CN115493843B - Quality monitoring method and equipment based on bearing retainer - Google Patents
Quality monitoring method and equipment based on bearing retainer Download PDFInfo
- Publication number
- CN115493843B CN115493843B CN202211442372.0A CN202211442372A CN115493843B CN 115493843 B CN115493843 B CN 115493843B CN 202211442372 A CN202211442372 A CN 202211442372A CN 115493843 B CN115493843 B CN 115493843B
- Authority
- CN
- China
- Prior art keywords
- image
- shadow
- bearing retainer
- information
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a quality monitoring method and equipment based on a bearing retainer, belongs to the technical field of image processing, and is used for solving the technical problems that in the conventional finished workpiece of the bearing retainer, partial repairable defective products are difficult to monitor and screen out, so that the waste of resources is easily caused, and the unnecessary production cost is increased. The method comprises the following steps: carrying out weight detection on the bearing retainer in the preset area to obtain weight information of the bearing retainer; performing metal surface characteristic detection on a first image corresponding to the bearing retainer to obtain smoothness information of the bearing retainer; generating a second image corresponding to a front shadow and a third image corresponding to a side shadow of the bearing holder by direct light in a preset area; detecting the shadow features of the image to obtain shadow feature information; and judging the area threshold of the weight information, the smoothness information and the shadow characteristic information of the bearing retainer to obtain the quality result of the bearing retainer.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a quality monitoring method and apparatus based on a bearing retainer.
Background
Cage (i.e., bearing cage, also known as a bearing retainer) refers to a bearing component that partially encases all or part of the rolling elements and moves with them to isolate the rolling elements and generally also guide and retain them within the bearing.
The manufacturing process of the bearing retainer mainly comprises the following steps: blanking, punching all pockets and pocket beams, rolling and welding, shaping, finishing and surface sand blasting. The bearing retainer is an important component of the rolling bearing, and once an abnormality occurs, the use of the rolling bearing is directly influenced, so that the monitoring of the finished product quality of the bearing retainer is a necessary condition for ensuring the normal operation of the rolling bearing.
At present, the finished product monitoring of the bearing retainer generally adopts manual detection to detect the finished product, uniform recovery processing is carried out on some unqualified finished products or defective finished products, some defective products meet repairable standards, but the defective products are uniformly treated as reported waste products, the repairable defective products are difficult to be screened out for secondary processing, resource waste is caused, the production cost of enterprises is increased, and the improvement of enterprise benefits is not facilitated.
Disclosure of Invention
The embodiment of the application provides a quality monitoring method and equipment based on a bearing retainer, which are used for solving the following technical problems: in the conventional finished workpiece of the bearing retainer, partial repairable defective products are difficult to monitor and screen, so that resource waste is easily caused, and unnecessary production cost is increased.
The embodiment of the application adopts the following technical scheme:
in one aspect, an embodiment of the present application provides a quality monitoring method based on a bearing retainer, where the method includes: carrying out weight detection on a bearing retainer in a preset area to obtain weight information of the bearing retainer; identifying the bearing retainer corresponding to the weight information to obtain identification information; carrying out metal surface characteristic detection on a first image corresponding to the bearing retainer to obtain smoothness information of the bearing retainer; generating a front shadow and a side shadow of the bearing holder by direct light rays in the preset area; acquiring images of the bearing retainer and the corresponding front shadow thereof to obtain a second image of the bearing retainer, and acquiring images of the bearing retainer and the corresponding side shadow thereof to obtain a third image of the bearing retainer; detecting the shadow features of the second image and the third image to obtain shadow feature information of the bearing retainer; wherein the shadow feature information at least comprises: aperture shadow feature information, roundness shadow feature information and shadow line slope feature information; and judging the area threshold of the weight information, the smoothness information and the shadow characteristic information of the bearing retainer to obtain the quality result of the bearing retainer, and feeding the quality result back to quality monitoring personnel according to the identification information.
According to the embodiment of the application, the weight of the bearing retainer, the smoothness of the metal surface and the shadow characteristic information of the bearing retainer are acquired, so that the finished workpiece of the bearing retainer is detected in all directions, the size, the shape, the burrs and the line angle of the workpiece can better meet the standard, and the use standard of the workpiece is met. Meanwhile, the bearing retainer capable of being repaired for the second time is detected out and repaired to reach the use standard, so that the cost is greatly reduced, the waste of resources is reduced, and by utilizing the marks of different color serial numbers of each workpiece, quality inspectors can more visually monitor which defective products can be repaired and which defective products cannot be repaired, so that the cost of manual detection is reduced, the monitoring efficiency of the quality inspectors is improved, the waste of available resources is also reduced, and the operating benefits of enterprises are improved.
In a possible embodiment, the metal surface feature detection is performed on the first image corresponding to the bearing holder to obtain the smoothness information of the bearing holder, and specifically includes: carrying out first photographing on the bearing retainer through a camera device in a preset rectangular area to obtain a first image; the camera device is positioned right above the rectangular area; acquiring light component parameters of indoor light in the rectangular area, and acquiring a highlight pixel value of a highest brightness area according to the brightness degree of the first image and the light component parameters; wherein the optical component parameter is a light refractive index value corresponding to different metals; carrying out linear reverse color mixing on the highlight pixel value to enable the brightness of a pixel area corresponding to the highlight pixel value to be reduced, and obtaining a defogged image; carrying out gray level conversion on the defogged image to obtain a gray level defogged image; carrying out image segmentation on the background area image and the bearing retainer entity area image in the defogged image through a first preset threshold value to obtain a first segmentation image; wherein the bearing retainer solid area image comprises a defect area image and a highlight area image; performing image segmentation on the defective area image and the highlight area image in the bearing retainer entity area image through a second preset threshold value to obtain a second segmentation image; according to the first divided image and the area images divided from the second divided image, removing redundant area images from the gray defogged image to obtain a metal surface characteristic point image of the gray defogged image; wherein the unnecessary region image includes: the highlight area image and the background area image; calculating the ratio of the image area of the metal surface characteristic point image to the gray defogging image to obtain the smoothness information of the bearing retainer; wherein the smoothness information represents a coverage of the bearing retainer defect area.
This application embodiment carries out the acquirement of metal surface smoothness to the first image of bearing retainer, is favorable to accurate burr and the flaw area that detects the bearing retainer surface, makes the bearing retainer have strict quality control standard, and the metal smoothness of controlling each bearing retainer is accurate, and it is improper to hold because of the quality control in the reduction use, causes the damage of bearing device.
In a possible implementation manner, the calculating the ratio of the image areas of the metal surface feature point image and the grayscale defogged image specifically includes: determining a color value of reflected light of the metal surface according to the Fresnel reflectivity of the metal surface in the bearing retainer; wherein the reflected light color values comprise reflected linear values and reflected RGB values; according to the reflected light color value, carrying out surface halo characteristic screening on the metal surface characteristic point image to determine a surface halo characteristic point image; removing the surface halo characteristic point image from the metal surface characteristic point image to obtain a metal surface flaw image; and calculating the ratio of the image area of the metal surface flaw image to the gray defogging image to obtain the smoothness information of the bearing retainer.
In a possible embodiment, the weight detection of the bearing holder in the preset area to obtain the weight information of the bearing holder specifically includes: arranging the plurality of bearing retainers by a preset automatic arranging machine; and transporting the aligned rows of the plurality of bearing retainers into a conveyor belt; sequentially feeding the plurality of bearing retainers into the preset area through the conveyor belt based on a preset time interval; the device comprises a preset area, a weighing device, a high-pressure gas injection device and a control device, wherein the preset area is a semi-closed space, the weighing device is arranged below the preset area, and the high-pressure gas injection device is arranged in the horizontal direction of the preset area; detecting the weight of the bearing retainer through the weighing device to obtain initial weight information; according to a third preset threshold, judging a threshold interval of the initial weight information; and performing gas injection type screening on the bearing holders corresponding to the initial weight which does not meet the threshold interval by the high-pressure gas injection device to obtain the screened weight information of the bearing holders.
This application embodiment carries out preliminary judgement through the weight to the bearing retainer earlier, lets some weight lightness or overweight bearing retainer carry out direct elimination to through high-pressure gas injection apparatus, these unqualified products are fallen in the automatic processing, simplify the monitoring process to the bearing retainer, accelerate the efficiency of its monitoring, realize the preliminary screening to the bearing retainer.
In a possible embodiment, the image obtaining the image of the bearing holder and the corresponding front shadow thereof to obtain the second image of the bearing holder, and the image obtaining the image of the bearing holder and the corresponding side shadow thereof to obtain the third image of the bearing holder specifically includes: irradiating the bearing holder according to light emitting devices in two directions based on a preset time interval; wherein, the light emitting device of two directions includes: the first light emitting device is positioned right in front of the bearing retainer, and the second light emitting device is positioned at the right side of the bearing retainer; irradiating the bearing retainer with front light through the first light emitting device to obtain a front shadow of the bearing retainer, and acquiring images of the bearing retainer and the front shadow thereof through a camera device in a preset rectangular area to obtain a second image; after the second image is obtained, right-side light irradiation is performed on the bearing retainer through the second light emitting device to obtain a side shadow of the bearing retainer, and the bearing retainer and the side shadow thereof are subjected to image acquisition through a camera device in a preset rectangular area to obtain a third image.
The shadow of the front and the right side of the bearing retainer is respectively obtained through the light emitting device, the image containing the shadow is respectively obtained, the light rays at different angles are favorably used, the internal and external features of the bearing retainer are uniformly obtained, namely the structural features of the dead angle position of the camera are obtained, the defect of the bearing retainer, which is not easy to find, can be further obtained, the bearing retainer is favorably accurately and compactly detected, the probability of missed detection is reduced, and the omnibearing detection of the bearing retainer is realized.
In a possible implementation, before the detecting the image shadow feature of the second image and the third image to obtain the shadow feature information of the bearing holder, the method further includes: carrying out integral image splicing on the second image and the third image to obtain a spliced image; carrying out color feature identification on the spliced image to obtain a single color area image; wherein the single color region image includes: a vivid color area image and a dim color area image; overlapping the spliced image and the vivid color image to obtain a color overlapping area image, and deleting the color overlapping area image in the spliced image to obtain an initial shadow characteristic image; identifying edge contour features of the initial shadow feature image to obtain an edge contour pixel value distribution map; determining a contour characteristic image according to the cross entropy of the pixel value distribution probability in the edge contour pixel value distribution diagram; wherein the contour feature image comprises: continuous profile feature images and discontinuous profile feature images; overlapping the non-continuous contour characteristic image and the initial shadow characteristic image to obtain a contour overlapping area, and deleting the contour overlapping area in the initial shadow characteristic image to obtain a shadow characteristic image; wherein the shadow feature image is a shadow image of the bearing retainer.
In a possible implementation manner, the detecting the image shadow feature of the second image and the third image to obtain the shadow feature information of the bearing holder specifically includes: detecting the sizes of a plurality of window holes of the bearing retainer in the shadow feature image to obtain the window hole shadow size, and calculating the ratio of the window hole shadow size to the real size of the window hole in the first image to obtain window hole shadow feature information; carrying out roundness detection on the bowl-shaped structure of the bearing retainer in the shadow feature image to obtain shadow roundness, and carrying out ratio calculation on the shadow roundness and the real roundness in the first image to obtain roundness shadow feature information; performing slope detection on the line of the bearing retainer in the shadow feature image to obtain a line shadow slope, and performing ratio calculation on the line shadow slope and the real slope of the line in the first image to obtain shadow line slope feature information; and obtaining shadow characteristic information of the bearing retainer according to the aperture window shadow characteristic information, the roundness shadow characteristic information and the shadow line slope characteristic information.
The embodiment of the application realizes the entity detection of the bearing retainer by acquiring the aperture shadow characteristic information, the roundness shadow characteristic information and the line shadow slope in the shadow picture of the bearing retainer, the formation of the shadow has a certain proportional relation with a standard device, when the proportional relation is not accordant, namely the shadow characteristic information is not accordant with the standard bearing retainer information, the device can be judged to have problems, the shadow picture can be detected, the detection is more simple, convenient and comprehensive, a plurality of pictures acquired by shooting the entity of the bearing retainer at multiple angles are not required to be processed, and the multi-angle omnibearing monitoring of the bearing retainer can be realized only by one camera and light sources in different directions.
In a possible implementation manner, the determining the region threshold for the weight information, the smoothness information, and the shadow feature information of the bearing holder to obtain the quality result of the bearing holder specifically includes: performing quality judgment on the weight information, smoothness information and shadow characteristic information of the bearing retainer through a preset quality threshold; wherein the quality threshold comprises: a standard weight threshold, a standard smoothness threshold, and a standard shadow feature threshold; if the numerical value of the weight information is larger than or equal to the standard weight threshold value, determining the weight information as first repairable information; if the weight information is first repairable information and the numerical value of the smoothness information is smaller than or equal to the standard smoothness threshold, determining the smoothness information as second repairable information; if the smoothness information is second repairable information and the numerical value of the shadow feature information is smaller than or equal to a standard shadow feature threshold, determining the shadow feature information as third repairable information; and if the third repairable information is acquired, the quality result of the bearing retainer is a repairable defective product, otherwise the quality result of the bearing retainer is an unrepairable defective product.
The embodiment of the application selects the repairable defective product and the unrepairable defective product by detecting the bearing retainer, the repairable defective product also contains the standard workpiece, the bearing retainer can be repaired after the standard workpiece is put forward, the cost is reduced by secondarily repairing the bearing retainer, the resource waste is reduced, the repaired bearing retainer can also be a device which is repaired and meets the standard, the secondary recycling of the resource is realized, and the quality standard of the product is also ensured.
In a possible implementation manner, feeding back the quality result to a quality monitoring staff according to the identification information specifically includes: marking serial numbers of the plurality of bearing retainers according to the identification information to obtain original marked serial numbers; judging whether the repairable defective products are repaired or not; if the repairable defective product is a standard component, color labeling the original labeled serial number corresponding to the standard component to obtain a green labeled serial number; if the repairable defective product is a repairable component, color labeling is carried out on an original labeling serial number corresponding to the repairable component to obtain a yellow labeling serial number; carrying out color marking on the original marking serial number corresponding to the unrepairable defective product to obtain a red marking serial number; and sending the green marking serial number, the yellow marking serial number and the red marking serial number corresponding to the quality result of the bearing retainer to a quality monitoring worker to realize quality monitoring of the bearing retainer.
In another aspect, an embodiment of the present application further provides a quality monitoring apparatus based on a bearing retainer, where the apparatus includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of bearing-holder-based quality monitoring according to any of the embodiments described above.
The embodiment of the application provides a quality monitoring method and equipment based on a bearing retainer, which realize the all-round detection of a finished workpiece of the bearing retainer by acquiring the weight of the bearing retainer, the smoothness of a metal surface and shadow characteristic information of the metal surface, so that the size, the shape, the burr and the line angle of the workpiece can better meet the standard and reach the use standard of the workpiece. Meanwhile, the bearing retainer capable of being repaired for the second time is detected out and repaired to reach the use standard, so that the cost is greatly reduced, the waste of resources is reduced, and by utilizing the marks of different color sequence numbers of each workpiece, quality inspectors can more intuitively monitor which defective products can be repaired and which defective products cannot be repaired, so that the cost of manual detection is reduced, the monitoring efficiency of the quality inspectors is improved, the waste of available resources is reduced, and the operating benefits of enterprises are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
FIG. 1 is a flow chart of a method for monitoring quality of a bearing retainer according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a shaded area of a bearing retainer according to an embodiment of the present disclosure;
FIG. 3 is a schematic view of an overall monitoring process of a bearing retainer according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a quality monitoring device based on a bearing retainer according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
The embodiment of the application provides a quality monitoring method based on a bearing retainer, and as shown in fig. 1, the quality monitoring method based on the bearing retainer specifically comprises the following steps of S101-S105:
s101, carrying out weight detection on the bearing retainer in the preset area to obtain weight information of the bearing retainer, and identifying the bearing retainer corresponding to the weight information to obtain identification information.
Specifically, an automatic arraying machine is preset to carry out arraying treatment on a plurality of bearing retainers; and transporting the aligned rows of the plurality of bearing holders to a conveyor.
Further, a plurality of bearing holders are sequentially fed into a preset area by a conveyor belt based on a preset time interval. The device comprises a preset area, a weighing device, a high-pressure gas injection device and a control device, wherein the preset area is a semi-closed space, the weighing device is arranged below the preset area, and the high-pressure gas injection device is arranged in the horizontal direction of the preset area. The weight of the bearing retainer is detected by the weighing device, and initial weight information is obtained.
Furthermore, a plurality of serial numbers are marked on the bearing retainer corresponding to the weight information, and the identification information of all the bearing retainers is obtained according to the marked serial numbers of the bearing retainers after marking.
Further, according to a third preset threshold, threshold interval judgment is carried out on the initial weight information. And carrying out gas injection type screening on the bearing retainer corresponding to the initial weight which does not meet the threshold interval by using the high-pressure gas injection device to obtain the weight information of the screened bearing retainer.
In an embodiment, fig. 3 is a schematic view of an overall monitoring process of a bearing holder provided by the embodiment of the present application, as shown in fig. 3, a bearing holder to be detected is conveyed to a quality monitoring area through a conveyor belt, and passes through a weighing device installed at a lower end of the quality monitoring area, weight detection is performed on each bearing holder entering the quality monitoring area, a serial number is marked on each bearing holder, interval weight values are identified according to preset threshold values and symmetric weight information, the bearing holders which do not meet the threshold interval are identified, and a high-pressure gas sprayed by a high-pressure spraying device is used to blow off unqualified devices, leave qualified bearing holders, record weight information of qualified devices, and store the weight information to a data rear end.
S102, metal surface feature detection is carried out on the first image corresponding to the bearing retainer, and smoothness information of the bearing retainer is obtained.
Specifically, a first photograph is taken of the bearing holder by a camera in a preset rectangular area, and a first image is obtained. The camera device is located right above the rectangular area. And acquiring light component parameters of indoor light in the rectangular region, wherein the light component parameters are light refractive index values corresponding to different metals. And acquiring a highlight pixel value of the highest brightness area according to the brightness degree and the light component parameters of the first image.
In one embodiment, the production and detection links of the bearing retainers are generally performed indoors, the brightness degree of the first image is affected by indoor light, the indoor light is stable, and the actual brightness degree of different pixel areas in each image corresponding to each bearing retainer can be stably obtained. The light component parameter of the indoor light is the light refractive index value of each metal generated by the indoor light irradiating on the surface of different metal parts, for example, the minimum value of the refractive index of copper is 1.100, the maximum value is 2.430, the minimum value of the refractive index of iron is 2.950I, the minimum value of the refractive index of nickel is 1.080, the minimum value of the refractive index of aluminum is 1.390, and the maximum value is 1.440, etc.
And further, carrying out linear reverse color mixing on the highlight pixel value to enable the brightness of a pixel area corresponding to the highlight pixel value to be adjusted downwards, and obtaining the defogged image.
In one embodiment, as shown in FIG. 3, a first image of the bearing retainer in the quality inspection area is first acquired and then the first image is subjected to a defogging process. Because the brightness of the reflective area of the bearing retainer is high, under the condition of indoor light, the brightness distribution of the metal surface is not uniform based on the curvature of the metal surface, the first image needs to be defogged, 0.5% of high-brightness pixels of the highest-brightness area are extracted through three channels of RGB and light component parameters of indoor light in each channel window according to the brightness of the first image, then the high brightness is analyzed according to linearity, the reverse color matching is carried out on the high brightness, the brightness in the area is reduced, and the defogged image after primary processing can be obtained.
And further, carrying out gray level conversion on the defogged image to obtain a gray level defogged image. And carrying out image segmentation on the background area image and the bearing retainer solid area image in the defogged image through a first preset threshold value to obtain a first segmentation image. Wherein the bearing retainer solid area image comprises a defect area image and a highlight area image.
Further, image segmentation is carried out on the defective area image and the highlight area image in the bearing retainer solid area image through a second preset threshold value, and a second segmentation image is obtained.
In one embodiment, the defogged image is subjected to multi-threshold segmentation through a first preset threshold and a second preset threshold, that is, the background area image, the solid area image, the defect area image and the highlight area image are respectively subjected to image segmentation according to different threshold standards, and finally a first segmentation image and a second segmentation image are obtained.
And further, according to the area images divided from the first divided image and the second divided image, removing redundant area images from the gray defogged image to obtain a metal surface characteristic point image of the gray defogged image. Wherein the unnecessary area image includes: a highlight region image and a background region image.
And further, calculating the ratio of the image area of the metal surface characteristic point image to the gray defogged image to obtain the smoothness information of the bearing retainer. Wherein the smoothness information indicates a coverage of the defective area of the bearing holder.
In one embodiment, smoothness information of the metal surface of the bearing retainer can be obtained through the coverage rate of the defect area of the bearing retainer by dividing the image and the area image divided from the second divided image, removing the redundant area image from the gray defogged image to obtain the metal surface characteristic point image of the gray defogged image, and then calculating the ratio of the image area to the gray defogged image.
Wherein, according to the Fresnel reflectivity of the metal surface in the bearing retainer, the color value of the reflected light of the metal surface is determined. The color value of the reflected light comprises a reflection linear value and a reflection RGB value. And according to the color value of the reflected light, carrying out surface halo characteristic screening on the metal surface characteristic point image to determine the surface halo characteristic point image. And removing the surface halo characteristic point image from the metal surface characteristic point image to obtain a metal surface flaw image. And calculating the ratio of the image area of the metal surface flaw image to the gray defogging image to obtain the smoothness information of the bearing retainer.
In one embodiment, the metal surface feature point image further comprises a surface halo feature of the metal surface, the halo portion of the metal surface is subjected to morphological processing according to the Fresnel reflectivity of the reflected light color, then the halo portion is obtained after the noisy interference of the surface is removed, the surface halo feature point image is determined according to the image area feature corresponding to the halo portion, then the image area corresponding to the surface halo feature point image is removed to obtain an image only containing metal surface defects, then the image area ratio is calculated with the gray defogged image, and finally the smoothness information of the bearing retainer is obtained.
S103, generating a front shadow and a side shadow of the bearing retainer through direct light rays in a preset area. The image acquisition is performed on the bearing retainer and the corresponding front shadow thereof to obtain a second image of the bearing retainer, and the image acquisition is performed on the bearing retainer and the corresponding side shadow thereof to obtain a third image of the bearing retainer.
Specifically, the bearing holder is irradiated according to the light emitting devices in two directions based on a preset time interval. Wherein, the light emission device of two directions includes: a first light emitting device located right in front of the bearing holder and a second light emitting device located right to the bearing holder.
In one embodiment, as shown in fig. 3, the light emitting devices located in two different directions in fig. 3 emit light, and the emitted artificial light sources irradiate the bearing holder at different angles, so that the bearing holder forms two shadows in two different directions, thereby facilitating the subsequent acquisition of two shadow images in two different directions. Compared with an indoor light source, the shadow can be formed more clearly and stably by using the added artificial light source with higher intensity for irradiation, and the error in image acquisition is reduced.
Further, through a first light emitting device, right ahead light irradiation is carried out on the bearing retainer to obtain a front shadow of the bearing retainer, and through a camera device in a preset rectangular area, the bearing retainer and the front shadow thereof are subjected to image acquisition to obtain a second image.
Further, after the second image is acquired, right-side light irradiation is performed on the bearing holder by the second light emitting device to obtain a side shadow of the bearing holder, and image acquisition is performed on the bearing holder and the side shadow thereof by the image pickup device in the preset rectangular area to obtain a third image.
In an embodiment, fig. 2 is a schematic diagram of a shadow area of a bearing holder provided in an embodiment of the present application, and as shown in fig. 2, after a bearing holder to be detected is sent to a quality monitoring area, light is emitted by a first light emitting device and a first light emitting device located right in front of the bearing holder to generate a shadow of the bearing holder, and then a camera right above the quality monitoring area is used to photograph an entity and the shadow of the front side of the bearing holder to obtain a second image. And then starting a second light emitting device, irradiating the side of the bearing retainer to obtain a side shadow, and taking a second photograph of the side shadow and the entity of the bearing retainer through a camera right above to obtain a third image.
S104, detecting the image shadow features of the second image and the third image to obtain shadow feature information of the bearing retainer. Wherein the shadow feature information at least comprises: aperture window shading characteristic information, roundness shading characteristic information, and shading line slope characteristic information.
Specifically, the second image and the third image are subjected to image integral splicing to obtain a spliced image. And carrying out color feature identification on the spliced image to obtain a single color area image. Wherein the single color region image includes: a vivid color area image and a dim color area image. And overlapping the spliced image and the vivid color image to obtain a color overlapping area image, and deleting the color overlapping area image in the spliced image to obtain an initial shadow characteristic image.
Further, the edge contour features of the initial shadow feature image are identified, and an edge contour pixel value distribution graph is obtained. And determining the profile characteristic image according to the cross entropy of the pixel value distribution probability in the edge profile pixel value distribution diagram. Wherein the contour feature image includes: a continuous profile feature image and a discontinuous profile feature image.
In one embodiment, the edge contour feature is identified for the initial shadow feature image, and the cross entropy of the pixel value distribution probability in the edge contour pixel value distribution diagram is determined according to the cross entropy, which is the pixel texture feature between the edge contour pixel value and the background pixel, wherein the smaller the similarity value of the texture between the images is, the larger the difference of the texture between the images is, and the larger the entropy value is.
Further, image overlapping is carried out on the non-continuous outline characteristic image and the initial shadow characteristic image to obtain an outline overlapping area, and the outline overlapping area in the initial shadow characteristic image is deleted to obtain a shadow characteristic image. Wherein the shadow feature image is a shadow image of the bearing holder.
In one embodiment, the discontinuous outline characteristic images are overlapped with the initial shadow characteristic images, so that the discontinuous outline characteristic images in the initial shadow characteristic images are eliminated, and only the shadow characteristic images related to the continuous outline characteristic images are reserved.
Further, size detection is carried out on a plurality of window holes of the bearing retainer in the shadow feature image to obtain window hole shadow sizes, and ratio calculation is carried out on the window hole shadow sizes and the real size of the window hole in the first image to obtain window hole shadow feature information.
Further, carrying out roundness detection on the bowl-shaped structure of the bearing retainer in the shadow feature image to obtain the roundness of the shadow, and carrying out ratio calculation on the roundness of the shadow and the real roundness in the first image to obtain roundness shadow feature information.
Further, slope detection is carried out on lines of the bearing retainer in the shadow feature image to obtain line shadow slope, and ratio calculation is carried out on the line shadow slope and the real slope of the lines in the first image to obtain shadow line slope feature information.
And obtaining shadow characteristic information of the bearing retainer according to the window hole shadow characteristic information, the roundness shadow characteristic information and the shadow line slope characteristic information.
In one embodiment, the window shadow characteristic information, the roundness shadow characteristic information and the shadow line slope characteristic information in the shadow characteristic information are acquired, so that the device characteristics of the shadow area corresponding to the bearing retainer can be accurately and comprehensively acquired, the probability of missing detection is reduced, the bearing retainer can be comprehensively detected by using fewer images, the difficulty of image information processing is reduced, and the monitoring efficiency of the bearing retainer is improved.
S105, judging the area threshold of the weight information, the smoothness information and the shadow characteristic information of the bearing retainer to obtain the quality result of the bearing retainer, and feeding the quality result back to quality monitoring personnel according to the identification information.
Specifically, the weight information, the smoothness information, and the shadow feature information of the bearing holder are subjected to quality judgment by presetting a quality threshold. Wherein the quality threshold comprises: a standard weight threshold, a standard smoothness threshold, and a standard shadow feature threshold.
And if the numerical value of the weight information is greater than or equal to the standard weight threshold value, determining the weight information as first repairable information. And if the weight information is first repairable information and the numerical value of the smoothness information is less than or equal to the standard smoothness threshold, determining the smoothness information as second repairable information.
And if the smoothness information is second repairable information and the numerical value of the shadow feature information is less than or equal to the standard shadow feature threshold, determining the shadow feature information as third repairable information. If the third repairable information is acquired, the quality result of the bearing holder is a repairable defective item, otherwise the quality result of the bearing holder is an unrepairable defective item.
In one embodiment, the weight information, smoothness information, and shadow signature information of the support holder are quality monitored by a preset quality threshold. And according to the layer-by-layer control of quality monitoring, whether the bearing retainer belongs to a repairable defective product or a non-repairable defective product is determined. Wherein, the repairable defect product also comprises devices which completely meet the standard.
Furthermore, serial numbers of the bearing retainers are marked through the identification information, and original marked serial numbers are obtained.
Further, the repairable defective item is judged whether to be repaired or not.
And if the repairable defective product is a standard component, performing color marking on the original marking serial number corresponding to the standard component to obtain a green marking serial number. And if the repairable defective product is a repairable component, performing color marking on the original marking serial number corresponding to the repairable component to obtain a yellow marking serial number. And carrying out color marking on the original marking serial number corresponding to the unrepairable defective product to obtain a red marking serial number.
And further, sending the green marking serial number, the yellow marking serial number and the red marking serial number corresponding to the quality result of the bearing retainer to a quality monitoring worker so as to realize quality monitoring of the bearing retainer.
In one embodiment, the repairable defect is a repairable part, shadow characteristic information comprises parts of which partial window holes are not punched, lines of the partial window holes are slightly inclined, the partial window holes are small in size, the partial window holes are not punched completely, and the like, and shadow characteristic information also belongs to the repairable part when the parts of which the roundness is slightly deformed, the smoothness is poor, burrs and the like, so that the bearing holders corresponding to the conditions are marked with yellow marking serial numbers and then fed back to a quality monitoring person at the monitoring rear end, the quality monitoring person finds the corresponding bearing holder according to the yellow marking serial number and repairs the bearing holder for the second time, the secondary utilization of available resources is realized, and the production cost of enterprises is reduced.
In addition, an embodiment of the present application further provides a quality monitoring device based on a bearing holder, and as shown in fig. 4, the quality monitoring device 400 based on a bearing holder specifically includes:
at least one processor 401; and a memory 402 communicatively coupled to the at least one processor 401; wherein the memory 402 stores instructions executable by the at least one processor 401 to enable the at least one processor 401 to:
carrying out weight detection on the bearing retainer in the preset area to obtain weight information of the bearing retainer; identifying the bearing retainer corresponding to the weight information to obtain identification information;
performing metal surface characteristic detection on a first image corresponding to the bearing retainer to obtain smoothness information of the bearing retainer;
generating a front shadow and a side shadow of the bearing holder by direct light rays in the preset area; acquiring images of the bearing retainer and the corresponding front shadow thereof to obtain a second image of the bearing retainer, and acquiring images of the bearing retainer and the corresponding side shadow thereof to obtain a third image of the bearing retainer;
detecting the shadow features of the second image and the third image to obtain shadow feature information of the bearing retainer; wherein the shadow feature information at least includes: aperture window shadow feature information, roundness shadow feature information and shadow line slope feature information;
and judging the regional threshold value of the weight information, the smoothness information and the shadow characteristic information of the bearing retainer to obtain the quality result of the bearing retainer, and feeding the quality result back to a quality monitoring worker according to the identification information.
The embodiment of the application provides a quality monitoring method and equipment based on a bearing retainer, which realize the all-round detection of a finished workpiece of the bearing retainer by acquiring the weight of the bearing retainer, the smoothness of a metal surface and shadow characteristic information of the metal surface, so that the size, the shape, the burr and the line angle of the workpiece can better meet the standard and reach the use standard of the workpiece. Meanwhile, the bearing retainer capable of being repaired for the second time is detected out and repaired to reach the use standard, so that the cost is greatly reduced, the waste of resources is reduced, and by utilizing the marks of different color serial numbers of each workpiece, quality inspectors can more visually monitor which defective products can be repaired and which defective products cannot be repaired, so that the cost of manual detection is reduced, the monitoring efficiency of the quality inspectors is improved, the waste of available resources is also reduced, and the operating benefits of enterprises are improved.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the embodiments of the present application pertain. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the embodiments of the present application shall be included in the scope of the claims of the present application.
Claims (8)
1. A method of quality monitoring based on a bearing retainer, the method comprising:
carrying out weight detection on a bearing retainer in a preset area to obtain weight information of the bearing retainer; identifying the bearing retainer corresponding to the weight information to obtain identification information;
carrying out metal surface feature detection on a first image corresponding to the bearing retainer to obtain smoothness information of the bearing retainer, and specifically comprising the following steps:
carrying out first photographing on the bearing retainer through a camera device in a preset rectangular area to obtain a first image; the camera device is positioned right above the rectangular area;
acquiring light component parameters of indoor light in the rectangular area, and acquiring a highlight pixel value of a highest brightness area according to the brightness degree of the first image and the light component parameters; wherein the optical component parameter is a light refractive index value corresponding to different metals;
carrying out linear reverse color matching on the highlight pixel value to enable the brightness of a pixel area corresponding to the highlight pixel value to be adjusted downwards, and obtaining a defogged image;
carrying out gray level conversion on the defogged image to obtain a gray level defogged image; performing image segmentation on the background area image and the bearing retainer entity area image in the defogged image through a first preset threshold value to obtain a first segmentation image; wherein the bearing retainer solid area image comprises a defect area image and a highlight area image;
performing image segmentation on the defective area image and the highlight area image in the bearing retainer entity area image through a second preset threshold value to obtain a second segmentation image;
according to the area images divided from the first divided image and the second divided image, removing redundant area images from the gray defogged image to obtain a metal surface characteristic point image of the gray defogged image; wherein the unnecessary region image includes: the highlight area image and the background area image;
calculating the ratio of the image area of the metal surface characteristic point image to the gray defogging image to obtain the smoothness information of the bearing retainer; wherein the smoothness information represents a coverage of the bearing holder flaw area;
generating a front shadow and a side shadow of the bearing holder by direct light rays in the preset area; acquiring images of the bearing retainer and the corresponding front shadow thereof to obtain a second image of the bearing retainer, and acquiring images of the bearing retainer and the corresponding side shadow thereof to obtain a third image of the bearing retainer;
detecting image shadow features of the second image and the third image to obtain shadow feature information of the bearing retainer; wherein the shadow feature information at least comprises: aperture window shadow feature information, roundness shadow feature information and shadow line slope feature information;
carrying out region threshold judgment on the weight information, the smoothness information and the shadow characteristic information of the bearing retainer to obtain a quality result of the bearing retainer, and specifically comprising the following steps:
performing quality judgment on the weight information, smoothness information and shadow characteristic information of the bearing retainer through a preset quality threshold; wherein the quality threshold comprises: a standard weight threshold, a standard smoothness threshold, and a standard shadow feature threshold;
if the numerical value of the weight information is greater than or equal to the standard weight threshold, determining the weight information as first repairable information;
if the weight information is first repairable information and the numerical value of the smoothness information is smaller than or equal to the standard smoothness threshold, determining the smoothness information as second repairable information;
if the smoothness information is second repairable information and the numerical value of the shadow feature information is smaller than or equal to a standard shadow feature threshold, determining the shadow feature information as third repairable information;
if the third repairable information is acquired, the quality result of the bearing holder is a repairable defective product, otherwise the quality result of the bearing holder is an unrepairable defective product;
and feeding the quality result back to quality monitoring personnel according to the identification information.
2. The quality monitoring method based on the bearing retainer as claimed in claim 1, wherein the image area ratio calculation of the metal surface feature point image and the gray level defogged image specifically comprises:
determining a color value of reflected light from a metal surface of the bearing retainer based on a Fresnel reflectivity of the metal surface; wherein the reflected light color values comprise reflected linearity values and reflected RGB values;
according to the reflected light color value, carrying out surface halo characteristic screening on the metal surface characteristic point image to determine a surface halo characteristic point image; removing the surface halo characteristic point image from the metal surface characteristic point image to obtain a metal surface flaw image;
and calculating the ratio of the image area of the metal surface flaw image to the gray defogging image to obtain the smoothness information of the bearing retainer.
3. The quality monitoring method based on the bearing retainer according to claim 1, wherein the step of detecting the weight of the bearing retainer in a preset area to obtain the weight information of the bearing retainer comprises the following steps:
arranging the bearing retainers by a preset automatic arranging machine; and transporting the aligned rows of the plurality of bearing retainers into a conveyor belt;
sequentially feeding the plurality of bearing holders into the preset area through the conveyor belt based on a preset time interval; the device comprises a preset area, a weighing device, a high-pressure gas injection device and a control device, wherein the preset area is a semi-closed space, the weighing device is arranged below the preset area, and the high-pressure gas injection device is arranged in the horizontal direction of the preset area;
detecting the weight of the bearing retainer through the weighing device to obtain initial weight information;
according to a third preset threshold, judging a threshold interval of the initial weight information;
and carrying out gas injection type screening on the bearing retainer corresponding to the initial weight which does not meet the threshold interval by the high-pressure gas injection device to obtain the weight information of the screened bearing retainer.
4. The method of claim 1, wherein the step of obtaining a second image of the bearing holder by obtaining an image of the bearing holder and its corresponding frontal shadow, and the step of obtaining a third image of the bearing holder by obtaining an image of the bearing holder and its corresponding lateral shadow comprises:
irradiating the bearing holder according to light emitting devices in two directions based on a preset time interval; wherein, the light emitting device of two directions includes: the first light emitting device is positioned right in front of the bearing retainer, and the second light emitting device is positioned at the right side of the bearing retainer;
irradiating the bearing retainer with front light through the first light emitting device to obtain a front shadow of the bearing retainer, and acquiring images of the bearing retainer and the front shadow thereof through a camera device in a preset rectangular area to obtain a second image;
after the second image is obtained, right-side light irradiation is performed on the bearing retainer through the second light emitting device to obtain a side shadow of the bearing retainer, and the bearing retainer and the side shadow thereof are subjected to image acquisition through a camera device in a preset rectangular area to obtain a third image.
5. The quality monitoring method based on the bearing retainer as claimed in claim 1, wherein before the second image and the third image are subjected to image shadow feature detection to obtain shadow feature information of the bearing retainer, the method further comprises:
carrying out integral image splicing on the second image and the third image to obtain a spliced image;
carrying out color feature identification on the spliced image to obtain a single color area image; wherein the single color region image includes: a vivid color area image and a dull color area image;
overlapping the spliced image with the vivid color area image to obtain a color overlapping area image, and deleting the color overlapping area image in the spliced image to obtain an initial shadow feature image;
identifying edge contour features of the initial shadow feature image to obtain an edge contour pixel value distribution map; determining a contour characteristic image according to the cross entropy of the pixel value distribution probability in the edge contour pixel value distribution diagram; wherein the contour feature image comprises: continuous profile feature images and discontinuous profile feature images;
overlapping the non-continuous contour characteristic image and the initial shadow characteristic image to obtain a contour overlapping area, and deleting the contour overlapping area in the initial shadow characteristic image to obtain a shadow characteristic image; wherein the shadow feature image is a shadow image of the bearing holder.
6. The quality monitoring method based on the bearing retainer according to claim 5, wherein the detecting of the image shadow feature of the second image and the third image to obtain the shadow feature information of the bearing retainer comprises:
detecting the sizes of a plurality of window holes of the bearing retainer in the shadow feature image to obtain the window hole shadow size, and calculating the ratio of the window hole shadow size to the real size of the window hole in the first image to obtain window hole shadow feature information;
carrying out roundness detection on the bowl-shaped structure of the bearing retainer in the shadow feature image to obtain the roundness of the shadow, and carrying out ratio calculation on the roundness of the shadow and the real roundness in the first image to obtain roundness shadow feature information;
performing slope detection on the line of the bearing retainer in the shadow feature image to obtain a line shadow slope, and performing ratio calculation on the line shadow slope and the real slope of the line in the first image to obtain shadow line slope feature information;
and obtaining shadow characteristic information of the bearing retainer according to the aperture window shadow characteristic information, the roundness shadow characteristic information and the shadow line slope characteristic information.
7. The quality monitoring method based on the bearing retainer according to claim 1, wherein the quality result is fed back to a quality monitoring person according to the identification information, and the quality monitoring method specifically comprises the following steps:
marking serial numbers of the bearing retainers according to the identification information to obtain original marked serial numbers;
judging whether the repairable defective products are repaired or not;
if the repairable defective product is a standard component, color labeling the original labeled serial number corresponding to the standard component to obtain a green labeled serial number;
if the repairable defect is a repairable component, color labeling the original labeled serial number corresponding to the repairable component to obtain a yellow labeled serial number;
carrying out color marking on the original marking serial number corresponding to the unrepairable defective product to obtain a red marking serial number;
and sending the green marking serial number, the yellow marking serial number and the red marking serial number corresponding to the quality result of the bearing retainer to the quality monitoring personnel so as to realize the quality monitoring of the bearing retainer.
8. A bearing retainer based quality monitoring apparatus, the apparatus comprising:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a bearing-holder based quality monitoring method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211442372.0A CN115493843B (en) | 2022-11-18 | 2022-11-18 | Quality monitoring method and equipment based on bearing retainer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211442372.0A CN115493843B (en) | 2022-11-18 | 2022-11-18 | Quality monitoring method and equipment based on bearing retainer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115493843A CN115493843A (en) | 2022-12-20 |
| CN115493843B true CN115493843B (en) | 2023-03-10 |
Family
ID=85116059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211442372.0A Active CN115493843B (en) | 2022-11-18 | 2022-11-18 | Quality monitoring method and equipment based on bearing retainer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115493843B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953397B (en) * | 2023-03-13 | 2023-06-02 | 山东金帝精密机械科技股份有限公司 | Method and equipment for monitoring process preparation flow of conical bearing retainer |
| CN116223037B (en) * | 2023-05-09 | 2023-09-19 | 山东金帝精密机械科技股份有限公司 | Operation monitoring method and equipment for wind power bearing retainer |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001165862A (en) * | 1999-12-03 | 2001-06-22 | Koyo Seiko Co Ltd | Bearing inspection device |
| JP2012181167A (en) * | 2011-03-03 | 2012-09-20 | Ntn Corp | Rolling/sliding fatigue life testing method and testing device for steel materials |
| CN103295013A (en) * | 2013-05-13 | 2013-09-11 | 天津大学 | Pared area based single-image shadow detection method |
| CN103837037A (en) * | 2012-12-04 | 2014-06-04 | 洛阳瑞泽石化工程有限公司 | Installing slide way for inserted heat exchanger on tower |
| CN204448629U (en) * | 2014-12-25 | 2015-07-08 | 衢州亿龙信息技术有限公司 | A kind of precision bearing ball automatic Surface Defect Detection System |
| KR101800677B1 (en) * | 2016-06-29 | 2017-11-23 | 한국과학기술연구원 | Cryogenic environment bearing behavior measurement apparatus and method |
| CN109255785A (en) * | 2018-09-26 | 2019-01-22 | 深圳源广安智能科技有限公司 | A kind of bearing open defect detection system |
| CN109345524A (en) * | 2018-09-26 | 2019-02-15 | 深圳市鑫汇达机械设计有限公司 | A kind of bearing open defect detection system of view-based access control model |
| CN110672321A (en) * | 2019-10-18 | 2020-01-10 | 洛阳轴承研究所有限公司 | Device for measuring radial load deformation of bearing |
| CN112308832A (en) * | 2020-10-29 | 2021-02-02 | 常熟理工学院 | Bearing quality detection method based on machine vision |
| CN216815325U (en) * | 2021-12-23 | 2022-06-24 | 瓦房店威远轴承制造有限公司 | Tapered roller bearing smoothness detection device of convenient operation |
| CN114723701A (en) * | 2022-03-31 | 2022-07-08 | 南通博莹机械铸造有限公司 | Gear defect detection method and system based on computer vision |
| CN115115841A (en) * | 2022-08-30 | 2022-09-27 | 苏州朗开医疗技术有限公司 | Shadow spot image processing and analyzing method and system |
-
2022
- 2022-11-18 CN CN202211442372.0A patent/CN115493843B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001165862A (en) * | 1999-12-03 | 2001-06-22 | Koyo Seiko Co Ltd | Bearing inspection device |
| JP2012181167A (en) * | 2011-03-03 | 2012-09-20 | Ntn Corp | Rolling/sliding fatigue life testing method and testing device for steel materials |
| CN103837037A (en) * | 2012-12-04 | 2014-06-04 | 洛阳瑞泽石化工程有限公司 | Installing slide way for inserted heat exchanger on tower |
| CN103295013A (en) * | 2013-05-13 | 2013-09-11 | 天津大学 | Pared area based single-image shadow detection method |
| CN204448629U (en) * | 2014-12-25 | 2015-07-08 | 衢州亿龙信息技术有限公司 | A kind of precision bearing ball automatic Surface Defect Detection System |
| KR101800677B1 (en) * | 2016-06-29 | 2017-11-23 | 한국과학기술연구원 | Cryogenic environment bearing behavior measurement apparatus and method |
| CN109255785A (en) * | 2018-09-26 | 2019-01-22 | 深圳源广安智能科技有限公司 | A kind of bearing open defect detection system |
| CN109345524A (en) * | 2018-09-26 | 2019-02-15 | 深圳市鑫汇达机械设计有限公司 | A kind of bearing open defect detection system of view-based access control model |
| CN110672321A (en) * | 2019-10-18 | 2020-01-10 | 洛阳轴承研究所有限公司 | Device for measuring radial load deformation of bearing |
| CN112308832A (en) * | 2020-10-29 | 2021-02-02 | 常熟理工学院 | Bearing quality detection method based on machine vision |
| CN216815325U (en) * | 2021-12-23 | 2022-06-24 | 瓦房店威远轴承制造有限公司 | Tapered roller bearing smoothness detection device of convenient operation |
| CN114723701A (en) * | 2022-03-31 | 2022-07-08 | 南通博莹机械铸造有限公司 | Gear defect detection method and system based on computer vision |
| CN115115841A (en) * | 2022-08-30 | 2022-09-27 | 苏州朗开医疗技术有限公司 | Shadow spot image processing and analyzing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 铁路轴承保持器兜孔垂直度检测;田雁翎 等;《应用能源技术》;20101231(第11（2010）期);第16-17页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115493843A (en) | 2022-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115493843B (en) | Quality monitoring method and equipment based on bearing retainer | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| EP2602763B1 (en) | Method for monitoring the quality of the primer layer applied on a motor-vehicle body before painting | |
| CN110161035B (en) | Structural surface crack detection method based on image feature and Bayesian data fusion | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| JP4150390B2 (en) | Appearance inspection method and appearance inspection apparatus | |
| EP2212909B1 (en) | Patterned wafer defect inspection system and method | |
| CN111275679A (en) | Solar cell defect detection system and method based on image | |
| CN111768363A (en) | Deep learning-based circuit board surface defect detection method and detection system | |
| US11203494B2 (en) | System and method for sorting moving objects | |
| JP2015049133A (en) | Surface defect inspection device and surface defect inspection method | |
| CN110567968A (en) | part defect detection method and device | |
| WO2005038445A1 (en) | Surface defect inspecting method and device | |
| CN108346138B (en) | Surface defect detection method and system based on image processing | |
| CN115953397A (en) | Method and equipment for monitoring process preparation flow of conical bearing retainer | |
| JP4322230B2 (en) | Surface defect inspection apparatus and surface defect inspection method | |
| CN1871506A (en) | Method and device for inspecting surface to be inspected | |
| CN111833350A (en) | Machine vision detection method and system | |
| CN113781458A (en) | Artificial intelligence based identification method | |
| CN109544514B (en) | Sawn timber identity identification method, device and equipment integrating apparent features | |
| WO2023134286A1 (en) | Online automatic quality testing and classification method for cathode copper | |
| JP4015436B2 (en) | Gold plating defect inspection system | |
| CN115791786A (en) | Part defect detection method and related device | |
| CN114813748A (en) | Steel surface defect detection method and system based on machine vision | |
| CN114383522A (en) | Method for measuring surface gap and surface difference of reflective difference workpiece |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |