yarn quality; When the strength qualification value is greater than 0.5, a rework calibration report is generated; The rework calibration report includes the batch number of the yarn and states that the yarn strength of that batch is substandard. The prediction tolerance is obtained by subtracting the absolute value of the actual yarn quality from the predicted yarn quality value. When the prediction tolerance is less than or equal to the tolerance threshold, a prediction qualification report is generated; It should be explained that the tolerance threshold is obtained through manual judgment and input; When the prediction tolerance exceeds the tolerance threshold, a prediction failure report is generated. The forecast report includes a statement indicating that the current yarn quality forecasting model has high accuracy. The report of unqualified prediction includes an explanation that the current yarn quality prediction model has low prediction accuracy, and asks staff to check whether all sensors are working properly. The yarn calibration report is obtained by packaging rework calibration reports, predicted pass reports, and predicted fail reports; The user visualization module is used to analyze the yarn quality decision report, implement corresponding measures based on the analysis results, display the environmental optimization compensation report and the yarn calibration report, and store the overall dataset. Furthermore, the methods for analyzing the yarn quality decision report and implementing corresponding measures based on the analysis results include: Decision-making report for identifying yarn quality; When the yarn quality decision report is a normal report, the normal report is displayed on the visualization panel and a green indicator light is constantly lit by the sound and light device. When the yarn quality decision report is a warning report, the warning report is displayed through the visualization panel, and a yellow light flashes and a buzzer is activated once every thirty seconds via the audio-visual equipment. When the yarn quality decision report is an alarm report, the alarm report is displayed through a visual panel, and a red light flashes and a buzzer is continuously activated via an audio-visual device. The overall dataset includes yarn dataset, environment dataset, feature dataset, yarn quality prediction values, yarn quality decision report, environmental optimization compensation report, measurement matching parameters, and yarn calibration report; In this embodiment, the beneficial effects are achieved by collecting a yarn dataset (including yarn diameter, material type, and twist coefficient data) and an environmental dataset (including ambient temperature, humidity, and vibration intensity data). Preprocessing both datasets yields a feature dataset. Analyzing this feature dataset generates a predicted yarn quality value. Further analysis of the predicted yarn quality value generates a yarn quality decision report. Processing this decision report generates an environmental optimization compensation report. Analyzing the material type data yields measurement matching parameters. Based on the yarn quality standard value, the predicted yarn quality value is processed to generate a yarn calibration report. Analyzing the decision report and implementing corresponding measures based on the analysis results, the environmental optimization compensation report and yarn calibration report are displayed. The overall dataset is stored, enabling the system to adapt to environmental conditions. This invention enables precise prediction of yarn twist under the influence of dynamic fluctuations, significantly reducing the probability of yarn rework and effectively improving enterprise efficiency. Furthermore, by analyzing yarn quality and reverse-calculating the environmental data required for yarn quality improvement, it further reduces the risk of rework due to insufficient twist. Moreover, by differentiating various material types and applying matching measurement parameters to each, it greatly improves measurement accuracy, avoiding inaccurate yarn twist predictions caused by insufficient sensor data. Simultaneously, by comparing the actual twist quality of finished yarns, it assists workers in quickly calibrating the yarn and making timely adjustments, further ensuring enterprise efficiency. Overall, this invention has significant advantages such as high accuracy in yarn twist measurement and prediction, excellent assistance to workers, and a strong feedback mechanism to adjust influencing factors.

[0019] Example 2: Please refer to Figure 2 As shown, the parts not described in detail in this embodiment are described in Embodiment 1. A method for measuring yarn twist is provided. The method includes: S1: collecting a yarn dataset, which includes yarn diameter data, material type data, and twist coefficient data; S2: Collect environmental datasets, which include ambient temperature data, ambient humidity data, and vibration intensity data; S3: Preprocess the yarn dataset and environment dataset to obtain the feature dataset; S4: Analyze the feature dataset to obtain the predicted yarn quality value; S5: Analyze the predicted yarn quality values ​​to obtain a yarn quality decision report; S6: Process the yarn quality decision report to obtain an environmental optimization compensation report; S7: Analyze the material type data to obtain the measurement matching parameters; S8: Process the predicted yarn quality value based on the standard yarn quality value to obtain a yarn calibration report; S9: Analyze the yarn quality decision report, implement corresponding measures based on the analysis results, display the environmental optimization compensation report and yarn calibration report, and store the overall dataset.

[0020] Example 3: It will be apparent to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0021] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0022] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0023] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0024] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A yarn twist measurement system, characterized in that, The system includes: a feature data processing module, a quality prediction value generation module, a prediction grading and early warning module, an environmental compensation mechanism module, an adaptive parameter adjustment module, and a yarn self-calibration module, wherein: The feature data processing module is used to preprocess the yarn dataset and the environment dataset to obtain the feature dataset; The quality prediction value generation module is used to analyze the feature dataset to obtain the yarn quality prediction value; The prediction and grading early warning module is used to analyze the predicted yarn quality values ​​and obtain a yarn quality decision report. The environmental compensation mechanism module is used to process the yarn quality decision report to obtain an environmental optimization compensation report; The adaptive parameter adjustment module is used to analyze material type data to obtain measurement matching parameters; The yarn self-calibration module is used to process the predicted yarn quality value based on the standard yarn quality value to obtain a yarn calibration report.

2. The yarn twist measuring system according to claim 1, characterized in that, The system also includes: a yarn data acquisition module, an environmental data acquisition module, and a user visualization module, wherein: The yarn data acquisition module is used to acquire yarn datasets, which include yarn diameter data, material type data, and twist coefficient data. The environmental data acquisition module is used to acquire environmental datasets, which include environmental temperature data, environmental humidity data, and vibration intensity data. The user visualization module is used to analyze the yarn quality decision report, implement corresponding measures based on the analysis results, display the environmental optimization compensation report and the yarn calibration report, and store the overall dataset.

3. The yarn twist measuring system according to claim 1, characterized in that, Methods for preprocessing yarn datasets and environment datasets include: Q1. Data cleaning and normalization were performed on the yarn dataset and the environment dataset using outlier removal and normalization formulas. Q2, Twist feature extraction is performed using yarn diameter data and twist coefficient data. The specific calculation formula for twist feature extraction is as follows: ； Obtain twist characteristic data ,in, This is the yarn diameter data. This refers to the twist coefficient data; Q3. Stable features are extracted from ambient temperature and humidity data. The specific calculation formula for stable feature extraction is as follows: ； Obtain stable feature data ,in, For ambient temperature data, This refers to ambient humidity data. Q4. Pack twist characteristic data, stability characteristic data and vibration intensity data to obtain the characteristic dataset.

4. The yarn twist measuring system according to claim 1, characterized in that, The steps for analyzing a feature dataset include: Step 1: Obtain a set of historical feature datasets stored in the database, compare them with the current time based on the timestamp, and group and label them in ascending order of time. The labeling results are L1, L2, L3, ..., Ln. Use the labeling results as the sample set. Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and build a yarn quality prediction model based on the sample set. Step 3: Based on the historical feature dataset, use a multi-layer heterogeneous sub-model to calculate and obtain the initial yarn quality prediction value set. The specific formula set for the calculation is as follows: ； Obtain the initial yarn quality prediction set ,in, , and These are the predicted values ​​for the first yarn quality, the second yarn quality, and the third yarn quality, respectively. For the Sigmoid function, For the size of the historical window data, The time decay coefficient, , and For nonlinear activation parameters, It is the hyperbolic tangent function. and For characteristic index parameters, Features The first difference, For Fourier transform, For frequency variables Integral infinitesimal element; Step 4: Calculate the predicted yarn quality value based on the initial yarn quality prediction set from Step 3. The specific formula for calculation is as follows: ； Obtain the predicted yarn quality value ,in, It is a weighted average function. For the first The model weighting factors for the yarn quality prediction values ​​in the initial set of yarn quality prediction values. A collection of historical feature datasets, Environmental sensitivity coefficient, For partial derivatives, For characteristic index parameters; Step 5: Based on the weighted average function in Step 4, perform... The value is re-verified when When, the output value is ;when When, the output value is Return and substitute into step four, where It is a median function; Step 6: Output the yarn quality prediction value to the prediction grading and early warning module.

5. The yarn twist measuring system according to claim 1, characterized in that, Methods for analyzing yarn quality predictions include: Subtract the standard yarn quality value from the predicted yarn quality value, divide by the standard yarn quality value, and then multiply by 100% to obtain the quality deviation rate. A normal report is generated when the quality deviation rate is greater than or equal to -5%; a warning report is generated when the quality deviation rate is less than -5% but greater than or equal to -10%; and an alarm report is generated when the quality deviation rate is less than -10%. A normal report includes a statement indicating that the predicted yarn quality is normal, and requesting staff to continue monitoring production. The warning report includes a description of predicted low yarn quality, requesting staff to check and verify the production environment; The alarm report includes a description of the predicted poor yarn quality, instructing staff to immediately stop the equipment and calibrate the yarn raw materials; Package the normal reports, warning reports, and alarm reports to obtain the yarn quality decision report.

6. The yarn twist measuring system according to claim 1, characterized in that, The methods for processing yarn quality decision reports include: When the yarn quality decision report is a warning report, adjust the ambient temperature data. The specific calculation formula for the adjustment is as follows: ； New ambient temperature data obtained ,in, This is an empirical coefficient. This refers to the quality deviation rate. Divide the ambient humidity data by 2 to obtain the new ambient humidity data; By packaging the new ambient temperature data and the new ambient humidity data, an environmental optimization and compensation report is obtained.

7. The yarn twist measuring system according to claim 1, characterized in that, Methods for analyzing material type data include: The material type data is tested, and measurement matching parameters are matched to the material type data through the parameter rule table; The specific rules of the parameter rule table are as follows: Cotton = (La=500, Lb=100), Polyester = (La=700, Lb=150), Nylon = (La=600, Lb=120), where La is the light source intensity and Lb is the sampling frequency; Input material type data, and output measurement matching parameters La and Lb.

8. The yarn twist measuring system according to claim 1, characterized in that, Methods for processing yarn quality predictions based on yarn quality standard values ​​include: Actual yarn quality values ​​were collected by randomly sampling sensors. The strength qualification value is obtained by calculating the absolute value of the difference between the actual yarn quality value and the standard yarn quality value; When the strength qualification value is greater than 0.5, a rework calibration report is generated; The rework calibration report includes the batch number of the yarn and states that the yarn strength of that batch is substandard. The prediction tolerance is obtained by subtracting the absolute value of the actual yarn quality from the predicted yarn quality value. When the prediction tolerance is less than or equal to the tolerance threshold, a prediction qualification report is generated; When the prediction tolerance is greater than the tolerance threshold, a prediction failure report is generated. The forecast report includes a statement indicating that the current yarn quality forecasting model has high accuracy. The report of unqualified prediction includes an explanation that the current yarn quality prediction model has low prediction accuracy, and asks staff to check whether all sensors are working properly. The yarn calibration report is obtained by packaging rework calibration reports, predicted pass reports, and predicted fail reports.

9. A yarn twist measuring system according to claim 2, characterized in that, The methods for analyzing yarn quality decision reports and implementing corresponding measures based on the analysis results include: Decision-making report for identifying yarn quality; When the yarn quality decision report is a normal report, the normal report is displayed on the visualization panel and a green indicator light is constantly lit by the sound and light device. When the yarn quality decision report is a warning report, the warning report is displayed through the visualization panel, and a yellow light flashes and a buzzer is activated once every thirty seconds via the audio-visual equipment. When the yarn quality decision report is an alarm report, the alarm report is displayed on the visualization panel, and a red light flashes and a buzzer is continuously activated by the sound and light device. The overall dataset includes yarn dataset, environment dataset, feature dataset, yarn quality prediction values, yarn quality decision report, environmental optimization compensation report, measurement matching parameters, and yarn calibration report.

10. A method for measuring yarn twist, implemented using a yarn twist measuring system according to any one of claims 1-9, characterized in that, The work includes the following steps: S1: Collect yarn dataset, which includes yarn diameter data, material type data, and twist coefficient data; S2: Collect environmental datasets, which include ambient temperature data, ambient humidity data, and vibration intensity data; S3: Preprocess the yarn dataset and environment dataset to obtain the feature dataset; S4: Analyze the feature dataset to obtain the predicted yarn quality value; S5: Analyze the predicted yarn quality values ​​to obtain a yarn quality decision report; S6: Process the yarn quality decision report to obtain an environmental optimization compensation report; S7: Analyze the material type data to obtain the measurement matching parameters; S8: Process the predicted yarn quality value based on the standard yarn quality value to obtain a yarn calibration report; S9: Analyze the yarn quality decision report, implement corresponding measures based on the analysis results, display the environmental optimization compensation report and yarn calibration report, and store the overall dataset.

Images