A textile weaving process data monitoring system based on internet of things technology

Abstract

The application discloses a kind of based on Internet of Things technology textile weaving process data monitoring system, it is related to textile weaving process data monitoring technical field.The based on Internet of Things technology textile weaving process data monitoring system, including data acquisition module, data processing analysis module and monitoring module.The first equipment data is compressed transmission to data processing analysis module by data acquisition module and the first equipment data is collected, third equipment data is obtained by decompression and pre-processing to data by data processing analysis module and is transmitted to monitoring module by edge computing node to obtain equipment evaluation index, and then improve textile weaving process data monitoring monitoring efficiency, solve the problem of low textile weaving process data monitoring monitoring efficiency in prior art.

Description

[0001] This application is a divisional application of the application filed on September 25, 2024, with application number 202411340071.6 and invention name “A textile weaving process data monitoring system based on Internet of Things technology”. Technical Field

[0002] The present invention relates to the technical field of textile weaving process data monitoring technology, and in particular to a textile weaving process data monitoring system based on Internet of Things technology. Background Art

[0003] With the rapid development of Internet of Things (IoT) technology, its application in industrial manufacturing is becoming increasingly widespread. Data monitoring of the textile weaving process is a crucial step in achieving intelligent and automated production for textile companies. Image data can monitor the operating status of textile equipment and visual defects in fabrics in real time, while numerical data provides key performance indicators during the production process, helping to monitor equipment status and optimize production efficiency. By combining image and numerical data, comprehensive monitoring of the production process can be achieved, potential problems can be promptly identified, and production quality and efficiency can be improved. Therefore, the development of a data monitoring system for the textile weaving process based on IoT technology is of great significance.

[0004] The existing system collects data through sensors on textile equipment, then preprocesses the data, uses mathematical analysis methods to analyze the data, and finally uses the analysis results to monitor the textile weaving process data, thereby achieving accurate monitoring and control of the textile weaving process data.

[0005] For example, the patent application with publication number CN114280060A discloses a machine vision-based intelligent textile inspection system, which includes: a display screen, a central processing unit, a data transmission module, a detection and analysis module, an image processing module, an image acquisition module, a lighting control module, and an image comparison module. The lighting control module includes a fill light, and the image acquisition module includes an image collector. The machine vision-based intelligent textile inspection system described in the present invention belongs to the field of intelligent textile inspection. By using the coordinated use of the monitoring and analysis module, the image processing module, the image acquisition module, the image collector, the lighting control module, and the fill light, light is irradiated on the textile to enable the image collector to clearly collect information about the textile. The textile is then inspected through various subsequent modules and machine vision inspection methods, thereby replacing the manual inspection method.

[0006] For example, patent application publication number CN114371244A discloses a quality control method for testing banned azo dyes in textiles. The method involves preparing a stock solution of a banned azo dye at a certain concentration as a quality control sample, and then using GC-MS to detect the carcinogenic aromatic amines produced by the reduction and cleavage of the control sample. A sufficient amount of test data is accumulated to establish multi-rule quality control rules and control charts. The test results of any batch of quality control samples are then evaluated to determine the reliability of the test results of textiles tested along with the same batch of quality control samples.

[0007] However, in the process of implementing the technical solutions of the embodiments of the present application, the present application discovered that the above technology has at least the following technical problems:

[0008] In the existing technology, since textile weaving process data monitoring requires collecting images and numerical data of textile equipment during operation, the huge amount of data leads to data transmission delays and low data reliability, resulting in low efficiency of textile weaving process data monitoring. Summary of the Invention

[0009] The embodiment of the present application solves the problem of low efficiency of textile weaving process data monitoring in the prior art by providing a textile weaving process data monitoring system based on Internet of Things technology, thereby improving the efficiency of textile weaving process data monitoring.

[0010] An embodiment of the present application provides a textile weaving process data monitoring system based on Internet of Things technology, comprising: a data acquisition module, a data processing and analysis module, and a monitoring module; wherein the data acquisition module is used to collect first device data through sensors on textile equipment, compress the collected first device data to obtain compressed data, and the first device data is used to describe the textile manufacturing process performed by the textile equipment; the data processing and analysis module is used to receive the compressed data and decompress and preprocess the compressed data and then transmit it to the monitoring module through an edge computing node, wherein the preprocessing includes data cleaning and denoising; the monitoring module is used to compare the preprocessed first device data with the mean of historical textile equipment data to obtain an equipment data evaluation index, and compare the equipment data evaluation index with a preset threshold to obtain a result judgment, and trigger an alarm mechanism for an abnormal situation, wherein the historical textile equipment data includes historical textile equipment images and historical textile equipment numerical data.

[0011] Furthermore, the data acquisition module includes a compression unit and a data transmission unit; the compression unit is used to compress the collected first device data to obtain compressed data, and compare the first device data with the compressed data according to the data volume to obtain compression efficiency, and the compression efficiency is used to measure the compression effect of the first device data; the data transmission unit is used to transmit the compressed data to the data processing and analysis module via the transmission protocol HTTP, and the transmission protocol HTTP is used to improve the transmission efficiency of compressed data.

[0012] Furthermore, the data processing and analysis module includes a decompression unit, a first preprocessing unit, a second preprocessing unit and an edge computing node unit; the decompression unit is used to receive compressed data and decompress the compressed data to obtain second device data, and compare the first device data with the second device data to obtain a data compression index, and the data compression index is used to evaluate the compression accuracy of the first device data; the first preprocessing unit is used to determine a value range based on the mean and variance of the obtained second device data, and compare the second device data with the value range to obtain cleaned second device data, and the comparison is used to remove data in the second device data that is not within the value range; the second preprocessing unit is used to replace the cleaned second device data by a window average value to obtain third device data, and the window average value is obtained by performing a mean operation on the data in the cleaned second device data within the window, and the third device data is the preprocessed second device data;

[0013] The edge computing node unit is configured to encrypt the third device data by using a symmetric encryption method and store the third device data in the edge computing node, and transmit the stored third device data to the monitoring module within a preset time period.

[0014] Furthermore, the compressing the collected first device data to obtain compressed data includes data identification of the collected first device data, and the data identification represents adding an identification field to the first device data according to the data type.

[0015] Furthermore, the specific process of obtaining the compressed data is: constructing a compression dictionary based on the data frequency distribution in the first device data, and scanning the first device data through the compression dictionary, the compression dictionary includes an index table and a mark, and the mark contains a code for replacing the first device data; replacing the first device data with the mark in the compression dictionary to obtain compressed data, and the data replacement means replacing the data in the first device data with the mark.

[0016] Furthermore, the specific acquisition process of the second device data is: scanning the compressed data according to the compression dictionary, decompressing the compressed data to obtain the second device data; performing a ratio operation on the second device data and the compressed data according to the data volume, and the ratio operation is used to obtain the decompression efficiency to measure the decompression effect of the compressed data; obtaining the data compression coefficient according to the compression efficiency and decompression efficiency, and the data compression coefficient is used to measure the compression and decompression effects of the first device data.

[0017] Furthermore, the data compression coefficient is calculated using the following formula:

[0018] ;

[0019] Where T is the data compression coefficient, is the data volume of the first device data, is the amount of compressed data, is the amount of data on the second device, The weight parameter representing the compression efficiency, A weight parameter representing the decompression efficiency.

[0020] Furthermore, the specific process for obtaining the data compression index is as follows: the first device data is sequentially sorted to obtain a first device data sequence, and the second device data is sequentially arranged to obtain a second device data sequence, and the data compression index is obtained based on the first device data sequence and the second device data sequence. The data compression index is calculated using the following formula:

[0021] ;

[0022] Where R is the data compression index, n is the sequence number of the data element in the first device data sequence, , N is the total number of data elements in the first device data sequence, is the nth data element in the first device data sequence, is the nth data element in the second device data sequence, and e represents a natural constant.

[0023] Furthermore, the specific process for obtaining the equipment data evaluation index is as follows: the third equipment data is classified and sorted according to the data type to obtain textile equipment image data and numerical data, the image data is converted into an image, and the numerical data is arranged in sequence to obtain a numerical data sequence; the image and historical textile equipment images are calculated according to the MSE formula to obtain textile equipment image similarity data, and the equipment data evaluation index is obtained according to the ratio of the textile equipment image similarity data and the textile equipment numerical data sequence to the mean sequence of the numerical data of historical textile equipment. The equipment data evaluation index is calculated using the following formula:

[0024] ;

[0025] Among them, S is the device data evaluation index, i is the sequence number of the image, , G is the total number of images, is the image similarity data of the i-th image, q is the data element number in the textile equipment numerical data sequence in the third equipment data, , Q is the total number of data elements in the textile equipment numerical data sequence in the third equipment data, is the qth data element of the textile equipment numerical data sequence, is the qth data element in the mean value sequence of historical numerical data of textile equipment, is the image similarity data weight parameter, is a numerical data weight parameter, e represents a natural constant; the image similarity data weight parameter represents the degree of influence of the textile equipment image similarity data on the equipment data evaluation index; the numerical data weight parameter represents the degree of influence of the textile equipment numerical data on the equipment data evaluation index.

[0026] Furthermore, the specific triggering method of the alarm mechanism is as follows: determine whether the equipment data evaluation index is lower than a preset threshold value obtained from a preset database: if the equipment data evaluation index is lower than the preset threshold value, the alarm mechanism is triggered, and the alarm mechanism includes sending an alarm to stop the operation of the textile equipment and generating an abnormality analysis report, and the abnormality analysis report includes the comparison result of the equipment data evaluation index with the preset threshold value and the triggering alarm time; if the equipment data evaluation index is not lower than the preset threshold value, continue to monitor the equipment data evaluation index.

[0027] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0028] 1. The third device data is obtained by compressing, transmitting and preprocessing the first device data, and the third device data is encrypted and transmitted to the monitoring module through the edge computing node to compare with the mean of historical textile equipment data to obtain the device data evaluation index, thereby achieving improvements in data security and data transmission efficiency, and further achieving improvements in the efficiency of textile weaving process data monitoring, effectively solving the problem of low efficiency of textile weaving process data monitoring in the existing technology.

[0029] 2. The first device data contains all the data of the textile equipment during operation. The data volume is very large, which causes transmission delays during data transmission. The first device data is compressed and transmitted through dictionary compression, which significantly reduces the data volume, thereby reducing the network bandwidth usage and data packet loss risk during data transmission, thereby improving the efficiency of data transmission and the reliability of data during transmission.

[0030] 3. Through the alarm mechanism, the operation monitoring and management efficiency of textile equipment is improved, thereby achieving immediate response to abnormal situations and effectively reducing production downtime caused by equipment failure or abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of the structure of a textile weaving process data monitoring system based on Internet of Things technology provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of the structure of a data processing and analysis module in a textile weaving process data monitoring system based on Internet of Things technology provided in an embodiment of the present application;

[0033] Figure 3 This is a device data evaluation index diagram provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The embodiment of the present application solves the problem of low efficiency of textile weaving process data monitoring in the prior art by providing a textile weaving process data monitoring system based on Internet of Things technology. The data acquisition module collects first device data and compresses the first device data and transmits it to the data processing and analysis module. The data processing and analysis module decompresses and preprocesses the data to obtain third device data. The third device data is transmitted to the monitoring module through the edge computing node, and is compared and verified with the mean of historical textile equipment data to obtain an equipment data evaluation index, thereby improving the efficiency of textile weaving process data monitoring.

[0035] The technical solution in the embodiment of the present application is to solve the problem of low efficiency of data monitoring during the textile weaving process. The overall idea is as follows:

[0036] The equipment data is collected through the data acquisition module and the data is compressed and transmitted to the data processing and analysis module. At the same time, the data is decompressed and preprocessed through the data processing and analysis module to obtain the third equipment data. Finally, the third equipment data is compared and verified with the mean of historical textile equipment data to obtain the equipment data evaluation index, thereby improving the efficiency of data monitoring of the textile weaving process.

[0037] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] like Figure 1As shown, it is a structural schematic diagram of a textile weaving process data monitoring system based on the Internet of Things technology provided in an embodiment of the present application. The textile weaving process data monitoring system based on the Internet of Things technology provided in an embodiment of the present application includes: a data acquisition module, a data processing and analysis module and a monitoring module: wherein the data acquisition module is used to collect first device data through sensors on textile equipment, compress the collected first device data to obtain compressed data, and the first device data is used to describe the textile manufacturing process of the textile equipment; the data processing and analysis module is used to receive compressed data and decompress and pre-process the compressed data and then transmit it to the monitoring module through the edge computing node, and the pre-processing includes data cleaning and denoising; the monitoring module is used to compare the pre-processed first device data with the mean of historical textile equipment data to obtain an equipment data evaluation index, and compare the equipment data evaluation index with a preset threshold to obtain a result judgment, and trigger an alarm mechanism for abnormal situations, and the historical textile equipment data includes historical textile equipment images and historical textile equipment numerical data.

[0039] In this embodiment, the compressed data obtains a corresponding tag based on the compressed first device data, and the tag occupies less storage space than the first device data, saving storage space costs; the edge computing node is a transit station for storing data and encrypting data, and the third device data is encrypted and transmitted by a key generated by the symmetric encryption method in the edge computing node. When maintenance engineers maintain and troubleshoot textile equipment through remote access monitoring systems, the device status and control instructions transmitted during remote operations are protected to prevent them from being intercepted and used by criminals, which can effectively enhance data security and privacy protection, and timely trigger alarms based on abnormal conditions of the equipment data evaluation index to reduce the situation where abnormalities cause low production efficiency.

[0040] Furthermore, the data acquisition module includes a compression unit and a data transmission unit; the compression unit is used to compress the collected first device data to obtain compressed data, and compare the first device data with the compressed data according to the data volume to obtain the compression efficiency, and the compression efficiency is used to measure the compression effect of the first device data; the data transmission unit is used to transmit the compressed data to the data processing and analysis module through the transmission protocol HTTP, and the transmission protocol HTTP is used to improve the transmission efficiency of the compressed data.

[0041] In this embodiment, the transmission protocol (HyperText Transfer Protocol, HTTP) reduces the size of transmitted data through compression and expansion. Transmitting compressed data through the transmission protocol HTTP helps reduce bandwidth consumption and transmission delay during compressed data transmission, thereby improving data transmission efficiency.

[0042] Further, the data processing and analysis module comprises a decompression unit, a first preprocessing unit, a second preprocessing unit and an edge computing node unit; the decompression unit is configured to receive compressed data, decompress the compressed data to obtain second device data, and compare the first device data and the second device data to obtain a data compression index, the data compression index being used to evaluate the compression accuracy of the first device data; the first preprocessing unit is configured to determine a value range according to the mean and variance of the obtained second device data, and compare the second device data and the value range to obtain cleaned second device data, the comparison being used to remove data in the second device data that is not within the value range; the second preprocessing unit is configured to replace the cleaned second device data by a window average to obtain third device data, the window average being obtained by performing a mean operation on the data in the windowed cleaned second device data, the third device data being the preprocessed second device data; and the edge computing node unit is configured to encrypt the third device data by a symmetric encryption method, store the third device data in an edge computing node, and transmit the stored third device data to the monitoring module within a preset time period.

[0043] In the present embodiment, the window size can contain 10 data in the cleaned second device data according to the frequency of the data in the cleaned second device data, the window is moved according to the window size, the average of the data in the windowed cleaned second device data is calculated to obtain a window average, and the window average is used to replace the original data in the window, so that the data is cleaned and denoised by the first preprocessing unit and the second preprocessing unit to improve the quality and reliability of the data and ensure the accuracy of subsequent analysis.

[0044] Further, the first device data collected is compressed to obtain compressed data, and the first device data collected includes data identification, which indicates that a data type identification field is added to the first device data according to the data type.

[0045] In the present embodiment, the data type corresponding to the first device data collected by the sensor device is recorded as the data type identification field, the identification field is used to distinguish the data type of the first device data, and the data type is distinguished by the identification field, which helps to sort the third device data according to the data type and improves the data type identification efficiency.

[0046] Further, the specific acquisition process of the compressed data is as follows: a compression dictionary is constructed according to the frequency distribution of the data in the first device data, and the first device data is scanned by the compression dictionary, the compression dictionary comprises an index table and a marker, and the marker contains an encoding used to replace the first device data; the first device data is replaced by the marker in the compression dictionary to obtain the compressed data, and the data replacement means that the data in the first device data is replaced by the marker.

[0047] In this embodiment, the image in the first device data is read according to cv2.imread() in Python to obtain image pixel values, the image pixel values ​​are replaced with the image to obtain the processed first device data, a unique index and label are assigned to each data element in the processed first device data according to the data frequency in the processed first device data, and the labels are stored in a mapping table to obtain a compression dictionary, the processed first device data is scanned by the compression dictionary, each data element of the processed first device data is traversed, and each data element in the processed first device data is replaced with a corresponding label according to the index table in the compression dictionary, and the labels are output sequentially to obtain compressed data. By compressing the first device data, the amount of data can be significantly reduced, thereby reducing transmission time and transmission bandwidth, improving data processing efficiency and reducing network transmission costs.

[0048] Furthermore, the specific process of obtaining the second device data is as follows: scanning the compressed data according to the compression dictionary, decompressing the compressed data to obtain the second device data; performing a ratio operation on the second device data and the compressed data according to the data volume, and the ratio operation is used to obtain the decompression efficiency to measure the decompression effect of the compressed data; obtaining the data compression coefficient according to the compression efficiency and decompression efficiency, and the data compression coefficient is used to measure the compression and decompression effects of the first device data.

[0049] In this embodiment, the compressed data is scanned according to the mapping relationship in the compression dictionary, each tag of the compressed data is traversed, and the tags in the compressed data are replaced with the corresponding processed first device data elements according to the index table in the compression dictionary. The second device data is obtained by sequentially outputting the data elements, and the efficiency of data decompression is quantitatively evaluated through the results of the ratio operation, which helps to evaluate the performance of the decompression method.

[0050] Furthermore, the data compression coefficient is calculated using the following formula:

[0051] ;

[0052] Where T is the data compression coefficient, is the data volume of the first device data, is the amount of compressed data, is the amount of data on the second device, The weight parameter representing the compression efficiency, A weight parameter representing the decompression efficiency.

[0053] The algorithm of this embodiment combines the factors affecting compression and decompression efficiency and comprehensively analyzes to obtain the data compression coefficient. There is a correlation between the compression efficiency and decompression efficiency that affects the data compression coefficient, which indicates the overall data processing efficiency of the device. Comprehensive analysis can accurately obtain the data compression coefficient result.

[0054] In this embodiment, the calculation of the data compression coefficient T consists of two parts. The first part is , the compression efficiency is obtained by dividing the difference between the first device data and the compressed data by the first device data. The second part is , the decompression efficiency is obtained based on the comparison between the second device data and the compressed data, Affects compression efficiency, Affects decompression efficiency, Directly affects the compression coefficient. constant, Enlargement will lead to The value becomes smaller, the data compression efficiency of the first device decreases, and thus the data compression coefficient decreases; if constant, The increase will cause the weight parameter of the decompression efficiency to change, thereby affecting the overall compression coefficient value; the weight parameter of the compression efficiency constructs a mapping set of the compression efficiency deviation value and its corresponding weight parameter according to the relationship between the historical compression efficiency deviation value and the data compression coefficient, and the real-time compression efficiency deviation value is input into the mapping set to obtain the corresponding weight parameter of the compressed data, the weight parameter of the decompression efficiency constructs a mapping set of the decompression efficiency deviation value and its corresponding weight parameter according to the relationship between the historical decompression efficiency deviation value and the data compression coefficient, and the real-time decompression efficiency deviation value is input into the mapping set to obtain the corresponding weight parameter of the decompressed data, and the compression coefficient reflects the overall compression efficiency level of the first device data by comprehensively considering the compression and decompression efficiencies.

[0055] Furthermore, the specific process for obtaining the data compression index is as follows: the first device data is sequentially sorted to obtain a first device data sequence, and the second device data is sequentially arranged to obtain a second device data sequence. At the same time, the data compression index is obtained based on the first device data sequence and the second device data sequence. The data compression index is calculated using the following formula:

[0056] ;

[0057] Where R is the data compression index, n is the sequence number of the data element in the first device data sequence, , N is the total number of data elements in the first device data sequence, is the nth data element in the first device data sequence, is the nth data element in the second device data sequence, and e represents a natural constant.

[0058] The algorithm of the embodiment combines the similarity factors of the first device data sequence and the second device data sequence, and obtains the data compression index through comprehensive analysis. In the formula, the first device data sequence and the second device data sequence have data similarity correlation, which indicates the effect of the compression algorithm in retaining data quality, and comprehensive analysis can accurately obtain the result of the first device data compression efficiency.

[0059] In the embodiment, the data compression index R reflects the relative change degree between the independent variables and , the comparison verification difference G of the first device data sequence and the second device data sequence is defined, , which reflects the relative change degree between the independent variables and , and the similarity degree of the first device data sequence and the second device data sequence can be obtained through the value of G, thereby helping to judge the data compression effect; when N = 1, the data compression index statistical table is shown in Table 1:

[0060] Table 1 Data compression index statistical table

[0061]

[0062] As can be seen from Table 1, the data compression index R of the fifth group of data is the lowest, and the data compression effect is achieved. If the data compression index is higher than 0.066, it indicates that the comparison verification difference G of the first device data and the second device data is greater than 0.05, and the preset data compression effect is not achieved, and the compression method needs to be replaced, such as the Huffman coding or the Brotli compression algorithm. According to the data compression index, the compression effect of the first device data is obtained, thereby judging whether the data compression meets the standard, and helping to ensure the reliability and accuracy of the data in the process of compression storage and transmission.

[0063] Further, the specific acquisition process of the device data evaluation index is as follows: the third device data is classified and sorted according to the data type to obtain textile equipment image data and numerical data, the image data is converted into an image, and the numerical data is sequentially arranged to obtain a numerical data sequence; the textile equipment image similarity data is obtained by calculating the image and the historical textile equipment image according to the MSE formula, and the device data evaluation index is obtained according to the ratio of the textile equipment image similarity data and the numerical data sequence of the textile equipment to the average sequence of the numerical data of the historical textile equipment. The device data evaluation index is calculated by the following formula:

[0064] ;

[0065] Wherein, S is the device data evaluation index, i is the serial number of the image, , G is the total number of images, is the image similarity data of the i-th image, q is the data element number in the textile equipment numerical data sequence in the third equipment data, , Q is the total number of data elements in the textile equipment numerical data sequence in the third equipment data, is the qth data element of the textile equipment numerical data sequence, is the qth data element in the mean value sequence of historical numerical data of textile equipment, is the image similarity data weight parameter, is a numerical data weight parameter, e represents a natural constant; the image similarity data weight parameter represents the degree of influence of the textile equipment image similarity data on the equipment data evaluation index; the numerical data weight parameter represents the degree of influence of the textile equipment numerical data on the equipment data evaluation index.

[0066] In this embodiment, for example, in the process of producing bed sheets by textile equipment, the image of the textile equipment includes the shuttle image, the yarn image and the bed sheet image in the textile equipment, and the numerical data includes the operating speed of the textile equipment, the temperature and humidity of the production environment and the yarn density of the bed sheet. According to the MSE formula, the pixel mean square error of the textile equipment image and the corresponding historical textile equipment image is obtained to obtain the image similarity data; the numerical data ratio is obtained by comparing the collected numerical data with the mean of the numerical data of the corresponding historical textile equipment, and the equipment data evaluation index of the corresponding textile equipment in the process of making bed sheets is obtained by combining the image similarity data and the numerical data ratio, thereby evaluating the operation status of the textile equipment.

[0067] The algorithm of this embodiment combines image similarity data and numerical data factors, and comprehensively analyzes to obtain the device data evaluation index. In this formula, there is a factor correlation between the image similarity data and the numerical data sequence ratio that comprehensively affects the device evaluation index, indicating the influence of image similarity data and numerical data on the device data evaluation index. The comprehensive analysis can accurately obtain the result of the device evaluation index.

[0068] like Figure 3 As shown, the equipment evaluation index is positively correlated with the image similarity data and the ratio of the numerical data sequence. As the image similarity data and the ratio of the numerical data sequence continue to increase, the value of the equipment data evaluation index continues to increase, indicating that the operation of the textile equipment is less likely to be abnormal. If the equipment data evaluation index value is less than the preset threshold, it will be triggered to stop the operation of the textile equipment.

[0069] In this embodiment, the image data is processed and converted into an image according to Image.fromarray() in Python; the image and numerical data mean sequences of the historical textile equipment are obtained by performing mean operations on the textile equipment images and numerical data of the historical operation of the textile equipment stored in the preset database and outputting them in sequence, and the definition is It is the ratio of numerical data sequences, so the calculation of S consists of two parts. The first part is based on the textile equipment image similarity data in the third equipment data, and the second part is the ratio of the textile equipment numerical data sequences in the third equipment data. The two weight parameters are used to better evaluate the effect of the change in the operation of the textile equipment; the image similarity data weight parameters are a mapping set of image similarity data deviation values ​​and their corresponding weight parameters constructed according to the relationship between the historical textile equipment image similarity data deviation values ​​and the equipment data evaluation index, and the real-time image similarity data deviation values ​​are input into the mapping set to obtain the corresponding image similarity data weight parameters; the numerical data weight parameters are a mapping set of numerical data deviation values ​​and their corresponding weight parameters constructed according to the relationship between the historical textile equipment numerical data deviation values ​​and the equipment data evaluation index, and the real-time operation numerical data deviation values ​​are input into the mapping set to obtain the corresponding numerical data weight parameters; judging the equipment operation status through the equipment data evaluation index is helpful to improve the production efficiency of textile products and the stability of textile equipment operation.

[0070] Furthermore, the specific triggering method of the alarm mechanism is as follows: determine whether the equipment data evaluation index is lower than the preset threshold value obtained from the preset database: if the equipment data evaluation index is lower than the preset threshold value, the alarm mechanism is triggered, and the alarm mechanism includes sending an alarm to stop the operation of the textile equipment and generating an abnormality analysis report. The abnormality analysis report includes the comparison result of the equipment data evaluation index with the preset threshold value and the triggering alarm time; if the equipment data evaluation index is not lower than the preset threshold value, continue to monitor the equipment data evaluation index.

[0071] In this embodiment, the preset threshold is an equipment data evaluation index obtained based on the textile equipment images and textile equipment numerical data of the historical operation of the textile equipment stored in the preset database, and the alarm mechanism helps to respond to abnormal situations that may occur in the equipment in a timely manner.

[0072] To sum up, the embodiment of the present application obtains third device data by compressing, transmitting and preprocessing the first device data, and encrypts and transmits the third device data to the monitoring module through the edge computing node to compare with the mean of historical textile equipment data to obtain the device data evaluation index, thereby achieving improved data security and data transmission efficiency, and further achieving improved efficiency of textile weaving process data monitoring, effectively solving the problem of low efficiency of textile weaving process data monitoring in the prior art.

[0073] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0077] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0078] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A textile weaving process data monitoring system based on Internet of Things technology, characterized in that: Including data acquisition module, data processing and analysis module and monitoring module: The data acquisition module is configured to acquire first device data through sensors on the textile equipment and compress the acquired first device data to obtain compressed data, wherein the first device data is used to describe a textile manufacturing process performed by the textile equipment; The data processing and analysis module is used to receive compressed data and decompress and preprocess the compressed data before transmitting it to the monitoring module through the edge computing node. The preprocessing includes data cleaning and denoising. The monitoring module is used to compare the pre-processed first device data with the average of historical textile equipment data to obtain a device data evaluation index, and compare the device data evaluation index with a preset threshold to obtain a result judgment, and trigger an alarm mechanism if it is judged to be an abnormal situation, wherein the historical textile equipment data includes historical textile equipment images and historical textile equipment numerical data; The data processing and analysis module includes a decompression unit, a first preprocessing unit, a second preprocessing unit and an edge computing node unit; The decompression unit is configured to receive compressed data and decompress the compressed data to obtain second device data, and compare the first device data with the second device data to obtain a data compression index, wherein the data compression index is used to evaluate the compression accuracy of the first device data; and to determine the compression effect of the first device data based on the data compression index, thereby determining whether the data compression meets the requirements; The first preprocessing unit is configured to determine a value range based on the mean and variance of the acquired second device data, and compare the second device data with the value range to obtain cleaned second device data, wherein the comparison is used to remove data in the second device data that is not within the value range; The second preprocessing unit is configured to replace the cleaned second device data by a window average value to obtain third device data, wherein the window average value is obtained by performing a mean operation on the cleaned second device data within a window, and the third device data is the preprocessed second device data; The edge computing node unit is configured to encrypt the third device data by using a symmetric encryption method and store the third device data in the edge computing node, and transmit the stored third device data to the monitoring module within a preset time period; The specific process of obtaining the compressed data is as follows: constructing a compression dictionary based on a frequency distribution of data in the first device data, and scanning the first device data using the compression dictionary, wherein the compression dictionary includes an index table and a tag, wherein the tag includes a code for replacing the first device data; Performing data replacement on the first device data using the marker in the compression dictionary to obtain compressed data, wherein the data replacement means replacing the data in the first device data with the marker; The specific process of obtaining the second device data is as follows: Scanning the compressed data according to the compression dictionary, and decompressing the compressed data to obtain the second device data; performing a ratio operation on the second device data and the compressed data according to the data volume, wherein the ratio operation is used to obtain a decompression efficiency to measure the decompression effect of the compressed data; Obtaining a data compression coefficient based on the compression efficiency and the decompression efficiency, wherein the data compression coefficient is used to measure the effect of compression and decompression of the data on the first device; The data compression coefficient is calculated using the following formula: ； Where T is the data compression coefficient, is the data volume of the first device data, is the amount of compressed data, is the amount of data on the second device, The weight parameter representing the compression efficiency, A weight parameter representing the decompression efficiency.

2. The textile weaving process data monitoring system based on Internet of Things technology according to claim 1, characterized in that: The specific process of obtaining the data compression index is as follows: The first device data is sequentially sorted to obtain a first device data sequence, and the second device data is sequentially arranged to obtain a second device data sequence. At the same time, a data compression index is obtained based on the first device data sequence and the second device data sequence. The data compression index is calculated using the following formula: ； Where R is the data compression index, n is the sequence number of the data element in the first device data sequence, , N is the total number of data elements in the first device data sequence, is the nth data element in the first device data sequence, is the nth data element in the second device data sequence, and e represents a natural constant.

3. The textile weaving process data monitoring system based on Internet of Things technology according to claim 1, characterized in that: The data acquisition module includes a compression unit and a data transmission unit; The compression unit is configured to compress the collected first device data to obtain compressed data, and compare the first device data with the compressed data according to the data volume to obtain a compression efficiency, wherein the compression efficiency is used to measure the compression effect of the first device data; The data transmission unit is used to transmit the compressed data to the data processing and analysis module via the transmission protocol HTTP, and the transmission protocol HTTP is used to improve the transmission efficiency of the compressed data.

4. The textile weaving process data monitoring system based on Internet of Things technology according to claim 1, characterized in that: The compressing of the collected first device data to obtain compressed data includes data identification of the collected first device data, where the data identification represents adding an identification field to the first device data according to the data type.

5. The textile weaving process data monitoring system based on Internet of Things technology as claimed in claim 1, characterized in that: The specific process of obtaining the device data evaluation index is as follows: The third equipment data is classified and sorted according to data type to obtain textile equipment image data and numerical data, the image data is converted into an image, and the numerical data is arranged in sequence to obtain a numerical data sequence; the image and historical textile equipment images are calculated according to the MSE formula to obtain textile equipment image similarity data, and the equipment data evaluation index is obtained according to the ratio of the textile equipment image similarity data and the textile equipment numerical data sequence to the mean sequence of the numerical data of historical textile equipment. The equipment data evaluation index is calculated using the following formula: ； Among them, S is the device data evaluation index, i is the sequence number of the image, , G is the total number of images, is the image similarity data of the i-th image, q is the data element number in the textile equipment numerical data sequence in the third equipment data, , Q is the total number of data elements of the textile equipment numerical data sequence in the third equipment data, is the qth data element of the textile equipment numerical data sequence, is the qth data element in the mean value sequence of historical numerical data of textile equipment, is the image similarity data weight parameter, is the numerical data weight parameter, e represents a natural constant; The image similarity data weight parameter represents the degree of influence of the textile equipment image similarity data on the equipment data evaluation index; The numerical data weight parameter represents the degree of influence of the numerical data of the textile equipment on the equipment data evaluation index.

6. The textile weaving process data monitoring system based on Internet of Things technology as claimed in claim 1, characterized in that: The specific triggering method of the alarm mechanism is as follows: Determine whether the device data evaluation index is lower than the preset threshold obtained from the preset database: If the equipment data evaluation index is lower than a preset threshold, an alarm mechanism is triggered, which includes sending an alarm to stop the operation of the textile equipment and generating an abnormality analysis report, which includes a comparison result of the equipment data evaluation index with the preset threshold and the time when the alarm was triggered; If the device data evaluation index is not lower than the preset threshold, the device data evaluation index continues to be monitored.

Images