Determination method and device for Vickers hardness of electrical steel, electronic equipment and storage medium

Abstract

The invention discloses an electrical steel Vickers hardness determination method and device, electronic equipment and a storage medium, and relates to the technical field of electrical steel detection. The method comprises the following steps: after determining that a quality evaluation result of a to-be-detected electrical steel surface is qualified, determining a predicted pressing template image for pressing a target area based on attribute parameters and a historical hardness sample area database; based on a preset template gray value corresponding to the predicted down-pressing template image and a boundary point gray value of each target sub-region in the target image, determining the similarity between the predicted down-pressing template image and each target sub-region; on the basis of each target indentation center coordinate, the Vickers hardness tester electric control platform is controlled to carry out moving downward pressing operation, all target indentation images corresponding to the to-be-detected electrical steel and the corresponding target Vickers hardness are determined, the clarity of the indentations is improved, the misjudgment rate of the indentations is reduced, and the accuracy of determining the Vickers hardness of the electrical steel is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical steel detection, and in particular to a method and device for determining the Vickers hardness of electrical steel, an electronic device, and a storage medium. BACKGROUND

[0002] At present, with the rapid development of image processing and machine vision technology, the Vickers hardness tester can realize automatic focusing imaging and automatic imaging function. However, in the industrial detection field of electrical steel products, the practical application of this technology still faces significant challenges.

[0003] However, since the surface coating of electrical steel mainly uses inorganic non-metallic materials such as phosphate and chromate, its optical reflectivity is generally low, which leads to insufficient contrast between the test indentation and the substrate, and further affects the accuracy of determining the Vickers hardness of electrical steel. In addition, the existing technology presents a periodic rolling mark on the surface coating of electrical steel, which has a high overlap with the standard hardness indentation feature, thereby affecting the clarity of the indentation and the misjudgment rate, and further affecting the accuracy of determining the Vickers hardness of electrical steel. SUMMARY

[0004] The embodiments of the present application provide a method and device for determining the Vickers hardness of electrical steel, an electronic device, and a storage medium. The embodiments provided by the present application solve the technical problem of affecting the clarity of the indentation and the misjudgment rate, and further affecting the accuracy of determining the Vickers hardness of electrical steel in the prior art. The embodiments provided by the present application improve the clarity of the indentation and reduce the misjudgment rate of the indentation, and improve the accuracy of determining the Vickers hardness of electrical steel.

[0005] In a first aspect of the embodiments of the present application, a method for determining the Vickers hardness of electrical steel is provided, which includes: Based on the target laser parameters matched with the attribute parameters of the electrical steel to be detected, the target area on the surface of the electrical steel to be detected is subjected to a coating removal treatment, and the quality evaluation result of the electrical steel after removing the surface coating is determined, wherein the size of the target area is set based on the size of the electrical steel to be detected; After determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, a predicted indentation template image for the next indentation treatment of the target area is determined based on the attribute parameters and a historical hardness sample area database. acquire a target image under the target region, determine a similarity between the predicted down-pressing template image and each target sub-region based on a preset template gray value corresponding to the predicted down-pressing template image and a boundary point gray value of each target sub-region in the target image, determine at least one target sub-region with a similarity greater than a preset similarity threshold as a target down-pressing region, and determine a center position coordinate corresponding to each target down-pressing region as a target indentation center coordinate; based on each target indentation center coordinate, control the electric control platform of the Vickers hardness tester to perform a moving down-pressing operation, determine each target indentation image corresponding to the to-be-detected electrical steel, and determine a target Vickers hardness corresponding to each target indentation image.

[0006] In a feasible implementation, the quality evaluation result of the to-be-detected electrical steel after the surface coating is removed is determined based on the target laser parameter adapted to the attribute parameter of the to-be-detected electrical steel, and includes: based on the target laser parameter adapted to the to-be-detected electrical steel, performing a coating removal treatment on a target region on the surface of the to-be-detected electrical steel to determine a target image under the target region; acquire a contrast and an average gray gradient of the target image; determine a quality evaluation result of the surface of the to-be-detected electrical steel based on the contrast and the average gray gradient.

[0007] In a feasible implementation, the quality evaluation result of the surface of the to-be-detected electrical steel is determined based on the contrast and the average gray gradient, and includes: if the contrast is less than a preset contrast and the average gray gradient is less than a preset gray gradient, the quality evaluation result of the surface of the to-be-detected electrical steel is determined to be qualified; if the contrast is greater than or equal to the preset contrast, or the average gray gradient is greater than or equal to the preset gray gradient, the quality evaluation result of the surface of the to-be-detected electrical steel is determined to be unqualified.

[0008] In a feasible implementation, the predicted down-pressing template image for down-pressing treatment of the target region is determined based on the attribute parameter and a historical hardness sample area database, and includes: based on the attribute parameter, determine a hardness value adapted to the attribute parameter from the historical hardness sample area database; based on the hardness value and a preset hardness diagonal conversion formula, determine a predicted indentation diagonal length for down-pressing treatment of the target region; determine a predicted pressing template image of the target region based on the predicted indentation diagonal length.

[0009] In an embodiment, the method further comprises: determining a similarity between each target sub-region and the predicted pressing template image based on a preset template gray value corresponding to the predicted pressing template image and a boundary point gray value of each target sub-region in the target image; determining at least one target sub-region with a similarity greater than a preset similarity threshold as a target pressing region; and determining a center position coordinate corresponding to each target pressing region as a target indentation center coordinate. dividing the target image into a plurality of local target images; traversing the local target images based on the predicted pressing template image to determine at least one target sub-region in each local target image that has a same shape as the predicted pressing template image; determining a gray average value corresponding to each target sub-region based on a gray value of each boundary point in the target sub-region; comparing each gray average value with the preset template gray value to determine a similarity between each target sub-region and the predicted pressing template image; determining at least one target sub-region with a similarity greater than a preset similarity threshold as a candidate pressing region; and determining a center position coordinate corresponding to each candidate pressing region as a candidate indentation center coordinate; screening each candidate indentation center coordinate based on a preset random screening algorithm and each candidate indentation center coordinate to determine a target indentation center coordinate.

[0010] In an embodiment, the method further comprises: screening each candidate indentation center coordinate based on a preset random screening algorithm and each candidate indentation center coordinate to determine a target indentation center coordinate. determining a boundary point coordinate of each candidate pressing region based on each candidate indentation center coordinate; filtering out the candidate pressing region with a defective boundary point coordinate based on a preset random screening algorithm to determine at least one target pressing region and a target indentation center coordinate corresponding to each target pressing region.

[0011] In an embodiment, the Vickers hardness tester control platform comprises a stage and a Vickers hardness tester. The method further comprises: controlling the Vickers hardness tester control platform to perform a moving pressing operation based on each target indentation center coordinate to determine each target indentation image corresponding to the to-be-detected electrical steel. For any target pressing area, based on the target indentation center coordinates and global center coordinates corresponding to the global target image, a horizontal offset of the object table is determined, and the object table is controlled to move horizontally to the target indentation center coordinates according to the horizontal offset; After determining that the object table moves to the target indentation center coordinates, a feature image of the electrical steel collected by an image collection device on an initial focal plane is acquired, wherein the image collection device is installed on the Vickers hardness tester; The feature image is input into a trained defocus distance regression prediction model to determine a predicted defocus amount. After controlling the Vickers hardness tester to drop by the predicted defocus amount, the Vickers hardness tester is controlled to perform a moving pressing operation to determine each target indentation image corresponding to the electrical steel to be detected and a target Vickers hardness corresponding to each target indentation image.

[0012] In a second aspect, the embodiments of the present application provide an electrical steel Vickers hardness determination device, which comprises: A first determination module is configured to perform a coating removal treatment on a target area on the surface of the electrical steel to be detected based on target laser parameters matched with attribute parameters of the electrical steel to be detected, and determine a quality evaluation result of the electrical steel to be detected after the surface coating is removed, wherein the size of the target area is set based on the size of the electrical steel to be detected. A second determination module is configured to determine a predicted pressing template image for pressing the target area after determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, based on the attribute parameters and a historical hardness sample area database. A third determination module is configured to acquire a target image under the target area, determine a similarity between the predicted pressing template image and each target sub-area based on preset template gray values corresponding to the predicted pressing template image and boundary point gray values of each target sub-area in the target image, determine at least one target sub-area with a similarity greater than a preset similarity threshold as a target pressing area, and determine a center position coordinate corresponding to each target pressing area as a target indentation center coordinate. A fourth determination module is configured to control a Vickers hardness tester electric control platform to perform a moving pressing operation based on each target indentation center coordinate, determine each target indentation image corresponding to the electrical steel to be detected, and determine a target Vickers hardness corresponding to each target indentation image.

[0013] In a third aspect, the embodiment of the present application provides an electronic device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the method for determining the Vickers hardness of the electrical steel.

[0014] In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the steps of the method for determining the Vickers hardness of the electrical steel.

[0015] Compared with the prior art, the method, device, electronic device and storage medium for determining the Vickers hardness of the electrical steel provided by the embodiment of the present application have the following advantages. The embodiment of the present application determines the quality evaluation result of the electrical steel to be detected after the surface coating is removed based on the target laser parameter matched with the attribute parameter of the electrical steel to be detected, and determines the predicted down-pressing template image for the target region based on the attribute parameter and the historical hardness sample area database after determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified. Then, the target image under the target region is obtained, and the similarity between the predicted down-pressing template image and each target sub-region is determined based on the preset template gray value corresponding to the predicted down-pressing template image and the boundary point gray value of each target sub-region in the target image. Then, at least one target sub-region with a similarity greater than a preset similarity threshold is determined as a target down-pressing region, and the center position coordinates corresponding to each target down-pressing region are determined as target indentation center coordinates. Then, the Vickers hardness tester electric control platform is controlled to move and press based on each target indentation center coordinate, and each target indentation image corresponding to the electrical steel to be detected is determined, and the target Vickers hardness corresponding to each target indentation image is determined. The embodiment of the present application improves the clarity of the indentation and reduces the misjudgment rate of the indentation, and improves the accuracy of determining the Vickers hardness of the electrical steel. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A flow block diagram of a method for determining the Vickers hardness of the electrical steel is shown; Figure 2 Different focal plane screenshots of a method for determining the Vickers hardness of the electrical steel are shown; Figure 3 A structure block diagram of a device for determining the Vickers hardness of the electrical steel is shown; Figure 4 A structure diagram of an electronic device is shown.

[0017] Figure 3 and Figure 4 The correspondence between the reference signs and the names of the figures is as follows: 300 device for determining the vickers hardness of electrical steel; 310 first determining module; 320 second determining module; 330 third determining module; 340 fourth determining module; 400 electronic device; 410 processor; 420 memory; 430 bus. DETAILED DESCRIPTION

[0018] In order to better understand the technical solutions provided by the embodiments of the present specification, the technical solutions of the embodiments of the present specification will be described in detail below through the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present specification and the embodiments are detailed descriptions of the technical solutions of the embodiments of the present specification, and not limitations of the technical solutions of the present specification. In the case of no conflict, the technical features in the embodiments of the present specification and the embodiments can be combined with each other.

[0019] In this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element. The term "two or more" includes two or more than two.

[0020] Firstly, the application scenarios applicable to the present application are introduced. The embodiments provided by the present application are applicable to the technical field of electrical steel detection, and particularly relate to a method and device for determining the vickers hardness of electrical steel, an electronic device and a storage medium.

[0021] At present, since the surface coating of electrical steel mainly adopts inorganic non-metallic materials such as phosphate and chromate, the optical reflectivity is generally low, which leads to insufficient contrast between the test indentation and the matrix, and further affects the accuracy of determining the vickers hardness of electrical steel. In addition, the existing technology presents a periodic rolling mark on the surface coating of electrical steel, the characteristics of which are highly overlapped with the standard hardness indentation characteristics, thereby affecting the clarity of the indentation and the misjudgment rate, and further affecting the accuracy of determining the vickers hardness of electrical steel.

[0022] Based on this, the embodiment of the present application provides a method and device for determining the Vickers hardness of electrical steel, an electronic device and a storage medium. The embodiment of the present application solves the technical problem of affecting the clarity of the indentation and the misjudgment rate in the prior art, further affecting the accuracy of determining the Vickers hardness of electrical steel. The embodiment of the present application improves the clarity of the indentation and reduces the misjudgment rate of the indentation, thereby improving the accuracy of determining the Vickers hardness of electrical steel.

[0023] Figure 1 A flow chart of a method for determining the Vickers hardness of electrical steel is shown. As shown in Figure 1 The method for determining the Vickers hardness of electrical steel includes the following steps: S101, based on the target laser parameter matched with the attribute parameter of the electrical steel to be detected, performing a coating removal treatment on a target area on the surface of the electrical steel to be detected, and determining the quality evaluation result of the electrical steel to be detected after the surface coating is removed, wherein the size of the target area is set based on the size of the electrical steel to be detected.

[0024] In this step, the embodiment provided by the present application, before performing a coating removal treatment on a target area on the surface of the electrical steel to be detected based on the target laser parameter matched with the attribute parameter of the electrical steel to be detected, first determines the attribute parameter based on a preset parameter acquisition strategy, wherein the preset parameter acquisition strategy includes at least one of the following: data recognition identification by scanning the surface of the electrical steel to be detected, manual input, and database import. Then, based on the attribute parameter and the preset laser electrical steel attribute parameter database, the target laser parameter corresponding to the attribute parameter is determined. After the target laser parameter corresponding to the attribute parameter is determined, the target area on the surface of the electrical steel to be detected is treated by using the target laser parameter, and the removal result of the target area of the electrical steel to be detected after the surface coating is removed is evaluated.

[0025] It can be understood that the embodiment provided by the present application obtains the attribute parameter of the electrical steel to be detected by scanning the data recognition identification on the surface of the electrical steel to be detected, manual input and database import, and then determines the target laser parameter corresponding to the attribute parameter from the preset laser electrical steel attribute parameter database, so as to realize efficient and lossless coating removal.

[0026] It should be noted that the target laser parameters in the embodiments provided in the present application can be customized, selected and used according to different application scenarios and use conditions. The target laser parameters in the embodiments provided in the present application can be specifically set as laser working power, scanning speed, scanning line spacing and scanning times, etc. The laser working power in the embodiments provided in the present application is generally 1%-20% of the total power. The scanning speed is set to 800-2000mm / s. The scanning line spacing is set to 1-20μm. The scanning times are set to 1-3 times.

[0027] The attribute parameters in the embodiments provided in the present application include but are not limited to the material of the electric steel to be detected, the coating type of the electric steel to be detected, the thickness of the electric steel to be detected and the density of the electric steel to be detected, etc.

[0028] In the embodiments provided in the present application, the equipment for removing the layer on the surface of the electric steel to be detected is generally a low-power laser. The total power of the low-power laser is generally not higher than 100W. The scanning speed is not less than 800mm / s. The scanning line spacing is not more than 20μm.

[0029] In the embodiments provided in the present application, the preset laser electric steel attribute parameter database is generally based on orthogonal experimental design for a single material. For example, four elements of working power, scanning speed, scanning line spacing product and scanning times are taken as factors. Each element is designed to have low, medium and high three levels to generate an orthogonal test model. Then, the optimal parameter range combination is obtained by testing according to the model parameters to enter the model library to form the preset laser electric steel attribute parameter database.

[0030] The shape of the target region in the embodiments provided in the present application can be customized, selected and used according to different application scenarios and use conditions. The target region is specifically set as a square region with a length of 10mm or a circular region with a diameter of 10mm in the embodiments provided in the present application.

[0031] For example, based on the target laser parameters matched with the attribute parameters of the electric steel to be detected, the target region on the surface of the electric steel to be detected is removed from the coating layer. The quality evaluation result of the electric steel to be detected after removing the surface coating layer is determined, including: Based on the target laser parameters matched with the electric steel to be detected, the target region on the surface of the electric steel to be detected is removed from the coating layer. The target image under the target region is determined. The contrast and average gray gradient of the target image are obtained. Based on the contrast and average gray gradient, the quality evaluation result of the surface of the electric steel to be detected is determined.

[0032] It should be noted that the embodiments provided in the present application will generally use a microscope or a confocal microscope with an industrial camera to take pictures after focusing on the target area, so as to determine the target image under the target area, and the target image under the target area is subjected to gray processing through visual software (such as Halcon, VisionPro, OpenCV, etc.), so as to determine the contrast and average gray gradient of the target image, facilitate quality evaluation, and determine the quality evaluation result of the surface of the electric steel to be detected.

[0033] For example, based on the contrast and the average gray gradient, the quality evaluation result of the surface of the electric steel to be detected is determined, including: If the contrast is less than the preset contrast, and the average gray gradient is less than the preset gray gradient, it is determined that the quality evaluation result of the surface of the electric steel to be detected is qualified; if the contrast is greater than or equal to the preset contrast, or the average gray gradient is greater than or equal to the preset gray gradient, it is determined that the quality evaluation result of the surface of the electric steel to be detected is unqualified.

[0034] In the above, if it is determined that the contrast is greater than or equal to the preset contrast (such as 20), or the average gray gradient is greater than or equal to the preset gray gradient (such as 15), it is determined that the quality evaluation result of the surface of the electric steel to be detected is unqualified, at which time the laser parameters need to be adjusted, and a secondary processing procedure based on the adjusted laser parameters is triggered, such as adjusting the working power of the low-power laser for the de-coating process. Specifically, it can be to improve the working efficiency by one level or to reduce the working efficiency by one level.

[0035] It can be understood that the embodiments provided in the present application calculate the average value and the standard deviation of all pixel points in the target area through the visual software, and when the standard deviation is lower than the set threshold value, it indicates that the surface contrast meets the acceptable requirements.

[0036] And the embodiments provided in the present application calculate the partial derivatives (Gx and Gy) of all pixel points in the target area in X and Y directions through convolution operation, and through the characteristics that the gray gradient value of the edge of the target area is high, the average gradient value in the target area is monitored in the moving process, the gradient value in the region should be less than the edge value, and the gradient change graph is formed in the moving process. When the graph abnormally rises, it indicates that the target coating is not removed or the substrate is burned, so as to achieve the purpose of monitoring the quality evaluation result of the surface of the electric steel to be detected.

[0037] It should be noted that the embodiments provided in the present application can use a preset pixel length as a unit step length for lateral movement and vertical movement width to take pictures and integrate the target area.

[0038] In the embodiments provided in the present application, the preset pixel length can be customized according to different application scenarios and use conditions, for example, the preset pixel length in the embodiments provided in the present application is set to 100x100.

[0039] In S102, after determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, a predicted indentation template image for the target region is determined based on the attribute parameter and the historical hardness sample area database.

[0040] In this step, after determining that the quality of the surface of the electrical steel to be detected is qualified, the historical hardness sample area data in a preset time period is analyzed based on the historical hardness sample area database, the average Vickers hardness value and the fluctuation value of each material are taken, and a predicted indentation template image for the target region is determined based on the attribute parameter.

[0041] For example, the predicted indentation template image for the target region is determined based on the attribute parameter and the historical hardness sample area database, including: Based on the attribute parameter, a hardness value suitable for the attribute parameter is determined from the historical hardness sample area database; based on the hardness value and a preset hardness diagonal conversion formula, a predicted indentation diagonal length for the target region is determined; and based on the predicted indentation diagonal length, a predicted indentation template image for the target region is determined.

[0042] It can be understood that the preset hardness diagonal conversion formula in the embodiments provided in the present application can be determined according to the material quality threshold and the hardness value and average diagonal conversion formula in the national standard, and the predicted indentation template image for the target region is determined based on the predicted indentation diagonal length in the embodiments provided in the present application.

[0043] It should be noted that the predicted indentation template image can be specifically set as a perfect square test sample area image with an inclination of 45 degrees and a diagonal of L, and the predicted indentation template image processing in the embodiments provided in the present application is generally binary or grayscale image processing, so that the edge features of the predicted indentation template image are closer to the imaging effect of the real indentation.

[0044] In the embodiments provided in the present application, the hardness value refers to the upper and lower thresholds of the material hardness value, which is generally determined by the average hardness value of the material ± 2 times the fluctuation value.

[0045] S103, acquire a target image under a target region, determine a similarity between the predicted down-pressing template image and each target sub-region based on a preset template gray value corresponding to the predicted down-pressing template image and a boundary point gray value of each target sub-region in the target image, determine at least one target sub-region with a similarity greater than a preset similarity threshold as a target down-pressing region, and determine a center position coordinate corresponding to each target down-pressing region as a target indentation center coordinate.

[0046] In this step, the embodiments provided in the present application will determine the optimal position for down-pressing operation on the electric steel to be detected, i.e., the target indentation center coordinate, after acquiring the target image under the target region, by predicting the preset template gray value corresponding to the predicted down-pressing template image and the boundary point gray value of each target sub-region in the target image. Specifically, the similarity between the predicted down-pressing template image and each target sub-region is determined, and at least one target sub-region with a similarity greater than a preset similarity threshold is determined as a target down-pressing region, and then the center position coordinate corresponding to each target down-pressing region is determined as the target indentation center coordinate.

[0047] It can be understood that, since the predicted down-pressing template image in the embodiments provided in the present application is specifically a smooth template image with a uniform gray value, the predicted down-pressing template image only corresponds to one preset template gray value, and defects such as recesses and protrusions may exist in each target sub-region in the target image. Therefore, the boundary point gray value of each target sub-region in the target image needs to be determined in the embodiments provided in the present application to avoid the occurrence of the target indentation center coordinate falling into the defects.

[0048] It should be noted that the size of the preset similarity threshold can be selected and used according to different application scenarios and use conditions. In the embodiments provided in the present application, the preset similarity threshold is set to determine and find several boundary points with the highest similarity values, and the coordinates of the above boundary points are determined as the center position coordinates corresponding to each target down-pressing region, and as the target indentation center coordinates.

[0049] In the embodiments provided in the present application, the target sub-region is set as follows: taking the predicted down-pressing template image as a moving window, and traversing all sub-regions of the target image according to a preset pixel unit for moving compensation.

[0050] Here, the size of the preset pixel unit can be selected and used according to different application scenarios and use conditions. In the embodiments provided in the present application, the preset pixel unit can be specifically set to 1-10 pixels.

[0051] For example, based on the preset template gray value corresponding to the predicted pressing template image and the boundary point gray value of each target sub-region in the target image, the similarity of the predicted pressing template image and each target sub-region is determined, at least one target sub-region with a similarity greater than a preset similarity threshold is determined as a target pressing region, and the center position coordinates corresponding to each target pressing region are determined as target indentation center coordinates, including: The target image is divided into a plurality of local target images; based on the predicted pressing template image, the local target images are traversed to determine at least one target sub-region in each local target image that is the same shape as the predicted pressing template image; based on the gray value of each boundary point in the target sub-region, the gray average value corresponding to the target sub-region is determined; each gray average value is compared with the preset template gray value to determine the similarity of each target sub-region to the predicted pressing template image, at least one target sub-region with a similarity greater than a preset similarity threshold is determined as a candidate pressing region, and the center position coordinates corresponding to each candidate pressing region are determined as candidate indentation center coordinates; based on a preset random screening algorithm and each candidate indentation center coordinate, each candidate indentation center coordinate is screened to determine the target indentation center coordinate.

[0052] It can be understood that the embodiments provided by the present application are to improve the efficiency of indentation processing of the to-be-detected electrical steel and determination of each target indentation image. Specifically, the target region can be divided into four regions by dividing the target region with orthogonal cross lines, and each region after the division is determined as a local target image. Then, the local target image is covered and traversed by taking the predicted pressing template image as a moving window to determine at least one target sub-region that is the same shape as the predicted pressing template image. Then, the boundary points of the target sub-region are located, and the gray values of each boundary point are determined. Then, the gray values of each boundary point are averaged to determine the gray average value, and the gray average value is determined as the gray average value corresponding to the target sub-region.

[0053] After the gray average value corresponding to the target sub-region is determined, each gray average value is compared with the preset template gray value to determine the similarity of each target sub-region to the predicted pressing template image, at least one target sub-region with a similarity greater than a preset similarity threshold is determined as a candidate pressing region, and the center position coordinates corresponding to each candidate pressing region are determined as candidate indentation center coordinates. These candidate indentation center coordinates can optimize the optimal position of subsequent indentation, and the electric control platform of the Vickers hardness tester is subjected to pressing treatment.

[0054] It should be noted that the embodiments provided in the present application need to eliminate the candidate indentation center coordinates after determining the candidate indentation center coordinates in order to ensure that the indentation is not pressed on the defects of the target area. At this time, the embodiments provided in the present application can specifically screen each candidate indentation center coordinate according to the preset random screening algorithm to determine the target indentation center coordinate.

[0055] In the above, the preset random screening algorithm in the embodiments provided in the present application can be customized for selection and use according to different application scenarios and use conditions. The preset random screening algorithm in the embodiments provided in the present application can be specifically set as a random sample consistency algorithm (Random Sample Consensus, RANSAC).

[0056] Among them, the specific division method of the local target image in the embodiments provided in the present application can be customized for setting and use according to different application scenarios and use conditions.

[0057] Illustratively, based on the preset random screening algorithm and each candidate indentation center coordinate, each candidate indentation center coordinate is screened to determine a target indentation center coordinate, comprising: Based on each candidate indentation center coordinate, the boundary point coordinates of each candidate pressing area are determined; based on the preset random screening algorithm, the candidate pressing area with defective boundary point coordinates is filtered out to determine at least one target pressing area and the target indentation center coordinate corresponding to each target pressing area.

[0058] It can be understood that the embodiments provided in the present application filter the boundary point coordinates of each candidate pressing area based on the RANSAC algorithm, remove the candidate pressing area with defective boundary point coordinates, and determine the remaining candidate pressing area as the target pressing area, and continue to determine the target indentation center coordinate corresponding to each target pressing area after screening, so as to accurately identify and avoid the area with defects.

[0059] Here, the embodiments provided in the present application set that not less than three target indentation center coordinates need to be determined in each local target image. If the target indentation center coordinates determined in the local target image do not meet three, it is necessary to move to the next local target image to re-determine three target indentation center coordinates.

[0060] S104, based on each target indentation center coordinate, control the electric control platform of the Vickers hardness tester to move and press, determine each target indentation image corresponding to the electric steel to be detected, and the target Vickers hardness corresponding to each target indentation image.

[0061] In this step, after determining the center coordinates of each target indentation, the embodiment provided in the present application needs to control the electric control platform of the Vickers hardness tester to move and press down. At this time, the position of the electric steel to be detected in the horizontal angle and the position in the vertical angle need to be adjusted, so as to more accurately press down the electric steel to be detected, and then more accurately determine each target indentation image, so as to complete the full-process automatic Vickers hardness detection, and then accurately determine the target Vickers hardness corresponding to each target indentation image.

[0062] For example, the Vickers hardness tester electric control platform includes a stage and a Vickers hardness tester. Based on the center coordinates of each target indentation, the Vickers hardness tester electric control platform is controlled to move and press down, and each target indentation image corresponding to the electric steel to be detected is determined, including: For any target pressing area, based on the target indentation center coordinates and the global center coordinates corresponding to the global target image, the horizontal offset of the stage is determined, and the stage is controlled to move horizontally to the target indentation center coordinates according to the horizontal offset. After determining that the stage moves to the target indentation center coordinates, the feature image of the electric steel collected by the image acquisition device on the initial focal plane is obtained, wherein the image acquisition device is installed on the Vickers hardness tester. The feature image is input into the trained out-of-focus distance regression prediction model to determine the predicted out-of-focus amount. After the Vickers hardness tester is controlled to drop by the predicted out-of-focus amount, the Vickers hardness tester is controlled to move and press down to determine each target indentation image corresponding to the electric steel to be detected and the target Vickers hardness corresponding to each target indentation image.

[0063] In this step, when the embodiment provided in the present application is used for any target pressing area, the stage of the Vickers hardness tester electric control platform needs to be moved horizontally, and the hardness tester needs to be moved vertically, so that the stage moves horizontally to the target indentation center coordinates according to the horizontal offset. The target indentation center coordinates are the absolute coordinates of the indentation center in the complete global target image converted according to the horizontal offset of the stage.

[0064] It can be understood that the Vickers hardness tester electric control platform in the embodiment provided in the present application is accurately positioned in combination with a double coordinate system, specifically, an absolute coordinate system based on the absolute zero point coordinate system moving to the absolute coordinate system of the preset detection point and a relative coordinate system taking the preset monitoring point as the relative zero point.

[0065] It should be noted that the embodiment provided in the application acquires a single frame feature image of the electrical steel collected by the image acquisition device on the initial focal plane at the target indentation center coordinate, then inputs the current feature image into the trained defocus distance regression prediction model to obtain the predicted defocus amount, drives the Z-axis movement of the Vickers hardness tester together with the image acquisition device installed on the Vickers hardness tester to move a corresponding line vertically, moves a compensation distance satisfying the defocus amount, and after moving, starts to collect a clear feature image, thereby solving the difficult problem of focusing of the Vickers hardness indentation caused by the low contrast of the surface of the electrical steel.

[0066] Among them, the embodiment provided in the application systematically collects a series of defocused feature images with a fixed step (usually 1 μm), and the number of single feature image collection is generally 20-50. When collecting the feature image, the Z-axis physical coordinate corresponding to the feature image is recorded synchronously, and the actual physical distance of the Z-axis physical coordinate from the best focal plane position is taken as the label value of the feature image. The position coordinate before the focus is negative, and the position coordinate after the focus is positive.

[0067] In the above, the unit of the actual physical distance is μm; and the embodiment provided in the application, the defocus range is at least ±20 μm to ensure the generalization ability of the model.

[0068] Here, the trained defocus distance regression prediction model in the embodiment provided in the application can be selected and used according to different application scenarios and use conditions. The trained defocus distance regression prediction model in the embodiment provided in the application can be specifically set as a convolutional neural network model, such as a CNN network model, which has a single-channel grayscale image as input, and the input layer size is generally normalized to 224×224 pixels. The CNN model structure generally includes: three convolutional layers (convolution kernel sizes are 7×7, 5×5 and 3×3 in turn, channel numbers are 32, 64 and 128 in turn, each convolutional layer is followed by a ReLU activation function and a 2×2 maximum pooling layer), a flattening layer, two fully connected layers (neuron numbers are generally 1024 and 512), and a linearly activated output layer (outputting a continuous numerical value, i.e. the predicted defocus amount).

[0069] Here, in the embodiment provided in the application, the training method of the defocus distance regression prediction model is specifically: using the sample set, taking the mean square error (MSE) as the loss function, and using the Adam optimizer for training. The initial learning rate is generally 1e-4, the batch size (BatchSize) is generally 16 or 32, and the training period (Epochs) is usually 50-100 times.

[0070] The way of controlling the Vickers hardness tester electric control platform by training the defocus distance regression prediction model is specifically: In real-time detection, the acquisition device collects a single frame feature image of the current scene, and then inputs the single frame feature image into the training defocus distance regression prediction model to output a predicted defocus amount, such as +3.5 μm. Then, according to the above, the Vickers hardness tester electric control platform is directly driven to move the corresponding distance of the Z-axis, such as moving 3.5 μ in the negative direction. This process usually converges to the best focal plane in only 1-2 iterations.

[0071] The embodiment provided in the application first needs to establish the conversion relationship between the image pixel size and the actual physical size after determining the best focal plane map. Usually, camera calibration is performed through a calibration plate to obtain the pixel equivalent (such as 0.1 μm / pixel). Then, a preset indentation profile extraction algorithm is used, and a Canny operator or Sobel operator prediction detection method is used for edge detection to obtain a pixel point set of the indentation edge. Then, the least square method is used to fit the discrete edge points to an ideal rhombus geometric model, and the physical length of the two diagonal lines is directly calculated from the fitted geometric model. Then, the target Vickers hardness corresponding to each target indentation image is calculated according to the formula in the national standard.

[0072] The following embodiment will specifically illustrate the way to determine the Vickers hardness of electrical steel: First, a 50WW800 electrical steel sample is selected, and the sample is processed into a circular sample with a diameter of 50 mm. A laser marking machine is used to mark an identification containing the sample test number and a two-dimensional code in a 10 mm ring area at the edge of the sample. The material parameters of the sample, such as the grade: 50WW800; the coating type: chromate; the thickness: 0.5 mm; the density: 7.75 g / cm³, etc. are recorded in the preset laser electrical steel attribute parameter database.

[0073] Then, according to the two-dimensional code of the sample, the material parameters are obtained. Specifically, according to the grade “50WW800” and the coating type “chromate”, the optimal target laser parameter combination is intelligently called from the pre-built preset laser electrical steel attribute parameter database, such as the total power of the laser 20 W, the working power 15% of the total power, the scanning speed 1400-1500 mm / s, the line spacing 10 μm, the scanning times 1, etc. Then, the historical average Vickers hardness value (110 HV) and the fluctuation value (7 HV) of the sample area database are queried according to the grade “50WW800”, and the template filling pattern corresponding to the upper and lower thresholds is obtained by calculation, and the target indentation center coordinates of 3 points meeting the requirements are determined through the preset random screening algorithm.

[0074] At each precisely positioned target indentation center coordinate, the acquisition device using adaptive focusing based on a deep learning model controls the Vickers hardness tester to move down at the position of the predicted defocus amount to determine the corresponding target indentation image of the to-be-detected electrical steel and the target Vickers hardness corresponding to each target indentation image.

[0075] In the above, the present application determines the optimal focal plane at which the Vickers hardness tester starts to press down by predicting the defocus amount, thereby improving the subsequent automatic detection result. Figure 2 A screenshot of a Vickers hardness determination method for electrical steel provided by an embodiment of the present application is shown. Figure 2 As shown, the pictures from left to right are the feature image before focusing, the feature image after determining the predicted defocus amount, and the feature image after focusing.

[0076] Compared with the prior art, the Vickers hardness determination method for electrical steel provided by the embodiment of the present application performs a coating removal process on a target region on the surface of the to-be-detected electrical steel based on a target laser parameter adapted to the attribute parameter of the to-be-detected electrical steel, determines the quality evaluation result of the to-be-detected electrical steel after the surface coating is removed, and after determining that the quality evaluation result of the surface of the to-be-detected electrical steel is qualified, determines a predicted pressing template image for the target region based on the attribute parameter and a historical hardness sample area database, then acquires a target image under the target region, and determines the similarity between the predicted pressing template image and each target sub-region based on the preset template gray value corresponding to the predicted pressing template image and the boundary point gray value of each target sub-region in the target image, then determines at least one target sub-region with a similarity greater than a preset similarity threshold as a target pressing region, and determines the center position coordinate corresponding to each target pressing region as a target indentation center coordinate, and controls the Vickers hardness tester electric control platform to move down based on each target indentation center coordinate to determine the corresponding target indentation image of the to-be-detected electrical steel and the target Vickers hardness corresponding to each target indentation image. The embodiment provided by the present application improves the clarity of the indentation and reduces the misjudgment rate of the indentation, thereby improving the accuracy of determining the Vickers hardness of the electrical steel. Moreover, the laser coating removal process of the present application ensures that the laser only acts on the coating, thereby reducing the thermal damage to the electrical steel substrate, providing a smooth, flat, and high-contrast target region for subsequent indentation imaging, further improving the accuracy of indentation boundary recognition, and supporting full-process data recording and backtracking.

[0077] Figure 3 A structural block diagram of a Vickers hardness determination device for electrical steel provided by an embodiment of the present application is shown. As shown in Figure 3 The Vickers hardness determination device for electrical steel 300 includes: The first determination module 310 is configured to perform a coating removal treatment on a target region on the surface of the electric steel to be detected based on target laser parameters matched with attribute parameters of the electric steel to be detected, and determine a quality evaluation result of the electric steel to be detected after the surface coating is removed, wherein the size of the target region is set based on the size of the electric steel to be detected.

[0078] The second determination module 320 is configured to, after determining that the quality evaluation result of the surface of the electric steel to be detected is qualified, determine a predicted pressing template image for performing a pressing treatment on the target region based on the attribute parameters and a historical hardness sample area database.

[0079] The third determination module 330 is configured to acquire a target image under the target region, determine a similarity between the predicted pressing template image and each target sub-region based on preset template gray values corresponding to the predicted pressing template image and boundary point gray values of each target sub-region in the target image, determine at least one target sub-region with a similarity greater than a preset similarity threshold as a target pressing region, and determine a center position coordinate corresponding to each target pressing region as a target indentation center coordinate.

[0080] The fourth determination module 340 is configured to control a Vickers hardness tester electric control platform to perform a moving pressing operation based on each target indentation center coordinate, determine each target indentation image corresponding to the electric steel to be detected, and determine a target Vickers hardness corresponding to each target indentation image.

[0081] For example, the first determination module 310 is specifically configured to: perform a coating removal treatment on a target region on the surface of the electric steel to be detected based on target laser parameters matched with the electric steel to be detected, and determine a target image under the target region.

[0082] acquire a contrast and an average gray gradient of the target image.

[0083] determine a quality evaluation result of the surface of the electric steel to be detected based on the contrast and the average gray gradient.

[0084] For example, the quality evaluation result of the surface of the electric steel to be detected is determined based on the contrast and the average gray gradient, including: if the contrast is less than a preset contrast and the average gray gradient is less than a preset gray gradient, it is determined that the quality evaluation result of the surface of the electric steel to be detected is qualified.

[0085] if the contrast is greater than or equal to the preset contrast or the average gray gradient is greater than or equal to the preset gray gradient, it is determined that the quality evaluation result of the surface of the electric steel to be detected is unqualified.

[0086] For example, the second determination module 320 is specifically configured to: Determine, based on the attribute parameter, a hardness value that matches the attribute parameter from a historical hardness sample area database.

[0087] Determine, based on the hardness value and a preset hardness diagonal conversion formula, a predicted indentation diagonal length of the target area after the pressing process.

[0088] Determine, based on the predicted indentation diagonal length, a predicted pressing template image of the target area after the pressing process.

[0089] The third determining module 330 is configured to: Divide the target image into a plurality of local target images.

[0090] Based on the predicted pressing template image, traverse the local target images to determine at least one target sub-area in each local target image that has the same shape as the predicted pressing template image.

[0091] Determine, based on the gray value of each boundary point in the target sub-area, a gray average value corresponding to the target sub-area.

[0092] Compare each gray average value with a preset template gray value to determine the similarity between each target sub-area and the predicted pressing template image, determine at least one target sub-area with a similarity greater than a preset similarity threshold as a candidate pressing area, and determine the center position coordinates corresponding to each candidate pressing area as candidate indentation center coordinates.

[0093] Based on a preset random screening algorithm and the candidate indentation center coordinates, screen the candidate indentation center coordinates to determine target indentation center coordinates.

[0094] Based on a preset random screening algorithm and the candidate indentation center coordinates, screen the candidate indentation center coordinates to determine target indentation center coordinates, including: Determine, based on the candidate indentation center coordinates, the boundary point coordinates of each candidate pressing area.

[0095] Based on the preset random screening algorithm, filter out candidate pressing areas with defective boundary point coordinates to determine at least one target pressing area and target indentation center coordinates corresponding to each target pressing area.

[0096] The fourth determining module 340 is configured to: For any target pressing area, determine, based on the target indentation center coordinates and global center coordinates corresponding to the global target image, a horizontal offset of the object table, and control the object table to move horizontally to the target indentation center coordinates according to the horizontal offset.

[0097] After determining that the object table moves to the target indentation center coordinate, a feature image of the electrical steel collected by the image collection device on the initial focal plane is acquired, wherein the image collection device is installed on the Vickers hardness tester.

[0098] The feature image is input into the trained defocus distance regression prediction model to determine the predicted defocus amount.

[0099] After controlling the Vickers hardness tester to descend by the predicted defocus amount, the Vickers hardness tester is controlled to perform a moving and pressing operation to determine each target indentation image corresponding to the electrical steel to be detected and a target Vickers hardness corresponding to each target indentation image.

[0100] The device 300 for determining the Vickers hardness of the electrical steel provided by the embodiments of the present application determines the quality evaluation result of the electrical steel to be detected after the surface coating is removed based on the target laser parameters matched with the attribute parameters of the electrical steel to be detected, and after determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, the predicted pressing template image for pressing the target region is determined based on the attribute parameters and the historical hardness sample area database, and then the target image under the target region is acquired, and the similarity between the predicted pressing template image and each target sub-region is determined based on the preset template gray value corresponding to the predicted pressing template image and the boundary point gray value of each target sub-region in the target image, and then at least one target sub-region with a similarity greater than a preset similarity threshold is determined as a target pressing region, and the center position coordinates corresponding to each target pressing region are determined as target indentation center coordinates, and based on each target indentation center coordinate, the electric control platform of the Vickers hardness tester is controlled to perform a moving and pressing operation to determine each target indentation image corresponding to the electrical steel to be detected and a target Vickers hardness corresponding to each target indentation image, the embodiments provided by the present application improve the clarity of the indentation and reduce the misjudgment rate of the indentation, improve the accuracy of determining the Vickers hardness of the electrical steel, and the laser coating removal process of the present application ensures that the laser only acts on the coating, reduces the thermal damage to the electrical steel substrate, provides a smooth, flat and high-contrast target region for subsequent indentation imaging, further improves the accuracy of indentation boundary recognition, and the present application supports full-process data recording and backtracking.

[0101] Please refer to Figure 4 , Figure 4 The structure of an electronic device provided by the embodiments of the present application is shown in FIG. 4. Figure 4 As shown in FIG. 4, the electronic device 400 includes a processor 410, a memory 420 and a bus 430.

[0102] The memory 420 stores machine readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 through the bus 430. When the machine readable instructions are executed by the processor 410, the machine readable instructions can perform the steps of the method for determining the Vickers hardness of the electrical steel as described above Figures 1 to 2 The steps of the method for determining the Vickers hardness of the electrical steel in the method embodiment are described above. For brevity and conciseness, the specific implementation manners can be referred to the method embodiment, and will not be described here.

[0103] The computer readable storage medium stores a computer program. When the computer program is run by the processor, the computer program can perform the steps of the method for determining the Vickers hardness of the electrical steel as described above Figures 1 to 2 The steps of the method for determining the Vickers hardness of the electrical steel in the method embodiment are described above. For brevity and conciseness, the specific implementation manners can be referred to the method embodiment, and will not be described here.

[0104] For the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0105] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0106] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer readable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer readable program code.

[0107] The present application is described with reference to flowcharts and / or block diagrams according to the method, device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a machine that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks

[0108] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 one or more flow or block Figure 1 one or more flow or block

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions executed on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more flow or block Figure 1 one or more flow or block

[0110] The embodiments of the present application also provide a computer program product, which comprises computer software instructions, when the computer software instructions are run on a processing device, the processing device executes the flow of the method for determining the Vickers hardness of electrical steel.

[0111] The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present application is produced. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that the computer can store or the data storage device such as server, data center, etc. integrated with one or more available media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0113] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0114] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0115] In addition, each functional unit in the embodiments of the present application can be integrated in a processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially or substantially, or all or part of the technical solutions, can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions that cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various media that can store program codes.

[0117] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent replacements; and these modifications or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0118] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to encompass within their scope all such alternatives, modifications and variations as fall within the scope of the present application. One skilled in the art will readily recognize from the disclosure herein, collaborative combinations of elements from the various embodiments of the application. It should be noted that, while the use of the singular includes the singular, use of the plural includes the plural, and use of the plural includes the singular as well. For example, a single processor or other unit can be implemented.

[0119] It is therefore intended that this specification and the claims be construed as including all such modifications and variations as fall within the scope of the application. It is the applicants' intention that their disclosure be of a nature sufficient to enable those skilled in the art to make and use the application.

Claims

1. A method of determining the Vickers hardness of an electrical steel, characterized in that, The method for determining the Vickers hardness of the electrical steel comprises the following steps: Based on the target laser parameters matched with the attribute parameters of the electrical steel to be detected, a target area on the surface of the electrical steel to be detected is subjected to a coating removal treatment, and a quality evaluation result of the electrical steel to be detected after the surface coating is removed is determined, wherein the size of the target area is set based on the size of the electrical steel to be detected; After determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, a predicted pressing template image for pressing the target area is determined based on the attribute parameters and a historical hardness sample area database; A target image under the target area is obtained, the similarity between the predicted pressing template image and each target sub-area is determined based on the preset template gray value corresponding to the predicted pressing template image and the boundary point gray value of each target sub-area in the target image, at least one target sub-area with a similarity greater than a preset similarity threshold is determined as a target pressing area, and the center position coordinates corresponding to each target pressing area are determined as target indentation center coordinates; Based on each target indentation center coordinate, a Vickers hardness tester electric control platform is controlled to perform a moving pressing operation, each target indentation image corresponding to the electrical steel to be detected is determined, and a target Vickers hardness corresponding to each target indentation image is determined.

2. The method of determining the Vickers hardness of electrical steel according to claim 1, characterized in that, The method for determining the Vickers hardness of the electrical steel comprises the following steps: Based on the target laser parameters matched with the attribute parameters of the electrical steel to be detected, a target area on the surface of the electrical steel to be detected is subjected to a coating removal treatment, and a quality evaluation result of the electrical steel to be detected after the surface coating is removed is determined, wherein the size of the target area is set based on the size of the electrical steel to be detected; After determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, a predicted pressing template image for pressing the target area is determined based on the attribute parameters and a historical hardness sample area database; A target image under the target area is obtained, the similarity between the predicted pressing template image and each target sub-area is determined based on the preset template gray value corresponding to the predicted pressing template image and the boundary point gray value of each target sub-area in the target image, at least one target sub-area with a similarity greater than a preset similarity threshold is determined as a target pressing area, and the center position coordinates corresponding to each target pressing area are determined as target indentation center coordinates; 3. The method of determining the Vickers hardness of electrical steel according to claim 2, characterized in that, Based on each target indentation center coordinate, a Vickers hardness tester electric control platform is controlled to perform a moving pressing operation, each target indentation image corresponding to the electrical steel to be detected is determined, and a target Vickers hardness corresponding to each target indentation image is determined. The method for determining the Vickers hardness of the electrical steel comprises the following steps: Based on the target laser parameters matched with the attribute parameters of the electrical steel to be detected, a target area on the surface of the electrical steel to be detected is subjected to a coating removal treatment, and a quality evaluation result of the electrical steel to be detected after the surface coating is removed is determined, wherein the size of the target area is set based on the size of the electrical steel to be detected; 4. The method of determining the Vickers hardness of electrical steel of claim 1, wherein, After determining that the quality evaluation result of the surface of the electrical steel to be detected is qualified, a predicted pressing template image for pressing the target area is determined based on the attribute parameters and a historical hardness sample area database; A target image under the target area is obtained, the similarity between the predicted pressing template image and each target sub-area is determined based on the preset template gray value corresponding to the predicted pressing template image and the boundary point gray value of each target sub-area in the target image, at least one target sub-area with a similarity greater than a preset similarity threshold is determined as a target pressing area, and the center position coordinates corresponding to each target pressing area are determined as target indentation center coordinates; Based on each target indentation center coordinate, a Vickers hardness tester electric control platform is controlled to perform a moving pressing operation, each target indentation image corresponding to the electrical steel to be detected is determined, and a target Vickers hardness corresponding to each target indentation image is determined. ​ 5. The method of determining the Vickers hardness of electrical steel of claim 2, wherein, The method comprises the following steps: dividing the target image into a plurality of local target images; based on the predicted down-pressing template image, traversing the local target images, and determining at least one target sub-region in each local target image that has the same shape as the predicted down-pressing template image; based on the gray value of each boundary point in the target sub-region, determining the average gray value corresponding to the target sub-region; comparing each gray average value with the preset template gray value to determine the similarity of each target sub-region with the predicted down-pressing template image, determining at least one target sub-region with a similarity greater than a preset similarity threshold as a candidate down-pressing region, and determining the center position coordinates corresponding to each candidate down-pressing region as candidate indentation center coordinates; based on a preset random screening algorithm and each candidate indentation center coordinate, screening each candidate indentation center coordinate to determine the target indentation center coordinate.

6. The method of determining the Vickers hardness of electrical steel according to claim 5, characterized in that, The method comprises the following steps: based on each candidate indentation center coordinate, determining the boundary point coordinates of each candidate down-pressing region; based on a preset random screening algorithm, filtering out the candidate down-pressing regions with defective boundary point coordinates to determine at least one target down-pressing region and the target indentation center coordinates corresponding to each target down-pressing region.

7. The method of determining the Vickers hardness of electrical steel of claim 2, wherein, The Vickers hardness tester electric control platform comprises a stage and a Vickers hardness tester. Based on each target indentation center coordinate, the Vickers hardness tester electric control platform is controlled to perform a moving down-pressing operation to determine each target indentation image corresponding to the to-be-detected electrical steel. For any target down-pressing region, based on the target indentation center coordinate and the global center coordinate corresponding to the global target image, the horizontal offset of the stage is determined, and the stage is controlled to move horizontally to the target indentation center coordinate according to the horizontal offset; after determining that the stage moves to the target indentation center coordinate, a feature image of the electrical steel collected by an image collection device on an initial focal plane is obtained, wherein the image collection device is installed on the Vickers hardness tester; the feature image is input into a trained out-of-focus distance regression prediction model to determine a predicted out-of-focus amount; after the Vickers hardness tester is controlled to drop by the predicted out-of-focus amount, the Vickers hardness tester is controlled to perform a moving down-pressing operation to determine each target indentation image corresponding to the to-be-detected electrical steel and the target Vickers hardness corresponding to each target indentation image.

8. An apparatus for determining the Vickers hardness of electrical steel, characterized by The electrical steel Vickers hardness determination device comprises: The first determination module is configured to perform a coating removal treatment on a target region on the surface of the electric steel to be detected based on target laser parameters matched with attribute parameters of the electric steel to be detected, and determine a quality evaluation result of the electric steel to be detected after the surface coating is removed, wherein the size of the target region is set based on the size of the electric steel to be detected. The second determination module is configured to, after determining that the quality evaluation result of the surface of the electric steel to be detected is qualified, determine a predicted pressing template image for performing a pressing treatment on the target region based on the attribute parameters and a historical hardness sample area database. The third determination module is configured to obtain a target image under the target region, determine a similarity between the predicted pressing template image and each target sub-region based on a preset template gray value corresponding to the predicted pressing template image and a boundary point gray value of each target sub-region in the target image, determine at least one target sub-region with a similarity greater than a preset similarity threshold as a target pressing region, and determine a center position coordinate corresponding to each target pressing region as a target indentation center coordinate. The fourth determination module is configured to control a Vickers hardness tester electric control platform to perform a moving pressing operation based on each target indentation center coordinate, determine each target indentation image corresponding to the electric steel to be detected, and determine a target Vickers hardness corresponding to each target indentation image.

9. An electronic device, comprising: The processor, the memory and the bus, the memory stores machine readable instructions executable by the processor, when the electronic device runs, the processor and the memory communicate through the bus, the machine readable instructions are executed by the processor to execute the steps of the electric steel Vickers hardness determination method in any one of the above claims 1-7. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the steps of the electric steel Vickers hardness determination method in any one of the above claims 1-7.

10. A computer-readable storage medium, characterized in that, ​

Images