Monocrystalline superalloy grinding processing plastic deformation layer thickness identification method and system

Abstract

The present application relates to the technical field of machining, and discloses a single crystal high-temperature alloy grinding plastic deformation layer thickness identification method and system, which uses the high-resolution imaging capability of a scanning electron microscope to collect a port cross-section image, then pre-processes the collected image, uses a Canny edge detection algorithm to accurately identify edge information in the image, then uses a HoughLinesP rectangle detection algorithm to identify crystal edge frames, calculates the crystal direction angle of each crystal in the image to distinguish the crystals in the undeformed area and the deformed area, and the maximum depth value of the corresponding area of the crystals, and combines a preset single crystal high-temperature alloy material grinding plastic deformation area crystal angle identification threshold to obtain the thickness value of the single crystal high-temperature alloy material grinding plastic deformation area. The present application can accurately analyze the thickness value of the single crystal high-temperature alloy material grinding plastic deformation area, and provides strong technical support for the control and optimization of material processing quality.

Description

Technical Field

[0001] This invention relates to the field of machining technology and discloses a method and system for identifying the thickness of the plastic deformation layer during grinding of single-crystal high-temperature alloys. Background Technology

[0002] Single-crystal superalloys possess excellent high-temperature mechanical properties, significantly improving the operating temperature of hot-end components in aero-engines and enhancing engine efficiency, making them one of the primary materials for aero-engine turbine blades. However, the unique grain boundary-free structure of these materials, while endowing them with outstanding high-temperature performance, also makes them highly susceptible to special plastic deformation phenomena during machining. Especially in precision grinding, the high-speed relative motion between the grinding wheel and the workpiece generates instantaneous high temperatures and extraordinary contact stresses in the contact area, inducing plastic deformation behaviors such as dynamic recovery, substructure evolution, and lattice distortion on the material surface, forming plastic deformation layers of varying thicknesses.

[0003] This microstructural degradation layer poses a serious threat to the service reliability of blades: micron-sized cracks are prone to initiation and propagation within the deformation region, forming fatigue crack initiation points along grain boundaries, ultimately leading to tenon joint failure or even blade breakage. Therefore, establishing a precise method for detecting the thickness of the grinding deformation layer is of great significance for optimizing machining parameters, controlling manufacturing quality, and predicting component lifespan.

[0004] Currently, the industry mainly uses three detection methods: metallographic analysis, which observes the structure through destructive sampling, can directly characterize the deformation morphology, but cannot achieve non-destructive testing; microhardness analysis, which indirectly infers the deformation depth through changes in hardness gradient, but has low detection efficiency and insufficient spatial resolution; and X-ray diffraction technology, which analyzes the degree of deformation based on lattice distortion, but has high equipment costs and is sensitive to surface roughness, making it difficult to meet the detection needs of complex curved surfaces. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for identifying the thickness of the plastic deformation layer in the grinding process of single-crystal high-temperature alloys. This method can accurately analyze the thickness value of the plastic deformation region after grinding of single-crystal high-temperature alloy materials, providing strong technical support for the control and optimization of material processing quality.

[0006] To achieve the above-mentioned technical effects, the technical solution adopted by the present invention is as follows:

[0007] A method for identifying the thickness of the plastic deformation layer during grinding of single-crystal superalloys, including:

[0008] Scanning electron microscopy was used to acquire cross-sectional images of the cut end of the single-crystal superalloy material after grinding.

[0009] convert the port section image into a gray image, adopt the Canny edge detection algorithm to perform grid edge detection on the gray image, and obtain weak edge curves with a gray gradient less than a first preset gradient threshold and strong edge curves with a gray gradient greater than a second preset gradient threshold on the gray image; wherein the first preset gradient threshold is less than the second preset gradient threshold;

[0010] take each of the strong edge curves as a backbone and an anchor point, combine the weak edge curve segments connected with the corresponding strong edge curve, and form a complete and continuous grid frame;

[0011] adopt the HoughLinesP rectangular detection algorithm to identify the grid frame in the gray image, calculate the direction angle according to the slope of the grid frame straight line, and count the average value of the direction angle of all grid frames;

[0012] sort the depth values of the identified grid center points in descending order of the direction angle, take the depth value of the grid center point corresponding to a first proportion value of the total number of the identified grids as the minimum depth value of the plastic deformation layer of the single-crystal high-temperature alloy grinding processing, and take the depth value of the grid center point corresponding to a second proportion value of the total number of the identified grids as the maximum depth value of the plastic deformation layer of the single-crystal high-temperature alloy grinding processing, wherein the first proportion value is less than the second proportion value;

[0013] analyze the thickness value of the plastic deformation region of the single-crystal high-temperature alloy material after grinding processing according to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of the direction angle of all grids, and a preset crystal angle recognition threshold of the plastic deformation region of the single-crystal high-temperature alloy material after grinding processing.

[0014] Further, after converting the port section image into a gray image and before performing grid edge detection on the gray image by using the Canny edge detection algorithm, a threshold algorithm is adopted to perform noise reduction preprocessing on the gray image.

[0015] Further, when the HoughLinesP rectangular detection algorithm is adopted to identify the grid frame in the gray image, the distance resolution in the HoughLinesP rectangular detection algorithm is 1 pixel, the angle resolution is 1 degree resolution, the accumulator threshold is 15 pixels, the minimum length of the line segment is 8 pixels, and the maximum allowed gap between points on the same straight line is 2 pixels.

[0016] Further, when counting the average value of the direction angle of all grid frames, if the grid direction angle is greater than 90 degrees, subtract 90 to make the grid direction angle distributed between [0, 90°], and then calculate the average value of the direction angle of all grid frames.

[0017] Further, the thickness value of the plastic deformation region of the single crystal superalloy material after grinding is determined according to is obtained by analysis, wherein is the thickness value of the plastic deformation region of the single crystal superalloy material after grinding, is the average value of all grid direction angles, is a preset crystal angle identification threshold of the plastic deformation region of the single crystal superalloy material after grinding, is 15°, is the maximum depth value of the plastic deformation layer, is the minimum depth value of the plastic deformation layer.

[0018] To achieve the above technical effects, the application further provides a single crystal superalloy plastic deformation layer thickness identification system, comprising:

[0019] an image acquisition module, configured to acquire a port cross-section image of the single crystal superalloy material after grinding by using a scanning electron microscope;

[0020] an edge curve processing module, configured to convert the port cross-section image into a gray-scale image, perform grid edge detection on the gray-scale image by using a Canny edge detection algorithm, and obtain weak edge curves with a gray-scale gradient less than a first preset gradient threshold and strong edge curves with a gray-scale gradient greater than a second preset gradient threshold on the gray-scale image; wherein the first preset gradient threshold is less than the second preset gradient threshold;

[0021] an edge contour processing module, configured to take each strong edge curve as a backbone and an anchor point, combine weak edge curve segments connected with the corresponding strong edge curve, and form a complete and continuous grid frame;

[0022] a direction angle analysis module, configured to identify the grid frame in the gray-scale image by using a HoughLinesP rectangular detection algorithm, calculate a direction angle according to a grid frame straight line slope, and count an average value of all grid frame direction angles;

[0023] a sorting analysis module, configured to sort the identified grid center point depth values in descending order of the direction angle, take a grid center point depth value corresponding to a first proportion value of the total number of the identified grids as a minimum depth value of the single crystal superalloy plastic deformation layer after grinding, and take a grid center point depth value corresponding to a second proportion value of the total number of the identified grids as a maximum depth value of the single crystal superalloy plastic deformation layer after grinding, wherein the first proportion value is less than the second proportion value;

[0024] a thickness analysis module configured to analyze a thickness value of the plastic deformation region of the single crystal superalloy material after the grinding processing according to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of all grid direction angles, and a preset crystal angle recognition threshold value of the plastic deformation region of the single crystal superalloy material after the grinding processing.

[0025] Further, the edge curve processing module comprises a preprocessing unit configured to, after converting the port cross-section image into a gray image, and before performing grid edge detection on the gray image by using the Canny edge detection algorithm, perform noise reduction preprocessing on the gray image by using a threshold threshold algorithm.

[0026] Further, in the direction angle analysis module, when the HoughLinesP rectangular detection algorithm identifies the grid frame in the gray image, the distance resolution in the HoughLinesP rectangular detection algorithm is 1 pixel, the angle resolution is 1 degree resolution, the accumulator threshold is 15 pixels, the minimum length of the line segment is 8 pixels, and the maximum allowed gap between points on the same line is 2 pixels.

[0027] Further, in the direction angle analysis module, when calculating the average value of all grid direction angles, if the grid direction angle is greater than 90 degrees, subtract 90 to make the grid direction angle distributed between [0, 90°], and then calculate the average value of all grid direction angles.

[0028] Further, in the thickness analysis module, the thickness value of the plastic deformation region of the single crystal superalloy material after the grinding processing is obtained according to wherein is the thickness value of the plastic deformation region of the single crystal superalloy material after the grinding processing, is the average value of all grid direction angles, is the preset crystal angle recognition threshold value of the plastic deformation region of the single crystal superalloy material after the grinding processing, is 15°, is the maximum depth value of the plastic deformation layer, is the minimum depth value of the plastic deformation layer.

[0029] Compared with the prior art, the single crystal high-temperature alloy plastic deformation layer thickness identification method provided by the present application has the advantages of the surface detection technology based on machine vision, and the plastic deformation layer image of the single crystal high-temperature alloy material after grinding is analyzed by a machine vision method and an image processing algorithm, the crystal direction angle of each crystal in the image is identified, the crystals in the deformed and undeformed regions are distinguished, and the maximum depth value of the crystals in the corresponding region is obtained, and the preset single crystal high-temperature alloy plastic deformation region crystal angle identification threshold is combined to accurately analyze the thickness value of the single crystal high-temperature alloy plastic deformation region after grinding, thereby providing strong technical support for the control and optimization of material processing quality. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 A single crystal high-temperature alloy grinding plastic deformation layer thickness identification method flowchart for example 1 or 2;

[0031] Figure 2 A single crystal high-temperature alloy grinding plastic deformation layer thickness identification system structure block diagram for example 1;

[0032] Figure 3 A fracture cross-section microstructure diagram collected in example 2;

[0033] Figure 4 A microstructure diagram after Gaussian enhancement of the gray-scale diagram in example 2;

[0034] Figure 5 A crystal direction identification result diagram in example 2;

[0035] Figure 6 A grid direction detection statistical histogram drawn in example 2;

[0036] Wherein, 1, an image acquisition module; 2, an edge curve processing module; 201, a preprocessing unit; 3, an edge contour processing module; 4, a direction angle analysis module; 5, a sorting analysis module; 6, a thickness analysis module. DETAILED DESCRIPTION

[0037] The present application will be further described in detail below in combination with the embodiments and the drawings. However, it should not be understood that the scope of the above-mentioned subject matter of the present application is limited to the following embodiments only, and any technology realized based on the content of the present application belongs to the scope of the present application.

[0038] Example 1

[0039] Reference Figure 1 and Figure 2 The single crystal high-temperature alloy plastic deformation layer thickness identification method comprises:

[0040] The scanning electron microscope is used to collect the port cross-section image of the single crystal superalloy material after grinding processing.

[0041] The port cross-section image is converted into a gray scale image, and the Canny edge detection algorithm is used to detect the grid edge of the gray scale image to obtain a weak edge curve with a gray scale gradient less than a first preset gradient threshold and a strong edge curve with a gray scale gradient greater than a second preset gradient threshold; the first preset gradient threshold is less than the second preset gradient threshold.

[0042] Each strong edge curve is taken as a backbone and an anchor point, and the weak edge curve segments connected with the corresponding strong edge curve are combined to form a complete and continuous grid frame.

[0043] The HoughLinesP rectangle detection algorithm is used to identify the grid frame in the gray scale image, and the direction angle is calculated according to the slope of the grid frame straight line, and the average value of the direction angle of all grid frames is counted.

[0044] The depth values of the identified grid center points are sorted in descending order of the direction angle, and the depth value of the grid center point corresponding to the first proportion value of the total number of the identified grids is taken as the minimum depth value of the plastic deformation layer of the single crystal superalloy after grinding processing, and the depth value of the grid center point corresponding to the second proportion value of the total number of the identified grids is taken as the maximum depth value of the plastic deformation layer of the single crystal superalloy after grinding processing, wherein the first proportion value is less than the second proportion value.

[0045] According to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of all grid direction angles, and the preset crystal angle recognition threshold of the plastic deformation region of the single crystal superalloy material after grinding processing, the thickness value of the plastic deformation region of the single crystal superalloy material after grinding processing is obtained.

[0046] In this embodiment, the high-resolution imaging capability of the scanning electron microscope is used to collect the port cross-section image to clearly reflect the microstructure characteristics of the material; then the collected image is preprocessed to convert it into a gray scale image and to reduce noise, and the Canny edge detection algorithm is used to accurately identify the edge information in the image; then the HoughLinesP rectangle detection algorithm is used to identify the crystal edge frame to calculate the crystal direction angle of each crystal in the image to distinguish the deformed region and the deformation region of the crystal, and the maximum depth value of the corresponding region, and combined with the preset crystal angle recognition threshold of the plastic deformation region of the single crystal superalloy material after grinding processing, the thickness value of the plastic deformation region of the single crystal superalloy material after grinding processing is accurately analyzed, which provides strong technical support for the control and optimization of material processing quality.

[0047] Based on the same inventive concept, the embodiment also provides a single-crystal superalloy plastic deformation layer thickness identification system for grinding processing, comprising:

[0048] An image acquisition module 1 is configured to acquire a port cross-section image of a single-crystal superalloy material after grinding processing by using a scanning electron microscope.

[0049] An edge curve processing module 2 is configured to convert the port cross-section image into a gray-scale image, perform grid edge detection on the gray-scale image by using a Canny edge detection algorithm, and obtain weak edge curves with a gray-scale gradient less than a first preset gradient threshold value and strong edge curves with a gray-scale gradient greater than a second preset gradient threshold value on the gray-scale image, wherein the first preset gradient threshold value is less than the second preset gradient threshold value.

[0050] An edge contour processing module 3 is configured to take each strong edge curve as a backbone and an anchor point, combine weak edge curve segments connected to the corresponding strong edge curve, and form a complete and continuous grid frame.

[0051] A direction angle analysis module 4 is configured to identify the grid frame in the gray-scale image by using a HoughLinesP rectangular detection algorithm, calculate a direction angle according to a grid frame straight line slope, and count an average value of all grid frame direction angles.

[0052] A sorting analysis module 5 is configured to sort the depth values of the identified grid center points in descending order of the direction angles, take a depth value of a grid center point corresponding to a first proportion value of the total number of the identified grids as a minimum depth value of a single-crystal superalloy plastic deformation layer for grinding processing, and take a depth value of a grid center point corresponding to a second proportion value of the total number of the identified grids as a maximum depth value of the single-crystal superalloy plastic deformation layer for grinding processing, wherein the first proportion value is less than the second proportion value.

[0053] A thickness analysis module 6 is configured to analyze a thickness value of a single-crystal superalloy plastic deformation region after grinding processing according to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of all grid direction angles, and a preset single-crystal superalloy material crystal angle identification threshold value of a plastic deformation region after grinding processing.

[0054] The edge curve processing module 2 in the embodiment comprises a preprocessing unit 201 configured to perform noise reduction preprocessing on the gray-scale image by using a threshold algorithm after converting the port cross-section image into a gray-scale image and before performing grid edge detection on the gray-scale image by using a Canny edge detection algorithm.

[0055] Embodiment 2

[0056] Referring to Figure 1A single crystal superalloy plastic deformation layer thickness identification method for grinding processing, comprising:

[0057] Step one, a scanning electron microscope is used to collect the port cross-section image of the single crystal superalloy material after grinding processing;

[0058] In this embodiment, the surface roughness Ra of the single crystal superalloy material after grinding processing is controlled to be not greater than 2.4 μm, and then the scanning electron microscope is used to observe it; before observation, the single crystal superalloy material to be observed is first placed in the center area of the sample area of the scanning electron microscope through the electric glue cloth, and faces the electron gun; the appropriate voltage is set in the controller to make the field of view clear and bright, and the spot size is adjusted to make the resolution above 500*400; then, the three steps of magnification, fine focusing and astigmatism correction are repeated until the magnification of the image meets the requirements and the image is clear, and the collected port cross-section image is saved through the computer as shown in Figure 3 .

[0059] Step two, the port cross-section image is converted into a gray scale image, and a threshold algorithm is used to pre-process the noise of the gray scale image to obtain a pre-processed image;

[0060] 2.1 first, the cvtcolor algorithm of opencv is used to convert the image into a gray scale image, if the picture saved by the scanning electron microscope is a gray scale image, this step can be skipped, or the gray scale value of each pixel point can be calculated through the following formula:

[0061]

[0062] In the formula, is the sample gray scale of the i-th pixel point of the image; , , and are the RGB values of the pixel point, , , and are the gray scale weights corresponding to the RGB values. In this embodiment, 0.299 is recommended as , 0.587 is recommended as , and 0.114 is recommended as .

[0063] 2.2 In order to further improve the image recognition effect, the GaussianBlur algorithm of opencv is used to enhance the grid boundary in the image by Gaussian, and the Gaussian kernel size of 5*5 is recommended, and the control parameter sigmax is 0. The enhanced image is shown in Figure 4 .

[0064] 2.3 Adaptive threshold processing is performed by a threshold algorithm, a threshold value is dynamically calculated according to local characteristics of different regions of an image, and the influence of uneven illumination is eliminated. It is recommended to select a gray threshold value of 180-255.

[0065] Step three, a grid edge detection is performed on the gray image by using a Canny edge detection algorithm, a weak edge curve with a gray gradient less than a first preset gradient threshold value and a strong edge curve with a gray gradient greater than a second preset gradient threshold value are obtained on the gray image; wherein the first preset gradient threshold value is less than the second preset gradient threshold value;

[0066] In this embodiment, a fine edge detection is performed on the image by using the Canny algorithm of opencv, it is recommended to select the first preset gradient threshold value (i.e. the weak edge detection gray threshold value) as 50 and the second preset gradient threshold value (the strong edge detection gray threshold value) as 150.

[0067] Step four, each strong edge curve is taken as a backbone and an anchor point, and the weak edge curve segments connected with the corresponding strong edge curve are merged to form a complete and continuous grid frame.

[0068] Step five, a HoughLinesP rectangle detection algorithm is used to identify the grid frame in the gray image, and a direction angle is calculated according to the slope of the grid frame straight line, and an average value of all grid frame direction angles is counted.

[0069] In this embodiment, the fine edge detection is performed on the image, and the HoughLinesP rectangle detection algorithm of opencv is used to detect the small edge frame of the crystal in the image, it is recommended that the distance resolution in the HoughLinesP rectangle detection algorithm is 1 pixel, the angle resolution is 1 degree resolution, the accumulator threshold value is 15 pixels, the minimum length of the line segment is 8 pixels, and the maximum allowed gap between points on the same straight line is 2 pixels. The crystal direction recognition result is as shown in Figure 5 .

[0070] In this embodiment, the direction of each grid identified is calculated and counted, and a grid direction detection statistical histogram (as shown in Figure 6 ) is drawn, if the recognition result is greater than 90 degrees, 90 is subtracted to make the angle distribution between [0, 90°], and then the average value of all grid direction angles is calculated, and the average value of the angle is taken as the crystal direction of the undeformed area of the single crystal high-temperature alloy material after grinding.

[0071] Step six, sort the identified grid center point depth values in descending order of the direction angle, take the grid center point depth value corresponding to the first proportion value of the total number of identified grids as the minimum depth value of the plastic deformation layer of the single crystal superalloy grinding processing, and take the grid center point depth value corresponding to the second proportion value of the total number of identified grids as the maximum depth value of the plastic deformation layer of the single crystal superalloy grinding processing, wherein the first proportion value is less than the second proportion value;

[0072] In this embodiment, the longitudinal depth value of the center region position of each identified crystal is recorded and sorted in descending order, the largest value is , followed by, and so on. The number of identified crystals is , the undeformed region depth threshold value and the deformed region coordinate threshold value are determined. The second proportion value is recommended to be selected , and the first proportion value is recommended to be selected .

[0073] Step seven, according to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of all grid direction angles, and the preset single crystal superalloy material plastic deformation region crystal angle identification threshold value after grinding processing, the thickness value of the single crystal superalloy material plastic deformation region after grinding processing is analyzed and obtained;

[0074] In this embodiment, the thickness value of the single crystal superalloy material plastic deformation region after grinding processing is analyzed and obtained according to , wherein is the thickness value of the single crystal superalloy material plastic deformation region after grinding processing, is the average value of all grid direction angles, is the preset single crystal superalloy material plastic deformation region crystal angle identification threshold value, the value is 15°, is the maximum depth value of the plastic deformation layer, is the minimum depth value of the plastic deformation layer.

[0075] The above is only a preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for identifying the thickness of a plastic deformation layer in grinding processing of a single crystal superalloy, characterized in that, The method comprises the following steps: Collecting a cut port cross-section image of a single-crystal high-temperature alloy material after grinding by using a scanning electron microscope; Converting the cut port cross-section image into a gray-scale image, and performing grid edge detection on the gray-scale image by using a Canny edge detection algorithm to obtain weak edge curves on the gray-scale image with a gray-scale gradient less than a first preset gradient threshold value, and strong edge curves with a gray-scale gradient greater than a second preset gradient threshold value; The first preset gradient threshold value is less than the second preset gradient threshold value; Taking each of the strong edge curves as a backbone and an anchor point, merging the weak edge curve segments connected to the corresponding strong edge curve to form a complete and continuous grid frame; Identifying the grid frame in the gray-scale image by using a HoughLinesP rectangle detection algorithm, and calculating a direction angle according to the slope of the grid frame straight line to statistically average all grid frame direction angles; According to the order of the direction angle from large to small, sorting the depth values of the identified grid center points, taking the depth value of the grid center point corresponding to a first proportion value of the total number of the identified grids as the minimum depth value of the plastic deformation layer of the single-crystal high-temperature alloy after grinding, and taking the depth value of the grid center point corresponding to a second proportion value of the total number of the identified grids as the maximum depth value of the plastic deformation layer of the single-crystal high-temperature alloy after grinding, wherein the first proportion value is less than the second proportion value; According to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of all grid direction angles, and a preset crystal angle recognition threshold value of the plastic deformation region of the single-crystal high-temperature alloy after grinding, the thickness value of the plastic deformation region of the single-crystal high-temperature alloy after grinding is obtained.

2. The method of claim 1, wherein the thickness of the plastically deformed layer is identified by a method comprising: After converting the cut port cross-section image into a gray-scale image, and before performing grid edge detection on the gray-scale image by using the Canny edge detection algorithm, the gray-scale image is preprocessed by using a threshold threshold algorithm. ​ 3. The method for identifying the thickness of the plastic deformation layer during grinding of single-crystal high-temperature alloys according to claim 1, characterized in that, When identifying the grid frame in the gray-scale image by using the HoughLinesP rectangle detection algorithm, the distance resolution in the HoughLinesP rectangle detection algorithm is 1 pixel, the angle resolution is 1 degree resolution, the accumulator threshold value is 15 pixels, the minimum length of the line segment is 8 pixels, and the maximum allowed gap between points on the same straight line is 2 pixels.

4. The method of claim 1, wherein the plastic deformation layer thickness is identified by a thickness of a single-crystal superalloy grinding plastic deformation layer. When calculating the average value of all grid frame direction angles, if the grid direction angle is greater than 90 degrees, 90 is subtracted to make the grid direction angle distributed between [0, 90°], and then the average value of all grid frame direction angles is calculated.

5. The method of claim 4, wherein the thickness of the plastically deformed layer is identified by a thickness of the single crystal superalloy grinding plastic deformation layer. The thickness value of the plastic deformation region of the single crystal superalloy material after grinding is obtained according to Analysis is obtained, wherein The thickness value of the plastic deformation region of the single crystal superalloy material after grinding is obtained according to The average value of all grid direction angles is The preset crystal angle identification threshold of the plastic deformation region of the single crystal superalloy material after grinding is The value is 15°, The maximum depth value of the plastic deformation layer is The minimum depth value of the plastic deformation layer is 6. A system for identifying the thickness of a plastic deformation layer in grinding of a single crystal superalloy, characterized by The method comprises the following steps: An image acquisition module is configured to collect a cut port cross-section image of a single-crystal high-temperature alloy material after grinding by using a scanning electron microscope; An edge curve processing module is configured to convert the cut port cross-section image into a gray-scale image, and perform grid edge detection on the gray-scale image by using a Canny edge detection algorithm to obtain weak edge curves on the gray-scale image with a gray-scale gradient less than a first preset gradient threshold value, and strong edge curves with a gray-scale gradient greater than a second preset gradient threshold value; The first preset gradient threshold value is less than the second preset gradient threshold value; Taking each of the strong edge curves as a backbone and an anchor point, merging the weak edge curve segments connected to the corresponding strong edge curve to form a complete and continuous grid frame; An edge profile processing module is configured to take each of the strong edge curves as a backbone and an anchor point, and combine the weak edge curve segments connected with the corresponding strong edge curve to form a complete and continuous grid frame. A direction angle analysis module is configured to identify the grid frame in the gray image by using a HoughLinesP rectangular detection algorithm, and calculate the direction angle according to the slope of the grid frame straight line, and statistically average the direction angle of all grid frames. An ordering analysis module is configured to order the depth values of the identified grid center points in descending order of the direction angle, take the depth value of the grid center point corresponding to a first proportion value of the total number of the identified grid as the minimum depth value of the plastic deformation layer of the single-crystal high-temperature alloy during grinding, and take the depth value of the grid center point corresponding to a second proportion value of the total number of the identified grid as the maximum depth value of the plastic deformation layer of the single-crystal high-temperature alloy during grinding, wherein the first proportion value is less than the second proportion value. A thickness analysis module is configured to analyze the thickness of the plastic deformation region of the single-crystal high-temperature alloy after grinding according to the minimum depth value of the plastic deformation layer, the maximum depth value of the plastic deformation layer, the average value of all grid direction angles, and a preset crystal angle recognition threshold of the plastic deformation region of the single-crystal high-temperature alloy after grinding.

7. The single crystal superalloy grinding-induced plastic deformation layer thickness identification system of claim 6, wherein, The edge curve processing module includes a preprocessing unit configured to convert the port cross-section image into a gray image, and perform noise reduction preprocessing on the gray image by using a threshold algorithm before performing grid edge detection on the gray image by using a Canny edge detection algorithm.

8. The single crystal superalloy grinding-induced plastic deformation layer thickness identification system of claim 6, wherein, In the direction angle analysis module, when the HoughLinesP rectangular detection algorithm identifies the grid frame in the gray image, the distance resolution in the HoughLinesP rectangular detection algorithm is 1 pixel, the angle resolution is 1 degree resolution, the accumulator threshold is 15 pixels, the minimum length of the line segment is 8 pixels, and the maximum allowed gap between points on the same straight line is 2 pixels.

9. The single crystal superalloy grinding-induced plastic deformation layer thickness identification system of claim 6, wherein, In the direction angle analysis module, when statistically averaging the direction angle of all grid frames, if the grid direction angle is greater than 90 degrees, subtract 90 to make the grid direction angle distributed between [0, 90°], and then calculate the average value of the direction angle of all grid frames.

10. The single crystal superalloy grinding process plastic deformation layer thickness identification system of claim 9, wherein, In the thickness analysis module, the thickness value of the plastic deformation region of the single crystal superalloy material after grinding is obtained according to Analysis obtains, wherein is the thickness value of the plastic deformation region of the single crystal superalloy material after grinding, is the average value of all grid direction angles, is a preset crystal angle recognition threshold of the plastic deformation region of the single crystal superalloy material after grinding, The value is 15°, is the maximum depth value of the plastic deformation layer, is the minimum depth value of the plastic deformation layer.

Images