Fatigue test method, system and equipment based on texture change of carbon fiber and medium

Abstract

The invention provides a fatigue test method, system and equipment based on texture change of carbon fibers and a medium, and belongs to the technical field of material tests.The method comprises the steps that a carbon fiber composite material is selected as a test sample; applying a fatigue load to the test sample according to a designed test condition, and collecting a surface image of the test sample; the method comprises the following steps of: preprocessing an acquired image, clustering according to the gray level and texture similarity of pixels to obtain a plurality of clustering subareas, and marking different clustering areas by using different colors to complete color mapping; extracting texture feature parameters from the image after color mapping, and performing PCA dimension reduction to obtain key texture feature parameters; and comparing the key texture feature parameters of the image under different test conditions, identifying texture feature changes, and completing fatigue performance evaluation. According to the method, image processing and texture feature analysis are combined, so that non-destructive testing of the CFRP fatigue performance is realized, and the testing accuracy and efficiency are improved.

Description

Technical Field

[0001] The present application belongs to the field of material testing technology, and specifically relates to a fatigue testing method, system, equipment and medium based on carbon fiber texture changes. Background Art

[0002] CFRP, short for Carbon Fiber Reinforced Polymer, is a carbon fiber reinforced composite material. Due to its high specific strength, corrosion resistance, and lightweight characteristics, CFRP is widely used in aerospace, rail transit, and other fields. For example, in aerospace, CFRP is used to manufacture key components such as aircraft fuselages and wings, significantly reducing aircraft weight and improving fuel efficiency and flight performance. In rail transit, it is used to manufacture train bodies, effectively reducing train operating energy consumption and increasing speed. However, CFRP's inherent heterogeneity and anisotropy make it prone to surface defects caused by stress concentration during processing. It is also prone to noise fatigue damage such as fiber pullout, delamination, and tearing during long-term service. Once these defects occur, they seriously threaten the service life and performance stability of the material. For example, if fiber pullout or delamination occurs on the surface of an aircraft wing, it can cause the structure to rapidly deteriorate when subjected to huge aerodynamic loads during flight, leading to serious safety accidents.

[0003] Most of the existing fatigue performance testing methods are centered on mechanical testing and combined with surface morphology observation. However, this type of method has many drawbacks that are difficult to overcome. In terms of precision testing methods, traditional methods often rely on single indicators such as surface roughness to evaluate fatigue performance. However, these indicators cannot fully discover the complex and changeable texture characteristics of the CFPR surface, resulting in a large deviation between the evaluation results and the actual situation. In terms of detection efficiency, mechanical testing often requires destructive testing of samples. Not only can real-time monitoring of the fatigue process not be achieved, but the samples cannot be reused, increasing the testing cost and time cost. In addition, for CFRP surfaces with complex texture morphology and various sizes, traditional methods are even more difficult to meet the needs of high-precision quantitative analysis. For example, for CFRP materials with special woven structures or microscopic pores, traditional methods find it difficult to accurately extract and analyze their surface texture characteristics, and cannot provide a reliable basis for fatigue performance evaluation. Summary of the Invention

[0004] In a first aspect, an embodiment of the present application provides a fatigue testing method based on carbon fiber texture changes, comprising the following steps: S1. Select a carbon fiber composite material sample as a test sample; S2. Design different test conditions, apply fatigue loads to the test samples according to the test conditions, start the fatigue test, and collect surface images of the test samples under different test conditions; S3. After image preprocessing of the collected test sample surface image, clustering is performed according to the grayscale and texture similarity of the pixels to obtain several cluster partitions, and different cluster areas of the test sample surface image are marked with different colors to complete color mapping; S4. Extract texture feature parameters from the surface image of the test sample after color mapping, perform PCA dimensionality reduction on the extracted texture feature parameters, and obtain key texture feature parameters; S5. Compare key texture feature parameters of the test sample surface images under different test conditions, identify texture feature changes, and complete fatigue performance evaluation.

[0005] Furthermore, the specific steps of step S2 are as follows: S21. Determine the load type, load quantity, and load cycle number for fatigue testing; S22. Design a combination of load type, load quantity, and load cycle number as a test condition set; S23. Select a test condition from the test condition set, apply fatigue load to the test sample using a fatigue testing machine according to the load type, load quantity, and load cycle number of the selected test condition, start the fatigue test, and use an industrial camera to capture surface images of the test sample under different test conditions.

[0006] Furthermore, the specific steps of step S3 are as follows: S31 industrial camera transmits the collected test sample surface image to the back-end processor via the transmission interface; the transmission interface uses a GigE interface; S32. The back-end processor performs sharpening, illumination compensation, and median filtering preprocessing on the test sample surface image; S33. Backend processor usage K The value clustering algorithm segments the pre-processed test sample surface image based on the similarity of grayscale and texture to obtain several cluster areas; S34. The back-end processor uses a rainbow gradient table to perform color mapping on different clustered areas of the test sample surface image, so that different clustered areas are identified by different colors.

[0007] Furthermore, the specific steps of step S32 are as follows: S321. Use a high-pass filtering algorithm, select a convolution kernel with a window size of 3×3, and perform a Laplace sharpening algorithm on the test sample surface image to enhance the edge information of the test sample surface image and complete the sharpening process; S322. Convert the sharpened test sample surface image into a grayscale image and apply a histogram equalization algorithm to the entire image for illumination compensation to reduce uneven contrast caused by light source changes; S323. For each pixel point in the test sample surface image after illumination compensation, the pixel value is updated by taking the median value of a preset neighborhood window to complete median filtering.

[0008] Furthermore, the specific steps of step S33 are as follows: S331. Initialize according to the size of the test sample surface image K value, and randomly select K Initial cluster centers; S332. Calculate the RGB value for each pixel and calculate the RGB value of each pixel K The distance between the cluster centers is calculated and the pixel value is assigned to the category to which the cluster center closest to the pixel belongs. S333. Recalculate the center of each cluster, that is, the mean of the RGB values of all pixels in the cluster; S334. Determine whether the difference between the updated cluster center and the cluster center before the update is less than a threshold; If yes, go to step S335; If not, return to step S333; S335. The area to which pixels belonging to the same cluster belong is regarded as a cluster area, and a number of cluster areas whose color and texture similarities are less than a threshold are obtained.

[0009] Furthermore, the specific steps of step S34 are as follows: S341. Calculate the grayscale eigenvalue for each cluster area; S342. Assigning a color to each cluster region using a rainbow color mapping table according to the grayscale feature value of each cluster region; S343. Use the assigned color to mark each cluster area.

[0010] Furthermore, the specific steps of step S4 are as follows: S41. Using the color co-occurrence matrix to extract the numerical value of the characteristic parameters of the carbon fiber texture image after color mapping; S42. Extracting the angular second moment parameter value of the texture feature of the test sample surface image after color mapping; S43 extracts the contrast parameter value from the texture features of the test sample surface image after color mapping; S44 extracts the energy parameter value from the texture features of the test sample surface image after color mapping; S45. After normalizing the extracted texture feature parameter values, a PCA dimensionality reduction model is used to select the number of principal components to retain based on the variance explained by the data. Through principal component analysis, the original texture feature set is converted into a new feature representation.

[0011] In a second aspect, an embodiment of the present application further provides a fatigue testing system based on carbon fiber texture changes, comprising: A test sample selection module is used to select carbon fiber composite material samples as test samples; The test condition design module is used to design different test conditions, apply fatigue loads to the test samples according to the test conditions, start fatigue testing, and collect surface images of the test samples under different test conditions; The image processing and partition mapping module is used to perform image preprocessing on the collected test sample surface image, cluster the pixels according to their grayscale and texture similarity to obtain a number of cluster partitions, and use different colors to mark different cluster areas of the test sample surface image to complete color mapping; The feature dimension reduction module is used to extract texture feature parameters from the test sample surface image after color mapping, and perform PCA dimension reduction on the extracted texture feature parameters to obtain key texture feature parameters; The fatigue performance assessment module compares key texture feature parameters of test sample surface images under different test conditions, identifies texture feature changes, and completes fatigue performance assessment. Through principal component analysis, the original texture feature set is converted into a new feature representation.

[0012] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the steps of the fatigue testing method based on carbon fiber texture changes as described in the first aspect are implemented.

[0013] In a fourth aspect, an embodiment of the present application further provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the fatigue testing method based on carbon fiber texture changes as described in the first aspect.

[0014] It can be seen from the above technical solutions that this application has the following advantages: The fatigue testing method, system, equipment and medium based on carbon fiber texture changes provided in this application use industrial cameras to collect images for analysis, avoid direct physical contact with carbon fiber composite samples, and reduce additional damage that may be introduced by contact testing. Through image preprocessing, clustering segmentation, color mapping image processing, and texture feature parameter extraction and dimensionality reduction, it is possible to accurately capture subtle changes in the surface texture of carbon fiber composite materials during fatigue, providing a data basis for fatigue performance evaluation. Compared with traditional detection methods, this greatly improves the accuracy of the evaluation and reduces the testing cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 It is a schematic flow chart of the fatigue testing method based on carbon fiber texture change of the present invention.

[0017] Figure 2 It is a schematic flow chart of the fatigue testing system based on carbon fiber texture change of the present invention. DETAILED DESCRIPTION

[0018] The various embodiments of the present disclosure will be described more fully below in detail in the specific steps of the fatigue testing method based on carbon fiber texture changes. The present disclosure can have various embodiments, and adjustments and changes can be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, and that the present disclosure should be construed to encompass all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of the present disclosure.

[0019] For example, carbon fiber reinforced plastic (CFRP), with its exceptional high specific strength, excellent corrosion resistance, and lightweight properties, plays a vital role in high-tech sectors such as aerospace and rail transportation. In aerospace, CFRP is widely used in the manufacture of core components such as aircraft fuselages and wings, significantly reducing aircraft weight and thus improving fuel efficiency and flight performance. In rail transportation, it has become an ideal material for train bodies, effectively reducing operating energy consumption and accelerating train speed increases. However, the heterogeneous and anisotropic properties of CFRP present numerous challenges during processing and use. During processing, the material is prone to surface defects due to stress concentration. Furthermore, over long-term service, it is susceptible to fatigue damage such as fiber pullout, delamination, and tearing. Once these defects develop, they pose a serious threat to the material's service life and performance stability. For example, if fiber pullout or delamination occurs on the surface of an aircraft wing, the structural strength of the wing will drop sharply when subjected to the enormous aerodynamic loads, potentially leading to serious safety accidents. Therefore, accurate and efficient testing of the fatigue properties of CFRP materials is crucial to ensuring their safety and reliability in practical applications.

[0020] However, existing fatigue performance testing methods have many limitations that are difficult to overcome. In terms of accuracy, traditional methods often rely on a single indicator such as surface roughness to evaluate fatigue performance. However, the surface texture of CFRP is complex and changeable, and these single indicators cannot fully reveal its true situation, resulting in a large deviation between the evaluation results and the actual situation. In terms of detection efficiency, mechanical testing usually requires destructive testing of samples, which not only cannot achieve real-time monitoring of the fatigue process, but also the samples cannot be reused once tested, thereby increasing the testing cost and time cost. In addition, faced with CERP surfaces with complex textures and diverse sizes, traditional methods are even more difficult to meet the needs of high-precision quantitative analysis. For example, for CFRP materials with special woven structures or microscopic pores, traditional methods find it difficult to accurately extract and analyze their surface texture characteristics, and thus cannot provide a reliable basis for fatigue performance evaluation.

[0021] In summary, the existing CFRP fatigue performance testing methods have shortcomings in terms of accuracy, efficiency and applicability, and new technologies and methods are urgently needed to overcome these limitations.

[0022] To address the above issues, this embodiment provides a fatigue testing method based on carbon fiber texture changes. By collecting surface images of carbon fiber composite material CFRP under different fatigue test conditions, these images are preprocessed, clustered, color mapped, and texture feature extracted using image processing. In combination with PCA dimensionality reduction technology, key texture feature parameters are obtained to evaluate the fatigue performance of CFRP. This not only improves the accuracy and efficiency of fatigue testing, but also reduces testing costs.

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] See also Figure 1 FIG. 1 is a flow chart of a fatigue testing method based on carbon fiber texture changes in a specific embodiment, the method comprising the following steps: S1. Select a carbon fiber composite material sample as a test sample; It should be noted that a specific type of carbon fiber composite material was used as the test sample; S2. Design different test conditions, apply fatigue loads to the test samples according to the test conditions, start the fatigue test, and collect surface images of the test samples under different test conditions; It should be noted that by designing diverse test conditions, we can simulate various fatigue conditions that materials may face in actual use, comprehensively evaluate material performance, and collect images under different test conditions to provide a data basis for subsequent analysis of texture changes of materials under different fatigue states. S3. After image preprocessing of the collected test sample surface image, clustering is performed according to the grayscale and texture similarity of the pixels to obtain several cluster areas, and different cluster areas of the test sample surface image are marked with different colors to complete color mapping; It should be noted that image preprocessing improves image quality and reduces noise and light interference; clustering partitioning can classify complex images according to texture features, facilitating subsequent analysis; color mapping allows different cluster areas to be presented intuitively, enhancing the visualization effect of image analysis and helping to quickly identify changes in texture features; S4. Extract texture feature parameters from the surface image of the test sample after color mapping, perform PCA dimensionality reduction on the extracted texture feature parameters, and obtain key texture feature parameters; It should be noted that through principal component analysis, the original texture feature set will be converted into a new feature representation. The surface texture of the material is quantitatively described by extracting texture feature parameters. PCA dimensionality reduction is used to remove redundant information and retain key features, which simplifies the data analysis process, improves analysis efficiency, and highlights the key texture features that have an important impact on fatigue performance evaluation. S5. Compare key texture feature parameters of the test sample surface images under different test conditions, identify texture feature changes, and complete fatigue performance evaluation; It should be noted that by comparing the key texture characteristic parameters under different test conditions, it is possible to identify the texture change pattern of the material under different fatigue states, thereby accurately evaluating the fatigue performance of the material.

[0025] This embodiment achieves non-destructive testing of CFRP fatigue properties by combining image processing and texture feature analysis, thereby improving the accuracy and efficiency of the test.

[0026] Furthermore, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another fatigue testing method based on carbon fiber texture changes is provided, which includes the following steps: S1. Select a carbon fiber composite material sample as a test sample; The specific steps of step S1 are as follows: S11. Determine the material type of the carbon fiber composite material to be tested; illustratively, the material type is T300 carbon fiber / epoxy resin composite material, or IM7 carbon fiber / epoxy resin composite material, or T700S carbon fiber / epoxy resin composite material; S12 determines the size and quantity of the carbon fiber composite material sample to be tested; illustratively, the size of the carbon fiber composite material sample to be tested includes the length, width and height of the sample; S2. Design different test conditions, apply fatigue loads to the test samples according to the test conditions, start the fatigue test, and collect surface images of the test samples under different test conditions; The specific steps of step S2 are as follows: S21. Determine the load type, load quantity, and load cycle number for fatigue testing; S22. Design a combination of load type, load quantity, and load cycle number as a test condition set; It should be noted that the load type is an alternating load; the alternating load requires determining the frequency, maximum load and stress ratio; the maximum load needs to be set according to the load that the carbon fiber composite material can withstand, and the stress ratio is the ratio of the minimum load to the maximum load that the carbon fiber composite material can withstand during actual service; for example, the frequency is 10 Hz, the maximum load does not exceed 50% of the load limit that the carbon fiber composite material can withstand, and the stress ratio is 0.1; the number of samples in step S12 can be set according to the number of loads to meet the fatigue test comparison of different load sizes under the same test conditions; the alternating load is applied to the test sample for a preset period of time as a load cycle; S23. Select a test condition from the test condition set, apply a fatigue load to the test sample using a fatigue testing machine according to the load type, load quantity, and load cycle number of the selected test condition, start the fatigue test, and use an industrial camera with a resolution higher than a set threshold to capture surface images of the test sample under different test conditions; For example, an alternating load with a frequency of 10 Hz, a stress ratio of 0.1, and a maximum load no greater than 50% of the load limit of the carbon fiber composite material is applied to the test sample using a fatigue testing machine; different maximum loads of 1000 N, 2000 N, and 3000 N are selected and applied to three test samples, and the number of fatigue cycles performed on each test sample for each maximum load value is set to 10,000; at the same time, a surface image (initial image) of each test sample before the fatigue load is applied and a surface image after 10,000 cycles are captured using an industrial camera with a resolution of 20 megapixels; Another fatigue test scenario involves applying an alternating load of 10 Hz, a stress ratio of 0.1, and a maximum load of 2000 N to a test specimen using a fatigue testing machine. The alternating load is applied to a single test specimen for 6,000, 8,000, and 10,000 fatigue cycles, respectively. Simultaneously, a 20-megapixel industrial camera captures surface images of the specimen before fatigue load application (initial image), after 6,000 cycles, after 8,000 cycles, and after 10,000 cycles. The following steps are also included before step S23: Determine the required working distance and field of view of the industrial camera in advance based on the size of the test sample; Before capturing the image of the test sample surface, adjust the position, angle, and focal length of the industrial camera according to the required working distance and desired field of view; S3. After image preprocessing of the collected test sample surface image, the pixels are clustered according to their grayscale and texture similarity to obtain several cluster partitions, and different cluster partitions of the test sample surface image are marked with different colors to complete color mapping; The specific steps of step S3 are as follows: S31 industrial camera transmits the collected test sample surface image to the back-end processor via the transmission interface; the transmission interface uses a GigE interface; S32. The back-end processor performs sharpening, illumination compensation, and median filtering preprocessing on the test sample surface image; S33. Backend processor usage K The value clustering algorithm segments the pre-processed test sample surface image based on the similarity of grayscale and texture to obtain several cluster areas; S34. The back-end processor performs color mapping on different clustered areas of the test sample surface image using a rainbow gradient table, so that different clustered areas are identified by different colors; S4. Extract texture feature parameters from the surface image of the test sample after color mapping, perform PCA dimensionality reduction on the extracted texture feature parameters, and obtain key texture feature parameters; The specific steps of step S4 are as follows: S41. Extracting the numerical value of characteristic parameters of the carbon fiber texture image after color mapping using the color co-occurrence matrix; Specifically, the pixel pair position in the color co-occurrence matrix ( i,j ) for element values P ( i,j ) for characterization; S42. Angular second-order moment parameter value in the texture feature parameter of the test sample surface image after color mapping Perform extraction;

[0027] in, L It is grayscale; S43. Testing the contrast parameter value in the texture feature parameter of the sample surface image after color mapping Perform extraction;

[0028] S44. Testing the energy parameter value of the texture feature parameter in the sample surface image after color mapping Perform extraction; ; S45. After normalizing the extracted texture feature parameters, a PCA dimensionality reduction model is used to select the number of principal components to be retained based on the variance explanation ratio of the data; Specifically, the feature matrix is constructed based on the extracted texture feature parameters X ; For the feature matrix X Standardize and get the standardized feature matrix X norm :

[0029] in, is the feature matrix X The mean of is the feature matrix X variance; Calculate the normalized feature matrix X norm The covariance matrix of C :

[0030] in, is the number of eigenvalues; Solving for the covariance matrix The eigenvalues and eigenvectors of k The eigenvalues of the principal components; Normalize the feature matrix X norm Project to the principal component space and get the projection matrix Z :

[0031] in, It is before kThe eigenvectors of the principal components; It should be noted that through principal component analysis, the original texture feature set will be converted into a new feature representation; S5. Compare key texture feature parameters of the test sample surface images under different test conditions, identify texture feature changes, and complete fatigue performance evaluation; The specific steps of step S5 are as follows: S51. Compare key texture characteristic parameters of the same test sample after fatigue loading with the same number of load cycles at different maximum load values to evaluate the fatigue performance of the test sample at different maximum load values; S52. Compare key texture feature parameters of the same test sample after performing fatigue loading with different numbers of load cycles at the same maximum load value, and evaluate the fatigue performance of the test sample when performing different load cycles at the same maximum load value.

[0032] In an embodiment of the present invention, based on step S32, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0033] The specific steps of step S32 are as follows: S321. Use a high-pass filtering algorithm, select a convolution kernel with a window size of 3×3, and perform a Laplace sharpening algorithm on the test sample surface image to enhance the edge information of the test sample surface image and complete the sharpening process;

[0034] in, is the original test sample surface image, Δ 2 is the Laplace operator, g ( x,y ) is the sharpened test sample surface image; For example, for a discrete image, the following convolution kernel with a size of 3×3 is usually determined as a filter: ; S322. Convert the sharpened test sample surface image into a grayscale image and apply a histogram equalization algorithm to the entire image for illumination compensation to reduce uneven contrast caused by light source changes;

[0035] in, is the grayscale value of the input test sample surface image, is the grayscale value of the output test sample surface image, The gray value is j The number of pixels, N is the total number of pixels in the test sample surface image; S323. Update the pixel value of each pixel in the test sample surface image after illumination compensation by taking the median of a preset neighborhood window to complete median filtering; For example, taking a 3×3 neighborhood window as an example, the pixel at the center is the pixel to be processed, and the pixel values of the other 8 pixels in the neighborhood window and the pixel to be processed are obtained. The pixel values are arranged in descending order, and the pixel value at the center, that is, the 5th pixel value, is used to replace the pixel value of the pixel to be processed to complete median filtering. Median filtering is performed on each pixel in the test sample surface image in this way. In an embodiment of the present invention, based on step S33, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0036] The specific steps of step S33 are as follows: S331. Initialize according to the size of the test sample surface image K value, and randomly select K Initial cluster centers ; S332. Calculate RGB value for each pixel , calculate the RGB value of each pixel and K The distance between cluster centers , and assign the pixel value to the category to which the nearest cluster center belongs;

[0037] in, is the cluster center; S333. Recalculate the center of each cluster, that is, the RGB values of all pixels in the cluster The mean of

[0038] in, Is assigned to j A set of pixel RGB values of clusters; S334. Determine whether the difference between the updated cluster center and the cluster center before the update is less than a threshold; If yes, go to step S335; If not, return to step S333; S335. The area to which pixels belonging to the same cluster belong is regarded as a cluster area, and a number of cluster areas whose color and texture similarities are less than a threshold are obtained.

[0039] In an embodiment of the present invention, based on step S34, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0040] The specific steps of step S34 are as follows: S341. Calculate the grayscale eigenvalue for each cluster area; S342. Assigning a color to each cluster region using a rainbow color mapping table according to the grayscale feature value of each cluster region; S343. Use the assigned color to mark each cluster area.

[0041] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0042] like Figure 2 As shown, the following is an embodiment of the fatigue testing system based on carbon fiber texture changes provided by the embodiment of the present disclosure. This system and the fatigue testing methods based on carbon fiber texture changes in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the fatigue testing system based on carbon fiber texture changes, please refer to the embodiment of the fatigue testing method based on carbon fiber texture changes above.

[0043] The system includes: A test sample selection module is used to select carbon fiber composite material samples as test samples; The test condition design module is used to design different test conditions, apply fatigue loads to the test samples according to the test conditions, start fatigue testing, and collect surface images of the test samples under different test conditions; The image processing and partition mapping module is used to perform image preprocessing on the collected test sample surface image, cluster the pixels according to their grayscale and texture similarity to obtain a number of cluster partitions, and use different colors to mark different cluster areas of the test sample surface image to complete color mapping; The feature dimension reduction module is used to extract texture feature parameters from the test sample surface image after color mapping, and perform PCA dimension reduction on the extracted texture feature parameters to obtain key texture feature parameters; The fatigue performance evaluation module is used to compare key texture feature parameters of the test sample surface images under different test conditions, identify texture feature changes, and complete fatigue performance evaluation.

[0044] This embodiment achieves a comprehensive evaluation of CFRP fatigue performance by integrating modules for test sample selection, test condition design, image processing and partition mapping, feature dimensionality reduction, and fatigue performance evaluation.

[0045] The fatigue testing method based on carbon fiber texture change provided in the embodiment of the present application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently. In the embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0046] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a button, a camera, a display, and a SIM card interface, etc.

[0047] It is understood that the structures illustrated in the embodiments of the present application do not constitute specific limitations on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0048] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0049] The processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals based on the instruction opcode and timing signal to complete the control of instruction fetching and execution.

[0050] The processor may also include a memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or is reusing. If the processor needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0051] The above-mentioned electronic device realizes the fatigue testing method based on carbon fiber texture change of the present application, which selects samples of carbon fiber composite materials as test samples; designs different test conditions, applies fatigue loads to the test samples according to the test conditions, starts fatigue testing, and collects surface images of the test samples under different test conditions; after image preprocessing, the collected surface images of the test samples are clustered according to the grayscale and texture similarity of the pixels to obtain several cluster partitions, and different cluster areas of the surface images of the test samples are marked with different colors to complete color mapping; texture feature parameters are extracted from the surface images of the test samples after color mapping, and the extracted texture feature parameters are subjected to PCA dimensionality reduction to obtain key texture feature parameters; the key texture feature parameters of the surface images of the test samples under different test conditions are compared, texture feature changes are identified, and the technical solution for fatigue performance evaluation is completed, thereby achieving the beneficial effect of realizing non-destructive testing of CFRP fatigue performance and improving the accuracy and efficiency of the test by combining image processing and texture feature analysis.

[0052] The storage medium provided in the present application stores a program product that can implement a fatigue testing method based on carbon fiber texture changes.

[0053] The fatigue testing method based on carbon fiber texture changes includes: selecting a sample of carbon fiber composite material as a test sample; designing different test conditions, applying fatigue load to the test sample according to the test conditions, starting the fatigue test, and collecting surface images of the test sample under different test conditions; performing image preprocessing on the collected surface images of the test sample, clustering them according to the grayscale and texture similarity of the pixels to obtain a number of cluster partitions, and using different colors to mark different cluster areas of the test sample surface image to complete color mapping; extracting texture feature parameters from the color-mapped surface image of the test sample, performing PCA dimensionality reduction on the extracted texture feature parameters to obtain key texture feature parameters; comparing the key texture feature parameters of the surface images of the test sample under different test conditions, identifying texture feature changes, and completing fatigue performance evaluation.

[0054] In some possible embodiments, the fatigue testing method based on carbon fiber texture changes disclosed herein can be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure.

[0055] The storage medium of the present disclosure may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0056] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fatigue testing method based on carbon fiber texture changes, characterized in that: The steps include: S1. Select a carbon fiber composite material sample as a test sample; S2. Design different test conditions, apply fatigue loads to the test samples according to the test conditions, start the fatigue test, and collect surface images of the test samples under different test conditions; S3. After image preprocessing of the collected test sample surface image, clustering is performed according to the grayscale and texture similarity of the pixels to obtain several cluster partitions, and different cluster areas of the test sample surface image are marked with different colors to complete color mapping; S4. Extract texture feature parameters from the surface image of the test sample after color mapping, perform PCA dimensionality reduction on the extracted texture feature parameters, and obtain key texture feature parameters; S5. Compare key texture feature parameters of the test sample surface images under different test conditions, identify texture feature changes, and complete fatigue performance evaluation.

2. The fatigue testing method based on carbon fiber texture change according to claim 1, characterized in that: The specific steps of step S2 are as follows: S21. Determine the load type, load quantity, and load cycle number for fatigue testing; S22. Design a combination of load type, load quantity, and load cycle number as a test condition set; S23. Select a test condition from the test condition set, apply fatigue load to the test sample using a fatigue testing machine according to the load type, load quantity, and load cycle number of the selected test condition, start the fatigue test, and use an industrial camera to capture surface images of the test sample under different test conditions.

3. The fatigue testing method based on carbon fiber texture change according to claim 2, characterized in that: The specific steps of step S3 are as follows: S31 industrial camera transmits the collected test sample surface image to the back-end processor via the transmission interface; the transmission interface uses a GigE interface; S32. The back-end processor performs sharpening, illumination compensation, and median filtering preprocessing on the test sample surface image; S33. Backend processor usage K The value clustering algorithm segments the pre-processed test sample surface image based on the similarity of grayscale and texture to obtain several cluster areas; S34. The back-end processor uses a rainbow gradient table to perform color mapping on different clustered areas of the test sample surface image, so that different clustered areas are identified by different colors.

4. The fatigue testing method based on carbon fiber texture change according to claim 3, characterized in that: The specific steps of step S32 are as follows: S321. Use a high-pass filtering algorithm, select a convolution kernel with a window size of 3×3, and perform a Laplace sharpening algorithm on the test sample surface image to enhance the edge information of the test sample surface image and complete the sharpening process; S322. Convert the sharpened test sample surface image into a grayscale image and apply a histogram equalization algorithm to the entire image for illumination compensation to reduce uneven contrast caused by light source changes; S323. For each pixel point in the test sample surface image after illumination compensation, the pixel value is updated by taking the median value of a preset neighborhood window to complete median filtering.

5. The fatigue testing method based on carbon fiber texture change according to claim 3, characterized in that: The specific steps of step S33 are as follows: S331. Initialize according to the size of the test sample surface image K value, and randomly select K Initial cluster centers; S332. Calculate the RGB value for each pixel and calculate the RGB value of each pixel K The distance between the cluster centers is calculated and the pixel value is assigned to the category to which the cluster center closest to the pixel belongs. S333. Recalculate the center of each cluster, that is, the mean of the RGB values of all pixels in the cluster; S334. Determine whether the difference between the updated cluster center and the cluster center before the update is less than a threshold; If yes, go to step S335; If not, return to step S333; S335. The area to which pixels belonging to the same cluster belong is regarded as a cluster area, and a number of cluster areas whose color and texture similarities are less than a threshold are obtained.

6. The fatigue testing method based on carbon fiber texture change according to claim 3, characterized in that: The specific steps of step S34 are as follows: S341. Calculate the grayscale eigenvalue for each cluster area; S342. Assigning a color to each cluster region using a rainbow color mapping table according to the grayscale feature value of each cluster region; S343. Use the assigned color to mark each cluster area.

7. The fatigue testing method based on carbon fiber texture change according to claim 1, characterized in that: The specific steps of step S4 are as follows: S41. Extracting the numerical value of the characteristic parameters of the carbon fiber texture image after color mapping using the pixels in the color co-occurrence matrix; S42. Extracting the angular second moment parameter value of the texture feature of the test sample surface image after color mapping; S43 extracts the contrast parameter value from the texture features of the test sample surface image after color mapping; S44 extracts the energy parameter value from the texture features of the test sample surface image after color mapping; S45. After the extracted texture feature parameter values are standardized, a PCA dimensionality reduction model is used, and the number of principal components to be retained is selected based on the variance explanation ratio of the data.

8. A fatigue testing system based on carbon fiber texture changes, characterized in that: include: A test sample selection module is used to select carbon fiber composite material samples as test samples; The test condition design module is used to design different test conditions, apply fatigue loads to the test samples according to the test conditions, start fatigue testing, and collect surface images of the test samples under different test conditions; The image processing and partition mapping module is used to perform image preprocessing on the collected test sample surface image, cluster the pixels according to their grayscale and texture similarity to obtain a number of cluster partitions, and use different colors to mark different cluster areas of the test sample surface image to complete color mapping; The feature dimension reduction module is used to extract texture feature parameters from the test sample surface image after color mapping, and perform PCA dimension reduction on the extracted texture feature parameters to obtain key texture feature parameters; The fatigue performance evaluation module is used to compare key texture feature parameters of the test sample surface images under different test conditions, identify texture feature changes, and complete fatigue performance evaluation.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the fatigue testing method based on carbon fiber texture change as claimed in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fatigue testing method based on carbon fiber texture change as claimed in any one of claims 1 to 7 are implemented.

Images