Carbonization line carbon fiber defect detection system and method

Abstract

The invention relates to the technical field of carbon fiber production, in particular to a carbonization line carbon fiber defect detection system and method, and the system comprises a light source auxiliary system which is arranged at a to-be-detected carbon fiber and applies illumination to the to-be-detected carbon fiber; the image acquisition system is used for performing image acquisition on the to-be-detected carbon fiber; the image processing system comprises a CNN neural network unit and is used for processing the image acquired by the image acquisition system and outputting a detection result through the CNN neural network unit; and the warning system is used for giving out a warning when the image processing system detects that the defects occur. According to the method, automatic detection of the defects of the carbon fibers is achieved through the steps, the missing detection risk of manual detection is avoided, and the detection efficiency and the quality control capability of carbon fiber production are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon fiber production, and in particular to a carbonized line carbon fiber defect detection system and method. 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] In the process of carbon fiber production, defects such as hair balls, hairy fibers, broken fibers, and joints will appear. Relying solely on manual visual methods to detect defects in the carbon fiber production process will inevitably result in missed detections, so it is necessary to rely on a visual system to conduct real-time online monitoring of carbon fiber defects in the carbon fiber production process.

[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 carbonized carbon fiber defect detection system and method, 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 carbonized carbon fiber defect detection system, comprising: A light source auxiliary system, which is arranged at the carbon fiber to be inspected and applies light to it; An image acquisition system, wherein the image acquisition system acquires images of the carbon fiber to be detected; An image processing system, wherein the image processing system includes a CNN neural network unit, processes the image acquired by the image acquisition system, and outputs the detection result through the CNN neural network unit; The warning system is used to issue a warning when the image processing system detects defects.

[0007] Furthermore, the light source auxiliary system comprises: Two light bars, the two light bars are arranged in parallel on the top of the carbon fiber, the middle interval includes at least one interval, and the two light bars are arranged perpendicular to the moving direction of the carbon fiber; A bottom plate, the bottom plate is arranged on the bottom of the carbon fiber, and the bottom plate is arranged to be white or transparent; A light shield is arranged on the two light bars, the carbon fiber to be detected and the bottom plate to shield them from light and prevent external light sources from entering.

[0008] Furthermore, the image acquisition system comprises: An industrial camera is arranged on the top of the carbon fiber to be detected, and collects images of the carbon fiber downward; Two grooved rollers are arranged at two ends of the carbon fiber to be detected, and the carbon fiber passes through the two grooved rollers.

[0009] Furthermore, the industrial camera is arranged on the upper part of the two light bars and is located in the interval between the two light bars.

[0010] Furthermore, the CNN neural network unit includes: An input layer, from which the collected image is input; A first convolutional layer, wherein the first convolutional layer preprocesses the input image; A first sampling layer, wherein the first sampling layer extracts features from the image; A second convolutional layer, wherein the second convolutional layer processes the extracted features; A second sampling layer, wherein the second sampling layer further extracts the processed features; A fully connected layer, wherein the fully connected layer performs label judgment on the extracted features; The output layer outputs the judgment result.

[0011] Furthermore, when extracting features from an image, the features include: the shape, width and / or angle of the graphic.

[0012] The present invention also includes a method for detecting defects in carbonized carbon fibers, using the system as described above, the method comprising: Apply light to the carbon fiber to be tested; Capturing an image of the carbon fiber to be detected to obtain a carbon fiber image, and converting the carbon fiber image into a grayscale image; Using a CNN neural network to extract and identify features of the carbon fiber in the grayscale image, and output a detection result; When a defect is detected, an alert is issued.

[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 light source auxiliary system is installed in the detection area of ​​the carbon fiber to be detected, and applies uniform and stable lighting to the carbon fiber to avoid the influence of external light changes on the image acquisition quality, thereby ensuring the clarity and consistency of the detection image; real-time image acquisition is performed on the carbon fiber area to be detected, and detailed images of the carbon fiber production process are captured to provide high-quality input data for subsequent image processing; the image processing system includes a CNN neural network unit, which is responsible for processing and analyzing the image data transmitted by the image acquisition system. The image processing model based on the CNN neural network can automatically extract a variety of features from the carbon fiber image, identify defects such as hair balls, hairy fibers, broken fibers and joints, and output the detection results; when the image processing system identifies a defect, the warning system will immediately send a warning signal. The warning system can ensure that the warning signal reaches the operator's area synchronously through delay settings, combined with the production line speed, so that defects can be handled in time to ensure the quality of carbon fiber production. 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 It is a structural schematic diagram of the system of the present invention; Figure 2 is a flow chart of the method of the present invention; Figure 3 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 Shown: A carbonized carbon fiber defect detection system, comprising: A light source auxiliary system, which is arranged at the carbon fiber to be inspected and applies light to it; An image acquisition system, wherein the image acquisition system acquires images of the carbon fiber to be inspected; The image processing system includes a CNN neural network unit, which processes the images collected by the image acquisition system and outputs the detection results through the CNN neural network unit; Warning system: The warning system is used to issue a warning when the image processing system detects defects.

[0020] The light source auxiliary system is installed in the detection area of ​​the carbon fiber to be detected, and applies uniform and stable lighting to the carbon fiber to avoid the influence of external light changes on the image acquisition quality, thereby ensuring the clarity and consistency of the detection image; real-time image acquisition is performed on the carbon fiber area to be detected, capturing detailed images of the carbon fiber production process, and providing high-quality input data for subsequent image processing; the image processing system includes a CNN neural network unit, which is responsible for processing and analyzing the image data transmitted by the image acquisition system. The image processing model based on the CNN neural network can automatically extract a variety of features from the carbon fiber image, identify defects such as hair balls, hairs, broken wires and joints, and output the detection results; when the image processing system identifies a defect, the warning system will immediately send a warning signal. The warning system can ensure that the warning signal reaches the operator's area synchronously through delay settings combined with the production line speed, so that defects can be handled in time to ensure the quality of carbon fiber production.

[0021] Through the above steps, automatic detection of carbon fiber defects is achieved, avoiding the risk of missed detection in manual inspection and greatly improving the inspection efficiency and quality control capabilities of carbon fiber production.

[0022] In this embodiment, the light source auxiliary system includes: Two light bars, the two light bars are arranged in parallel on the top of the carbon fiber, the middle interval includes at least one interval, and the two light bars are arranged perpendicular to the moving direction of the carbon fiber; A bottom plate, the bottom plate is arranged on the bottom of the carbon fiber, and the bottom plate is arranged to be white or transparent; The shading hood is set on the two light bars, the carbon fiber to be inspected and the bottom plate to shield them from light and prevent external light sources from entering.

[0023] Two light source strips are arranged in parallel above the carbon fiber and perpendicular to the direction of movement of the carbon fiber. A certain interval is kept between the two light strips to provide uniform lighting effects, reduce shadows and uneven brightness problems, and thus improve the clarity of image acquisition. The base plate is located below the carbon fiber and is designed to be white or transparent. The white base plate can enhance the light reflection effect and help highlight the defect characteristics of the carbon fiber; the transparent base plate reduces background interference in specific application scenarios and provides clearer contrast. The sunshade covers the top and sides of the two light strips, carbon fiber and base plate to block interference from external ambient light. The design of the sunshade ensures the uniformity of the light source, so that the image acquisition system can obtain stable lighting effects under various external light conditions, and reduces reflection and glare to ensure the consistency and quality of the detection image.

[0024] Among them, the image acquisition system includes: Industrial camera: The industrial camera is set on the top of the carbon fiber to be tested, and collects images of the carbon fiber downward; Two grooved rollers are arranged at both ends of the carbon fiber to be detected, and the carbon fiber passes through the two grooved rollers.

[0025] The industrial camera is installed above the carbon fiber and faces downward to capture images of the carbon fiber. The camera can adapt to fast-moving carbon fiber and has high resolution and high frame rate, ensuring that clear image details can be captured in high-speed carbon fiber production lines (such as 20 meters / minute), providing high-quality image input for defect detection. Two grooved rollers are respectively set at both ends of the carbon fiber to be detected, so that the carbon fiber can pass through the detection area stably under the guidance of the grooved rollers. The design of the grooved roller fixes the position of the carbon fiber to prevent it from shaking up and down or left and right during operation, thereby reducing image distortion caused by carbon fiber position offset, and further ensuring the stability and accuracy of the collected image.

[0026] As a preferred embodiment of the above embodiment, the industrial camera is arranged on the upper part of the two light bars and located in the interval between the two light bars.

[0027] The industrial camera is installed above the two light bars and in the interval between them. By placing the camera in the interval between the light bars, direct reflections of the lighting source can be effectively avoided from entering the camera's field of view, thereby reducing glare and unnecessary light interference. Placing the industrial camera in the center interval of the light bars not only evenly receives balanced light from the light bars on both sides, but also ensures that the light source can evenly cover the entire inspection area. This layout ensures the stability and uniformity of the lighting, so that the images collected by the camera have better contrast and clarity.

[0028] Among them, the CNN neural network unit includes: Input layer, the collected images are input from the input layer; The first convolution layer, the first convolution layer preprocesses the input image; The first sampling layer extracts features from the image; The second convolutional layer processes the extracted features; The second sampling layer further extracts the processed features; Fully connected layer, the fully connected layer performs label judgment on the extracted features; Output layer: The output layer outputs the judgment results.

[0029] The first convolution layer performs preliminary feature extraction on the input image, and uses multiple convolution kernels to scan local areas of the image to extract basic features such as edges and textures of carbon fiber defects. This process weights the features, enhances significant features, and suppresses irrelevant background. The first sampling layer (usually the pooling layer) downsamples the feature map after convolution, reducing the data dimension while retaining key features, thereby reducing the amount of calculation and enhancing the translation invariance of the features.

[0030] The second convolutional layer further processes the features extracted by the first sampling layer, digging deeper into higher-level feature information, allowing the system to more accurately capture the subtle features of carbon fiber defects. The second sampling layer downsamples the convolutional feature map again to further reduce the amount of data and improve the generalization ability of the model to ensure detection accuracy. In the fully connected layer, the extracted features are combined and mapped to a higher-dimensional space for analysis, and various defects (such as hair balls, hairs, broken wires, and joints) are classified and labeled.

[0031] The design of the CNN neural network unit structure can effectively extract the key features in carbon fiber images, and through layer-by-layer processing and discrimination, it can achieve efficient and accurate detection of defects, providing reliable technical support for quality monitoring of carbon fiber production.

[0032] As a preferred embodiment of the above embodiment, when extracting features from an image, the features include: the shape, width and / or angle of the graphic.

[0033] In the preferred embodiment of the above carbonized line carbon fiber defect detection system, the feature extraction process is further refined, and the extraction of features in the image includes the following key parameters: Shape: refers to the shape characteristics of a specific defect or structure. Different types of defects can be identified by analyzing the outline and shape of the object in the carbon fiber image. Shape can be used to distinguish the shape differences of defects, such as distinguishing the morphological characteristics of hair balls and broken fibers.

[0034] Width: During the inspection process, the width feature helps to identify areas of abnormal thickness in the carbon fiber. By analyzing the width changes of the carbon fiber, the system can detect abnormal thickness that is different from normal fibers, which is particularly important in the detection of defects such as broken fibers and hairy fibers.

[0035] Angle: Angle feature extraction is used to analyze the directionality or tilt of carbon fiber defects, which can further help distinguish between fiber connection and breakage. For example, in joint defects, angle features can be used to determine whether the joining direction of the carbon fiber is as expected.

[0036] By extracting these characteristic parameters (squareness, width and angle), the CNN neural network unit can more accurately characterize the characteristics of different defects, thereby improving the accuracy and robustness of detection, making the system's detection effect more reliable and stable in actual production.

[0037] like Figure 2 As shown, this embodiment also includes a carbonized carbon fiber defect detection method, using the above-mentioned system, the method includes: Apply light to the carbon fiber to be tested; Capturing images of the carbon fiber to be detected to obtain a carbon fiber image, and converting the carbon fiber image into a grayscale image; Use CNN neural network to extract and identify the features of carbon fiber in grayscale images and output the detection results; When a defect is detected, an alert is issued.

[0038] An industrial camera is used to capture images of carbon fiber. The captured images are usually color images, but in order to simplify subsequent processing, the images will be converted into grayscale images. Grayscale images can reduce the interference of color information and focus on reflecting the shape, texture and other characteristics of carbon fiber surface defects.

[0039] The converted grayscale image is input into the CNN neural network unit. Through the convolution layer and sampling layer of the neural network, the key features of the carbon fiber image (such as shape, width, angle, etc.) are extracted, and defects are identified based on the extracted features. Through multi-level feature processing, the CNN neural network finally determines whether there are defects in the image and classifies the types of defects detected (such as hair balls, hair fibers, broken fibers, joints, etc.).

[0040] Once the inspection system identifies defects in the carbon fiber, the warning system will issue an alarm in real time based on the production line speed and inspection position. The alarm can be a voice prompt, light signal or other form to remind the operator to deal with the defects in time.

[0041] This method combines light source auxiliary systems, industrial cameras, CNN neural networks and other technologies to achieve efficient and real-time detection of defects in the carbon fiber production process, effectively reduce the missed detection rate of manual inspection, and improve the quality control accuracy of the production process.

[0042] See also Figure 3 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.

[0043] 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.

[0044] 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 storage, flash memory, disk or optical disk.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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 carbonized carbon fiber defect detection system, characterized in that: include: A light source auxiliary system, which is arranged at the carbon fiber to be inspected and applies light to it; An image acquisition system, wherein the image acquisition system acquires images of the carbon fiber to be detected; An image processing system, wherein the image processing system includes a CNN neural network unit, processes the image acquired by the image acquisition system, and outputs the detection result through the CNN neural network unit; The warning system is used to issue a warning when the image processing system detects defects.

2. The carbonized wire carbon fiber defect detection system according to claim 1 is characterized in that: The light source auxiliary system comprises: Two light bars, the two light bars are arranged in parallel on the top of the carbon fiber, the middle interval includes at least one interval, and the two light bars are arranged perpendicular to the moving direction of the carbon fiber; A bottom plate, the bottom plate is arranged on the bottom of the carbon fiber, and the bottom plate is arranged to be white or transparent; A light shield is arranged on the two light bars, the carbon fiber to be detected and the bottom plate to shield them from light and prevent external light sources from entering.

3. The carbonized wire carbon fiber defect detection system according to claim 2, characterized in that: The image acquisition system comprises: An industrial camera is arranged on the top of the carbon fiber to be detected, and collects images of the carbon fiber downward; Two grooved rollers are arranged at two ends of the carbon fiber to be detected, and the carbon fiber passes through the two grooved rollers.

4. The carbonized wire carbon fiber defect detection system according to claim 3 is characterized in that: The industrial camera is arranged on the upper part of the two light bars and is located at the interval between the two light bars.

5. The carbonized wire carbon fiber defect detection system according to claim 1, characterized in that: The CNN neural network unit includes: An input layer, from which the collected image is input; A first convolutional layer, wherein the first convolutional layer preprocesses the input image; A first sampling layer, wherein the first sampling layer extracts features from the image; A second convolutional layer, wherein the second convolutional layer processes the extracted features; A second sampling layer, wherein the second sampling layer further extracts the processed features; A fully connected layer, wherein the fully connected layer performs label judgment on the extracted features; An output layer outputs a judgment result.

6. The carbonized wire and carbon fiber defect detection system according to claim 5, characterized in that: When extracting features from an image, the features include: the shape, width and / or angle of the graphic.

7. A method for detecting defects in carbonized carbon fibers, characterized in that: Using the system as claimed in any one of claims 1 to 6, the method comprises: Apply light to the carbon fiber to be tested; Capturing an image of the carbon fiber to be detected to obtain a carbon fiber image, and converting the carbon fiber image into a grayscale image; Using a CNN neural network to extract and identify features of the carbon fiber in the grayscale image, and output a detection result; When a defect is detected, an alert is issued.

8. 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 as claimed in claim 7 is implemented.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method as claimed in claim 7 is implemented.

Images