Method and device for detecting tensile resistance of fastener

Abstract

The application discloses a kind of tensile resistance performance detection method and device of fastener, including obtaining the attribute parameter of fastener to be measured, fastener to be tested is installed in the clamping mechanism of tensile resistance performance detection device;Start tensile resistance performance detection device, according to the tensile rate of pre-set, force tensile is carried out to fastener to be tested, the tensile force data and deformation image data collected will be synchronous processing, then force data is removed and data smoothing processing, image pre-processing is carried out to deformation image data;By analyzing deformation image data, extract key deformation feature, construct stress-deformation model, analyze and obtain critical deformation point, and judge abnormal deformation point in tensile test process, obtain maximum force value by critical deformation point operation, maximum force value is corrected using abnormal deformation point, obtain the tensile resistance performance index of fastener;The accuracy and reliability of fastener tensile resistance performance detection are greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of performance detection, in particular to a tensile property detection method and device of fastener. BACKGROUND

[0002] The requirements for structural parts and connecting parts in the field of aerospace are extremely strict. As an important element for connecting and fixing key parts, the tensile property of fastener is directly related to the safety and reliability of the overall structure. In aircraft, satellites, rockets and other aerospace vehicles, fasteners not only need to withstand high-strength tensile load, but also must adapt to extreme temperature, vibration and impact and other complex environments. Therefore, the field of aerospace puts forward higher requirements for the material, process and performance detection standard of fastener, and it is urgent to develop a high-precision detection technology which can accurately capture the stress state of fastener and real-time monitor the deformation details.

[0003] The current commonly used tensile test technology of fastener mainly relies on traditional mechanical sensors or strain gauges. By applying tensile load and recording the force and deformation curve, the performance of fastener is evaluated. Although this method can reflect the tensile capacity of fastener in a macroscopic way, relying on single mechanical data alone often cannot accurately capture the small deformation and local damage of the surface and internal of fastener during the tensile process, especially in the application scene of aerospace field which requires high precision, the traditional technology has obvious shortcomings in identifying key critical deformation points and abnormal deformation signals.

[0004] In view of this, it is necessary to improve the existing tensile test technology of fastener to solve the technical problem that it is difficult to meet the high-precision test requirement. SUMMARY

[0005] The purpose of the present application is to provide a tensile property detection method and device of fastener, which solves the above technical problems.

[0006] To achieve this purpose, the present application adopts the following technical solutions:

[0007] A tensile property detection device of fastener, comprising:

[0008] Obtain the attribute parameters of the fastener to be tested, and install the fastener to be tested in the clamping mechanism of the tensile property detection device; the tensile property detection device is configured with a depth camera and a mechanical sensor;

[0009] Start the tensile property detection device, and perform force stretching on the fastener to be tested at a preset stretching rate. In the stretching process, the mechanical sensor continuously records the force data of the sample, and at the same time, the depth camera captures the deformation image data of the sample surface;

[0010] In the test process, the collected tensile stress data and deformation image data are processed synchronously, and then the stress data is processed for noise removal and data smoothing, and the deformation image data is processed for image preprocessing;

[0011] By analyzing the deformation image data, key deformation features are extracted, and a stress-deformation model is constructed in combination with the stress data in the tensile process;

[0012] Based on the stress-deformation model analysis, a critical deformation point is obtained, and an abnormal deformation point in the tensile test process is judged, the maximum stress value is obtained through the critical deformation point operation, and the maximum stress value is corrected by using the abnormal deformation point to obtain a corrected maximum stress value;

[0013] Based on the corrected maximum stress value, the tensile performance index of the fastener is obtained.

[0014] Optionally, the mechanical sensor and the depth camera are both attached with a timestamp generated by a unified system clock; and the collected tensile stress data and deformation image data are processed synchronously in the test process, specifically including:

[0015] According to the timestamps attached to each data point, the mechanical data and the image data are preliminarily matched according to a preset sampling period;

[0016] For the case that the sampling frequencies are different, a linear interpolation or spline interpolation algorithm is used to adjust the data sequence, so that a one-to-one corresponding data pair is formed on the same time scale;

[0017] The formed synchronous data pair is stored in a cache module to provide unified time sequence cache data.

[0018] Optionally, the stress data is then processed for noise removal and data smoothing, and the deformation image data is processed for image preprocessing, specifically including:

[0019] A low-pass filter is used to preliminarily denoise the original stress data to suppress high-frequency noise components;

[0020] A moving average filter or median filter algorithm is applied to the stress data for secondary smoothing processing to eliminate transient abnormal fluctuations;

[0021] The internal and external parameters obtained by pre-camera calibration are used to correct the geometric distortion of the deformation image data;

[0022] For the original image noise in the deformation image data, a Gaussian filter is used with a filter kernel size of 5x5 and a standard deviation of 1.0 for noise suppression;

[0023] The image is subjected to brightness normalization processing through histogram equalization technology to enhance the contrast and detail performance of the deformation region in the image.

[0024] According to the test requirements, the region of interest is preset, the image is cropped, and the image data of the key surface region of the fastener is retained.

[0025] Optionally, after the image is cropped according to the test requirements, the region of interest is preset, and the image data of the key surface region of the fastener is retained, the method further includes:

[0026] The stress data and the deformation image data obtained after processing are uniformly stored in time sequence, and a corresponding data index database is constructed.

[0027] Optionally, the stress-deformation model is constructed by analyzing the deformation image data and extracting key deformation features, in combination with the stress data during the stretching process, and specifically includes:

[0028] The preprocessed deformation image data is subjected to morphological operations including erosion and dilation, and the operation size can be set to a convolution kernel of 3x3 or 5x5.

[0029] An image segmentation algorithm, such as threshold-based segmentation, is applied to segment the image into multiple regions to highlight the regions where deformation occurs on the surface of the sample.

[0030] Key deformation features are extracted from the segmented deformation regions, including the area of the deformation region, the deformation rate, and the deformation mode.

[0031] Through multi-scale analysis, the deformation at different stretching stages is tracked to form deformation sequence data.

[0032] Optionally, after the deformation sequence data is formed by tracking the deformation at different stretching stages through multi-scale analysis, the method further includes:

[0033] The stress data and the key deformation features processed synchronously are matched one by one according to the time stamp, so that each stress data point corresponds to a deformation state.

[0034] A regression analysis method is used to analyze the quantitative relationship between stress and deformation features, and to identify the nonlinear relationship between force and deformation.

[0035] Key points in the stretching process are extracted, including the initial stress, the elastic stage, the yield point, and the maximum stress point, and in combination with the turning points of deformation, a mechanical model describing the tensile performance is constructed.

[0036] A finite element analysis method is used to establish a stress-deformation model to simulate the deformation mode and stress distribution of the fastener under different stress conditions.

[0037] The stress-deformation model is verified and corrected through actual test data and a constructed mechanical model.

[0038] Optionally, the critical deformation point is obtained based on the stress-deformation model analysis, and an abnormal deformation point in the tensile test process is judged, and specifically includes:

[0039] According to the stress-deformation model, the deformation rate and stress change of the fastener sample at each stage in the entire tensile process are first calculated;

[0040] The force-deformation curve is smoothed by a local smoothing algorithm;

[0041] The critical point is identified using the force-deformation curve and a second derivative method, that is, by calculating the second derivative of the curve, the inflection point of the curve is found;

[0042] All the deformation points calculated in the stress-deformation model are compared with the actual test data, and the abnormal deformation point significantly different from most data is identified by calculating the standard deviation of the deformation or based on the maximum difference method;

[0043] For the identified abnormal deformation point, an outlier detection algorithm is used to further verify whether the point is abnormal data caused by external interference or equipment failure during the test process;

[0044] If the abnormal deformation point is valid data, it is retained, otherwise the abnormal point is marked as invalid data and removed from the calculation.

[0045] Optionally, the maximum stress value is obtained by operating the critical deformation point, and the maximum stress value is corrected using the abnormal deformation point to obtain a corrected maximum stress value, and specifically includes:

[0046] Based on the stress-deformation model, the maximum stress value at the critical deformation point is first determined;

[0047] According to the identified abnormal deformation point, the maximum stress value is adjusted by a data correction algorithm;

[0048] The maximum stress value calculated at the critical deformation point is corrected by a weighted average algorithm combined with the critical point and the data after removing the abnormal point to obtain a corrected maximum stress value.

[0049] The application also provides a fastener tensile performance detection device, characterized by being applied to realize the fastener tensile performance detection method as described above, and the tensile performance detection device includes:

[0050] The clamping mechanism is used for accurately fixing the fastener to be tested;

[0051] a tensile testing machine for providing a tensile force;

[0052] a mechanical sensor for recording tensile force and strain data of the fastener in real time during the tensile process;

[0053] a depth camera for capturing deformation images of the surface of the fastener in real time, providing deformation data.

[0054] Compared with the prior art, the present application has the following beneficial effects: first, the attribute parameters of the fastener to be tested are first collected and installed in the detection device with a depth camera and a mechanical sensor, the detection device is started according to the preset tensile rate, the sample is subjected to tensile loading, and the force data recorded by the mechanical sensor and the deformation images of the surface of the sample captured by the depth camera are collected in real time. The collected force data is subjected to noise removal and data smoothing processing, and the deformation images are preprocessed. The key deformation features are extracted from the preprocessed image data, and a force-deformation model is constructed in combination with the force data, revealing the physical behavior of the sample during the tensile process. The critical deformation point is determined by using the constructed model, and the abnormal deformation is identified. The maximum force value of the sample is calculated through the critical point, and the value is further corrected. The tensile resistance performance index of the fastener is determined according to the corrected maximum force value, and the whole detection process is completed. The present application combines the depth camera with the mechanical sensor to realize real-time synchronous collection and processing of force data and deformation images, and through the steps of data preprocessing, noise filtering, force-deformation modeling and critical point identification, the problems of incomplete data capture, difficult identification of abnormal deformation and inaccurate calculation of the maximum force value in the prior art are effectively solved, thereby greatly improving the accuracy and reliability of the tensile resistance performance detection of the fastener. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0056] The structures, proportions, sizes, etc. shown in the drawings of the present specification are only used to cooperate with the content disclosed in the specification, to enable those skilled in the art to understand and read, and are not used to limit the limiting conditions under which the present application can be implemented, so they do not have technical significance. Any modification of structure, change of proportion relationship or adjustment of size, which does not affect the effects and purposes that the present application can produce, should still fall within the scope of the technical content disclosed by the present application.

[0057] Figure 1A flowchart of a tensile resistance performance detection method of the fastener of Example 1 is shown in the figure.

[0058] Figure 2 A structural layout diagram of a tensile resistance performance detection device of the fastener of Example 2 is shown in the figure. DETAILED DESCRIPTION

[0059] In order to make the inventive purposes, features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the following described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0060] In the description of the present application, it should be understood that the terms "upper", "lower", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. It should be noted that when a component is considered to be "connected" to another component, it can be directly connected to the other component or there can be a component disposed therebetween.

[0061] The technical solutions of the present application will be further described below in conjunction with the accompanying drawings and through specific embodiments.

[0062] Example 1

[0063] In conjunction with the drawings shown, the embodiments of the present application provide a tensile resistance performance detection method of a fastener, comprising: Figure 1

[0064] S1, obtaining the attribute parameters of the fastener to be tested, and installing the fastener to be tested in the clamping mechanism of the tensile resistance performance detection device; the tensile resistance performance detection device is configured with a depth camera and a mechanical sensor.

[0065] The attribute parameters include material, size, shape and use environment, which will help to determine the applicable tensile test parameters, such as maximum stress, test loading rate, etc. And ensure that the clamping mechanism can adapt to the specific size and shape of the sample.

[0066] S2, starting the tensile resistance performance detection device, and performing force stretching on the fastener to be tested at a preset stretching rate. In the stretching process, the mechanical sensor continuously records the stress data of the sample, and at the same time, the depth camera captures the deformation image data of the surface of the sample. ​

[0067] The deformation image data in this process will be the key to subsequent analysis, ensuring that the sample can be fully monitored for small changes during the stress process. Real-time monitoring data includes tension, deformation, initial signs of sample surface cracks or fractures, etc.

[0068] S3, during the test, the collected tensile stress data and deformation image data will be processed synchronously, and then the stress data will be processed for noise removal and data smoothing, and the deformation image data will be preprocessed.

[0069] Image preprocessing such as removing background noise, correcting image distortion, standardizing image size, etc. The preprocessed data will be the basis for subsequent analysis, ensuring the accuracy and consistency of the data.

[0070] S4, by analyzing the deformation image data, key deformation features are extracted, and combined with the stress data during the stretching process, a stress-deformation model is constructed.

[0071] The stress-deformation model can reveal the deformation law of the fastener under certain stress conditions, especially the critical deformation point. Through these data, it is determined whether the sample has abnormal deformation, whether it has reached the critical stress point, and the ultimate tensile performance (such as tensile fracture point, maximum deformation, etc.) is predicted.

[0072] S5, based on the stress-deformation model analysis, the critical deformation point is obtained, and the abnormal deformation point in the tensile test process is judged, the maximum stress value is obtained by critical deformation point operation, and the abnormal deformation point is used to correct the maximum stress value to obtain the corrected maximum stress value.

[0073] S6, based on the corrected maximum stress value, the tensile performance index of the fastener is obtained.

[0074] The working principle of the present application is as follows: first, the attribute parameters of the fastener to be tested are collected and installed in a detection device with a depth camera and a mechanical sensor, the detection device is started according to a preset stretching rate, the sample is subjected to tensile loading, and the force data recorded by the mechanical sensor and the sample surface deformation image captured by the depth camera are collected in real time, the collected force data is subjected to noise removal and data smoothing processing, and the deformation image is preprocessed, the key deformation features are extracted from the preprocessed image data, and a force-deformation model is constructed in combination with the force data to reveal the physical behavior of the sample in the stretching process; the model is used to determine the critical deformation point and identify abnormal deformation, the maximum force value of the sample is calculated through the critical point, and the value is further corrected; the tensile performance index of the fastener is determined according to the corrected maximum force value, and the whole detection process is completed; the present application combines the depth camera with the mechanical sensor to realize real-time synchronous collection and processing of force data and deformation image, and through the steps of data preprocessing, noise filtering, force-deformation modeling and critical point identification, the problems of incomplete data capture, difficult identification of abnormal deformation and inaccurate calculation of the maximum force value in the prior art are effectively solved, thereby greatly improving the accuracy and reliability of the tensile performance detection of the fastener.

[0075] In the present embodiment, the mechanical sensor and the depth camera are both attached with time stamps generated by a unified system clock; the step S3 specifically comprises:

[0076] S301, according to the time stamps attached to each data point, the mechanical data and the image data are preliminarily matched according to a preset sampling period (for example, 10 ms).

[0077] S302, for the case where the sampling frequencies are different, linear interpolation or spline interpolation algorithm is used to adjust the data sequence, so that a one-to-one corresponding data pair is formed on the same time scale.

[0078] S303, the formed synchronous data pair is stored in a cache module to provide unified time sequence cache data.

[0079] S304, a low-pass filter (for example, the cutoff frequency can be set to 50 Hz, and fine adjustment can be made according to the actual detection instrument characteristics and test requirements) is used to preliminarily denoise the original force data to suppress high-frequency noise components.

[0080] S305, moving average filtering (such as using a 10-point window) or median filtering algorithm is applied to the force data for secondary smoothing processing to eliminate transient abnormal fluctuations; while maintaining the force change trend and key features.

[0081] S306, the internal and external parameters obtained by pre-camera calibration are used to correct the geometric distortion of the deformation image data; the accuracy of the image size and proportion is ensured.

[0082] S307, for the original image noise in the deformation image data, Gaussian filtering is adopted, the filter kernel size is 5x5, and the standard deviation is set to 1.0, noise suppression is performed; the image quality is improved.

[0083] S308, the histogram equalization technique is used to perform brightness normalization processing on the image, so as to enhance the contrast and detail performance of the deformation region in the image.

[0084] S309, according to the test requirements, the region of interest (ROI) is preset, the image is cropped, and the image data of the key surface region of the fastener is retained; so as to facilitate subsequent deformation feature extraction and analysis.

[0085] S310, the stress data and deformation image data obtained after processing are uniformly stored in time sequence, and a corresponding data index database is constructed.

[0086] In this embodiment, the step S4 specifically includes:

[0087] S41, morphological operations including erosion and dilation are performed on the preprocessed deformation image data, and the operation size can be set to a convolution kernel of 3x3 or 5x5; used to extract edges and details in the image, and ensure accurate identification of the deformation region.

[0088] S42, an image segmentation algorithm is applied, such as threshold-based segmentation, to segment the image into multiple regions, so as to highlight the region where the sample surface is deformed.

[0089] S43, key deformation features are extracted from the segmented deformation region, including the area of the deformation region, the deformation rate (the degree of region deformation), and the deformation mode (such as expansion, compression, bending, etc.).

[0090] S44, through multi-scale analysis, the deformation at different stretching stages is tracked to form deformation sequence data; ensure that the whole process from micro-deformation to large-scale deformation can be accurately captured.

[0091] S45, the stress data and key deformation features processed synchronously are matched one by one according to the time stamp, so that each stress data point corresponds to a deformation state.

[0092] S46, a regression analysis method is used to analyze the quantitative relationship between stress and deformation features, and identify the nonlinear relationship between force and deformation.

[0093] S47, extract the key points in the stretching process, including the initial stress, elastic stage, yield point and maximum stress point, combined with the turning point of deformation, to build a mechanical model describing the tensile performance.

[0094] S48, use finite element analysis method to establish stress-deformation model to simulate the deformation mode and stress distribution of fastener under different stress conditions.

[0095] S49, verify and correct the stress-deformation model through actual test data and the constructed mechanical model; ensure the accuracy of the model, and predict the reliability and durability of the fastener under different working conditions.

[0096] In this embodiment, step S5 specifically includes:

[0097] According to the stress-deformation model, first calculate the deformation rate and stress change of the fastener sample at each stage in the entire stretching process.

[0098] Pay special attention to the deformation acceleration stage. In the deformation acceleration stage, the stress and deformation of the sample change sharply, which is the candidate interval of the critical deformation point.

[0099] Smooth the force-deformation curve by local smoothing algorithm;

[0100] To improve the accuracy, in the identification process of critical points, the original curve can be smoothed by local smoothing algorithm (such as Savitzky-Golay filter) to reduce the influence of noise and ensure the positioning of critical points more accurate

[0101] Use the force-deformation curve, combined with the second derivative method (acceleration method) to identify the critical point, that is, find the inflection point of the curve by calculating the second derivative of the curve; this usually corresponds to the yield point or the turning point of the maximum deformation rate of the sample.

[0102] Compare all the deformation points calculated in the stress-deformation model with the actual test data, and identify the abnormal deformation points that are significantly different from most data by calculating the standard deviation of deformation or based on the maximum difference method (such as by maximum cosine distance method);

[0103] For the identified abnormal deformation points, use outlier detection algorithm (such as DBSCAN or LOF algorithm) to further verify whether the point is abnormal data caused by external interference or equipment failure during the test process;

[0104] If the abnormal deformation point is valid data, it is retained, otherwise the abnormal point will be marked as invalid data and excluded from the calculation.

[0105] Based on the stress-deformation model, first determine the maximum stress value at the critical deformation point, this value usually corresponds to the sample appears obvious deformation or yield point, at this time the stress reaches the peak value;

[0106] According to the identified abnormal deformation point, by data correction algorithm (for example using the median or weighted average method), adjust the maximum stress value; remove the interference of abnormal value to test results;

[0107] By weighted average algorithm combined with critical point and remove abnormal point after data, the maximum stress value calculated by the critical deformation point is corrected to obtain the corrected maximum stress value. The abnormal deformation point is used to correct the value, and the correction process ensures that the corrected maximum stress value is more accurate and stable.

[0108] Embodiment two:

[0109] In combination Figure 2 As shown in the figure, the application also provides a tensile property detection device of fastener, applied to realize the tensile property detection method of fastener as in embodiment one, the tensile property detection device of fastener comprises:

[0110] Clamping mechanism 10, for accurately fixing the fastener to be tested;

[0111] Tensile testing machine 20, for providing tensile force;

[0112] Mechanical sensor 30, for real-time recording of tensile force and strain data of fastener in the tensile process;

[0113] Depth camera 40, for real-time capturing of deformation image of fastener surface, providing deformation data.

[0114] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of detecting tensile resistance of a fastener, characterized by, The utility model relates to a kind of method for testing the tensile property of fastener, comprising: Obtain the attribute parameters of the fastener to be tested, and install the fastener to be tested in the clamping mechanism of the tensile property testing device; The tensile property testing device is provided with a depth camera and a mechanical sensor; Start the tensile property testing device, and perform force stretching on the fastener to be tested at a predetermined stretching rate. In the stretching process, the mechanical sensor continuously records the force data of the sample, and the depth camera captures the deformation image data of the sample surface. During the test, the collected stretching force data and deformation image data are processed synchronously, and then the force data is subjected to noise removal and data smoothing processing, and the deformation image data is subjected to image preprocessing. By analyzing the deformation image data, the key deformation features are extracted, and the force-deformation model is constructed by combining the force data during the stretching process. Based on the force-deformation model analysis, the critical deformation point is obtained, and the abnormal deformation point in the stretching test process is judged. The maximum force value is obtained by calculating the critical deformation point, and the maximum force value is corrected using the abnormal deformation point to obtain the corrected maximum force value. Based on the corrected maximum force value, the tensile property index of the fastener is obtained. Wherein, based on the force-deformation model analysis, the critical deformation point is obtained, and the abnormal deformation point in the stretching test process is judged. The maximum force value is obtained by calculating the critical deformation point, and the maximum force value is corrected using the abnormal deformation point to obtain the corrected maximum force value, specifically including: According to the force-deformation model, first calculate the deformation rate and force change of the fastener sample at each stage during the entire stretching process; Smooth the force-deformation curve using a local smoothing algorithm; Use the force-deformation curve to identify the critical deformation point using the second derivative method, i.e. find the inflection point of the curve by calculating the second derivative of the curve; Compare all the calculated deformation points in the force-deformation model with the actual test data, and identify the abnormal deformation points that are significantly different from most data by calculating the standard deviation of the deformation or using the maximum difference method; For the identified abnormal deformation points, use the outlier detection algorithm to further verify whether the points are abnormal data caused by external interference or equipment failure factors during the test; If the abnormal deformation point is valid data, it is retained, otherwise the abnormal deformation point is marked as invalid data and excluded from the calculation; Based on the force-deformation model, first determine the maximum force value at the critical deformation point; Correct the maximum force value calculated at the critical deformation point using a weighted average algorithm combined with the critical deformation point and the data after removing the abnormal deformation points to obtain the corrected maximum force value.

2. The method of claim 1, wherein The mechanical sensor and the depth camera are both attached with timestamps generated by a unified system clock; During the test, the collected stretching force data and deformation image data are processed synchronously, specifically including: According to the timestamps attached to each data point, the mechanical data and image data are preliminarily matched according to the predetermined sampling period; For cases where the sampling frequencies differ, use linear interpolation or spline interpolation algorithm to adjust the data sequence so that a one-to-one correspondence of data pairs is formed on the same time scale; The synchronous data formed is stored in the cache module, and uniform timing cache data is provided.

3. The method for testing the tensile properties of fasteners according to claim 2, characterized in that, The stress data is subjected to noise removal and data smoothing processing, and the deformation image data is subjected to image preprocessing, specifically including: A low-pass filter is used to preliminarily denoise the original stress data and suppress high-frequency noise components; A moving average filter or median filter algorithm is applied to the stress data for secondary smoothing processing to eliminate transient abnormal fluctuations; The internal and external parameters obtained during the camera calibration are used to correct the geometric distortion of the deformation image data; Gaussian filtering is used to suppress noise in the original image noise in the deformation image data, with a filter kernel size of 5x5 and a standard deviation of 1.0; A histogram equalization technique is used to perform brightness normalization processing on the image to enhance the contrast and detail performance of the deformation region in the image; According to the test requirements, the region of interest is preset, the image is cropped, and the image data of the key surface region of the fastener is retained.

4. The method of claim 3, wherein the method is characterized by, According to the test requirements, the region of interest is preset, the image is cropped, and the image data of the key surface region of the fastener is retained. The stress data and deformation image data obtained after processing are uniformly stored in time sequence, and a corresponding data index database is constructed.

5. The method of claim 1, wherein The deformation image data is analyzed to extract key deformation features, and a stress-deformation model is constructed by combining the stress data during the stretching process, specifically including: Morphological operations including erosion and dilation are performed on the preprocessed deformation image data, and the operation size can be set to a convolution kernel of 3x3 or 5x5; An image segmentation algorithm, such as threshold-based segmentation, is applied to segment the image into multiple regions to highlight the deformation regions on the sample surface; Key deformation features are extracted from the segmented deformation regions, including the area, deformation rate, and deformation mode of the deformation region; Through multi-scale analysis, the deformation at different stretching stages is tracked to form deformation sequence data.

6. The method of claim 5, wherein the step of determining the tensile strength of the fastener is performed by a tensile tester. Through multi-scale analysis, the deformation at different stretching stages is tracked to form deformation sequence data. The stress data and key deformation features are matched one by one according to the time stamp, so that each stress data point corresponds to a deformation state; A regression analysis method is used to analyze the quantitative relationship between stress and deformation features and identify the nonlinear relationship between force and deformation; Key points in the stretching process are extracted, including the initial stress, elastic stage, yield point, and maximum stress point, and combined with the turning points of deformation, a mechanical model describing the tensile performance is constructed.

Images