Engineering material tensile experiment strain measurement method and related device

Abstract

The invention provides an engineering material tensile experiment strain measurement method and a related device, and belongs to the technical field of engineering experiments. The method comprises the steps of obtaining an image in an engineering material stretching process; performing image segmentation on the image in the stretching process of the engineering material to obtain contour information of the engineering material; performing feature point matching on the contour information of the engineering material to obtain displacement change information of feature points on the surface of the engineering material in the stretching process; and obtaining a local strain measurement result of the engineering material based on the displacement change information of the feature points on the surface of the engineering material in the stretching process. The problem that the accuracy of strain measurement of the tensile experiment of the engineering material is not high is solved.

Description

Technical Field

[0001] This invention belongs to the field of engineering experimental technology, specifically relating to a method and related apparatus for measuring strain in tensile tests of engineering materials. Background Technology

[0002] In tensile testing of engineering materials, accurate measurement of strain is crucial for evaluating the material's mechanical properties. Traditional strain measurement methods mainly include the resistance strain gauge method and the extensometer method.

[0003] The resistance strain gauge method involves attaching strain gauges to the surface of a specimen and indirectly obtaining the strain value by measuring the change in the strain gauge's resistance. However, this method has some limitations. First, the strain gauge attachment process requires high precision; the quality of the attachment directly affects the measurement accuracy. Issues such as air bubbles or uneven adhesive layers during attachment can lead to measurement errors. Second, the strain gauge has a limited range, making it prone to nonlinear errors or even damage to the strain gauge when measuring large strains.

[0004] The extensometer method directly measures the deformation within the gauge length of a specimen using mechanical or optical devices. However, extensometers also have their problems in use. The clamping force of a mechanical extensometer may generate additional stress on the specimen, affecting the accuracy of the experimental results. While optical extensometers avoid the clamping force problem, they have high requirements for the experimental environment; factors such as the stability of light and the reflectivity of the specimen surface can affect measurement accuracy. Moreover, optical extensometers are more expensive.

[0005] Furthermore, most existing strain measurement methods are single-point or limited-point measurements, making it difficult to obtain the full-field strain distribution of the specimen during tensile testing. For some complex materials or structures, full-field strain information is crucial for a deeper understanding of the material's deformation mechanism and damage evolution process. With the development of materials science, the requirements for research on the mechanical properties of materials are becoming increasingly stringent, urgently necessitating a more accurate and comprehensive strain measurement technology. Summary of the Invention

[0006] The purpose of this invention is to provide a method and related apparatus for measuring strain in tensile tests of engineering materials, in order to solve the problem of low accuracy in the existing technology for measuring strain in tensile tests of engineering materials.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for measuring strain in tensile tests of engineering materials, comprising the following steps: Acquire images of engineering materials during the tensile process; Image segmentation is performed on images of engineering materials during the stretching process to obtain the contour information of the engineering materials; Feature point matching is performed on the contour information of engineering materials to obtain the displacement change information of feature points on the surface of engineering materials during the stretching process; Based on the displacement change information of feature points on the surface of engineering materials during the tensile process, the local strain measurement results of engineering materials are obtained.

[0008] A further improvement of the present invention is that the acquisition of images of the engineering material during the stretching process is specifically achieved by acquiring images of the engineering material during the stretching process using a high-resolution industrial camera and an auxiliary lighting device.

[0009] A further improvement of the present invention is that, before performing image segmentation on the image of the engineering material stretching process to obtain the contour information of the engineering material, the acquired image of the engineering material stretching process is filtered, enhanced, compressed, and quality inspected.

[0010] A further improvement of the present invention is that the method of obtaining the local strain measurement result of the engineering material based on the displacement change information of the feature points on the surface of the engineering material during the tensile process is specifically: using digital image correlation algorithm and sub-pixel matching technology, the local strain measurement result of the engineering material is obtained based on the displacement change information of the feature points on the surface of the engineering material during the tensile process.

[0011] A further improvement of the present invention is that, after obtaining the local strain measurement results of the engineering material, the local strain measurement results of the engineering material are evaluated to obtain the evaluation results of the local strain measurement of the engineering material.

[0012] A further improvement of this invention is that if the local strain measurement and evaluation results of the engineering material do not meet the requirements, feedback and adjustments are made based on the local strain measurement and evaluation results of the engineering material.

[0013] A further improvement of this invention is that, after obtaining the local strain measurement results of the engineering material, the strain measurement results of the entire engineering material are obtained based on the local strain measurement results of the engineering material.

[0014] Secondly, the present invention provides a strain measurement system for tensile testing of engineering materials, comprising: The data acquisition module is used to acquire images of engineering materials during the tensile process; The image segmentation module is used to segment images of engineering materials during the stretching process to obtain the contour information of the engineering materials. The feature point matching module is used to match feature points on the contour information of engineering materials to obtain the displacement change information of feature points on the surface of engineering materials during the stretching process. The measurement module allows for the measurement of local strain of engineering materials based on the displacement changes of feature points on the surface of the engineering material during the tensile process.

[0015] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the tensile strain measurement method for engineering materials described above.

[0016] Fourthly, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method for measuring strain in tensile tests of engineering materials.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The proposed method for measuring strain in tensile tests of engineering materials involves two aspects. First, image segmentation is performed on the image of the engineering material during the tensile process to obtain its contour information. This operation can accurately define the boundary of the measurement target, eliminate background interference, and thus improve the accuracy of subsequent tensile strain measurements. Second, feature point matching is performed on the contour information of the engineering material to obtain the displacement change information of feature points on the surface of the engineering material during the tensile process. This operation can establish a precise spatial correspondence for measuring the strain in tensile tests of engineering materials, ensuring that the measurement benchmark remains consistent at different times, thereby reducing measurement deviations. Attached Figure Description

[0018] Figure 1 This is a flowchart of the tensile strain measurement method for engineering materials according to the present invention; Figure 2 This is a schematic diagram of the strain measurement system for tensile testing of engineering materials according to the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device of the present invention. Detailed Implementation

[0019] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0020] Example 1: The flowchart of the strain measurement method for tensile tests on engineering materials of this invention is as follows: Figure 1 As shown, the tensile strain measurement method for engineering materials of the present invention includes the following steps: S1. Acquire images of the engineering material during the tensile process; S2. Perform image segmentation on the image of the engineering material during the stretching process to obtain the contour information of the engineering material; S3. Perform feature point matching on the contour information of the engineering material to obtain the displacement change information of the feature points on the surface of the engineering material during the stretching process; S4. Based on the displacement change information of feature points on the surface of the engineering material during the tensile process, the local strain measurement results of the engineering material are obtained.

[0021] Example 2: A schematic diagram of the strain measurement system for tensile testing of engineering materials of this invention is shown below. Figure 2 As shown, the tensile strain measurement system for engineering materials of the present invention includes: The data acquisition module is used to acquire images of engineering materials during the tensile process; The image segmentation module is used to segment images of engineering materials during the stretching process to obtain the contour information of the engineering materials. The feature point matching module is used to match feature points on the contour information of engineering materials to obtain the displacement change information of feature points on the surface of engineering materials during the stretching process. The measurement module allows for the measurement of local strain of engineering materials based on the displacement changes of feature points on the surface of the engineering material during the tensile process.

[0022] Example 3: The method for measuring strain in tensile tests of engineering materials according to the present invention includes the following steps: S1. Acquire images of the engineering material during the tensile process.

[0023] This step involves acquiring images of the engineering material during the stretching process, specifically by using a high-resolution industrial camera and auxiliary lighting.

[0024] S2. Perform image segmentation on the image of the engineering material during the stretching process to obtain the contour information of the engineering material.

[0025] Before performing image segmentation on the images of the engineering material during the stretching process to obtain the contour information of the engineering material, this step involves filtering, image enhancement, compression, and quality inspection on the acquired images of the engineering material during the stretching process.

[0026] S3. Perform feature point matching on the contour information of the engineering material to obtain the displacement change information of the feature points on the surface of the engineering material during the stretching process.

[0027] S4. Based on the displacement change information of feature points on the surface of the engineering material during the tensile process, the local strain measurement results of the engineering material are obtained.

[0028] In this step, the local strain measurement results of the engineering material are obtained based on the displacement change information of the feature points on the surface of the engineering material during the tensile process. Specifically, the local strain measurement results of the engineering material are obtained by using digital image correlation algorithm and sub-pixel matching technology based on the displacement change information of the feature points on the surface of the engineering material during the tensile process.

[0029] After obtaining the local strain measurement results of the engineering material, the local strain measurement results of the engineering material are evaluated to obtain the evaluation results of the local strain measurement of the engineering material.

[0030] If the results of the local strain measurement and evaluation of the engineering materials do not meet the requirements, feedback and adjustments will be made based on the results of the local strain measurement and evaluation of the engineering materials.

[0031] After obtaining the local strain measurement results of the engineering material, the strain measurement results of the entire engineering material are obtained based on the local strain measurement results.

[0032] Example 4: The method of the present invention will be described in detail below: The method of this invention is implemented through four intelligent agents (image acquisition agent, data processing agent, strain calculation agent, and result evaluation agent). The image acquisition agent, data processing agent, strain calculation agent, and result evaluation agent are described in detail below: A. Image Acquisition Intelligent Agent In the precise strain measurement of tensile tests on engineering materials, the image acquisition agent plays a crucial role. It needs to capture images of the engineering material (this embodiment uses a specimen as an example) in real time throughout the experiment to provide basic data for subsequent strain calculations.

[0033] a. Hardware selection and layout This intelligent agent employs a high-resolution industrial camera as the core device for image acquisition. The reason for choosing a high-resolution industrial camera is that in tensile tests, the deformation of the specimen can be extremely subtle; high resolution ensures that these minute changes are captured, guaranteeing accurate strain measurement. The frame rate of the industrial camera is carefully set, determining the appropriate shooting frequency based on the speed of the tensile test and the expected rate of specimen deformation. This ensures that clear images are acquired at every critical stage of specimen deformation, without missing important deformation information.

[0034] The camera setup is carefully optimized, taking into full account the size and shape of the specimens. The camera position, angle, and distance are adjusted accordingly for specimens of different sizes and shapes. For example, for large plate-shaped specimens, multiple cameras may be deployed from different angles to ensure complete coverage of the specimen surface and capture comprehensive deformation information. For small cylindrical specimens, the cameras are placed in appropriate positions based on their diameter and length to ensure clear imaging of the gauge length, which is the deformation area we are focusing on.

[0035] b. Lighting conditions guarantee To ensure stable image quality, auxiliary lighting is an essential component. It provides uniform and stable illumination. During experiments, the uniformity of illumination is crucial; uneven lighting can lead to shadows or excessive brightness differences in the images, interfering with subsequent image analysis and feature point recognition. By strategically arranging the auxiliary lighting, such as using ring or surface light sources, the surface of the specimen can receive uniform illumination, thus preventing lighting issues from affecting image quality.

[0036] c. Intelligent adjustment The image acquisition agent possesses autofocus and image correction functions, which are crucial for ensuring clear and accurate images. During tensile testing, the specimen undergoes displacement and deformation, and its position and orientation may continuously change. The autofocus function monitors the specimen's positional changes in real time and automatically adjusts the camera's focal length to ensure the specimen remains in a clear image. The image correction function performs geometric and distortion correction on the acquired image. Due to the optical characteristics of the camera lens and the shooting angle, the acquired image may contain certain geometric distortions and deformations. The image correction function processes the image according to pre-set correction parameters to eliminate these distortions, ensuring that the acquired image accurately reflects the actual shape and size of the specimen.

[0037] d. Image transmission and preprocessing The acquired image data is transmitted in real time to the subsequent data processing agent via a high-speed data transmission interface. Before transmission, the image acquisition agent performs some simple preprocessing on the images. For example, it compresses the images to reduce data transmission volume and improve transmission efficiency. Simultaneously, it performs preliminary quality checks on the images, checking for issues such as blurriness, excessive darkness, or excessive brightness. If the image quality is found to be unsatisfactory, it promptly adjusts camera parameters or re-acquires images to ensure that the image data transmitted to the data processing agent is of good quality, providing a reliable foundation for subsequent strain calculations.

[0038] B. Data Processing Intelligent Agent The data processing agent plays a crucial role in the entire multi-agent collaborative system for precise strain measurement in tensile testing of engineering materials. It receives image data from the image acquisition agent, performs a series of refined processing steps on this data, and provides accurate and usable feature point displacement information for the subsequent strain calculation agent.

[0039] a. Image preprocessing Upon receiving image data from the image acquisition agent, the data processing agent first performs image preprocessing. Images may be subject to various noise interferences during acquisition, such as electromagnetic interference from the environment and electronic noise from the camera itself. To remove this noise, the data processing agent employs image filtering techniques. Median filtering is a commonly used method; it sorts the gray values ​​of each pixel and its neighboring pixels, then takes the median value as the new gray value for that pixel, effectively removing impulse noise such as salt-and-pepper noise. Gaussian filtering can also be used, employing a Gaussian function to apply a weighted average to the image, smoothing it, reducing the impact of random noise, and improving the signal-to-noise ratio.

[0040] Besides filtering, image enhancement algorithms are also a crucial preprocessing step. Tensile test images may suffer from insufficient contrast and low clarity, which can affect subsequent extraction of specimen feature information. The data processing agent uses histogram equalization to enhance image contrast. This algorithm adjusts the image's grayscale histogram to make the grayscale distribution more uniform, thus making details in the image clearer. Furthermore, sharpening algorithms are also employed, which enhance edge information to further improve image clarity and highlight the specimen's contours and key features.

[0041] b. Image segmentation After image preprocessing, the data processing agent needs to separate the specimen from the complex background to obtain its contour information, which involves the application of image segmentation technology. Since the specimen and background differ in grayscale, color, texture, and other features, the data processing agent can employ a threshold-based segmentation method. It determines a suitable threshold based on the image's grayscale histogram, dividing the pixels in the image into two categories: pixels above the threshold are grouped into one category, and pixels below the threshold are grouped into another. This allows the specimen to be distinguished from the background, and its contour information extracted.

[0042] For situations with complex backgrounds and indistinct differences between the specimen and background features, the data processing agent may employ edge detection-based segmentation methods. The Canny edge detection algorithm is a commonly used edge detection technique. It calculates the gradient values ​​and directions of pixels in an image to find edge points, then connects these edge points to form a contour, thereby segmenting the specimen from the background. Additionally, region growing-based segmentation methods are also considered. Starting with seed points, it continuously merges adjacent pixels into the same region based on pre-defined similarity criteria, ultimately obtaining the specimen's region.

[0043] c. Feature point matching After extracting the specimen's contour information, the data processing agent needs to perform feature point matching on images (the specimen's contour information) at different times. This is to mark the displacement changes of feature points on the specimen's surface during the stretching process. First, the data processing agent needs to select some representative feature points in the initial image. These feature points can be texture features on the specimen's surface, corner points, etc. For example, the Harris corner detection algorithm can be used to detect corner points in the image, as these corner points have obvious features in the image, facilitating subsequent matching operations.

[0044] In subsequent images, the data processing agent locates corresponding feature points by calculating the similarity of their neighborhoods. A commonly used similarity metric is the Normalized Cross-Correlation (NCC) algorithm. This algorithm determines similarity between two image regions by calculating the correlation between their grayscale values. If the correlation value exceeds a certain threshold, a corresponding feature point is considered to have been found. In this way, the data processing agent can mark the positions of feature points on the specimen surface in images at different times, thereby obtaining information on the displacement changes of these feature points during the tensile process, providing crucial input data for the strain calculation agent.

[0045] C. Strain calculation intelligent agent In the entire precision strain measurement system for tensile testing of engineering materials, the strain calculation agent plays a crucial role in transforming the characteristic point displacement information output by the data processing agent into strain distribution results. Utilizing advanced algorithms and processing techniques, it aims to achieve high-precision calculation of specimen strain, providing key evidence for accurately evaluating the mechanical properties of materials.

[0046] a. Employing the Digital Image Correlation (DIC) algorithm The strain calculation agent uses the Digital Image Correlation (DIC) algorithm as the basis for strain calculation. This algorithm is based on comparing the gray-level correlation of feature points in two adjacent image frames. During a tensile test, feature points on the specimen surface shift as the material deforms. The data processing agent has already matched feature points in images at different times and determined their positional changes. The DIC algorithm then further refines the displacement calculation by analyzing the gray-level information of small regions surrounding these feature points.

[0047] In practice, the strain calculation AI selects a sub-region of interest in a reference image (usually the image at the start of stretching), centered on a specific feature point. Then, it searches for the region with the most similar grayscale distribution in subsequent deformation images, determining the displacement of the feature point by calculating the grayscale correlation between the two. This grayscale correlation-based calculation method fully utilizes the texture information in the image, enabling relatively accurate tracking of the feature point's movement trajectory even when the specimen surface texture is complex.

[0048] b. Subpixel matching technology improves accuracy To further improve the accuracy of strain calculation, the strain calculation agent employs subpixel matching technology. In traditional pixel-level matching, the displacement of feature points can only be accurate to integer pixels, which is far from sufficient for measuring some minute deformations. Subpixel matching technology, on the other hand, can improve the accuracy of displacement measurement to the subpixel level.

[0049] The strain calculation agent employs methods such as the Newton-Raphson iterative method to achieve sub-pixel matching. This method, based on gray-level gradient information, finds the best-matching sub-pixel position through continuous iterative optimization. Specifically, it first calculates a more accurate displacement correction based on the approximate position obtained from pixel-level matching, using the gray-level gradients of surrounding pixels. Then, it continuously adjusts the position estimation of feature points until certain convergence conditions are met. This significantly improves the accuracy of feature point displacement measurement, thereby providing more precise data for strain calculation.

[0050] c. Strain calculation and meshing After acquiring high-precision feature point displacement information, the strain calculation agent begins to calculate the strain of the specimen. The strain calculation is based on the fundamental principles of mechanics of materials, determining the strain value according to the displacement changes of feature points and their initial distance relationships. For strain calculations in a two-dimensional plane, normal strain and shear strain are typically calculated along different directions.

[0051] To obtain the strain distribution across the entire specimen, the strain calculation agent performs gridding on the strain calculation results. It divides the specimen surface into several small grid regions, each grid being a square or triangle, etc. Then, for each grid region, it calculates the average strain value of its internal feature points as the representative strain value for that region. In this way, the discrete feature point strain information can be extended to the entire specimen surface, forming a continuous full-field strain distribution (the strain measurement results for the entire specimen). Gridding not only provides a more intuitive display of the specimen's strain but also facilitates subsequent analysis and comparison of strain in different regions, such as identifying key information like strain concentration areas.

[0052] d. Verification and optimization of calculation results After completing strain calculation and meshing, the strain calculation agent will verify and optimize the results. It will compare the calculated strain with known theoretical values ​​or empirical data. If a large deviation is found between the calculated results and the reference values, the strain calculation agent will re-examine the calculation process, including the parameter settings of the DIC algorithm, the accuracy of sub-pixel matching, and the rationality of the meshing process.

[0053] For example, if a significant anomaly in strain values ​​is detected in a certain region, the strain calculation agent will re-analyze the matching of feature points within that region to check for matching errors or inaccurate extraction of grayscale information. Simultaneously, it will consider adjusting algorithm parameters, such as the correlation coefficient threshold in the DIC algorithm and the number of iterations for sub-pixel matching, to improve the accuracy of the calculation results. Through this verification and optimization mechanism, the strain calculation agent can continuously improve the accuracy and reliability of strain calculations, providing high-quality results for strain measurement in tensile tests of engineering materials.

[0054] D. Outcome Evaluation Agent The result evaluation agent plays a crucial role in quality control and feedback optimization within the entire multi-agent collaborative system for precise strain measurement in tensile testing of engineering materials. Its core task is to comprehensively and thoroughly evaluate the strain results output by the strain calculation agent, ensuring the accuracy and stability of the measurement results and providing a solid guarantee for the accurate evaluation of the mechanical properties of engineering materials.

[0055] a. Comparison and analysis with theoretical strain values The first step in the evaluation agent's work is to compare and analyze the actual strain measurements with the theoretical strain values. To obtain the theoretical strain values, it establishes a corresponding material constitutive model based on the material's properties and the specific conditions of the tensile test. For example, for common linear elastic materials, Hooke's law is used to construct the model; while for nonlinear materials, a more complex elastoplastic constitutive model is selected.

[0056] b. Accuracy assessment After establishing the constitutive model, the theoretical strain value is calculated by combining parameters such as the external force applied in the tensile test and the dimensions of the specimen. Subsequently, these theoretical strain values ​​are meticulously compared point-by-point or region-by-region with the actual measured strain values ​​output by the strain calculation agent. If a significant deviation is found, the result evaluation agent will mark these areas of large deviation and conduct an in-depth analysis of the possible causes of the deviation. This may involve inaccuracies in the material constitutive model, interference from external factors during the experiment, or problems in the preceding image acquisition, data processing, and strain calculation stages.

[0057] c. Stability assessment In addition to accuracy assessment, the results evaluation agent also rigorously evaluates the stability of the measurement results. It judges the stability of the measurement system by analyzing the fluctuations in strain measurements over different time periods. Specifically, the entire tensile test process is divided into multiple time periods according to certain time intervals, and then the mean, variance, and other statistical quantities of the strain measurements are calculated for each time period.

[0058] If the variance of strain measurements is too large within a certain time period, it indicates that the measurement results fluctuate drastically during that period, and the measurement system may have unstable factors. These unstable factors may originate from vibrations of the experimental equipment, changes in ambient temperature, unstable lighting during image acquisition, etc. Once the result evaluation agent detects a stability problem, it will promptly record relevant information and further investigate the specific cause.

[0059] d. Feedback and Adjustment Mechanism When the result evaluation agent detects a large error or instability in the measurement results, it immediately initiates a feedback and adjustment mechanism. This mechanism relays the problem to other agents in the system, triggering corresponding adjustment operations.

[0060] If the problem is due to poor image acquisition quality, it will instruct the image acquisition agent to readjust camera parameters such as focal length, aperture, and exposure time, or optimize lighting conditions and reacquire images. If a problem is suspected in the data processing stage, it will instruct the data processing agent to check for any unreasonable aspects in the image preprocessing algorithm, image segmentation method, and feature point matching algorithm, and make corresponding optimizations. For the strain calculation stage, it will prompt the strain calculation agent to check the parameter settings of the DIC algorithm, the accuracy of sub-pixel matching, and the rationality of the meshing process, and make necessary corrections.

[0061] After the adjustment operation is triggered, the result evaluation agent continuously monitors subsequent measurement results and re-evaluates them until the accuracy and stability of the measurement results meet the predetermined requirements. Through this continuous feedback and adjustment cycle, the result evaluation agent ensures that the entire measurement system (also called the measurement environment, which is a measurement system composed of four agents) can output high-precision, stable, and reliable strain measurement results, laying the foundation for the smooth conduct of tensile tests on engineering materials and the accurate evaluation of the mechanical properties of materials.

[0062] The hardware architecture used in this embodiment is the foundation for the smooth operation of the entire strain precision measurement work, and it consists of multiple key devices working together.

[0063] The industrial camera is the core hardware for image acquisition. To meet the requirements for acquiring images of specimen deformation in tensile tests of engineering materials, a high-resolution industrial camera was selected. High resolution can capture subtle changes on the specimen surface, providing rich and accurate image information for subsequent strain calculations. Its frame rate can be flexibly set according to the specific circumstances of the tensile test, ensuring that clear images are acquired in a timely manner at each stage of specimen deformation. For example, for experiments with rapid deformation, the camera frame rate is increased; for experiments with slow deformation, the frame rate is appropriately reduced to balance data volume and acquisition quality. The camera lens was also carefully selected, possessing excellent optical performance to reduce image distortion and other problems.

[0064] Auxiliary lighting is a crucial component in ensuring image quality. Stable and uniform illumination is essential for image acquisition during experiments. Therefore, specialized auxiliary lighting equipment, such as ring lights or area lights, is employed. Ring lights can be arranged around the camera lens to provide uniform ring illumination, effectively avoiding shadows, and are particularly suitable for situations requiring high detail on the specimen surface. Area lights provide large-area, uniform illumination, suitable for photographing larger specimens. The brightness of these lighting devices can be adjusted according to the actual experimental environment to achieve optimal imaging results.

[0065] The image acquisition card is responsible for transmitting image data captured by the industrial camera to the computer. It features high-speed data transmission capabilities, ensuring that image data is transmitted without loss or interruption. The image acquisition card has excellent compatibility with both the industrial camera and the computer, reliably transferring image data from the camera to the computer's memory, preparing it for subsequent data processing.

[0066] The computer is the processing center of the entire hardware architecture. It possesses powerful computing capabilities and storage capacity, enabling it to run software programs for various intelligent agents. The computer's processor needs a high number of cores and a high clock speed to handle the demands of complex tasks such as image data processing and strain calculation. Sufficient memory capacity is required to cache large amounts of image data and intermediate calculation results. The hard drive needs fast read / write speeds and a large storage capacity for long-term storage of experimental image data and final strain measurement results. Furthermore, the computer is equipped with a high-resolution monitor, allowing operators to view experimental images and measurement results in real time.

[0067] In this embodiment, each of the four intelligent agents corresponds to an independent software module, and the software modules have a clear division of labor and close cooperation.

[0068] Each intelligent agent software module has its own input / output interfaces, data processing logic, and communication interfaces. Input / output interfaces are the channels through which modules interact with the outside world.

[0069] The image acquisition agent software module receives camera parameters and other information set by the operator through its input interface, and sends the acquired image data to the data processing agent software module through its output interface. The data processing logic is the core of each agent software module, enabling the agent's specific functions. For example, the data processing logic in the data processing agent software module includes algorithms for image filtering, enhancement, segmentation, and feature point matching, processing the input image data according to a predetermined process.

[0070] The communication interface is responsible for communication between modules and the message queue. The message queue plays a role in data transfer and coordination within the software architecture. Each agent software module sends its generated data or requests to the message queue through the communication interface, and simultaneously receives data or instructions from other modules from the message queue. For example, the strain calculation agent software module obtains feature point displacement information sent by the data processing agent module from the message queue through the communication interface. After completing the strain calculation, it sends the strain results back to the message queue through the communication interface for the result evaluation agent software module to obtain and evaluate.

[0071] This modular software architecture design gives the measurement system excellent scalability and maintainability. If the functionality of a particular agent needs to be optimized or extended, only the corresponding software module needs to be modified, without affecting the normal operation of other modules. At the same time, new functional modules can be easily added to the measurement system, working in conjunction with existing modules to continuously improve the performance and functionality of the entire measurement system.

[0072] Example 5: Please see Figure 3 As shown, the present invention also provides an electronic device 100 for measuring strain in tensile tests of engineering materials; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0073] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the tensile strain measurement method for engineering materials described in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0074] The at least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100, connecting various parts of the electronic device 100 via various interfaces and lines.

[0075] The memory 101 in the electronic device 100 stores multiple instructions to implement a tensile strain measurement method for engineering materials, and the processor 102 can execute the multiple instructions to achieve the following: Acquire images of engineering materials during the tensile process; Image segmentation is performed on images of engineering materials during the stretching process to obtain the contour information of the engineering materials; Feature point matching is performed on the contour information of engineering materials to obtain the displacement change information of feature points on the surface of engineering materials during the stretching process; Based on the displacement change information of feature points on the surface of engineering materials during the tensile process, the local strain measurement results of engineering materials are obtained.

[0076] Example 6: If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0077] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0079] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0080] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for measuring strain in tensile tests of engineering materials, characterized in that, Includes the following steps: Acquire images of engineering materials during the tensile process; Image segmentation is performed on images of engineering materials during the stretching process to obtain the contour information of the engineering materials; Feature point matching is performed on the contour information of engineering materials to obtain the displacement change information of feature points on the surface of engineering materials during the stretching process; Based on the displacement change information of feature points on the surface of engineering materials during the tensile process, the local strain measurement results of engineering materials are obtained.

2. The method for measuring strain in tensile tests of engineering materials according to claim 1, characterized in that, The acquisition of images during the stretching process of engineering materials specifically involves acquiring images of the stretching process of engineering materials using a high-resolution industrial camera and auxiliary lighting devices.

3. The method for measuring strain in tensile tests of engineering materials according to claim 1, characterized in that, Before performing image segmentation on the images of the engineering material during the stretching process to obtain the contour information of the engineering material, the acquired images of the engineering material during the stretching process are filtered, enhanced, compressed, and quality inspected.

4. The method for measuring strain in tensile tests of engineering materials according to claim 1, characterized in that, The method of obtaining local strain measurement results of engineering materials based on the displacement change information of feature points on the surface of engineering materials during the tensile process is as follows: using digital image correlation algorithm and sub-pixel matching technology, local strain measurement results of engineering materials are obtained based on the displacement change information of feature points on the surface of engineering materials during the tensile process.

5. The method for measuring strain in tensile tests of engineering materials according to claim 1, characterized in that, After obtaining the local strain measurement results of the engineering material, the local strain measurement results of the engineering material are evaluated to obtain the evaluation results of the local strain measurement of the engineering material.

6. The method for measuring strain in tensile tests of engineering materials according to claim 5, characterized in that, If the results of the local strain measurement and evaluation of the engineering materials do not meet the requirements, feedback and adjustments will be made based on the results of the local strain measurement and evaluation of the engineering materials.

7. The method for measuring strain in tensile tests of engineering materials according to claim 1, characterized in that, After obtaining the local strain measurement results of the engineering material, the strain measurement results of the entire engineering material are obtained based on the local strain measurement results.

8. A strain measurement system for tensile testing of engineering materials, characterized in that, include: The data acquisition module is used to acquire images of engineering materials during the tensile process; The image segmentation module is used to segment images of engineering materials during the stretching process to obtain the contour information of the engineering materials. The feature point matching module is used to match feature points on the contour information of engineering materials to obtain the displacement change information of feature points on the surface of engineering materials during the stretching process. The measurement module allows for the measurement of local strain of engineering materials based on the displacement changes of feature points on the surface of the engineering material during the tensile process.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the tensile strain measurement method for engineering materials as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the tensile strain measurement method for engineering materials as described in any one of claims 1 to 7.

Images