A cotton web quality detection system in the carding process

Abstract

The present invention relates to the technical field of cotton web quality detection, and specifically discloses a cotton web quality detection system in a cotton combing process, comprising a processor and an image acquisition module, a cotton web quality detection module and a quality comparison control module which are communicatively connected to the processor; the system is used to solve the problem that only taking the uniformity of the cotton web as the quality detection result of the cotton web is not comprehensive; the present invention collects cotton web images through a high-resolution camera, processes the cotton web images, and analyzes the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the processed cotton web images, imports the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web image into a cotton web quality analysis model, calculates cotton web quality indicators, and compares the cotton web quality indicators with preset cotton web quality indicator thresholds to determine whether the quality of the cotton web meets the standards, thereby being able to comprehensively evaluate the quality of the cotton web and improving the accuracy and efficiency of detection.

Description

Technical Field

[0001] The present invention relates to the technical field of cotton web quality detection, and more specifically, to a cotton web quality detection system in a cotton carding process. Background Art

[0002] In the spinning process, the carding step is to comb the cotton into a cotton net or a fiber net. Only after the cotton net is formed can it be made into yarn. If the quality of the cotton net is not high, such as poor straightness, uniformity, and parallelism, the yarn produced will easily break.

[0003] For example, a Chinese patent with the authorization publication number CN207051206U discloses a cotton web quality detection system for a carding machine, including a cotton web output device, a camera device, a light source and a detection device. The camera device and the light source are both arranged above the outlet of the cotton web output device, the light source and the camera device are at a certain angle, the camera device and the detection device are electrically connected, and also include a detection box, the left and right side walls of the detection box are respectively provided with a first channel and a second channel, and the cotton web passes through the first channel and the second channel; a dust suction pipe is provided at the top of the detection box, and the dust suction pipe is connected to filter cotton through a fan; the camera device and the light source are arranged in the detection box. Based on the computer vision detection device, the cotton web of the carding machine is detected, the uniformity of the cotton web is calculated, and the detection result is accurate and objective. The camera device and the light source are arranged in the detection box, which effectively avoids the scattering and pollution of fiber dust and the pollution of the cotton web by the external environment, thereby improving the final detection accuracy.

[0004] The above patents all have the problems existing in the background technology: when the prior art conducts quality inspection on the cotton web on the carding machine surface, only taking the uniformity of the cotton web as the quality inspection result of the cotton web is not comprehensive, and the yarn made therefrom still has the problem of easy breakage. In order to solve the above problem, a technical solution is now provided. Summary of the invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cotton web quality detection system in a cotton combing process comprises a processor and an image acquisition module, a cotton web quality detection module and a quality comparison control module which are communicatively connected to the processor. The image acquisition module is used to acquire cotton web images through a high-resolution camera, and store and transmit the cotton web images; the cotton web quality detection module is used to process the cotton web images, and analyze the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the processed cotton web images, and import the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web images into a cotton web quality analysis model to calculate the cotton web quality index. The formula of the cotton web quality analysis model is:

[0007] ;

[0008] Where: It is the cotton web quality index. is the characteristic value of the straightness of the cotton web, is the characteristic value of the parallelism of the cotton web, is the uniformity characteristic value of the cotton web.

[0009] As a further solution of the present invention, the image acquisition module includes an image acquisition module, an image storage module and an image transmission module; the cotton web quality detection module includes a cotton web image processing module, a cotton web feature extraction module and a cotton web quality analysis module; the quality comparison module includes a quality comparison module and an alarm module.

[0010] As a further solution of the present invention, the cotton web image processing module is used to grayscale the cotton web image and convert the cotton web image into a fixed area. Split into sub-image blocks, and obtaining the cotton web fiber image of each sub-image block respectively;

[0011] The cotton web feature extraction module is used to calculate the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web respectively;

[0012] The cotton web quality analysis module is used to calculate the cotton web quality index by importing the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web into the cotton web quality analysis model.

[0013] As a further solution of the present invention, the cotton web feature extraction module includes a first data extraction unit, a first feature analysis unit, a second data extraction unit, a second feature analysis unit, a third data extraction unit, a third feature analysis unit and a feature output module.

[0014] As a further solution of the present invention, the first data extraction unit is used to extract the mean effective length of the first fiber and the mean spacing of the first fiber in the cotton web fiber image under the maximum tensile bearing force, and the mean effective length of the second fiber and the mean spacing of the second fiber in the cotton web fiber image under the maximum compressive bearing force by respectively acquiring the cotton web fiber image under the maximum tensile bearing force and the cotton web fiber image under the maximum compressive bearing force; the first feature analysis unit is used to calculate the straightness feature value by establishing a straightness feature calculation model.

[0015] As a further solution of the present invention, the second data extraction unit is used to obtain the cotton web fiber image under the maximum tensile bearing force and the cotton web fiber image under the maximum compressive bearing force, respectively, obtain the angle between the fiber direction and the fiber main axis direction by linear fitting the direction of the fiber, extract the relative angle between each fiber in the cotton web fiber image, and calculate the mean value of the relative angle;

[0016] The second feature analysis unit is used to calculate the parallelism feature value by establishing a parallelism feature calculation model;

[0017] The third data extraction unit is used to obtain the fixed area Split into The cotton web image of each sub-image block is extracted, and the pixel grayscale mean of each sub-image block is obtained, and the thickness and volume of each sub-image block in the cotton web are obtained.

[0018] The third feature analysis unit is used to calculate The uniformity eigenvalue of the sub-image blocks,

[0019] The feature output module is used to output the straightness feature value, the parallelism feature value and the uniformity feature value respectively.

[0020] As a further solution of the present invention, the straightness characteristic value is calculated by importing the first fiber effective length mean, the first fiber spacing mean, the second fiber effective length mean and the second fiber spacing mean in the cotton web fiber image into the straightness characteristic calculation model. The calculation formula of the straightness characteristic value calculation model is:

[0021]

[0022] Where: is the characteristic value of the straightness of the cotton web, is the total number of sub-image blocks in the cotton web image, For the The average effective length of the first fiber of the sub-image blocks, For the The average effective length of the second fiber of the sub-image blocks, For the The mean of the first fiber distances of sub-image blocks, For the The second fiber distance mean of the sub-image blocks.

[0023] As a further solution of the present invention, the relative angle between each fiber and the mean value of the relative angle are introduced into the parallelism characteristic calculation model to calculate the parallelism characteristic value. The formula of the parallelism characteristic calculation model is:

[0024]

[0025] Where: is the characteristic value of the parallelism of the cotton web, is the total number of sub-image blocks in the cotton web image, is the relative angle between the fibers, is the relative angle mean, is the number of relative angles between the fibers.

[0026] The technical effects and advantages of a cotton web quality detection system in a cotton combing process of the present invention are as follows: the present invention collects cotton web images by a high-resolution camera, processes the cotton web images, and analyzes the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the processed cotton web images, imports the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web image into a cotton web quality analysis model, calculates the cotton web quality index, and determines whether the quality of the cotton web meets the standard by comparing the cotton web quality index with a preset cotton web quality index threshold, thereby being able to comprehensively evaluate the quality of the cotton web and improving the accuracy and efficiency of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic diagram of the structure of a system for detecting the quality of a cotton web in a carding process provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solution in the present invention. Obviously, the described technical solution is only a part of the present invention, not all of it. Based on the technical solution in the present invention, all other technical solutions obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] Embodiment 1

[0030] Figure 1 FIG. 1 is a schematic diagram showing the structure of a cotton web quality detection system in a cotton combing process provided by Embodiment 1 of the present invention. Figure 1 As shown, a cotton web quality detection system in a cotton combing process in this embodiment includes a processor and an image acquisition module, a cotton web quality detection module and a quality comparison control module that are connected to the processor in communication.

[0031] The image acquisition module is connected to the cotton web quality detection module, and is used to acquire cotton web images through a high-resolution camera, and store and transmit the cotton web images;

[0032] The cotton web quality detection module is connected to the quality comparison control module, and is used to process the cotton web image and extract the quality features of the processed cotton web image, and import the quality features of the cotton web image into the cotton web quality analysis model to calculate the cotton web quality index;

[0033] The quality comparison module is used to determine whether the quality of the cotton web meets the standard by comparing the cotton web quality index with the preset cotton web quality index threshold.

[0034] The cotton web image is collected by a high-resolution camera, the cotton web image is processed, and the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the processed cotton web image are analyzed, and the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web image are imported into the cotton web quality analysis model to calculate the cotton web quality index, and by comparing the cotton web quality index with the preset cotton web quality index threshold, it is determined whether the quality of the cotton web meets the standard, which can comprehensively evaluate the quality of the cotton web and improve the accuracy and efficiency of detection.

[0035] The image acquisition module includes an image acquisition module, an image storage module and an image transmission module; the image acquisition module is connected to the image storage module, and the image storage module is connected to the image transmission module;

[0036] The cotton web quality detection module includes a cotton web image processing module, a cotton web feature extraction module and a cotton web quality analysis module; the cotton web image processing module is connected to the cotton web feature extraction module, and the cotton web feature extraction module is connected to the cotton web quality analysis module;

[0037] The quality comparison module includes a quality comparison module and an alarm module; the quality standard comparison module is connected to the alarm module.

[0038] The image acquisition module is used to acquire cotton web images through a high-resolution camera, and obtain cotton web images under normal conditions, cotton web images under maximum tensile bearing force, and cotton web images under maximum compressive bearing force respectively;

[0039] The image storage module is used to store the cotton web image;

[0040] The image transmission module is used to transmit the cotton web image.

[0041] Among them, the image of the cotton mesh under the maximum tensile bearing force is obtained by fixing the cotton mesh sample in the fixture of the material testing machine, setting the tensile rate of the testing machine, and testing in millimeters / minute. The material testing machine is started and the tensile force is gradually increased until the cotton mesh sample breaks or reaches the predetermined tensile force. During the whole process, a high-resolution camera will continuously capture the cotton mesh image and record the morphological changes of the cotton mesh during the stretching process.

[0042] The image of the cotton web under maximum compression bearing force is obtained by using a compression test device. The cotton web sample is placed on the test platform of the compression test device, the compression rate and pressure of the test machine are set, the test machine is started, and the compression force is gradually increased until the cotton web sample reaches a predetermined compression force or deformation occurs. During the test, a high-resolution camera is also used to record the image of the cotton web during the compression process.

[0043] The cotton web image processing module is used to grayscale the cotton web image and convert the cotton web image into a fixed area. Split into sub-image blocks, and obtaining the cotton web fiber image of each sub-image block respectively;

[0044] The cotton web feature extraction module is used to calculate the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web respectively;

[0045] The cotton web quality analysis module is used to calculate the cotton web quality index by importing the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web into the cotton web quality analysis model.

[0046] The quality comparison module is used to compare the cotton web quality index with the preset cotton web quality index threshold. When the cotton web quality index is greater than or equal to the preset cotton web quality index threshold, the quality of the cotton web meets the standard; when the cotton web quality index is less than the preset cotton web quality index threshold, the quality of the cotton web does not meet the standard.

[0047] The alarm module is used to send out an alarm for cotton webs that do not meet the quality standards.

[0048] The cotton web feature extraction module includes a first data extraction unit, a first feature analysis unit, a second data extraction unit, a second feature analysis unit, a third data extraction unit, a third feature analysis unit and a feature output module; the first data extraction unit is connected to the first feature analysis unit, the second data extraction unit is connected to the second feature analysis unit, the third data extraction unit is connected to the third feature analysis unit, and the first feature analysis unit, the second feature analysis unit and the third feature analysis unit are respectively connected to the feature output module.

[0049] The first data extraction unit is used to extract the first fiber effective length mean and the first fiber spacing mean in the cotton web fiber image under the maximum tensile bearing force, and the second fiber effective length mean and the second fiber spacing mean in the cotton web fiber image under the maximum compressive bearing force by respectively acquiring the cotton web fiber image under the maximum tensile bearing force and the cotton web fiber image under the maximum compressive bearing force;

[0050] The first characteristic analysis unit is used to calculate the straightness characteristic value by establishing a straightness characteristic calculation model;

[0051] The second data extraction unit is used to obtain the cotton web fiber image under the maximum tensile bearing force and the cotton web fiber image under the maximum compressive bearing force, respectively, obtain the angle between the fiber direction and the fiber main axis direction by linear fitting the direction of the fiber, extract the relative angle between each fiber in the cotton web fiber image, and calculate the average value of the relative angle;

[0052] The second feature analysis unit is used to calculate the parallelism feature value by establishing a parallelism feature calculation model;

[0053] The third data extraction unit is used to obtain the fixed area Split into The cotton web image of sub-image blocks, where is the length of the sub-image block, is the width of the sub-image block, the mean grayscale value of each sub-image block is extracted, and the thickness and volume of each sub-image block in the cotton web are obtained.

[0054] The third feature analysis unit is used to calculate The uniformity feature value of the sub-image block.

[0055] The feature output module is used to output the straightness feature value, the parallelism feature value and the uniformity feature value respectively.

[0056] Through the first data extraction unit and the second data extraction unit, the system can obtain the cotton web fiber image under the maximum tensile and compressive bearing force, and extract the effective length, spacing and fiber direction of the fibers, so as to fully understand the properties of the fibers; the first feature analysis unit and the second feature analysis unit establish a straightness and parallelism feature calculation model, which can accurately calculate the straightness and parallelism feature values, providing precise data support for cotton web quality assessment; the third data extraction unit obtains the pixel grayscale mean, thickness, volume and other information of each sub-image block of the cotton web image, and the third feature analysis unit can calculate the uniformity feature value based on this, and make a detailed assessment of the uniformity of the cotton web.

[0057] The straightness characteristic value is calculated by importing the first fiber effective length mean, the first fiber spacing mean, the second fiber effective length mean and the second fiber spacing mean in the cotton web fiber image into the straightness characteristic calculation model. The calculation formula of the straightness characteristic value calculation model is:

[0058] ;

[0059] Where: is the characteristic value of the straightness of the cotton web, is the total number of sub-image blocks in the cotton web image, For the The average effective length of the first fiber of the sub-image blocks, For the The average effective length of the second fiber of the sub-image blocks, For the The mean of the first fiber distances of sub-image blocks, For the The second fiber distance mean of the sub-image blocks.

[0060] By considering the effective length and the average spacing of the first and second fibers, the fiber distribution of the cotton web can be more comprehensively reflected, which helps to more accurately evaluate the straightness characteristics of the cotton web; the calculation formula of the straightness characteristic value comprehensively considers the differences in the effective length and spacing of the fibers, and quantifies these differences into straightness characteristic values, making the evaluation of the straightness characteristics more objective and accurate; there may be differences in the sub-image blocks in the cotton web image, including fiber length and spacing. Considering the contribution of each sub-image block, the straightness characteristic value is calculated by summing up all sub-image blocks, which can better reflect the straightness of the entire cotton web, help to discover and correct potential problems in the cotton web manufacturing process, and improve the accuracy and reliability of the evaluation.

[0061] By importing the relative angles between the fibers and the mean of the relative angles into the parallelism characteristic calculation model, the parallelism characteristic value is calculated. The formula of the parallelism characteristic calculation model is:

[0062]

[0063] Where: is the characteristic value of the parallelism of the cotton web, is the total number of sub-image blocks in the cotton web image, is the relative angle between the fibers, is the relative angle mean, is the number of relative angles between the fibers.

[0064] The parallelism characteristic calculation model comprehensively considers the relative angle between each fiber and its mean value. It can not only detect whether there is a non-parallel situation, but also take into account the overall parallelism situation, which is helpful to comprehensively evaluate the parallelism characteristics of the cotton web; by comparing the relative angle with its mean value, it can more accurately evaluate the contribution of each fiber to the overall parallelism, which is helpful to identify and correct possible parallelism problems; the mean value of the relative angle between all fibers is imported into the model, and by taking the weighted sum of all relative angles, the parallelism situation between each fiber is comprehensively considered, and then the parallelism characteristic value of the overall cotton web is obtained, which is helpful to more comprehensively evaluate the parallelism of the cotton web.

[0065] The third feature analysis unit is used to calculate The uniformity eigenvalue of the sub-image block is calculated by the formula:

[0066]

[0067]

[0068] Where: is the uniformity characteristic value, is the average gray value of the cotton web image, is the thickness of the sub-image block in the cotton web, is the volume of the sub-image block in the cotton web, For high The area is The mean grayscale value of the sub-image block.

[0069] The calculation formula of the uniformity eigenvalue takes into account the average grayscale value of the cotton web image, which can comprehensively reflect the overall grayscale situation of the cotton web image and help evaluate the overall uniformity of the cotton web, rather than just the local grayscale uniformity; the calculation formula of the uniformity eigenvalue includes the thickness and volume information of the sub-image block, which means that the size of the sub-image block is taken into consideration, making the evaluation more accurate, because sub-image blocks of different sizes may contribute differently to the overall uniformity; the uniformity eigenvalue quantifies the uniformity feature into a percentage value by weighted summing up the pixel grayscale means of each sub-image block and comparing it with the average grayscale value, making the evaluation of the uniformity feature more objective and accurate.

[0070] The cotton web quality analysis module is used to calculate the cotton web quality index by importing the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web into the cotton web quality analysis model, wherein the formula of the cotton web quality analysis model is:

[0071]

[0072] Where: It is the cotton web quality index. is the characteristic value of the straightness of the cotton web, is the characteristic value of the parallelism of the cotton web, is the characteristic value of uniformity of the cotton web.

[0073] Combining the three eigenvalues ​​of straightness, parallelism and uniformity can comprehensively consider the fiber stretching, fiber arrangement and uniformity of the cotton web, and more comprehensively evaluate the quality of the cotton web; the cotton web quality analysis model calculates the three eigenvalues ​​to obtain the cotton web quality index, which can intuitively reflect the quality of the cotton web and facilitate comparison and evaluation of different cotton webs; the calculation formula of the cotton web quality index takes into account the comprehensive influence of the three eigenvalues. When any eigenvalue is abnormal, it will affect the final cotton web quality index, which helps to identify potential quality problems in time and provide a basis for quality control.

[0074] The embodiment of the present invention collects cotton web images through a high-resolution camera, processes the cotton web images, and analyzes the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the processed cotton web image, imports the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web image into a cotton web quality analysis model, calculates the cotton web quality index, and determines whether the quality of the cotton web meets the standard by comparing the cotton web quality index with a preset cotton web quality index threshold. This can comprehensively evaluate the quality of the cotton web and improve the accuracy and efficiency of detection.

[0075] 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.

[0076] 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 cotton web quality detection system in a cotton combing process, comprising a processor, an image acquisition module, a cotton web quality detection module and a quality comparison control module connected to the processor, characterized in that: The image acquisition module is used to collect cotton web images through a high-resolution camera, and store and transmit the cotton web images; the cotton web quality detection module is used to process the cotton web images, and analyze the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the processed cotton web images, and import the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web image into the cotton web quality analysis model to calculate the cotton web quality index. The formula of the cotton web quality analysis model is: Where: It is the cotton web quality index. is the characteristic value of the straightness of the cotton web, is the characteristic value of the parallelism of the cotton web, is the characteristic value of uniformity of the cotton web; The image acquisition module includes an image acquisition module, an image storage module and an image transmission module; the cotton web quality detection module includes a cotton web image processing module, a cotton web feature extraction module and a cotton web quality analysis module; the quality comparison module includes a quality comparison module and an alarm module; the cotton web image processing module is used to grayscale the cotton web image and convert the cotton web image into a fixed area. Split into sub-image blocks, and obtaining the cotton web fiber image of each sub-image block respectively; The cotton web feature extraction module is used to calculate the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web respectively; The cotton web quality analysis module is used to calculate the cotton web quality index by importing the straightness characteristic value, parallelism characteristic value and uniformity characteristic value of the cotton web into the cotton web quality analysis model; The cotton web feature extraction module includes a first data extraction unit, a first feature analysis unit, a second data extraction unit, a second feature analysis unit, a third data extraction unit, a third feature analysis unit and a feature output module; The second data extraction unit is used to obtain the cotton web fiber image under the maximum tensile bearing force and the cotton web fiber image under the maximum compressive bearing force, respectively, obtain the angle between the fiber direction and the fiber main axis direction by linear fitting the direction of the fiber, extract the relative angle between each fiber in the cotton web fiber image, and calculate the average value of the relative angle; The second feature analysis unit is used to calculate the parallelism feature value by establishing a parallelism feature calculation model; The third data extraction unit is used to obtain the fixed area Split into The cotton web image of sub-image blocks, where is the length of the sub-image block, is the width of the sub-image block, extract the mean grayscale value of each sub-image block, and obtain the thickness and volume of each sub-image block in the cotton web. The third feature analysis unit is used to calculate The uniformity eigenvalue of the sub-image blocks, The characteristic output module is used to output the straightness characteristic value, the parallelism characteristic value and the uniformity characteristic value respectively; The straightness characteristic value is calculated by importing the first fiber effective length mean, the first fiber spacing mean, the second fiber effective length mean and the second fiber spacing mean in the cotton web fiber image into the straightness characteristic calculation model. The calculation formula of the straightness characteristic value calculation model is: Where: is the characteristic value of the straightness of the cotton web, is the total number of sub-image blocks in the cotton web image, is the mean effective length of the first fiber of the nth sub-image block, For the The average effective length of the second fiber of the sub-image blocks, For the The mean of the first fiber distances of sub-image blocks, For the The second fiber distance average of the sub-image blocks; By importing the relative angles between the fibers and the average of the relative angles into the parallelism characteristic calculation model, the parallelism characteristic value is calculated. The formula of the parallelism characteristic calculation model is: Where: is the characteristic value of the parallelism of the cotton web, is the total number of sub-image blocks in the cotton web image, is the relative angle between the fibers, is the relative angle mean, is the number of relative angles between the fibers; The quality comparison module is used to compare the cotton web quality index with the preset cotton web quality index threshold. When the cotton web quality index is greater than or equal to the preset cotton web quality index threshold, the quality of the cotton web meets the standard; when the cotton web quality index is less than the preset cotton web quality index threshold, the quality of the cotton web does not meet the standard.

2. A cotton web quality detection system in a carding process according to claim 1, characterized in that: The first data extraction unit is used to extract the first fiber effective length mean and the first fiber spacing mean in the cotton web fiber image under the maximum tensile bearing force, and the second fiber effective length mean and the second fiber spacing mean in the cotton web fiber image under the maximum compressive bearing force by respectively acquiring the cotton web fiber image under the maximum tensile bearing force and the cotton web fiber image under the maximum compressive bearing force; The first feature analysis unit is used to calculate the straightness feature value by establishing a straightness feature calculation model.

Images