CN117325012B - Crack defect management device for grinding bearing - Google Patents
Crack defect management device for grinding bearing Download PDFInfo
- Publication number
- CN117325012B CN117325012B CN202311392261.8A CN202311392261A CN117325012B CN 117325012 B CN117325012 B CN 117325012B CN 202311392261 A CN202311392261 A CN 202311392261A CN 117325012 B CN117325012 B CN 117325012B
- Authority
- CN
- China
- Prior art keywords
- image
- grinding
- arithmetic mean
- end processing
- inclination correction
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 29
- 238000012937 correction Methods 0.000 claims abstract description 79
- 238000012545 processing Methods 0.000 claims abstract description 77
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000003062 neural network model Methods 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 61
- 238000005457 optimization Methods 0.000 claims description 30
- 230000000875 corresponding effect Effects 0.000 claims description 25
- 238000004891 communication Methods 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 7
- 230000002596 correlated effect Effects 0.000 claims description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 2
- 238000003754 machining Methods 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 229910001566 austenite Inorganic materials 0.000 description 1
- 239000011362 coarse particle Substances 0.000 description 1
- 239000002173 cutting fluid Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B5/00—Machines or devices designed for grinding surfaces of revolution on work, including those which also grind adjacent plane surfaces; Accessories therefor
- B24B5/36—Single-purpose machines or devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
Abstract
The invention relates to a crack defect management device for a grinding bearing, which comprises: the grinding mechanism is used for performing grinding treatment on the current bearing part so as to obtain and push the bearing part subjected to grinding treatment; and the tail end processing equipment is used for sending out a grinding crack undetected signal when no grinding crack exists in each image area where each target in the inclination correction image is located, or sending out a grinding crack detection signal otherwise. The crack defect management device for the grinding bearing is intelligent in design and simple and convenient to operate. Because whether grinding cracks exist in the image area where each bearing part is located can be judged intelligently based on the combination of the depth neural network model and the visual data, the method provides assistance for quality identification of the bearing parts of the high-precision parts, and poor bearing parts are prevented from flowing into the market.
Description
Technical Field
The invention relates to the field of bearing part machining, in particular to a crack defect management device for a grinding machining bearing.
Background
During grinding processing of bearing parts, grinding cracks are easily generated on the parts due to too large grinding wheel feeding amount, runout of a grinding wheel shaft, insufficient cutting fluid supply, blunt grinding wheel abrasive particles and the like. In addition, the excessive quenching temperature during the heat treatment causes the structure of the part to overheat, the grains to be coarse, the residual austenite amount to be large, and the net-shaped and coarse particles to be present. The magnetic marks of the grinding defects are generally in a net shape, a radial shape, a parallel linear shape or a crack shape, the magnetic marks are thin and sharp, the outline is clear, the number of the magnetic marks is large, and the magnetic marks are generally perpendicular to the grinding direction. The magnetic marks are distributed in the middle part in a plurality of ways, are long-line or dendritic along the circumferential direction, are branched locally and are converged. After a metallographic specimen with a crack section is prepared, the crack is observed to be thinner and vertical to the surface, and foreign matter such as material inclusion, oxide skin and the like are not found in the crack.
In the field of bearing grinding technology, related grinding methods have been disclosed such as:
1. a hub bearing grinding method for ensuring the groove position of an inner ring is disclosed, and the application publication number is: CN114850978A, comprising the steps of: grinding the hub bearing blank by taking the large surface or the small surface of the hub bearing as a reference, performing heat treatment on the hub bearing coarse material, and grinding the clamped hub bearing coarse material by utilizing a grinding wheel. The method ensures the grinding mode of the groove position by carrying out rough machining, heat treatment and finish machining on the hub bearing and matching with the mode of directly contacting with the magnetic pole of the grinding machine by virtue of the small surface, avoids the defect of large input of roller grinding for ensuring the groove position, also avoids the defect that the grinding machine is used for ensuring the whole height to be uniform before grinding the groove diameter/the groove position, further ensures the defect that the equipment input and the working procedure are increased by the groove position of the inner ring on the side surface, avoids generating surface cracks, ensures the high precision of the produced hub bearing, ensures the subsequent assembly precision and avoids the safety accidents.
2. A one-time turning forming method for miniature bearings is disclosed, and the application publication number is: CN113458426a, method comprising: the main shaft chuck clamps the steel bar for turning; cutting off the formed prefabricated workpiece from the steel bar, clamping the prefabricated workpiece by a chuck of the auxiliary main shaft, and turning a cut surface; and pushing out the finished product, and taking off to finish the process. The auxiliary main shaft chuck is provided with three tyre seams along the radial direction on the chuck body. The pushing device comprises a push rod, a spring and a limiting ring. According to the bearing ring turning forming method, all turning operations of the bearing ring can be completed in one clamping, clamping positioning errors of the bearing ring and auxiliary time of clamping positioning are reduced, relative positions and dimensional accuracy of all surfaces of the bearing ring are improved, and an effective foundation is laid for reducing grinding allowance of the miniature bearing.
It can be seen from the disclosed prior art that since the bearing part is a high-precision part, the grinding cracks on the surface of the bearing part are extremely fine, and the common detection mode is difficult to effectively and timely identify the grinding cracks on the surface of the bearing part, thereby obstructing the quality identification of the bearing part.
Disclosure of Invention
In order to solve the problems, the invention provides a grinding bearing crack defect management device which can intelligently judge whether grinding cracks exist in an image area where each bearing part is located based on the combination of a deep neural network model and visual data, so that the device provides assistance for quality identification of the bearing parts of high-precision parts.
The invention provides a crack defect management device for a grinding bearing, which comprises the following components:
the grinding mechanism is used for performing grinding treatment on the current bearing part so as to obtain and push the bearing part subjected to grinding treatment;
the shot image mechanism is arranged right above the output end of the grinding mechanism and is used for realizing shot image action of the bearing part which is pushed by the grinding mechanism and is subjected to grinding processing by adopting a shot lens so as to obtain a shot monitoring image corresponding to the current time stamp;
the edge sharpening device is arranged in the control box body of the nodding imaging mechanism accessory and connected with the nodding imaging mechanism and is used for executing edge sharpening processing on the received nodding monitoring image so as to obtain and output a corresponding edge sharpening image;
an arithmetic mean filtering device connected with the edge sharpening device and used for executing arithmetic mean filtering processing on the received edge sharpening image so as to obtain and output a corresponding arithmetic mean filtering image;
a tilt correction device, connected to the arithmetic mean filtering device, for performing tilt correction processing on the received arithmetic mean filtered image to obtain and output a corresponding tilt corrected image;
the front-end processing device is connected with the inclination correction device and is used for detecting a plurality of geometric features of an image area where each target in the inclination correction image is located, wherein the geometric features comprise the number of pixels in the length direction, the number of pixels in the width direction and the maximum curvature and the minimum curvature of an area edge curve of the corresponding image area;
the middle-end processing equipment is connected with the front-end processing equipment and is used for inputting a plurality of geometric features of an image area where each target is located, a signal-to-noise ratio of the inclination correction image and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and operating the deep neural network model so as to determine whether grinding cracks exist in the image area where each target is located;
and the tail end processing equipment is connected with the middle end processing equipment and is used for sending out a grinding crack undetected signal when no grinding crack exists in each image area where each target in the inclination correction image is located, or sending out a grinding crack detection signal otherwise.
The crack defect management device for the grinding bearing is intelligent in design and simple and convenient to operate. Because whether grinding cracks exist in the image area where each bearing part is located can be judged intelligently based on the combination of the depth neural network model and the visual data, the method provides assistance for quality identification of the bearing parts of the high-precision parts, and poor bearing parts are prevented from flowing into the market.
Drawings
Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic view of a bearing structure according to various embodiments of the present invention.
Fig. 2 is a schematic view showing an internal structure of a crack defect management device for a grinding bearing according to a first embodiment of the present invention.
Fig. 3 is a schematic view showing an internal structure of a crack defect management device for a grinding bearing according to a second embodiment of the present invention.
Fig. 4 is a schematic view showing an internal structure of a crack defect management device for a grinding bearing according to a third embodiment of the present invention.
Detailed Description
An embodiment of the grinding bearing crack defect management device of the present invention will be described in detail below with reference to the accompanying drawings.
First embodiment
Fig. 2 is a schematic view showing an internal structure of a crack defect management apparatus for a grinding bearing according to a first embodiment of the present invention, the apparatus including:
the grinding mechanism is used for performing grinding treatment on the current bearing part so as to obtain and push the bearing part subjected to grinding treatment;
the shot image mechanism is arranged right above the output end of the grinding mechanism and is used for realizing shot image action of the bearing part which is pushed by the grinding mechanism and is subjected to grinding processing by adopting a shot lens so as to obtain a shot monitoring image corresponding to the current time stamp;
illustratively, the nodding imaging mechanism comprises a nodding lens, a CMOS sensor and a main controller, and is used for realizing the nodding imaging action of the bearing part pushed by the grinding mechanism and finished by grinding;
the edge sharpening device is arranged in the control box body of the nodding imaging mechanism accessory and connected with the nodding imaging mechanism and is used for executing edge sharpening processing on the received nodding monitoring image so as to obtain and output a corresponding edge sharpening image;
an arithmetic mean filtering device connected with the edge sharpening device and used for executing arithmetic mean filtering processing on the received edge sharpening image so as to obtain and output a corresponding arithmetic mean filtering image;
a tilt correction device, connected to the arithmetic mean filtering device, for performing tilt correction processing on the received arithmetic mean filtered image to obtain and output a corresponding tilt corrected image;
the front-end processing device is connected with the inclination correction device and is used for detecting a plurality of geometric features of an image area where each target in the inclination correction image is located, wherein the geometric features comprise the number of pixels in the length direction, the number of pixels in the width direction and the maximum curvature and the minimum curvature of an area edge curve of the corresponding image area;
the middle-end processing equipment is connected with the front-end processing equipment and is used for inputting a plurality of geometric features of an image area where each target is located, a signal-to-noise ratio of the inclination correction image and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and operating the deep neural network model so as to determine whether grinding cracks exist in the image area where each target is located;
the tail end processing equipment is connected with the middle end processing equipment and is used for sending out a grinding crack undetected signal when grinding cracks do not exist in each image area where each target in the inclination correction image is located, or sending out a grinding crack detection signal;
wherein the deep neural network model includes a single input layer, a single output layer, and a plurality of hidden layers located between the single input layer and the single output layer and the number of hidden layers is positively correlated with the contrast of the tilt-corrected image.
Second embodiment
Fig. 3 is a schematic view showing an internal structure of a crack defect management device for a grinding bearing according to a second embodiment of the present invention.
Referring to fig. 3, the grinding bearing crack defect management apparatus according to the second embodiment of the present invention may include, in addition to the components of the first embodiment:
the image optimization mechanism is respectively connected with the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment and is used for respectively carrying out image optimization on respective output image signals of the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment so as to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment;
wherein, respectively performing image optimization on the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, comprises: the first-layer image optimization is used for carrying out spatial differential sharpening on respective output image signals of front-end processing equipment, edge sharpening equipment, arithmetic mean filtering equipment and inclination correction equipment;
the image optimization method includes the steps of respectively performing image optimization on respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and further includes: sub-layer image optimization is used for removing artifacts from respective output image signals of front-end processing equipment, edge sharpening equipment, arithmetic mean filtering equipment and inclination correction equipment;
the image optimization method includes the steps of respectively performing image optimization on respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and further includes: performing affine transformation on respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device through secondary image optimization;
the image optimization method includes the steps of respectively performing image optimization on respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and further includes: the final image optimization performs smooth linear filtering on the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device, respectively.
Third embodiment
Fig. 4 is a schematic view showing an internal structure of a crack defect management device for a grinding bearing according to a third embodiment of the present invention.
Referring to fig. 4, the crack defect management device for a grinding bearing according to the third embodiment of the present invention may include, in addition to the components of the first embodiment:
the parallel data interfaces are respectively connected with the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment and are used for respectively executing parallel data communication service between the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment;
the parallel data interface is respectively connected with the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and is used for respectively executing parallel data communication service between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and comprises the following components: performing parallel data communication services between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device respectively based on an 8-bit parallel data bus;
and wherein the parallel data interfaces are respectively connected with the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and are used for respectively executing parallel data communication service between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and the parallel data communication service comprises: the parallel data communication services between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device are respectively executed based on a 16-bit parallel data bus.
In addition, in the grinding bearing crack defect management device, inputting a plurality of geometric features of an image area where each target is located, a signal-to-noise ratio of the inclination correction image, and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and running the deep neural network model to determine whether or not a grinding crack exists in the image area where each target is located includes: and (3) adopting a MATLAB tool box to complete simulation and test of a data processing process of inputting a plurality of geometric features of an image area where each target is located, a signal-to-noise ratio of the inclination correction image and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and running the deep neural network model so as to determine whether grinding cracks exist in the image area where each target is located.
Therefore, the invention mainly has the following remarkable technical effects:
first,: introducing a deep neural network model comprising a single input layer, a single output layer, and a plurality of hidden layers for performing identification of grinding cracks, wherein the plurality of hidden layers are located between the single input layer and the single output layer and the number of hidden layers is positively correlated with the contrast of the tilt correction image;
secondly: intelligently identifying whether grinding cracks exist in the image area where each target is located by adopting a deep neural network model according to a plurality of geometric features of the image area where each target is located and a plurality of visual data of a picture where each target is located;
again: the method adopts a targeted picture signal enhancement mechanism comprising edge sharpening equipment, arithmetic mean filtering equipment and inclination correction equipment, improves the quality of a field monitoring picture of the bearing part, and provides reliable high-quality basic data for the detection of subsequent grinding cracks.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are to be protected by the present invention.
Claims (7)
1. A grinding bearing crack defect management apparatus, the apparatus comprising:
the grinding mechanism is used for performing grinding treatment on the current bearing part so as to obtain and push the bearing part subjected to grinding treatment;
the shot image mechanism is arranged right above the output end of the grinding mechanism and is used for realizing shot image action of the bearing part which is pushed by the grinding mechanism and is subjected to grinding processing by adopting a shot lens so as to obtain a shot monitoring image corresponding to the current time stamp;
the edge sharpening device is arranged in the control box body of the nodding imaging mechanism accessory and connected with the nodding imaging mechanism and is used for executing edge sharpening processing on the received nodding monitoring image so as to obtain and output a corresponding edge sharpening image;
an arithmetic mean filtering device connected with the edge sharpening device and used for executing arithmetic mean filtering processing on the received edge sharpening image so as to obtain and output a corresponding arithmetic mean filtering image;
a tilt correction device, connected to the arithmetic mean filtering device, for performing tilt correction processing on the received arithmetic mean filtered image to obtain and output a corresponding tilt corrected image;
the front-end processing device is connected with the inclination correction device and is used for detecting a plurality of geometric features of an image area where each target in the inclination correction image is located, wherein the geometric features comprise the number of pixels in the length direction, the number of pixels in the width direction and the maximum curvature and the minimum curvature of an area edge curve of the corresponding image area;
the middle-end processing equipment is connected with the front-end processing equipment and is used for inputting a plurality of geometric features of an image area where each target is located, a signal-to-noise ratio of the inclination correction image and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and operating the deep neural network model so as to determine whether grinding cracks exist in the image area where each target is located;
the method for determining whether grinding cracks exist in the image area of each target comprises the steps of inputting a plurality of geometric features of the image area of each target, a signal-to-noise ratio of the inclination correction image and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and operating the deep neural network model to determine whether the grinding cracks exist in the image area of each target or not, wherein the steps comprise: the simulation and test of the data processing process of inputting a plurality of geometric features of an image area where each target is located, a signal-to-noise ratio of the inclination correction image and an area ratio occupied by a background area of the inclination correction image into a deep neural network model and running the deep neural network model are completed by adopting a MATLAB tool box so as to determine whether grinding cracks exist in the image area where each target is located;
the tail end processing equipment is connected with the middle end processing equipment and is used for sending out a grinding crack undetected signal when grinding cracks do not exist in each image area where each target in the inclination correction image is located, or sending out a grinding crack detection signal;
the deep neural network model comprises a single input layer, a single output layer and a plurality of hidden layers, wherein the plurality of hidden layers are positioned between the single input layer and the single output layer, and the number of hidden layers is positively correlated with the contrast ratio of the inclination correction image;
the image optimization mechanism is respectively connected with the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment and is used for respectively carrying out image optimization on respective output image signals of the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment so as to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment;
wherein, respectively performing image optimization on the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device to obtain respective image optimization images respectively corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, comprises: the first-layer image optimization performs spatial differential sharpening on respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device.
2. The grinding bearing crack defect management apparatus as defined in claim 1, wherein:
image optimization of the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the tilt correction device, respectively, to obtain respective image-optimized images corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the tilt correction device, respectively, further includes: the sub-layer image optimization performs artifact removal on the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device, respectively.
3. The grinding bearing crack defect management apparatus as defined in claim 2, wherein:
image optimization of the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the tilt correction device, respectively, to obtain respective image-optimized images corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the tilt correction device, respectively, further includes: the second layer image optimization affine transforms the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device, respectively.
4. A grinding bearing crack defect management device as defined in claim 3, wherein:
image optimization of the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the tilt correction device, respectively, to obtain respective image-optimized images corresponding to the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the tilt correction device, respectively, further includes: the final image optimization performs smooth linear filtering on the respective output image signals of the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device, respectively.
5. The apparatus for managing crack defects in a ground bearing as set forth in claim 1, further comprising:
and the parallel data interfaces are respectively connected with the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment and are used for respectively executing parallel data communication service between the front-end processing equipment, the edge sharpening equipment, the arithmetic mean filtering equipment and the inclination correction equipment.
6. The grinding bearing crack defect management apparatus as defined in claim 5, wherein:
the parallel data interface is respectively connected with the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and is used for respectively executing parallel data communication service between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and comprises the following steps: the parallel data communication services between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device are respectively executed based on an 8-bit parallel data bus.
7. The grinding bearing crack defect management apparatus as defined in claim 5, wherein:
the parallel data interface is respectively connected with the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and is used for respectively executing parallel data communication service between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device and the inclination correction device, and comprises the following steps: the parallel data communication services between the front-end processing device, the edge sharpening device, the arithmetic mean filtering device, and the inclination correction device are respectively executed based on a 16-bit parallel data bus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311392261.8A CN117325012B (en) | 2023-10-25 | 2023-10-25 | Crack defect management device for grinding bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311392261.8A CN117325012B (en) | 2023-10-25 | 2023-10-25 | Crack defect management device for grinding bearing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117325012A CN117325012A (en) | 2024-01-02 |
| CN117325012B true CN117325012B (en) | 2024-04-12 |
Family
ID=89295259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311392261.8A Active CN117325012B (en) | 2023-10-25 | 2023-10-25 | Crack defect management device for grinding bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117325012B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5309486A (en) * | 1992-11-12 | 1994-05-03 | Westinghouse Electric Corp. | Non-contact flaw detection for cylindrical nuclear fuel pellets |
| CN109118471A (en) * | 2018-06-26 | 2019-01-01 | 广东工业大学 | A kind of polishing workpiece, defect detection method suitable under complex environment |
| KR101948852B1 (en) * | 2017-10-25 | 2019-05-29 | 세종대학교산학협력단 | Hybrid image scanning method and apparatus for noncontact crack evaluation |
| CN110618140A (en) * | 2019-11-01 | 2019-12-27 | 杭州深度视觉科技有限公司 | Machine vision detection system and method for bearing ring grinding vibration lines |
| CN110766689A (en) * | 2019-11-06 | 2020-02-07 | 深圳微品致远信息科技有限公司 | Method and device for detecting article image defects based on convolutional neural network |
| CN110809782A (en) * | 2018-10-22 | 2020-02-18 | 上海联影医疗科技有限公司 | Attenuation correction system and method |
| CN112053318A (en) * | 2020-07-20 | 2020-12-08 | 清华大学 | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning |
| CN115496671A (en) * | 2021-06-18 | 2022-12-20 | 哲库科技(上海)有限公司 | Image noise reduction device and method, processing chip and electronic equipment |
| CN116136393A (en) * | 2023-03-02 | 2023-05-19 | 宁波川原精工机械有限公司 | Bearing ring inner ring detection system and method |
-
2023
- 2023-10-25 CN CN202311392261.8A patent/CN117325012B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5309486A (en) * | 1992-11-12 | 1994-05-03 | Westinghouse Electric Corp. | Non-contact flaw detection for cylindrical nuclear fuel pellets |
| KR101948852B1 (en) * | 2017-10-25 | 2019-05-29 | 세종대학교산학협력단 | Hybrid image scanning method and apparatus for noncontact crack evaluation |
| CN109118471A (en) * | 2018-06-26 | 2019-01-01 | 广东工业大学 | A kind of polishing workpiece, defect detection method suitable under complex environment |
| CN110809782A (en) * | 2018-10-22 | 2020-02-18 | 上海联影医疗科技有限公司 | Attenuation correction system and method |
| CN110618140A (en) * | 2019-11-01 | 2019-12-27 | 杭州深度视觉科技有限公司 | Machine vision detection system and method for bearing ring grinding vibration lines |
| CN110766689A (en) * | 2019-11-06 | 2020-02-07 | 深圳微品致远信息科技有限公司 | Method and device for detecting article image defects based on convolutional neural network |
| CN112053318A (en) * | 2020-07-20 | 2020-12-08 | 清华大学 | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning |
| CN115496671A (en) * | 2021-06-18 | 2022-12-20 | 哲库科技(上海)有限公司 | Image noise reduction device and method, processing chip and electronic equipment |
| CN116136393A (en) * | 2023-03-02 | 2023-05-19 | 宁波川原精工机械有限公司 | Bearing ring inner ring detection system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117325012A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108747825B (en) | Laser trimming and forming grinding wheel device based on visual detection and trimming method thereof | |
| CN1238690C (en) | Method and apparatus for measuring vehicle wheel roll radius | |
| US6743486B1 (en) | Method for producing spectacle lens and lens processing system | |
| CN110717872B (en) | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning | |
| CN114092403A (en) | Grinding wheel wear detection method and system based on machine vision | |
| EP1260312A1 (en) | Improvement in and relating to edge grinding | |
| CN117325012B (en) | Crack defect management device for grinding bearing | |
| CN105139391A (en) | Edge detecting method for traffic image in fog-and-haze weather | |
| US20110021025A1 (en) | Method for producing laser-marked semiconductor wafer | |
| CN110340805B (en) | Grinding wheel/workpiece complex arc profile on-line detection method and device | |
| CN113781458A (en) | Artificial intelligence based identification method | |
| WO2020174853A1 (en) | End mill inspection device | |
| CN106826399B (en) | Intelligent deburring method for hub | |
| CN113409229B (en) | Method for evaluating contour of abrasive particles of large-abrasive-particle superhard abrasive grinding wheel | |
| CN111127410B (en) | Automatic detection method for printing flaws of automobile instrument panel | |
| CN113165041B (en) | Defect grinding method for round steel and method for manufacturing steel | |
| CN106926134A (en) | Aspheric grinding Arc Diamond Wheel 3D shape error precision measurement method in place | |
| JP7355128B2 (en) | Method for determining surface condition of material to be ground, device for determining surface condition of material to be ground, grinding device, method for grinding material to be ground, and method for manufacturing metal material | |
| CN115686027A (en) | Path planning and control method of curved surface constant force polishing robot | |
| CN109219731B (en) | Method for discriminating foreign matter adhesion of green tire | |
| CN115502892A (en) | Method and system for removing surface material of steel material during ultra-precise grinding | |
| JP2001124094A (en) | Land finishing method of outer ring of bearing and bearing | |
| CN113351580B (en) | Method for detecting laser cleaning quality of inner surface of tire through identification mark | |
| Lin et al. | Study on the segmentation of abrasive grains in diamond tools | |
| CN116572078B (en) | Method for detecting abrasion of turning tool |
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 |