Textile fabric production monitoring system based on intelligent manufacturing

Abstract

The invention relates to the technical field of intelligent manufacturing, in particular to a textile fabric production monitoring system based on intelligent manufacturing, which comprises a fiber tension monitoring module, a data processing module, an intelligent analysis module, an early warning module and a production control module, wherein the fiber tension monitoring module is used for collecting tension data of fibers in the textile production process in real time; the data processing module is used for carrying out denoising and synchronous calibration processing on the collected fiber tension data; the intelligent analysis module is used for analyzing the processed monitoring data and identifying abnormal tension change in the production process; and the early warning module is used for generating an early warning signal according to the abnormal detection result. According to the invention, through real-time monitoring and intelligent analysis of fiber tension changes, abnormal conditions can be automatically identified and pre-warned, and production parameters can be dynamically adjusted, so that the automation level, production efficiency and fabric quality of textile production are remarkably improved, and equipment faults and unqualified products are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing, and particularly relates to a textile fabric production monitoring system based on intelligent manufacturing. BACKGROUND

[0002] With the continuous development of intelligent manufacturing technology, the textile industry gradually moves towards intelligentization and automation. Fiber tension control in the textile production process is one of the key factors to ensure production efficiency and fabric quality. In traditional textile production processes, fiber tension is usually adjusted by manual or simple control devices, lacking real-time monitoring and accurate control of tension fluctuations. This approach is not only susceptible to human factors, but also unable to detect potential tension abnormalities early, resulting in quality fluctuations in the production process, and even causing equipment failure or production interruption, affecting production efficiency and product quality.

[0003] Although some tension monitoring devices and automatic control systems have been adopted in the prior art, the prior art still has many deficiencies. First, traditional tension monitoring methods are often limited to single physical sensors, which cannot comprehensively and real-time monitor and adjust tension changes in complex production environments. Second, existing tension control systems lack automatic diagnosis and early warning functions for abnormal fluctuations, making it difficult to take preventive measures before abnormalities occur to avoid equipment damage or production quality decline. In addition, existing systems lack precise algorithm support for traction force and yarn feeding speed adjustment of textile equipment, and usually rely on experience or simple rules for adjustment, unable to dynamically adjust control strategies based on real-time monitoring data. SUMMARY

[0004] Based on the above purpose, the present application provides a textile fabric production monitoring system based on intelligent manufacturing.

[0005] A textile fabric production monitoring system based on intelligent manufacturing, comprising a fiber tension monitoring module, a data processing module, an intelligent analysis module, an early warning module and a production control module. Wherein:

[0006] The fiber tension monitoring module is used to collect fiber tension data in real time during the textile production process.

[0007] The data processing module is used to denoise and synchronize calibration processing of the collected fiber tension data, and generate processed monitoring data.

[0008] The intelligent analysis module communicates with the data processing module, analyzes the processed monitoring data based on an abnormality detection algorithm, and identifies tension change abnormalities in the production process.

[0009] Early warning module: connected with the intelligent analysis module, used for generating early warning signals according to the abnormal detection results when abnormal tension fluctuation is detected, prompting that the production equipment has potential failure or operation abnormality;

[0010] Production control module: connected with the early warning module, adjusting the parameters of the traction force and the yarn feeding speed of the textile equipment according to the early warning signals, to ensure that the fiber tension is maintained within the predetermined safe range.

[0011] Optionally, the fiber tension monitoring module includes an optical fiber sensing unit, a strain sensing unit, a force sensing unit, and a data acquisition interface; wherein:

[0012] Optical fiber sensing unit: configured with an optical fiber sensor, which uses the principle of optical fiber sensing to detect the change of fiber tension in real time during the textile production process by using the fact that the reflected light intensity of the optical fiber is proportional to the fiber tension, and provides high-sensitivity tension data;

[0013] Strain sensing unit: including a strain sensor, installed on the traction wheel or spinning head of the textile machine, the strain sensor converts the micro deformation generated during the textile process into an electrical signal to reflect the change of fiber tension;

[0014] Force sensing unit: equipped with a micro force sensor, directly installed on the textile head or tension adjusting device of the textile machine, which measures the actual tensile force of the fiber during the production process to obtain fiber tension data;

[0015] Data acquisition interface: used for transmitting the fiber tension data collected by the optical fiber sensing unit, the strain sensing unit and the force sensing unit to the data processing module.

[0016] Optionally, the data processing module includes a denoising unit, a synchronous calibration unit and a data format conversion unit; wherein:

[0017] Denoising unit: used for filtering the fiber tension data collected by the fiber tension monitoring module, using Kalman filtering algorithm or low-pass filtering algorithm to remove environmental interference and sensor noise;

[0018] Synchronous calibration unit: used for time synchronization calibration of the denoised fiber tension data, adjusting the deviation of different sensor data collection times based on time stamp to ensure the time sequence consistency of each data source;

[0019] Data format conversion unit: used for converting the fiber tension data after synchronous calibration into a unified digital format, specifically converting the data into floating point values, conforming to the 32-bit or 64-bit floating point number format of IEEE 754 standard.

[0020] Optionally, the intelligent analysis module includes a feature extraction unit, an anomaly detection unit, a decision-making unit, and a result output unit; wherein:

[0021] Feature extraction unit: used to extract relevant features from the processed fiber tension data, including tension change rate, fluctuation amplitude and duration;

[0022] Anomaly Detection Unit: Based on the relevant features extracted by the feature extraction unit, the anomaly detection algorithm of Isolation Forest is used to analyze the fiber tension data and identify abnormal data points that are different from the normal tension fluctuation pattern;

[0023] Decision unit: Used to determine whether there is an abnormality in fiber tension based on the analysis results of the anomaly detection unit. If there is an abnormality, it generates corresponding anomaly identification information.

[0024] Optionally, the feature extraction unit includes:

[0025] Tension Change Rate Extraction Subunit: Used to calculate the tension change rate at each time point in the processed fiber tension data. The formula is as follows: ,in, For time points The rate of change of tension, For time points Fiber tension data, For time intervals;

[0026] Fluctuation amplitude extraction sub-unit: used to calculate the fluctuation amplitude of fiber tension data within a certain time window. The fluctuation amplitude is defined as the difference between the maximum and minimum tension values ​​within that time period.

[0027] Duration Extraction Subunit: Used to calculate the duration of fiber tension data that continuously exceeds the normal range. Specifically, based on a preset normal tension range, it counts the duration of fiber tension outside this range. The calculation formula is as follows: ,in, For duration, For the number of fiber tension data, For indicator functions, when Exceeding normal tension range When the condition is met, the value is 1; otherwise, the value is 0.

[0028] Optionally, the anomaly detection unit includes:

[0029] Data preprocessing subunit: Used to standardize the feature data of tension change rate, fluctuation amplitude and duration from the feature extraction unit to ensure that all feature data are on the same scale;

[0030] The Isolation Forest algorithm application subunit is used for anomaly detection based on standardized feature data. Isolation Forest partitions the data by constructing multiple random trees; the specific steps include:

[0031] Constructing a random tree: For each sample, select random features and random cut points, divide the sample data in the feature space, and repeat this process multiple times until each sample point is assigned to a separate leaf node.

[0032] Calculate the anomaly score: For each sample point, calculate the anomaly score based on its depth in the tree. The formula for the anomaly score is: ,in, For sample points Abnormal scores, For sample points Average path length across all random trees For standardized constants, This represents the number of sample points.

[0033] Optionally, the decision-making unit includes:

[0034] Anomaly detection subunit: Used to determine the anomaly score of a sample and set a threshold. When the abnormal score is greater than When an outlier occurs, the sample is marked as an anomaly; the anomaly score formula is:

[0035] ;

[0036] Output anomaly identification subunit: used to mark the identified abnormal data points as abnormal and transmit the anomaly identification information to the early warning module.

[0037] Optionally, the early warning module includes an anomaly identifier receiving unit, a threshold determination unit, and an early warning signal generation unit; wherein:

[0038] Anomaly Identifier Receiving Unit: Used to receive anomaly identifier information output by the anomaly identifier subunit, wherein the anomaly identifier information includes the duration and severity of the anomaly data point;

[0039] Threshold determination unit: Based on the preset threshold standard, it determines whether the received abnormal identification information meets the predetermined warning conditions. The preset threshold standard includes the threshold for the severity of the abnormality and the limit for the duration of the abnormality.

[0040] The early warning signal generation unit is configured to generate a corresponding early warning signal when the abnormality identification information meets the early warning condition according to the determination result of the threshold determination unit, and the early warning signal includes a visual alarm, an audible alarm or a remote notification signal.

[0041] Optionally, the threshold determination unit includes:

[0042] The abnormality severity determination subunit is configured to determine whether the abnormality severity in the received abnormality identification information exceeds a preset abnormality severity threshold value, and the abnormality severity in the abnormality identification information is If the following condition is met, it is determined that the abnormality is severe: wherein, is the severity of the abnormal data point, is the preset severity threshold value;

[0043] The abnormality duration determination subunit is configured to determine whether the abnormality duration in the received abnormality identification information exceeds a preset duration threshold value, and the abnormality duration The determination formula of the abnormality duration is: wherein, is the timestamp of the start of the abnormality, is the timestamp of the end of the abnormality, is the abnormality duration; if the preset duration threshold value is exceeded, it is determined that the abnormality is persistent;

[0044] The comprehensive determination subunit is configured to comprehensively determine whether the preset early warning condition is met according to the determination results of the abnormality severity determination unit and the abnormality duration determination unit, and if either the severity or the duration meets the condition, it is determined that the early warning signal is triggered.

[0045] Optionally, the production control module includes an early warning signal receiving unit, a control strategy generation unit and an adjustment control unit; wherein:

[0046] The early warning signal receiving unit is configured to receive the early warning signal generated from the early warning module, including the duration of the abnormal data point and the severity of the abnormality;

[0047] The control strategy generation unit is configured to generate a corresponding adjustment value according to the abnormality severity and the abnormality duration in the received early warning signal; specifically, if the abnormality severity exceeds the preset threshold value or the abnormality duration exceeds the set limit value, the control strategy generation unit will generate the adjustment value of the traction force and the yarn feeding speed according to the following formula: and wherein, is the adjustment value of the traction force, is an adjustment value of the yarn feeding speed, is a preset adjustment coefficient;

[0048] The adjustment control unit is used to generate the traction force and the yarn feeding speed adjustment value according to the output of the control strategy generation unit, to adjust the traction force and the yarn feeding speed of the textile equipment in real time, and to ensure that the fiber tension is maintained within a predetermined safe range.

[0049] The beneficial effects of the present application are as follows:

[0050] The present application can accurately capture the fluctuation of fiber tension in the textile production process by integrating multiple modules such as real-time monitoring of fiber tension, data processing and intelligent analysis. The system can collect fiber tension data in real time during production and perform denoising and synchronous calibration through the data processing module to ensure data accuracy and reliability. The intelligent analysis module uses advanced anomaly detection algorithms to automatically identify abnormal conditions in tension fluctuations and issue early warning signals in a timely manner, effectively avoiding the lack of early warning and intervention in traditional monitoring systems. This not only improves the degree of automation in the production process, but also reduces manual intervention and reduces the risk of production interruption.

[0051] The present application can dynamically adjust the working parameters of the production equipment through the control strategy generated according to the early warning signal, ensuring that the fiber tension is always maintained within a predetermined safe range, thereby effectively preventing equipment failure or fabric quality problems caused by abnormal tension and reducing the production of defective products. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only a part of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0053] Fig. 1 is a schematic diagram of the textile fabric production monitoring system of the present application;

[0054] Fig. 2 is a schematic diagram of the intelligent analysis module of the present application. DETAILED DESCRIPTION

[0055] ​The application will be described in detail below with reference to the drawings and specific embodiments. It should be noted that in order to make the embodiments more detailed, the following embodiments are the best, preferred embodiments, and other alternative ways can also be implemented by those skilled in the art for some known technologies; and the drawings are only used to describe the embodiments in more detail, and are not intended to specifically limit the application.

[0056] It should be noted that in the specification, "one embodiment", "embodiment", "exemplary embodiment", "some embodiments" and the like indicate that the described embodiment can include a specific feature, structure or property, but not necessarily every embodiment includes this specific feature, structure or property. In addition, when a specific feature, structure or property is described in combination with an embodiment, it should be within the knowledge of those skilled in the related art to realize this feature, structure or property in combination with other embodiments (whether or not explicitly described).

[0057] Generally, the terms can be understood at least in part from the context of their use. For example, depending on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular or can be used to describe combinations of features, structures, or characteristics, whether large or small, whether used alone or in combination. In addition, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but can instead, at least in part, depend on the context, allowing the presence of other factors not necessarily explicitly described.

[0058] As shown in Figs. 1-2 A smart manufacturing-based textile fabric production monitoring system includes a fiber tension monitoring module, a data processing module, an intelligent analysis module, a warning module, and a production control module. Wherein:

[0059] The fiber tension monitoring module is used to collect real-time fiber tension data in the textile production process.

[0060] The data processing module is used to denoise and synchronize calibration processing of the collected fiber tension data, and generate processed monitoring data.

[0061] The intelligent analysis module communicates with the data processing module, analyzes the processed monitoring data based on an anomaly detection algorithm, and identifies tension change anomalies in the production process.

[0062] The warning module is connected with the intelligent analysis module, and is used to generate a warning signal according to the anomaly detection result when an abnormal tension fluctuation is detected, prompting potential faults or operation anomalies of the production equipment.

[0063] The production control module is connected with the warning module, adjusts the traction force and yarn feeding speed parameters of the textile equipment according to the warning signal, and ensures that the fiber tension is maintained within a predetermined safe range.

[0064] The fiber tension monitoring module comprises an optical fiber sensing unit, a strain sensing unit, a force sensing unit, and a data acquisition interface; wherein:

[0065] The optical fiber sensing unit is configured with an optical fiber sensor, which uses the principle of optical fiber sensing to detect the change in fiber tension in real time during the textile production process by using the fact that the change in reflected light intensity of the optical fiber is directly proportional to the fiber tension, and provides high-sensitivity tension data;

[0066] The strain sensing unit comprises a strain sensor installed on the traction wheel or spinning head of the textile machine. The strain sensor converts the small deformation generated during the textile process into an electrical signal to reflect the change in fiber tension, thereby ensuring the high precision and real-time nature of the tension data;

[0067] The force sensing unit is equipped with a miniature force sensor, which is directly installed on the textile head or tension adjustment device of the textile machine. By measuring the actual tensile force of the fiber during the production process, the fiber tension data is obtained, ensuring the comprehensiveness of the tension monitoring;

[0068] The data acquisition interface is used to transmit the fiber tension data collected by the optical fiber sensing unit, strain sensing unit, and force sensing unit to the data processing module, ensuring the real-time nature, accuracy, and reliability of the data. By integrating the optical fiber sensing unit, strain sensing unit, and force sensing unit, the fiber tension monitoring module can comprehensively and accurately collect fiber tension data during the textile production process. The different principles of each sensing unit complement each other, ensuring high sensitivity and real-time response to tension fluctuations, thereby effectively ensuring the stability of the fabric quality during the textile production process.

[0069] The data processing module comprises a denoising unit, a synchronous calibration unit, and a data format conversion unit; wherein:

[0070] The denoising unit is used to filter the fiber tension data collected by the fiber tension monitoring module. The Kalman filtering algorithm or low-pass filtering algorithm is used to remove environmental interference and sensor noise, ensuring the purity and accuracy of the data;

[0071] The synchronous calibration unit is used to calibrate the time synchronization of the denoised fiber tension data. Based on the timestamp, the deviation in data collection time between different sensors is adjusted to ensure the time sequence consistency of each data source;

[0072] Data format conversion unit: This unit converts the synchronously calibrated fiber tension data into a unified digital format, specifically converting the data into floating-point values, conforming to the IEEE 754 standard 32-bit or 64-bit floating-point format, to facilitate efficient processing and analysis by the subsequent intelligent analysis module. By integrating the denoising unit, synchronous calibration unit, and data format conversion unit, the data processing module can effectively purify and unify the fiber tension data, eliminate noise and timing deviations in the data, and convert the data into a standardized digital format, ensuring the accuracy, consistency, and efficiency of the data. This precise data processing mechanism provides high-quality input data for the intelligent analysis module.

[0073] The intelligent analysis module includes a feature extraction unit, an anomaly detection unit, a decision-making unit, and a result output unit; among which:

[0074] Feature extraction unit: used to extract relevant features from the processed fiber tension data, including tension change rate, fluctuation amplitude and duration, to facilitate subsequent anomaly detection;

[0075] Anomaly Detection Unit: Based on the relevant features extracted by the feature extraction unit, the anomaly detection algorithm of Isolation Forest is used to analyze the fiber tension data and identify abnormal data points that are different from the normal tension fluctuation pattern;

[0076] Decision unit: Based on the analysis results of the anomaly detection unit, it determines whether there is an anomaly in fiber tension. If an anomaly is found, it generates corresponding anomaly identification information. Through the combination of the above units, the intelligent analysis module can efficiently and accurately perform in-depth analysis and anomaly identification on the processed fiber tension data. The feature extraction unit ensures the accurate extraction of key features, and the anomaly detection unit uses the Isolation Forest algorithm to improve the accuracy and reliability of anomaly identification, thereby enhancing the system's ability to anticipate potential problems in the production process.

[0077] The feature extraction unit includes:

[0078] Tension Change Rate Extraction Subunit: Used to calculate the tension change rate at each time point in the processed fiber tension data. The formula is as follows: ,in, For time points The rate of change of tension, For time points Fiber tension data, Using the time interval as an example, this formula extracts the rate of change of tension over time, thus reflecting the rapid fluctuations in fiber tension.

[0079] The fluctuation amplitude extraction subunit is configured to calculate the fluctuation amplitude of the fiber tension data within a time window, and the fluctuation amplitude is defined as the difference between the maximum value and the minimum value of the tension within the time period. The specific calculation formula is: wherein, is the fluctuation amplitude, is the maximum value of the tension within the time window, is the minimum value of the tension within the time window; through the formula, the fluctuation range of the fiber tension within the specified time period is extracted, which is used to identify abnormal fluctuations;

[0080] The duration extraction subunit is configured to calculate the length of time that the fiber tension data continuously exceeds the normal range. Specifically, according to the pre-set normal tension range, the duration of the fiber tension outside the range is counted, and the calculation formula is: wherein, is the duration, is the number of fiber tension data, is an indicator function, which takes the value of 1 when the fiber tension exceeds the normal tension range , and otherwise takes the value of 0; through this formula, the time period of the fiber tension data outside the normal range is extracted, which helps to identify abnormal and continuous tension fluctuations; through the close cooperation of the above subunits, the feature extraction unit can accurately extract the key features of the tension change from the processed fiber tension data, which provides an important basis for anomaly detection.

[0081] The anomaly detection unit includes:

[0082] The data preprocessing subunit is configured to perform standardization processing on the feature data of the tension change rate, the fluctuation amplitude and the duration from the feature extraction unit, so as to ensure that all feature data are on the same scale, so that the Isolation Forest algorithm can be effectively analyzed;

[0083] The Isolation Forest algorithm application subunit is configured to perform anomaly detection based on the standardized feature data using the Isolation Forest algorithm. Isolation Forest divides data by constructing multiple random trees (Isolation Trees). The specific steps include:

[0084] Constructing a random tree: for each sample, a random feature and a random cutting point are selected to divide the sample data in the feature space, and the process is repeated multiple times until each sample point is assigned to a separate leaf node;

[0085] Calculating the anomaly score: for each sample point, the anomaly score is calculated according to its depth in the tree, and the anomaly score formula is: wherein, is the anomaly score of the sample point , is the average path length of the sample point in all random trees, is a normalization constant, is the number of sample points, the shorter the path of the sample point, the higher the anomaly score, indicating that it is more likely to be divided, and may be an abnormal point.

[0086] The decision unit comprises:

[0087] Anomaly judgment subunit: for judging samples according to the anomaly score, setting a threshold , when the anomaly score is greater than , the sample is marked as an abnormal data point; the anomaly score formula is:

[0088] ; through this step, abnormal data points significantly different from the normal tension fluctuation pattern are identified;

[0089] Output anomaly identification subunit: for marking the identified abnormal data points as abnormal, and transmitting the anomaly identification information to the early warning module for subsequent processing; through the data preprocessing unit, feature standardization is carried out, and the IsolationForest algorithm is used for anomaly detection. The anomaly detection unit can efficiently and accurately identify abnormal data points different from the normal tension fluctuation pattern. This method can automatically process large-scale data sets, reduce manual intervention, improve the accuracy and efficiency of anomaly detection, and thus ensure the stability of the equipment and the consistency of the fabric quality in the textile production process.

[0090] The early warning module comprises an anomaly identification receiving unit, a threshold judgment unit and an early warning signal generating unit; wherein:

[0091] Anomaly identification receiving unit: for receiving the anomaly identification information output by the output anomaly identification subunit, the anomaly identification information including the duration of the abnormal data point and the severity of the anomaly;

[0092] Threshold judgment unit: according to the preset threshold standard, judge whether the received anomaly identification information meets the predetermined early warning condition, the preset threshold standard including the abnormal severity threshold and the limitation of the abnormal duration;

[0093] The early warning signal generation unit is configured to generate a corresponding early warning signal when the abnormality identification information meets the early warning condition according to the determination result of the threshold determination unit, the early warning signal including a visual alarm, a sound alarm or a remote notification signal, so as to ensure that relevant personnel can respond in time; through the above-mentioned units, the early warning module can quickly generate an early warning signal according to the abnormality detection result when detecting abnormal tension fluctuation, so as to ensure that the abnormal situation occurring in the production process can be detected in time.

[0094] The threshold determination unit includes:

[0095] The abnormality severity judgment sub-unit is configured to judge whether the abnormality severity in the received abnormality identification information exceeds a preset abnormality severity threshold value; the abnormality severity in the abnormality identification information is If the following condition is met, it is determined that the abnormality is serious: wherein, is the severity of the abnormal data point, is a preset severity threshold value;

[0096] The abnormality duration judgment sub-unit is configured to judge whether the abnormality duration in the received abnormality identification information exceeds a preset duration threshold value; the abnormality duration The judgment formula of the abnormality duration is: wherein, is the timestamp of the start of the abnormality, is the timestamp of the end of the abnormality, is the abnormality duration; if exceeds the preset duration threshold value , it is determined that the abnormality is continuous;

[0097] The comprehensive judgment sub-unit is configured to comprehensively judge whether the preset early warning condition is met according to the judgment results of the abnormality severity judgment unit and the abnormality duration judgment unit, and determine that the early warning signal is triggered if any one of the severity or the duration meets the condition; through the above-mentioned sub-units, it can be judged whether the early warning signal is triggered based on the received abnormality identification information; by setting reasonable severity threshold value and duration threshold value, abnormal tension fluctuation having important influence on the production process can be effectively screened out, and false positives and false negatives can be reduced.

[0098] The production control module includes an early warning signal receiving unit, a control strategy generation unit and an adjustment control unit; wherein:

[0099] The early warning signal receiving unit is configured to receive the early warning signal generated from the early warning module, including the duration of the abnormal data point and the abnormality severity;

[0100] The control strategy generation unit is configured to generate corresponding adjustment values according to the abnormal severity and the abnormal duration in the received early warning signal. Specifically, if the abnormal severity exceeds a preset threshold or the abnormal duration exceeds a set limit value, the control strategy generation unit will generate adjustment values for the traction force and the yarn feeding speed according to the following formula: The control strategy generation unit will generate adjustment values for the traction force and the yarn feeding speed according to the following formula: and wherein, is the adjustment value for the traction force, is the adjustment value for the yarn feeding speed, and is a preset adjustment coefficient; the expression of the adjustment coefficient is as follows: and wherein, and are constants related to the device type and the tension characteristics, respectively, is the maximum tension fluctuation range that the device can withstand, which is usually set by the structure and material characteristics of the device; the constants and can be obtained through experimental or simulation data and adjusted by the controller to optimize the response speed and accuracy of the device;

[0101] The adjustment control unit is configured to adjust the traction force and the yarn feeding speed of the textile device in real time according to the adjustment values for the traction force and the yarn feeding speed output by the control strategy generation unit, to ensure that the fiber tension is maintained within a predetermined safe range and to avoid negative effects of abnormal tension on the production process and fabric quality. Through the design of the above-mentioned units, the production control module can quickly respond to abnormal tension fluctuations in the textile production process, adjust the traction force and the yarn feeding speed in real time to ensure that the fiber tension is maintained within a predetermined safe range, effectively reduce equipment failures and unstable factors in the production process, and improve production efficiency and reduce the rejection rate.

[0102] The present application encompasses any alternatives, modifications, equivalent methods and solutions made to the essence and scope of the present application. In order to fully understand the present application, specific details are described in the following preferred embodiments of the present application, which can also be fully understood by those skilled in the art without these details. In addition, in order to avoid unnecessary confusion to the essence of the present application, well-known methods, processes, procedures, elements and circuits, etc. are not described in detail.

[0103] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.​

Claims

1. A smart manufacturing based textile fabric production monitoring system, characterized in that, The system comprises a fiber tension monitoring module, a data processing module, an intelligent analysis module, an early warning module, and a production control module. The fiber tension monitoring module is used to collect fiber tension data in real time during the textile production process. The data processing module is used to denoise and synchronize the collected fiber tension data, and generate processed monitoring data. The intelligent analysis module communicates with the data processing module, analyzes the processed monitoring data based on an anomaly detection algorithm, and identifies abnormal tension changes in the production process. The early warning module is connected to the intelligent analysis module and generates a warning signal based on the anomaly detection results when an abnormal tension fluctuation is detected, prompting potential faults or abnormal operations of the production equipment. The production control module is connected to the early warning module and adjusts the traction force and yarn feeding speed of the textile equipment based on the warning signal to ensure that the fiber tension is maintained within a predetermined safe range.

2. The system as claimed in claim 1, wherein The fiber tension monitoring module includes an optical fiber sensing unit, a strain sensing unit, a force sensing unit, and a data acquisition interface. The optical fiber sensing unit is equipped with an optical fiber sensor that uses the principle of optical fiber sensing to detect changes in fiber tension during the textile production process in real time. The strain sensing unit includes a strain sensor installed on the traction wheel or spinning head of the textile machine. The force sensing unit is equipped with a miniature force sensor installed directly on the textile head or tension adjustment device of the textile machine. The data acquisition interface is used to transmit the fiber tension data collected by the optical fiber sensing unit, strain sensing unit, and force sensing unit to the data processing module.

3. The system as claimed in claim 1, wherein, The data processing module includes a denoising unit, a synchronization calibration unit, and a data format conversion unit. The denoising unit is used to filter the fiber tension data collected by the fiber tension monitoring module using Kalman filtering or low-pass filtering to remove environmental interference and sensor noise. The synchronization calibration unit is used to synchronize and calibrate the denoised fiber tension data based on timestamps to adjust the time deviation between different sensor data collection times and ensure the time consistency of each data source. The data format conversion unit is used to convert the synchronized fiber tension data into a unified digital format, specifically converting the data into floating-point values conforming to the IEEE 754 standard 32-bit or 64-bit floating-point number format.

4. The system as claimed in claim 1, wherein, The intelligent analysis module includes a feature extraction unit, an anomaly detection unit, a decision unit, and a result output unit. The feature extraction unit is used to extract relevant features from the processed fiber tension data, including tension change rate, fluctuation amplitude, and duration. The abnormality detection unit uses an Isolation Forest algorithm to analyze the fiber tension data based on the relevant features extracted by the feature extraction unit, and identifies abnormal data points that are different from the normal tension fluctuation pattern. The decision unit is used to determine whether the fiber tension is abnormal based on the analysis results of the abnormality detection unit, and if there is an abnormality, corresponding abnormal identification information is generated.

5. The smart manufacturing based textile fabric production monitoring system as claimed in claim 4, wherein, The feature extraction unit includes: a tension change rate extraction subunit configured to calculate a tension change rate at each time point in the processed fiber tension data according to the following formula: wherein is the tension change rate at time point is the fiber tension data at time point is the time interval;​​ The fluctuation amplitude extraction sub-unit is used to calculate the fluctuation amplitude of the fiber tension data within a certain time window, and the fluctuation amplitude is defined as the difference between the maximum and minimum values of the tension within the time period. Duration extraction subunit: used to calculate the length of time that the fiber tension data continuously exceeds the normal range, specifically according to the preset normal tension range, the duration of the fiber tension outside the range is counted, and the calculation formula is: wherein, is the duration, is the number of fiber tension data, is an indicator function, when the normal tension range is exceeded , the value is 1, otherwise the value is 0.

6. The smart manufacturing based textile fabric production monitoring system as claimed in claim 5, wherein, The abnormality detection unit includes: The data preprocessing sub-unit is used to standardize the feature data of the tension rate of change, fluctuation amplitude and duration from the feature extraction unit, ensuring that all feature data is on the same scale. The Isolation Forest algorithm application sub-unit is used to perform abnormality detection based on the standardized feature data using the Isolation Forest algorithm, which divides the data by constructing multiple random trees; the specific steps include: Constructing a random tree: for each sample, select a random feature and a random cut point to divide the sample data in the feature space, and repeat multiple times until each sample point is assigned to a separate leaf node. Calculate the anomaly score: For each sample point, calculate the anomaly score based on its depth in the tree. The formula for the anomaly score is: ,in, For sample points Abnormal scores, For sample points Average path length across all random trees For standardized constants, This represents the number of sample points.

7. The smart manufacturing based textile fabric production monitoring system as claimed in claim 6, wherein, The decision unit includes: Anomaly determination subunit: for determining the sample according to the anomaly score, setting a threshold When the anomaly score is greater than , the sample is marked as an anomaly data point; the anomaly score formula is: ； The output abnormality identification sub-unit is used to mark the identified abnormal data points as abnormal, and transmit the abnormal identification information to the warning module.

8. The smart manufacturing based textile fabric production monitoring system as claimed in claim 7, wherein, The warning module includes an abnormality identification receiving unit, a threshold determination unit, and a warning signal generation unit; wherein: The abnormality identification receiving unit is used to receive the abnormality identification information output by the output abnormality identification sub-unit, which includes the duration of the abnormal data points and the severity of the abnormality; The threshold determination unit determines whether the received abnormality identification information meets the predetermined warning condition according to the preset threshold standard, which includes the abnormal severity threshold and the abnormal duration limit; The warning signal generation unit is used to generate a corresponding warning signal when the abnormality identification information meets the warning condition according to the judgment result of the threshold determination unit, and the warning signal includes visual alarm, sound alarm or remote notification signal.

9. The smart manufacturing based textile fabric production monitoring system as claimed in claim 8, wherein, The threshold determination unit includes: abnormality severity judgment subunit: for judging whether the preset abnormality severity threshold is exceeded according to the abnormality severity in the received abnormality identification information; the abnormality severity in the abnormality identification information is If the following condition is met, it is determined as a serious abnormality: wherein, is the severity of the abnormal data point, is the preset severity threshold; anomaly duration judgment subunit: used for judging whether the preset duration threshold is exceeded according to the anomaly duration in the received anomaly identification information; anomaly duration The judgment formula is as follows: Wherein, is the timestamp of the anomaly start, is the timestamp of the anomaly end, is the anomaly duration; if the preset duration threshold is exceeded , it is determined that the anomaly is persistent. The comprehensive judgment sub-unit is used to comprehensively judge whether the preset warning condition is met according to the judgment results of the abnormal severity judgment unit and the abnormal duration judgment unit, and if either the severity or the duration meets the condition, the warning signal is triggered.

10. The smart manufacturing based textile fabric production monitoring system as claimed in claim 1, wherein, The production control module includes a warning signal receiving unit, a control strategy generation unit, and an adjustment control unit; wherein: The warning signal receiving unit is used to receive the warning signal generated by the warning module, including the duration of the abnormal data points and the severity of the abnormality; Control strategy generation unit: used to generate corresponding adjustment values ​​based on the severity and duration of the anomaly in the received warning signal; specifically, if the severity of the anomaly... Exceeding the preset threshold or abnormal duration If the set limits are exceeded, the control strategy generation unit will generate adjustment values ​​for traction force and yarn feed speed according to the following formula: and ,in, This is the adjustment value for traction force. This is the adjustment value for the yarn feed speed. and This is a preset adjustment coefficient; The adjustment control unit is used to adjust the traction force and yarn feeding speed of the textile equipment in real time according to the traction force and yarn feeding speed adjustment values output by the control strategy generation unit, to ensure that the fiber tension is maintained within the predetermined safe range.

Images