Yarn quality detection system, method and device

Abstract

The present invention relates to the technical field of yarn detection, and specifically discloses a yarn quality detection system, method and equipment. Shooting parameter information is adjusted based on yarn quality standards and external configuration information, and original image data of yarn in a production process is collected in real time using a high-speed camera corresponding to the shooting parameter information. The original image data is processed to obtain yarn feature information, wherein the yarn feature information includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knots; based on the yarn feature information, defects on the yarn surface are classified to obtain yarn defect categories; based on the yarn defect category, defect abnormal areas on the enhanced image are identified, and statistical analysis is performed on the defect abnormal areas to generate a quality detection report, and the quality detection report is transmitted to a control module and a display alarm module.

Description

Technical Field

[0001] The present invention relates to the technical field of yarn detection, and more specifically, to a yarn quality detection system, method and equipment. Background Art

[0002] In the textile industry, the quality of yarn directly affects the quality of the final product. However, traditional yarn quality testing methods usually rely on manual testing, which is not only inefficient but also inaccurate. Although some existing automated testing systems can partially replace manual testing, they still have shortcomings in detection accuracy and comprehensiveness.

[0003] For example, the Chinese patent publication number CN118464937A discloses a method for analyzing the appearance quality of semi-spun yarn based on image feature recognition. The target finished product image is pre-processed by image grayscale and binarization, and an image coordinate system is constructed to obtain the coordinates of each pixel in each target finished product image, thereby obtaining the yarn appearance quality and analyzing the yarn appearance quality problem from multiple aspects. However, the following problems still exist:

[0004] 1. In practical applications, grayscale processing of images will weaken the judgment of yarn color, or the judgment of yarn color is carried out through other detection means, which requires additional detection elements and complicates the yarn analysis process.

[0005] 2. Some information can be weakened or enhanced in the binarization preprocessing. Regardless of whether it is weakening or enhancing means, it may cause the original image to be too bright or too blurred, resulting in inaccurate and unreliable detection image data. In addition, for hairiness defects and knot defects, the pixel difference is too large during the processing process, resulting in the originally hidden or inconspicuous defects being magnified, resulting in the appearance quality assessment results being unscientific and unreliable.

[0006] In view of this, the present invention provides a yarn quality detection system, method and equipment to solve the above problems. Summary of the invention

[0007] In order to overcome the problems in the prior art, the present invention provides a yarn quality detection system, method and equipment.

[0008] In a first aspect, the present invention provides a yarn quality detection system, comprising an image acquisition module, an image processing module, a data analysis module, a control module and a display alarm module, wherein the modules are connected to each other by wire or wirelessly;

[0009] An image acquisition module adjusts shooting parameter information based on yarn quality standards and external configuration information, uses a high-speed camera corresponding to the shooting parameter information to collect original image data of the yarn in the production process in real time, and transmits the original image data to an image processing module;

[0010] The image processing module processes the original image data to obtain yarn characteristic information, wherein the yarn characteristic information includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knots; and transmits the yarn characteristic information to the data analysis module:

[0011] A data analysis module, which classifies the defects on the yarn surface based on the yarn feature information to obtain the yarn defect category; identifies the abnormal defect area on the enhanced image based on the yarn defect category, performs statistical analysis on the abnormal defect area to generate a quality inspection report, and transmits the quality inspection report to the control module and the display alarm module;

[0012] The control module adjusts the parameters of the production equipment in real time based on the quality inspection report to achieve dynamic optimization of yarn production quality and ensure yarn quality;

[0013] The display alarm module is used to display real-time test data and quality test reports, and send out an alarm signal when quality problems are found.

[0014] As a first aspect of the present invention, a preferred technical solution is provided. The acquisition logic of the shooting parameter information is as follows: As a first aspect of the present invention, a preferred technical solution is provided. The denoising processing method is a Gaussian filtering algorithm. The Gaussian filtering algorithm includes:

[0015] The external configuration information includes shooting environment information, yarn movement data and shooting reference information. The same yarn quality standards and external configuration information are traversed and queried from the historical database, and the yarn image with the highest definition is selected as the yarn comparison image;

[0016] Compare and analyze the clarity of the yarn image taken by the high-speed camera and the corresponding yarn comparison image:

[0017] If the yarn image clarity does not meet the preset conditions, repair or replace the high-speed camera and light source components;

[0018] If the clarity of the yarn image meets the preset conditions, the shooting parameter information of the high-speed camera is adaptively adjusted according to the yarn thickness and yarn movement data, so that the shooting frequency of the high-speed camera is synchronized with the yarn movement data. The shooting parameter information includes the focal length of the high-speed camera, the field of view of the lens, the image acquisition time frame and the brightness of the light source component.

[0019] As a first aspect of the present invention, a preferred technical solution is provided, in which the processing logic of the original image data is:

[0020] Step A1: marking the pixel value difference before and after the shooting reference information as noise influence information, and performing denoising processing on the original image data after the noise influence information is removed to obtain pre-processed image data;

[0021] Step A2: note the yarn material in advance, and determine the current yarn color and yarn thickness based on the pixel value of the preprocessed image data;

[0022] Step A3: Use the Canny edge detection algorithm to process the preprocessed image data to obtain the binary image, gradient amplitude and gradient direction after edge detection. The binary image is combined with the gradient direction to perform connected domain analysis to obtain the connected domain. According to the size, shape and distribution characteristics of the connected domain, the hairiness area is identified.

[0023] Step A4: using a morphological dilation operation to process the original image to obtain a dilated image, and performing a morphological erosion operation on the original image to obtain an eroded image; performing a pixel-by-pixel subtraction operation on the dilated image and the eroded image to obtain a differential image, and identifying an area with significant brightness as a defect area based on the brightness distribution of the differential image;

[0024] Step A5: Superimpose the gradient amplitude onto the preprocessed image to obtain an enhanced image, traverse the historical pixel information table corresponding to the yarn material in the historical database, and compare and analyze the pixel information of the enhanced image with the historical pixel information table to obtain the fiber uniformity of the current yarn.

[0025] As a first aspect of the present invention, a preferred technical solution is provided, in which the denoising process is performed by a Gaussian filtering algorithm, and the Gaussian filtering algorithm includes: ,

[0026] in: Represents the coordinate position in the original image data; Indicates the original image data after Gaussian filtering The pixel value at the coordinate position, represents the filter window size, Indicates the coordinate position of the original image data The relative filter removes the pixel value corresponding to the center coordinate of the Gaussian kernel. Represents the center coordinates of the Gaussian kernel set by the filter itself The degree of filtering is determined by convolving the normalized Gaussian kernel with the original image data to remove the original image data that affects the information.

[0027] As a first aspect of the present invention, a preferred technical solution is provided, wherein the binary processing logic:

[0028] Two thresholds are set for the pixel values ​​of the preprocessed image data to distinguish strong edges from weak edges, and the thresholds include a high threshold and a low threshold;

[0029] The edges detected by the Canny edge detection algorithm are marked as strong edges if the pixel values ​​of the edge points of the image are higher than the high threshold.

[0030] The edges that are higher than the low threshold but lower than the high threshold are marked as weak edges. If the weak edge is connected to the strong edge, it is retained. Otherwise, the weak edge is removed to obtain a binary image.

[0031] The edge area of ​​the binary image is obtained through the connected domain algorithm, and the hairiness area is extracted based on the morphological characteristics of the edge area to obtain the number and length of the hairiness.

[0032] As a first aspect of the present invention, a preferred technical solution is provided, wherein the data analysis logic of the quality problem is:

[0033] Step B1: Determine the yarn defect category based on the yarn feature information, and represent the yarn defect category by a vector: , represents the total amount of yarn defect categories, , indicating that the yarn defect categories include color difference, fiber unevenness, hairiness and knots;

[0034] Step B2: using the predefined yarn standard feature information, the yarn feature information is compared and matched with the yarn standard feature information to obtain a matching score, and the normal area and abnormal area of ​​the yarn surface are divided based on the matching score, and the number of normal areas and the number of abnormal areas are statistically analyzed to obtain quality problems corresponding to different yarn defect categories;

[0035] Step B3: Summarize the quality problems to generate a quality inspection report, which includes inspection parameters, judgment results, quality trend analysis and suggestion feedback.

[0036] As a first aspect of the present invention, a preferred technical solution is provided, wherein the control module includes the design of control strategy, the processing of real-time feedback and the interactive operation of production equipment, and the specific contents are as follows:

[0037] Design of control strategy: Based on the PID controller, different quality problems are controlled and adjusted in sequence. Specifically, the severity of the quality problem determines the order of adjustment. Different quality problems are solved by adjusting the parameters of different production equipment. The PID controller minimizes the detected quality deviation through closed-loop control, so that the yarn quality is stable within the preset standard range, thus achieving the stability of yarn quality.

[0038] Real-time feedback processing: The control strategy designed based on the quality inspection report is fed back in real time, and the parameters of the production equipment are adjusted based on the control strategy; the adjusted production equipment continues to produce the yarn, and the yarn analyzes the quality inspection report obtained, and the quality inspection report is fed back in real time;

[0039] Production equipment interaction: signal transmission of detection signals on production equipment, control of the execution of adjustment instructions of production equipment, and monitoring of production equipment status.

[0040] In a second aspect, the present invention provides a yarn quality detection method, based on the implementation of the first aspect, comprising the following steps:

[0041] Adjust the shooting parameter information based on the yarn quality standard and the external configuration information, and use the high-speed camera corresponding to the shooting parameter information to collect the original image data of the yarn in the production process in real time;

[0042] The original image data is processed to obtain yarn feature information, which includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knot defects:

[0043] Based on the yarn feature information, the defects on the yarn surface are classified to obtain the yarn defect category; based on the yarn defect category, the defect abnormal area on the enhanced image is identified, and the defect abnormal area is statistically analyzed to generate a quality inspection report;

[0044] Adjust the parameters of production equipment in real time based on quality inspection reports to achieve dynamic optimization of yarn production quality and ensure yarn quality;

[0045] It is used to display real-time inspection data and quality inspection reports, and send out alarm signals when quality problems are found.

[0046] In a third aspect, the present invention provides a yarn quality detection device, comprising:

[0047] at least one image acquisition module;

[0048] At least one display alarm module;

[0049] at least one processor; and,

[0050] A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the system of the first aspect.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the system of the first aspect.

[0052] The specific advantages of the present invention are as follows:

[0053] The present invention can collect and process the original image data of yarn in real time, and timely discover the quality problems in the production process; detect various yarn feature information through the image processing module, automatically classify and statistically analyze the yarn defects, generate a quality inspection report, and reduce the time and energy of manual analysis. And adjust the production equipment parameters in real time according to the quality inspection report, through timely detection and adjustment, realize the dynamic optimization of the production process, improve the production efficiency and product quality, ensure the continuity of production, significantly improve the automation level of yarn production, ensure product quality, reduce production costs, and enhance the market competitiveness of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a structural schematic diagram of the yarn quality detection system of the present invention;

[0055] Figure 2 This is a schematic diagram of the installation of the yarn quality detection area component of the present invention;

[0056] Figure 3 It is a schematic diagram of the yarn quality detection method of the present invention;

[0057] Figure 4 It is a schematic diagram of the image processing method flow of the present invention;

[0058] Figure 5 It is a schematic diagram of the image analysis method of the present invention;

[0059] Figure 6 It is a schematic diagram of the structure of the yarn quality detection equipment of the present invention.

[0060] In the figure: 1. Image acquisition module; 2. Image processing module; 3. Data analysis module; 4. Control module; 5. Display alarm module;

[0061] 101. Detection area; 102. High-speed camera; 103. Light source assembly; 104. Reference object; 600. Yarn transmission device. DETAILED DESCRIPTION

[0062] 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.

[0063] Example 1: Please refer to Figure 1, the present invention provides a technical solution: a yarn quality detection system, including an image acquisition module 1, an image processing module 2, a data analysis module 3, a control module 4 and a display alarm module 5, and each module is connected by wire or wireless;

[0064] The image acquisition module 1 adjusts the shooting parameter information based on the yarn quality standard and the external configuration information, uses the high-speed camera 102 corresponding to the shooting parameter information to collect the original image data of the yarn in the production process in real time, and transmits the original image data to the image processing module 2;

[0065] Specifically, the logic for obtaining the shooting parameter information is as follows:

[0066] Given the yarn quality standard and external configuration information, the yarn image with the highest definition is matched from the historical database as the yarn comparison image;

[0067] It should be noted that: the yarn image with the highest matching clarity of the same yarn quality standard and external configuration information is selected in the historical database as the yarn comparison image;

[0068] The yarn image captured by the high-speed camera 102 is compared with the yarn comparison image:

[0069] If the yarn image clarity does not meet the preset conditions, the high-speed camera 102 and the light source assembly 103 are repaired or replaced;

[0070] If the clarity of the yarn image meets the preset conditions, the shooting parameter information of the high-speed camera 102 is adaptively adjusted according to the yarn thickness and yarn movement data to ensure that it can accurately focus on the yarn surface and cover the entire width of the yarn; the shooting parameter information includes the focal length of the high-speed camera 102, the lens field of view, the image acquisition time frame and the brightness of the light source assembly 103;

[0071] Specifically, according to the yarn movement data and detection requirements, the exposure time, frame rate and brightness of the light source of the high-speed camera 102 are dynamically adjusted, and the shooting frequency of the high-speed camera 102 is synchronized with the movement of the yarn. The working frequency of the high-speed camera 102 is adjusted accordingly to achieve synchronous acquisition and ensure the quality of image acquisition;

[0072] The high-speed camera 102: an industrial-grade high-speed camera 102 with a high frame rate is used, and the resolution should reach the level of megapixels to ensure that clear original image information can still be obtained when the yarn moves at high speed. The high-speed camera 102 transmits the extracted original image information to the image processing module 2 in real time and without delay through a data transmission interface; the data transmission interface includes one of GigE, USB 3.0 or Camera Link interface;

[0073] The external configuration information includes shooting environment information, yarn movement data and shooting reference information. The shooting environment information includes the position information corresponding to the high-speed camera 102 and the light source assembly 103. In factory production, the high-speed camera 102 and the light source assembly 103 are fixed according to the best shooting effect; Figure 2 As shown, a detection area 101 is constructed on the yarn transmission device 600 corresponding to the production equipment, and a high-speed camera 102 is arranged on the detection area 101. The light source assembly 103 is evenly distributed around the high-speed camera 102. The light source assembly 103 adopts diffuse light or annular light illumination to ensure that each part of the yarn can be fully illuminated. For the case where the yarn surface is smoother, a polarized light source is added to reduce the influence of surface reflection and avoid shadow and reflection interference.

[0074] The yarn transmission device 600 needs to maintain a normal speed to move forward during yarn transmission. Generally, the yarn movement data is at a uniform speed. If there is a change, it is likely that the yarn transmission device 600 has an abnormality. A reference object 104 is set in the shooting area of ​​the high-speed camera 102. The data of the reference object 104 obtained by the high-speed camera 102 is marked as shooting reference information. The reference object 104 and the yarn transmission device 600 are on the same horizontal plane. When the yarn image captured by the high-speed camera 102 is abnormal, the degree of abnormality of the original image data can be inferred based on the degree of abnormality of the shooting reference information, that is, the difference in the yarn shooting environment is weakened by external configuration information.

[0075] Image processing module 2 processes the original image data to obtain yarn feature information, wherein the yarn feature information includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knots; and transmits the yarn feature information to data analysis module 3:

[0076] Specifically, if Figure 4 As shown, the processing logic of the original image data is:

[0077] Step A1: Mark the pixel value difference before and after the reference information is shot as noise impact information, and perform denoising on the original image data after the noise impact information is removed to obtain pre-processed image data; the denoising method is a Gaussian filtering algorithm, and the Gaussian filtering algorithm includes: (1)

[0078] in: Represents the coordinate position in the original image data; Indicates the original image data after Gaussian filtering The pixel value at the coordinate position, represents the filter window size, Indicates the coordinate position of the original image data The relative filter removes the pixel value corresponding to the center coordinate of the Gaussian kernel. Represents the center coordinates of the Gaussian kernel set by the filter itself The degree of filtering is determined by convolving the normalized Gaussian kernel with the original image data to remove the original image data that affects the information.

[0079] Step A2: note the yarn material in advance, and determine the current yarn color and yarn thickness based on the pixel value of the preprocessed image data;

[0080] Step A3: Use the Canny edge detection algorithm to process the preprocessed image data to obtain a binary image after edge detection, perform connected domain analysis on the binary image to obtain a connected domain, and identify the hairiness area based on the size, shape and distribution characteristics of the connected domain.

[0081] It should be noted that the hairiness area is smaller and more dispersed than the main edge area of ​​the yarn. Each hairiness area corresponds to a yarn hairiness. The number of hairiness areas is counted, that is, the total number of hairinesses, and the length of each hairiness area is measured.

[0082] Specifically, the Canny edge detection algorithm includes: ,

[0083] in: represents the gradient magnitude of the preprocessed image data, and Indicates the preprocessed image data in Axis and The gradient in the axis direction;

[0084] Based on the Canny edge detection algorithm, the gradient amplitude and gradient direction of the preprocessed image data are detected, the edge points are determined based on the gradient amplitude and gradient direction, and the edge points are binarized to obtain a binary image. The binarization process includes: setting two thresholds for the pixel values ​​of the preprocessed image data to distinguish strong edges from weak edges, and the thresholds include a high threshold and a low threshold; marking edges above the high threshold as strong edges, and marking edges above the low threshold but below the high threshold as weak edges. The weak edges are retained when they are connected to the strong edges, otherwise the weak edges are removed, thereby obtaining a binary image;

[0085] Connected domain algorithms include: ,

[0086] in: Represents the image pixel value after edge detection algorithm processing, Pixel neighborhood; obtaining the edge region through the connected domain algorithm, extracting the hairiness region based on the morphological characteristics of the edge region, and obtaining the number and length of the hairiness;

[0087] Step A4: using a morphological dilation operation to process the original image to obtain a dilated image, and performing a morphological erosion operation on the original image to obtain an eroded image; performing a pixel-by-pixel subtraction operation on the dilated image and the eroded image to obtain a differential image, and identifying an area with significant brightness as a defect area based on the brightness distribution of the differential image;

[0088] It should be noted that the dilation operation can enhance the bright areas in the image and make the defects more obvious; the erosion operation can eliminate small protrusions and help highlight larger irregular shapes. The bright spots in the differential image represent irregular protrusions or depressions in the original image. The specific location and size of the defects can be determined through connected domain analysis.

[0089] Specifically, the morphological processing algorithm formula is: ;

[0090] in: is the pixel value of the dilated image, is the pixel value of the eroded image, For differential images, the specific location and size of the defects can be identified by analyzing the brightness distribution of the differential images;

[0091] Step A5: superimpose the gradient amplitude onto the preprocessed image to obtain an enhanced image, traverse the historical pixel information table corresponding to the yarn material in the historical database, compare and analyze the pixel information of the enhanced image and the historical pixel information table to obtain the fiber uniformity of the current yarn;

[0092] The fiber uniformity is determined by counting the variance of the pixel value distribution corresponding to the cross-sectional area intercepted by the yarn detection. The fiber uniformity formula is: ,

[0093] in, represents the total number of sample points, , represents the average cross-sectional area, Indicates The sample points correspond to the cross-sectional area of ​​the yarn. , ; Indicates uniformity. The smaller the uniformity, the more uniform the fiber distribution of the yarn.

[0094] The data analysis module 3 classifies the defects on the yarn surface based on the yarn feature information to obtain the yarn defect category; identifies the abnormal defect area on the enhanced image based on the yarn defect category, performs statistical analysis on the abnormal defect area to generate a quality inspection report, and transmits the quality inspection report to the control module 4 and the display alarm module 5;

[0095] Specifically, if Figure 5As shown, the data analysis logic of the quality problem is:

[0096] Step B1: Determine the yarn defect category based on the yarn feature information, and represent the yarn defect category by a vector: , represents the total amount of yarn defect categories, , indicating that the yarn defect categories include color difference, fiber unevenness, hairiness and knots;

[0097] Step B2: using the predefined yarn standard feature information, the yarn feature information is compared and matched with the yarn standard feature information to obtain a matching score, and the normal area and abnormal area of ​​the yarn surface are divided based on the matching score, and the number of normal areas and the number of abnormal areas are statistically analyzed to obtain quality problems corresponding to different yarn defect categories;

[0098] Specifically, the statistical analysis includes calculating the mean, variance, skewness and kurtosis, obtaining statistical indicators based on the statistical analysis, and reflecting the overall situation of the yarn quality based on the statistical indicators; specifically including:

[0099] Mean: It is used to reflect the average level of yarn characteristic information. The mean of fiber uniformity can indicate the overall consistency of the yarn.

[0100] Variance: It is used to measure the degree of dispersion of yarn characteristic information. The smaller the variance, the more stable the yarn quality. The larger the variance, the greater the fluctuation of yarn quality and the higher the unevenness.

[0101] Skewness: It is used to measure the symmetry of data distribution. Skewness can help identify the distribution characteristics of local convexities or concavities in the yarn: it can help check whether there are obvious local unevenness in the yarn;

[0102] Kurtosis: It is used to measure the sharpness of the data distribution. A higher kurtosis may mean that there are obvious knots in the yarn: It measures the sharpness of the data distribution. If the data distribution has a sharp peak, it means that there are prominent knots or hairiness in the yarn. A higher kurtosis means that there are significant defects on the yarn surface.

[0103] The formula for the matching score is: ,

[0104] in, is the yarn characteristic information, is the yarn standard characteristic information, The matching score is the matching threshold. The matching score is used to determine whether the yarn has defects. When the number of defects is small, the formula matching calculation is fast and efficient.

[0105] In real-time yarn detection, it may be necessary to use machine learning algorithms for classification to determine quality standards. Specifically, support vector machines are used to train different yarn feature information to automatically identify different types of quality problems. The yarn feature information is used as input information, and the quality problems of the current enhanced image are identified and output through the judgment function of the classifier.

[0106] Step B3: Summarize the quality issues and generate a quality inspection report, which includes inspection parameters, determination results, quality trend analysis and suggestion feedback:

[0107] Detection parameters: List all detected yarn feature information and their corresponding statistical data;

[0108] Determination result: According to the preset quality standards, the system will indicate in the report whether each parameter is qualified and the comprehensive quality assessment results;

[0109] Quality trend analysis: If the test is carried out continuously, the report will also show the trend graph of yarn quality to help users analyze the quality changes;

[0110] Suggestion feedback: For unqualified yarn, the system will generate corresponding improvement suggestions.

[0111] Control module 4 adjusts the parameters of production equipment in real time based on the quality inspection report to achieve dynamic optimization of yarn production quality and ensure yarn quality;

[0112] Specifically, the control module 4 includes the design of control strategy, the processing of real-time feedback and the interactive operation of production equipment, and the specific contents are as follows:

[0113] Design of control strategy: Based on the PID controller, different quality problems are controlled and adjusted in sequence. Specifically, the severity of the quality problem determines the order of adjustment. Different quality problems are solved by adjusting the parameters of different production equipment. The PID controller minimizes the detected quality deviation through closed-loop control, so that the yarn quality is stable within the preset standard range, thus achieving the stability of yarn quality.

[0114] Real-time feedback processing: The control strategy designed based on the quality inspection report is fed back in real time, and the parameters of the production equipment are adjusted based on the control strategy; the adjusted production equipment continues to produce the yarn, and the yarn analyzes the quality inspection report obtained, and the quality inspection report is fed back in real time;

[0115] Production equipment interaction: signal transmission of detection signals on production equipment, control of the execution of adjustment instructions of production equipment, and monitoring of production equipment status.

[0116] The display alarm module 5 is used to display real-time detection data and quality detection reports, and to send out an alarm signal when quality problems are found.

[0117] Specifically, the display alarm module 5 specifically includes the following functions:

[0118] Display of real-time detection data: responsible for visualizing the yarn quality data detected in real time, which is used by operators to monitor various key indicators in the production process; in addition to real-time data, the display module provides a playback function for historical data, allowing operators to review quality data for a specific time period, analyze the root causes of yarn quality problems or evaluate the effectiveness of control measures;

[0119] Function of the alarm system: When the yarn quality is detected to be abnormal or exceeds the preset standard, the alarm module will immediately send a signal to prompt the operator to check and handle it; different types of alarms are set with different priorities, allowing operators to give priority to the most urgent problems.

[0120] Example 2

[0121] like Figure 3 As shown, the part not described in detail in this embodiment is as shown in Example 1. This embodiment provides a yarn quality detection method, comprising the following steps:

[0122] Adjusting the shooting parameter information based on the yarn quality standard and the external configuration information, and using the high-speed camera 102 corresponding to the shooting parameter information to collect the original image data of the yarn in the production process in real time;

[0123] The original image data is processed to obtain yarn feature information, which includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knot defects:

[0124] Based on the yarn feature information, the defects on the yarn surface are classified to obtain the yarn defect category; based on the yarn defect category, the defect abnormal area on the enhanced image is identified, and the defect abnormal area is statistically analyzed to generate a quality inspection report;

[0125] Adjust the parameters of production equipment in real time based on quality inspection reports to achieve dynamic optimization of yarn production quality and ensure yarn quality;

[0126] It is used to display real-time inspection data and quality inspection reports, and send out alarm signals when quality problems are found.

[0127] The logic for obtaining the shooting parameter information:

[0128] Given the yarn quality standard and external configuration information, the yarn image with the highest definition is matched from the historical database as the yarn comparison image;

[0129] The yarn image captured by the high-speed camera 102 is compared with the yarn comparison image:

[0130] If the yarn image clarity does not meet the preset conditions, the high-speed camera 102 and the light source assembly 103 are repaired or replaced;

[0131] If the clarity of the yarn image meets the preset conditions, the shooting parameter information of the high-speed camera 102 is adaptively adjusted according to the yarn thickness and yarn movement data, and the shooting parameter information includes the focal length of the high-speed camera 102, the lens field of view, the image acquisition time frame and the brightness of the light source assembly 103.

[0132] The processing logic of the original image data is as follows:

[0133] Step A1: marking the pixel value difference before and after the shooting reference information as noise influence information, and performing denoising processing on the original image data after the noise influence information is removed to obtain pre-processed image data;

[0134] Step A2: note the yarn material in advance, and determine the current yarn color and yarn thickness based on the pixel value of the preprocessed image data;

[0135] Step A3: Use the Canny edge detection algorithm to process the preprocessed image data to obtain a binary image, gradient amplitude and gradient direction after edge detection, perform connected domain analysis on the binary image to obtain a connected domain, and identify the hairiness area based on the size, shape and distribution characteristics of the connected domain;

[0136] Step A4: using a morphological dilation operation to process the original image to obtain a dilated image, and performing a morphological erosion operation on the original image to obtain an eroded image; performing a pixel-by-pixel subtraction operation on the dilated image and the eroded image to obtain a differential image, and identifying an area with significant brightness as a defect area based on the brightness distribution of the differential image;

[0137] Step A5: Superimpose the gradient amplitude onto the preprocessed image to obtain an enhanced image, traverse the historical pixel information table corresponding to the yarn material in the historical database, and compare and analyze the pixel information of the enhanced image with the historical pixel information table to obtain the fiber uniformity of the current yarn.

[0138] The denoising method is a Gaussian filtering algorithm, which includes: ,

[0139] in: Represents the coordinate position in the original image data; Indicates the original image data after Gaussian filtering The pixel value at the coordinate position, represents the filter window size, Indicates the coordinate position of the original image data The relative filter removes the pixel value corresponding to the center coordinate of the Gaussian kernel. Represents the center coordinates of the Gaussian kernel set by the filter itself The degree of filtering is determined by convolving the normalized Gaussian kernel with the original image data to remove the original image data that affects the information.

[0140] The binary processing logic:

[0141] Two thresholds are set for the pixel values ​​of the preprocessed image data to distinguish strong edges from weak edges, and the thresholds include a high threshold and a low threshold;

[0142] The edges detected by the Canny edge detection algorithm are marked as strong edges if the pixel values ​​of the edge points of the image are higher than the high threshold.

[0143] The edges that are higher than the low threshold but lower than the high threshold are marked as weak edges. If the weak edge is connected to the strong edge, it is retained. Otherwise, the weak edge is removed to obtain a binary image.

[0144] The edge area of ​​the binary image is obtained through the connected domain algorithm, and the hairiness area is extracted based on the morphological characteristics of the edge area to obtain the number and length of the hairiness.

[0145] The data analysis logic of the quality issues mentioned above:

[0146] Step B1: Determine the yarn defect category based on the yarn feature information, and represent the yarn defect category by a vector: , represents the total amount of yarn defect categories, , indicating that the yarn defect categories include color difference, fiber unevenness, hairiness and knots;

[0147] Step B2: using the predefined yarn standard feature information, the yarn feature information is compared and matched with the yarn standard feature information to obtain a matching score, and the normal area and abnormal area of ​​the yarn surface are divided based on the matching score, and the number of normal areas and the number of abnormal areas are statistically analyzed to obtain quality problems corresponding to different yarn defect categories;

[0148] Step B3: Summarize the quality problems to generate a quality inspection report, which includes inspection parameters, judgment results, quality trend analysis and suggestion feedback.

[0149] The control module includes the design of control strategy, the processing of real-time feedback and the interactive operation of production equipment. The specific contents are as follows:

[0150] Design of control strategy: Based on the PID controller, different quality problems are controlled and adjusted in sequence. Specifically, the severity of the quality problem determines the order of adjustment. Different quality problems are solved by adjusting the parameters of different production equipment. The PID controller minimizes the detected quality deviation through closed-loop control, so that the yarn quality is stable within the preset standard range, thus achieving the stability of yarn quality.

[0151] Real-time feedback processing: The control strategy designed based on the quality inspection report is fed back in real time, and the parameters of the production equipment are adjusted based on the control strategy; the adjusted production equipment continues to produce the yarn, and the yarn analyzes the quality inspection report obtained, and the quality inspection report is fed back in real time;

[0152] Production equipment interaction: signal transmission of detection signals on production equipment, control of the execution of adjustment instructions of production equipment, and monitoring of production equipment status.

[0153] Example 3

[0154] The part of the present invention not described in detail is as described in Example 1. This embodiment provides a yarn quality detection device, at least one image acquisition module 1;

[0155] At least one display alarm module 5;

[0156] at least one processor; and,

[0157] A memory is communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute to implement a yarn quality detection system.

[0158] Figure 6 It is an electronic framework diagram of a yarn quality detection device provided in an embodiment of the present application. The yarn quality detection device may have relatively large differences due to different configurations or performances, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement a yarn quality detection device provided in the above-mentioned various method embodiments.

[0159] The yarn quality detection device can also include other components for realizing the functions of the device, for example, the yarn quality detection device can also have components such as a wired or wireless network interface and an input / output interface for input and output. The embodiments of the present application are not described in detail here.

[0160] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0161] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0162] Example 4

[0163] According to an exemplary embodiment, a computer-readable storage medium is shown, on which a rewritable computer program is stored;

[0164] When the computer program is run on a computer device, the computer device is enabled to execute the above-mentioned yarn quality detection system.

[0165] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0166] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0171] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0172] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0173] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0174] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A yarn quality detection system, characterized in that: It comprises an image acquisition module (1), an image processing module (2), a data analysis module (3), a control module (4) and a display alarm module (5), wherein the modules are connected to each other via wires or wirelessly; An image acquisition module (1) adjusts shooting parameter information based on yarn quality standards and external configuration information, uses a high-speed camera corresponding to the shooting parameter information to collect original image data of the yarn in the production process in real time, and transmits the original image data to an image processing module (2); An image processing module (2) processes the original image data to obtain yarn characteristic information, wherein the yarn characteristic information includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knots; and transmits the yarn characteristic information to a data analysis module (3); A data analysis module (3) is used to classify the defects on the yarn surface based on the yarn characteristic information to obtain the yarn defect category; Based on the yarn defect category, the abnormal defect area on the enhanced image is identified, a statistical analysis is performed on the abnormal defect area to generate a quality inspection report, and the quality inspection report is transmitted to the control module (4) and the display alarm module (5); A control module (4) adjusts the parameters of the production equipment in real time based on the quality inspection report, thereby achieving dynamic optimization of yarn production quality and ensuring yarn quality; Display alarm module (5), for displaying real-time test data and quality test reports, and issuing an alarm signal when quality problems are found; The processing logic of the original image data is as follows: Step A1: marking the pixel value difference before and after the shooting reference information as noise influence information, and performing denoising processing on the original image data after the noise influence information is removed to obtain pre-processed image data; Step A2: note the yarn material in advance, and determine the current yarn color and yarn thickness based on the pixel value of the preprocessed image data; Step A3: Use the Canny edge detection algorithm to process the preprocessed image data to obtain a binary image, gradient amplitude and gradient direction after edge detection. Perform a connected domain analysis on the binary image combined with the gradient direction to obtain a connected domain, and identify the hairiness area according to the size, shape and distribution characteristics of the connected domain; Step A4: using a morphological dilation operation to process the original image to obtain a dilated image, and performing a morphological erosion operation on the original image to obtain an eroded image; The dilated image and the eroded image are subtracted pixel by pixel to obtain a difference image, and the area with significant brightness is identified as the defect area based on the brightness distribution of the difference image; Step A5: Superimpose the gradient amplitude onto the preprocessed image to obtain an enhanced image, traverse the historical pixel information table corresponding to the yarn material in the historical database, and compare and analyze the pixel information of the enhanced image with the historical pixel information table to obtain the fiber uniformity of the current yarn.

2. A yarn quality detection system according to claim 1, characterized in that: The logic for obtaining the shooting parameter information: The external configuration information includes shooting environment information, yarn movement data and shooting reference information. The same yarn quality standards and external configuration information are traversed and queried from the historical database, and the yarn image with the highest definition is selected as the yarn comparison image; Compare and analyze the clarity of the yarn image taken by the high-speed camera and the corresponding yarn comparison image: If the yarn image clarity does not meet the preset conditions, repair or replace the high-speed camera and light source components; If the clarity of the yarn image meets the preset conditions, the shooting parameter information of the high-speed camera is adaptively adjusted according to the yarn thickness and yarn movement data, so that the shooting frequency of the high-speed camera is synchronized with the yarn movement data. The shooting parameter information includes the focal length of the high-speed camera, the field of view of the lens, the image acquisition time frame and the brightness of the light source component.

3. A yarn quality detection system according to claim 2, characterized in that: The denoising method is a Gaussian filtering algorithm, which includes: , in: Represents the coordinate position in the original image data; Indicates the original image data after Gaussian filtering The pixel value at the coordinate position, represents the filter window size, Indicates the coordinate position of the original image data The relative filter removes the pixel value corresponding to the center coordinate of the Gaussian kernel. Represents the center coordinates of the Gaussian kernel set by the filter itself The degree of filtering is determined by convolving the normalized Gaussian kernel with the original image data to remove the original image data that affects the information.

4. A yarn quality detection system according to claim 3, characterized in that: The binary processing logic: Two thresholds are set for the pixel values ​​of the preprocessed image data to distinguish strong edges from weak edges, and the thresholds include a high threshold and a low threshold; The edges detected by the Canny edge detection algorithm are marked as strong edges if the pixel values ​​of the edge points of the image are higher than the high threshold. The edges that are higher than the low threshold but lower than the high threshold are marked as weak edges. If the weak edge is connected to the strong edge, it is retained. Otherwise, the weak edge is removed to obtain a binary image. The edge area of ​​the binary image is obtained through the connected domain algorithm, and the hairiness area is extracted based on the morphological characteristics of the edge area to obtain the number and length of the hairiness.

5. A yarn quality detection system according to claim 4, characterized in that: The data analysis logic of the quality issues mentioned above: Step B1: determining yarn defect categories based on the yarn characteristic information, wherein the yarn defect categories include color difference, fiber unevenness, hairiness and knots; Step B2: using the predefined yarn standard feature information, the yarn feature information is compared and matched with the yarn standard feature information to obtain a matching score, and the normal area and abnormal area of ​​the yarn surface are divided based on the matching score, and the number of normal areas and the number of abnormal areas are statistically analyzed to obtain quality problems corresponding to different yarn defect categories; Step B3: Summarize the quality problems to generate a quality inspection report, which includes inspection parameters, judgment results, quality trend analysis and suggestion feedback.

6. A yarn quality detection system according to claim 5, characterized in that: The control module (4) includes the design of control strategy, the processing of real-time feedback and the interactive operation of production equipment, and the specific contents are as follows: Design of control strategy: Based on the PID controller, different quality problems are controlled and adjusted in sequence. Specifically, the severity of the quality problem determines the order of adjustment. Different quality problems are solved by adjusting the parameters of different production equipment. The PID controller minimizes the detected quality deviation through closed-loop control, so that the yarn quality is stable within the preset standard range, thus achieving the stability of yarn quality. Real-time feedback processing: The control strategy designed based on the quality inspection report is fed back in real time, and the parameters of the production equipment are adjusted based on the control strategy; the adjusted production equipment continues to produce the yarn, and the yarn analyzes the quality inspection report obtained, and the quality inspection report is fed back in real time; Production equipment interaction: signal transmission of detection signals on production equipment, control of the execution of adjustment instructions of production equipment, and monitoring of production equipment status.

7. A yarn quality detection method, based on the implementation of a yarn quality detection system according to any one of claims 1 to 6, characterized in that: The following steps are involved: Adjust the shooting parameter information based on the yarn quality standard and the external configuration information, and use the high-speed camera corresponding to the shooting parameter information to collect the original image data of the yarn in the production process in real time; The original image data is processed to obtain yarn feature information, which includes yarn material, yarn color, yarn thickness, fiber uniformity, hairiness and knot defects: Classifying the defects on the yarn surface based on the yarn characteristic information to obtain the yarn defect category; Based on the yarn defect category, the abnormal defect area on the enhanced image is identified, and the abnormal defect area is statistically analyzed to generate a quality inspection report; Adjust the parameters of production equipment in real time based on quality inspection reports to achieve dynamic optimization of yarn production quality and ensure yarn quality; It is used to display real-time inspection data and quality inspection reports, and send out alarm signals when quality problems are found.

8. A yarn quality detection device, characterized in that: include: At least one image acquisition module (1); At least one display alarm module (5); at least one processor; as well as, A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a yarn quality detection system as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute a yarn quality detection system as described in any one of claims 1 to 6.

Images