A method, system, device and medium for detecting carbon fiber defects

Abstract

The present invention relates to the technical field of carbon fiber production, and particularly to a carbon fiber defect detection method, system, device and medium. The method includes: setting a double-roller structure in the camera detection area to apply a set tension to the carbon fiber yarn; collecting an image of the carbon fiber yarn and identifying the contour of the carbon fiber yarn in the image; calculating the minimum circumscribed rectangle for each carbon fiber yarn contour and calculating the angle between the long side of the minimum circumscribed rectangle and the side of the image; setting an angle threshold range and screening out the yarn contours that do not meet the angle threshold range; through a double-threshold segmentation method, dividing the screened-out yarn contours into a pure black area and a light black area; judging whether the area of the light black area in the yarn contour exceeds a set value. If it exceeds, it is judged as interference; if it does not exceed, it is judged as a defect. In the present invention, false alarms caused by the shaking of the carbon fiber tow can be effectively reduced, and the accuracy and reliability of defect detection can be significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon fiber production, and particularly relates to a method, a system, a device and a medium for detecting carbon fiber defects. Background Art

[0002] Carbon fiber has a series of excellent properties such as high specific strength, high specific modulus, fatigue resistance, creep resistance, corrosion resistance and small thermal expansion coefficient. Therefore, it is widely used as a reinforcement for carbon fiber reinforced resin matrix composites (CFRP) in national defense cutting-edge technologies such as aerospace and aviation, and is also a new material for the upgrading of civilian industries.

[0003] During the production process of carbon fiber, defects such as "fluffs", "hairs", "broken filaments", joints, etc. will occur. Relying solely on the manual visual method to detect the defects in the carbon fiber production process will inevitably result in missed detections. Therefore, it is necessary to rely on a vision detection system to conduct real-time online monitoring of the carbon fiber defects that occur during the carbon fiber production process.

[0004] During the carbon fiber production process, problems such as the shaking and swaying of the tow often cause certain shadows to appear in the image, resulting in false alarms in vision detection and affecting production.

[0005] The information disclosed in this background art section is only intended to deepen the understanding of the overall background art of the present invention, and should not be regarded as an admission or any form of suggestion that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0006] The present invention provides a method, a system, a device and a medium for detecting carbon fiber defects, thereby effectively solving the problems in the background art.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is: a method for detecting carbon fiber defects, including the following steps:

[0008] Set a double-roller structure in the camera detection area to apply a set tension to the carbon fiber yarn;

[0009] Collect an image of the carbon fiber yarn and identify the contour of the carbon fiber yarn in the image;

[0010] Calculate the minimum bounding rectangle for each of the carbon fiber yarn contours and calculate the angle between the long side of the minimum bounding rectangle and the side of the image;

[0011] Set an angle threshold range and screen out the yarn contours that do not meet the angle threshold range;

[0012] Through a double-threshold segmentation method, divide the screened yarn contours into a pure black area and a light black area;

[0013] Judge whether the area of the light black region in the yarn contour exceeds a set value. If it exceeds, it is judged as interference; if it does not exceed, it is judged as a defect.

[0014] Further, a double-roller structure is arranged in the camera detection area, including: arranging a pressure roller and a pulling roller in the area where the camera collects images to apply tension to the carbon fiber yarn.

[0015] Further, the identification of the carbon fiber yarn contour in the image includes the following steps:

[0016] Convert the carbon fiber yarn image into a grayscale image;

[0017] Perform threshold segmentation on the grayscale image to extract the pixel points with grayscale values less than the set value;

[0018] Perform connected component extraction on the extracted pixel points, and screen them through an area threshold to remove the connected components with an area smaller than the area threshold to obtain the carbon fiber yarn contour.

[0019] Further, the method of dividing the screened yarn contour into a pure black region and a light black region by double-threshold segmentation includes the following steps:

[0020] Extract the pure black pixel points in the extracted carbon fiber yarn contour by setting the pure black grayscale value threshold;

[0021] Perform connected component extraction on the extracted pure black pixel points to obtain the pure black region;

[0022] For each carbon fiber yarn contour, calculate the complement of the pure black region therein to obtain the light black region of each carbon fiber yarn contour.

[0023] Further, the pure black grayscale threshold is:

[0024] Calculate the average grayscale value of each yarn contour in the image that meets the angle threshold range, and calculate the average value of the calculated average grayscale values. The obtained average value is the pure black grayscale threshold.

[0025] Further, in the judgment of whether the area of the light black region in the yarn contour exceeds the set value, the set value is 50%.

[0026] Further, when judging whether the area of the light black region in the yarn contour exceeds the set value, if it exceeds, it is judged as interference, and it also includes:

[0027] Judge whether the average grayscale value of the light black region is greater than the average grayscale value of the pure black region plus 20. If it is greater, it is judged as interference.

[0028] The present invention further includes a carbon fiber defect detection system, which uses the method as described above. The detection system includes:

[0029] A tension unit, configured to set a double-roller structure in the camera detection area and apply a set tension to the carbon fiber yarn;

[0030] An image acquisition unit, configured to acquire an image of the carbon fiber yarn and identify the contour of the carbon fiber yarn in the image;

[0031] An included angle calculation unit, configured to calculate the minimum circumscribed rectangle for each of the carbon fiber yarn contours and calculate the included angle between the long side of the minimum circumscribed rectangle and the side of the image;

[0032] An angle judgment unit, configured to set an angle threshold range and screen out the yarn contours that do not meet the angle threshold range;

[0033] A double-threshold segmentation unit, configured to divide the screened yarn contours into a pure black area and a light black area by a double-threshold segmentation method;

[0034] A judgment unit, configured to judge whether the area of the light black area in the yarn contour exceeds a set value. If it exceeds, it is judged as interference; if it does not exceed, it is judged as a defect.

[0035] The present invention further includes a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method as described above is implemented.

[0036] The present invention further includes a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method as described above is implemented.

[0037] The beneficial effects of the present invention are as follows: The present invention calculates the area ratio of the light black area in the yarn contour. If the area ratio of the light black area exceeds a preset threshold, it is judged as interference, that is, the shadow interference caused by shaking. If the area ratio of the light black area does not exceed the set value, the area is judged as a real defect. Through the above steps, false alarms caused by the shaking of the carbon fiber tow can be effectively reduced, and the accuracy and reliability of defect detection can be significantly improved. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1is a flow chart of the method of the present invention;

[0040] Figure 2 It is a structural schematic diagram of the system of the present invention;

[0041] Figure 3 It is a schematic diagram of the structure of the computer device of the present invention. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0043] like Figure 1 As shown: A carbon fiber defect detection method comprises the following steps:

[0044] A double roller structure is set in the camera detection area to apply a set tension to the carbon fiber yarn;

[0045] Collect carbon fiber yarn images and identify the contours of the carbon fiber yarns in the images;

[0046] Calculate the minimum circumscribed rectangle for each carbon fiber yarn contour, and calculate the angle between the long side of the minimum circumscribed rectangle and the image side;

[0047] Set the angle threshold range to filter out the yarn profiles that do not meet the angle threshold range;

[0048] The screened yarn contours are divided into pure black area and light black area by using a double threshold segmentation method;

[0049] Determine whether the light black area occupies the yarn contour area exceeding the set value. If so, it is judged as interference; if not, it is judged as a defect.

[0050] In the detection area of ​​the camera, a double roller structure is set to apply a set tension to the carbon fiber yarn to reduce false alarms caused by yarn shaking and shaking. This step stabilizes the motion state of the yarn by mechanical means to reduce the impact of shaking on detection accuracy. An industrial camera is used to collect real-time images of carbon fiber yarns, and the image processing algorithm is used to identify the yarn contour in the image. This step is used to separate the yarn from the background and form contour data for analysis.

[0051] For each recognized carbon fiber yarn profile, calculate its minimum bounding rectangle. Then, further calculate the angle between the long side of the minimum bounding rectangle and the image boundary. Through this calculation, the skewing phenomenon caused by the yarn's wobbling can be captured. Based on the angle distribution of normal yarns (usually 0 degrees or 180 degrees), set an angle threshold range (e.g., ± several degrees). Through this threshold range, filter out the yarn profiles that do not meet the angle requirements, which may deviate from the normal angle due to wobbling.

[0052] For the filtered abnormal yarn profiles, use the double-threshold segmentation method to divide them into a pure black area and a light black area. The pure black area corresponds to the normal carbon fiber yarn, while the light black area may be shadows or defects caused by wobbling. Calculate the area ratio of the light black area in the yarn profile. If the area ratio of the light black area exceeds the preset threshold, it is judged as interference, i.e., shadow interference caused by wobbling. If the area ratio of the light black area does not exceed the set value, it is judged that the area is a real defect.

[0053] Through the above steps, false alarms caused by the wobbling of carbon fiber tows can be effectively reduced, significantly improving the accuracy and reliability of defect detection.

[0054] In this embodiment, a double-roller structure is set in the camera detection area, including: setting a pressure roller and a pulling roller in the area where the camera performs image acquisition to apply tension to the carbon fiber yarn.

[0055] By setting the pressure roller and the pulling roller, the carbon fiber yarn can be effectively controlled in the detection area, reducing the jitter amplitude of the yarn, thereby reducing false alarms caused by wobbling. This can improve the accuracy of the visual detection system, ensure the stability of the yarn during the image acquisition process, and help better identify actual defects.

[0056] Among them, recognizing the carbon fiber yarn profile in the image includes the following steps:

[0057] Convert the carbon fiber yarn image into a grayscale image;

[0058] Perform threshold segmentation on the grayscale image to extract the pixel points with grayscale values less than the set value;

[0059] Perform connected component extraction on the extracted pixel points and filter them through an area threshold to remove the connected components with an area smaller than the area threshold, obtaining the carbon fiber yarn profile.

[0060] First, convert the collected image of the carbon fiber yarn into a grayscale image. The grayscale image can simplify image processing, reduce computational complexity, and make the difference between the brightness of the yarn and the background more obvious. Perform a threshold segmentation operation on the grayscale image. Set a grayscale threshold and extract the pixel points with grayscale values less than the set value. This step can effectively separate the darker yarn area from the brighter background area.

[0061] Perform a connected component analysis on the extracted pixel points to identify the connected pixel groups in the image and form independent regions. This step separates each part of the yarn from the background by analyzing the connectivity of the pixels. Perform an area screening on the extracted connected components. Set an area threshold and remove the connected components with areas less than the threshold. This step is used to filter out noise and other possible misdetected regions, and only retain the connected components with larger areas, finally obtaining the contour of the carbon fiber yarn.

[0062] Among them, through the double-threshold segmentation method, the selected yarn contour is divided into a pure black area and a light black area, including the following steps:

[0063] Extract the pure black pixel points in the extracted carbon fiber yarn contour by setting a pure black grayscale value threshold;

[0064] Perform a connected component extraction on the extracted pure black pixel points to obtain a pure black area;

[0065] For each carbon fiber yarn contour, calculate the complement of the pure black area in it to obtain the light black area of each carbon fiber yarn contour.

[0066] First, set a pure black grayscale value threshold for the carbon fiber yarn contour. This threshold is used to distinguish the very dark pixel points in the yarn from other pixel points. In the extracted carbon fiber yarn contour, for all pixel points, screen out the pixel points with grayscale values lower than the set pure black grayscale value threshold. In this way, the pixel points of the pure black part in the yarn can be extracted.

[0067] Perform a connected component analysis on the extracted pure black pixel points to combine the connected pure black pixel points together to form one or more independent pure black areas. The purpose of this step is to ensure that each pure black area is a continuous dark area in the yarn and filter out isolated noise points.

[0068] For each carbon fiber yarn contour, calculate the complement of the pure black area. The complement refers to the yarn pixel points that do not belong to the pure black area. These pixel points usually have slightly brighter grayscale values than the pure black area, so they are defined as the light black area. The calculation method of the light black area is to subtract the pixels of the pure black area from the total pixels of the yarn contour, and the remaining pixel points are the light black area. Dividing the contour of the carbon fiber yarn into a pure black area and a light black area provides a basis for subsequent judgment of whether there are defects or interferences in the yarn.

[0069] In this embodiment, the pure black grayscale threshold is:

[0070] Calculate the average grayscale value of each yarn contour that meets the angular threshold range in the image, and calculate the average value of the calculated average grayscale values. The obtained average value is the pure black grayscale threshold.

[0071] For each carbon fiber yarn contour that meets the angular threshold range selected, calculate the average grayscale value of all pixels within the contour to obtain the average grayscale value of each yarn contour. For example, for yarn contours A, B, and C, their average grayscale values g_A, g_B, and g_C are calculated respectively.

[0072] Sum up the average grayscale values of all yarn contours that meet the angular threshold range and calculate their average value. Suppose there are n yarn contours that meet the conditions, then the calculation formula for the total average grayscale value g_avg is:

[0073] ;

[0074] The pure black grayscale threshold calculated by this method can be adaptively determined according to the brightness of normal yarn contours in the image, so as to accurately segment the pure black area in the carbon fiber yarn. This dynamic threshold setting can improve the reliability and adaptability of detection.

[0075] As a preference of the above embodiment, when judging whether the area of the light black region in the yarn contour exceeds the set value, the set value is 50%.

[0076] Among them, when judging whether the area of the light black region in the yarn contour exceeds the set value, if it exceeds, it is judged as interference, and it also includes:

[0077] Judge whether the average grayscale value of the light black region is greater than the average grayscale value of the pure black region plus 20. If it is greater, it is judged as interference.

[0078] Calculate the grayscale values of the pixels in the light black region to obtain the average grayscale value G of the light black region 淡黑 , and at the same time, calculate the average grayscale value G of the pure black region 纯黑 , compare G 淡黑 and G 纯黑 + 20:

[0079] If G 淡黑 > G 纯黑If it is +20, then it is determined that this area is an interference area because at this time, the gray level of the light black area is significantly higher than that of the pure black area, indicating that this area is affected by interference factors such as jitter and smear. By combining the dual judgments of the area ratio and the gray level difference, the recognition accuracy of the interference factors in carbon fiber detection can be effectively improved, and false alarms caused by problems such as jitter and shadow can be avoided.

[0080] As Figure 2 shown, this embodiment also includes a carbon fiber defect detection system. Using the method as described above, the detection system includes:

[0081] A tension unit for setting a double-roller structure in the camera detection area and applying a set tension to the carbon fiber yarn;

[0082] An image acquisition unit for acquiring carbon fiber yarn images and identifying the carbon fiber yarn contours in the images;

[0083] An included angle calculation unit for calculating the minimum circumscribed rectangle for each carbon fiber yarn contour and calculating the included angle between the long side of the minimum circumscribed rectangle and the image side;

[0084] An angle judgment unit for setting an angle threshold range and screening out the yarn contours that do not meet the angle threshold range;

[0085] A dual-threshold segmentation unit for dividing the screened yarn contours into a pure black area and a light black area by the dual-threshold segmentation method;

[0086] A judgment unit for judging whether the area of the light black area in the yarn contour exceeds a set value. If it exceeds, it is judged as interference; if it does not exceed, it is judged as a defect.

[0087] Please refer to Figure 3 the structural schematic diagram of the computer device provided by the embodiment of the present application shown. A computer device 400 provided by the embodiment of the present application includes: a processor 410 and a memory 420. The memory 420 stores a computer program executable by the processor 410. When the computer program is executed by the processor 410, it executes the method as described above.

[0088] The embodiment of the present application also provides a storage medium 430. A computer program is stored on the storage medium 430. When the computer program is run by the processor 410, it executes the method as described above.

[0089] Among them, the storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0090] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The meaning of "a plurality" is two or more unless otherwise specifically defined.

[0091] In the present invention, unless otherwise clearly specified and limited, the terms "mounted", "connected", "coupled", "fixed", etc. shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0092] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0093] Any process or method description represented in a flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where functions may be performed in an order not shown or discussed, including in a substantially simultaneous manner according to the functions involved or in a reverse order, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0094] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0095] It should be understood that the various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0096] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-described embodiment methods can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0097] The storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A carbon fiber defect detection method, characterized in that: The steps include: A double roller structure is set in the camera detection area to apply a set tension to the carbon fiber yarn; Collect carbon fiber yarn images and identify the contours of the carbon fiber yarns in the images; Calculating a minimum circumscribed rectangle for each of the carbon fiber yarn contours, and calculating an angle between a long side of the minimum circumscribed rectangle and an edge of the image; Setting an angle threshold range and screening out yarn profiles that do not meet the angle threshold range; The screened yarn contours are divided into pure black area and light black area by using a double threshold segmentation method; Determine whether the light black area occupies the yarn contour area beyond the set value. If so, it is judged as interference; if not, it is judged as a defect; The method of identifying the carbon fiber yarn profile in the image comprises the following steps: Convert the carbon fiber yarn image to a grayscale image; Performing threshold segmentation on the grayscale image to extract pixel points whose grayscale values ​​are less than a set value; Performing connected domain extraction on the extracted pixel points, and screening them by an area threshold, removing connected domains whose areas are smaller than the area threshold, and obtaining the carbon fiber yarn profile; The method of dividing the screened yarn contour into a pure black area and a light black area by using a double threshold segmentation method includes the following steps: extracting pure black pixel points from the extracted carbon fiber yarn contour by setting a pure black gray value threshold; Perform connected domain extraction on the extracted pure black pixel points to obtain a pure black area; For each carbon fiber yarn profile, the complement of the pure black area is calculated to obtain the light black area of ​​each carbon fiber yarn profile; The pure black grayscale threshold is: The average grayscale value of each yarn profile in the image that meets the angle threshold range is calculated, and the average of the calculated average grayscale values ​​is calculated, and the obtained average value is the pure black grayscale threshold.

2. The carbon fiber defect detection method according to claim 1, characterized in that: The double-roll structure is arranged in the camera detection area, including: a pressing roller and a pulling roller are arranged in the camera image acquisition area to apply tension to the carbon fiber yarn.

3. The carbon fiber defect detection method according to claim 1, characterized in that: In the process of judging whether the light black region occupies more than a set value in the yarn contour area, the set value is 50%.

4. The carbon fiber defect detection method according to claim 3, characterized in that: The method of judging whether the area of ​​the light black region occupied by the yarn outline exceeds a set value, and if so, judging it as interference, further includes: It is determined whether the average grayscale value of the light black area is greater than the average grayscale value of the pure black area plus 20. If it is greater, it is determined to be interference.

5. A carbon fiber defect detection system, characterized in that: Using the method according to any one of claims 1 to 4, the detection system comprises: A tension unit, which is used to set a double roller structure in the camera detection area to apply a set tension to the carbon fiber yarn; An image acquisition unit, used for acquiring carbon fiber yarn images and identifying the contours of the carbon fiber yarns in the images; An angle calculation unit, used for calculating the minimum circumscribed rectangle for each of the carbon fiber yarn contours, and calculating the angle between the long side of the minimum circumscribed rectangle and the image side; An angle judgment unit, used to set an angle threshold range and filter out yarn profiles that do not meet the angle threshold range; A double-threshold segmentation unit is used to divide the screened yarn profile into a pure black area and a light black area by a double-threshold segmentation method; The judging unit is used to judge whether the area of ​​the light black area occupied by the yarn contour exceeds the set value. If it exceeds, it is judged as interference; if it does not exceed, it is judged as a defect.

6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

7. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images