CN117091953A - Automatic measuring method, computer equipment, system and storage medium for sample deformation - Google Patents

Automatic measuring method, computer equipment, system and storage medium for sample deformation Download PDF

Info

Publication number
CN117091953A
CN117091953A CN202311354234.1A CN202311354234A CN117091953A CN 117091953 A CN117091953 A CN 117091953A CN 202311354234 A CN202311354234 A CN 202311354234A CN 117091953 A CN117091953 A CN 117091953A
Authority
CN
China
Prior art keywords
sample
deformation
clamp
gauge length
testing machine
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311354234.1A
Other languages
Chinese (zh)
Inventor
李长太
毕胜昔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Haisaimu Technology Co ltd
Original Assignee
Shenzhen Haisaimu Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Haisaimu Technology Co ltd filed Critical Shenzhen Haisaimu Technology Co ltd
Priority to CN202311354234.1A priority Critical patent/CN117091953A/en
Publication of CN117091953A publication Critical patent/CN117091953A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N3/08—Investigating strength properties of solid materials by application of mechanical stress by applying steady tensile or compressive forces
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N3/02—Details
    • G01N3/06—Special adaptations of indicating or recording means
    • G01N3/068—Special adaptations of indicating or recording means with optical indicating or recording means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00584—Control arrangements for automatic analysers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/0099—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor comprising robots or similar manipulators
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N2203/0001—Type of application of the stress
    • G01N2203/0003—Steady
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N2203/0014—Type of force applied
    • G01N2203/0016—Tensile or compressive
    • G01N2203/0017—Tensile
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N2203/0058—Kind of property studied
    • G01N2203/0069—Fatigue, creep, strain-stress relations or elastic constants
    • G01N2203/0075—Strain-stress relations or elastic constants
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N2203/02—Details not specific for a particular testing method
    • G01N2203/06—Indicating or recording means; Sensing means
    • G01N2203/0641—Indicating or recording means; Sensing means using optical, X-ray, ultraviolet, infrared or similar detectors
    • G01N2203/0647—Image analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N2203/02—Details not specific for a particular testing method
    • G01N2203/06—Indicating or recording means; Sensing means
    • G01N2203/067—Parameter measured for estimating the property
    • G01N2203/0682—Spatial dimension, e.g. length, area, angle

Abstract

The application relates to vision measurement technology, and discloses an automatic measurement method for sample deformation, which comprises the following steps: the control manipulator grabs a sample from the sample placing platform and clamps the sample between a first clamp and a second clamp of the testing machine; controlling a video extensometer to collect pictures of a sample on the testing machine, and controlling the testing machine to stretch the sample through the first clamp and the second clamp to obtain a series of pictures of the sample in the stretching process; identifying scale distance features in each picture based on the artificial intelligence model; deformation data of the sample is generated based on the digital image correlation method and scale features in a series of pictures. The application also discloses a computer device, a deformation measurement system and a computer readable storage medium. The application aims to realize automation of sample loading and deformation detection and efficiently measure deformation data of a sample.

Description

Automatic measuring method, computer equipment, system and storage medium for sample deformation
Technical Field
The present application relates to the field of vision measurement technology, and in particular, to an automatic measurement method for deformation of a sample, a computer device, a deformation measurement system, and a computer readable storage medium.
Background
Along with the wide application of the detection of the deformation of the material in the mechanical properties in industrial application, how to accurately and efficiently detect the deformation of the material is increasingly important. The deformation detection can be applied to the composition and structure test of various materials, so that the qualification of the product quality can be ensured, and the rationality of the composition and structure design of the materials can be verified.
At present, in the mechanical property measurement link of material delivery, the requirement of customers on detection frequency is higher and higher, and extensometer equipment with higher degree of automation is needed to detect the deformation of the material, so that the deformation detection efficiency is improved. The extensometer device used in the prior material deformation test often has very complicated mechanical structure, so that the whole extensometer has very complicated processes of fixing, stretching and scattering the sample, and the time consumption is very long (such as a full-automatic mechanical extensometer disclosed in the patent document with the publication number of CN 102778393A), and the requirement of efficiently detecting the material deformation is difficult to meet.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The application mainly aims to provide an automatic measuring method, computer equipment, a deformation measuring system and a computer readable storage medium for sample deformation, and aims to realize automation of sample loading and deformation detection and efficiently measure deformation data of a sample.
In order to achieve the above object, the present application provides an automatic measurement method for deformation of a sample, comprising the steps of:
the control manipulator grabs a sample from the sample placing platform and clamps the sample between a first clamp and a second clamp of the testing machine;
controlling a video extensometer to collect pictures of a sample on the testing machine, and controlling the testing machine to stretch the sample through the first clamp and the second clamp to obtain a series of pictures of the sample in the stretching process;
identifying scale distance features in each picture based on the artificial intelligence model;
deformation data of the sample is generated based on the digital image correlation method and scale features in a series of pictures.
Optionally, the step of identifying the scale distance feature in each picture based on the artificial intelligence model includes:
inputting each picture acquired by the video extensometer into a pre-trained artificial intelligent model to detect fuzzy coordinates corresponding to the mark distance characteristic positions in the pictures;
intercepting a gauge length region image in the picture according to the fuzzy coordinates;
and carrying out edge detection on the gauge length region image, and determining gauge length features based on an edge detection result.
Optionally, before the step of performing edge detection on the gauge length area image and determining the gauge length feature based on the edge detection result, the method further includes:
and carrying out noise reduction processing on the gauge length region image.
Optionally, the step of performing noise reduction processing on the gauge length area image includes:
and carrying out gray conversion and mean value filtering treatment on the scale distance area image.
Optionally, the automatic measurement method for deformation of the sample further includes:
after the average value filtering processing is carried out on the gauge length region image, the type of the gauge length feature is determined according to the central point pixel of the gauge length region image;
determining a filtering threshold according to the scale distance characteristic type;
and filtering the gauge length region image based on the filtering threshold value.
Optionally, after the step of generating deformation data of the sample based on the digital image correlation method and the scale features in the series of pictures, the method further includes:
synchronously transmitting the deformation data to the testing machine;
and controlling the testing machine to stretch the sample to fracture, and generating a tensile test report according to the received deformation data.
Optionally, the automatic measurement method for deformation of the sample further includes:
and after the testing machine stretches the sample to be broken, controlling the manipulator to move the broken sample to a sample recovery position, and returning to the step of executing the control manipulator to grasp the sample from the sample placement platform and clamp the sample between a first clamp and a second clamp of the testing machine.
To achieve the above object, the present application also provides a computer apparatus comprising: the automatic deformation measuring device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the computer program realizes the steps of the automatic deformation measuring method for the sample when being executed by the processor.
To achieve the above object, the present application also provides a deformation measuring system comprising the computer device as described above, and comprising a manipulator, a testing machine and a video extensometer.
In order to achieve the above object, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the automatic measurement method of sample deformation as described above.
According to the automatic measuring method, the computer equipment, the deformation measuring system and the computer readable storage medium for the deformation of the sample, the automation of sample loading and deformation detection is realized based on the combination of the manipulator, the testing machine and the video extensometer, and deformation data are measured through an artificial intelligent model and a digital image correlation method, so that the requirement of efficiently detecting the deformation of the sample is met.
Drawings
FIG. 1 is a schematic diagram showing steps of an automatic measurement method for deformation of a sample according to an embodiment of the present application;
FIG. 2 is an exemplary diagram of a deformation measurement system disposed at a measurement site in accordance with one embodiment of the present application;
fig. 3 is a schematic block diagram illustrating an internal structure of a computer device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below are exemplary and intended to illustrate the present application and should not be construed as limiting the application, and all other embodiments, based on the embodiments of the present application, which may be obtained by persons of ordinary skill in the art without inventive effort, are within the scope of the present application.
Furthermore, the description of "first," "second," etc. in this disclosure is for descriptive purposes only (e.g., to distinguish between identical or similar elements) and is not to be construed as indicating or implying a relative importance or an implicit indication of the number of features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.
Referring to fig. 1, in one embodiment, the method for automatically measuring deformation of a sample includes:
s10, controlling a manipulator to grasp a sample from a sample placement platform, and clamping the sample between a first clamp and a second clamp of a testing machine;
s20, controlling a video extensometer to collect pictures of a sample on the testing machine, and controlling the testing machine to stretch the sample through the first clamp and the second clamp to obtain a series of pictures of the sample in the stretching process;
step S30, identifying scale distance features in each picture based on the artificial intelligent model;
and S40, generating deformation data of the sample based on the digital image correlation method and the scale distance features in a series of pictures.
In this embodiment, the execution terminal of the embodiment may be a computer device, or other device or apparatus for controlling a computer device (such as a virtual control apparatus loaded on the computer device).
Alternatively, referring to fig. 2, a strain measurement system is disposed at a strain measurement site of a sample, the strain measurement system including a computer device, a manipulator, a testing machine, and a video extensometer, and the manipulator, the testing machine, and the video extensometer are all in communication with and controlled by the computer device.
Optionally, a sample placing platform is further arranged on the deformation measurement site and is used for placing all samples to be detected; the sample can be a material to be detected, which needs to detect mechanical properties such as components, structures and the like.
Optionally, a sample recovery site (such as a collection box) is also arranged at the deformation measurement site, and is used for recovering the measured sample.
Alternatively, in order to fix the manipulator, the deformation measurement site may be provided with a manipulator platform, and the manipulator is mounted on the manipulator platform.
As described in step S10, the computer device is preloaded with a control program for the manipulator, and transmits a command to control the movement of the manipulator through communication with the manipulator. The manipulator is provided with a proper clamping part to ensure that the sample can be accurately clamped and placed between the clamps of the testing machine; and presetting a grabbing and placing strategy of the manipulator according to the geometric dimension and shape of the sample.
Optionally, when the deformation measurement is started to the sample, the clamping part of the control manipulator is opened and descends to the upper part of the sample placing platform, and then after a sample is grabbed from the sample placing platform according to the preset clamping force, the manipulator is lifted, so that the sample leaves the sample placing platform.
Then, the control manipulator grips the specimen and moves between the first clamp and the second clamp of the testing machine, and places the specimen.
Optionally, the first clamp and the second clamp of the testing machine are designed in advance according to the geometric shape and the size of the sample, so that the parts of the first clamp and the second clamp for clamping the sample can be matched with the sample. And the first clamp and the second clamp are preset with proper clamping force, so that the sample is ensured to be clamped firmly, and meanwhile, the sample is prevented from being additionally deformed or damaged.
As described in step S20, a control program of the video extensometer is pre-programmed to establish a connection with the computer device and receive the control signal. The computer equipment can set configuration parameters of the video extensometer, such as frame rate, resolution and other parameters of the acquired pictures, so as to meet detection requirements.
Optionally, the video extensometer is set in advance at a position kept at a certain distance from the testing machine, so that the image acquisition range of the video extensometer can cover the first clamp and the second clamp of the testing machine.
Optionally, when the computer device or the video extensometer receives the notification information of starting to stretch the sample sent by the testing machine, the video extensometer is triggered to start to continuously collect the picture of the sample on the testing machine.
Meanwhile, the control testing machine stretches the sample by using the first clamp and the second clamp based on a preset clamp moving distance or stretching speed. It should be understood that the direction of specimen stretching is determined by the relative positional relationship of the first clamp and the second clamp; if the first clamp and the second clamp are oppositely arranged along the vertical direction, the sample can be vertically stretched; if one clamp and the second clamp are arranged opposite to each other in the horizontal direction, the sample can be horizontally stretched.
Optionally, the video extensometer collects pictures according to a preset frequency in the test process to obtain a series of pictures of the deformation of the sample, and in the process of collecting the pictures, the collected pictures are transmitted to the computer equipment for processing and storage. And the computer equipment can store all the received pictures according to the time of collecting each picture in time sequence.
As described in step S30, the artificial intelligence model for picture gauge length feature recognition is trained in advance using the specimen picture dataset labeled with known surface features and gauge lengths in combination with the deep learning technique. The trained artificial intelligent model can be deployed on a video extensometer or a computer device or other devices which can be communicated and called by the computer device.
An example of the training process for an artificial intelligence model is as follows:
1. and (3) data acquisition: a test sample picture dataset marked with known gauge length features is collected, and each picture is labeled with the location and value of the gauge length feature. The collected picture data is preprocessed, including resizing, cropping, denoising, etc., to provide clear and consistent input data.
2. And (3) establishing a model: based on the deep learning technique, an image recognition model is trained using the collected samples with the annotation data. The method can select a proper convolutional neural network architecture (such as a CNN convolutional neural network) as a basic model, and adjust network structures and parameters according to actual requirements.
3. Model training: dividing the picture data set into a training set, a verification set and a test set, training and optimizing the model by using the training set, evaluating the performance and adjustment parameters of the model by using the verification set, and finally evaluating the accuracy of the final model by using the test set to obtain the artificial intelligent model after training.
Optionally, after each picture is acquired by the video extensometer, the picture acquired in real time can be input into the trained artificial intelligence model to identify the scale distance features. And identifying the scale distance characteristics of the sample surface by utilizing the artificial intelligent model, and simultaneously, accurately positioning and tracking the scale distance characteristics in the picture by combining a digital image correlation method (Digital Image Correlation, DIC) with the identification result of the artificial intelligent model.
Therefore, by utilizing an image recognition technology based on an artificial intelligent model, the automatic recognition and measurement of the mark distance features in the test sample picture can be realized, so that the accuracy and efficiency of deformation measurement are improved.
After identifying and marking the scale features in the series of pictures, the series of pictures may be further image processed (e.g., binarized, filtered, etc.) to enhance image correlation, as described in step S40.
Optionally, a digital image correlation method is used to calculate the displacement of each scale distance feature between different pictures, and deformation data of the sample in the stretching process is obtained. The displacement corresponding to the scale distance feature can be calculated by adopting the existing mode of calculating the displacement of the feature point between different time sequence pictures based on the digital image correlation method.
Optionally, deformation data of the specimen, such as stress-strain curves, young's modulus, poisson's ratio, etc., are calculated and generated from the displacement of the gauge length feature and the geometric dimensions of the specimen.
In an embodiment, the automation of sample fixing and deformation detection is realized based on a combination of a manipulator, a testing machine and a video extensometer, and deformation data is measured through an artificial intelligent model and a digital image correlation method, so that the requirement of efficiently detecting the deformation of the sample is met.
Compared with the traditional mechanical full-automatic extensometer or the traditional full-automatic video extensometer, the automatic measuring method for the deformation of the sample has high degree of automation, can automatically load, loft and stretch the sample, reduces the steps of manual intervention, saves the labor cost and improves the measuring efficiency; and moreover, the surface characteristics of the sample can be automatically identified and the scale distance characteristics can be defined through deep learning and a visual algorithm, manual marking or setting is not needed, the high-accuracy scale distance definition is ensured, and the measurement efficiency and accuracy are improved.
In an embodiment, based on the above embodiment, the identifying the scale features in each picture based on the artificial intelligence model includes:
inputting each picture acquired by the video extensometer into a pre-trained artificial intelligent model to detect fuzzy coordinates corresponding to the mark distance characteristic positions in the pictures;
intercepting a gauge length region image in the picture according to the fuzzy coordinates;
and carrying out edge detection on the gauge length region image, and determining gauge length features based on an edge detection result.
In this embodiment, each picture acquired by the video extensometer is input into a pre-trained artificial intelligence model, which analyzes and processes the picture and detects fuzzy coordinates (x, y, w, h) that may contain the scale feature positions.
It should be noted that the fuzzy coordinates (x, y, w, h) are a form of coordinates for representing the position and size of the target area, and are commonly used in the fields of computer vision and image processing. The specific meanings are as follows:
x: the horizontal position (or abscissa) representing the target area is typically a pixel position starting with the upper left corner of the image as a reference point (it will be appreciated that it may also be the upper right corner, lower left corner, lower right corner or center point, depending on the actual situation).
y: the vertical position (or ordinate) representing the target area is also the pixel position with the upper left corner of the image as the reference point (it will be understood that the upper right corner, lower left corner, lower right corner or center point may be provided as the case may be).
w: the width of the target area, i.e., the horizontal span (in pixel units) of the target frame is represented.
h: the height of the target area, i.e., the vertical span (in pixel units) of the target frame is represented.
The fuzzy coordinates may be used to locate a target region of interest in an image or video, as in this scenario, to locate and intercept a region image containing a gauge length feature. By providing the position and size information of the region, the fuzzy coordinates can help the program to accurately locate and extract the required target region, so that subsequent processing operations such as feature extraction, analysis or measurement can be performed.
Optionally, according to the fuzzy coordinates, a scale distance region image containing scale distance features is intercepted from the original picture. The truncated area image should cover the full range of gauge length to ensure subsequent edge detection accuracy.
Alternatively, the edge detection is performed on the gauge length region image using a suitable image processing algorithm (e.g., canny edge detection operator), and the edge detection result can provide rough position and shape information of the gauge length feature, so that obvious edges in the image can be effectively detected. The Canny edge detection operator performs gradient calculation and non-maximum suppression on the image so as to keep stronger edge characteristics.
Optionally, the detected edge contour is screened, and judgment and filtration can be performed according to the length, shape, direction and other characteristics of the edge. And selecting edges meeting preset conditions for subsequent processing by setting threshold values and parameters.
The preset condition may be a length threshold, for example, setting a minimum length of an edge profile, and filtering out too short edges to eliminate noise or irrelevant details; the preset condition can also be shape screening, and screening is performed according to shape characteristics of edges, such as bending degree of edge curves, R square value of straight line fitting and the like; the preset condition can also be a direction threshold value, the direction range of the edge contour is limited, and the edge inconsistent with the target can be eliminated; the preset condition can also be an intensity/gradient threshold value, and the intensity or gradient threshold value of the edge is set so as to exclude weaker or unobvious edges; the preset condition can also be closure/connectivity detection, namely whether the edges form a closed communication profile or not is detected, and incomplete or broken edges can be eliminated; the preset condition may also be a proportional relationship, and by considering the aspect ratio of the edge profile or the proportional relationship of the area and the whole image, the abnormal or unexpected edge may be eliminated.
It should be noted that these preset conditions may be adjusted and defined according to specific application scenarios and actual requirements, so as to screen and select an edge profile meeting the requirements for subsequent fitting and determination of scale distance features. In practical application, the method can be debugged and optimized according to specific conditions so as to obtain the best effect.
Alternatively, the edges that pass the filtering are fitted, for example, using a least squares fit line, a polynomial curve, or the like. The fitting process finds the best fitting result according to the shape of the edge and the fitting model.
Optionally, the central position of the gauge length feature is determined according to the central point or the key point of the fitting result. The center point coordinates may be the geometric center of the fitting result, the center of gravity, the peak position of the fitting curve, etc.
Through the steps, edge detection is carried out by using a Canny edge detection operator, the edges meeting the requirements are fitted, and the center point coordinates of the gauge length features are extracted from the fitting result. Thus, the scale distance characteristics can be effectively positioned, and relevant position information is provided, so that the subsequent deformation measurement and analysis are facilitated; namely, the automatic identification of the gauge length features is realized, so that the accuracy and the efficiency of measurement are improved.
In an embodiment, before the step of performing edge detection on the gauge length area image and determining the gauge length feature based on the edge detection result, the method further includes:
and carrying out noise reduction processing on the gauge length region image.
In this embodiment, before edge detection, a suitable noise reduction processing mode may be selected according to the image characteristics and the noise type, so as to perform noise reduction processing on the image of the gauge length region, so as to reduce noise interference in the image.
The noise reduction processing mode can be mean filtering, median filtering, gaussian filtering, bilateral filtering and the like.
Optionally, the noise reduction processing mode may adopt various filters or filtering algorithms to smooth the image in the space domain or the frequency domain or remove isolated noise points.
Optionally, after the noise reduction processing, quality evaluation can be further performed on the noise-reduced image, and the noise reduction effect and the retention degree of image details can be checked. For example, the noise index, the structural similarity index and the like are adopted for evaluation, so that the quality and the detail of the image after the noise reduction treatment can still meet the requirement of edge detection.
By carrying out noise reduction processing on the gauge length region image, the interference of noise on edge detection can be reduced, and the accuracy and the robustness of the edge detection are improved.
In an embodiment, on the basis of the foregoing embodiment, the step of performing noise reduction processing on the gauge length area image includes:
and carrying out gray conversion and mean value filtering treatment on the scale distance area image.
In this embodiment, the gauge length region image is converted from a color or other color space to a gray scale image, which facilitates subsequent processing and edge detection.
Then, the gray level image is subjected to mean value filtering processing to reduce noise of the image by taking the average value of the neighborhood around the pixel. The average value filtering algorithm calculates an average gray value of pixels in the neighborhood at each pixel position, and takes the average gray value as a gray value of an output pixel.
In using OpenCV for gray scale conversion and mean filtering of a feature area image, the feature area image may be converted from color or other color space to a gray scale image using the cvtColor function of OpenCV, and the gray scale image may be mean filtered using the blu function of OpenCV.
In this way, by performing gradation conversion and average filtering processing on the gauge region image, the image can be converted into a gradation space and noise can be reduced. The gray conversion simplifies the image processing, and the average filtering processing reduces noise in the image by averaging gray values of neighboring pixels. And gray conversion and mean filtering processing are carried out on the image before edge detection, so that the accuracy and the robustness of subsequent edge detection can be improved.
In an embodiment, on the basis of the foregoing embodiment, after performing a mean filtering process on the gauge length region image, a gauge length feature type is determined according to a center point pixel of the gauge length region image;
determining a filtering threshold according to the scale distance characteristic type;
and filtering the gauge length region image based on the filtering threshold value.
In this embodiment, when the average filtering process is performed on the gauge length region image, the gauge length feature type is classified and determined according to the pixel value of the center point of the gauge length region image. For example, assuming that the scale feature types are classified into two categories, "a" and "B", the feature type of the scale may be determined by comparing the center pixel gray value with other preset gray values by a threshold.
Wherein the gauge length features are pre-classified into different types according to specific criteria and experience. Each type of scale features has different morphological, color, texture, etc. features, as well as corresponding filtering thresholds. The filtering threshold may be a different type of threshold for gray values, color ranges, morphological parameters, etc.
And then, according to the determined scale distance characteristic type, acquiring a corresponding filtering threshold value.
Optionally, after the average filtering processing is performed on the gauge length region image, binarization can be performed on the filtered image according to a determined filtering threshold value, so as to filter out feature regions which do not meet requirements or extract feature regions of interest, and then edge detection is performed subsequently based on the rest of the gauge length region image, so that accuracy and reliability of identifying the gauge length features are improved.
In an embodiment, after the step of generating deformation data of the sample based on the digital image correlation method and the scale features in the series of pictures, the method further includes:
synchronously transmitting the deformation data to the testing machine;
and controlling the testing machine to stretch the sample to fracture, and generating a tensile test report according to the received deformation data.
In this embodiment, the computer device transmits the generated deformation data to the testing machine through a suitable communication manner (for example, a data line or network connection), so as to monitor and record the deformation condition of the sample in real time, ensure that the deformation data can be accurately and efficiently transmitted to the testing machine, and maintain the integrity and accuracy of the data.
Optionally, the testing machine can also adjust the tensile load applied to the sample, such as adjusting the tensile speed, the tensile strength, etc., through a suitable control system or software according to the received deformation data.
Optionally, after the testing machine stretches the sample to fracture, a tensile test report can be generated and output according to the received deformation data and in combination with the loading process of the testing machine and other relevant test data. The tensile test report may include tensile performance indexes such as maximum strength and elongation at break of the test specimen, and data such as deformation curve and stress-strain curve during loading.
Alternatively, the testing machine may analyze and process the deformation data using appropriate software or algorithms to generate tensile test reports conforming to standard formats and requirements, according to test requirements and criteria.
Therefore, the real-time transmission synchronization of deformation data and the automatic generation of test results can be realized, the automation degree and the efficiency of the test are improved, and powerful support is provided for the recording and the analysis of the test results.
In an embodiment, on the basis of the foregoing embodiment, the automatic measurement method for deformation of a sample further includes:
and after the testing machine stretches the sample to be broken, controlling the manipulator to move the broken sample to a sample recovery position, and returning to the step of executing the control manipulator to grasp the sample from the sample placement platform and clamp the sample between a first clamp and a second clamp of the testing machine.
In this embodiment, after the sample is broken, the computer device or the testing machine may send a trigger signal to the manipulator to control the manipulator to move to the sample position at the testing machine, grasp the broken sample, and accurately move the broken sample to the sample recovery position.
Wherein the sample collection site may be a specially designed location or container for collecting the broken sample.
And then returning to execute the step (namely returning to execute the step S10) of controlling the manipulator to grasp the sample from the sample placing platform and clamp the sample between the first clamp and the second clamp of the testing machine, returning the controlling manipulator to the position of the sample placing platform, accurately grasping the next sample to be tested, and repositioning the sample at the corresponding position of the testing machine.
Therefore, automatic recovery and re-clamping operation after sample fracture can be realized, and correct clamping of the samples in the next test is ensured, so that continuity and efficiency of deformation measurement on a plurality of samples are improved, and manual intervention is reduced.
The embodiment of the application also provides computer equipment, and the internal structure of the computer equipment can be shown in fig. 3. The computer device includes a processor, a memory, a communication interface, and a database connected by a system bus. Wherein the processor is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store data of computer program calls. The communication interface of the computer device is used for data communication with an external terminal. The input device of the computer device is used for receiving signals input by external equipment. The computer program is executed by the processor to implement an automatic measurement method of deformation of a sample as described in the above embodiments.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
In addition, the application also provides a deformation measuring system, referring to FIG. 2, which comprises the computer equipment, a manipulator, a testing machine and a video extensometer; and the manipulator, the testing machine and the video extensometer are respectively in communication connection with the computer equipment. Because the deformation measuring system adopts all the technical schemes of all the embodiments, at least the technical effects brought by the technical schemes of the embodiments are achieved, and the description is omitted herein.
Furthermore, the present application also proposes a computer-readable storage medium comprising a computer program which, when executed by a processor, implements the steps of the method for automatic measurement of deformation of a sample as described in the above embodiments. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
In summary, the method, the computer device, the deformation measurement system and the computer-readable storage medium for automatically measuring the deformation of the sample provided by the embodiment of the application realize the automation of sample loading and deformation detection based on the combination of the manipulator, the testing machine and the video extensometer, and measure the deformation data through an artificial intelligent model and a digital image correlation method, thereby meeting the requirement of efficiently detecting the deformation of the sample.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present application and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application or direct or indirect application in other related technical fields are included in the scope of the present application.

Claims (10)

1. An automatic measurement method of deformation of a sample, comprising:
the control manipulator grabs a sample from the sample placing platform and clamps the sample between a first clamp and a second clamp of the testing machine;
controlling a video extensometer to collect pictures of a sample on the testing machine, and controlling the testing machine to stretch the sample through the first clamp and the second clamp to obtain a series of pictures of the sample in the stretching process;
identifying scale distance features in each picture based on the artificial intelligence model;
deformation data of the sample is generated based on the digital image correlation method and scale features in a series of pictures.
2. The method for automatically measuring deformation of a sample according to claim 1, wherein the step of identifying the gauge length feature in each picture based on the artificial intelligence model comprises:
inputting each picture acquired by the video extensometer into a pre-trained artificial intelligent model to detect fuzzy coordinates corresponding to the mark distance characteristic positions in the pictures;
intercepting a gauge length region image in the picture according to the fuzzy coordinates;
and carrying out edge detection on the gauge length region image, and determining gauge length features based on an edge detection result.
3. The method for automatically measuring deformation of a sample according to claim 2, wherein prior to the step of edge detecting the gauge length area image and determining the gauge length feature based on the edge detection result, further comprising:
and carrying out noise reduction processing on the gauge length region image.
4. The method for automatically measuring deformation of a sample according to claim 3, wherein the step of denoising the gauge length area image comprises:
and carrying out gray conversion and mean value filtering treatment on the scale distance area image.
5. The method for automatically measuring deformation of a sample according to claim 4, further comprising:
after the average value filtering processing is carried out on the gauge length region image, the type of the gauge length feature is determined according to the central point pixel of the gauge length region image;
determining a filtering threshold according to the scale distance characteristic type;
and filtering the gauge length region image based on the filtering threshold value.
6. The method for automatically measuring deformation of a sample according to any one of claims 1-5, wherein after the step of generating deformation data of the sample based on the digital image correlation method and the scale features in the series of pictures, further comprises:
synchronously transmitting the deformation data to the testing machine;
and controlling the testing machine to stretch the sample to fracture, and generating a tensile test report according to the received deformation data.
7. The method for automatically measuring deformation of a sample according to claim 6, further comprising:
and after the testing machine stretches the sample to be broken, controlling the manipulator to move the broken sample to a sample recovery position, and returning to the step of executing the control manipulator to grasp the sample from the sample placement platform and clamp the sample between a first clamp and a second clamp of the testing machine.
8. A computer device, characterized in that it comprises a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when being executed by the processor, carries out the steps of the method for automatic measurement of deformation of a sample according to any one of claims 1 to 7.
9. A deformation measurement system comprising the computer device of claim 8, and comprising a manipulator, a testing machine, and a video extensometer.
10. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements the steps of the method for automatic measurement of deformation of a sample according to any one of claims 1 to 7.
CN202311354234.1A 2023-10-19 2023-10-19 Automatic measuring method, computer equipment, system and storage medium for sample deformation Pending CN117091953A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311354234.1A CN117091953A (en) 2023-10-19 2023-10-19 Automatic measuring method, computer equipment, system and storage medium for sample deformation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311354234.1A CN117091953A (en) 2023-10-19 2023-10-19 Automatic measuring method, computer equipment, system and storage medium for sample deformation

Publications (1)

Publication Number Publication Date
CN117091953A true CN117091953A (en) 2023-11-21

Family

ID=88777349

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311354234.1A Pending CN117091953A (en) 2023-10-19 2023-10-19 Automatic measuring method, computer equipment, system and storage medium for sample deformation

Country Status (1)

Country Link
CN (1) CN117091953A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117492161A (en) * 2023-12-29 2024-02-02 深圳市迈腾电子有限公司 Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101832895A (en) * 2010-03-26 2010-09-15 北京纳克分析仪器有限公司 Visual tensile testing system
US20220051141A1 (en) * 2020-08-13 2022-02-17 The Boeing Company Material Characterization System and Method
CN114518289A (en) * 2022-01-25 2022-05-20 深圳三思纵横科技股份有限公司 Control method for deformation strain control by video acquisition
CN115014228A (en) * 2022-06-21 2022-09-06 深圳市海塞姆科技有限公司 Embedded extensometer based on vision measurement and double-shaft vision measurement method
CN115143895A (en) * 2022-06-21 2022-10-04 深圳市海塞姆科技有限公司 Deformation vision measurement method, device, equipment, medium and double-shaft measurement extensometer
KR20220161061A (en) * 2021-05-28 2022-12-06 현대제철 주식회사 Tensile testing device
CN116797648A (en) * 2023-06-08 2023-09-22 深圳市海塞姆科技有限公司 Width measuring method, device, equipment, system and medium for material deformation process
CN116839495A (en) * 2023-06-25 2023-10-03 深圳市海塞姆科技有限公司 Deformation vision measurement method based on laser speckle, video extensometer and medium

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101832895A (en) * 2010-03-26 2010-09-15 北京纳克分析仪器有限公司 Visual tensile testing system
US20220051141A1 (en) * 2020-08-13 2022-02-17 The Boeing Company Material Characterization System and Method
KR20220161061A (en) * 2021-05-28 2022-12-06 현대제철 주식회사 Tensile testing device
CN114518289A (en) * 2022-01-25 2022-05-20 深圳三思纵横科技股份有限公司 Control method for deformation strain control by video acquisition
CN115014228A (en) * 2022-06-21 2022-09-06 深圳市海塞姆科技有限公司 Embedded extensometer based on vision measurement and double-shaft vision measurement method
CN115143895A (en) * 2022-06-21 2022-10-04 深圳市海塞姆科技有限公司 Deformation vision measurement method, device, equipment, medium and double-shaft measurement extensometer
CN116797648A (en) * 2023-06-08 2023-09-22 深圳市海塞姆科技有限公司 Width measuring method, device, equipment, system and medium for material deformation process
CN116839495A (en) * 2023-06-25 2023-10-03 深圳市海塞姆科技有限公司 Deformation vision measurement method based on laser speckle, video extensometer and medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117492161A (en) * 2023-12-29 2024-02-02 深圳市迈腾电子有限公司 Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium
CN117492161B (en) * 2023-12-29 2024-04-12 深圳市迈腾电子有限公司 Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium

Similar Documents

Publication Publication Date Title
WO2021000524A1 (en) Hole protection cap detection method and apparatus, computer device and storage medium
CN108956614B (en) Mining steel wire rope dynamic flaw detection method and device based on machine vision
CN117091953A (en) Automatic measuring method, computer equipment, system and storage medium for sample deformation
KR20190118451A (en) Apparel production monitoring system using image recognition
CN106568783A (en) Hardware part defect detecting system and method
CN110596120A (en) Glass boundary defect detection method, device, terminal and storage medium
CN111539927B (en) Detection method of automobile plastic assembly fastening buckle missing detection device
CN104101600A (en) Method and apparatus for detecting fine cracks on cross section of continuous casting slab
CN110781913B (en) Zipper cloth belt defect detection method
CN111462056B (en) Workpiece surface defect detection method, device, equipment and storage medium
CN113850749A (en) Method for training defect detector
KR101045393B1 (en) Determination method of internal crack and center segregation in steel process
KR102242996B1 (en) Method for atypical defects detect in automobile injection products
CN112927223A (en) Glass curtain wall detection method based on infrared thermal imager
KR20080060851A (en) Defect detecting method of log surface
Xu et al. Fiber-image analysis part I: Fiber-image enhancement
JP6818263B2 (en) Fracture surface analysis device and fracture surface analysis method
CN113450383B (en) Quantitative analysis method, device, equipment and medium of immunochromatographic test paper
CN111948041B (en) Method for determining elastic-plastic transition boundary line of high-speed tensile plate-shaped sample
CN109753858A (en) A kind of road barricade object detecting method and device based on binocular vision
JP4998722B2 (en) Work defect inspection method by image processing
CN114972350B (en) Method, device and equipment for detecting abnormality of mold and storage medium
Nordin et al. Feature Extraction of Mold Defects on Fine Arts Painting using Derivative Oriented Thresholding
CN106767337B (en) Machine vision-based inclination angle reading method for rail inspection trolley verification platform
CN116989691B (en) Visual measurement method and device for material strain, visual strain gauge and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination