A method, apparatus, system, and storage medium for material fatigue testing.

Abstract

This application provides a method, apparatus, system, and storage medium for material fatigue detection. The method acquires a target virtual image of a fatigued workpiece via a terminal, obtains preliminary detection results corresponding to the fatigued workpiece, and sends these preliminary detection results to a controller. The controller checks if the preliminary detection results match an analog signal to determine the final deformation detection result. It then determines whether to load the fatigued workpiece or mark it so that the measuring head can continue acquiring the corresponding virtual image. This invention eliminates the need for contact-based detection, achieving closed-loop real-time feedback for fatigued workpiece detection. It reduces the marking frequency or even eliminates the need for marking, thereby triggering changes in the fatigued workpiece's imaging frequency, lowering the performance requirements of the imaging equipment, eliminating the need for higher-resolution images, and achieving multi-dimensional deformation detection results through highly accurate image processing, overcoming the limitations of one-dimensional detection.

Description

Technical Field

[0001] This application relates to the field of computer processing technology, specifically to a method, device, system, and storage medium for material fatigue detection. Background Technology

[0002] Deformation testing is applied to various materials, not only to ensure product quality but also to verify the rationality of material design. During operation, the stress at various points in a material changes periodically over time; this periodically changing stress is called alternating stress (also known as cyclic stress). Under alternating stress, even if the stress on a part is below the material's yield point, cracks may still appear after a long period of operation, or a sudden complete fracture may occur—a phenomenon known as metal fatigue. Therefore, fatigue testing is needed to detect fatigue strength and ensure the reliability of various mechanical parts.

[0003] Traditional detection methods employ two approaches. One is full-field speckle recognition and measurement, such as the visual extensometer implementation method based on data speckle disclosed in patent document CN103575227B. However, this method involves complex image acquisition, using a sampling frequency of 10-20 times within a fatigue test loading cycle. This places extremely high demands on the sampling frequency of the industrial camera in the measuring head and requires very high computer processing power, and it cannot accurately obtain peak and trough data. Another approach uses contact measurement methods, such as the contact strain gauge disclosed in patent document CN 215766881 U. This method measures strain based on changes in resistance. However, it requires contact, has poor accuracy, is complex to operate, and has limited application scenarios, providing only measurement results in a single dimension and failing to obtain comprehensive measurement data.

[0004] Therefore, a new fatigue workpiece inspection solution is needed. Summary of the Invention

[0005] In view of this, embodiments of this specification provide a method, apparatus, system, and medium for detecting material fatigue, used for detecting deformation and strain processes in fatigued workpieces.

[0006] The embodiments in this specification provide the following technical solutions:

[0007] This specification provides a method for material fatigue testing, the method comprising: a controller acquiring a simulated signal of fatigue workpiece deformation; a terminal acquiring a target virtual image of the fatigue workpiece; the terminal obtaining a preliminary detection result of the target virtual image corresponding to the fatigue workpiece based on the target virtual image, and sending the preliminary detection result to the controller; wherein the target virtual image is used to obtain peak and trough information corresponding to the fatigue workpiece deformation; the controller receiving the preliminary detection result of the target virtual image corresponding to the fatigue workpiece sent by the terminal; if the simulated signal matches the preliminary detection result, determining the deformation detection result of the fatigue workpiece based on the target virtual image; and sending the deformation detection result to a fatigue testing machine; the fatigue testing machine receiving the deformation detection result returned by the controller, and determining, based on the deformation detection result, not to load the fatigue workpiece or not to mark the fatigue workpiece; or determining, based on the deformation detection result, to load the fatigue workpiece or re-mark the fatigue workpiece so that the measuring head continues to acquire the virtual image corresponding to the fatigue workpiece.

[0008] This specification also provides a terminal for material fatigue testing, the terminal comprising:

[0009] The first acquisition module is used to acquire a target virtual image of the fatigued workpiece;

[0010] The first obtaining module is used to obtain preliminary detection results of the target virtual image corresponding to the fatigued workpiece based on the target virtual image, and send the preliminary detection results to the controller; wherein the target virtual image is used to obtain peak and trough information corresponding to the deformation of the fatigued workpiece.

[0011] This specification also provides a controller for material fatigue detection, applied in the process of workpiece deformation detection, the controller comprising:

[0012] The second acquisition module is used to acquire the analog signal of the deformation of the fatigued workpiece;

[0013] The first receiving module is used to receive the preliminary detection results of the target virtual image corresponding to the fatigued workpiece sent by the terminal;

[0014] The second obtaining module is used to determine the deformation detection result of the fatigued workpiece based on the target virtual image if the simulated signal matches the preliminary detection result.

[0015] This specification also provides a fatigue testing machine for material fatigue detection, applied in the process of workpiece deformation detection. The fatigue testing machine includes:

[0016] The second receiving module is used to receive the deformation detection results sent by the controller, so as to determine whether to not load the fatigued workpiece or not to mark the fatigued workpiece based on the deformation detection results; or to determine whether to load the fatigued workpiece or to re-mark the fatigued workpiece based on the deformation detection results, so that the measuring head can continue to acquire the virtual image corresponding to the fatigued workpiece.

[0017] This invention also provides a measuring head for material fatigue detection, applied in the process of workpiece deformation detection. The measuring head includes: a laser rangefinder, a light source, an industrial lens, and an industrial camera.

[0018] A laser rangefinder is used to obtain the distance between the fatigued workpiece and the measuring head;

[0019] Industrial lenses and industrial cameras are used to acquire virtual images of the workpiece under test based on distance;

[0020] Light source, used to set the supplementary lighting information during the capture of the virtual image of the fatigued workpiece;

[0021] The industrial lens and industrial camera are also used to capture a target virtual image of the corresponding peaks and troughs during the deformation process of a fatigued workpiece, based on the supplementary lighting information.

[0022] This invention also provides a material fatigue detection system, comprising: a memory, a processor, and a computer program. The computer program is stored in the memory, and the processor executes the following method: a controller acquires a simulated signal of fatigue workpiece deformation; a terminal acquires a target virtual image of the fatigue workpiece; the terminal obtains a preliminary detection result corresponding to the target virtual image of the fatigue workpiece based on the target virtual image, and sends the preliminary detection result to the controller; wherein the target virtual image is used to obtain peak and trough information corresponding to the fatigue workpiece deformation; the controller receives the preliminary detection result of the target virtual image of the fatigue workpiece sent by the terminal; if the simulated signal matches the preliminary detection result, the deformation detection result of the fatigue workpiece is determined based on the target virtual image; and the deformation detection result is sent to a fatigue testing machine; the fatigue testing machine receives the deformation detection result returned by the controller, and determines, based on the deformation detection result, whether to not load the fatigue workpiece or not to mark the fatigue workpiece; or determines, based on the deformation detection result, to load the fatigue workpiece or re-mark the fatigue workpiece so that the measuring head continues to acquire the virtual image corresponding to the fatigue workpiece.

[0023] This invention also provides a readable storage medium storing a computer program. When executed by a processor, the computer program implements the following method: a controller acquires a simulated signal of fatigue workpiece deformation; a terminal acquires a target virtual image of the fatigue workpiece; the terminal obtains a preliminary detection result of the target virtual image corresponding to the fatigue workpiece based on the target virtual image, and sends the preliminary detection result to the controller; wherein the target virtual image is used to obtain peak and trough information corresponding to the fatigue workpiece deformation; the controller receives the preliminary detection result of the target virtual image corresponding to the fatigue workpiece sent by the terminal; if the simulated signal matches the preliminary detection result, the deformation detection result of the fatigue workpiece is determined based on the target virtual image; and the deformation detection result is sent to a fatigue testing machine; the fatigue testing machine receives the deformation detection result returned by the controller, and determines whether to not load the fatigue workpiece or not to mark the fatigue workpiece based on the deformation detection result; or determines whether to load the fatigue workpiece or re-mark the fatigue workpiece based on the deformation detection result, so that the measuring head continues to acquire the virtual image corresponding to the fatigue workpiece.

[0024] Compared with the prior art, the beneficial effects that at least one technical solution adopted in the embodiments of this specification can achieve include at least:

[0025] Non-contact detection not only achieves closed-loop real-time feedback for fatigue workpiece detection, but also determines whether to continue loading the fatigue workpiece or re-mark it (which can reduce the marking frequency or even eliminate the need for marking). This triggers a change in the shooting frequency of the fatigue workpiece, which can reduce the shooting frequency and thus lower the performance requirements of the shooting equipment. It eliminates the need to acquire higher-resolution images and can obtain multi-dimensional deformation detection results through high-precision image processing, breaking through the limitations of one-dimensional detection. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a scene diagram of material fatigue detection provided in an embodiment of the present invention;

[0028] Figure 2 This is an interactive schematic diagram of a material fatigue detection method provided in an embodiment of the present invention;

[0029] Figure 3 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 1;

[0030] Figure 4 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 2 ;

[0031] Figure 5 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 3 ;

[0032] Figure 6 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 4 ;

[0033] Figure 7 This is a schematic diagram of the structure of a measuring head provided in an embodiment of the present invention;

[0034] Figure 8 This is a schematic diagram of the structure of the terminal applied in the workpiece deformation detection process provided in an embodiment of the present invention;

[0035] Figure 9 This is a schematic diagram of the controller applied in the workpiece deformation detection process provided in an embodiment of the present invention;

[0036] Figure 10 This is a schematic diagram of the structure of a fatigue testing machine applied in the workpiece deformation detection process provided in an embodiment of the present invention;

[0037] Figure 11 This is a schematic diagram of a material fatigue detection system provided in the embodiments of this specification. Detailed Implementation

[0038] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0039] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this application, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0041] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0042] Additionally, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that practice can be carried out without these specific details.

[0043] Existing materials, such as mechanical parts like shafts, gears, bearings, blades, and springs, experience cyclical stress changes over time during operation. However, after a long period, metal fatigue and other phenomena can occur, leading to cracks or fractures. Therefore, fatigue tests are necessary to assess the strength of these materials.

[0044] In view of this, the inventors found that material fatigue testing usually adopts contact testing methods, which can only detect strain in one dimension and cannot achieve comprehensive measurement data. Alternatively, full-field speckle measurement methods are used, which take pictures but require extremely high camera sampling frequency. For example, even with a sampling frequency as high as 20 times, it is still impossible to obtain peak and trough data during fatigue testing, resulting in inaccurate detection. Furthermore, it has high requirements for camera performance, leading to high testing costs.

[0045] Based on this, the embodiments of this specification propose a processing solution: such as Figure 1 As shown, Figure 1This is a scenario diagram of material fatigue testing provided by an embodiment of the present invention. Specifically, a workpiece is loaded onto the fatigue testing machine 11 and marked, triggering the measuring head 12 to take a picture. The terminal 13 processes the captured virtual image to obtain a preliminary detection result and sends it to the controller 14. The controller obtains the simulated signal of the fatigued workpiece and receives the preliminary detection result sent by the terminal. If the simulated signal matches the preliminary detection result, the final deformation detection result is determined. By returning the deformation detection result to the fatigue testing machine through the controller, it can be further determined whether to continue loading the workpiece or mark the workpiece (e.g., reduce the frequency of workpiece placement), thereby triggering the measuring head to take a picture. That is, the shooting frequency can be controlled to a certain extent, especially by reducing the shooting frequency, reducing the performance requirements of the shooting equipment, and eliminating the need for high-frequency equipment and high processing power. On the other hand, the terminal of the present invention can improve the accuracy and efficiency of obtaining detection results by adopting a new processing method.

[0046] It should be noted that the controller can be integrated into a fatigue testing machine or terminal, or even into a measuring head or other equipment. This embodiment does not impose any limitations, as long as the functions of the controller described above can be achieved.

[0047] The technical solutions provided by the various embodiments of this application are described below with reference to the accompanying drawings.

[0048] Figure 2 Figure 2 is an interactive schematic diagram of a material fatigue detection method provided by an embodiment of the present invention. As shown in Figure 2, the method of the embodiment of the present invention may include:

[0049] Step S210: The controller acquires the analog signal of the fatigue workpiece deformation.

[0050] Specifically, see Figure 1 ,like Figure 1 As shown, the fatigue testing machine is connected to the controller. When a fatigue workpiece specimen is loaded on the fatigue testing machine, in some embodiments, marking points or speckle strain gauges are arranged on the workpiece specimen. When the fatigue testing machine performs tensile, compressive, or alternating tensile and compressive load fatigue performance tests on the workpiece specimen, the controller can read relevant signals and perform amplification and fitting processing to obtain simulated signals. The simulated signals may include the maximum or minimum values ​​of stress, etc.

[0051] Step S220: The terminal acquires the target virtual image of the fatigued workpiece.

[0052] Combination Figure 1When a fatigued workpiece is loaded onto the fatigue testing machine, the measuring head takes a picture to obtain a virtual image of the workpiece sample. The terminal then obtains the virtual image of the fatigued workpiece through the measuring head, ultimately acquiring the target virtual image to obtain the peak and trough information corresponding to the deformation of the fatigued workpiece. Existing high-frequency visual fatigue testing places extremely high demands on the sampling frequency of the industrial camera in the measuring head, as well as very high image processing capabilities, resulting in inaccurate measurements. Even with sampling frequencies as high as 20 times higher, accurate peak and trough data cannot be obtained. This invention eliminates the need for high-frequency sampling in the measuring head, thus eliminating the need for a terminal with high processing capabilities.

[0053] Step S230: The terminal obtains the preliminary detection result of the target virtual image corresponding to the fatigued workpiece based on the target virtual image, and sends the preliminary detection result to the controller; wherein the target virtual image is used to obtain the peak and trough information corresponding to the deformation of the fatigued workpiece.

[0054] The terminal receives virtual images captured by the measuring head, obtains preliminary detection results corresponding to the virtual image of the fatigued workpiece, and sends these preliminary detection results to the controller. If the controller detects that the preliminary detection results match the analog signal, it determines that the virtual image is the target virtual image, meaning that the detection result corresponding to the preliminary detection result is the detection result of the fatigued workpiece. In some embodiments, the measuring head captures several virtual images, but high-frequency acquisition is not required. The terminal extracts features from the virtual image captured at the current moment and sends the preliminary detection results to the controller. If the controller detects that the preliminary detection results match the analog signal, it determines that the virtual image is the target virtual image, meaning that the detection result corresponding to the preliminary detection result is the deformation detection result of the fatigued workpiece, and the target virtual image can obtain peak and trough information corresponding to the deformation of the fatigued workpiece. This invention can accurately obtain the deformation and strain process of fatigued workpieces by processing virtual images, breaking through the limitations of one-dimensional detection and realizing comprehensive image detection. In particular, it can detect the boundaries of images in the axial and lateral directions to obtain more accurate detection results. Furthermore, by processing the changes in image pixel display on the terminal, the maximum and minimum strain forces in the corresponding strain process can be obtained. Therefore, the deformation detection results correspond to the peak and trough information of the fatigued workpiece deformation displayed in the target virtual image.

[0055] Step S240: The controller receives the preliminary detection results of the target virtual image corresponding to the fatigued workpiece sent by the terminal.

[0056] In conjunction with the above embodiments, the controller receives the preliminary detection result of the virtual image corresponding to the fatigued workpiece sent by the terminal. If the controller detects that the preliminary detection result matches the acquired analog signal, it determines that the virtual image of the preliminary detection result is the target virtual image, and then determines the deformation detection result of the fatigued workpiece based on the target virtual image.

[0057] The virtual image can include one or more, meaning the corresponding preliminary detection results can also include one or more.

[0058] Step S250: If the controller detects that the analog signal matches the preliminary detection result, it determines the deformation detection result of the fatigued workpiece based on the target virtual image and sends the deformation detection result to the fatigue testing machine.

[0059] Specifically, if the controller detects a match between the analog signal and the preliminary detection result, the virtual image corresponding to the preliminary detection result is determined as the target virtual image. Based on this target virtual image, the deformation detection result corresponding to the fatigued workpiece is then determined. Finally, this deformation detection result is returned to the fatigue testing machine so that the machine can determine whether to load the fatigued workpiece or re-mark it. If the fatigue testing machine reloads or re-marks the fatigued workpiece, it further triggers the measuring head to determine whether to photograph the fatigued workpiece and obtain the corresponding virtual image.

[0060] Step S260: The fatigue testing machine receives the deformation detection results returned by the controller, and determines whether to not load the fatigue workpiece or not to mark the fatigue workpiece based on the deformation detection results, or determines whether to load the fatigue workpiece or to re-mark the fatigue workpiece based on the deformation detection results, so that the measuring head can continue to acquire the virtual image corresponding to the fatigue workpiece.

[0061] In conjunction with the above embodiments, the controller returns the deformation detection results to the fatigue testing machine. The fatigue testing machine then determines whether to load the fatigued workpiece or re-mark the fatigued workpiece based on the deformation detection results. If the fatigue testing machine reloads the fatigued workpiece or re-marks it, it further triggers the measuring head to determine whether it is necessary to take pictures of the fatigued workpiece and obtain the corresponding virtual image.

[0062] This invention employs, as follows Figure 1 The method shown feeds measurement data back to the fatigue testing machine, forming a closed-loop control that allows for accurate and reasonable setting of the sampling frequency, thereby accurately obtaining data on the peaks and troughs of the fatigue test. It eliminates the need for high-frequency imaging, reducing the performance requirements of the imaging equipment, while still achieving efficient and accurate test results and enabling strain control.

[0063] Figure 3This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 1 Terminals used in the workpiece deformation detection process, such as Figure 3 As shown, the method may include steps S310 to S320. Step S310 involves acquiring a target virtual image of the fatigued workpiece.

[0064] Step S320: Based on the target virtual image, obtain the preliminary detection result of the target virtual image corresponding to the fatigued workpiece, and send the preliminary detection result to the controller; wherein the target virtual image is used to obtain the peak and trough information corresponding to the deformation of the fatigued workpiece.

[0065] Steps S310 to S320 in this embodiment can be executed. Figure 2 For the technical solution in the method shown, please refer to the specific implementation process and technical principles. Figure 2 The relevant descriptions of the methods shown in steps S220 to S230 are not repeated here.

[0066] In this embodiment, the terminal can process all data in the image, especially the detection of axial and lateral boundaries and the efficient processing of marker points, thereby improving the accuracy and efficiency of deformation detection and overcoming the limitations of one-dimensional detection.

[0067] In some embodiments, obtaining a preliminary detection result of the target virtual image corresponding to the fatigued workpiece based on the target virtual image includes: obtaining an image sub-region corresponding to the target virtual image based on the target virtual image; performing grayscale and filtering processing on the image sub-region to obtain a filtered grayscale image; if the filtered grayscale image meets the speckle strain gauge conditions, then obtaining a preliminary detection result of the target virtual image.

[0068] Specifically, a target virtual image of the fatigued workpiece is obtained. Using pixels as the basic unit of virtual image composition, image processing is performed on the target virtual image. This involves dividing the target virtual image into different image sub-regions, and then performing grayscale and filtering processing on these sub-regions to obtain filtered grayscale images. For example, methods in OpenCV can be used to perform grayscale conversion and mean filtering on the image sub-regions. Specifically, grayscale conversion is performed based on the pixel matrix, and less important pixels in the image sub-regions are colored with the background color, thus highlighting the important parts of the virtual image.

[0069] Then, if the filtered grayscale image meets the speckle strain gauge conditions, a preliminary detection result of the target virtual image is obtained. Specifically, the Canny (edge ​​detection) algorithm is used to obtain the parts with prominent grayscale intensity changes on the filtered grayscale image. The filter grayscale image is then checked to see if it meets the speckle strain gauge conditions. This involves comparing the filtered grayscale image with a standard speckle strain gauge. If the gradient change of the filtered grayscale image conforms to the range of a speckle strain gauge, the filtered grayscale image is determined to be a speckle strain gauge, thus obtaining a preliminary detection result of the target virtual image. Specifically, pixel calculations are performed on the image sub-region of the speckle strain gauge to obtain the average pixel value of the image sub-region, and this average pixel value is marked at the center coordinates of the image sub-region. In some embodiments, the gradient change pattern of the speckle strain gauge in the Canny algorithm is used, for example, a certain grayscale gradient change range is defined as a speckle strain gauge, corresponding to a standard speckle strain gauge.

[0070] This embodiment not only uses a neural network model to quickly and accurately identify important information in images, especially information at fatigue workpiece marker points, but also performs local image segmentation to combine image grayscale pixel information to enhance the acquisition of deformation and stress changes at fatigue workpiece marker points, thereby improving the accuracy and efficiency of fatigue workpiece detection results.

[0071] For specific details, please refer to the following description. In some embodiments, obtaining the image sub-region corresponding to the target virtual image based on the target virtual image includes: inputting the target virtual image into a neural network model to obtain the coordinate information of the marker points on the fatigued workpiece in the target virtual image; and obtaining the image sub-region corresponding to the target virtual image based on the coordinate information.

[0072] Specifically, the target virtual image is input into a neural network model. This model, through the configuration of convolutional and connection layers, can accurately obtain the coordinate information of the fatigued workpiece in the target virtual image, especially the coordinate information of the fatigued workpiece marker points, such as (x, y, w, h; x and y represent the coordinate values ​​of the center point on the x and y axes, w represents the width, and h represents the height). Based on the coordinate information of the fatigued workpiece marker points, the target virtual image is divided into multiple corresponding image sub-regions. These image sub-regions are then used to obtain preliminary detection results of the fatigued workpiece. By obtaining the coordinates of the marker points on the target virtual image, the target virtual image is specifically divided, allowing for the subsequent clear acquisition of image information at the fatigued workpiece marker points. This facilitates the processing of the target virtual image, reduces processing requirements and processing space, and improves both the accuracy and efficiency of image processing. Compared to the existing technology that uses binocular stereo vision to acquire fatigued workpiece images, this embodiment of the invention only requires a measuring head with a single imaging module, reducing the requirements for cameras or video cameras used to capture fatigued workpiece images, thereby reducing shooting requirements and even the cost of the imaging equipment.

[0073] In some embodiments, the neural network model is trained using a large number of speckle strain gauge images. Convolutional layers are used for image feature extraction, followed by compression or segmentation to continuously optimize the threshold settings of each connection layer. Ultimately, coordinate information matching the coordinates of each sub-region in the speckle strain gauge is obtained, particularly the coordinates of marker points on the fatigued workpiece. The successfully trained neural network model is then applied to the above embodiments to obtain the coordinate information corresponding to marker points in the target virtual image and to obtain image sub-regions based on the marker point coordinate information.

[0074] In some embodiments, if the filtered grayscale image meets the speckle strain gauge conditions, a preliminary detection result of the target virtual image is obtained, including: if the filtered grayscale image meets the grayscale gradient threshold range, then the filtered grayscale image is a speckle strain gauge; processing the image sub-region corresponding to each speckle strain gauge to obtain preliminary detection results corresponding to all speckle strain gauges. Specifically, the preliminary detection result may include stress changes at the marked points of the fatigue workpiece, such as the maximum and minimum stresses, as well as the overall deformation and stress changes of the fatigue workpiece. In some embodiments, the stress conditions during the deformation process of the fatigue workpiece, such as being stretched or compressed, can be displayed through the characteristic changes of image grayscale, for example, a stress change curve can be obtained. In some cases, the maximum and minimum stress values ​​during the deformation process can be obtained through precise image processing, corresponding to the peak and trough information of the fatigue workpiece deformation in the image. Furthermore, the accuracy of the image capture or processing can be verified by obtaining the peak and trough values, and whether the image capture or processing meets the requirements.

[0075] Specifically, the coordinate information of fatigue workpiece markers on the target virtual image is obtained through a neural network model. The target virtual image is then divided into multiple image sub-regions, resulting in filtered grayscale images corresponding to each sub-region. The Canny algorithm is used to identify regions with prominent grayscale intensity changes on the filtered grayscale images. The filtered grayscale images are then tested to ensure they meet the criteria for a speckle strain gauge. This involves comparing the filtered grayscale image with a standard speckle strain gauge. If the gradient change of the filtered grayscale image conforms to the range of a speckle strain gauge, the filtered grayscale image is determined to be a speckle strain gauge, thus obtaining the preliminary detection result for the target virtual image. Specifically, pixel calculations are performed on the image sub-regions of the speckle strain gauge to obtain the average pixel value of the image sub-region, which is then marked at the center coordinates of the image sub-region. In some embodiments, the gradient change pattern of the speckle strain gauge is used in the Canny algorithm, for example, by setting a certain grayscale gradient change range as the speckle strain gauge, which corresponds to the standard speckle strain gauge.

[0076] This embodiment, following the virtual image obtained through a neural network model, uses the Canny edge detection algorithm to process the image sub-regions. This includes identifying the edges of each sub-region and the pixel grayscale value changes. If the grayscale value changes satisfy the speckle strain condition, a preliminary detection result is output from the filtered grayscale image that meets the condition. This eliminates the need for further neural network model processing, reducing image processing requirements. Following the prominent marker point information obtained from the neural network model, the Canny edge detection algorithm is used to further derive preliminary detection results based on the speckle strain defined by the marker points. This eliminates the need for complex algorithm settings, improving both the accuracy and speed of deformation detection.

[0077] In some embodiments, the method further includes: receiving a notification of the deformation detection result corresponding to the fatigued workpiece determined by the controller.

[0078] Specifically, the terminal sends the preliminary detection result to the controller. If the controller detects that the preliminary detection result matches the analog signal, it determines that the preliminary detection result is a deformation detection result and returns it to the terminal. In some embodiments, after receiving the notification of the deformation detection result, the terminal reduces the frequency of virtual image processing or narrows the scope of virtual image processing (e.g., virtual images before receiving the notification do not require processing). This ensures the accuracy of the image detection results while improving the detection rate.

[0079] Figure 4 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 2 Controllers used in the workpiece deformation detection process, such as Figure 4As shown, the method may include steps S410 to S430. Specifically, step S410 involves acquiring a simulated signal of fatigue workpiece deformation. Step S420 involves receiving a preliminary detection result from a target virtual image corresponding to the fatigue workpiece sent by a terminal. Step S430 involves determining the deformation detection result of the fatigue workpiece based on the target virtual image if the simulated signal matches the preliminary detection result.

[0080] Steps S410 to S430 in this embodiment can be executed. Figure 2 For the technical solution in the method shown, please refer to the specific implementation process and technical principles. Figure 2 The relevant descriptions of the methods shown in steps S210, S240 to S250 are not repeated here.

[0081] This invention, through the setting of a controller, not only acquires the analog signal of the fatigue testing machine, but also receives the preliminary test results obtained by the terminal processing. When the analog signal and the preliminary test results match, the final deformation test result is determined, so that the fatigue testing machine can further determine the loading of the workpiece or the marking of the workpiece, thereby indirectly controlling the shooting frequency, reducing the sampling frequency, eliminating the need for high-frequency shooting, reducing the equipment performance requirements, and still obtaining test results efficiently and accurately, thus realizing strain control.

[0082] In some embodiments, if the simulated signal matches the preliminary detection result, the target virtual image is used to obtain peak and trough information corresponding to the deformation of the fatigued workpiece.

[0083] In this embodiment of the invention, the controller acquires the deformation or strain process of a fatigued workpiece, obtains the maximum or minimum stress through analog signals, and the terminal extracts features from a virtual image to obtain the pixel display during the deformation or strain process, and then converts the pixel display into a stress pattern. The controller then matches the pixel conversion pattern with the maximum or minimum stress corresponding to the analog signal. If a match is found, a target virtual image is obtained, and this target virtual image can obtain the peak and trough information corresponding to the deformation of the fatigued workpiece.

[0084] In some embodiments, the method further includes sending the deformation detection results to a fatigue testing machine and a terminal.

[0085] In conjunction with the above embodiments, if the controller detects that the analog signal obtained from the fatigue testing machine matches the preliminary detection result obtained from the terminal, it determines that the preliminary detection result is a deformation detection result and sends the deformation detection result to the fatigue testing machine or the terminal. Then, after receiving the deformation detection result, the fatigue testing machine determines, based on the deformation detection result, whether to load the fatigue workpiece or not to mark the fatigue workpiece; or it determines, based on the deformation detection result, to load the fatigue workpiece or to re-mark the fatigue workpiece, so as to affect whether the measuring head continues to acquire the virtual image corresponding to the fatigue workpiece. In some embodiments, after receiving the notification of the deformation detection result, the terminal reduces the frequency of virtual image processing or narrows the scope of virtual image processing (e.g., virtual images before receiving the notification do not need to be processed). This forms a closed-loop control, realizing strain control, which can control the acquisition and shooting frequency of the measuring head, thereby reducing the requirements for the sampling frequency of the industrial camera, and at the same time reducing the requirements for the terminal's processing power; the sampling frequency does not need to be set to 20 times or higher.

[0086] Figure 5 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 3 Fatigue testing machines used in the process of workpiece deformation detection, such as Figure 5 As shown, the method includes step S510: receiving deformation detection results sent by the controller, so as to determine whether to not load the fatigued workpiece or not to mark the fatigued workpiece based on the deformation detection results; or to determine whether to load the fatigued workpiece or to re-mark the fatigued workpiece based on the deformation detection results, so that the measuring head can continue to acquire the virtual image corresponding to the fatigued workpiece. Step S510 in this embodiment can be executed... Figure 2 For the technical solution in the method shown, please refer to the specific implementation process and technical principles. Figure 2 The relevant descriptions of the method shown in step S260 will not be repeated here.

[0087] In conjunction with the above embodiments, after receiving the deformation detection result, the fatigue testing machine determines whether to not load the fatigued workpiece or not to mark it, based on the deformation detection result; or it determines whether to load the fatigued workpiece or re-mark it, so as to affect whether the measuring head continues to acquire the virtual image corresponding to the fatigued workpiece. This forms a closed-loop control, realizing strain control, which can control the acquisition and imaging frequency of the measuring head, thereby reducing the requirements for the sampling frequency of the industrial camera, and at the same time reducing the requirements for the terminal processing power. The sampling frequency does not need to be set to 20 times or higher.

[0088] Figure 6 This is a method flow chart for material fatigue detection provided by an embodiment of the present invention. Figure 4 Measuring heads used in workpiece deformation detection processes, such as Figure 6As shown, the method includes steps S610 to S620. Step S610 involves setting supplementary lighting information during the capture of the virtual image of the fatigued workpiece. Step S620 involves capturing a virtual image of the target corresponding to the peaks and troughs during the deformation process of the fatigued workpiece based on the supplementary lighting information.

[0089] See Figure 7 , Figure 7 This is a schematic diagram of the structure of a measuring head provided in an embodiment of the present invention, as shown below. Figure 7 As shown, the measuring head includes a laser rangefinder, a light source, an industrial camera, and an industrial lens. The laser rangefinder is used to acquire the distance between the fatigued workpiece and the measuring head. The industrial lens and industrial camera are used to acquire a virtual image of the workpiece based on the distance. The light source is used to set supplementary lighting information during the capture of the virtual image of the fatigued workpiece. The industrial lens and industrial camera are also used to capture a virtual image of the fatigued workpiece based on the supplementary lighting information, corresponding to the peaks and troughs during deformation.

[0090] Specifically, during the process of acquiring a virtual image, the measuring head obtains the virtual image based on the distance between the fatigued workpiece and the industrial camera obtained by the laser rangefinder. In some embodiments, since the lighting requirements for the shooting process vary depending on the distance, the measuring head sets supplementary lighting information during the shooting process of the target virtual image corresponding to the fatigued workpiece; then, based on the supplementary lighting information, it captures a target virtual image of the peaks and troughs corresponding to the deformation process of the fatigued workpiece. This improves the clarity of the acquired virtual image, thereby overcoming the limitations of one-dimensional detection and achieving comprehensive data detection, especially the detection of axial and transverse edges and marked areas. Furthermore, a new image algorithm can accurately and efficiently obtain the detection results, thereby achieving strain control. It can accurately and reasonably set the sampling frequency, thus accurately obtaining the peak and trough data of the fatigue test. High-frequency shooting is not required, reducing equipment performance requirements, while still obtaining detection results efficiently and accurately, achieving strain control.

[0091] Figure 8 This is a schematic diagram of the structure of a terminal applied in the workpiece deformation detection process provided in an embodiment of the present invention, as shown below. Figure 8 As shown, the terminal 80 includes:

[0092] The first acquisition module 81 is used to acquire a target virtual image of the fatigued workpiece;

[0093] The first obtaining module 82 is used to obtain a preliminary detection result of the target virtual image corresponding to the fatigued workpiece based on the target virtual image, and send the preliminary detection result to the controller; wherein the target virtual image is used to obtain the peak and trough information corresponding to the deformation of the fatigued workpiece.

[0094] Figure 8 The device of the illustrated embodiment can be used to perform corresponding actions. Figure 2 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0095] Figure 9 This is a schematic diagram of the controller applied in the workpiece deformation detection process provided in an embodiment of the present invention, as shown below. Figure 9 As shown, the controller 90 includes:

[0096] The second acquisition module 91 is used to acquire the analog signal of the deformation of the fatigued workpiece;

[0097] The first receiving module 92 is used to receive the preliminary detection results of the target virtual image corresponding to the fatigued workpiece sent by the terminal;

[0098] The second obtaining module 93 is used to determine the deformation detection result of the fatigued workpiece based on the target virtual image if the simulated signal matches the preliminary detection result.

[0099] Figure 9 The device of the illustrated embodiment can be used to perform corresponding actions. Figure 2 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0100] Figure 10 This is a schematic diagram of the structure of a fatigue testing machine applied in the workpiece deformation detection process provided in an embodiment of the present invention, as shown below. Figure 10 As shown, the fatigue testing machine includes:

[0101] The second receiving module 101 is used to receive the deformation detection results sent by the controller, so as to determine whether to load the fatigued workpiece or not to mark the fatigued workpiece based on the deformation detection results.

[0102] Figure 10 The device of the illustrated embodiment can be used to perform corresponding actions. Figure 2 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0103] Figure 11 This is a schematic diagram of a material fatigue detection system provided in the embodiments of this specification, such as... Figure 11 As shown, the system 110 includes: a processor 111, a memory 112, and a computer program; wherein

[0104] The memory 112 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0105] The processor 111 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0106] Alternatively, the memory 112 can be either standalone or integrated with the processor 111.

[0107] When the memory 112 is a device independent of the processor 111, the device may further include:

[0108] Bus 113 is used to connect the memory 112 and the processor 111.

[0109] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods provided in the various embodiments described above.

[0110] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0111] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0112] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0113] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the product embodiments described later are relatively simple since they correspond to the methods; relevant parts can be referred to the descriptions in the system embodiments.

[0114] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for material fatigue testing, characterized in that, An application of a terminal in the workpiece deformation detection process, the method comprising: The controller acquires analog signals of the deformation of the fatigued workpiece; The terminal acquires a target virtual image of the fatigued workpiece; Based on the target virtual image, a preliminary detection result corresponding to the target virtual image of the fatigued workpiece is obtained, and the preliminary detection result is sent to the controller so that the controller can detect the simulation signal and match the initial detection result. Then, based on the target virtual image, the deformation detection result corresponding to the fatigued workpiece is determined, and the controller returns the deformation detection result to the fatigue testing machine so that the fatigue testing machine can further determine whether to load the workpiece or mark the workpiece. The controller dynamically adjusts the shooting frequency through a closed-loop feedback mechanism; wherein the target virtual image is used to obtain the peak and trough information corresponding to the deformation of the fatigued workpiece. The terminal enables convenient axial and lateral detection and processing of marked points; The preliminary detection results of the target virtual image corresponding to the fatigued workpiece are obtained based on the target virtual image, including: Based on the target virtual image, obtain the image sub-region corresponding to the target virtual image; The image sub-region is subjected to grayscale and filtering processing to obtain a filtered grayscale image; If the filtered grayscale image meets the speckle strain gauge conditions, a preliminary detection result of the target virtual image is obtained; The method for obtaining the image sub-region corresponding to the target virtual image, based on the target virtual image, includes: The target virtual image is input into a neural network model to obtain the coordinate information of the marked points on the fatigued workpiece in the target virtual image; Based on the coordinate information, the image sub-region corresponding to the target virtual image is obtained.

2. The method according to claim 1, characterized in that, If the filtered grayscale image meets the speckle strain gauge conditions, a preliminary detection result of the target virtual image is obtained, including: If the filtered grayscale image meets the grayscale gradient threshold range, then the filtered grayscale image is a speckle strain gauge. The image sub-region corresponding to each speckle strain gauge is processed to obtain preliminary detection results for all speckle strain gauges.

3. The method according to claim 1, characterized in that, The method further includes: Receive notification of the deformation detection results corresponding to the fatigued workpiece as determined by the controller.

4. The method according to claim 1, characterized in that, A fatigue testing machine applied in the process of workpiece deformation detection, the method comprising: The device receives deformation detection results from the controller to determine whether to not load or mark the fatigued workpiece; or to determine whether to load or re-mark the fatigued workpiece based on the deformation detection results, so that the measuring head can continue to acquire the virtual image corresponding to the fatigued workpiece.

5. The method according to claim 1, characterized in that, A measuring head applied in the process of workpiece deformation detection, the method includes: setting supplementary lighting information during the capture of a virtual image of a fatigued workpiece; Based on the supplementary lighting information, a virtual image of the target corresponding to the peaks and troughs during the deformation process of the fatigued workpiece is captured.

6. A terminal for material fatigue testing, characterized in that, The terminal, applied in the process of workpiece deformation detection and employing the material fatigue detection method as described in any one of claims 1-5, comprises: The first acquisition module is used to acquire a target virtual image of the fatigued workpiece; The first obtaining module is used to obtain a preliminary detection result of the target virtual image corresponding to the fatigued workpiece based on the target virtual image, and send the preliminary detection result to the controller so that the controller can detect that the analog signal matches the initial detection result. Then, the controller determines the deformation detection result corresponding to the fatigued workpiece based on the target virtual image, and the controller returns the deformation detection result to the fatigue testing machine so that the fatigue testing machine can further determine whether to load the workpiece or mark the workpiece. The controller dynamically adjusts the shooting frequency through a closed-loop feedback mechanism. The terminal enables convenient axial and lateral detection and processing of marked points.

7. A controller for material fatigue detection, characterized in that, The controller, applied in the process of workpiece deformation detection and employing the material fatigue detection method as described in any one of claims 1-5, comprises: The second acquisition module is used to acquire the analog signal of the deformation of the fatigued workpiece; The first receiving module is used to receive the preliminary detection results of the target virtual image corresponding to the fatigued workpiece sent by the terminal; The second obtaining module is used to determine the deformation detection result of the fatigued workpiece based on the target virtual image if the simulated signal matches the preliminary detection result; The deformation detection results are returned to the fatigue testing machine so that the fatigue testing machine can further determine the loading of the workpiece or the marking of the workpiece. The shooting frequency is dynamically adjusted through a closed-loop feedback mechanism. The target virtual image is used to obtain the peak and trough information corresponding to the deformation of the fatigue workpiece. The terminal realizes convenient axial and lateral detection and processing of the marked points to overcome the limitations of one-dimensional detection. Send a notification of the deformation detection to the terminal.

8. A fatigue testing machine for material fatigue detection, characterized in that, The fatigue testing machine, used in the process of workpiece deformation detection and employing the material fatigue testing method as described in any one of claims 1-5, comprises: The second receiving module is used to receive the deformation detection results sent by the controller, so as to determine whether to not load the fatigued workpiece or not to mark the fatigued workpiece based on the deformation detection results; or to determine whether to load the fatigued workpiece or to re-mark the fatigued workpiece based on the deformation detection results, so that the measuring head can continue to acquire the virtual image corresponding to the fatigued workpiece.

9. A measuring head for material fatigue testing, characterized in that, The measuring head is used in the process of workpiece deformation detection and adopts the material fatigue detection method as described in any one of claims 1-5. The measuring head includes: a laser rangefinder, a light source, an industrial lens, and an industrial camera. A laser rangefinder is used to obtain the distance between the fatigued workpiece and the measuring head; Industrial lenses and industrial cameras are used to acquire virtual images of workpieces under test based on distance. Light source, used to set the supplementary lighting information during the capture of the virtual image of the fatigued workpiece; The industrial lens and industrial camera are also used to capture a target virtual image of the corresponding peaks and troughs during the deformation process of a fatigued workpiece, based on the supplementary lighting information.

10. A system for detecting material fatigue, characterized in that, include: The device includes a memory, a processor, and a computer program, the computer program being stored in the memory, and the processor executing the computer program to perform the material fatigue detection method according to any one of claims 1 to 5.

11. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, is used to implement the material fatigue detection method according to any one of claims 1 to 5.

Images