Home textile fiber fabric production quality monitoring system

Abstract

The invention discloses a home textile fiber fabric production quality monitoring system. The system comprises a fabric edge data acquisition module, a data processing module, a defect identification module, an alarm module, a data storage module, a user interaction module and a cloud monitoring module. The fabric edge data acquisition module comprises a high-resolution industrial camera and is used for acquiring quality data of home textile fiber fabric edge sewing on a production line in real time; the data processing module adopts a high-performance computing platform, extracts image data of the edge of the home textile fiber fabric, processes the extracted image data, analyzes the image data by using a deep learning algorithm, and identifies potential defects of the edge of the home textile fiber fabric; through the fabric edge data acquisition module, image data of home textile fiber fabric edges on a production line and data of other sensors can be acquired in real time, it is ensured that the system can find quality problems in the production process in time, and the detection efficiency is improved through real-time data acquisition and analysis.

Description

Technical Field

[0001] The invention belongs to the technical field of fabric production, and in particular relates to a home textile fiber fabric production quality monitoring system. Background Art

[0002] With the development of the national economy and the continuous progress of society, people's living standards are improving day by day, and the requirements for the fashion, comfort and other performance of civilian home textile fabrics are also increasing, which has also promoted the inspection of the quality of home textile fabrics. Fabric quality monitoring is the last control before fabric products leave the factory. The quality of fabrics will affect the sales of products, so the accuracy of the quality monitoring system will affect the final market sales of fabrics.

[0003] For example, a home textile fiber fabric production quality monitoring system disclosed in announcement number CN114677062B includes: a first data acquisition module for dividing the home textile fiber fabric into a plurality of sub-areas and obtaining the fabric thickness of each sub-area; a preliminary screening module for obtaining a first quality evaluation result of the home textile fiber fabric and obtaining a better fabric according to the first quality evaluation result; a second data acquisition module for obtaining the fabric density and light transmittance of each sub-area in the better fabric; dividing the sub-areas into a plurality of groups and obtaining the synchronous distance between each adjacent two groups; a quality screening module for linearly fitting the synchronous distance and obtaining the fitting degree of each adjacent two groups in the better fabric, and judging whether the fabric is of qualified quality according to the fitting degree.

[0004] Although the above-mentioned home textile fiber fabric production quality monitoring system has improved the detection efficiency of home textile fiber fabrics and improved the detection accuracy, it does not carry out targeted monitoring on the edge part of the home textile fiber fabric, and the edge part of the home textile fiber fabric is prone to defects that are not easy to be found. If these defects cannot be discovered in time, it will lead to quality problems in the produced home textile fiber fabrics. For this reason, we propose a home textile fiber fabric production quality monitoring system. Summary of the invention

[0005] The object of the present invention is to provide a home textile fiber fabric production quality monitoring system to solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a home textile fiber fabric production quality monitoring system, comprising a fabric edge data acquisition module, a data processing module, a defect recognition module, an alarm module, a data storage module, a user interaction module and a cloud monitoring module;

[0007] The fabric edge data acquisition module includes a high-resolution industrial camera for real-time acquisition of quality data of the edge stitching of home textile fiber fabrics on the production line;

[0008] The data processing module uses a high-performance computing platform to extract image data of the edge of the home textile fiber fabric, processes the extracted image data, analyzes the image data using a deep learning algorithm, identifies potential defects at the edge of the home textile fiber fabric, fuses the image data with the sensor data, and transmits the processed data;

[0009] The defect recognition module is used to identify defects on the edge of home textile fiber fabrics based on a database of defect types by comparing with the defect types in the database;

[0010] The alarm module is used to send out an alarm signal when a defect is detected on the edge of the home textile fiber fabric, send the alarm information to the remote monitoring center through wireless communication technology, and record the information of each alarm for later statistical analysis;

[0011] The data storage module is used to store the collected data and analysis results;

[0012] The user interaction module is used to provide a friendly user interface for user operation and setting;

[0013] The cloud monitoring module is used to upload data to the cloud and provide remote monitoring functions, support remote monitoring of the status of the production line via the Internet, provide data analysis tools to help users analyze production data, and provide fault diagnosis functions to help users quickly locate problems.

[0014] Preferably, the fabric edge data acquisition module also includes a tension sensor, a temperature sensor and a data transmission unit, the tension sensor is used to detect the tension of the edge of the home textile fiber fabric, the temperature sensor is used to detect the temperature of the surface of the home textile fiber fabric, and the data transmission unit is used to transmit the collected quality data of the home textile fiber fabric.

[0015] Preferably, the data processing module is also used to extract tension data and surface temperature data of the edge of the home textile fiber fabric, analyze the tension data and surface temperature data, and transmit the analyzed data to the defect identification module.

[0016] Preferably, the defect recognition module includes a database establishment unit, an image comparison unit, a defect recognition unit and a real-time feedback unit. The database establishment unit is used to establish the defect types of common home textile fiber fabric edges. The image comparison unit is used to compare the defect types of common home textile fiber fabric edges with the collected image data of home textile fiber fabric edges. The defect recognition unit is used to use deep learning models such as convolutional neural networks to identify defects in the edge images of home textile fiber fabrics. The real-time feedback unit is used to feed back the defect recognition results in real time so that defects can be discovered in a timely manner.

[0017] Preferably, the data processing module uses a convolution operation to extract features from the image, and the convolution operation includes the following formula:

[0018]

[0019] For two-dimensional images, the following formulas are included:

[0020]

[0021] Among them, f is the input image or signal; g is the convolution kernel; t is the time variable in one dimension; x, y are the spatial variables in two dimensions; τ is the integral variable in one dimension; i, j are the summation variables in two dimensions.

[0022] Preferably, the defect recognition module uses a loss function to measure the gap between the predicted result and the actual result. The loss function includes a cross entropy loss. The specific formula is as follows:

[0023]

[0024] Among them, y is the true label (0 or 1); is the predicted probability; is the value of the loss function.

[0025] Preferably, the defect recognition module further includes a back propagation algorithm, which is used to update the network weights to minimize the loss function. The specific formula is as follows:

[0026]

[0027] in, is the weight at the tth iteration; is the weight at the t+1th iteration; η is the learning rate, which controls the speed of weight update; is the partial derivative of the loss function with respect to the weight.

[0028] Preferably, the data storage module includes local storage, cloud storage and data encryption. The data storage module is used to store the collected data and analysis results in the local server, upload the data to the cloud via the Internet to achieve data backup, and encrypt the stored data to ensure data security.

[0029] Preferably, it also includes an automatic classification module, which is used to establish a classification rule base, classify different defects according to their characteristics according to the classification rule base, and use a decision tree algorithm to classify the identified defects, and automatically mark the classified defects for subsequent processing.

[0030] Preferably, the quality monitoring system monitors the production quality of home textile fiber fabrics including the following steps:

[0031] S1. Use industrial cameras to capture images of the edges of home textile fabrics in real time, and use sensors to monitor various parameters of the production line in real time;

[0032] S2. Process the collected data using a high-performance computing platform and identify defects in the image using a deep learning algorithm;

[0033] S3. Identify defects in the image through deep learning models such as convolutional neural networks, and compare the identification results with a database of defect types;

[0034] S4. When a defect is detected, an alarm signal is issued through an audible and visual alarm, and the alarm information is sent to a remote monitoring center through wireless communication technology;

[0035] S5. Store the collected data and analysis results in the local server and upload them to the cloud via the Internet;

[0036] S6. Provide a friendly user interface for user operation and settings;

[0037] S7. Remotely monitor the status of the production line through the Internet, and use the provided data analysis tools to perform fault diagnosis to ensure the normal progress of quality monitoring.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] (1) The fabric edge data acquisition module provided in the present invention can collect image data and other sensor data of the edge of home textile fiber fabrics on the production line in real time, ensuring that the system can timely discover quality problems in the production process and improve detection efficiency by real-time data acquisition and analysis;

[0040] (2) The present invention uses a data processing module to improve the accuracy of defect recognition, reduce false positives and false negatives, and save labor costs. When a defect is detected, an alarm signal can be issued in time through an alarm module to ensure that quality problems are dealt with in a timely manner.

[0041] (3) The defect identification module provided in the present invention can replace the traditional manual sampling method, realize automatic detection, and improve detection efficiency. The data storage module provided adopts local storage and cloud storage to ensure the security and reliability of data. The system also supports remote monitoring of the status of the production line, thereby improving management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1It is a structural block diagram of the present invention;

[0043] Figure 2 It is a structural block diagram of the fabric edge data acquisition module of the present invention;

[0044] Figure 3 It is a structural block diagram of the defect identification module of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] See also Figure 1-Figure 3 , the present invention provides a technical solution: a home textile fiber fabric production quality monitoring system, including a fabric edge data acquisition module, a data processing module, a defect recognition module, an alarm module, a data storage module, a user interaction module and a cloud monitoring module;

[0047] The fabric edge data acquisition module includes a high-resolution industrial camera for real-time acquisition of quality data of the edge stitching of home textile fiber fabrics on the production line;

[0048] The data processing module uses a high-performance computing platform to extract image data of the edge of the home textile fiber fabric, processes the extracted image data, analyzes the image data using a deep learning algorithm, identifies potential defects at the edge of the home textile fiber fabric, fuses the image data with the sensor data, and transmits the processed data;

[0049] The defect recognition module is used to identify defects on the edge of home textile fiber fabrics based on a database of defect types by comparing with the defect types in the database;

[0050] The alarm module is used to send out an alarm signal when a defect is detected on the edge of the home textile fiber fabric, send the alarm information to the remote monitoring center through wireless communication technology, and record the information of each alarm for later statistical analysis;

[0051] The data storage module is used to store the collected data and analysis results;

[0052] The user interaction module is used to provide a friendly user interface for user operation and setting;

[0053] The cloud monitoring module is used to upload data to the cloud and provide remote monitoring functions, support remote monitoring of the status of the production line via the Internet, provide data analysis tools to help users analyze production data, and provide fault diagnosis functions to help users quickly locate problems.

[0054] In this embodiment, preferably, the fabric edge data acquisition module also includes a tension sensor, a temperature sensor and a data transmission unit, the tension sensor is used to detect the tension of the edge of the home textile fiber fabric, the temperature sensor is used to detect the temperature of the surface of the home textile fiber fabric, and the data transmission unit is used to transmit the collected quality data of the home textile fiber fabric.

[0055] In this embodiment, preferably, the data processing module is also used to extract tension data and surface temperature data of the edge of the home textile fiber fabric, analyze the tension data and surface temperature data, and transmit the analyzed data to the defect recognition module.

[0056] In this embodiment, preferably, the defect recognition module includes a database establishment unit, an image comparison unit, a defect recognition unit and a real-time feedback unit, the database establishment unit is used to establish the defect types of common home textile fiber fabric edges, the image comparison unit is used to compare the defect types of common home textile fiber fabric edges with the collected image data of home textile fiber fabric edges, the defect recognition unit is used to use deep learning models such as convolutional neural networks to identify defects in the edge images of home textile fiber fabrics, and the real-time feedback unit is used to feed back the defect recognition results in real time so that defects can be discovered in time.

[0057] In this embodiment, preferably, the data processing module uses a convolution operation to extract features from the image, and the convolution operation includes the following formula:

[0058]

[0059] For two-dimensional images, the following formulas are included:

[0060]

[0061] Among them, f is the input image or signal; g is the convolution kernel; t is the time variable in one dimension; x, y are the spatial variables in two dimensions; τ is the integral variable in one dimension; i, j are the summation variables in two dimensions.

[0062] In this embodiment, preferably, the data processing module uses a convolution operation to extract features from the image, and the convolution operation includes the following formula:

[0063]

[0064] For two-dimensional images, the following formulas are included:

[0065]

[0066] Among them, f is the input image or signal; g is the convolution kernel; t is the time variable in one dimension; x, y are the spatial variables in two dimensions; τ is the integral variable in one dimension; i, j are the summation variables in two dimensions.

[0067] In this embodiment, preferably, the defect recognition module further includes a back propagation algorithm, which is used to update the network weights to minimize the loss function. The specific formula is as follows:

[0068]

[0069] in, is the weight at the tth iteration; is the weight at the t+1th iteration; η is the learning rate, which controls the speed of weight update; is the partial derivative of the loss function with respect to the weight.

[0070] In this embodiment, preferably, the data storage module includes local storage, cloud storage and data encryption. The data storage module is used to store the collected data and analysis results in the local server, upload the data to the cloud via the Internet to achieve data backup, and encrypt the stored data to ensure data security.

[0071] In this embodiment, preferably, it also includes an automatic classification module, which is used to establish a classification rule base, classify different defects according to their characteristics according to the classification rule base, and use a decision tree algorithm to classify the identified defects, and automatically mark the classified defects for subsequent processing.

[0072] In this embodiment, preferably, the quality monitoring system monitors the production quality of home textile fiber fabrics including the following steps:

[0073] S1. Use industrial cameras to capture images of the edges of home textile fabrics in real time, and use sensors to monitor various parameters of the production line in real time;

[0074] S2. Process the collected data using a high-performance computing platform and identify defects in the image using a deep learning algorithm;

[0075] S3. Identify defects in the image through deep learning models such as convolutional neural networks, and compare the identification results with a database of defect types;

[0076] S4. When a defect is detected, an alarm signal is issued through an audible and visual alarm, and the alarm information is sent to a remote monitoring center through wireless communication technology;

[0077] S5. Store the collected data and analysis results in the local server and upload them to the cloud via the Internet;

[0078] S6. Provide a friendly user interface for user operation and settings;

[0079] S7. Remotely monitor the status of the production line through the Internet, and use the provided data analysis tools to perform fault diagnosis to ensure the normal progress of quality monitoring.

[0080] Principles and advantages of the present invention:

[0081] The present invention can collect image data and other sensor data of the edges of home textile fiber fabrics on the production line in real time through the fabric edge data acquisition module, thereby ensuring that the system can timely discover quality problems in the production process, and improve detection efficiency by real-time data acquisition and analysis; through the data processing module, advanced image processing technology and deep learning algorithm are used to improve the accuracy of defect recognition, reduce false alarms and missed alarms, and save labor costs; through the alarm module, an alarm signal can be issued in time when a defect is detected, thereby ensuring that quality problems are handled in a timely manner; through the defect recognition module, traditional manual sampling methods can be replaced, automatic detection can be realized, and detection efficiency can be improved; through the data storage module, local storage and cloud storage are used to ensure data security and reliability, and the system supports remote monitoring of the status of the production line, thereby improving management efficiency.

[0082] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A home textile fiber fabric production quality monitoring system, characterized by: It includes fabric edge data acquisition module, data processing module, defect recognition module, alarm module, data storage module, user interaction module and cloud monitoring module; The fabric edge data acquisition module includes a high-resolution industrial camera for real-time acquisition of quality data of the edge stitching of home textile fiber fabrics on the production line; The data processing module uses a high-performance computing platform to extract image data of the edge of the home textile fiber fabric, processes the extracted image data, analyzes the image data using a deep learning algorithm, identifies potential defects at the edge of the home textile fiber fabric, fuses the image data with the sensor data, and transmits the processed data; The defect recognition module is used to identify defects on the edge of home textile fiber fabrics based on a database of defect types by comparing with the defect types in the database; The alarm module is used to send out an alarm signal when a defect is detected on the edge of the home textile fiber fabric, send the alarm information to the remote monitoring center through wireless communication technology, and record the information of each alarm for later statistical analysis; The data storage module is used to store the collected data and analysis results; The user interaction module is used to provide a friendly user interface for user operation and setting; The cloud monitoring module is used to upload data to the cloud and provide remote monitoring functions, support remote monitoring of the status of the production line via the Internet, provide data analysis tools to help users analyze production data, and provide fault diagnosis functions to help users quickly locate problems.

2. A home textile fiber fabric production quality monitoring system according to claim 1, characterized in that: The fabric edge data acquisition module also includes a tension sensor, a temperature sensor and a data transmission unit. The tension sensor is used to detect the tension of the edge of the home textile fiber fabric, the temperature sensor is used to detect the temperature of the surface of the home textile fiber fabric, and the data transmission unit is used to transmit the collected quality data of the home textile fiber fabric.

3. A home textile fiber fabric production quality monitoring system according to claim 2, characterized in that: The data processing module is also used to extract the tension data and surface temperature data of the edge of the home textile fiber fabric, analyze the tension data and surface temperature data, and transmit the analyzed data to the defect recognition module.

4. A home textile fiber fabric production quality monitoring system according to claim 3, characterized in that: The defect recognition module includes a database establishment unit, an image comparison unit, a defect recognition unit and a real-time feedback unit. The database establishment unit is used to establish the defect types of common home textile fiber fabric edges. The image comparison unit is used to compare the defect types of common home textile fiber fabric edges with the collected image data of home textile fiber fabric edges. The defect recognition unit is used to use deep learning models such as convolutional neural networks to identify defects in the edge images of home textile fiber fabrics. The real-time feedback unit is used to feed back defect recognition results in real time so that defects can be discovered in a timely manner.

5. A home textile fiber fabric production quality monitoring system according to claim 4, characterized in that: The data processing module uses a convolution operation to extract features from the image, and the convolution operation includes the following formula: For two-dimensional images, the following formulas are included: Among them, f is the input image or signal; g is the convolution kernel; t is the time variable in one dimension; x, y are the spatial variables in two dimensions; τ is the integral variable in one dimension; i, j are the summation variables in two dimensions.

6. A home textile fiber fabric production quality monitoring system according to claim 5, characterized in that: The defect recognition module uses a loss function to measure the gap between the predicted result and the actual result. The loss function includes a cross entropy loss. The specific formula is as follows: Among them, y is the true label (0 or 1); is the predicted probability; is the value of the loss function.

7. A home textile fiber fabric production quality monitoring system according to claim 6, characterized in that: The defect recognition module also includes a back propagation algorithm, which is used to update the network weights to minimize the loss function. The specific formula is as follows: in, is the weight at the tth iteration; is the weight at the t+1th iteration; η is the learning rate, which controls the speed of weight update; is the partial derivative of the loss function with respect to the weight.

8. The home textile fiber fabric production quality monitoring system according to claim 1, characterized in that: The data storage module includes local storage, cloud storage and data encryption. The data storage module is used to store the collected data and analysis results in the local server, upload the data to the cloud via the Internet to achieve data backup, and encrypt the stored data to ensure data security.

9. A home textile fiber fabric production quality monitoring system according to claim 1, characterized in that: It also includes an automatic classification module, which is used to establish a classification rule base, classify different defects according to their characteristics according to the classification rule base, and use a decision tree algorithm to classify the identified defects, and automatically mark the classified defects for subsequent processing.

10. A home textile fiber fabric production quality monitoring system according to claim 1, characterized in that: The quality monitoring system monitors the production quality of home textile fiber fabrics and comprises the following steps: S1. Use industrial cameras to capture images of the edges of home textile fabrics in real time, and use sensors to monitor various parameters of the production line in real time; S2. Process the collected data using a high-performance computing platform and identify defects in the image using a deep learning algorithm; S3. Identify defects in the image through deep learning models such as convolutional neural networks, and compare the identification results with a database of defect types; S4. When a defect is detected, an alarm signal is issued through an audible and visual alarm, and the alarm information is sent to a remote monitoring center through wireless communication technology; S5. Store the collected data and analysis results in the local server and upload them to the cloud via the Internet; S6. Provide a friendly user interface for user operation and settings; S7. Remotely monitor the status of the production line through the Internet, and use the provided data analysis tools to perform fault diagnosis to ensure the normal progress of quality monitoring.

Images