Bearing cage pocket inspection method and device

Abstract

The present invention belongs to the technical field of bearing cage inspection, and discloses a method and device for inspecting pockets of bearing cage in order to solve the technical problem that the pockets of conventional bearing cages are mostly inspected manually, which is prone to high labor costs and low inspection efficiency, and affects the straight-through rate of bearing cages. The method includes: comparing and matching each pocket image in an initial pocket image set with each other, screening some pocket images with abnormal matching in the comparison matching result to obtain some abnormal pocket images, recognizing and marking abnormal area images in the abnormal pocket images to obtain abnormal mark areas, classifying pocket abnormalities for the abnormal mark areas to obtain the types of pocket abnormalities, taking pocket images for the abnormal pockets corresponding to the types of pocket abnormalities a second time to obtain images of real pocket abnormalities, and performing beam positioning in a two-dimensional coordinate system to obtain position information of the abnormal pockets.

Description

[Technical Field]

[0001] The present application relates to the related field of image inspection of bearing cages, and more particularly to a method and apparatus for inspecting pockets in bearing cages. [Background technology]

[0002] A retainer (i.e., bearing retainer, also called a bearing cage) is a bearing part that partially surrounds all or some of the rolling elements and moves with them, is used to isolate the rolling elements, and generally guides the rolling elements and holds them within the bearing.

[0003] Currently, most of the quality inspection methods for bearing cages are manual inspections, where workers carefully inspect each bearing cage step by step, and especially for some bearing cages that require special pocket processing, manual inspections must be carried out to check the pocket size, pocket dimension, column inclination, and whether holes have been drilled, which not only consumes a lot of manpower but also reduces the efficiency of the quality inspection. Because manual inspections rely on the experience and diligence of workers, some human error is likely to affect the quality of bearing cage products and make it difficult to ensure the first-pass rate of bearing cages. Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present application provide a method and device for inspecting pockets of a bearing cage to solve the technical problems that conventionally, the pockets of a bearing cage are mostly inspected manually, which results in high labor costs and a decrease in inspection efficiency, and also makes it difficult to inspect the pockets comprehensively and thoroughly, which affects the first-pass rate of the bearing cage. [Means for solving the problem]

[0005] The embodiments of the present application use the following technical means. In one aspect of the present application, an embodiment of the present application includes: taking continuous pocket images of a bearing cage on a rotary table with a camera to obtain an initial pocket image set; comparing and matching each pocket image in the initial pocket image set with each other; screening some pocket images in the comparison matching result that are abnormally matched to obtain some abnormal pocket images based on the comparison matching result; recognizing and marking abnormal area images in the abnormal pocket images to obtain abnormal marked areas in the abnormal pocket images; and classifying the abnormal pocket areas to obtain pocket abnormalities of the bearing cage, wherein the pocket abnormality types include at least pocket abnormalities. and determining a pocket inspection result for the bearing cage from the position information of the abnormal pocket based on the type of the pocket abnormality and the image of the true pocket abnormality, and transmitting the pocket inspection result to a terminal of an operator.

[0006] In the embodiment of the present application, a rotary table and a camera are used to inspect the pockets of a bearing cage, and all the identified pockets are compared with each other. Then, abnormal pockets are screened to determine the type of pocket abnormality. The location and type of abnormal pocket can be accurately identified, and the actual image of the pocket abnormality can be sent to the back-end operator, which helps the operator to greatly reduce the amount of pocket inspection work and has a high accuracy rate. Combined with laser positioning, it helps the operator to quickly find pockets with abnormal conditions and determine the corresponding abnormal fault type, which greatly reduces labor costs and improves inspection efficiency. Furthermore, pockets can be inspected comprehensively and thoroughly, reducing human error and improving the first-pass rate of bearing cages.

[0007] In one possible embodiment, taking successive pocket images of the bearing cage on the rotary table with a camera to obtain an initial pocket image set specifically includes obtaining drawing information of the bearing cage to be manufactured, the drawing information including at least the number of pockets, the pocket size, the radius of the bearing cage, and processing parameters of the columns; inputting the number of pockets and the radius of the bearing cage in the drawing information into a control unit of a rotary table control system, the rotary table control system including the control unit, a servo motor unit, and a laser emission unit; determining the angular velocity of the rotary table from the interval of the camera based on the number of pockets to take images of each pocket of the bearing cage; controlling the operation of the rotary table based on the angular velocity of the rotary table; and taking successive pocket images of the bearing cage with the camera. the pockets of the bearing cage are photographed automatically to obtain a partial pocket image set, the partial pocket image set being an image set photographed by a camera at an initial plurality of time intervals; detecting pillar pixel areas for a grayscale image set of the partial pocket image set based on a preset Canny operator to obtain actual pillar pixel areas; matching the area value of the actual pillar pixel areas based on a reference pixel area of ​​the pillars; determining the actual pillar pixel areas that are successfully matched as complete pillar pixel values; determining the pocket images corresponding to the complete pillar pixel values ​​as first pocket images; and completely photographing each pocket of the bearing cage to obtain the initial pocket image set by re-feeding back to a control unit of the rotary table control system based on the first pocket images and the corresponding camera photographing time intervals.

[0008] In the embodiment of the present application, the servo motor of the rotary table and the camera's shooting time interval are controlled so that they can be matched with each other, and the image edge detection of the Canny operator is used to ensure that each pocket of each different type of bearing cage can be completely captured, that is, the rotation of the servo motor and the shooting of the camera are ensured to be compatible with each other, and an initial pocket image set of all pockets of the bearing cage is obtained.

[0009] In one possible embodiment, comparing and matching each pocket image in the initial pocket image set with each other specifically includes: performing grayscale preprocessing on each pocket image to obtain several grayscale pocket images; dividing the grayscale pocket image into regions using predetermined dividing lines based on the actual pixel sizes of the grayscale pocket images to obtain grayscale pixel regions, where each grayscale pocket image is divided into nine grayscale pixel regions; scanning pixel features in each grayscale pixel region, where the pixel features include a brightness gradient feature and a corresponding pixel coordinate location feature of each pixel point; and performing similarity comparison matching between each grayscale pocket image for several pixel features that correspond one-to-one to each grayscale pixel region in the several grayscale pocket images based on the pixel features in each grayscale pixel region to obtain the comparative matching result, where the comparative matching result includes normal matching and abnormal matching, and the similarity comparison matching is matching the similarity of corresponding pixel features between any two groups of grayscale pocket images.

[0010] In the embodiment of the present application, after comparing and matching any two grayscale pocket images in the initial pocket image set with each other, the pocket images with abnormal conditions can be quickly found, thereby obtaining the comparison group, reducing the difficulty of image processing and shortening the inspection time of the entire bearing cage.

[0011] In one possible embodiment, based on the comparison matching result, screening some pocket images with abnormal matching in the comparison matching result to obtain some abnormal pocket images specifically includes: if the comparison matching result is a matching abnormality, obtaining several groups of grayscale pocket images with matching abnormality; extracting distinguishing pixel features and corresponding distinguishing grayscale pixel regions in the several groups of grayscale pocket images; obtaining normal grayscale pixel regions based on several normal pocket images with normal matching in the comparison matching result; and calculating related intersections between the distinguishing grayscale pixel regions and the normal grayscale pixel regions based on a convolutional neural network and a sigmoid function. The method includes: learning and training pixel feature similarities to obtain a cross-classification network model, wherein the cross-classification network model uses a Siamese network as a basic structure; assigning weights according to differences between the distinguishing grayscale pixel regions and the normal grayscale pixel regions using the cross-classification network model; performing cross-classification on the several groups of grayscale pocket images to remove normal pixel features from the distinguishing pixel features and obtain abnormal pixel features from the distinguishing pixel features, wherein the abnormal pixel features are pixel features corresponding to abnormal pocket images in the grayscale pocket images of each group; and screening several grayscale pixel regions corresponding to the abnormal pixel features to obtain the several corresponding abnormal pocket images.

[0012] The embodiment of the present application cross-classifies several groups of grayscale pocket images using a cross-classification network model to screen pocket images with truly abnormal pixel features in the comparison matching group, i.e., abnormal pocket images.

[0013] In one possible embodiment, the method further includes, before recognizing and marking abnormal area images in the abnormal pocket images to obtain abnormal marked areas in the abnormal pocket images, performing an image sequence encoding process on all pocket images in the initial pocket image set to obtain an encoded data set, and marking anomalies against encoding numbers corresponding to the abnormal pocket images in the encoded data set based on positions of some of the abnormal pocket images corresponding to the initial pocket image set to obtain encoding numbers of the anomalies.

[0014] The embodiment of the present application first encodes all pocket images in the initial pocket image set, and then individually marks the recognized abnormal pocket images to obtain an abnormality encoding number, which helps to accurately locate each abnormal pocket, and also helps workers later find the corresponding abnormal pocket based on the marked abnormal pocket images.

[0015] In one possible embodiment, recognizing and marking an abnormal region image in the abnormal pocket image to obtain an abnormal marked region in the abnormal pocket image specifically includes: segmenting the abnormal pocket image corresponding to the coding number of the abnormality based on the grayscale pixel region corresponding to the abnormal pixel feature to obtain an original abnormal region image; performing grayscale processing on the original abnormal region image; performing elementary edge image feature constraint on the original abnormal region image after grayscale processing by second-order differentiation to obtain a candidate abnormal region; calculating the minimum pixel distance between the centroid of the candidate abnormal region and the edge image feature region to obtain a distance constraint, where the edge image feature region is the edge pixel region of the candidate abnormal region; constructing an edge slope coordinate system from the candidate abnormal region based on the image corner in the candidate abnormal region and the centroid; locating the direction of a slope angle with respect to the image slope pixel in the candidate abnormal region based on the edge slope coordinate system to obtain a direction constraint; and performing edge image feature constraint on the candidate abnormal region for a second time based on the distance constraint and the direction constraint to obtain the abnormal marked region.

[0016] In the embodiment of the present application, based on the original abnormal region images in several abnormal pocket images, candidate abnormal regions are located by edge constraint processing on the grayscale image by second-order differentiation, and then image edge feature constraints are performed for the grayscale pixels in the candidate abnormal regions for a second time based on distance constraints and direction constraints to locate and mark the abnormal grayscale pixels with more accurate constraints, thereby obtaining abnormal marked regions corresponding to the abnormal grayscale pixels.

[0017] In one possible embodiment, performing pocket abnormality classification for the abnormal mark area to obtain the type of pocket abnormality of the bearing cage specifically includes performing pocket abnormality classification matching for the abnormal mark area with a pocket abnormality template in a past pocket abnormality database, and if matching is successful, determining the pocket abnormality type corresponding to the pocket abnormality template as the pocket abnormality type of the abnormal mark area, and if matching is not successful, determining the pocket abnormality type for the abnormal mark area; and performing line detection of pixel point sets for horizontal column pixels and vertical column pixels of the pocket in the abnormal mark area using a line detection algorithm based on Hough transform to obtain pocket size information. calculating the slope of a line for a set of pixels with the same brightness gradient in the abnormal mark area using a Hough transform to obtain pillar slope information; recognizing non-intersecting curves in the abnormal mark area using a circle detection algorithm based on a Hough transform to obtain a circular outline area; calculating the area of ​​the same pixel in the circular outline area based on adjacent connected areas in the abnormal mark area to obtain hole area information; calculating the pixel length for the uneven area in the abnormal mark area to obtain groove depth information; and comparing the pocket size information, pillar slope information, hole area information, and groove depth information with drawing information to determine the type of pocket anomaly in the abnormal mark area.

[0018] In the embodiment of the present application, some abnormal mark areas are recognized and first compared with a database of past pocket anomalies, thereby realizing rapid matching and recognition of some common types of anomalies. Next, various types of judgments are made for the mark areas where no abnormalities are recognized, and a Hough detection algorithm is used to recognize and judge the pixel curves, pixel areas, lengths of consecutive identical pixels, and adjacent connected areas of pixels in the abnormal mark areas, etc., to obtain corresponding pocket size information, pillar inclination information, hole area information, and groove depth information. This information is then judged and compared with the corresponding reference ranges of each size and range information in the uploaded drawing information, thereby screening and recognizing the corresponding pocket anomaly types in the abnormal mark areas.

[0019] In one possible embodiment, using the rotary table and the camera to take a second pocket image of an abnormal pocket corresponding to the type of pocket abnormality to obtain an image of a true pocket abnormality specifically includes: obtaining an abnormality coding number of the abnormal pocket corresponding to the type of pocket abnormality; performing rotational feedback control on the servo motor of the rotary table based on the sequence position of the abnormality coding number in the encoding data set to face the abnormal pocket corresponding to the abnormality coding number toward the camera, wherein the rotational feedback control controls the rotational operation of the servo motor based on the shooting time interval between the abnormality coding number and the target coding number; and using the camera to take a second pocket image of several abnormal pockets corresponding to the abnormality coding numbers to obtain images of several of the true pocket abnormalities.

[0020] In the embodiment of the present application, the rotation of the motor in the rotary table is controlled based on the abnormality code number of the abnormal pocket, and the abnormal pocket is photographed a second time to obtain an image of the true abnormal pocket, thereby realizing a second inspection of the abnormal pocket, which may also provide the operator with a criterion for determining whether the pocket is abnormal, and when combined with the type of abnormal pocket detected by the system, the operator can make a better judgment.

[0021] In one possible embodiment, using a laser beam to position the beam in a two-dimensional coordinate system relative to the pocket positions corresponding to the images of the real pocket anomalies to obtain position information of the abnormal pockets specifically includes: after obtaining images of all the real pocket anomalies and the corresponding coding numbers of the several anomalies, using the laser beam to irradiate a single-line laser onto the several abnormal pockets corresponding to the images of the real pocket anomalies to obtain several laser beams; and positioning beam tilt angles for the several laser beams according to a two-dimensional coordinate system preset on a rotary table to obtain several beam tilt angles, and determining the position information of the several abnormal pockets based on the several beam tilt angles and the coding numbers of the several anomalies.

[0022] In the embodiment of the present application, after obtaining images of all the true pocket abnormalities and the corresponding several anomaly code numbers, a laser beam is emitted from a laser emitter at the center of the rotary table to illuminate the abnormal pockets, thereby forming several laser beams, and then the tilt angle of each abnormal pocket is determined according to a two-dimensional coordinate system preset on the rotary table, and then the position information of the abnormal pocket is finally determined based on the corresponding anomaly code number. This helps workers to timely find the corresponding abnormal pockets based on the position information of the abnormal pocket obtained from the tilt angle and the anomaly code number, saving workers' searching time and further improving the efficiency of bearing cage pocket inspection.

[0023] In another aspect, an embodiment of the present application also provides a bearing retainer pocket inspection device comprising at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, thereby enabling the at least one processor to perform the bearing retainer pocket inspection method described in any of the above embodiments. [Effects of the Invention]

[0024] In this application, a rotary table and a camera are used to inspect the pockets of the bearing cage, and all the recognized pockets are compared with each other. Then, abnormal pockets are screened to determine the type of pocket abnormality. The location and type of abnormal pocket can be accurately recognized, and the actual image of the pocket abnormality can be sent to the back-end workers, which helps the workers to greatly reduce the amount of pocket inspection work and has a high accuracy rate. Combined with laser positioning, it helps the workers to quickly find pockets with abnormal conditions and determine the corresponding abnormal fault type, which greatly reduces labor costs and improves inspection efficiency. Furthermore, it allows for comprehensive and thorough inspection of pockets, reduces human error, and improves the first-pass rate of bearing cages. [Brief explanation of the drawings]

[0025] In order to more clearly describe the technical solutions of the embodiments of the present application or the prior art, the following briefly introduces drawings to be used in the description of the embodiments or the prior art. It goes without saying that the drawings in the following description are only some of the embodiments described in the present application, and those skilled in the art can also obtain other drawings based on these drawings without performing any novel work. In the drawings,

[0026] [Figure 1] FIG. 1 is a flowchart of a pocket inspection method for a bearing cage provided by an embodiment of the present application. [Figure 2]FIG. 2 is an overall structural view of a pocket inspection device for a bearing cage provided by an embodiment of the present application. [Figure 3] FIG. 3 is a plan view of a two-dimensional coordinate system of a rotary table provided by an embodiment of the present application. [Figure 4] FIG. 4 is a schematic diagram of a pocket structure of a bearing cage provided by an embodiment of the present application. [Figure 5] FIG. 5 is a schematic diagram of the pocket and column structure of the bearing cage provided by the embodiment of the present application. [Figure 6] FIG. 6 is a structural schematic diagram of a pocket inspection device for a bearing cage provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0027] In order to allow those skilled in the art to better understand the technical solutions of the present application, the technical solutions of the embodiments of the present application will be described below clearly and completely with reference to the drawings of the embodiments of the present application, and it goes without saying that the described embodiments are only a part of the embodiments of the present application, and are not all of the embodiments, and all other embodiments that those skilled in the art can obtain from the embodiments of the present application without any novel work shall fall within the protection scope of the present application.

[0028] An embodiment of the present application provides a pocket inspection method for a bearing cage, and as shown in FIG. 1, the pocket inspection method for a bearing cage specifically includes steps S101 to S106. In S101, a camera takes successive pocket images of a bearing cage on a rotary table to obtain an initial pocket image set.

[0029] Specifically, drawing information for the bearing cage to be manufactured is acquired, and the drawing information includes at least the number of pockets, the pocket size, the radius of the bearing cage, and the processing parameters of the posts. The number of pockets and the radius of the bearing cage in the drawing information are input into a control unit of a rotary table control system. The rotary table control system includes the control unit, a servo motor unit, and a laser emission unit.

[0030] Furthermore, based on the number of pockets, the angular velocity of the rotary table is determined from the camera interval, and each pocket of the bearing cage is photographed.

[0031] In one embodiment, Fig. 2 is a diagram of the overall structure of a bearing cage pocket inspection system provided by an embodiment of the present application. As shown in Fig. 2, first, the drawing information of the bearing cage to be manufactured is uploaded to the bearing cage pocket inspection system. Fig. 4 is a schematic diagram of the pocket structure of a bearing cage provided by an embodiment of the present application, and Fig. 5 is a schematic diagram of the pocket and pillar structure of a bearing cage provided by an embodiment of the present application. As shown in Figs. 4 and 5, the pockets and pillars of the bearing cage have various complex types of structures to suit the operating characteristics of various bearings, so the pass-test of the bearing cage pockets is a condition for stable operation of the bearing. For example, suppose there are 36 pockets to be manufactured, each 4 x 6 cm in length and width, 1 cm in thickness, and 35 cm in radius. The pillars have four inclined surfaces, each with a 45° angle. The front of each pillar has three holes with a radius of 2 mm. The bottom of each pocket has two 1 cm-wide grooves, all of which are designed to allow the lubricant to flow smoothly. Next, the pocket number information and bearing cage radius information in the drawing information are input into the rotary table control system by the pocket inspection system, and the rotational angular velocity of the servo motor is calculated from the camera shooting interval, so that the camera and rotary table can be linked together to photograph each pocket of the bearing cage.

[0032] Furthermore, the operation of the rotary table is controlled based on the angular velocity of the rotary table, and the camera continuously captures pocket images of the bearing cage to obtain a partial pocket image set, which is an image set captured by the camera at the first multiple time intervals, for example, the camera captures image sets at the first five time intervals.

[0033] Furthermore, based on a preset Canny operator, the area of ​​the pillar pixel is detected for the grayscale image set of the partial pocket image set to obtain the actual pillar pixel area. Based on the reference pixel area of ​​the pillar, the area value is matched for the actual pillar pixel area. The actual pillar pixel area that is successfully matched is determined as the complete pillar pixel value. The pocket image corresponding to the complete pillar pixel value is determined as the first pocket image. Based on the first pocket image and the corresponding camera's shooting time interval, each pocket of the bearing cage is completely photographed by re-feeding back to the control unit of the rotary table control system to obtain an initial pocket image set.

[0034] In one embodiment, as shown in FIG. 2, to ensure that the camera can be fully matched to the rotary table, i.e., that each image captured by the camera contains one complete bearing retaining pocket, partial photography pre-processing is first performed to determine the activation time of the servo motor on the rotary table, and rough extraction is performed using a Canny operator to detect the area of ​​the pillar pixels in the grayscale image set of the partial pocket image set to obtain the actual pillar pixel area, i.e., the pillar pixel area in each image is calculated one by one, and then converted to the pillar reference pixel area based on the pillar reference area in the drawing information. The actual pillar pixel area is then compared with the area value to determine the actual pillar pixel area that is successfully matched as the complete pillar pixel value, and the pocket image corresponding to the recognized complete pillar pixel value is defined as the first pocket image. The first pocket image and the corresponding camera time interval are then fed back to the control unit to control the rotation of the servo motor, and the angular velocity of the servo motor and the camera photography time are matched to ensure that each pocket of the bearing retainer is completely photographed.

[0035] S102: Compare and match each pocket image in the initial pocket image set with each other; Based on the comparison and matching result, screen some pocket images with abnormal matching in the comparison and matching result to obtain some abnormal pocket images.

[0036] Specifically, grayscale preprocessing is performed on each pocket image to obtain several grayscale pocket images. Based on the actual pixel size of the grayscale pocket image, the grayscale pocket image is divided into regions using preset dividing lines to obtain grayscale pixel regions. Each grayscale pocket image is divided into nine grayscale pixel regions.

[0037] Furthermore, pixel features in each grayscale pixel region are scanned. The pixel features include brightness gradient features of each pixel point and corresponding pixel coordinate location features. Based on the pixel features in each grayscale pixel region, similarity comparison matching is performed between each grayscale pocket image for several pixel features that correspond one-to-one to each grayscale pixel region in several grayscale pocket images, to obtain a comparison matching result. The comparison matching result includes normal matching and abnormal matching. The similarity comparison matching is to match the similarity of corresponding pixel features between any two groups of grayscale pocket images.

[0038] In one embodiment, first, grayscale pre-processing is performed on each pocket image in the acquired initial pocket image set, then, based on the actual pixel size of the grayscale pocket image, each grayscale pocket image is divided by two horizontal and two vertical dividing lines to obtain nine grayscale pixel regions, and then, based on the light-dark gradient feature and corresponding pixel coordinate location feature of each scanned pixel point, a similarity comparison matching is performed between each grayscale pocket image for several pixel features that correspond one-to-one with each grayscale pixel region in several grayscale pocket images, that is, for the same grayscale pixel region in any two grayscale images in the initial pocket image set, the light-dark gradient feature and corresponding pixel coordinate location feature of the related pixel point are matched one by one, and finally several groups of comparison matching results are obtained.

[0039] Furthermore, if the comparison matching result is a matching abnormality, several groups of gray-scale pocket images with matching abnormality are obtained, distinguishing pixel features and corresponding distinguishing gray-scale pixel regions are extracted from the several groups of gray-scale pocket images, and normal gray-scale pixel regions are obtained based on several normal pocket images with a comparison matching result of normal matching.

[0040] Furthermore, based on a convolutional neural network and a sigmoid function, the similarity of the associated cross-pixel features for the distinct grayscale pixel regions and the normal grayscale pixel regions is learned and trained to obtain a cross-classification network model. The cross-classification network model uses a Siamese network as its basic structure, and the cross-classification network model assigns weights based on the differences between the distinct grayscale pixel regions and the normal grayscale pixel regions. Several groups of grayscale pocket images are cross-classified, and the normal pixel features from the distinct pixel features are removed to obtain abnormal pixel features from the distinct pixel features. The abnormal pixel features are pixel features corresponding to the abnormal pocket images from the grayscale pocket images of each group. The normal pixel features are pixel features corresponding to the normal pocket images from the grayscale pocket images of each group. Next, several grayscale pixel regions corresponding to the abnormal pixel features are screened to obtain several corresponding abnormal pocket images.

[0041] In one embodiment, for some groups of gray-scale pocket images with abnormal matching in the comparison matching results, distinguishing pixel features and corresponding distinguishing gray-scale pixel regions are extracted, and normal gray-scale pixel regions are also obtained from some normal pocket images with normal matching. Next, a cross-classification network model with distinguishing cross-classification effect for gray-scale pixel region images is obtained through learning and training by utilizing the image similarity comparison effect of a convolutional neural network and a sigmoid function. The several groups of gray-scale pocket images with abnormal matching are cross-classified from the normal gray-scale pixel region image template to recognize normal gray-scale pocket images from each group of gray-scale pocket images. Next, the normal pixel features from the distinguishing pixel features of each group are removed, i.e., the corresponding normal gray-scale pocket images are removed, and only the abnormal pocket images corresponding to the abnormal pixel features are left, thereby completing the classification of some groups of gray-scale pocket images with abnormal matching, and finally obtaining each classified abnormal pocket image.

[0042] In S103, the abnormal area image in the abnormal pocket image is recognized and marked to obtain the abnormal marked area in the abnormal pocket image.

[0043] Specifically, an image sequence encoding process is performed on all pocket images in the initial pocket image set to obtain an encoded data set, and an anomaly is marked with an encoding number corresponding to the abnormal pocket image in the encoded data set based on the corresponding position of some abnormal pocket images in the initial pocket image set to obtain an anomaly encoding number.

[0044] In one embodiment, after obtaining an initial pocket image set, an image sequence encoding is performed for each pocket image in the initial pocket image set to construct an encoded data set, and then, after recognizing an abnormal pocket image, the abnormality is marked with an encoding number corresponding to the abnormal pocket image, for example, by marking with a color mark or a special code, and finally, an encoding number of the marked abnormality is obtained.

[0045] Further, the image is segmented based on the grayscale pixel regions corresponding to the abnormal pixel features, for the abnormal pocket images corresponding to the coding numbers of the abnormalities, to obtain the original abnormal region images.The original abnormal region images are subjected to grayscale processing.

[0046] Furthermore, a primary edge image feature constraint is applied to the original grayscale processed abnormal region image by second-order differentiation to obtain a candidate abnormal region. The minimum pixel distance is calculated between the centroid of the candidate abnormal region and the edge image feature region to obtain a distance constraint. The edge image feature region is the edge pixel region of the candidate abnormal region. An edge slope coordinate system is constructed from the candidate abnormal region based on the image corner and centroid in the candidate abnormal region. Based on the edge slope coordinate system, the slope angle direction is located with respect to the image slope pixels in the candidate abnormal region to obtain a direction constraint. A second edge image feature constraint is applied to the candidate abnormal region based on the distance constraint and the direction constraint to obtain an abnormal mark region.

[0047] In one embodiment, the cross-classification network model first obtains the grayscale pixel region corresponding to the input abnormal pixel feature, i.e., determines the abnormal pocket image corresponding to the abnormal code number, then performs image segmentation on the abnormal pocket image using a dividing line to define it as the original abnormal region image, then performs edge image feature constraint on the original abnormal region image using second-order differentiation to obtain a rough candidate abnormal region, then uses the image corner and centroid in the abnormal region to locate the slope angle direction for the image slope pixels in the candidate abnormal region, and calculates the minimum pixel distance between the centroid and edge image feature region of the candidate abnormal region, and respectively performs a second feature constraint on the image edge feature for the candidate abnormal region, i.e., uses direction constraint and distance constraint to further perform image edge feature constraint on the candidate region to obtain the accurate abnormal region of the abnormal pocket image, then performs box selection marking on the accurate abnormal region to box select the abnormal mark region.

[0048] In one possible embodiment, the calculation of the minimum pixel distance in the distance constraint is d ={√((x i -x 平均 ) 2 -(y i -y 平均 ) 2 ),(x i ,y i )∈T}, where T is the upper boundary area of ​​the texture image of the pocket anomaly in the candidate anomaly region, and (x 平均 ,y 平均 ) is the centroid of the abnormal candidate edge of the texture image of the pocket anomaly, and x i and y i are the coordinates of each pixel point in the candidate abnormal region, and D d is the minimum pixel distance. Locating the tilt angle direction relative to the image tilt plane pixel in the direction constraint is θ=0.5 argtan((2M 11 ) / (M 20 -M 02 )) to obtain a relative angle θ of the image tilt plane pixel based on M 11 , M 20, M 02 respectively represent different image corners in the candidate abnormal region, where M ij =Σ (r,c)∈R (r0-r) i (c0-c) j is the image corner, R is the candidate anomaly region, (r0, c0) is the centroid of the candidate region, and (r, c) is the intersection coordinate of the texture image of the pocket anomaly in the candidate anomaly region and its edge.

[0049] In step S104, the pocket abnormality type of the bearing cage is obtained by classifying the pocket abnormality for the abnormal mark area based on the past pocket abnormality database, and the pocket abnormality type includes at least one or more of pocket size abnormality, column inclination abnormality, hole penetration abnormality, and groove depth abnormality.

[0050] Specifically, a pocket anomaly classification matching is performed for the abnormal mark area using a pocket anomaly template in the past pocket anomaly database. If the matching is successful, the type of pocket anomaly corresponding to the pocket anomaly template is determined as the type of pocket anomaly for the abnormal mark area.

[0051] In one embodiment, image template matching is performed between the box-selected abnormal mark area and the pocket abnormality template in the past pocket abnormality database. For example, parameter information such as pocket size information, pillar inclination information, hole area information, and groove depth information in the pocket abnormality template is compared and matched with the corresponding information in the abnormal mark area. If the comparison and matching are successful, the type of pocket abnormality corresponding to the pocket abnormality template is determined as the type of pocket abnormality corresponding to the abnormal mark area, i.e., the type of pocket abnormality corresponding to the abnormal pocket.

[0052] Furthermore, if matching is not successful, the type of pocket abnormality is determined for the abnormal mark area. A line detection algorithm using Hough transform is used to perform line detection of pixel point sets for the horizontal and vertical column pixels of the pocket in the abnormal mark area to obtain pocket size information. A Hough transform is used to calculate the slope of a line for a set of pixels with the same brightness gradient in the abnormal mark area to obtain column slope information. A circle detection algorithm using Hough transform is used to recognize non-intersecting curves in the abnormal mark area to obtain a circular outline area. Based on adjacent connected areas in the abnormal mark area, the area of ​​the same pixel in the circular outline area is calculated to obtain hole area information. Pixel lengths are calculated for concave and convex areas in the abnormal mark area to obtain groove depth information.

[0053] Furthermore, the drawing information is collated with the pocket size information, pillar inclination information, hole area information, and groove depth information to determine the type of pocket abnormality in the abnormal mark area.

[0054] In one embodiment, as shown in Figures 5 and 6, the type of pocket anomaly is determined for an abnormal mark area image that does not match the pocket anomaly template. Using the pixel layout features in the box-selected abnormal mark area, a Hough transform line detection algorithm and a Hough transform circle detection algorithm are used to recognize and obtain information on the brightness features of various pixel point sets in the pocket, the same pixel layout, the distribution of adjacent connected areas, and the same pixel area size, thereby obtaining pocket size information, pillar tilt information, hole area information, and groove depth information, respectively. The error range is then compared with the drawing information uploaded to the pocket inspection system. For example, if the error between the actual area of ​​a single hole after conversion in the hole area information and the reference hole area in the drawing information is within 1%, the hole area information is considered to be acceptable; otherwise, it is considered to be a through-hole anomaly. Finally, the size information, pillar tilt information, and groove depth information of all unacceptable pockets are determined as pocket size anomaly information, pillar tilt anomaly information, and groove depth anomaly information, respectively, to determine the pocket anomaly type corresponding to each abnormal pocket.

[0055] In step S105, the rotary table and the camera are used to take a second pocket image of the abnormal pocket corresponding to the type of the pocket abnormality, thereby obtaining an image of the true pocket abnormality. The laser beam is used to perform beam positioning in the two-dimensional coordinate system relative to the pocket position corresponding to the image of the true pocket abnormality, thereby obtaining position information of the abnormal pocket.

[0056] Specifically, an anomaly coding number of the anomalous pocket corresponding to the type of pocket anomaly is obtained. Based on the sequence position of the anomaly coding number in the coding data set, rotation feedback control is performed on the servo motor of the rotary table to orient the anomalous pocket corresponding to the anomaly coding number toward the camera. In the rotation feedback control, the rotation operation of the servo motor is controlled based on the shooting time interval between the anomaly coding number and the target coding number. Next, the camera takes a second pocket image of some anomalous pockets corresponding to the anomaly coding number to obtain some true pocket anomaly images.

[0057] In one embodiment, after all pocket abnormality types are recognized, the servo motor in the rotary table is controlled to turn off. Then, based on the position in the entire encoding data set of the anomaly code number corresponding to the pocket abnormality type and the position of the camera, the abnormal pocket corresponding to each anomaly code number is re-rotated and moved in front of the camera so that the abnormal pocket corresponding to the anomaly code number faces the camera. The rotation time of the servo motor is determined by the anomaly code number, the target code number in front of the camera, and the camera's shooting time interval. Combined with the constant angular speed of the rotary table, each abnormal pocket of the bearing cage on the rotary table is photographed a second time by the camera, which helps operators view the true status of the bearing cage pockets in the back-end system.

[0058] Furthermore, after obtaining the images of all the true pocket anomalies and the coding numbers of the corresponding several anomalies, a single line laser is irradiated onto several abnormal pockets corresponding to the images of the true pocket anomalies to obtain several laser beams.

[0059] Furthermore, the beam tilt angles of the several laser beams are positioned according to a two-dimensional coordinate system preset on the rotary table to obtain several beam tilt angles, and the position information of several abnormal pockets is determined according to the several beam tilt angles and the encoding numbers of the several abnormal pockets.

[0060] In one embodiment, Figure 3 is a plan view of a two-dimensional coordinate system of a rotary table provided by an embodiment of the present application. As shown in Figures 3 and 2, the two-dimensional coordinate system on the rotary table is used to accurately position the abnormal pocket with the laser beam emitted from the laser emitter, and the beam tilt angle formed by the laser beam at this time is obtained. Then, based on the corresponding abnormality coding number, the position information of the abnormal pocket with the related beam tilt angle-abnormality coding number is obtained.

[0061] In S106, the pocket inspection result of the bearing cage is determined based on the position information of the abnormal pocket, the type of the pocket abnormality, and an image of the true pocket abnormality, and the pocket inspection result is sent to the terminal of the worker.

[0062] Specifically, based on the position information of the abnormal pockets, the abnormality code numbers, and the types of the pocket abnormalities, the position information of the abnormal pockets and the actual images of the pocket abnormalities obtained in the second photograph after feedback control of the rotary table are sent to the pocket inspection system terminal. The pocket inspection results are in tabular data format, with the header including the position information of the abnormal pockets, the type of the pocket abnormality, and the actual images of the pocket abnormalities. The data is then displayed one by one according to the abnormality code number, finally forming the pocket inspection results for the bearing cage. The tabular pocket inspection result data is then displayed to the workers, who can manually review the automatic bearing cage pocket inspection results, further helping to ensure the first-pass rate of the bearing cage, reducing human error and improving the efficiency of bearing cage pocket inspection.

[0063] In addition, an embodiment of the present application also provides a pocket inspection device for a bearing cage. As shown in FIG. 6, the pocket inspection device 600 for a bearing cage specifically includes: The system includes at least one processor 601 and a memory 602 communicatively connected to the at least one processor 601, the memory 602 storing instructions executable by the at least one processor 601, such that the at least one processor 601: taking successive pocket images of a bearing cage on a rotary table with a camera to obtain an initial set of pocket images; Compare and match each pocket image in the initial pocket image set with each other, and based on the comparison and matching result, screen some pocket images in the comparison and matching result that are abnormally matched to obtain some abnormal pocket images; Recognizing and marking an abnormal region image in the abnormal pocket image to obtain an abnormal marked region in the abnormal pocket image; Classifying pocket abnormalities for the abnormal mark area to obtain the type of pocket abnormality of the bearing cage, the type of pocket abnormality including at least one of pocket size abnormality, column inclination abnormality, hole penetration abnormality, and groove depth abnormality; Using the rotary table and the camera, take a second pocket image of the abnormal pocket corresponding to the type of pocket abnormality to obtain an image of the true pocket abnormality, and use the laser beam to perform beam positioning in the two-dimensional coordinate system relative to the pocket position corresponding to the image of the true pocket abnormality to obtain position information of the abnormal pocket; From the position information of the abnormal pocket, the pocket inspection result of the bearing cage can be determined based on the type of pocket abnormality and an image of the actual pocket abnormality, and the pocket inspection result can be transmitted to the operator's terminal.

[0064] In this application, a rotary table and a camera are used to inspect the pockets of the bearing cage, and all the recognized pockets are compared with each other. Then, abnormal pockets are screened to determine the type of pocket abnormality. The location and type of abnormal pocket can be accurately recognized, and the actual image of the pocket abnormality can be sent to the back-end workers, which helps the workers to greatly reduce the amount of pocket inspection work and has a high accuracy rate. Combined with laser positioning, it helps the workers to quickly find pockets with abnormal conditions and determine the corresponding abnormal fault type, which greatly reduces labor costs and improves inspection efficiency. Furthermore, it allows for comprehensive and thorough inspection of pockets, reduces human error, and improves the first-pass rate of bearing cages.

[0065] In this application, each embodiment is described in a chain-like manner, and reference may be made to the same or similar parts between the embodiments, and the description of each embodiment will focus on the differences from other embodiments. In particular, in the case of an apparatus and a non-volatile computer storage medium, since they are similar to the method embodiments, they are described briefly, and reference may be made to the description of the method embodiments for related parts.

[0066] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the examples and still achieve desirable results. Also, processes depicted in the figures do not necessarily achieve desirable results in the particular order or sequential order shown. In some embodiments, multitasking or parallel processing may be possible or beneficial.

[0067] The above-mentioned are merely examples of the present application and are not intended to limit the present application. Those skilled in the art may have various modifications and variations to the present application. Any amendments, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A bearing cage pocket inspection method applied to a bearing cage pocket inspection device, comprising: the bearing cage pocket inspection device includes at least one processor and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, thereby enabling the at least one processor to execute the bearing cage pocket inspection method, the bearing cage pocket inspection method comprising: taking successive pocket images of a bearing cage on a rotary table with a camera to obtain an initial set of pocket images; Comparing and matching each pocket image in the initial pocket image set with each other, and based on the comparison and matching result, screening some pocket images with abnormal matching in the comparison and matching result to obtain some abnormal pocket images, specifically, when the comparison and matching result is abnormal matching, obtaining several groups of grayscale pocket images with abnormal matching; An abnormal area image in the abnormal pocket image is recognized and marked to obtain an abnormal marked area in the abnormal pocket image, specifically, performing an image sequence encoding process on all pocket images in the initial pocket image set to obtain an encoded data set; marking an anomaly against a coding number corresponding to the anomalous pocket image in the coded data set based on a position of some of the anomalous pocket images relative to the initial set of pocket images to obtain a coding number for the anomaly; Segmenting the image into regions for the abnormal pocket image corresponding to the coding number of the abnormality based on the grayscale pixel regions corresponding to the abnormal pixel features to obtain an original abnormal region image, and performing grayscale processing on the original abnormal region image, wherein the abnormal pixel features are pixel features corresponding to the abnormal pocket image in the grayscale pocket image of each group, and each grayscale pocket image is divided into nine grayscale pixel regions; By second-order differentiation, perform elementary edge image feature constraint on the original abnormal region image after grayscale processing to obtain candidate abnormal regions; calculating a minimum pixel distance between the centroid of the candidate abnormal region and an edge image feature region to obtain a distance constraint, wherein the edge image feature region is an edge pixel region of the candidate abnormal region; constructing an edge slope coordinate system from the candidate abnormal region based on the image corners in the candidate abnormal region and the centroid; locating a slope angle direction relative to image slope pixels in the candidate abnormal region based on the edge slope coordinate system to obtain a direction constraint; performing edge image feature constraints on the candidate abnormal regions for a second time based on the distance constraint and the direction constraint to obtain the abnormal mark regions; Classifying pocket abnormalities for the abnormal mark area to obtain a type of pocket abnormality of the bearing cage, the type of pocket abnormality including at least one of pocket size abnormality, column inclination abnormality, hole penetration abnormality, and groove depth abnormality; Using the rotary table and the camera, take a second pocket image of the abnormal pocket corresponding to the type of pocket abnormality to obtain an image of the true pocket abnormality, and perform beam positioning of a laser beam in a two-dimensional coordinate system relative to the pocket position corresponding to the image of the true pocket abnormality to obtain position information of the abnormal pocket; determining a pocket inspection result for the bearing cage based on the position information of the abnormal pocket, the type of the pocket abnormality, and an image of the actual pocket abnormality, and transmitting the pocket inspection result to an operator's terminal.

2. Specifically, the camera takes successive pocket images of the bearing cage on the rotary table to obtain the initial pocket image set. Acquiring drawing information of a bearing cage to be manufactured, the drawing information including at least the number of pockets, the size of the pockets, the radius of the bearing cage, and processing parameters of the columns; inputting the number of pockets and the radius of the bearing cage in the drawing information into a control unit of a rotary table control system, the rotary table control system including the control unit, a servo motor unit, and a laser emission unit; determining an angular velocity of the rotary table from an imaging interval of the camera based on the number of pockets, and photographing each pocket of the bearing cage; Controlling the operation of the rotary table based on the angular velocity of the rotary table, and continuously photographing pockets with the camera relative to the bearing cage to obtain a partial pocket image set, the partial pocket image set being an image set photographed by the camera at an initial plurality of time intervals; According to a preset Canny operator, detect the area of ​​pillar pixels in the grayscale image set of the partial pocket image set to obtain an actual pillar pixel area, and according to the reference pixel area of ​​the pillar, compare the area value of the actual pillar pixel area, and determine the successfully matched actual pillar pixel area as a complete pillar pixel value; The method for inspecting pockets of a bearing cage as described in claim 1, characterized in that it includes determining a pocket image corresponding to the complete pillar pixel value as a first pocket image, and re-feeding back to a control unit of the rotary table control system based on the first pocket image and the shooting time interval of the corresponding camera, thereby completely photographing each pocket of the bearing cage and obtaining the initial pocket image set.

3. Specifically, comparing and matching each pocket image in the initial pocket image set with each other includes: performing grayscale preprocessing on each pocket image to obtain several grayscale pocket images; Dividing the grayscale pocket image into grayscale pixel regions by a predetermined dividing line based on the actual pixel size of the grayscale pocket image, and each of the grayscale pocket images is divided into nine grayscale pixel regions; scanning pixel features in each of the grayscale pixel regions, the pixel features including a brightness gradient feature and a corresponding pixel coordinate location feature of each pixel point; 2. The method for inspecting pockets of a bearing cage according to claim 1, further comprising: performing a similarity comparison matching between each of the grayscale pocket images for several pixel features that correspond one-to-one with each of the grayscale pixel areas in the several grayscale pocket images based on pixel features in each of the grayscale pixel areas to obtain the comparison matching results, wherein the comparison matching results include normal matching and abnormal matching, and the similarity comparison matching is matching the similarities of corresponding pixel features between the grayscale pocket images of any two groups.

4. According to the comparison matching result, screening some pocket images having abnormal matching in the comparison matching result to obtain some abnormal pocket images specifically includes: Extracting distinguishable pixel features and corresponding distinguishable grayscale pixel regions in the several groups of grayscale pocket images, and obtaining normal grayscale pixel regions according to the several normal pocket images whose comparison matching results are normal; Based on a convolutional neural network and a sigmoid function, learning and training the similarity of cross-pixel features related to the distinguished grayscale pixel region and the normal grayscale pixel region to obtain a cross-classification network model, wherein the cross-classification network model uses a Siamese network as a basic structure; Using the cross-classification network model, weights are assigned according to the differences between the distinguishing grayscale pixel regions and the normal grayscale pixel regions, and cross-classification is performed on the grayscale pocket images of the several groups to remove normal pixel features from the distinguishing pixel features and obtain abnormal pixel features from the distinguishing pixel features, where the abnormal pixel features are pixel features corresponding to abnormal pocket images in the grayscale pocket images of each group; 2. The method for inspecting pockets of a bearing cage according to claim 1, further comprising screening several grayscale pixel regions corresponding to the abnormal pixel features to obtain the several abnormal pocket images corresponding thereto.

5. Specifically, the classification of the pocket abnormality for the abnormal mark area to obtain the type of pocket abnormality of the bearing cage is performed as follows: Performing classification matching of pocket abnormalities for the abnormal mark area with a pocket abnormality template in a past pocket abnormality database, and if matching is successful, determining the type of pocket abnormality corresponding to the pocket abnormality template as the type of pocket abnormality for the abnormal mark area; If the matching is not successful, determining a pocket anomaly type for the abnormal mark region; Using a line detection algorithm based on Hough transform, perform line detection of pixel point sets on horizontal and vertical column pixels of pockets in the abnormal mark area to obtain pocket size information; Calculating the slope of a line for a set of pixels with the same brightness gradient in the abnormal mark area by Hough transform to obtain the slope information of the pillar; Using a circle detection algorithm based on Hough transform, the non-intersecting curves in the abnormal mark area are recognized to obtain a circular outline area, and the area of ​​the same pixel in the circular outline area is calculated based on the adjacent connected areas in the abnormal mark area to obtain hole area information; Calculating pixel lengths for the irregular areas in the abnormal mark area to obtain groove depth information; 2. A method for inspecting pockets of a bearing retainer as described in claim 1, characterized in that it includes comparing drawing information with information on the size of the pocket, the tilt of the pillar, the hole area, and the depth of the groove to determine the type of pocket abnormality in the abnormal mark area.

6. Specifically, the method of taking a pocket image for the abnormal pocket corresponding to the type of the pocket abnormality for the second time using the rotary table and the camera to obtain an image of the true pocket abnormality includes: Obtaining an abnormality coding number of the abnormal pocket corresponding to the pocket abnormality type; performing rotation feedback control on a servo motor of the rotary table based on a sequence position in the encoding data set of the anomaly encoding number, so as to face the anomaly pocket corresponding to the anomaly encoding number to the camera, wherein the rotation feedback control controls the rotation operation of the servo motor based on a photographing time interval between the anomaly encoding number and the target encoding number; 2. The method for inspecting pockets in a bearing cage according to claim 1, further comprising using the camera to take pocket images a second time for several abnormal pockets corresponding to the coded numbers of the abnormalities, thereby obtaining images of several of the true pocket abnormalities.

7. Specifically, the method of obtaining position information of the abnormal pocket by using a laser beam to perform beam positioning in a two-dimensional coordinate system relative to the pocket position corresponding to the image of the true pocket abnormality includes: After obtaining all the images of the true pocket anomalies and the corresponding coded numbers of the anomalies, irradiating the laser beam with a single line laser on the several abnormal pockets corresponding to the images of the true pocket anomalies to obtain several laser beams; 2. The method for inspecting pockets of a bearing cage according to claim 1, further comprising: positioning beam inclination angles for the several laser beams according to a two-dimensional coordinate system preset on a rotary table to obtain several beam inclination angles; and determining position information of several abnormal pockets based on the several beam inclination angles and the several abnormality coding numbers.

8. at least one processor; a memory communicatively connected to the at least one processor; A bearing retainer pocket inspection device characterized in that the memory stores instructions that can be executed by the at least one processor, thereby enabling the at least one processor to perform the bearing retainer pocket inspection method described in any one of claims 1 to 7.

Images