Carbon fiber tow joint detection method, device, equipment and medium
By performing grayscale processing and convolutional edge extraction on the carbon fiber tow images, combined with threshold segmentation, the problem of defect detection of carbon fiber joints is solved, automatic identification and alarm are realized, and production quality control is improved.
Patent Information
- Application Number
- CN202411249985.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
During the carbon fiber production process, manual operation cannot effectively monitor the yarn conveyed at high speed, making it difficult to detect joint defects, especially the joint and hair mass are visually similar, and the prior art is difficult to distinguish.
By acquiring the carbon fiber tow image, performing grayscale processing and using lateral and longitudinal matrix convolution to extract edge information, combining the grayscale value threshold for communication domain segmentation, and determining whether the area area and perimeter exceed the set value to identify joint defects.
Automatic real-time detection and alarm of carbon fiber tow joint defects is realized, the production quality control level is improved, and the quality problems in high-speed production lines can be effectively dealt with.
Smart Images

Figure CN119090856A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of carbon fiber production, and in particular to a method, device, equipment and medium for detecting carbon fiber tow joints. 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 the reinforcement of carbon fiber reinforced resin-based composites (CFRP) in cutting-edge defense technologies such as aerospace and aviation. It is also a new material for the upgrading of civilian industries.
[0003] During the production process of carbon fiber, defects such as joints may occur, which will affect the quality of carbon fiber yarn. Due to the high speed of yarn delivery in the carbon fiber production line, it is impossible to achieve 100% state monitoring by manual labor, and it is easy to make mistakes. Joints and hair balls appear similar in appearance on the carbon fiber, so it is necessary to propose a joint detection method that is different from hair ball detection.
[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention
[0005] The present invention provides a carbon fiber tow joint detection method, device, equipment and medium, thereby effectively solving the problems in the background technology.
[0006] In order to achieve the above object, the technical solution adopted by the present invention is: a carbon fiber tow joint detection method, comprising the following steps: Obtain a carbon fiber tow image and perform grayscale processing to convert the image into a grayscale image; Convolving the grayscale image using a horizontal matrix and a vertical matrix respectively to obtain two convolved images; Combine the pixels at the same position in the two convolution images to obtain an edge point image; Extracting pixels in the edge point image by gray value threshold, and segmenting connected domains to obtain a plurality of region sets; It is determined whether the area and perimeter of the region set exceed the set value. If so, it is determined that there is a joint defect.
[0007] Furthermore, the transverse matrix Gx is: ; After convolving the grayscale image using the horizontal matrix, a convolution image GrayX(x, y) is obtained, where x and y are the horizontal and vertical coordinates in the image, respectively.
[0008] Furthermore, the longitudinal matrix Gy is: ; After convolving the grayscale image using the vertical matrix, a convolution image GrayY (x, y) is obtained.
[0009] Furthermore, combining the pixels at the same position in the two convolution images to obtain the edge point image includes: The pixels at the same position in the two convolution images are combined using the following formula: ; Wherein, EdgeGray(x, y) is the edge point image composed of the combined pixel points.
[0010] Furthermore, in extracting the pixel points in the edge point image by using a gray value threshold, the gray value threshold is [10, 255].
[0011] Further, the determining whether the area and perimeter of the region set exceed a set value includes: Filtering out regions with an area greater than 1*Height from the region set, where Height is the height of the carbon fiber tow image; Calculate the perimeter of the screened area. If the perimeter of an area is greater than 2.5*Height, it is determined that there is a joint defect.
[0012] The present invention also includes a carbon fiber tow joint detection device, using the above method, the detection device comprises: An image acquisition unit is used to acquire an image of a carbon fiber tow and perform grayscale processing to convert the image into a grayscale image; A convolution unit, used to convolve the grayscale image using a horizontal matrix and a vertical matrix respectively to obtain two convolution images; An edge point extraction unit is used to combine the pixels at the same position in the two convolution images to obtain an edge point image; A region extraction unit, used to extract pixel points in the edge point image by gray value threshold, and segment connected domains to obtain a plurality of region sets; The judging unit is used to judge whether the area and perimeter of the region set exceed the set value. If so, it is judged that there is a joint defect.
[0013] The present invention also includes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described above is implemented.
[0014] The present invention also includes a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.
[0015] The beneficial effects of the present invention are as follows: the present invention automatically determines the presence of joint defects and issues an alarm by real-time analysis of the connected areas in the image. This method can deal with quality problems that may occur in high-speed production lines and improve the production quality control level of carbon fiber. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is the grayscale image after grayscale processing; Figure 3 is the edge point image; Figure 4 It is the image after the pixels are extracted by gray value threshold; Figure 5 is the image after segmenting the connected domain; Figure 6 An image of a joint defect detected; Figure 7 It is a structural schematic diagram of the device of the present invention; Figure 8 It is a structural schematic diagram of the computer device of the present invention. DETAILED DESCRIPTION
[0018] 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.
[0019] like Figure 1 As shown: A method for detecting a carbon fiber tow joint comprises the following steps: Obtain the carbon fiber tow image and perform grayscale processing to convert the image into a grayscale image. The grayscale image is as follows Figure 2 As shown; Convolve the grayscale image using a horizontal matrix and a vertical matrix respectively to obtain two convolved images; The pixels at the same position in the two convolution images are combined to obtain the edge point image. The edge point image is as follows: Figure 3 As shown; The pixel points in the edge point image are extracted by gray value threshold. The extracted image is as follows Figure 4 As shown, the connected domain is segmented to obtain several region sets. The region set image is as follows Figure 5 As shown; Determine whether the area and perimeter of the region set exceed the set value. If so, it is determined that there is a joint defect. The joint defect is as follows: Figure 6 shown.
[0020] The image of the carbon fiber tow is obtained and converted into a grayscale image to reduce the complexity of the image. Grayscale processing can remove color information and retain brightness information, thereby simplifying subsequent edge detection and feature extraction operations. The grayscale image is convolved with a transverse matrix and a longitudinal matrix respectively to extract horizontal and vertical edge information in the image. The transverse matrix can extract edges in the horizontal direction, and the longitudinal matrix can extract edges in the vertical direction. After the convolution operation, two convolution images are obtained, which contain edge information in the horizontal direction and vertical direction respectively. The pixels at the same position in the two convolution images are combined together. This step is to generate a comprehensive edge point image. The combined image contains all possible edge information in the carbon fiber tow, including joints or defect edges in the horizontal and vertical directions.
[0021] The edge point image is extracted using the gray value threshold to further retain significant edges. By setting an appropriate threshold, noise can be eliminated and important edge information can be retained. Then connected domain segmentation is performed to segment the image into several independent region sets. Connected domain segmentation is based on the connectivity between pixels, and pixels with connected relationships are classified into one region, thereby forming candidate regions for joints or defects.
[0022] The segmented area set is judged and the area and perimeter of each area are calculated. By comparing whether the area and perimeter of these areas exceed the preset threshold, it is determined whether there is a joint defect. Generally speaking, the shape and size of the joint will be different from the area of the normal carbon fiber tow, and the area exceeding the set value is considered a joint defect.
[0023] In this embodiment, the transverse matrix Gx is: ; After convolving the grayscale image with the horizontal matrix, the convolution image GrayX(x, y) is obtained, where x and y are the horizontal and vertical coordinates of the image respectively.
[0024] The essence of convolution is to use the matrix Gx as a filter, traverse the grayscale image pixel by pixel, and calculate the weighted sum at each position. Suppose the grayscale image of the original image is represented as Gray(x,y), where x and y are the horizontal and vertical coordinates of the image. Then after convolution, the convolution image GrayX(x,y) is represented as: ; Among them, Gx(i,j) is the element of the Gx matrix, and Gray(x+i,y+j) is the grayscale value of the adjacent pixel. This formula means that the Gx matrix is overlaid on a small block of the image, and then the elements at the corresponding positions are multiplied and summed, and the result is assigned to the convolution image GrayX(x,y) at the corresponding position. By performing a convolution operation on the entire grayscale image, the horizontal edges will be highlighted, forming a convolution image that reflects the horizontal changes in the carbon fiber tow. This convolution image can be used as the basic data for subsequent edge point extraction, connected domain segmentation and other steps to further analyze and detect joint defects.
[0025] The longitudinal matrix Gy is: ; After convolving the grayscale image with the vertical matrix, the convolved image GrayY(x, y) is obtained.
[0026] Similarly, the longitudinal matrix will highlight the vertical edges by performing a convolution operation on the entire grayscale image, forming a convolution image that reflects the vertical changes in the carbon fiber tow.
[0027] As a preferred embodiment of the above, combining pixels at the same position in two convolution images to obtain an edge point image includes: The pixels at the same position in the two convolution images are combined using the following formula: ; Wherein, EdgeGray(x, y) is the edge point image composed of the combined pixel points.
[0028] In this way, the obtained EdgeGray (x, y) image will contain both horizontal and vertical edge information. This is more comprehensive than using only horizontal or vertical convolution images, and can more accurately reflect the edge features of defects such as joints and hairballs.
[0029] Among them, in the process of extracting pixel points in the edge point image through the gray value threshold, the gray value threshold is [10, 255].
[0030] Grayscale values of 0 represent black, 255 represent white, and values between the two represent different brightness levels. By setting the lower limit to 10, low-brightness noise pixels are removed. This noise may come from the background or other irrelevant minor interference. By filtering out pixels with grayscale values below 10, noise interference in the image can be effectively reduced. These noises may be caused by slight brightness fluctuations or minor errors in the optical system and are usually not meaningful. Pixels with grayscale values above 10 are retained. These pixels are more likely to represent significant edge information in the image, especially when detecting joint defects. These edges may reflect the outline or shape of the defect. The significant edge area in the carbon fiber tow can be effectively extracted, while removing useless noise. This provides cleaner input data for subsequent connected domain segmentation and defect detection, and improves the accuracy and reliability of the detection system.
[0031] In this embodiment, determining whether the area and perimeter of the region set exceed the set value includes: Filter out regions with an area greater than 1*Height in the region set, where Height is the height of the carbon fiber tow image; Calculate the perimeter of the screened area. If the perimeter of an area is greater than 2.5*Height, it is determined that there is a joint defect.
[0032] Joint defects are often accompanied by larger areas and longer perimeters, because the fibers at the joints may be entangled or overlapped, resulting in complex shapes and obvious edges. The combination of area and perimeter can effectively distinguish joint defects from other possible interferences, such as hair balls. The area and perimeter of hair balls are usually small and do not meet these two conditions. Due to their special geometric characteristics, joint defects can be accurately located in complex carbon fiber images through this geometric screening method. By analyzing the connected areas in the image in real time, the presence of joint defects is automatically determined and an alarm is issued. This method can deal with quality problems that may occur in high-speed production lines and improve the production quality control level of carbon fiber.
[0033] like Figure 7 As shown, this embodiment also includes a carbon fiber tow joint detection device, using the above method, the detection device includes: An image acquisition unit is used to acquire an image of a carbon fiber tow and perform grayscale processing to convert the image into a grayscale image; A convolution unit, used to convolve the grayscale image using a horizontal matrix and a vertical matrix respectively, to obtain two convolution images; An edge point extraction unit is used to combine the pixels at the same position in the two convolution images to obtain an edge point image; A region extraction unit is used to extract pixel points in the edge point image through a gray value threshold, and to segment the connected domain to obtain a number of region sets; The judging unit is used to judge whether the area and perimeter of the region set exceed the set value. If so, it is judged that there is a joint defect.
[0034] See also Figure 8 A computer device 400 provided in an embodiment of the present application includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program executable by the processor 410, and when the computer program is executed by the processor 410, the above method is executed.
[0035] The embodiment of the present application further provides a storage medium 430 on which a computer program is stored. When the computer program is run by the processor 410, the above method is executed.
[0036] 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 red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.
[0037] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.
[0038] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0039] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.
[0040] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.
[0041] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0042] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0043] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0044] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, 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 cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.
Claims
1. A method for detecting carbon fiber tow joints, It is characterized in that The steps include: Obtain a carbon fiber tow image and perform grayscale processing to convert the image into a grayscale image; Convolving the grayscale image using a horizontal matrix and a vertical matrix respectively to obtain two convolved images; Combine the pixels at the same position in the two convolution images to obtain an edge point image; Extracting pixels in the edge point image by gray value threshold, and segmenting connected domains to obtain a plurality of region sets; It is determined whether the area and perimeter of the region set exceed the set value. If so, it is determined that there is a joint defect.
2. The carbon fiber tow joint detection method according to claim 1, It is characterized in that The transverse matrix Gx is: ; After convolving the grayscale image using the horizontal matrix, a convolution image GrayX(x, y) is obtained, where x and y are the horizontal and vertical coordinates in the image, respectively.
3. The carbon fiber tow joint detection method according to claim 2, It is characterized in that The longitudinal matrix Gy is: ; After convolving the grayscale image using the vertical matrix, a convolution image GrayY (x, y) is obtained.
4. The carbon fiber tow joint detection method according to claim 3, It is characterized in that The pixel points at the same position in the two convolution images are combined to obtain an edge point image, including: The pixels at the same position in the two convolution images are combined using the following formula: EdgeGray(x,y) = ; Wherein, EdgeGray(x, y) is the edge point image composed of the combined pixel points.
5. The carbon fiber tow joint detection method according to claim 1, It is characterized in that In the extracting of pixels in the edge point image by using a gray value threshold, the gray value threshold is [10, 255].
6. The carbon fiber tow joint detection method according to claim 1, It is characterized in that The determining whether the area and perimeter of the region set exceed a set value includes: Filtering out regions with an area greater than 1*Height from the region set, where Height is the height of the carbon fiber tow image; Calculate the perimeter of the screened area. If the perimeter of an area is greater than 2.5*Height, it is determined that there is a joint defect.
7. A carbon fiber tow joint detection device, It is characterized in that Using the method according to any one of claims 1 to 6, the detection device comprises: An image acquisition unit is used to acquire an image of a carbon fiber tow and perform grayscale processing to convert the image into a grayscale image; A convolution unit, used to convolve the grayscale image using a horizontal matrix and a vertical matrix respectively to obtain two convolution images; An edge point extraction unit is used to combine the pixels at the same position in the two convolution images to obtain an edge point image; A region extraction unit, used to extract pixel points in the edge point image by gray value threshold, and segment connected domains to obtain a plurality of region sets; The judging unit is used to judge whether the area and perimeter of the region set exceed the set value. If so, it is judged that there is a joint defect.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.
9. A storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
Citation Information
Patent Citations
Metal surface fine defect detection method and device based on deep learning
CN110189290A
Photovoltaic cell panel surface defect positioning method and device based on artificial intelligence
CN112288730A
Egg crack detection method and device
CN113686876A
Edge point extraction method, computer equipment and storage medium
CN113836479A
Style migration enhanced airport target detection method
CN114943869A
Cited By
Carbon fiber joint detection device and method suitable for warp knitting
CN120651746A
Image processing method and device, equipment, storage medium and program product
CN120852406A
