A method, storage medium and device for detecting wear marks on the surface of a grinding workpiece

Abstract

The present invention relates to the field of surface defect detection, and in particular to a method, storage medium and device for detecting the quality of wear scars on the surface of a ground workpiece. It includes: obtaining the pixel depth characteristic value and the pixel width characteristic value of the wear scars on the surface to be detected according to the grayscale information corresponding to all target wear scars; generating the cross-sectional depth detection value and the cross-sectional curvature radius detection value of the wear scars on the surface to be detected according to the pixel depth characteristic value; using the cross-sectional depth detection value and the cross-sectional curvature radius detection value to evaluate and detect the quality of the wear scars on the surface to be detected. In the present invention, the grayscale information corresponding to all target wear scars is counted, and the grayscale mode in the grayscale information is used as the pixel depth characteristic value for characterizing the depth of most wear scars, and the cross-sectional depth detection value of the wear scars on the surface to be detected is generated. This value can characterize the approximate depth of all wear scar sections in the surface to be detected, and then evaluate the surface processing quality of the detected workpiece.

Description

Background Art

[0002] Grinding is a precision machining method that uses abrasive tools (such as grinding wheels) to cut workpieces. It removes material through the relative movement between the high-speed rotating abrasive tool and the workpiece to achieve the required dimensional accuracy, shape accuracy and surface quality. Grinding is widely used in machinery manufacturing, automotive industry, aerospace and other fields, especially for the finishing of hard materials.

[0003] At the same time, during the grinding process, due to the randomness of the abrasive particles on the surface of the grinding tool and the complexity of the grinding process, grinding will form micron-level wear marks (i.e., tiny cracks) on the surface of the workpiece, and the micro defects caused by these wear marks will cause local stress concentration on the surface of the titanium alloy and significantly reduce the service performance of the workpiece. How to better accurately and effectively evaluate and detect the wear marks on the surface of the workpiece after grinding is crucial to the evaluation of the workpiece processing quality. Summary of the invention

[0004] In view of the above technical problems, the technical solution adopted by the present invention is:

[0005] According to one aspect of the present invention, a method for detecting wear marks on a surface of a grinding workpiece is provided, the method comprising the following steps:

[0006] According to the topography information map used to represent the height information of the surface to be detected, grayscale information of the image area corresponding to each target wear mark in the topography information map is obtained; the target wear mark is a wear mark whose depth is greater than a preset depth; different heights in the topography information map are represented by different colors;

[0007] According to the grayscale information corresponding to all target wear marks, the pixel depth characteristic value and pixel width characteristic value of the wear marks on the surface to be detected are obtained; the pixel depth characteristic value is the grayscale mode in all grayscale information; the pixel width characteristic value is the average pixel width of the image area corresponding to all target wear marks;

[0008] Generate a cross-sectional depth detection value of the wear scar on the surface to be detected according to the pixel depth feature value;

[0009] Generate a cross-sectional curvature radius detection value of the wear scar on the surface to be detected according to the cross-sectional depth detection value and the pixel width characteristic value of the wear scar on the surface to be detected;

[0010] The wear scar quality of the surface to be tested is evaluated and tested using the section depth test value and the section curvature radius test value.

[0011] Furthermore, according to the pixel depth feature value, a cross-sectional depth detection value of the wear mark on the surface to be detected is generated, including:

[0012] According to the mapping relationship between the grayscale value corresponding to the grayscale mode and the actual depth information, a cross-sectional depth detection value of the wear mark on the surface to be detected is generated.

[0013] Furthermore, according to the cross-sectional depth detection value and the pixel width characteristic value of the wear scar on the surface to be detected, a cross-sectional curvature radius detection value of the wear scar on the surface to be detected is generated, including:

[0014] Generate a cross-sectional width detection value w of the wear scar on the surface to be detected according to a mapping relationship between the pixel width corresponding to the pixel width feature value and the actual width information;

[0015] According to the cross-sectional depth detection values ​​h and w of the wear scar on the surface to be detected, the cross-sectional curvature radius detection value ρ of the wear scar on the surface to be detected is generated; ρ meets the following conditions:

[0016] .

[0017] Furthermore, the method also includes:

[0018] According to the topography information map used to represent the height information of the surface to be detected, an image area corresponding to each target wear mark in the topography information map is obtained;

[0019] Generate the average wear scar area ratio and the average wear scar perimeter ratio of the surface to be tested according to the morphology information map and the pixel information of the image area corresponding to each target wear scar;

[0020] Generate the average value of the wear scar aspect ratio and the average value of the wear scar fractal dimension of the surface to be detected according to the pixel information of the image area corresponding to each target wear scar;

[0021] The wear scar quality of the surface to be tested is evaluated and tested using the average wear scar area ratio, the average wear scar perimeter ratio, the average wear scar aspect ratio, the average wear scar fractal dimension, the cross-sectional depth test value, and the cross-sectional curvature radius test value of the surface to be tested;

[0022] The mean value d of the wear scar fractal dimension satisfies the following conditions:

[0023] ;

[0024] Where n is the total number of target wear marks on the surface to be tested; i 2 is the total number of boundary pixels in the image area corresponding to the i-th target wear scar; i 1 is the total number of remaining pixels excluding boundary pixels in the image area corresponding to the i-th target wear scar.

[0025] Furthermore, the average value a of the wear scar area ratio, the average value b of the wear scar perimeter ratio, and the average value c of the wear scar aspect ratio of the surface to be tested respectively meet the following conditions:

[0026] ; ; ;

[0027] Among them, S i is the total number of pixels in the image area corresponding to the i-th target wear scar; S z is the total number of pixels of the morphological information map; P i is the total number of boundary pixels in the image area corresponding to the i-th target wear scar; P z is the total number of boundary pixels of the morphological information map; Q iw is the total number of pixels in the width direction of the circumscribed rectangle of the image area corresponding to the i-th target wear mark; Q ic is the total number of pixels in the length direction of the circumscribed rectangle of the image area corresponding to the i-th target wear mark.

[0028] Further, according to the topography information map used to represent the height information of the surface to be detected, an image area corresponding to each target wear mark in the topography information map is obtained, including:

[0029] The morphology information map is input into the target Yolov8 algorithm model to generate the image area corresponding to each target wear mark in the morphology information map; Gaussian filtering is used in the training samples of the target Yolov8 algorithm model to remove the small point-like wear mark area in the morphology information map.

[0030] Further, according to the topography information map used to represent the height information of the surface to be detected, the grayscale information of the image area corresponding to each target wear mark in the topography information map is obtained, including:

[0031] According to the boundary position information of the image area corresponding to each target wear mark, a sub-topography image area corresponding to each target wear mark is intercepted from the topography information;

[0032] The sub-topography image area corresponding to each target wear mark is converted into the grayscale information of the image area corresponding to each target wear mark.

[0033] Furthermore, before inputting the morphological information graph into the target Yolov8 algorithm model, the method further includes:

[0034] Use white light interferometer, atomic force microscope or ultra-depth camera to collect the topographic information of the surface to be inspected.

[0035] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for detecting wear mark quality on the surface of a ground workpiece is implemented.

[0036] According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for detecting wear mark quality on the surface of a ground workpiece when executing the computer program.

[0037] The present invention has at least the following beneficial effects:

[0038] In the present invention, the surface undulation of the position of the surface to be detected is reflected by using different colors to represent the morphological information map of different heights. At the same time, since the depth of the wear mark is bound to be significantly different from the depth of the surrounding non-wear mark area, the image area corresponding to the wear mark can also be segmented and the corresponding grayscale information can be obtained, and different grayscale values ​​are used to represent the different height values ​​at the corresponding position. On this basis, since the grinding conditions of the workpiece surface in the same grinding stage are roughly the same, the depth and shape of most of the wear marks on the workpiece surface after grinding will have certain similarities. At the same time, due to the randomness of the abrasive particles on the surface of the grinding tool and the complexity of the grinding process, a small part of the wear marks on the workpiece surface after grinding will have special depths and shapes, and there are certain differences. Based on this, the present invention counts the grayscale information corresponding to all target wear marks, and uses the grayscale mode in the grayscale information as the pixel depth feature value for characterizing the depth of most wear marks, and generates the cross-sectional depth detection value of the wear marks on the surface to be detected. This value can characterize the approximate depth of all wear mark sections in the surface to be detected, and then evaluate the surface processing quality of the detected workpiece.

[0039] In addition, the pixel width average of the image area corresponding to all target wear scars is used as the approximate width information of all wear scar sections in the surface to be detected. Then, the cross-sectional curvature radius detection value of the wear scar is obtained based on the depth and width values. This value can reflect whether the cross-sectional shape of the wear scar is sharp or gentle, and thus the degree of stress concentration caused by the wear scar can be better evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A flow chart of a method for detecting wear marks on a surface of a grinding workpiece provided by an embodiment of the present invention;

[0042] Figure 2A schematic diagram of the training process of the target Yolov8 algorithm model provided in an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the segmentation result of the target Yolov8 algorithm model provided in an embodiment of the present invention;

[0044] Figure 4 A schematic diagram illustrating six evaluation and detection parameters provided in an embodiment of the present invention;

[0045] Figure 5 A schematic diagram of feasibility analysis corresponding to the topography images of the titanium alloy surface randomly selected at three different points after processing at the same wear stage in the CFBG process provided by an embodiment of the present invention, wherein the binary images of the three topography images are as follows Figure 5 As shown in (a), Figure 5 (b) to (e) in the figure respectively represent the histograms of the average wear scar area percentage, the average wear scar perimeter percentage, the average wear scar aspect ratio and the average wear scar fractal dimension corresponding to the morphological images obtained at three different points;

[0046] Figure 6 A schematic diagram of feasibility analysis corresponding to the topography images of the titanium alloy surface randomly selected at three different points after processing at the same wear stage during the CBG process provided by the embodiment of the present invention, wherein the binary images of the three topography images are as follows Figure 6 As shown in (a), Figure 6 (b) to (e) in the figure respectively represent the histograms of the average wear scar area percentage, the average wear scar perimeter percentage, the average wear scar aspect ratio and the average wear scar fractal dimension corresponding to the morphological images obtained at three different points;

[0047] Figure 7 A schematic diagram of feasibility verification of cross-sectional depth detection values ​​in CFBG and CBG processes provided by an embodiment of the present invention, wherein the morphological information (including color information) of the wear scar area corresponding to CBG and CFBG respectively, such as Figure 7 (a) and Figure 7 As shown in (d) in , the corresponding grayscale statistical histogram in CBG is as follows Figure 7 As shown in (b) in the figure, the grayscale statistical histogram of wear scars in CFBG is as follows: Figure 7 As shown in (c);

[0048] Figure 8 A schematic diagram of geometric calculation of the cross-sectional curvature radius detection value provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0050] As a possible embodiment of the present invention, Figure 1 As shown, a method for detecting the wear mark quality of a grinding workpiece surface is provided, and the method comprises the following steps:

[0051] S100: According to the morphology information map used to represent the height information of the surface to be detected, grayscale information of the image area corresponding to each target wear mark in the morphology information map is obtained. The target wear mark is a wear mark with a depth greater than a preset depth. Different heights in the morphology information map are represented by different colors.

[0052] The preset depth needs to be determined according to the actual use field. Since the definition of surface defects of different products is different, for example, in some scenes with low precision requirements, deeper wear marks are required to be considered as target wear marks, while in some scenes with high precision requirements, shallower wear marks will be considered as target wear marks. Therefore, the preset depth needs to be determined by the technicians according to the actual use scenario.

[0053] S100 includes:

[0054] S101: Use a white light interferometer, an atomic force microscope, or an ultra-depth-of-field camera to collect a morphology information map of the surface to be inspected.

[0055] The above-mentioned white light interferometer, atomic force microscope or super depth of field camera can be used to obtain the contour information of the workpiece representing the surface to be detected, and then obtain the topography information map in this embodiment. And because the white light interferometer, atomic force microscope or super depth of field camera have different acquisition accuracy, the height information resolution of the topography information map obtained will also be different. In actual use scenarios, it can be selected according to actual needs.

[0056] In this embodiment, a white light interferometer is used to obtain the height point cloud information of the surface to be detected, and finally a morphology information map is formed using different colors to represent different height information. Specifically, Figure 3 As shown in (a), the closer to the dark blue, the lower the surface height, that is, the wear scar area.

[0057] S102: Input the morphology information map into the target Yolov8 algorithm model to generate an image area corresponding to each target wear mark in the morphology information map. Use Gaussian filtering in the training samples of the target Yolov8 algorithm model to remove the small point-shaped wear mark areas in the morphology information map.

[0058] In order to better reflect the wear mark area in this embodiment, the segmented image is also converted into a binary image.

[0059] The YOLO algorithm has the characteristics of fast response speed, high accuracy and strong generalization ability. It has become a very popular algorithm and is widely used in surface polishing, additive manufacturing and defect detection in processing. The Yolov8 algorithm uses advanced data enhancement technology (MixUp and CutMix) to improve the robustness and generalization ability of the model, and each variant of the Yolov8 series is optimized for its respective task to ensure high performance and high accuracy. In addition, these models are also compatible with various operating modes, including reasoning, verification, training and output, which is convenient for use in different stages of deployment and development. Therefore, this embodiment chooses to use the Yolov8 algorithm to segment the wear marks.

[0060] In order to make the target Yolov8 algorithm model have higher segmentation accuracy, the initial Yolov8 algorithm model can be trained by collecting training samples in the corresponding grinding field. In this embodiment, the grinding surface morphology image generated when the TC4 titanium alloy is ground by a CNC grinder is used as a training sample for explanation. The specific training process is as follows: Figure 2 As shown:

[0061] (1) Use white light interferometry to collect images of the surface morphology of titanium alloy after grinding with abrasive tools at different wear stages (e.g. Figure 2 Labelme was used to annotate the wear scar areas in the images (as shown in (a)). Figure 2 The target wear mark depth can be set according to actual needs. Convert the marked Json file into a txt file (as shown in (b)). Figure 2 As shown in (c) in the figure), it is convenient to train the initial Yolov8 model.

[0062] (2) The Yolov8 algorithm is used to train the dataset (864 images) (e.g. Figure 2 As shown in (d) in Figure 1, the ratio of training set to validation set is 8:2. The Epoch is set to 200, the Batch is set to 16, and other hyper parameters are shown in Table 1.

[0063] Table 1

[0064]

[0065] (3) The target Yolov8 algorithm model obtained after the above training can have a good segmentation effect. The corresponding segmented morphological image is as follows: Figure 2 As shown in (e) in , the segmented image is then processed and converted into a binary image, such as Figure 2 As shown in (f) in .

[0066] like Figure 3 The following is the result of segmentation using the target Yolov8 algorithm model after training. Figure 3 (a) is the original input picture of the algorithm. Figure 3 (b) in the figure is the labeled picture. Figure 3 (c) in the figure is a binary image after segmentation by the algorithm. It can be seen in the figure that the wear mark area and the marked position in the original image have been completely recognized by the algorithm, which shows that the algorithm has a good effect in identifying the wear marks on the surface morphology after grinding of the abrasive tool. It can also be seen that the algorithm also segments out some small unmarked dot-like areas. Combining the original image, it can be known that this part belongs to the wear mark area, but this area is ignored during the marking process, which will affect the accuracy of the algorithm to a certain extent. However, considering that the impact of such small wear marks is extremely small in actual use, it is generally not considered too much for analysis, so the segmentation of the model can also achieve filtering processing to avoid filtering the image again in subsequent image processing to remove these small dot-like wear marks.

[0067] In order to better achieve the purpose of filtering, Gaussian filtering can be used for downsampling when preparing training samples in the early stage to remove the small point-like wear marks in the morphology information map.

[0068] Precision, Recall, and F1 values ​​are important indicators for evaluating the performance of classification models. After the training in this embodiment, the Precision value of the target Yolov8 algorithm model is 0.85, the Recall value is 0.72, and the F1 value is 0.78, which shows that the robustness and generalization ability of the algorithm are good, and the performance of the algorithm in this task is relatively superior.

[0069] S103: According to the boundary position information of the image area corresponding to each target wear mark, a sub-topography image area corresponding to each target wear mark is intercepted from the topography information.

[0070] Specifically, this step can be done by using Figure 2 In (e) and (f), the position information of the target wear scar image area is segmented to form a mask, and the original topography image (i.e. Figure 2 (a) in the figure is intercepted to obtain the color information of the morphology, so as to form a sub-morphology image area as shown in Figure 2 As shown in (g) in .

[0071] S104: Convert the sub-topography image region corresponding to each target wear mark into grayscale information of the image region corresponding to each target wear mark.

[0072] S200: According to the grayscale information corresponding to all target wear marks, the pixel depth characteristic value and the pixel width characteristic value of the wear marks on the surface to be detected are obtained. The pixel depth characteristic value is the grayscale mode in all grayscale information. The pixel width characteristic value is the average pixel width of the image area corresponding to all target wear marks.

[0073] In the sub-topography image area of ​​this embodiment, different colors are used to represent the topography information diagrams of different heights to reflect the depth information corresponding to the wear marks. Therefore, the grayscale values ​​of different pixels can represent different height values ​​at the corresponding pixel positions. On this basis, since the grinding conditions of the workpiece surface in the same grinding stage are roughly the same, the depth and shape of most of the wear marks on the workpiece surface after grinding will have a certain similarity. At the same time, due to the randomness of the abrasive particles on the surface of the grinding tool and the complexity of the grinding process, a small part of the wear marks on the workpiece surface after grinding will have a special depth and shape, and there will be a certain difference.

[0074] Based on this, the present invention counts the grayscale information corresponding to all target wear scars, and uses the grayscale mode in the grayscale information as the pixel depth feature value used to characterize the depth of most wear scars. In addition, the pixel width mean of the image area corresponding to all target wear scars is used as the approximate width information used to characterize all wear scar sections in the surface to be detected.

[0075] S300: Generate a cross-sectional depth detection value of the wear mark on the surface to be detected according to the pixel depth feature value.

[0076] S300 includes:

[0077] S301: Generate a cross-sectional depth detection value of the wear scar on the surface to be detected according to a mapping relationship between the grayscale value corresponding to the grayscale mode and the actual depth information.

[0078] S400: Generate a cross-sectional curvature radius detection value of the wear scar on the surface to be detected according to the cross-sectional depth detection value and the pixel width characteristic value of the wear scar on the surface to be detected.

[0079] Through the conversion relationship between the camera coordinate system and the real world coordinate system, the mapping relationship between pixels and actual size can be obtained. Therefore, the approximate cross-sectional depth and cross-sectional width of all wear scars in the surface to be detected can be roughly reflected based on the pixel depth characteristic value and the pixel width characteristic value. Furthermore, these two values ​​can characterize the approximate depth and width of all wear scar cross sections in the surface to be detected. Then, the cross-sectional curvature radius detection value of the wear scar is obtained based on the depth and width values.

[0080] The specific S400 includes:

[0081] S401: Generate a cross-sectional width detection value w of the wear mark on the surface to be detected according to a mapping relationship between the pixel width corresponding to the pixel width characteristic value and the actual width information.

[0082] S402: Generate a cross-sectional curvature radius detection value ρ of the wear scar on the surface to be detected based on the cross-sectional depth detection values ​​h and w of the wear scar on the surface to be detected. ρ meets the following conditions:

[0083] .

[0084] The calculation formula of ρ in this embodiment can be calculated according to Figure 8 The geometric relationship is inferred from the one shown in .

[0085] S500: Use the section depth detection value and the section curvature radius detection value to evaluate and detect the wear scar quality of the surface to be detected.

[0086] Since the depth of the wear scar can reflect the impact of the wear scar on the actual workpiece performance, the cross-sectional depth test value can be used to evaluate the impact of the wear scar on the quality of the surface to be tested. At the same time, the cross-sectional curvature radius test value can also reflect whether the cross-sectional shape of the wear scar is sharp or gentle, and thus better evaluate the degree of stress concentration caused by the wear scar.

[0087] As another possible embodiment of the present invention, the method further includes:

[0088] S600: According to the topography information map used to represent the height information of the surface to be detected, an image area corresponding to each target wear mark in the topography information map is obtained.

[0089] S700: Generate an average wear scar area ratio and an average wear scar perimeter ratio of the surface to be detected according to the morphology information map and pixel information of the image area corresponding to each target wear scar.

[0090] S800: Generate a mean value of the wear scar aspect ratio and a mean value of the wear scar fractal dimension of the surface to be inspected according to pixel information of the image region corresponding to each target wear scar.

[0091] Specifically, Figure 4 As shown in the figure, the average wear scar area ratio a, the average wear scar perimeter ratio b and the average wear scar aspect ratio c of the surface to be tested meet the following conditions:

[0092] . . .

[0093] Among them, S i is the total number of pixels in the image area corresponding to the i-th target wear scar. z is the total number of pixels of the morphological information map. i is the total number of boundary pixels in the image area corresponding to the i-th target wear scar. z is the total number of boundary pixels of the morphological information map. iw Q is the total number of pixels in the width direction of the circumscribed rectangle of the image area corresponding to the i-th target wear mark. ic is the total number of pixels in the length direction of the circumscribed rectangle of the image area corresponding to the i-th target wear mark.

[0094] like Figure 4 As shown in the figure, the mean fractal dimension d of the wear scar satisfies the following conditions:

[0095] .

[0096] Where n is the total number of target wear marks on the surface to be tested. 2 is the total number of boundary pixels in the image area corresponding to the i-th target wear scar. 1 is the total number of remaining pixels excluding boundary pixels in the image area corresponding to the i-th target wear scar.

[0097] S900: The wear scar quality of the surface to be tested is evaluated and tested using the average wear scar area ratio, the average wear scar perimeter ratio, the average wear scar aspect ratio, the average wear scar fractal dimension, the cross-sectional depth detection value, and the cross-sectional curvature radius detection value of the surface to be tested.

[0098] When the above-mentioned multiple parameters are used for evaluation and detection, the influence of the wear marks on the quality of the workpiece can be determined by setting a corresponding threshold for each parameter.

[0099] The four evaluation parameters of the wear scar area ratio average, the wear scar perimeter ratio average, the wear scar aspect ratio average, and the wear scar fractal dimension average in this embodiment mainly describe the state of the wear scar from the surface morphology level of the wear scar. The two parameters of the cross-sectional depth detection value and the cross-sectional curvature radius detection value mainly describe the state of the wear scar from the cross-sectional morphology level of the wear scar. Therefore, through multiple parameters in two dimensions, the influence of the wear scar on the surface quality to be detected can be described in more detail.

[0100] Specifically, the four evaluation parameters of the wear scar area ratio, the wear scar perimeter ratio, the wear scar aspect ratio, and the wear scar fractal dimension in this embodiment can respectively represent the following physical meanings of the target wear scar:

[0101] The average wear scar area ratio can reflect the number and size of target wear scars on the surface to be tested.

[0102] The mean value of the wear scar perimeter ratio and the mean value of the wear scar area ratio can also reflect the number and size of the wear scar defects (target wear scars) in the surface to be detected. At the same time, the difference between the mean value of the wear scar perimeter ratio and the mean value of the wear scar area ratio is that the mean value of the wear scar perimeter ratio may be greater than 1. Based on this, the mean value of the wear scar perimeter ratio can also be used to reflect whether the wear scar defects in the surface to be detected are roughly in the shape of a convex function or a concave function. Usually, when the mean value of the wear scar perimeter ratio is greater than 1, it can be said that the wear scar defects in the surface to be detected are roughly in the shape of a concave function. These concave function wear scar shapes are usually caused by the superposition of two wear scars. Therefore, the mean value of the wear scar perimeter ratio can also be used to reflect the superposition of wear scar defects in the surface to be detected. Usually, the superposition of wear scars will also increase the depth and size of wear scars to a greater extent, thereby causing more serious impact on the surface to be detected.

[0103] The average aspect ratio of the wear scar can reflect whether the general shape of the target wear scar in the surface to be tested is slender or wide and short. Generally, the slender wear scar shape will cause greater stress concentration.

[0104] The mean value of the fractal dimension of the wear scar can reflect the complexity of the boundary shape of the target wear scar in the surface to be detected. The larger the value, the more complex the boundary shape of the target wear scar, that is, there will be more concave and convex shapes in the boundary, which will lead to greater stress concentration. On the contrary, the smaller the value, the smoother the boundary of the target wear scar, which will reduce the stress concentration.

[0105] In this embodiment, the surface of TC4 titanium alloy was ground by a CNC grinder using two grinding methods, namely, creep feed (CFBG) and conventional grinding (CBG), to verify the feasibility of the above evaluation parameters. Specifically, the feed speed selected in this grinding experiment was 100 mm / min and the grinding depth was 0.51 mm. A grinding tool with a grain size of 80# and a width of 10 mm of aluminum oxide abrasive was selected for the grinding experiment, and the specific grinding parameter selection is shown in Table 2.

[0106] Table 2

[0107]

[0108] In the CFBG process, after processing at the same wear stage, the topography images of the titanium alloy surface at three different points were randomly selected, and then segmented using the target Yolov8 algorithm model to obtain its binary image as shown in Figure 5 As shown in (a) in . Figure 5 (b) to (e) in the figure represent the average wear scar area percentage, average wear scar perimeter percentage, average wear scar aspect ratio and average wear scar fractal dimension corresponding to the morphological images obtained at three different points. It can be seen from the figure that the differences between the average wear scar area percentage, average wear scar perimeter percentage, average wear scar aspect ratio and average wear scar fractal dimension are 0.004, 0.04, 0.02 and 0.038 respectively. Compared with the value range of the above corresponding parameters, these four parameters remain relatively stable, which also shows that the wear scar features at different positions in the same wear stage have strong similarities. This also verifies that the above four evaluation parameters are feasible in CFBG and can be used in the evaluation of surface wear scars.

[0109] At the same time, in the CBG process, after processing at the same wear stage, the topography images of the titanium alloy surface at three different points were randomly selected, and then segmented using the target Yolov8 algorithm model to obtain its binary image as shown in Figure 6 As shown in (a), Figure 6 (b) to (e) in the figure represent the average values ​​of the wear scar area percentage, the average value of the wear scar perimeter percentage, the average value of the wear scar aspect ratio and the average value of the wear scar fractal dimension corresponding to the morphological images obtained at three different points. It can be seen from the figure that the average values ​​of the wear scar area percentage, the average value of the wear scar perimeter percentage, the average value of the wear scar aspect ratio and the average value of the wear scar fractal dimension at different positions are about 0.025, 0.265, 0.41 and 1.736 respectively. The differences of these characteristic parameters in different regions are relatively low. It can be considered that the surface characteristics of the titanium alloy morphology in different regions have great similarity, which also proves that the four evaluation parameters proposed are relatively feasible and can be used in the evaluation of surface wear scars.

[0110] In addition, in the CFBG and CBG processes, the topography images of the titanium alloy surface at three different points were randomly selected after processing at the same wear stage, and then segmented using the target Yolov8 algorithm model, and the topography information (including color information) of the wear scar area was obtained after subsequent processing, such as Figure 7 (a) and Figure 7 As shown in (d) in .

[0111] Then the grayscale information of all wear scar areas is counted, and the corresponding grayscale statistical histogram in CBG is as follows: Figure 7 As shown in (b) in the figure, the grayscale statistical histogram of wear scars in CFBG is as follows: Figure 7As shown in (c) in the figure. The horizontal axis in the grayscale histogram is the corresponding grayscale value, and the vertical axis is the number of pixels of the corresponding grayscale value. In this embodiment, the grayscale value (peak skewness) corresponding to the wear scar peak is used as the wear scar depth feature. It can be seen in the figure that under the same wear conditions, the peak values ​​of the grayscale corresponding to different positions have large differences, which indicates that the number of wear scars and the size of the wear scar area are different. However, the grayscale peak skewness corresponding to different wear scars is basically the same (the same in CBG and CFBG), which indicates that in the same abrasive wear stage, the depth of the wear scar is basically the same, and the corresponding wear scar characteristics under different grinding methods are different. This shows that it is feasible to use the grayscale of the wear scar to characterize the wear scar depth. This also verifies that the above-mentioned evaluation parameter of the cross-sectional depth detection value is feasible in CBG and CFBG, and can be used in the evaluation of surface wear scars.

[0112] Again, the cross-sectional curvature radius detection value in this embodiment is an evaluation parameter of the cross-sectional shape of the wear scar generated based on the cross-sectional depth detection value and combined with the cross-sectional width detection value, so as to more comprehensively describe the cross-sectional shape of the wear scar, and further more comprehensively detect the quality of the workpiece.

[0113] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0114] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0115] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0116] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0117] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0118] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0119] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0120] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0121] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0122] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0123] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface. In addition, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0124] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0125] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0126] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0127] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0128] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0129] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0130] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0131] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0132] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for detecting the wear scar quality of a grinding workpiece surface, characterized in that: The method comprises the following steps: According to the topography information map used to represent the height information of the surface to be detected, grayscale information of the image area corresponding to each target wear mark in the topography information map is obtained; the target wear mark is a wear mark with a depth greater than a preset depth; different heights in the topography information map are represented by different colors; According to the grayscale information corresponding to all the target wear marks, the pixel depth characteristic value and the pixel width characteristic value of the wear marks on the surface to be detected are obtained; The pixel depth feature value is the grayscale mode of all grayscale information; the pixel width feature value is the average pixel width of the image area corresponding to all target wear marks; Generating a cross-sectional depth detection value of the wear scar on the surface to be detected according to the pixel depth feature value; Generate a cross-sectional curvature radius detection value of the wear scar on the surface to be detected according to the cross-sectional depth detection value and the pixel width characteristic value of the wear scar on the surface to be detected; Using the cross-sectional depth detection value and the cross-sectional curvature radius detection value, evaluating and detecting the wear scar quality of the surface to be detected; According to the topography information map used to represent the height information of the surface to be detected, an image area corresponding to each target wear mark in the topography information map is obtained; Generate the average wear scar area ratio and the average wear scar perimeter ratio of the surface to be detected according to the morphology information map and the pixel information of the image area corresponding to each target wear scar; Generate a mean value of the wear scar aspect ratio and a mean value of the wear scar fractal dimension of the surface to be detected according to pixel information of the image area corresponding to each target wear scar; The wear scar quality of the surface to be tested is evaluated and tested using the average wear scar area ratio, the average wear scar perimeter ratio, the average wear scar aspect ratio, the average wear scar fractal dimension, the cross-sectional depth detection value, and the cross-sectional curvature radius detection value of the surface to be tested; The wear scar fractal dimension mean d satisfies the following conditions: ； Where n is the total number of target wear marks on the surface to be tested; i 2 is the total number of boundary pixels in the image area corresponding to the i-th target wear scar; i 1 is the total number of remaining pixels excluding boundary pixels in the image area corresponding to the i-th target wear scar; The average value a of the wear scar area ratio, the average value b of the wear scar perimeter ratio and the average value c of the wear scar aspect ratio of the surface to be tested respectively meet the following conditions: ； ； ； Among them, S i is the total number of pixels in the image area corresponding to the i-th target wear scar; S z is the total number of pixels of the morphological information map; P i is the total number of boundary pixels in the image area corresponding to the i-th target wear scar; P z is the total number of boundary pixels of the morphological information map; Q iw is the total number of pixels in the width direction of the circumscribed rectangle of the image area corresponding to the i-th target wear mark; Q ic is the total number of pixels in the length direction of the circumscribed rectangle of the image area corresponding to the i-th target wear mark.

2. The method according to claim 1, characterized in that Generating a cross-sectional depth detection value of the wear scar on the surface to be detected according to the pixel depth feature value includes: According to the mapping relationship between the grayscale value corresponding to the grayscale mode and the actual depth information, a cross-sectional depth detection value of the wear scar on the surface to be detected is generated.

3. The method according to claim 1, characterized in that: Generating a cross-sectional curvature radius detection value of the wear scar on the surface to be detected according to the cross-sectional depth detection value and the pixel width characteristic value of the wear scar on the surface to be detected, including: Generate a cross-sectional width detection value w of the wear scar on the surface to be detected according to a mapping relationship between the pixel width corresponding to the pixel width characteristic value and the actual width information; According to the cross-sectional depth detection values ​​h and w of the wear scar on the surface to be detected, a cross-sectional curvature radius detection value ρ of the wear scar on the surface to be detected is generated; ρ meets the following conditions: 。 4. The method according to claim 1, characterized in that: According to the topography information map used to represent the height information of the surface to be detected, an image area corresponding to each target wear mark in the topography information map is obtained, including: The morphology information map is input into the target Yolov8 algorithm model to generate an image area corresponding to each target wear mark in the morphology information map; Gaussian filtering is used in the training samples of the target Yolov8 algorithm model to remove the small point-like wear mark areas in the morphology information map.

5. The method according to claim 4, characterized in that According to the topography information map used to represent the height information of the surface to be detected, the grayscale information of the image area corresponding to each target wear mark in the topography information map is obtained, including: According to the boundary position information of the image area corresponding to each target wear mark, a sub-topography image area corresponding to each target wear mark is intercepted from the topography information; The sub-topography image area corresponding to each target wear mark is converted into the grayscale information of the image area corresponding to each target wear mark.

6. The method according to claim 4, characterized in that Before inputting the morphological information graph into the target Yolov8 algorithm model, the method further includes: A white light interferometer, an atomic force microscope or an ultra-depth-of-field camera is used to collect a topographic information map of the surface to be detected.

7. A non-transitory computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for detecting wear mark quality on the surface of a ground workpiece as claimed in any one of claims 1 to 6 is implemented.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the computer program, the method for detecting wear mark quality on the surface of a ground workpiece according to any one of claims 1 to 6 is implemented.

Images