Bearing corrosion degree evaluation system, method, equipment and medium

Abstract

The invention discloses a bearing corrosion degree evaluation system, method and device and a medium, and relates to the technical field of computers, and the system comprises a camera whose optical axis passes through the axis of a bearing and is perpendicular to the plane of the bearing, and the camera is used for shooting a plurality of bearing images corresponding to the current bearing; the plurality of bearing images are respectively corresponding images before and after the current bearing horizontally rotates for a plurality of times by taking the axis of the bearing as a rotation center; the total rotation degree of the horizontal rotation is 360 degrees; the image processing software platform is used for extracting a plurality of bearing inner ring images from the plurality of bearing images, and automatically counting the corrosion area of each bearing inner ring image based on a pixel quantity statistical mode to obtain the corrosion degree of the bearing, and calculating the average value of the plurality of bearing corrosion degrees to obtain the final inner ring corrosion degree of the current bearing. According to the invention, the bearing corrosion degree evaluation precision can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly relates to a bearing rust degree evaluation system, method, device and medium. Background Art

[0002] Currently, the evaluation method for the rust degree of bearings mainly relies on visual inspection, and the test results given are usually "pass" and "fail". Another method is to use the transparent grid method to estimate the proportion of the rust area of the bearing. However, this method is relatively cumbersome to operate, and there is also a possibility of missing the counted points during the actual operation process.

[0003] First of all, the transparent grid method can only provide a rough proportion of the rust area. For some rust areas with complex shapes or irregular distributions, the accuracy of the estimation will be greatly affected. Using the transparent grid method requires manually placing the grid on the bearing surface and counting the number of grids occupied by the rust area one by one. For bearings with large areas or complex rust conditions, this process is very time-consuming and error-prone. After counting the number of grids in the rust area, a series of data processing and calculations are still required to obtain the final proportion of the rust area.

[0004] In addition, the transparent grid method is mainly applicable to planes or relatively regular geometric shapes. For some complex curved surfaces in the bearing, it will be very difficult to place the grid and count the rust area. As a result, the evaluation results lack obvious differences when distinguishing different anti-rust schemes.

[0005] In summary, how to improve the evaluation accuracy of the bearing rust degree is an urgent problem to be solved currently. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a bearing rust degree evaluation system, method, device and medium, which can improve the evaluation accuracy of the bearing rust degree. The specific solutions are as follows:

[0007] In a first aspect, the present application discloses a bearing rust degree evaluation system, including:

[0008] A camera whose optical axis passes through the bearing axis and is perpendicular to the bearing plane, used to take a plurality of bearing images corresponding to the current bearing; the plurality of bearing images are respectively the images corresponding to the current bearing before and after horizontally rotating several times with the bearing axis as the rotation center; the total rotation degree of the horizontal rotation is 360°;

[0009] An image processing software platform, used to extract a plurality of bearing inner ring images from the plurality of bearing images, automatically count the rust area of each bearing inner ring image based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of the plurality of bearing rust degrees to obtain the final inner ring rust degree of the current bearing.

[0010] Among them, the image processing software platform is further configured to extract a plurality of inner ring images of the bearing from the plurality of bearing images based on geometric Boolean operations.

[0011] Among them, the image processing software platform is specifically configured to perform grayscale processing on each of the inner ring images of the bearing to obtain a grayscale image of the inner ring of the bearing, and perform binarization processing on each of the grayscale images of the inner ring of the bearing to automatically count the rust area of each of the inner ring images of the bearing based on the pixel quantity statistics method to obtain the bearing rust degree.

[0012] Among them, the image processing software platform is specifically further configured to obtain a first image in which the inner ring area of the bearing is white and other areas are black by adjusting the second binarization threshold, and use the number of white pixels in the first image to represent the first area of the inner ring area of the bearing;

[0013] Select a partial rust area from the inner ring image of the bearing, obtain a second image in which the partial rust area is black-displayed in the same way as the partial rust area in the inner ring image of the bearing by adjusting the first binarization threshold of the first image, and use the number of black pixels in the inner ring area of the second image to represent the second area of the total rust area;

[0014] Calculate the product of the ratio of the second area to the first area and 100 as the bearing rust degree of each inner ring grayscale image of the bearing; the ratio is the ratio of the second area to the first area.

[0015] Among them, the image processing software platform is specifically further configured to evenly divide the inner ring area in the inner ring image of the bearing into a plurality of divided areas, and select a partial rust area from each of the divided areas, and obtain the second image in which all the partial rust areas are black-displayed in the same way as the partial rust area in the inner ring image of the bearing by adjusting the first binarization threshold in the inner ring image of the bearing, and use the number of black pixels in the inner ring area of the second image to represent the second area of the total rust area.

[0016] Among them, the bearing rust degree evaluation system further includes:

[0017] A circular bearing support with a bracket diameter equal to the bearing diameter, for placing the current bearing;

[0018] A spirit level, for adjusting the current bearing to be parallel to the horizontal plane.

[0019] Wherein, the current bearing is the bearing obtained by drying the bearing after ultrasonic cleaning in an incubator at the target temperature; the bearing after ultrasonic cleaning is the bearing obtained by placing the wiped bearing in a target container filled with a target liquid and cleaning it in an ultrasonic cleaning device.

[0020] In a second aspect, the present application discloses a method for evaluating the rust degree of a bearing, which is applied to a bearing rust degree evaluation system. The system includes a camera and an image processing software platform. The optical axis of the camera passes through the axis of the bearing and is perpendicular to the bearing plane. The method includes:

[0021] Taking a plurality of bearing images corresponding to the current bearing through the camera; the plurality of bearing images are the images corresponding to the current bearing before and after horizontally rotating a plurality of times with the axis of the bearing as the rotation center; the total rotation degree of the horizontal rotation is 360°;

[0022] Extracting a plurality of bearing inner ring images from the plurality of bearing images through the image processing software platform, automatically counting the rust area of each bearing inner ring image based on the pixel quantity statistics method to obtain the bearing rust degree, and calculating the average value of the plurality of bearing rust degrees to obtain the final inner ring rust degree of the current bearing.

[0023] In a third aspect, the present application discloses an electronic device, including:

[0024] A memory for storing a computer program;

[0025] A processor for executing the computer program to implement the aforementioned method for evaluating the rust degree of a bearing.

[0026] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned method for evaluating the rust degree of a bearing is implemented.

[0027] It can be seen that the camera of the present application has its optical axis passing through the axis of the bearing and perpendicular to the bearing plane, and is used to capture a number of bearing images corresponding to the current bearing; the number of bearing images is the images corresponding to the current bearing before and after rotating horizontally several times with the axis of the bearing as the rotation center; the total rotation degree of the horizontal rotation is 360°; an image processing software platform is used to extract a number of inner ring images of the bearing from the number of bearing images, automatically count the rust area of each inner ring image of the bearing based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of the number of bearing rust degrees to obtain the final inner ring rust degree of the current bearing. Thus, it can be seen that the present application uses a camera to obtain a number of bearing images of the inner ring of the bearing at different angles, and extracts the inner ring images of the bearing, avoiding the omission of rust areas caused by the shooting angle and improving the accuracy; the present application automatically counts and calculates the rust degree through the image processing software platform without manual participation, improving objectivity and also avoiding mistakes caused by humans, which is beneficial to improving the accuracy and processing speed; in addition, the present application uses the pixel quantity statistics method for statistics, which is applicable to rust areas with complex shapes or irregular distributions, improving the applicability and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0029] Figure 1 Schematic diagram of a bearing rust degree evaluation system disclosed in the present application;

[0030] Figure 2 Schematic diagram of a bearing image disclosed in the present application;

[0031] Figure 3 Schematic diagram of a specific bearing rust degree evaluation system disclosed in the present application;

[0032] Figure 4 Schematic diagram of the placement of a camera and the current bearing disclosed in the present application;

[0033] Figure 5 Schematic diagram of an image of the inner ring of a bearing after marking disclosed in the present application;

[0034] Figure 6 Schematic diagram of an extracted inner ring image of a bearing disclosed in the present application;

[0035] Figure 7 Schematic diagram of a first image disclosed in the present application;

[0036] Figure 8 A schematic diagram of a second image disclosed in this application;

[0037] Figure 9 A schematic diagram of the adjustment process of a first image disclosed in this application;

[0038] Figure 10 Another schematic diagram of the adjustment process of a first image disclosed in this application;

[0039] Figure 11 A schematic diagram of the adjustment process of a second image disclosed in this application;

[0040] Figure 12 A schematic diagram of four divided regions disclosed in this application;

[0041] Figure 13 An image of the inner ring of a bearing after determining the marked contour, disclosed in this application;

[0042] Figure 14 An adjusted image disclosed in this application;

[0043] Figure 15 A flowchart of a method for evaluating the rust degree of a bearing disclosed in this application;

[0044] Figure 16 A structural diagram of an electronic device disclosed in this application. Detailed implementation manners

[0045] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] First of all, the transparent grid method can only provide a rough proportion of the rust area. For some rust areas with complex shapes or irregular distributions, the accuracy of the estimation will be greatly affected. Using the transparent grid method requires manually placing the grid on the bearing surface and counting the number of grids occupied by the rust area one by one. For bearings with a large area or complex rust conditions, this process is very time-consuming and error-prone. After counting the number of grids in the rust area, a series of data processing and calculations are still required to obtain the final proportion of the rust area.

[0047] In addition, the transparent grid method is mainly applicable to planes or relatively regular geometric shapes. For some complex curved surfaces in the bearing, it will be very difficult to place the grid and count the rust area. As a result, the evaluation results lack obvious differences when distinguishing different anti-rust schemes.

[0048] To this end, the embodiments of the present application propose a bearing rust degree evaluation scheme, which can improve the accuracy of bearing rust degree evaluation.

[0049] The embodiments of the present application disclose a bearing rust degree evaluation system 10. Refer to Figure 1 As shown, the system includes a camera 11 whose optical axis passes through the axis of the bearing and is perpendicular to the bearing plane, and an image processing software platform 12. Specifically:

[0050] The camera 11 whose optical axis passes through the axis of the bearing and is perpendicular to the bearing plane is used to take a plurality of bearing images corresponding to the current bearing; the plurality of bearing images are the images corresponding to the current bearing before and after rotating horizontally several times with the axis of the bearing as the rotation center; the total rotation degree of the horizontal rotation is 360°;

[0051] The image processing software platform 12 is used to extract a plurality of bearing inner ring images from the plurality of bearing images, automatically count the rust area of each bearing inner ring image based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of the plurality of bearing rust degrees to obtain the final inner ring rust degree of the current bearing.

[0052] It can be seen that the camera of the present application whose optical axis passes through the axis of the bearing and is perpendicular to the bearing plane is used to take a plurality of bearing images corresponding to the current bearing; the plurality of bearing images are the images corresponding to the current bearing before and after rotating horizontally several times with the axis of the bearing as the rotation center; the total rotation degree of the horizontal rotation is 360°; the image processing software platform is used to extract a plurality of bearing inner ring images from the plurality of bearing images, automatically count the rust area of each bearing inner ring image based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of the plurality of bearing rust degrees to obtain the final inner ring rust degree of the current bearing. Thus, the present application uses a camera to obtain a plurality of bearing images of the bearing inner ring at different angles, and extracts the bearing inner ring images, avoiding the omission of rust areas caused by the shooting angle and improving the accuracy; the present application automatically counts and calculates the rust degree through the image processing software platform without manual participation, improving objectivity and also avoiding mistakes caused by humans, which is beneficial to improving accuracy and processing speed; in addition, the present application uses the pixel quantity statistics method for statistics, which is applicable to rust areas with complex shapes or irregular distributions, improving applicability and accuracy.

[0053] It should be noted that the rotation angle each time during horizontal rotation can be the same or different. The camera is a high-definition camera.

[0054] In a specific embodiment, the rotation angle each time during horizontal rotation is 120°, and it rotates twice to take three bearing images. The three bearing images are asFigure 2 As shown, it is a schematic diagram of bearing images, showing three bearing images, namely T-1, T-2, and T-3.

[0055] It should be noted that by rotating for multi-angle shooting, it can avoid missing the rust area due to the shooting angle problem and also avoid misidentifying the rust area due to light problems, thus improving the accuracy.

[0056] In this embodiment, the bearing rust degree evaluation system further includes: a circular bearing bracket 13 with a diameter equal to that of the bearing, for placing the current bearing; a level 14, for adjusting the current bearing to be parallel to the horizontal plane. For details, please refer to Figure 3 As shown, it is a schematic diagram of a specific bearing rust degree evaluation system.

[0057] It should be noted that in this application, the dried outer ring of the bearing is placed in a circular area with a diameter equal to its own, ensuring that the center of the outer ring of the bearing coincides with the center of the circular area. Use a level to adjust the level of the bearing to ensure that the outer ring of the bearing is parallel to the horizontal plane. Use a camera for shooting, adjust the optical axis of the camera to be perpendicular to the axis of the bearing and align it, and adjust the focal length to the optimal position. Fix the shooting distance to ensure that the bearing is not missing in the shot.

[0058] Refer to Figure 4 As shown, it is a schematic diagram of the placement of a camera and the current bearing. In the figure, the lens plane of the camera is plane A2, and the plane where the current bearing is located is plane A1. The distance between the two planes is h (i.e., the shooting distance), and the line connecting the center points of the two planes is perpendicular to plane A1 (i.e., the optical axis of the camera passes through the axis of the bearing and is perpendicular to the bearing plane).

[0059] In this embodiment, the current bearing is the bearing obtained by drying the bearing after ultrasonic cleaning in a constant temperature oven at the target temperature; the bearing after ultrasonic cleaning is the bearing obtained by placing the wiped bearing in a target container filled with a target liquid and cleaning it in an ultrasonic cleaning device.

[0060] It should be noted that the target liquid is petroleum ether or ethanol, and the target container is a plastic container; the specific bearing cleaning process is as follows: First, use a clean test paper to wipe the grease on the surface of the bearing to ensure that there are no obvious stains on the surface. Put the cleaned bearing into a plastic container filled with petroleum ether or ethanol to ensure that the bearing is completely immersed. Place the plastic container in an ultrasonic cleaning device for ultrasonic cleaning for 10 - 15 minutes to ensure that the rusty surface is completely exposed. After the ultrasonic cleaning is completed, use a clean test paper to wipe the surface of the bearing again to remove the residual cleaning liquid. Put the cleaned bearing into a 40°C constant temperature oven and dry it for 2 hours to ensure that there is no residual liquid on the surface, facilitating subsequent image acquisition.

[0061] In this embodiment, the image processing software platform is further configured to extract a plurality of inner ring images of the bearing from the plurality of bearing images based on geometric Boolean operations.

[0062] It should be noted that each bearing image is imported into the image processing software platform to draw a marked area overlapping with the upper and lower edges of the bearing inner ring in the software. The intersection of the two marked areas is extracted through geometric Boolean operations to obtain a picture of the surface of the bearing inner ring. It should be noted that using geometric Boolean operations can effectively complete image denoising to reduce the interference of other areas (bearing areas other than the bearing inner ring).

[0063] See Figure 5 As shown, it is a schematic diagram of an image of the bearing inner ring after marking. The figure includes the upper edge of the inner ring and the lower edge of the inner ring. The middle area between the two edges is the bearing inner ring area. See Figure 6 As shown, it is a schematic diagram of the extracted bearing inner ring image.

[0064] In this embodiment, the image processing software platform 12 is specifically configured to perform grayscale processing on each of the bearing inner ring images to obtain bearing inner ring grayscale images, and perform binarization processing on each of the bearing inner ring grayscale images to automatically count the rust area of each of the bearing inner ring images based on the pixel quantity statistics method to obtain the bearing rust degree.

[0065] It should be noted that the image is converted to an 8-bit grayscale image format with a grayscale range of 0 - 255. 0 represents black, indicating that the pixel has no brightness at all. 255 represents white, indicating that the pixel has the maximum brightness. 1 - 254 represents a gradual change from black to white. The smaller the value, the closer the color is to black; the larger the value, the closer the color is to white.

[0066] It should be noted that the grayscale image is binarized, and the pixels in the image are divided into a background area and a target area (bearing inner ring area).

[0067] It should be noted that by using grayscale processing and binarization processing in this application, it is convenient to count the number of pixels and improve the accuracy of bearing rust degree evaluation.

[0068] In this embodiment, the image processing software platform 12 is further specifically configured to obtain a first image in which the inner ring area of the bearing is white and other areas are black by adjusting the second binary threshold, and use the number of white pixels in the first image to represent the first area of the inner ring area of the bearing; select a part of the rust area from the inner ring image of the bearing, and obtain a second image in which the part of the rust area is black and displayed consistently with the part of the rust area in the inner ring image of the bearing by adjusting the first binary threshold of the first image, and use the number of black pixels in the inner ring area of the second image to represent the second area of the total rust area; calculate the product of the target percentage corresponding to each inner ring gray-scale image of the bearing and 100 as the bearing rust degree of each inner ring image of the bearing; the target percentage is the ratio of the second area to the first area.

[0069] It should be noted that it is necessary to calculate the ratio of the rust area of the bearing to the area of the inner ring of the bearing, and take the product of the ratio and 100 as the rust degree.

[0070] It should be noted that based on the first image, this application is adjusted so that the part of the rust area is black. At this time, the area of the white pixels is counted in the area where the white pixels are located. By subtracting the area of the white pixel area (S2) in the second image from the first area (S1) in the first image, the number of black pixels in the inner ring area of the second image can be obtained, that is, the second area (S1 - S2).

[0071] See Figure 7 shown, which is a schematic diagram of the first image; in the figure, the black area is the background area, and the white area is the target area; the white area is the area of the inner ring of the bearing, that is, the area of the white pixels is S1; see Figure 8 shown, which is a schematic diagram of a second image. In the figure, the black area in the inner ring area of the bearing is the rust area (S1 - S2).

[0072] In a specific embodiment, see Figure 9 and Figure 10 shown, Figure 9 which is a schematic diagram of the adjustment process of a first image; Figure 10 which is another schematic diagram of the adjustment process of the first image; Figure 9 There is some black in the inner ring area of the bearing, and it is necessary to adjust the second binary threshold (threshold 2, that is, the low threshold) to remove the black area, Figure 10 in which the second binary threshold (threshold 2) is changed from Figure 9 172 in

[0073] In a specific embodiment, see Figure 11As shown, it is a schematic diagram of a second image adjustment process; based on Figure 10 , the first binary threshold (threshold 1, that is, the high threshold) is adjusted from 0 to 66, so that some rust areas are displayed as black pixels. At the same time, some rust areas outside the rust areas are also displayed.

[0074] In this embodiment, the image processing software platform 12 is specifically further configured to evenly divide the bearing inner ring area in the bearing inner ring image into several divided areas, and select some rust areas from each of the divided areas. By adjusting the first binary threshold in the bearing inner ring image, the second image in which the selected rust areas are displayed in black in the bearing inner ring image is obtained, and the number of black pixels in the bearing inner ring area of the second image is used to represent the second area of the total rust area.

[0075] It should be noted that the number of the divided areas can be specifically set according to the situation. In one embodiment, it can be 4. Refer to Figure 12 As shown, it is a schematic diagram of four divided areas. Some rust areas (rust spots) in each area are circled with circles.

[0076] It should be noted that the specific steps of obtaining the second image in which the selected rust areas are displayed in black in the bearing inner ring image by adjusting the first binary threshold in the bearing inner ring image are as follows: mark each of the selected rust areas in the bearing inner ring image with a marked contour of a fixed shape; there are at least two intersections between the marked contour and the rust part corresponding to the selected rust area in the bearing inner ring image; adjust the first binary threshold in the bearing inner ring image in real time to obtain an image being adjusted, and translate each marked contour to the corresponding selected rust area in the image being adjusted; if all the marked contours in the bearing inner ring image can match the corresponding rust identification areas in the image being adjusted, then the second image in which the selected rust areas are displayed in black in the bearing inner ring image is obtained, and the current first binary threshold is the optimal threshold. It should be noted that if the intersection situation between the marked contour and the rust part of the corresponding rust identification area in the image being adjusted is the same, then they match.

[0077] It should be noted that the fixed shape can be various shapes and can be circular in a specific embodiment. Specifically, the adjustment steps are as follows: Place the image being adjusted and the inner ring image of the bearing on the picture processing software platform, and adjust the sizes of the two images to a state where the inner rings can completely coincide. Then, use the circular marking contour to mark the rust marking points (the rust parts of the partially rusted areas) in the inner ring image of the bearing, so that at least two points on the outer contour of the rust marking points are in contact with the circular marking contour. Fix the circular diameter of the circular marking contour matching the rust points, and translate the circular marking contour to the position of the same rust marking points in the image being adjusted. If the four rust marking point areas in the inner ring image of the bearing can all match the four rust marking points in the image being adjusted, it is considered that the value corresponding to the current first binarization threshold is the optimal threshold. If they cannot be completely matched, continue to adjust the first binarization threshold until the four rust marking points in the image being adjusted can all match the corresponding circles. At this time, it is considered that the first binarization threshold is adjusted to the optimal value. The white area obtained under this threshold is the area of the inner ring of the bearing excluding the rust part, that is, the white pixel area; see Figure 13 As shown, it is an inner ring image of the bearing after the marking contour is determined. In the figure, there are at least two intersection points between the marking contour (circle) of each partially rusted area and the rust part of the corresponding partially rusted area; see Figure 14 As shown, it is an image being adjusted. In the figure, the four circular marking contours correspond one by one to the Figure 13 circular marking contours therein.

[0078] It should be noted that during the process of adjusting the threshold to obtain the second image, it is necessary to ensure that several partially rusted areas are similar to the corresponding actual rust areas, that is, similar to the rust areas corresponding to the inner ring image of the bearing, so as to ensure that the rust parts in other areas can also be normally displayed in black; it should be noted that selecting partially rusted areas is to reduce the software comparison difficulty. If partially rusted areas are not selected, all rust areas need to be similar to the corresponding actual rust areas, the comparison difficulty is relatively large, which is not conducive to speeding up the area calculation process. When the observation range is large, it also increases the risk of observation errors, increases the error rate, and is not conducive to improving the rust degree accuracy.

[0079] In summary, the present application accurately calculates the rust area of the bearing through image processing techniques (such as grayscale conversion and binarization processing), realizes the quantitative evaluation of the rust degree, and overcomes the subjectivity and inaccuracy of traditional methods (such as the transparent grid method); in addition, by using a camera and multi-angle shooting, combined with image processing techniques, the rust information of the inner ring of the bearing can be efficiently and accurately extracted, significantly improving the accuracy and efficiency of the evaluation; the standardized operation process of the present application, including bearing cleaning, image acquisition, image processing, and rust degree calculation, is simple and easy to implement, reducing human errors; in addition, the present application can effectively evaluate the rust condition of complex curved surfaces such as the inner ring of the bearing, overcoming the limitations of traditional methods in the application of complex geometric shapes.

[0080] The embodiment of the present application discloses a specific method for evaluating the rust degree of a bearing, which is applied to a bearing rust degree evaluation system. The system includes a camera and an image processing software platform. The optical axis of the camera passes through the axis of the bearing and is perpendicular to the bearing plane. Compared with the previous embodiment, the technical solution in this embodiment is further described and optimized. Refer to Figure 15 as shown, specifically including:

[0081] Step S11: Take a plurality of bearing images corresponding to the current bearing through the camera; the plurality of bearing images are the images corresponding to the current bearing before and after rotating horizontally several times with the bearing axis as the rotation center; the total rotation degree of the horizontal rotation is 360°.

[0082] In this embodiment, before collecting the images, the current bearing also needs to be cleaned. Specifically, the current bearing is the bearing obtained by drying the bearing after ultrasonic cleaning in a constant temperature oven at the target temperature; the bearing after ultrasonic cleaning is the bearing obtained by placing the wiped bearing in a target container filled with a target liquid and cleaning it in an ultrasonic cleaning device. The cleaning process is as follows: Wipe the grease on the bearing surface with a clean test paper to ensure that there are no obvious stains on the surface. Put the cleaned bearing into a plastic container filled with petroleum ether or ethanol, ensuring that the bearing is completely immersed. Place the plastic container in an ultrasonic cleaning device for ultrasonic cleaning for 10 - 15 minutes to ensure that the rusty surface is completely exposed. After the ultrasonic cleaning is completed, wipe the bearing surface with a clean test paper again to remove the residual cleaning liquid. Put the cleaned bearing into a 40°C constant temperature oven and dry it for 2 hours to ensure that there is no residual liquid on the surface, facilitating subsequent image acquisition.

[0083] In this embodiment, to facilitate image acquisition, the current bearing needs to be properly placed. A circular bearing bracket with a diameter equal to that of the bearing is used to place the current bearing; a spirit level is used to adjust the current bearing to be parallel to the horizontal plane. Specifically, the outer ring of the dried bearing is placed within a circular area with a diameter equal to its own diameter, ensuring that the center of the outer ring of the bearing coincides with the center of the circular area. The spirit level is used to adjust the level of the bearing to ensure that the outer ring of the bearing is parallel to the horizontal plane. A camera is used for shooting. The optical axis of the camera is adjusted to be vertically aligned with the axis of the bearing, and the focal length is adjusted to the optimal position. The shooting distance is fixed, and the bearing is rotated horizontally by 120° in sequence to obtain 3 images of the inner ring rust of the bearing.

[0084] Step S12: Extract a number of inner ring images of the bearing from the several bearing images through an image processing software platform, automatically count the rust area of each inner ring image of the bearing based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of several bearing rust degrees to obtain the final inner ring rust degree of the current bearing.

[0085] In this embodiment, a number of inner ring images of the bearing are extracted from the several bearing images based on geometric Boolean operations.

[0086] In this embodiment, each inner ring image of the bearing is grayscaled to obtain a grayscale image of the inner ring of the bearing, and each grayscale image of the inner ring of the bearing is binarized to automatically count the rust area of each inner ring image of the bearing based on the pixel quantity statistics method to obtain the bearing rust degree.

[0087] In this embodiment, a first image in which the inner ring area of the bearing is white and other areas are black is obtained by adjusting the second binarization threshold, and the number of white pixels in the first image is used to represent the first area of the inner ring area of the bearing; a part of the rust area is selected from the inner ring image of the bearing, and a second image in which the part of the rust area is black-displayed consistently with the part of the rust area in the inner ring image of the bearing is obtained by adjusting the first binarization threshold of the first image, and the number of black pixels in the inner ring area of the second image is used to represent the second area of the total rust area; the product of the target percentage corresponding to each grayscale image of the inner ring of the bearing and 100 is calculated as the bearing rust degree of each inner ring image of the bearing; the target percentage is the ratio of the second area to the first area.

[0088] In this embodiment, the bearing inner ring area in the bearing inner ring image is evenly divided into a number of divided areas, and a part of the rust areas are selected from each of the divided areas. By adjusting the first binarization threshold in the bearing inner ring image, a second image in which the part of the rust area is displayed in black and is consistent with the part of the rust area in the bearing inner ring image is obtained. The number of black pixels in the bearing inner ring area of the second image is used to represent the second area of the total rust area.

[0089] It should be noted that the specific steps for obtaining the second image in which the part of the rust area is displayed in black and is consistent with the part of the rust area in the bearing inner ring image by adjusting the first binarization threshold in the bearing inner ring image are as follows: Mark each of the part of the rust areas in the bearing inner ring image with a marked contour of a fixed shape; There are at least two intersection points between the marked contour and the rust part corresponding to the part of the rust area in the bearing inner ring image; Adjust the first binarization threshold in the bearing inner ring image in real time to obtain an image being adjusted, and translate each of the marked contours to the corresponding part of the rust area in the image being adjusted; If all the marked contours in the bearing inner ring image can match the corresponding rust identification areas in the image being adjusted, then the second image in which the part of the rust area is displayed in black and is consistent with the part of the rust area in the bearing inner ring image is obtained, and the current first binarization threshold is the optimal threshold. It should be noted that if the intersection situations between the marked contour and the rust part of the corresponding rust identification area in the image being adjusted are the same, then they match.

[0090] It can be seen that the camera of the present application has its optical axis passing through the bearing axis and perpendicular to the bearing plane, and is used to capture a number of bearing images corresponding to the current bearing; The number of bearing images are the images respectively corresponding to the current bearing before and after horizontally rotating a number of times with the bearing axis as the rotation center; The total rotation degree of the horizontal rotation is 360°; An image processing software platform is used to extract a number of bearing inner ring images from the number of bearing images, automatically calculate the rust area of each bearing inner ring image based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of the number of bearing rust degrees to obtain the final inner ring rust degree of the current bearing. Thus, it can be seen that the present application uses a camera to obtain a number of bearing images of the bearing inner ring at different angles, and extracts the bearing inner ring images, avoiding the omission of rust areas caused by the shooting angle and improving the accuracy; The present application automatically calculates and calculates the rust degree through the image processing software platform without manual participation, improving objectivity and also avoiding mistakes caused by humans, which is beneficial to improving the accuracy and processing speed; In addition, the present application uses the pixel quantity statistics method for statistics, which is applicable to rust areas with complex shapes or irregular distributions, improving the applicability and accuracy.

[0091] Furthermore, an embodiment of the present application also provides an electronic device. Figure 16 FIG. 20 is a structural diagram of an electronic device shown according to an exemplary embodiment. The content in the figure should not be considered as any limitation on the scope of use of the present application.

[0092] Figure 16 FIG. 20 is a schematic structural diagram of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the bearing corrosion degree evaluation method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0093] In this embodiment, the power supply 26 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and no specific limitation is imposed on it here; the input / output interface 24 is used to obtain external input data or output data to the outside, and the specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0094] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a disk, or an optical disc, etc. The resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. Among them, in addition to the computer program that can be used to complete the bearing corrosion degree evaluation method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0095] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the bearing corrosion degree evaluation method disclosed above is implemented.

[0096] For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.

[0097] In the present application, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0098] Those skilled in the art can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0099] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the technical field.

[0100] Finally, it should also be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0101] The above has introduced in detail a bearing rust degree evaluation system, method, device, and storage medium provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A bearing rust degree evaluation system, characterized in that Including: A camera with its optical axis passing through the axis of the bearing and perpendicular to the bearing plane, which is used to capture a number of bearing images corresponding to the current bearing; the number of bearing images is the images corresponding to the current bearing before and after rotating horizontally several times with the axis of the bearing as the rotation center; the total rotation degree of the horizontal rotation is 360°; An image processing software platform, which is used to extract a number of inner ring images of the bearing from the number of bearing images, automatically calculate the rust area of each inner ring image of the bearing based on the pixel quantity statistics method to obtain the bearing rust degree, and calculate the average value of the number of bearing rust degrees to obtain the final inner ring rust degree of the current bearing.

2. The bearing rust degree evaluation system according to claim 1, wherein The image processing software platform is further used to extract a number of inner ring images of the bearing from the number of bearing images based on geometric Boolean operations.

3. The bearing rust degree evaluation system according to claim 1, wherein The image processing software platform is specifically used to perform grayscale processing on each inner ring image of the bearing to obtain a grayscale image of the inner ring of the bearing, and perform binarization processing on each grayscale image of the inner ring of the bearing to automatically calculate the rust area of each inner ring image of the bearing based on the pixel quantity statistics method to obtain the bearing rust degree.

4. The bearing rust degree evaluation system according to claim 3, wherein The image processing software platform is specifically further used to obtain a first image in which the inner ring area of the bearing is white and other areas are black by adjusting the second binarization threshold, and use the number of white pixels in the first image to represent the first area of the inner ring area of the bearing; Select a part of the rust area from the inner ring image of the bearing, obtain a second image in which the part of the rust area is black and displayed consistently with the part of the rust area in the inner ring image of the bearing by adjusting the first binarization threshold of the first image, and use the number of black pixels in the inner ring area of the second image to represent the second area of the total rust area; Calculate the product of the target percentage corresponding to each grayscale image of the inner ring of the bearing and 100 as the bearing rust degree of each inner ring image of the bearing; the target percentage is the ratio of the second area to the first area.

5. The bearing rust degree evaluation system according to claim 4, wherein The image processing software platform is specifically further used to evenly divide the inner ring area of the bearing in the inner ring image of the bearing into a number of divided areas, and select a part of the rust area from each divided area, obtain the second image in which the part of the rust area is black and displayed consistently with the part of the rust area in the inner ring image of the bearing by adjusting the first binarization threshold in the inner ring image of the bearing, and use the number of black pixels in the inner ring area of the second image to represent the second area of the total rust area.

6. The bearing rust degree evaluation system according to claim 1, wherein It further includes: A circular bearing bracket with the same diameter as the bearing diameter, which is used to place the current bearing; A spirit level, which is used to adjust the current bearing to be parallel to the horizontal plane.

7. The bearing rust degree evaluation system according to any one of claims 1 to 6, characterized in that, The current bearing is the bearing obtained by drying the bearing after ultrasonic cleaning in an incubator at the target temperature; the bearing after ultrasonic cleaning is the bearing obtained by placing the wiped bearing in a target container filled with a target liquid and cleaning it in an ultrasonic cleaning device.

8. A method for evaluating the degree of bearing rust, characterized in that Applied to a bearing corrosion degree evaluation system, the system includes a camera and an image processing software platform. The optical axis of the camera passes through the axis of the bearing and is perpendicular to the bearing plane. The method includes: Taking a plurality of bearing images corresponding to the current bearing through the camera; the plurality of bearing images are the images corresponding to the current bearing before and after rotating horizontally several times with the axis of the bearing as the rotation center; the total rotation degree of the horizontal rotation is 360°; Extracting a plurality of bearing inner ring images from the plurality of bearing images through an image processing software platform, automatically counting the corrosion area of each bearing inner ring image based on the pixel quantity statistics method to obtain the bearing corrosion degree, and calculating the average value of the plurality of bearing corrosion degrees to obtain the final inner ring corrosion degree of the current bearing.

9. An electronic device, characterized in that, Including: A memory for storing a computer program; A processor for executing the computer program to implement the bearing corrosion degree evaluation method as described in claim 8.

10. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by the processor, it implements the bearing corrosion degree evaluation method as described in claim 8.

Images