A spinning system operating state detection method and system

Abstract

The present application relates to the field of spinning system detection, and in particular to a spinning system operation status detection method and system, the method comprising the steps of: acquiring images of continuous frames and dividing yarn regions, the yarn regions including initial defect regions and initial yarn trunk regions; clustering the pixels in the yarn regions to obtain a number of clustering clusters as clustering results, the clustering results being the optimal yarn trunk regions, and the other regions being the optimal defect regions; processing the optimal defect regions, calculating the yarn evaluation quality of the optimal defect regions, and in response to the yarn evaluation quality being greater than a preset quality threshold, reducing the yarn feed speed. The present application reduces the phenomenon of missed or misdetected yarn defects caused by a fixed clustering radius, and reduces the probability that the yarn system needs to frequently adjust the yarn feed speed during the production process.

Description

Technical Field

[0001] The present application relates to the field of spinning system detection, and in particular to a spinning system operating status detection method and system. Background Art

[0002] The spinning system generally refers to a series of interrelated equipment, processes and operating procedures that work together to transform fiber raw materials into yarn. Yarn defects refer to defects that occur during the yarn production and processing process. These defects affect the quality, strength, appearance of the yarn and the performance of the final textile product. The following are some common yarn defects: Cotton neps: small knots or lumps formed by the entanglement of cotton fibers in the yarn. Hairiness: short fiber ends on the surface of the yarn, affecting the smoothness and appearance of the yarn.

[0003] Yarn defects are usually caused by improper parameter settings in the process of spinning. In the prior art, the parameters of the spinning system can be adjusted according to the defects of the yarn. For example, the application document with the publication number CN118505068A discloses a method for monitoring and controlling the production of textile yarns. The basic operating data of each facility is determined by obtaining the fiber properties of various raw materials, and the defect status of each production process of the textile yarn is detected in real time to make corresponding corrections to each implementation step of the textile yarn.

[0004] High-speed yarn feeding increases the friction between the yarn and mechanical parts. This friction may cause fiber wear and breakage on the yarn surface, resulting in more defects. Therefore, defects can be detected during the production process, and the yarn feeding speed can be reduced by controlling the defect situation to ensure the quality of the yarn. In the prior art, defects can be identified through images. For example, the application document with publication number CN110021023A discloses an electronic cloth defect segmentation method, which uses the K-means algorithm to cluster the filtered image; finally, the pixels of the clustered image are marked according to the cluster category, and binarization is performed according to the marking result to segment the fabric defects.

[0005] However, the clustering radius of clustering in the prior art is usually a fixed value set based on experience, and the clustering accuracy is low. If the clustering radius is set too large, multiple defects may be merged into one, causing some smaller defects to be ignored. If the clustering radius is set too small, non-defective textures or patterns may be mistakenly identified as defects, increasing the false detection rate. Therefore, a fixed clustering radius will lead to false detection or missed detection, and the yarn system needs to adjust the yarn feeding speed more frequently during the production process, which will reduce production efficiency. Summary of the invention

[0006] In order to reduce the frequent adjustment of yarn feeding in the yarn system, the present application provides a method and system for detecting the operating status of a spinning system.

[0007] In a first aspect, the present application provides a method for detecting the operating status of a spinning system, which adopts the following technical solution:

[0008] A method for detecting the running state of a spinning system comprises the following steps: acquiring images of continuous frames and dividing a yarn region, wherein the yarn region comprises an initial defect region and an initial yarn trunk region; clustering pixel points in the yarn region to obtain a plurality of clustering clusters as clustering results, wherein the clustering result is an optimal yarn trunk region, and other regions are optimal defect regions; processing the optimal defect region, calculating the yarn evaluation quality of the optimal defect region, and in response to the yarn evaluation quality being greater than a preset quality threshold, reducing the yarn feeding speed; wherein the clustering radius is the product of the position distance and the gradient distance; when the Euclidean distance value between two pixel points is less than a preset threshold, the position distance is 1, otherwise, the position distance is 0; when the absolute value of the difference between the grayscale values ​​of the two pixel points and 1 is less than or equal to a preset gradient response value, the gradient distance is 1, otherwise, the gradient distance is 0; calculating the verification condition of the clustering cluster, completing the clustering when the verification condition meets the preset standard, otherwise, adjusting the clustering radius until the verification condition is met to complete the clustering.

[0009] The clustering radius is set to the product of the position distance and the gradient distance. This method can dynamically adjust the clustering radius according to the actual situation of the yarn, improve the accuracy of clustering, reduce the dependence on a single threshold, make the clustering process more stable, improve the precision of identifying defective areas, reduce the phenomenon of frequent adjustment of the yarn feeding speed in the yarn system during the production process, and improve production efficiency.

[0010] Optionally, the preset standard is: only one cluster has a verification condition value greater than a preset condition threshold.

[0011] Optionally, the method for adjusting the cluster radius is: if the verification conditions of the cluster clusters are all less than or equal to the preset condition threshold, lower the gradient response value; if the verification conditions of at least two cluster clusters are greater than the preset condition threshold, increase the gradient response value.

[0012] By setting verification conditions and preset standards, the optimal clustering radius can be quickly identified to improve the efficiency of clustering. The method of dynamically adjusting the gradient response value makes the clustering process more flexible and able to adapt to different image features and yarn characteristics.

[0013] Optionally, the expression of the validation condition is: ,in, Indicates the verification condition. Indicates the width of the image. Pixel The horizontal axis of Pixel The vertical coordinate of Pixel The horizontal axis of Pixel The vertical coordinate of is the diameter of the yarn in the image, Represents the maximum value function.

[0014] Optionally, in calculating the yarn evaluation quality, the absolute value of the difference between the ratio of the number of pixels in the connected domain of the optimal yarn trunk region and the number of pixels in the optimal yarn trunk region and 1 is used as the yarn evaluation quality.

[0015] The connected domain of the optimal yarn trunk area is the area where defects such as cotton knots on the yarn are located and the area where the yarn trunk is located. The ratio of the number of pixels in the connected domain of the optimal yarn trunk area to the number of pixels in the optimal yarn trunk area represents the proportion of the yarn trunk area in the connected domain. This is used to quantify the yarn quality evaluation, which does not rely on complex statistical models, has a simple calculation process, and the results are intuitive.

[0016] Optionally, calculating the yarn evaluation quality includes the steps of: taking the average of the grayscale values ​​of the pixels in the optimal yarn trunk area as the yarn grayscale value; inputting the grayscale values ​​of the pixels in the optimal defect area into a mixed Gaussian model to obtain multiple peaks, and taking the peak values ​​corresponding to the yarn grayscale values ​​as the yarn peak values; constructing a sequence according to the yarn peak values ​​within a preset range, and taking the absolute value of the difference between the ratio of the number of pixels corresponding to the sequence and the number of pixels in the optimal yarn trunk area and 1 as the yarn evaluation quality.

[0017] The ratio of the number of pixels corresponding to the sequence to the number of pixels in the main area of ​​the yarn is used as the yarn evaluation quality to quantify the consistency of the yarn quality. The closer the ratio is to 1, the more uniform the yarn quality is and the fewer defects it has. The smaller the ratio is, the more defects it has.

[0018] Optional, preset range is ( ),in, represents the mean value of the yarn peak value, Indicates the standard deviation of the yarn peak.

[0019] By dividing the normal distribution curve by ( ) interval as a preset range, you can focus on the yarn peak value and ignore extreme data, which helps to reduce false positives and negatives and improve the accuracy of quality evaluation.

[0020] In a second aspect, the present application provides a spinning system operation status detection system, which adopts the following technical solution:

[0021] A spinning system operation status detection system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the spinning system operation status detection method described above is implemented.

[0022] The spinning system operation status detection method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor. Thus, a system is made based on the memory and the processor for easy use.

[0023] This application has the following technical effects:

[0024] 1. Set the clustering radius to the product of the position distance and the gradient distance. This method can dynamically adjust the clustering radius according to the actual situation of the yarn, improve the accuracy of clustering, reduce the dependence on a single threshold, make the clustering process more stable, and improve the precision of identifying defective areas.

[0025] 2. The connected domain of the optimal yarn trunk area is the area where defects such as cotton knots on the yarn are located and the area where the yarn trunk is located. The ratio of the number of pixels in the connected domain of the optimal yarn trunk area to the number of pixels in the optimal yarn trunk area represents the proportion of the yarn trunk area in the connected domain. This is used to quantify the yarn quality evaluation, which does not rely on complex statistical models, has a simple calculation process, and the results are intuitive. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0027] Figure 1 It is a method flow chart of a method for detecting the operating status of a spinning system according to an embodiment of the present application.

[0028] Figure 2 It is a flow chart of a method for evaluating quality calculation in a spinning system operating status detection method in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0030] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0031] The present application embodiment discloses a method for detecting the operating status of a spinning system, referring to Figure 1 , including steps S1 to S3, which are specifically as follows:

[0032] S1: Acquire images of continuous frames and divide the yarn area, where the yarn area includes an initial defect area and an initial yarn trunk area.

[0033] Use a high-speed camera or other image acquisition equipment to continuously capture the video of the yarn in the production process, extract frames from the video, and delete the pictures with lower definition. Since the shooting angle is fixed and the color and shape of the yarn are relatively stable, in actual monitoring, first mark the initial defect area (cotton neps, hairiness, etc.) and the initial yarn trunk area of ​​the yarn in the collected picture, where the initial defect area is a rectangular area distributed on both sides of the initial yarn trunk area. Establishing the initial defect area can avoid environmental noise in the image. The width of the initial defect area can be set by the user according to the actual application scenario. In principle, defects such as cotton neps are completely within the initial defect area, and the length of the initial defect area can be equal to the length of the image. The initial defect area and the initial yarn trunk area constitute the yarn area.

[0034] S2: Clustering the pixel points in the yarn area to obtain several clusters as clustering results. The clustering result is the optimal yarn trunk area, and other areas are optimal defect areas.

[0035] In one embodiment, the clustering algorithm uses DBSCAN (Density Based Spatial Clustering of Applications with Noise). DBSCAN clustering is an existing technology and will not be described in detail here. The clustering radius is expressed as:

[0036] ;

[0037] ;

[0038] ;

[0039] in, represents the cluster radius, Indicates the location distance, represents the gradient distance, Pixel The horizontal axis of Pixel The vertical coordinate of Pixel The horizontal axis of Pixel The vertical coordinate of Pixel The gray value of Pixel The gray value of It represents the gradient response value, which can be set by the user according to the actual application scenario. For example, Take 0.7.

[0040] The cluster radius is the product of the position distance and the gradient distance. When the Euclidean distance between two pixels is less than a preset threshold, the position distance is 1, otherwise, the position distance is 0, and the threshold is 2. When the absolute value of the difference between the grayscale values ​​of the two pixels and 1 is less than or equal to a preset gradient response value, the gradient distance is 1, otherwise, the gradient distance is 0.

[0041] Calculate the verification conditions of the clustering clusters. When the verification conditions meet the preset standards, the clustering is completed. Otherwise, adjust the clustering radius until the verification conditions are met and the clustering is completed.

[0042] In one embodiment, the expression of the verification condition is:

[0043] ,in, Indicates the verification condition. Indicates the width of the image. Pixel The horizontal axis of Pixel The vertical coordinate of Pixel The horizontal axis of Pixel The vertical coordinate of is the diameter of the yarn in the image, Represents the maximum value function.

[0044] In one embodiment, the expression of the verification condition is:

[0045] ,in, Indicates the verification condition. Indicates the width of the image. Pixel The horizontal axis of Pixel The vertical coordinate of Pixel The horizontal axis of Pixel The vertical coordinate of is the diameter of the yarn in the image, Represents the maximum value function.

[0046] The preset standard may be: only one cluster has a verification condition value greater than a preset condition threshold. Exemplarily, the condition threshold is set to 0.9.

[0047] The method for adjusting the cluster radius is: if the verification conditions of the cluster clusters are all less than or equal to the preset condition threshold, the gradient response value is lowered; if the verification conditions of at least two cluster clusters are greater than the preset condition threshold, the gradient response value is increased.

[0048] The method for adjusting the gradient response value is: using a linear function for adjustment. The expression of the linear function is: ,in, is the coefficient, is a constant, for example, Set to 1, Set to 0, Indicates the verification condition. Indicates the adjustment value of the gradient response value.

[0049] In summary, when there is only one cluster whose verification condition value is greater than 0.9, clustering is completed. When there are two or more clusters whose verification condition values ​​are greater than 0.9, clustering is completed. As the adjusted gradient response value, when the verification condition values ​​of the clusters are all less than or equal to 0.9, As the adjusted gradient response value, exemplarily, is 0.05. 0.7 is an example value of the above gradient response value.

[0050] S3: Processing the optimal defect area, calculating the yarn evaluation quality of the optimal defect area, and in response to the yarn evaluation quality being greater than a preset quality threshold, reducing the yarn feeding speed.

[0051] The yarn evaluation quality is calculated after the optimal defect area is expanded. The expansion process is a prior art and will not be described in detail here. For example, the quality threshold is 0.8.

[0052] In one embodiment, the calculation method for evaluating the quality is: the absolute value of the difference between the ratio of the number of pixels in the connected domain of the optimal yarn trunk region and the number of pixels in the optimal yarn trunk region and 1 is used as the yarn evaluation quality. The connected domain of the optimal yarn trunk region is the region where defects such as cotton knots on the yarn are located and the region where the yarn trunk is located. The ratio of the number of pixels in the connected domain of the optimal yarn trunk region to the number of pixels in the optimal yarn trunk region represents the proportion of the yarn trunk region in the connected domain, so as to quantify the yarn quality evaluation. The closer the ratio is to 1, the closer the yarn quality evaluation is to 0, indicating that the higher the yarn quality is, the fewer defects such as cotton knots are.

[0053] In one embodiment, referring to Figure 2 , the quality evaluation includes steps S30 to S32, which are as follows:

[0054] S30: taking the average grayscale value of the pixel points in the optimal yarn trunk area as the yarn grayscale value.

[0055] By calculating the grayscale mean of the yarn trunk area, the overall brightness level of the yarn in the image can be obtained, providing a benchmark value for the grayscale characteristics of the yarn.

[0056] S31: The grayscale values ​​of the pixels in the optimal defect area are input into the mixed Gaussian model to obtain multiple peaks, and the peak value corresponding to the yarn grayscale value is taken as the yarn peak value.

[0057] The mixed Gaussian model is an existing technology and will not be described in detail here. The mixed Gaussian model can model the grayscale distribution of the defective area and reveal the multi-peak distribution characteristics of the grayscale value. Different grayscale levels of the yarn defective area can be distinguished according to the peak value.

[0058] S32: constructing a sequence according to the yarn peak value within a preset range, and taking the absolute value of the difference between the ratio of the number of pixel points corresponding to the sequence and the number of pixel points in the optimal yarn trunk area and 1 as the yarn evaluation quality.

[0059] In one embodiment, the preset range is ( ),in, represents the mean value of the yarn peak value, Represents the standard deviation of the yarn peak value. The gray value of the defect area is normally distributed, and the normal distribution curve ( ) as the amplitude range, in the normal distribution curve, 99.7% of the data values ​​fall within ( ) interval, that is, 99.7% of the data values ​​are concentrated within three standard deviations of the mean. ) data points outside the interval are considered to be outliers or abnormal values.

[0060] By dividing the normal distribution curve by ( ) interval as a preset range, you can focus on the yarn peak value and ignore extreme data, which helps to reduce false positives and negatives and improve the accuracy of quality evaluation.

[0061] The ratio of the number of pixels corresponding to the sequence to the number of pixels in the main area of ​​the yarn is used as the yarn evaluation quality to quantify the consistency of the yarn quality. The closer the ratio is to 1, the closer the yarn evaluation quality is to 0, indicating that the yarn quality is more uniform and the defects are fewer; conversely, it means that there are more defects and the quality evaluation is lower.

[0062] An embodiment of the present application also discloses a spinning system operating status detection system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a spinning system operating status detection method according to the present application is implemented.

[0063] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0064] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0065] Although this specification has shown and described a plurality of embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein may be adopted.

[0066] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for detecting the operating status of a spinning system, It is characterized in that Includes steps: Acquire images of continuous frames and divide the yarn area, the yarn area includes an initial defect area and an initial yarn trunk area; cluster the pixel points in the yarn area to obtain a number of clustering clusters as clustering results, the clustering result is the optimal yarn trunk area, and other areas are optimal defect areas; The optimal defect area is processed, and the yarn evaluation quality of the optimal defect area is calculated, including the following steps: taking the mean value of the grayscale values ​​of the pixels in the optimal yarn trunk area as the yarn grayscale value; inputting the grayscale values ​​of the pixels in the optimal defect area into a mixed Gaussian model to obtain multiple peaks, and taking the peak value corresponding to the yarn grayscale value as the yarn peak value; constructing a sequence according to the yarn peak value within a preset range, taking the absolute value of the difference between the ratio of the number of pixels corresponding to the sequence and the number of pixels in the optimal yarn trunk area and 1 as the yarn evaluation quality, and in response to the yarn evaluation quality being greater than a preset quality threshold, reducing the yarn feeding speed; Among them, the cluster radius is the product of the position distance and the gradient distance; when the Euclidean distance between two pixels is less than the preset threshold, the position distance is 1, otherwise, the position distance is 0; when the absolute value of the difference between the grayscale value of the two pixels and 1 is less than or equal to the preset gradient response value, the gradient distance is 1, otherwise, the gradient distance is 0; the verification condition for calculating the clustering cluster is expressed as follows: ,in, Indicates the verification condition. Indicates the width of the image. Pixel The horizontal axis of Pixel The vertical coordinate of Pixel The horizontal axis of Pixel The vertical coordinate of is the diameter of the yarn in the image, Represents the maximum value function. When the verification condition meets the preset standard, clustering is completed. Otherwise, the clustering radius is adjusted until the verification condition is met and clustering is completed.

2. The method for detecting the operating status of a spinning system according to claim 1, It is characterized in that The preset standard is that only one cluster has a verification condition value greater than the preset condition threshold.

3. The method for detecting the operating status of a spinning system according to claim 2, It is characterized in that The method for adjusting the cluster radius is: if the verification conditions of the cluster clusters are all less than or equal to the preset condition threshold, the gradient response value is lowered; if the verification conditions of at least two cluster clusters are greater than the preset condition threshold, the gradient response value is increased.

4. The method for detecting the operating status of a spinning system according to any one of claims 1 to 3, It is characterized in that In calculating the yarn evaluation quality, the absolute value of the difference between the ratio of the number of pixels in the connected domain of the optimal yarn trunk area and the number of pixels in the optimal yarn trunk area and 1 is taken as the yarn evaluation quality.

5. The method for detecting the operating status of a spinning system according to claim 1, It is characterized in that The preset range is ( ),in, represents the mean value of the yarn peak value, Indicates the standard deviation of the yarn peak.

6. A spinning system operation status detection system, It is characterized in that include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the spinning system operating status detection method according to any one of claims 1-5 is implemented.

Images