Evaluation processing method and system for tensile resistance of arc contact image

Abstract

The invention discloses an evaluation processing method and system for tensile resistance of an arc contact image, and the method comprises the following operation steps: collecting a tensile load image sequence of an arc contact, carrying out the preprocessing of the tensile load image sequence of the arc contact, and obtaining a to-be-detected arc contact image of the image sequence; uniform optical speckles are sprayed on the surface of the arc contact; acquiring the stress and strain field of the tensile load of the arc contact from the to-be-detected arc contact image in the image sequence; the fatigue degree of the to-be-detected arc contact is judged through the stress and strain fields; the tensile resistance of the arc contact to be detected is obtained through the fatigue degree; the stress and strain field comprises a speckle strain field and a stable strain field; and generating an evaluation report of the arc contact based on the tensile resistance of the to-be-detected arc contact.

Description

Technical Field

[0001] The present invention relates to the field of arc contact tensile strength detection, and in particular to an evaluation and processing method and system for the tensile strength of an arc contact image. Background Art

[0002] Arc contacts are key components in electrical equipment and are widely used in power systems, such as circuit breakers, switchgear, etc. The main function of arc contacts is to contact the circuit under high current conditions and bear the load, and to quickly disconnect when an arc is generated to ensure the normal operation of the power system. The performance of arc contacts directly affects the reliability, safety and service life of the equipment, so the evaluation of their tensile strength and fatigue resistance is of great significance for extending the service life of equipment, reducing maintenance costs and avoiding failures.

[0003] Traditionally, the performance evaluation of arc contacts mainly relies on manual inspection and regular mechanical testing methods. However, existing detection methods often have some shortcomings. First, manual inspection cannot provide sufficient accuracy and consistency, and it is difficult to effectively identify small cracks or fatigue damage. Secondly, traditional mechanical testing methods often rely on destructive testing and cannot obtain the deformation process of arc contacts under dynamic loads in real time. Therefore, it is difficult for existing methods to achieve real-time monitoring and prediction of the long-term health status of arc contacts, and it is difficult to detect potential fatigue damage or cracks in advance.

[0004] In recent years, with the development of computer vision technology and image processing technology, non-destructive testing methods based on image analysis have been gradually applied to the detection of arc contacts. These methods use high-speed cameras to capture the deformation process of arc contacts under external forces in real time, and use image processing technology to extract stress and strain fields, thereby analyzing the fatigue of arc contacts. However, in these existing technologies, how to efficiently and accurately obtain the stress and strain fields of arc contacts and evaluate their tensile resistance in combination with fatigue is still a problem that needs to be solved.

[0005] At present, there are still some challenges in the research on the evaluation of arc contact tensile resistance. First, how to accurately infer the fatigue damage degree of arc contact through the strain field in the image sequence, especially the deformation behavior under high-frequency dynamic load, requires high-precision image acquisition and analysis technology. Secondly, how to accurately evaluate the tensile resistance of arc contact and predict its remaining service life based on the stress and strain field analysis results is still a complex engineering problem. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for evaluating and processing the tensile resistance of arc contact images, which solves the above-mentioned technical problems pointed out in the prior art.

[0007] The present invention provides a method for evaluating and processing the tensile resistance of an arc contact image, comprising the following steps:

[0008] Collecting a tensile load image sequence of an arc contact, preprocessing the tensile load image sequence of the arc contact, and obtaining an image sequence of an arc contact to be detected;

[0009] The surface of the arc contact is sprayed with uniform optical speckles;

[0010] Obtaining the stress and strain field of the tensile load of the arc contact from the image of the arc contact to be detected in the image sequence; judging the fatigue degree of the arc contact to be detected by the stress and strain field; and obtaining the tensile resistance of the arc contact to be detected by the fatigue degree;

[0011] The stress and strain field includes a speckle strain field and a stable strain field;

[0012] An evaluation report of the arc contact is generated based on the tensile strength of the arc contact to be tested.

[0013] Preferably, the stress and strain field of the tensile load of the arc contact is obtained from the arc contact image to be detected, and the steps include:

[0014] Pixel points of the same gray value are clustered for each arc contact image to be detected in the image sequence to obtain pixel point clustering clusters; the dispersion of the pixel point clustering clusters is analyzed, and the speckle area and the stable area in the arc contact image to be detected are obtained according to the dispersion of the pixel point clustering clusters; and the displacement field operation is performed on the speckle area and the stable area to obtain the speckle strain field and the stable strain field.

[0015] Preferably, the fatigue degree of the arc contact to be detected is calculated by using the stress and strain field, and the specific operation steps are as follows:

[0016] The strain field deviation value is calculated for the stable strain field and the speckle strain field, and the strain field mutation area of ​​the arc contact image to be detected is extracted by using the strain field deviation value, and the crack contour is extracted through the strain field mutation area; the crack distribution density of the crack contour is calculated, and the damage value of the arc contact image to be detected is calculated through the crack distribution density as the fatigue value of the arc contact of the arc contact image to be detected.

[0017] Preferably, the tensile strength of the arc contact to be tested is obtained through the fatigue degree, and the specific operation steps are as follows:

[0018] Preset an arc contact fatigue threshold e; determine whether the arc contact fatigue of the arc contact image to be detected is greater than the arc contact fatigue threshold e;

[0019] If not, it is determined that the tensile load of the arc contact of the arc contact image to be detected is qualified, and the tensile resistance of the arc contact is determined to be qualified;

[0020] If so, it is determined that the tensile load of the arc contact of the arc contact image to be detected is unqualified, and it is determined that the tensile resistance of the arc contact is unqualified.

[0021] Preferably, a strain field deviation value is calculated for the stable strain field and the speckle strain field, and the strain field mutation region of the arc contact image to be detected is extracted using the strain field deviation value. The specific operation steps are as follows:

[0022] Drawing strain field distribution diagrams for the stable strain field and the speckle strain field respectively to obtain a stable strain field distribution diagram and a speckle strain field distribution diagram;

[0023] Selecting the maximum strain value in the stable strain field distribution map and the maximum strain value in the speckle strain field distribution map respectively; calculating the maximum strain value in the stable strain field distribution map and the maximum strain value in the speckle strain field distribution map to obtain the strain field deviation value;

[0024] Establishing a strain assignment threshold r, and judging whether the strain field deviation value is greater than the strain assignment threshold r;

[0025] If not, it is determined that the arc contact of the arc contact image to be detected does not have a sudden change in strain field;

[0026] If so, the arc contact of the arc contact image to be detected has a sudden change in strain field;

[0027] Calculating a sudden change gradient for the arc contact image to be detected;

[0028] Performing Laplace operator construction of stress and strain fields on the arc contact image to be detected, obtaining local extreme value points of stress and strain fields of the arc contact image to be detected as potential mutation points of stress and strain fields;

[0029] Constructing a Hessian matrix of stress and strain fields according to the second-order partial derivatives, and calculating the eigenvalues ​​of the Hessian matrix;

[0030] The gradient mutation points of the arc contact image to be detected are extracted through the mutation gradient, the potential mutation points and the eigenvalues ​​of the Hessian matrix, and all the gradient mutation points are collected to obtain the strain mutation area.

[0031] Preferably, the crack contour is extracted through the strain field mutation area; the crack distribution density of the crack contour is calculated, and the damage value of the arc contact image to be detected is calculated through the crack distribution density. The specific operation steps are as follows:

[0032] Performing regional growth of gradient mutation points on the strain mutation region using a regional growing algorithm to obtain a crack profile in the strain mutation region;

[0033] Calculating the crack distribution density of the crack contour according to the extension direction of the crack contour; tracking the surface morphology evolution of the image sequence according to the crack distribution density to obtain a damage evolution image sequence; extracting key damage feature parameters according to the damage evolution image sequence to calculate the damage value of the arc contact of the arc contact image to be detected;

[0034] The key damage characteristic parameters include: crack distribution density, crack growth rate and crack morphology changes.

[0035] Preferably, the crack distribution density of the crack profile is calculated by the extension direction of the crack profile; the surface morphology evolution of the image sequence is tracked by the crack distribution density to obtain a damage evolution image sequence, and the specific operation steps are as follows:

[0036] The strain mutation area is divided into grid units evenly, and the number of cracks in the internal crack contour is calculated for each grid unit;

[0037] Calculating crack distribution density according to the number of cracks in each grid unit;

[0038] The crack distribution density of the arc contact image to be detected in the image sequence is tracked by using an image registration algorithm, and the crack position change relationship at different time points in the image sequence is established to obtain a damage evolution image sequence that tracks the evolution of the surface morphology.

[0039] Preferably, the key damage characteristic parameters are extracted through the damage evolution image sequence, and the damage value of the arc contact of the arc contact image to be detected is calculated. The specific operation steps are as follows:

[0040] The total area of ​​the crack contour in the strain mutation region of each frame of the arc contact image to be detected is calculated for the damage evolution image sequence; the crack propagation rate is obtained by calculating the total area of ​​the crack contour between the previous and next frames;

[0041] The crack profile is subjected to crack branch point detection using a skeletonization method, and it is obtained that the crack profile shows branch extension and the crack profile shows crack morphology changes.

[0042] The damage value of the arc contact of the arc contact image to be detected is calculated through the crack distribution density, crack growth rate and crack morphology change.

[0043] Accordingly, the present invention also proposes an evaluation and processing system for the tensile resistance of arc contact images, which is characterized by comprising: a collection module; a processing module; an evaluation module;

[0044] The acquisition module is used to acquire the tensile load image sequence of the arc contact, pre-process the tensile load image sequence of the arc contact, and obtain the arc contact to be detected in the image sequence; the processing module is used to obtain the stress and strain field of the tensile load of the arc contact from the arc contact image to be detected in the image sequence; the fatigue degree of the arc contact to be detected is judged by the stress and strain field; the tensile resistance of the arc contact to be detected is obtained by the fatigue degree; the evaluation module is used to generate an evaluation report of the arc contact based on the tensile resistance of the arc contact to be detected.

[0045] Compared with the prior art, the embodiments of the present invention have at least the following technical advantages:

[0046] By analyzing the above-mentioned arc contact image tensile resistance evaluation processing method and system provided by the present invention, it can be known that in specific applications, spraying uniform optical speckles on the arc contact can analyze the deformation process of the arc contact during the tensile load process, and at the same time, record a high-definition image sequence during the tensile load, and perform a denoising preprocessing operation on the recorded high-definition image sequence to obtain the arc contact image to be detected;

[0047] Furthermore, pixels with the same grayscale value are clustered for each arc contact image to be detected in the image sequence to help identify different areas in the arc contact image to be detected, especially those with consistent grayscale features, such as surface speckles or uniform areas; the Euclidean distance between pixel clustering clusters is calculated to measure the distribution difference of different clustering clusters; the dispersion of pixel clustering clusters is obtained through the Euclidean distance between pixel clustering clusters; if the dispersion between pixel clustering clusters is large, it means that there are large differences in grayscale values ​​or textures in the region, which can reflect the stretchability of the arc contact during tensile load; the grayscale mean of each pixel clustering cluster is calculated for the speckle area and the stable area in each arc contact image to be detected in the image sequence; the grayscale distribution of the speckle area is relatively messy, and the area with a higher grayscale mean of the pixel clustering cluster may correspond to a more prominent speckle feature; the pixel clustering cluster with the highest grayscale mean in the stable area is selected as the stable area. Determine the feature points; use the optical flow method to move the image sequence of the stable feature points in the stable area of ​​each arc contact image to be detected, so as to obtain an accurate motion estimation and a stable displacement field of the stable feature points, which reflects the real deformation of the object; the stable displacement field directly reflects the motion state of the arc contact, and the strain field can further reveal the strain distribution of the material, so the stable displacement field is mapped to the strain field to obtain a stable strain field of the stress and strain field; use the fast matching image registration method to divide the speckle area in the arc contact image to be detected into a plurality of small blocks, and obtain the speckle displacement field through the image sequence of the plurality of small blocks. By dividing the speckle area into small blocks, the motion of the speckle area can be analyzed more carefully, so as to more accurately estimate the displacement of the speckle area; the speckle displacement field can also be mapped to obtain the strain field, revealing the stress and strain distribution on the surface of the arc contact, and helping to analyze the local overload or abnormal deformation that may occur in the arc contact during operation;

[0048] Furthermore, the strain field distribution diagrams are drawn for the stable strain field and the speckle strain field, respectively, to obtain the stable strain field distribution diagram and the speckle strain field distribution diagram; the strain field deviation value is obtained by selecting the maximum strain value in the stable strain field distribution diagram and the maximum strain value in the speckle strain field distribution diagram for calculation; if the deviation between the maximum strain value of the speckle strain field and the maximum strain value of the stable strain field is too large, it means that the strain change in the area is abnormal; the mutation gradient is calculated for the arc contact image to be detected, and the Laplace operator and the Hessian matrix are used to double extract the mutation points of the stress and strain fields for the arc contact image to be detected, the gradient mutation points are calculated by the mutation gradient and mutation points, the mutation area is reflected by the gradient mutation points, and the strain mutation area is obtained; the regional growth algorithm is used to perform regional growth of the gradient mutation points in the strain mutation area to obtain the crack contour in the strain mutation area, which can identify the crack contour that may appear in the arc contact during the tensile load process;

[0049] Furthermore, the number of cracks in the crack contour is queried through the crack contour, and the crack distribution density is calculated based on the number of cracks, which helps to understand the specific distribution of cracks inside the material, thereby reflecting the tensile resistance of the arc contact; all arc contact images to be detected are tracked and evolved according to the crack distribution density to obtain a damage evolution image sequence, which can indicate the distribution and morphology of cracks on the surface of the arc contact material in each frame of the arc contact image to be detected; the crack expansion rate can be calculated through the total area of ​​the crack contour of each frame of the arc contact image to be detected, and the speed of crack diffusion in each frame of the arc contact image to be detected can be understood; the crack contour is then detected by a skeletonization method to detect crack branch points, and it is determined whether the morphological changes of the cracks are diffused, reflecting the tensile strength of the arc contact; the damage value of the arc contact of the arc contact image to be detected is calculated through the crack distribution density, the crack expansion rate and the crack morphological changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a main flow chart of a method for evaluating and processing the tensile resistance of an arc contact image according to a first embodiment of the present invention;

[0051] Figure 2 A flowchart of a method for evaluating the tensile strength of an arc contact image in accordance with a first embodiment of the present invention for identifying the tensile strength of an arc contact in an arc contact image to be detected;

[0052] Figure 3 A flow chart of calculating the damage value of an arc contact in an arc contact image to be detected in a method for evaluating the tensile strength of an arc contact image according to a first embodiment of the present invention;

[0053] Figure 4 A flowchart of a method for evaluating the tensile strength of an arc contact image according to a first embodiment of the present invention, for calculating a damage value based on key damage characteristic parameters;

[0054] Figure 5 This is a flow chart of a system for evaluating and processing the tensile resistance of an arc contact image according to a second embodiment of the present invention;

[0055] Label: acquisition module 10; processing module 20; evaluation module 30. DETAILED DESCRIPTION

[0056] The present invention is further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0057] Embodiment 1

[0058] like Figure 1 As shown, the present invention provides a method for evaluating and processing the tensile resistance of an arc contact image, comprising the following steps:

[0059] S1: collecting a tensile load image sequence of an arc contact, preprocessing the tensile load image sequence of the arc contact, and obtaining an image sequence of an arc contact to be detected;

[0060] The surface of the arc contact is sprayed with uniform optical speckles;

[0061] It should be noted that, first, before collecting the tensile load image of the arc contact, a layer of optical speckle is evenly sprayed on the surface of the arc contact for subsequent image analysis to obtain deformation information of the arc contact; the speckle pattern should be detailed and cover the key area of ​​the entire arc contact; a high-speed camera is used to capture the deformation process of the arc contact under the tensile load in real time, and the tensile load image of the arc contact taken by the high-speed camera will be used for subsequent strain field analysis (that is, the high-speed camera is used to capture the deformation process of the arc contact in the process of stretching or bearing force in real time, and can record high-frequency changes to help analyze the behavioral characteristics of the arc contact under dynamic load);

[0062] At the same time, a pre-processing operation of denoising is performed on the tensile load image of the arc contact to obtain an image of the arc contact to be detected;

[0063] S2: obtaining the stress and strain field of the tensile load of the arc contact from the image of the arc contact to be detected in the image sequence; judging the fatigue degree of the arc contact to be detected by the stress and strain field; and obtaining the tensile resistance of the arc contact to be detected by the fatigue degree;

[0064] The stress and strain field includes a speckle strain field and a stable strain field;

[0065] It should be noted that the stress field describes the stress distribution at each point of an object under the action of external forces; the stress and strain fields describe the deformation of an object due to stress, and these fields can reveal fatigue cracks or other damaged areas that may exist on the surface of the arc contact; by analyzing the abnormal areas or local high strain areas in the stress and strain fields, the fatigue damage of the material can be inferred; these high strain areas are often related to cracks, etc., and can be used as a basis for judging fatigue;

[0066] At the same time, stress and strain fields include speckle strain fields and stable strain fields; stable strain fields refer to the situation in which the strain distribution inside or on the surface of an object tends to no longer change after the external force or strain reaches a certain stable state during the deformation of the object; in other words, stable strain fields describe the situation in which the strain field of an object no longer changes with time or load after the deformation reaches a certain stage, and exhibits a stable strain state; speckle strain fields refer to a method of measuring the strain distribution of an object by analyzing the changes in the speckle pattern on the surface of the object; speckle pattern is a small, randomly distributed spot pattern formed by the interference effect of light, usually formed by coating tiny particles on the surface of the object or using some technology; by capturing the speckle pattern on the surface of the object before and after loading with a high-resolution camera and performing image processing (such as digital image correlation, DIC), the local strain distribution on the surface of the object during the deformation process can be obtained;

[0067] Under high fatigue conditions, the arcing contact’s resistance to stretching may be reduced, meaning it may not be able to withstand greater loads or even break;

[0068] Based on the fatigue degree obtained from the stress and strain field analysis, the tensile strength of the arc contact can be further calculated; this provides an important basis for the subsequent issuance of an evaluation report;

[0069] S3: generating an evaluation report of the arc contact based on the tensile strength of the arc contact to be tested;

[0070] It should be noted that the report usually includes the fatigue, tensile strength, possible cracks or damaged areas of the arc contact, and the remaining service life of the arc contact is evaluated based on the fatigue of the arc contact, reflecting the health status assessment of the arc contact;

[0071] Specifically, Figure 2 As shown, in step S2, the stress and strain field of the tensile load of the arc contact is obtained from the arc contact image to be detected, and the steps include:

[0072] Clustering pixels of the same gray value is performed on each arc contact image to be detected in the image sequence to obtain pixel clustering clusters; analyzing the dispersion of the pixel clustering clusters, and obtaining the speckle area and the stable area in the arc contact image to be detected according to the dispersion of the pixel clustering clusters; performing displacement field operation on the speckle area and the stable area to obtain the speckle strain field and the stable strain field. The specific operation steps are as follows:

[0073] S21: clustering pixels with the same grayscale value for each arc contact image to be detected in the image sequence to obtain pixel clusters;

[0074] Calculating the Euclidean distance between the pixel point clusters, and obtaining the dispersion of the pixel point clusters through the Euclidean distance between the pixel point clusters;

[0075] Preset a distribution threshold t of the pixel clustering cluster; determine whether the dispersion of the pixel clustering cluster is greater than the distribution threshold t of the pixel clustering cluster;

[0076] If not, it is determined that the pixel clusters are unevenly dispersed, and the unevenly dispersed pixel clusters are regarded as speckle areas;

[0077] If so, it is determined that the pixel clusters are evenly dispersed and the evenly dispersed pixel clusters are regarded as stable areas;

[0078] It should be noted that the pixels in the image are clustered according to their grayscale values ​​to form pixel clusters; the purpose of clustering is to group pixels with similar grayscale values ​​or similar features in the image together; this can help identify different areas in the image, especially those with consistent grayscale features, such as surface speckles or uniform areas;

[0079] Calculate the Euclidean distance between pixel clusters. The Euclidean distance can measure the distribution differences between different clusters. The smaller the distance, the closer the positions between clusters are, and the grayscale value or texture of the image area is more uniform. The larger the distance, the greater the difference between clusters, and the more significant the texture change of the image area, which reflects the degree of dispersion of pixel clusters.

[0080] Based on the Euclidean distance between pixel clusters, the dispersion (i.e., the degree of dispersion of pixel clusters) is calculated; the dispersion reflects the distribution between pixel clusters; if the dispersion between pixel clusters is large, it means that there are large differences in grayscale values ​​or textures in the region, and it can also reflect that during the tensile load process of the arc contact, the arc contact under tension will be affected by the dispersion of pixels, so the dispersion between the pixel clusters of the arc contact under tension load is large; if the dispersion is small, it means that the grayscale value or texture in the region is relatively uniform, that is, the pixel clusters of the part that does not bear the tensile load or the part of the arc contact under tension load have not undergone significant deformation, reflecting that the arc contact has good stretchability during the tensile load process; for example, in material detection, the speckle area may be related to surface defects or local deformation, while the stable area represents the normal area of ​​the material;

[0081] Through the preset pixel point clustering distribution threshold t, it is screened out which pixel point clustering clusters in the arc contact image to be detected have a large dispersion in the area where the clustering clusters are gathered, forming a speckle area (that is, the speckle area represents the deformation area that may appear after the arc contact is subjected to the tensile load); which pixel point clustering clusters have a small dispersion in the area where the clustering clusters are gathered, forming a stable area (that is, the stable area represents the area that has not been subjected to the tensile load but has not undergone the deformation change after the stretching).

[0082] S22: calculating the grayscale mean of each pixel cluster in the speckle area and the stable area in each arc contact image to be detected in the image sequence;

[0083] Select the pixel cluster with the highest grayscale mean and the largest number in the speckle area (for example, there are 10 pixel clusters in the speckle area, of which the pixel cluster with the highest grayscale mean is 200, and there are 2 of them; then the second highest pixel cluster is 180 grayscale mean, and there are 5 of them. At this time, the second highest 180 grayscale mean of the pixel cluster is selected as the speckle feature point; first sort the pixel clusters in the speckle area according to the grayscale mean, and select the pixel cluster with the highest grayscale mean and the largest number as the speckle feature point, which can reflect the tensile deformation changes in different places in the speckle area, so as to better reflect the stretchability of the arc contact) as the speckle feature point;

[0084] Select the pixel cluster with the highest grayscale mean in the stable area as the stable feature point;

[0085] It should be noted that in the speckle area, selecting the cluster with the highest grayscale mean means finding the part with the most significant grayscale value in the area; usually, the grayscale distribution in the speckle area is relatively messy, and selecting an area with a higher grayscale mean may correspond to a more prominent speckle feature, which helps to extract key change information in subsequent image processing and analysis. Speckle feature points may represent noise, deformation or local reflection points in the image, and are the key to subsequent processing and change analysis;

[0086] In the stable area, selecting the cluster with the highest grayscale mean means selecting the most representative and consistent part of the area; the stable area usually reflects some areas in the image that are not affected by changes. The grayscale values ​​of these areas are usually relatively stable. By selecting the area with the highest grayscale mean, the unchanged or most iconic part of the image can be effectively obtained; stable feature points are helpful for subsequent tracking and matching, because these points can be used as reference benchmarks to help determine the deformation or position change of objects in the image sequence;

[0087] S23: using the optical flow method to move the stable feature points of the stable area in each arc contact image to be detected in an image sequence, and obtain a stable displacement field (i.e., a motion vector) of the stable feature points. A stable displacement field refers to a situation in which the displacement distribution on the surface or inside the material remains stable, uniform, or does not change significantly in a certain direction during the deformation of the object under force; in short, it means that the displacement distribution of the object tends to be stable over time, and the displacement field is not affected by additional disturbances or changes);

[0088] Mapping the stable displacement field to a strain field to obtain a stable strain field of stress and strain fields;

[0089] It should be noted that the optical flow method is a method for estimating the displacement of an object or surface in an image by analyzing the movement of pixels in an image sequence. In this step, the optical flow method is used to track stable feature points in the arc contact image (these feature points usually remain stable in the image sequence) and calculate the displacement field (motion vector) of the stable area; these stable feature points appear as parts with small displacement or no interference in the image sequence, usually reflecting areas where the surface of the object is relatively smooth or has no significant changes;

[0090] By using the optical flow method to analyze the displacement of stable feature points in the stable area, accurate motion estimation can be obtained, especially in areas where there is no significant deformation or noise interference on the arc contact surface; at this time, the stable feature point motion reflects the real deformation of the object, so they can be used to infer the strain and stress changes on the arc contact surface;

[0091] The obtained stable displacement field is mapped into a strain field; the displacement field describes the movement of each stable feature point in the arc contact image to be detected, while the strain field describes the deformation of the object at different positions, which is usually calculated by the change of the displacement field; the deformation of each point on the surface of the arc contact is obtained through the stable displacement field (motion vector), which is the basis of stress-strain analysis.

[0092] The stable displacement field directly reflects the motion state of the arc contact, while the strain field can further reveal the strain distribution of the material; the purpose of this mapping is to obtain the physical deformation during the operation of the arc contact, to help understand and predict the performance of the arc contact under actual working conditions;

[0093] S24: dividing the speckle area in the arc contact image to be detected into a plurality of small blocks by using a fast matching image registration method;

[0094] Taking the speckle feature point as the center, randomly selecting a small block around the speckle feature point as a position block; traversing the speckle areas in all arc contact images to be detected in the image sequence to filter out the position blocks;

[0095] Through the grayscale mean square error of all position blocks, the two position blocks with the highest similarity are selected;

[0096] Calculating the offset of the speckle feature points of the speckle area in the arc contact image to be detected of the two position blocks, and obtaining the displacement vector of the speckle feature point as the speckle displacement field of the speckle feature point (i.e., the speckle displacement field refers to the use of surface speckle patterns (patterns composed of tiny, randomly distributed points or spots) to track the displacement of the surface of an object during deformation. The speckle pattern is usually formed by spraying optical speckles (such as fine particles) on the surface of the object. The speckle pattern of the surface of the object before and after loading is photographed by a high-speed camera, and the changes in the pattern are compared by image processing technology, and then the displacement of each point on the surface is calculated);

[0097] Mapping the speckle displacement field to a strain field to obtain a speckle strain field of stress and strain fields;

[0098] It should be noted that, in the arc contact image to be detected, the speckle area is divided into multiple small blocks, and the small blocks are selected for matching according to the positions of the speckle feature points; the block matching method is usually used for image registration, and the matching points in the speckle area are found by comparing the similarity of each position block (such as grayscale mean square error);

[0099] The speckle area contains local texture information of the arc contact image to be detected, and these textures can provide information for accurate registration and displacement estimation. By dividing the speckle area into small blocks, the movement of the speckle area can be analyzed more carefully, so that the displacement of the speckle area can be estimated more accurately. This method is particularly suitable for processing high-resolution image data.

[0100] By calculating the mean square error of grayscale between different position blocks, the position block with the highest similarity is selected, and the displacement is estimated by calculating the offset between the two position blocks. This is a matching method based on similarity calculation, which can help accurately find the motion trajectory of the speckle feature points.

[0101] The speckle feature points are usually represented by similar grayscale patterns in the speckle areas in different arc contact images to be detected; using grayscale mean square error as the matching criterion helps to reduce the interference of factors such as illumination changes and noise, and ensure the consistency and accuracy of the selected matching blocks in different images;

[0102] By calculating the offset of the two selected position blocks, the displacement vector of the speckle feature point is obtained; the speckle displacement field is the set of displacement vectors of these speckle feature points, which represents the displacement of the speckle area in the image sequence.

[0103] The speckle feature points are important local feature points in the image of the arc contact to be detected. Their movement can reflect the displacement of a certain part of the image of the arc contact to be detected. By calculating the displacement vectors of these speckle feature points, more detailed motion information can be obtained, and then the strain field on the surface of the object can be derived. This process is crucial for accurately describing the movement and deformation of the arc contact. Similar to the stable displacement field in step S23, the speckle displacement field can also be mapped to obtain the strain field, revealing the stress and strain distribution on the surface of the arc contact.

[0104] The speckle area is the local texture point in the image of the arc contact to be detected. Their displacement changes can provide more detailed information, especially in the local area of ​​the arc contact. Mapping the speckle displacement field into a strain field helps to reveal the local deformation and help analyze the local overload or abnormal deformation that may occur in the arc contact during operation.

[0105] In step S2, the step of "calculating fatigue of the arc contact to be detected by using the stress and strain field; and obtaining tensile strength of the arc contact to be detected by using the fatigue" is specifically performed as follows:

[0106] S25: calculating a strain field deviation value for the stable strain field and the speckle strain field, extracting a strain field mutation region of the arc contact image to be detected by using the strain field deviation value, and extracting a crack profile through the strain field mutation region; calculating a crack distribution density of the crack profile, and calculating a damage value of the arc contact image to be detected through the crack distribution density as a fatigue degree of the arc contact of the arc contact image to be detected;

[0107] It should be noted that the strain field describes the strain changes on the surface of an object under the action of external forces; the stable strain field usually refers to the relatively uniform strain distribution on the surface of an object under the action of load; and the speckle strain field refers to the area of ​​sudden strain changes caused by local damage, cracks or other defects.

[0108] By calculating the deviation between the stable strain field and the speckle strain field, the local strain abnormal area on the surface can be found, that is, the area where the strain field changes suddenly, which is usually the manifestation of cracks or fatigue damage;

[0109] Since cracks usually cause significant changes in the strain field, extracting the crack contour from the mutation area can help identify the damage location and morphology on the material surface;

[0110] The calculation of crack distribution density helps to quantify the degree of material damage. Dense crack distribution usually means that the fatigue damage of the material is more serious, which may affect its performance and life.

[0111] The damage value calculated based on the crack distribution density of the crack profile is used as the fatigue degree, which reflects the damage level of the arc contact; the higher the fatigue degree, the more serious the fatigue damage experienced by the material, which may lead to earlier failure;

[0112] S26: Preset an arc contact fatigue threshold e; determine whether the arc contact fatigue of the arc contact image to be detected is greater than the arc contact fatigue threshold e;

[0113] If not, it is determined that the tensile load of the arc contact of the arc contact image to be detected is qualified, and the tensile resistance of the arc contact is determined to be qualified;

[0114] If yes, it is determined that the tensile load of the arc contact of the arc contact image to be detected is unqualified, and the tensile resistance of the arc contact is unqualified;

[0115] It should be noted that the preset fatigue threshold ee, i.e. a critical fatigue value, is used to determine whether the arc contact meets the tensile resistance requirements. This threshold represents the maximum fatigue damage that the material can withstand. When the fatigue exceeds this threshold, it means that the fatigue damage of the arc contact is too large;

[0116] If the fatigue degree of the arc contact to be tested is lower than the threshold, it is determined that the arc contact has qualified tensile resistance, that is, it is considered that the arc contact can safely withstand the tensile load and will not fail; if the fatigue degree is higher than the threshold, it means that the arc contact has excessive fatigue damage, unqualified tensile resistance, and has a high risk of failure;

[0117] Specifically, Figure 3 As shown, in step S25, the strain field deviation value is calculated for the stable strain field and the speckle strain field, the strain field mutation region of the arc contact image to be detected is extracted by using the strain field deviation value, and the crack contour is extracted through the strain field mutation region; the crack distribution density of the crack contour is calculated, and the damage value of the arc contact image to be detected is calculated through the crack distribution density. The specific operation steps are as follows:

[0118] S251: drawing strain field distribution maps for the stable strain field and the speckle strain field respectively, to obtain a stable strain field distribution map and a speckle strain field distribution map;

[0119] Selecting the maximum strain value in the stable strain field distribution map and the maximum strain value in the speckle strain field distribution map respectively; calculating the maximum strain value in the stable strain field distribution map and the maximum strain value in the speckle strain field distribution map to obtain the strain field deviation value;

[0120] Establishing a strain assignment threshold r, and judging whether the strain field deviation value is greater than the strain assignment threshold r;

[0121] If not, it is determined that the arc contact of the arc contact image to be detected does not have a sudden change in strain field;

[0122] If so, the arc contact of the arc contact image to be detected has a sudden change in strain field;

[0123] It should be noted that the stable strain field refers to the strain distribution diagram of the arc contact under normal working conditions without external disturbances or material defects, which indicates the deformation of the material or structure under ideal conditions; the speckle strain field is usually a strain field obtained by optical or other sensor technologies, which may cause local fluctuations in strain due to experimental errors, noise, surface speckles and other factors;

[0124] Comparing the two can reveal the difference between the noise caused by speckle and the normal strain field. In particular, if the strain value of the speckle strain field in some areas is much larger than the strain value of the stable strain field, it may indicate that a sudden strain change has occurred in the area, that is, the material or structure may be abnormally deformed or damaged in the area.

[0125] The deviation value reflects the difference between the speckle strain field and the stable strain field. If the deviation between the maximum strain value of the speckle strain field and the maximum strain value of the stable strain field is too large, it means that the strain change in the area is abnormal, which may be a mutation caused by external factors; set a threshold r to determine whether the strain field deviation is greater than the threshold; the purpose of this is to avoid false mutation results caused by small measurement errors or noise; if the deviation value exceeds the threshold r, it is considered that a strain field mutation has occurred in the area, indicating possible damage, stress concentration or structural problems;

[0126] S252: calculating a sudden change gradient for the arc contact image to be detected;

[0127] Performing Laplace operator construction of stress and strain fields on the arc contact image to be detected, obtaining local extreme value points of stress and strain fields of the arc contact image to be detected as potential mutation points of stress and strain fields;

[0128] Constructing a Hessian matrix of stress and strain fields according to the second-order partial derivatives, and calculating the eigenvalues ​​of the Hessian matrix (i.e., the eigenvalues ​​of the Hessian matrix can reveal mutation points, which are usually located in the local extreme value region of the strain field and may indicate local instability of the material or crack initiation points);

[0129] The gradient mutation points of the arc contact image to be detected are extracted through the mutation gradient, the potential mutation points and the eigenvalues ​​of the Hessian matrix, and all the gradient mutation points are collected to obtain the strain mutation area (that is, the gradient mutation point set refers to those points with large gradient changes (that is, mutation gradients), significant Laplace operator values, or Hessian matrix eigenvalues ​​indicating abnormal changes, which are potential strain mutation areas);

[0130] It should be noted that the mutation gradient represents the rate of local change in the strain field. Generally, a region with a large mutation gradient means that the strain or stress at that location has changed dramatically, which may be a precursor to material crack propagation or other abnormal phenomena; therefore, calculating the mutation gradient can help identify these potential strain mutation regions;

[0131] In the strain field, the Laplace operator can highlight the local extreme points, that is, the points where the strain changes most dramatically; the mutation area is usually located at the local extreme value of the strain, which may correspond to local instability of the material, crack initiation or other structural problems; the local extreme points obtained by the Laplace operator can be used as potential mutation points of the stress and strain fields, further improving the recognition accuracy of the mutation area;

[0132] The Hessian matrix is ​​a matrix composed of second-order partial derivatives, which is used to describe the local curvature of a function (such as a strain field) at a certain point. The eigenvalues ​​of the Hessian matrix can reveal the direction and intensity of changes in the strain field. If there are abnormal values ​​in the eigenvalues ​​of the Hessian matrix, it means that there are large changes in the strain or stress field in the area. These areas usually correspond to local extreme points or stress concentration points, which may lead to crack expansion or other instability phenomena.

[0133] Combining the mutation gradient, local extreme points and the eigenvalues ​​of the Hessian matrix, the gradient mutation points in the strain field can be accurately identified; these gradient mutation points are the signs of the mutation area, and the drastic changes in strain that usually occur at these locations are caused by local stress concentration, material defects or other structural anomalies;

[0134] The strain mutation area is composed of these gradient mutation points and is a potential risk area. By extracting these areas, the abnormal areas (i.e., crack contours) that may exist in the arc contact can be identified in advance.

[0135] S253: performing regional growth of gradient mutation points on the strain mutation region using a region growing algorithm to obtain a crack profile in the strain mutation region;

[0136] It should be noted that the region growing algorithm is common knowledge. One of the gradient mutation points is selected as a seed point for neighborhood growth, and finally the crack contour is obtained. It will not be described in detail here. Cracks may appear in the arc contact during the tensile load process. Therefore, the crack contour is obtained by performing region growth through the abnormal gradient protruding points, and the crack distribution density is further calculated through the crack contour.

[0137] S254: calculating the crack distribution density of the crack contour according to the extension direction of the crack contour; tracking the surface morphology evolution of the image sequence according to the crack distribution density to obtain a damage evolution image sequence; extracting key damage feature parameters according to the damage evolution image sequence, and calculating the damage value of the arc contact of the arc contact image to be detected;

[0138] The key damage characteristic parameters include: crack distribution density and crack growth rate and crack morphology change;

[0139] It should be noted that the crack profile is obtained through the regional growth algorithm, and the crack distribution density is calculated according to the extension direction, distribution and number of the crack profile. The crack density distribution can reflect the severity of fatigue damage on the material surface; the denser the crack distribution, the more serious the fatigue damage may be;

[0140] With the continuous evolution of the time series images (i.e., image sequences), the crack distribution will become more and more dense, the morphology of the arc contact surface will change, and larger cracks, fatigue pits or other damage forms may gradually appear on the surface; by comparing and analyzing a series of time series images, tracking the evolution of the surface morphology, it is possible to understand the damage evolution of the material under different fatigue cycles; through the image data of the time series, a series of images of the evolution process of the arc contact surface damage are established; each image represents the damage state of the arc contact surface at a certain point in time or under fatigue cycles, so as to calculate the damage value;

[0141] Specifically, Figure 4 As shown, in step S254, the crack distribution density of the crack contour is calculated according to the extension direction of the crack contour; the surface morphology evolution of the image sequence is tracked by the crack distribution density to obtain a damage evolution image sequence, and the specific operation steps are as follows:

[0142] S2541: Evenly divide the strain mutation area into grid units, and calculate the number of cracks in the internal crack contour of each grid unit;

[0143] Calculating crack distribution density according to the number of cracks in each grid unit;

[0144] It should be noted that the strain mutation area is divided into multiple small grid units, each grid unit is a calculation area, which is used to analyze the crack characteristics in the area; the number of cracks in the crack profile in the grid unit is calculated; by calculating the number of cracks in each grid unit, the crack density in the area can be quantified; this helps to understand the specific distribution of cracks inside the material; in the strain mutation area, the cracks may have a higher density, affecting the mechanical properties of the material; therefore, accurately calculating the number of cracks helps to assess the degree of damage in the area;

[0145] S2542: using an image registration algorithm to track the crack distribution density of the arc contact image to be detected in the image sequence, establishing a crack position change relationship at different time points in the image sequence, and obtaining a damage evolution image sequence that tracks the evolution of the surface morphology;

[0146] It should be noted that the image registration algorithm (such as feature-based registration, phase correlation method, etc.) is used to align the arc contact images to be detected at different time points (that is, the image sequence is a time series image, so there are arc contact images to be detected at different time points) to achieve crack tracking; in this way, the relationship between the crack position changes between different time points can be established, and then the dynamic process of crack propagation can be analyzed; through the analysis of crack distribution density and the tracking of crack propagation trajectory, a damage evolution image sequence can be obtained; each frame of the arc contact image to be detected shows the distribution and morphology of cracks on the surface of the arc contact material at a specific time or under specific loading conditions;

[0147] In step S254, the step of "extracting key damage characteristic parameters through the damage evolution image sequence and calculating the damage value of the arc contact of the arc contact image to be detected" is also performed as follows:

[0148] S2543: calculating the total area of ​​the crack contour in the strain mutation region of each frame of the arc contact image to be detected for the damage evolution image sequence (that is, the calculation of the total area of ​​the crack contour is common knowledge and will not be described in detail);

[0149] The time interval is set to Δt, and the total area of ​​the crack contour between the two frames is calculated to obtain the crack growth rate. The calculation formula is:

[0150]

[0151] In the formula, v crack The crack growth rate expressed as the crack distribution density in the damage evolution image sequence;

[0152] A 1 It is expressed as the total area of ​​the crack contour in the previous frame in the damage evolution image sequence (i.e., the total area of ​​the crack contour at time t);

[0153] A 2 It is expressed as the total area of ​​the crack contour in the next frame in the damage evolution image sequence (i.e., the total area of ​​the crack contour at time t-1);

[0154] It should be noted that the crack growth rate is obtained through this formula, which describes the crack growth speed in time; if the growth rate is high, it means that the crack grows faster in this time period; if it is low, the crack grows slower; at the same time, it can also reflect that the damage to the arc contact under the tensile load state is gradually increasing, so the crack growth rate can also briefly indicate the continuous tensile resistance time of the arc contact, thereby reflecting the tensile resistance of the arc contact;

[0155] S2544: Detect crack branch points on the crack contour using a skeletonization method, and determine whether crack contours in different time frames have branches.

[0156] If not, it is determined that the crack profile does not branch and expand (i.e., judging by the crack profiles of different time frames, if the crack profile does not branch and expand, it means that the crack profile changes with time, and the crack may not have changed seriously, and the arc contact has good tensile properties);

[0157] If yes, it is determined that the crack profile has branched and expanded, and the crack profile has crack morphology changes;

[0158] It should be noted that after applying the skeletonization method on the crack contour, the topological structure of the crack can be more easily detected, such as whether there are complex changes such as branches and mergers; skeletonization is an image processing technology that converts the crack contour in the image into a slender "skeleton" shape, thereby simplifying the crack structure; in the crack skeleton image, the branch point is the place where the crack divides from a main trunk into multiple branches; these branch points can be identified by analyzing the topological structure of the crack skeleton;

[0159] Compare the crack skeletons in different time frames to determine whether the crack has branched and expanded. If the crack skeleton splits from a main crack into multiple branches in the two frames before and after, it can be determined that the crack has branched and expanded;

[0160] If crack branching occurs: it means that the crack morphology has changed and the extension is more complicated, which usually means that the crack development has entered a new stage and may cause more serious damage; in this case, the crack morphology has undergone a "morphological change";

[0161] S2545: Calculate the damage value of the arc contact of the arc contact image to be detected by the crack distribution density, crack extension rate and crack morphology change, and the calculation formula is:

[0162]

[0163] Where ρ(xy) represents the crack distribution density in each grid unit at present;

[0164] exp(-μt) is expressed as the time diffusion factor (i.e., describing the time dependence of the crack growth rate, which means that as time changes, the crack growth rate in the damage evolution image sequence will become faster and faster, and the crack speed will also become faster and faster);

[0165] α is the weight coefficient of crack distribution density (i.e., used to adjust the contribution of density term);

[0166] dA micro-element area (i.e., integration over the entire strain mutation region. Micro-element area is the basic unit for integral calculation and is used to refine the local manifestation of crack extension. By summing at the micro-element scale, the crack extension of the entire region can be obtained);

[0167] v crack Expressed as crack growth rate;

[0168] cos 2 θ is expressed as the crack directionality factor (i.e., θ is the angle between the crack extension direction and the principal stress direction);

[0169] k(s) is expressed as a curvature function (i.e., it describes the curvature of the crack path and refers to the complexity of the crack branching direction);

[0170] β represents the weight coefficient of crack growth rate;

[0171] i represents one of the branch directions of the crack;

[0172] M(s) is expressed as the crack morphology factor (i.e., the crack shape characteristics of crack morphology changes);

[0173] ψ(s) is expressed as the crack morphology function (i.e., as the characteristic of the crack profile);

[0174] γ represents the weight coefficient of crack morphology factor;

[0175] ds is the line integral differential element along the crack boundary (i.e., a crack is usually a continuous boundary, and integration along the boundary can obtain various parameters on the crack boundary (such as crack growth rate, curvature, etc.); by performing line integration along the crack boundary, the crack growth and its impact on the material can be accurately calculated);

[0176] It should be noted that in the above formula, the formula actually transforms the incremental accumulation process into a "state description"; the influence of the time history is implied by the exp(-μt) term; at the same time, each integral essentially contains the cumulative effect of damage evolution; and the current damage degree (that is, ρ(xy) is expressed as the crack distribution density in each grid unit) is expressed by v crackCharacterizing the damage development trend and the complexity of damage embodied by κ(s) and ψ(s) reflects the total damage value of the arc contact, avoiding the complexity of step-by-step cumulative calculation (i.e., calculating the incremental damage value of the arc contact, the incremental damage value is expressed as first calculating the damage values ​​of two adjacent frames of arc contact images to be detected, and obtaining the total damage value of the arc contact through the damage value of each frame, but this calculation method avoids cumulative calculation through parameters such as factors in the above formula), reducing the accumulation of calculation errors and improving calculation efficiency;

[0177] The crack distribution density, crack growth rate, crack morphology changes and their respective factors (such as directionality, curvature, morphology, etc.) have different effects on crack growth; the damage value of the arc contact is calculated by weighting and adjusting the contribution of these factors;

[0178] Embodiment 2

[0179] like Figure 5 As shown, the present invention also provides an evaluation and processing system for the tensile resistance of arc contact images, comprising: an acquisition module 10; a processing module 20; an evaluation module 30;

[0180] The acquisition module 10 is used to acquire a tensile load image sequence of the arc contact, pre-process the tensile load image sequence of the arc contact, and obtain an image sequence of the arc contact to be detected;

[0181] The processing module 20 is used to obtain the stress and strain field of the tensile load of the arc contact from the arc contact image to be detected in the image sequence; judge the fatigue degree of the arc contact to be detected through the stress and strain field; and obtain the tensile resistance of the arc contact to be detected through the fatigue degree;

[0182] The evaluation module 30 is used to generate an evaluation report of the arc contact based on the tensile strength of the arc contact to be tested.

[0183] In summary, the present invention proposes a method and system for evaluating the tensile resistance of arc contact images, which sprays uniform optical speckles on the arc contact to analyze the deformation process of the arc contact during tensile load, and simultaneously records a high-definition image sequence during tensile load, performs a denoising preprocessing operation on the recorded high-definition image sequence, and obtains the arc contact image to be detected;

[0184] Furthermore, pixels with the same grayscale value are clustered for each arc contact image to be detected in the image sequence to help identify different areas in the arc contact image to be detected, especially those with consistent grayscale features, such as surface speckles or uniform areas; the Euclidean distance between pixel clustering clusters is calculated to measure the distribution difference of different clustering clusters; the dispersion of pixel clustering clusters is obtained through the Euclidean distance between pixel clustering clusters; if the dispersion between pixel clustering clusters is large, it means that there are large differences in grayscale values ​​or textures in the region, which can reflect the stretchability of the arc contact during tensile load; the grayscale mean of each pixel clustering cluster is calculated for the speckle area and the stable area in each arc contact image to be detected in the image sequence; the grayscale distribution of the speckle area is relatively messy, and the area with a higher grayscale mean of the pixel clustering cluster may correspond to a more prominent speckle feature; the pixel clustering cluster with the highest grayscale mean in the stable area is selected as the stable area. Determine the feature points; use the optical flow method to move the image sequence of the stable feature points in the stable area of ​​each arc contact image to be detected, so as to obtain an accurate motion estimation and a stable displacement field of the stable feature points, which reflects the real deformation of the object; the stable displacement field directly reflects the motion state of the arc contact, and the strain field can further reveal the strain distribution of the material, so the stable displacement field is mapped to the strain field to obtain a stable strain field of the stress and strain field; use the fast matching image registration method to divide the speckle area in the arc contact image to be detected into a plurality of small blocks, and obtain the speckle displacement field through the image sequence of the plurality of small blocks. By dividing the speckle area into small blocks, the motion of the speckle area can be analyzed more carefully, so as to more accurately estimate the displacement of the speckle area; the speckle displacement field can also be mapped to obtain the strain field, revealing the stress and strain distribution on the surface of the arc contact, and helping to analyze the local overload or abnormal deformation that may occur in the arc contact during operation;

[0185] Furthermore, the strain field distribution diagrams are drawn for the stable strain field and the speckle strain field, respectively, to obtain the stable strain field distribution diagram and the speckle strain field distribution diagram; the mutation gradient is calculated for the arc contact image to be detected, and the Laplace operator and the Hessian matrix are used to double extract the mutation points of the stress and strain fields for the arc contact image to be detected, the gradient mutation point is obtained by calculating the mutation gradient and the mutation point, the mutation area is reflected by the gradient mutation point, and the strain mutation area is obtained; the regional growth algorithm is used to perform regional growth of the gradient mutation point in the strain mutation area to obtain the crack contour in the strain mutation area, which can identify the crack contour that may appear in the arc contact during the tensile load process;

[0186] Furthermore, the number of cracks in the crack profile is queried through the crack profile, and the crack distribution density is calculated based on the number of cracks, which helps to understand the specific distribution of cracks inside the material, thereby reflecting the tensile strength of the arc contact, and finally generating an evaluation report of the arc contact based on the tensile strength of the arc contact to be tested.

[0187] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. A person skilled in the art may modify the technical solutions described in the above embodiments, or replace part or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating and processing the tensile resistance of an arc contact image, characterized in that: The steps are as follows: Collecting a tensile load image sequence of an arc contact, preprocessing the tensile load image sequence of the arc contact, and obtaining an image sequence of an arc contact to be detected; The surface of the arc contact is sprayed with uniform optical speckles; Obtaining the stress and strain field of the tensile load of the arc contact from the image of the arc contact to be detected in the image sequence; judging the fatigue degree of the arc contact to be detected by the stress and strain field; and obtaining the tensile resistance of the arc contact to be detected by the fatigue degree; The stress and strain field includes a speckle strain field and a stable strain field; An evaluation report of the arc contact is generated based on the tensile strength of the arc contact to be tested.

2. The method for evaluating the tensile resistance of an arc contact image according to claim 1, characterized in that: Obtaining the stress and strain field of the tensile load of the arc contact from the arc contact image to be detected includes the following steps: Clustering pixels with the same grayscale value for each arc contact image to be detected in the image sequence to obtain pixel clusters; Analyzing the dispersion of the pixel point clusters, and obtaining a speckle area and a stable area in the arc contact image to be detected according to the dispersion of the pixel point clusters; A displacement field operation is performed on the speckle region and the stable region to obtain a speckle strain field and a stable strain field.

3. The method for evaluating the tensile resistance of an arc contact image according to claim 2, characterized in that: The fatigue degree of the arc contact to be detected is calculated by using the stress and strain field. The specific operation steps are as follows: The strain field deviation value is calculated for the stable strain field and the speckle strain field, and the strain field mutation area of ​​the arc contact image to be detected is extracted by using the strain field deviation value, and the crack contour is extracted through the strain field mutation area; the crack distribution density of the crack contour is calculated, and the damage value of the arc contact image to be detected is calculated through the crack distribution density as the fatigue value of the arc contact of the arc contact image to be detected.

4. The method for evaluating the tensile resistance of an arc contact image according to claim 3, characterized in that: The tensile strength of the arc contact to be tested is obtained through the fatigue degree, and the specific operation steps are as follows: Preset an arc contact fatigue threshold e; determine whether the arc contact fatigue of the arc contact image to be detected is greater than the arc contact fatigue threshold e; If not, it is determined that the tensile load of the arc contact of the arc contact image to be detected is qualified, and the tensile resistance of the arc contact is determined to be qualified; If so, it is determined that the tensile load of the arc contact of the arc contact image to be detected is unqualified, and it is determined that the tensile resistance of the arc contact is unqualified.

5. The method for evaluating the tensile resistance of an arc contact image according to claim 4, characterized in that: The strain field deviation value is calculated for the stable strain field and the speckle strain field, and the strain field mutation region of the arc contact image to be detected is extracted using the strain field deviation value. The specific operation steps are as follows: Drawing strain field distribution diagrams for the stable strain field and the speckle strain field respectively to obtain a stable strain field distribution diagram and a speckle strain field distribution diagram; Selecting the maximum strain value in the stable strain field distribution map and the maximum strain value in the speckle strain field distribution map respectively; calculating the maximum strain value in the stable strain field distribution map and the maximum strain value in the speckle strain field distribution map to obtain the strain field deviation value; Establishing a strain assignment threshold r, and judging whether the strain field deviation value is greater than the strain assignment threshold r; If not, it is determined that the arc contact of the arc contact image to be detected does not have a sudden change in strain field; If so, the arc contact of the arc contact image to be detected has a sudden change in strain field; Calculating a sudden change gradient for the arc contact image to be detected; Performing Laplace operator construction of stress and strain fields on the arc contact image to be detected, obtaining local extreme value points of stress and strain fields of the arc contact image to be detected as potential mutation points of stress and strain fields; Constructing a Hessian matrix of stress and strain fields according to the second-order partial derivatives, and calculating the eigenvalues ​​of the Hessian matrix; The gradient mutation points of the arc contact image to be detected are extracted through the mutation gradient, the potential mutation points and the eigenvalues ​​of the Hessian matrix, and all the gradient mutation points are collected to obtain the strain mutation area.

6. The method for evaluating the tensile resistance of an arc contact image according to claim 5, characterized in that: Extracting a crack profile through the strain field mutation region; calculating the crack distribution density of the crack profile, and calculating the damage value of the arc contact image to be detected through the crack distribution density. The specific operation steps are as follows: Performing regional growth of gradient mutation points on the strain mutation region using a regional growing algorithm to obtain a crack profile in the strain mutation region; Calculating the crack distribution density of the crack contour according to the extension direction of the crack contour; tracking the surface morphology evolution of the image sequence according to the crack distribution density to obtain a damage evolution image sequence; extracting key damage feature parameters according to the damage evolution image sequence to calculate the damage value of the arc contact of the arc contact image to be detected; The key damage characteristic parameters include: crack distribution density, crack growth rate and crack morphology changes.

7. The method for evaluating the tensile resistance of an arc contact image according to claim 6, characterized in that: The crack distribution density of the crack contour is calculated according to the extension direction of the crack contour; the surface morphology evolution of the image sequence is tracked according to the crack distribution density to obtain a damage evolution image sequence. The specific operation steps are as follows: The strain mutation area is divided into grid units evenly, and the number of cracks in the internal crack contour is calculated for each grid unit; Calculating crack distribution density according to the number of cracks in each grid unit; The crack distribution density of the arc contact image to be detected in the image sequence is tracked by using an image registration algorithm, and the crack position change relationship at different time points in the image sequence is established to obtain a damage evolution image sequence that tracks the evolution of the surface morphology.

8. The method for evaluating the tensile resistance of an arc contact image according to claim 7, characterized in that: The key damage characteristic parameters are extracted through the damage evolution image sequence, and the damage value of the arc contact of the arc contact image to be detected is calculated. The specific operation steps are as follows: The total area of ​​the crack contour in the strain mutation region of each frame of the arc contact image to be detected is calculated for the damage evolution image sequence; the crack propagation rate is obtained by calculating the total area of ​​the crack contour between the previous and next frames; The crack profile is subjected to crack branch point detection using a skeletonization method, and it is obtained that the crack profile shows branch extension and the crack profile shows crack morphology changes. The damage value of the arc contact of the arc contact image to be detected is calculated through the crack distribution density, crack growth rate and crack morphology change.

9. A system for evaluating and processing the tensile resistance of arc contact images, characterized in that: include: Acquisition module; Processing module; Evaluation module; The acquisition module is used to acquire the tensile load image sequence of the arc contact, pre-process the tensile load image sequence of the arc contact, and obtain the arc contact to be detected in the image sequence; The processing module is used to obtain the stress and strain field of the tensile load of the arc contact from the image of the arc contact to be detected in the image sequence; judge the fatigue degree of the arc contact to be detected through the stress and strain field; and obtain the tensile resistance of the arc contact to be detected through the fatigue degree; The evaluation module is used to generate an evaluation report of the arc contact based on the tensile strength of the arc contact to be tested.

Images