CN116136393A - Bearing ring inner ring detection system and method - Google Patents
Bearing ring inner ring detection system and method Download PDFInfo
- Publication number
- CN116136393A CN116136393A CN202310191884.2A CN202310191884A CN116136393A CN 116136393 A CN116136393 A CN 116136393A CN 202310191884 A CN202310191884 A CN 202310191884A CN 116136393 A CN116136393 A CN 116136393A
- Authority
- CN
- China
- Prior art keywords
- bearing ring
- imaging
- ring
- bearing
- nodding
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000003384 imaging method Methods 0.000 claims abstract description 163
- 230000007246 mechanism Effects 0.000 claims abstract description 75
- 230000009471 action Effects 0.000 claims abstract description 59
- 238000004519 manufacturing process Methods 0.000 claims abstract description 50
- 239000000463 material Substances 0.000 claims abstract description 33
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 32
- 239000010959 steel Substances 0.000 claims abstract description 32
- 238000005266 casting Methods 0.000 claims abstract description 30
- 238000009826 distribution Methods 0.000 claims description 33
- 238000005457 optimization Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 12
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005242 forging Methods 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- 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 relates to a bearing ring inner ring detection system, which comprises: the bearing ring production line is used for completing piece-by-piece bearing ring production based on steel materials for casting the bearing rings; the customized triggering mechanism is used for triggering the real photographing imaging action when the mean square deviation of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by the single-piece bearing ring performing the nodding imaging action facing the nodding imaging mechanism is not over-limited; and the state detection part is used for determining whether to send out a ring standard signal based on the consistency degree of the curvature of the fitting curve of the inner ring in the real shooting image. The invention also relates to a method for detecting the inner ring of the bearing ring. According to the invention, the reliability of information acquisition of the bearing ring is determined through a customized signal processing mechanism, and the morphological standard degree of the bearing ring inner ring is judged according to the consistency of the curvature of the fitting curve of the bearing ring inner ring, so that the quality of a factory bearing ring product is ensured.
Description
Technical Field
The invention relates to the field of bearing rings, in particular to a bearing ring inner ring detection system and a bearing ring inner ring detection method.
Background
A bearing ring (bearing ring) is an annular part of a radial rolling bearing with one or several raceways. Generally, the production steps of the bearing ring are as follows:
1. forging: if overburning, overheating, internal cracking into net carbide and the like are generated in the forging process, the toughness and strength of the ferrule are reduced. Therefore, the processing temperature, the cyclic heating, the heat dissipation conditions after forging (such as spray cooling) and the like must be strictly controlled all the time, and particularly after final forging of a ferrule of a larger variety, the ferrule is not stacked and placed at the temperature of more than 700 ℃.
2. And (3) heat treatment: close monitoring of heat treatment equipment is an important job in workshops. The reliability of the device is monitored. Important temperature controllers such as meters, thermocouples and the like need to be closely monitored, so that accurate and reliable measurement data are ensured; the error exceeding is required to be replaced in time, and the operation with diseases is strictly forbidden.
3. Monitoring of the grinding process: the finished inlet bearing ring does not allow grinding burn and grinding crack, and especially the matching surface of the inner ring with the taper is not burnt. If the ferrule is pickled, the ferrule should be fully inspected, burn products are removed, severe burns cannot be repaired or the ferrule with the grinding burn is rejected after being repaired disqualification, and the ferrule with the grinding burn is not allowed to enter the assembly process.
4. Identification management: after the steel is put in storage and before the ferrule is ground, each working procedure must be strictly managed, and two materials and products of different materials of GCR15 and GCR15SIMN are strictly distinguished.
However, in the actual production process of the bearing ring, the quality of the inner ring determines the safety and stability of the subsequent use of the bearing ring, so that the quality of the inner ring is more important than the quality of the outer ring, and the method is an important detection procedure when the bearing ring leaves a factory. However, the quality inspection mechanism of the bearing ring in the prior art aims at the whole shape of the bearing ring, and lacks a specific detection scheme for the inner ring of the bearing ring, not to mention improving the accuracy of the shape detection of the inner ring of the bearing ring.
Disclosure of Invention
In order to solve the technical problems in the related art, the invention provides a bearing ring inner ring detection system and a bearing ring inner ring detection method, wherein the reliability of information acquisition of a bearing ring is determined through a customized signal processing mechanism, and then the morphological standard degree of the bearing ring inner ring is judged according to the consistency of the curvature of the fitting curve of the bearing ring inner ring, so that the safety and the stability of the subsequent use of the bearing ring are ensured.
According to an aspect of the present invention, there is provided a bearing ring inner ring detection system, the system comprising:
the bearing ring production line is used for completing piece-by-piece production operation of each bearing ring based on steel materials for casting the bearing rings;
the customized triggering mechanism is used for sending out a front-view detection signal to trigger the nose-view imaging mechanism to execute real-time imaging actions on the horizontally placed single-piece bearing rings pushed by the bearing ring production line when the mean square deviation of the depth of field values respectively corresponding to all pixel points of the bearing ring imaging area in the preview image obtained by the nose-view imaging mechanism to execute the nose-view imaging actions on the horizontally placed single-piece bearing rings pushed by the bearing ring production line is smaller than or equal to a set mean square deviation threshold;
the data optimizing mechanism is connected with the customized triggering mechanism and is used for sequentially executing point-image multiplexing action, image content enhancing action based on exponential transformation and random noise eliminating action on the field photographed image corresponding to the photographed imaging action so as to obtain a corresponding data optimizing image;
the region segmentation component is connected with the data optimization mechanism and is used for analyzing a bearing ring imaging region in the data optimization image based on a brightness value distribution interval of a steel material for casting the bearing ring and extracting an inner ring imaging subarea from the bearing ring imaging region based on a distribution form of an inner ring and an outer ring of the bearing ring;
the state detection component is connected with the region segmentation component and is used for fitting the inner ring imaging subareas to obtain corresponding inner ring contour curves, each curvature corresponding to each position on the curve is obtained on the inner ring contour curves at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, a ring standard signal is sent out;
wherein the state detecting means is further configured to issue a loop deviation signal when an absolute value of a difference between a maximum curvature and a minimum curvature of the respective curvatures is greater than the set difference limit.
According to another aspect of the present invention, there is also provided a method for detecting an inner ring of a bearing ring, the method comprising:
using a bearing ring production line for completing piece-by-piece production operation of each bearing ring based on steel materials for casting the bearing rings;
the method comprises the steps that a custom trigger mechanism is used for sending out a front view detection signal to trigger a real shooting imaging action of the nodding imaging mechanism on a single bearing ring which is pushed by a bearing ring production line and is horizontally placed when the mean square deviation of depth values corresponding to all pixel points of a bearing ring imaging area in a preview image obtained by the nodding imaging mechanism facing the single bearing ring which is pushed by the bearing ring production line and is horizontally placed is smaller than or equal to a set mean square deviation threshold;
the data optimizing mechanism is connected with the customized triggering mechanism and is used for sequentially executing point-image multiplexing action, image content enhancing action based on exponential transformation and random noise eliminating action on the field photographed image corresponding to the photographed imaging action so as to obtain a corresponding data optimized image;
the region segmentation component is connected with the data optimization mechanism and is used for analyzing a bearing ring imaging region in a data optimization image based on a brightness value distribution interval of a steel material for casting the bearing ring and extracting an inner ring imaging subarea from the bearing ring imaging region based on a distribution form of an inner ring and an outer ring of the bearing ring;
the using state detection component is connected with the region segmentation component and is used for fitting the inner ring imaging subareas to obtain corresponding inner ring contour curves, each curvature corresponding to each position on the curve is obtained on the inner ring contour curves at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, a ring standard signal is sent out;
wherein the state detecting means is further configured to issue a loop deviation signal when an absolute value of a difference between a maximum curvature and a minimum curvature of the respective curvatures is greater than the set difference limit.
Therefore, the invention at least needs to have the following two remarkable technical improvements:
firstly, when the average square error of depth values corresponding to each pixel point of a bearing ring imaging area in a preview image obtained by performing a nodding imaging action on a single bearing ring which is pushed by a nodding imaging mechanism and is horizontally placed and faces a bearing ring production line is smaller than or equal to a set average square error threshold, judging that an imaging lens of the nodding imaging mechanism is parallel to the upper surface of the single bearing ring which is horizontally placed, so as to trigger the nodding imaging mechanism to perform an actual imaging action on the single bearing ring which is pushed by the bearing ring production line and is horizontally placed, thereby providing reliable reference data for judging the morphological standard of an inner ring of the subsequent bearing ring;
and secondly, extracting an inner ring imaging subarea from the bearing ring imaging area based on the distribution form of the inner ring and the outer ring of the bearing ring, fitting the inner ring imaging subarea to obtain a corresponding inner ring profile curve, acquiring each curvature corresponding to each position on the curve on the inner ring profile curve at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, sending out a ring standard signal, otherwise, sending out a ring deviation signal, thereby completing high-precision morphological standard judgment of the inner ring of the bearing ring and avoiding the bearing ring with inferior morphology from flowing into the market.
Drawings
Embodiments of the present invention will be described below with reference to the accompanying drawings, in which:
fig. 1 is a block diagram showing the structure of a bearing ring inner ring detection system according to a first embodiment of the present invention.
Fig. 2 is a block diagram showing the structure of a bearing ring inner ring detection system according to a second embodiment of the present invention.
Fig. 3 is a flow chart of steps of a method for detecting an inner ring of a bearing ring according to a third embodiment of the present invention.
Detailed Description
An embodiment of the bearing ring inner ring detection method of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a block diagram showing a structure of a bearing ring inner ring detection system according to a first embodiment of the present invention, the system including:
the bearing ring production line is used for completing piece-by-piece production operation of each bearing ring based on steel materials for casting the bearing rings;
the customized triggering mechanism is used for sending out a front-view detection signal to trigger the nose-view imaging mechanism to execute real-time imaging actions on the horizontally placed single-piece bearing rings pushed by the bearing ring production line when the mean square deviation of the depth of field values respectively corresponding to all pixel points of the bearing ring imaging area in the preview image obtained by the nose-view imaging mechanism to execute the nose-view imaging actions on the horizontally placed single-piece bearing rings pushed by the bearing ring production line is smaller than or equal to a set mean square deviation threshold;
for example, the mean square error of the depth of field values corresponding to the pixel points of the imaging area of the bearing ring represents the difference degree of the visual distance of each refinement position of the bearing ring target relative to the imaging lens, and when the mean square error value is smaller, the whole bearing ring is parallel to the imaging lens;
the data optimizing mechanism is connected with the customized triggering mechanism and is used for sequentially executing point-image multiplexing action, image content enhancing action based on exponential transformation and random noise eliminating action on the field photographed image corresponding to the photographed imaging action so as to obtain a corresponding data optimizing image;
the region segmentation component is connected with the data optimization mechanism and is used for analyzing a bearing ring imaging region in the data optimization image based on a brightness value distribution interval of a steel material for casting the bearing ring and extracting an inner ring imaging subarea from the bearing ring imaging region based on a distribution form of an inner ring and an outer ring of the bearing ring;
the distribution pattern of the inner and outer rings of the bearing ring means, for example, the structural layout of the outer ring of the bearing ring surrounding the inner ring in the contour of the bearing ring;
the state detection component is connected with the region segmentation component and is used for fitting the inner ring imaging subareas to obtain corresponding inner ring contour curves, each curvature corresponding to each position on the curve is obtained on the inner ring contour curves at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, a ring standard signal is sent out;
wherein the state detecting means is further configured to issue a loop deviation signal when an absolute value of a difference between a maximum curvature and a minimum curvature of the respective curvatures is greater than the set difference limit.
Fig. 2 is a block diagram showing the structure of a bearing ring inner ring detection system according to a second embodiment of the present invention.
As shown in fig. 2, the bearing ring inner ring detection system in fig. 2 may further comprise the following components, unlike fig. 1:
the nodding imaging mechanism is arranged right above the inner ring detection station to face a single bearing ring which is pushed by the bearing ring production line and is horizontally placed;
illustratively, the nodding imaging mechanism is internally provided with a photoelectric sensor and a nodding lens, wherein the nodding lens is arranged at the front end of the photoelectric sensor, and the photoelectric sensor is used for executing actual photoelectric sensing operation.
Next, a specific configuration of the bearing ring inner ring detection system according to the present invention will be further described.
In the bearing ring inner ring detection system according to various embodiments of the present invention:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, wherein the real imaging action comprises the following steps: the nodding imaging mechanism adopts a first set resolution to obtain a preview image, and also adopts a second set resolution to realize a real imaging action so as to obtain a field real imaging image;
wherein, the obtaining of preview image is realized to the imaging mechanism that takes over the time adopts first settlement resolution, still adopts the second settlement resolution to realize taking over the time imaging action in order to obtain the scene and take over the time the image includes: the first set resolution is less than the second set resolution;
wherein the first set resolution is smaller than the second set resolution includes: the second set resolution is a multiple of the first set resolution.
In the bearing ring inner ring detection system according to various embodiments of the present invention:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute the nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute the real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, the method further comprises: analyzing an imaging area of the bearing ring in the preview image based on a brightness value distribution interval of a steel material for casting the bearing ring;
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: taking pixel points, of which the brightness value is within a brightness value distribution interval of a steel material for casting the bearing ring, in the preview image as ring forming pixel points;
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: and fitting the pixel points formed by each ferrule in the preview image after removing the isolated pixel points to obtain a bearing ferrule imaging area in the preview image.
Fig. 3 is a flow chart of steps of a method for detecting an inner ring of a bearing ring according to a third embodiment of the present invention, the method comprising:
using a bearing ring production line for completing piece-by-piece production operation of each bearing ring based on steel materials for casting the bearing rings;
the method comprises the steps that a custom trigger mechanism is used for sending out a front view detection signal to trigger a real shooting imaging action of the nodding imaging mechanism on a single bearing ring which is pushed by a bearing ring production line and is horizontally placed when the mean square deviation of depth values corresponding to all pixel points of a bearing ring imaging area in a preview image obtained by the nodding imaging mechanism facing the single bearing ring which is pushed by the bearing ring production line and is horizontally placed is smaller than or equal to a set mean square deviation threshold;
for example, the mean square error of the depth of field values corresponding to the pixel points of the imaging area of the bearing ring represents the difference degree of the visual distance of each refinement position of the bearing ring target relative to the imaging lens, and when the mean square error value is smaller, the whole bearing ring is parallel to the imaging lens;
the data optimizing mechanism is connected with the customized triggering mechanism and is used for sequentially executing point-image multiplexing action, image content enhancing action based on exponential transformation and random noise eliminating action on the field photographed image corresponding to the photographed imaging action so as to obtain a corresponding data optimized image;
the region segmentation component is connected with the data optimization mechanism and is used for analyzing a bearing ring imaging region in a data optimization image based on a brightness value distribution interval of a steel material for casting the bearing ring and extracting an inner ring imaging subarea from the bearing ring imaging region based on a distribution form of an inner ring and an outer ring of the bearing ring;
the distribution pattern of the inner and outer rings of the bearing ring means, for example, the structural layout of the outer ring of the bearing ring surrounding the inner ring in the contour of the bearing ring;
the using state detection component is connected with the region segmentation component and is used for fitting the inner ring imaging subareas to obtain corresponding inner ring contour curves, each curvature corresponding to each position on the curve is obtained on the inner ring contour curves at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, a ring standard signal is sent out;
wherein the state detecting means is further configured to issue a loop deviation signal when an absolute value of a difference between a maximum curvature and a minimum curvature of the respective curvatures is greater than the set difference limit.
Next, specific steps of the bearing ring inner ring detection method of the present invention will be further described.
In the bearing ring inner ring detection method according to the above embodiment, the method may further include the steps of:
a nodding imaging mechanism is used and is arranged right above the inner ring detection station to face a single bearing ring which is pushed by a bearing ring production line and is horizontally placed;
illustratively, the nodding imaging mechanism is internally provided with a photoelectric sensor and a nodding lens, wherein the nodding lens is arranged at the front end of the photoelectric sensor, and the photoelectric sensor is used for executing actual photoelectric sensing operation.
In the bearing ring inner ring detection method according to the above-described embodiment:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, wherein the real imaging action comprises the following steps: the nodding imaging mechanism adopts a first set resolution to obtain a preview image, and also adopts a second set resolution to realize a real imaging action so as to obtain a field real imaging image;
wherein, the obtaining of preview image is realized to the imaging mechanism that takes over the time adopts first settlement resolution, still adopts the second settlement resolution to realize taking over the time imaging action in order to obtain the scene and take over the time the image includes: the first set resolution is less than the second set resolution;
wherein the first set resolution is smaller than the second set resolution includes: the second set resolution is a multiple of the first set resolution.
In the bearing ring inner ring detection method according to the above-described embodiment:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute the nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute the real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, the method further comprises: analyzing an imaging area of the bearing ring in the preview image based on a brightness value distribution interval of a steel material for casting the bearing ring;
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: taking pixel points, of which the brightness value is within a brightness value distribution interval of a steel material for casting the bearing ring, in the preview image as ring forming pixel points;
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: and fitting the pixel points formed by each ferrule in the preview image after removing the isolated pixel points to obtain a bearing ferrule imaging area in the preview image.
In addition, in the bearing ring inner ring detection system and the bearing ring inner ring detection method, the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material of the cast bearing ring comprises the following steps: and taking the pixel points, the brightness values of which are outside the brightness value distribution interval of the steel material for casting the bearing rings, in the preview image as non-ring-forming pixel points.
By adopting the bearing ring inner ring detection system and the bearing ring inner ring detection method, the technical problem that the bearing ring inner ring lacks a high-precision and targeted morphological quality detection mechanism in the prior art is solved, the reliability of information acquisition of the bearing ring is determined through a customized signal processing mechanism, and the morphological standard degree of the bearing ring inner ring is judged according to the consistency of the curvature of the fitting curve of the bearing ring inner ring, so that the quality of a finished bearing ring product is ensured.
The description of the preferred embodiments of the present invention has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the invention in the form disclosed. Those skilled in the art will recognize that changes may be made to the embodiments described above without departing from the broad inventive concept thereof. For example, the invention may be implemented on a leadframe panel. In addition, a leadframe having more than two rows of terminals may be formed, wherein one or more of the inner rows are stepped. It is understood, therefore, that this invention is not limited to the particular embodiments disclosed, but it is intended to cover modifications within the spirit and scope of the present invention as defined by the appended claims.
Claims (10)
1. A bearing ring inner ring detection system, the system comprising:
the bearing ring production line is used for completing piece-by-piece production operation of each bearing ring based on steel materials for casting the bearing rings;
the customized triggering mechanism is used for sending out a front-view detection signal to trigger the nose-view imaging mechanism to execute real-time imaging actions on the horizontally placed single-piece bearing rings pushed by the bearing ring production line when the mean square deviation of the depth of field values respectively corresponding to all pixel points of the bearing ring imaging area in the preview image obtained by the nose-view imaging mechanism to execute the nose-view imaging actions on the horizontally placed single-piece bearing rings pushed by the bearing ring production line is smaller than or equal to a set mean square deviation threshold;
the data optimizing mechanism is connected with the customized triggering mechanism and is used for sequentially executing point-image multiplexing action, image content enhancing action based on exponential transformation and random noise eliminating action on the field photographed image corresponding to the photographed imaging action so as to obtain a corresponding data optimizing image;
the region segmentation component is connected with the data optimization mechanism and is used for analyzing a bearing ring imaging region in the data optimization image based on a brightness value distribution interval of a steel material for casting the bearing ring and extracting an inner ring imaging subarea from the bearing ring imaging region based on a distribution form of an inner ring and an outer ring of the bearing ring;
the state detection component is connected with the region segmentation component and is used for fitting the inner ring imaging subareas to obtain corresponding inner ring contour curves, each curvature corresponding to each position on the curve is obtained on the inner ring contour curves at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, a ring standard signal is sent out;
wherein the state detecting means is further configured to issue a loop deviation signal when an absolute value of a difference between a maximum curvature and a minimum curvature of the respective curvatures is greater than the set difference limit.
2. The bearing ring inner race detection system of claim 1, further comprising:
the nodding imaging mechanism is arranged right above the inner ring detection station to face a single bearing ring which is pushed by the bearing ring production line and is horizontally placed.
3. Bearing ring inner ring detection system according to any of claims 1-2, characterized in that:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, wherein the real imaging action comprises the following steps: the nodding imaging mechanism adopts a first set resolution to obtain a preview image, and also adopts a second set resolution to realize a real imaging action so as to obtain a field real imaging image;
wherein, the obtaining of preview image is realized to the imaging mechanism that takes over the time adopts first settlement resolution, still adopts the second settlement resolution to realize taking over the time imaging action in order to obtain the scene and take over the time the image includes: the first set resolution is less than the second set resolution;
wherein the first set resolution is smaller than the second set resolution includes: the second set resolution is a multiple of the first set resolution.
4. Bearing ring inner ring detection system according to any of claims 1-2, characterized in that:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute the nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute the real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, the method further comprises: and analyzing the imaging area of the bearing ring in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring.
5. The bearing ring inner race detection system of claim 4, wherein:
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: taking pixel points, of which the brightness value is within a brightness value distribution interval of a steel material for casting the bearing ring, in the preview image as ring forming pixel points;
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: and fitting the pixel points formed by each ferrule in the preview image after removing the isolated pixel points to obtain a bearing ferrule imaging area in the preview image.
6. A method for detecting an inner ring of a bearing ring, the method comprising:
using a bearing ring production line for completing piece-by-piece production operation of each bearing ring based on steel materials for casting the bearing rings;
the method comprises the steps that a custom trigger mechanism is used for sending out a front view detection signal to trigger a real shooting imaging action of the nodding imaging mechanism on a single bearing ring which is pushed by a bearing ring production line and is horizontally placed when the mean square deviation of depth values corresponding to all pixel points of a bearing ring imaging area in a preview image obtained by the nodding imaging mechanism facing the single bearing ring which is pushed by the bearing ring production line and is horizontally placed is smaller than or equal to a set mean square deviation threshold;
the data optimizing mechanism is connected with the customized triggering mechanism and is used for sequentially executing point-image multiplexing action, image content enhancing action based on exponential transformation and random noise eliminating action on the field photographed image corresponding to the photographed imaging action so as to obtain a corresponding data optimized image;
the region segmentation component is connected with the data optimization mechanism and is used for analyzing a bearing ring imaging region in a data optimization image based on a brightness value distribution interval of a steel material for casting the bearing ring and extracting an inner ring imaging subarea from the bearing ring imaging region based on a distribution form of an inner ring and an outer ring of the bearing ring;
the using state detection component is connected with the region segmentation component and is used for fitting the inner ring imaging subareas to obtain corresponding inner ring contour curves, each curvature corresponding to each position on the curve is obtained on the inner ring contour curves at uniform intervals, and when the absolute value of the difference value of the maximum curvature and the minimum curvature in each curvature is smaller than or equal to a set difference value limit, a ring standard signal is sent out;
wherein the state detecting means is further configured to issue a loop deviation signal when an absolute value of a difference between a maximum curvature and a minimum curvature of the respective curvatures is greater than the set difference limit.
7. The method for detecting an inner ring of a bearing ring according to claim 6, further comprising:
the single bearing ring is pushed by the bearing ring production line and placed horizontally.
8. A method of detecting an inner ring of a bearing ring according to any one of claims 6 to 7, characterized in that:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, wherein the real imaging action comprises the following steps: the nodding imaging mechanism adopts a first set resolution to obtain a preview image, and also adopts a second set resolution to realize a real imaging action so as to obtain a field real imaging image;
wherein, the obtaining of preview image is realized to the imaging mechanism that takes over the time adopts first settlement resolution, still adopts the second settlement resolution to realize taking over the time imaging action in order to obtain the scene and take over the time the image includes: the first set resolution is less than the second set resolution;
wherein the first set resolution is smaller than the second set resolution includes: the second set resolution is a multiple of the first set resolution.
9. A method of detecting an inner ring of a bearing ring according to any one of claims 6 to 7, characterized in that:
when the mean square error of each depth of field value corresponding to each pixel point of the bearing ring imaging area in the preview image obtained by pushing the horizontally placed single-piece bearing ring pushed by the bearing ring production line by the nodding imaging mechanism to execute the nodding imaging action is smaller than or equal to a set mean square error threshold, sending a front view detection signal to trigger the nodding imaging mechanism to execute the real imaging action on the horizontally placed single-piece bearing ring pushed by the bearing ring production line, the method further comprises: and analyzing the imaging area of the bearing ring in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring.
10. The method for detecting an inner ring of a bearing ring according to claim 9, wherein:
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: taking pixel points, of which the brightness value is within a brightness value distribution interval of a steel material for casting the bearing ring, in the preview image as ring forming pixel points;
the analysis of the bearing ring imaging area in the preview image based on the brightness value distribution interval of the steel material for casting the bearing ring comprises the following steps: and fitting the pixel points formed by each ferrule in the preview image after removing the isolated pixel points to obtain a bearing ferrule imaging area in the preview image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310191884.2A CN116136393B (en) | 2023-03-02 | 2023-03-02 | Bearing ring inner ring detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310191884.2A CN116136393B (en) | 2023-03-02 | 2023-03-02 | Bearing ring inner ring detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116136393A true CN116136393A (en) | 2023-05-19 |
| CN116136393B CN116136393B (en) | 2023-07-28 |
Family
ID=86333544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310191884.2A Active CN116136393B (en) | 2023-03-02 | 2023-03-02 | Bearing ring inner ring detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116136393B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274252A (en) * | 2023-11-20 | 2023-12-22 | 海澜智云科技有限公司 | Steel product surface flaw detection system based on identification analysis |
| CN117325012A (en) * | 2023-10-25 | 2024-01-02 | 江阴市精奇数控有限公司 | Crack defect management device for grinding bearing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08304302A (en) * | 1995-05-15 | 1996-11-22 | Nachi Fujikoshi Corp | Method for detecting surface flaws of object to be inspected |
| CN108230285A (en) * | 2016-12-09 | 2018-06-29 | 广东技术师范学院 | Baffle ring quality determining method based on machine vision |
| 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 |
| CN111062919A (en) * | 2019-12-12 | 2020-04-24 | 韦士肯(厦门)智能科技有限公司 | Bearing ring appearance defect detection method |
| CN113096106A (en) * | 2021-04-16 | 2021-07-09 | 洛阳理工学院 | Steel ball detection method based on machine vision |
| CN113447493A (en) * | 2021-07-30 | 2021-09-28 | 安徽工程大学 | Bearing ring defect detection device and detection method |
| CN115147407A (en) * | 2022-08-29 | 2022-10-04 | 聊城市博源节能科技有限公司 | Bearing quality detection method based on computer vision |
| CN115656335A (en) * | 2022-10-10 | 2023-01-31 | 中国计量大学 | Method for quickly detecting and identifying internal defects of bearing ring |
| CN115689998A (en) * | 2022-09-30 | 2023-02-03 | 芜湖佳先传动轴有限公司 | Multi-channel automatic flaw detection system for automobile bearing ring |
-
2023
- 2023-03-02 CN CN202310191884.2A patent/CN116136393B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08304302A (en) * | 1995-05-15 | 1996-11-22 | Nachi Fujikoshi Corp | Method for detecting surface flaws of object to be inspected |
| CN108230285A (en) * | 2016-12-09 | 2018-06-29 | 广东技术师范学院 | Baffle ring quality determining method based on machine vision |
| 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 |
| CN111062919A (en) * | 2019-12-12 | 2020-04-24 | 韦士肯(厦门)智能科技有限公司 | Bearing ring appearance defect detection method |
| CN113096106A (en) * | 2021-04-16 | 2021-07-09 | 洛阳理工学院 | Steel ball detection method based on machine vision |
| CN113447493A (en) * | 2021-07-30 | 2021-09-28 | 安徽工程大学 | Bearing ring defect detection device and detection method |
| CN115147407A (en) * | 2022-08-29 | 2022-10-04 | 聊城市博源节能科技有限公司 | Bearing quality detection method based on computer vision |
| CN115689998A (en) * | 2022-09-30 | 2023-02-03 | 芜湖佳先传动轴有限公司 | Multi-channel automatic flaw detection system for automobile bearing ring |
| CN115656335A (en) * | 2022-10-10 | 2023-01-31 | 中国计量大学 | Method for quickly detecting and identifying internal defects of bearing ring |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117325012A (en) * | 2023-10-25 | 2024-01-02 | 江阴市精奇数控有限公司 | Crack defect management device for grinding bearing |
| CN117325012B (en) * | 2023-10-25 | 2024-04-12 | 江阴市精奇数控有限公司 | Crack defect management device for grinding bearing |
| CN117274252A (en) * | 2023-11-20 | 2023-12-22 | 海澜智云科技有限公司 | Steel product surface flaw detection system based on identification analysis |
| CN117274252B (en) * | 2023-11-20 | 2024-01-26 | 海澜智云科技有限公司 | Steel product surface flaw detection system based on identification analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116136393B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116136393B (en) | Bearing ring inner ring detection system and method | |
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| US6701615B2 (en) | Inspection and sorting system and method for part repair | |
| TWI232298B (en) | Apparatus and method for detecting surface defects on a workpiece such as a rolled/drawn metal bar | |
| CN109488888B (en) | Metal pipeline leakage monitoring method based on infrared temperature field multivariate analysis | |
| US9230318B2 (en) | Analysis of the digital image of the external surface of a tyre and processing of false measurement points | |
| US10209199B2 (en) | Surface inspection method, surface inspection device, manufacturing system, method of identifying defect formed area, and manufacturing method of steel pipe | |
| CN114536529B (en) | Automatic control method and system for AI-based shield segment forming process | |
| JP2017227606A (en) | Defect detection device and defect detection method | |
| Liu et al. | An improved image acquisition method for measuring hot forgings using machine vision | |
| AbouelNour et al. | Assisted defect detection by in-process monitoring of additive manufacturing using optical imaging and infrared thermography | |
| CN116402827B (en) | Image processing-based cable clamp plate defect detection method and device for coal mining machine | |
| CN107677677B (en) | Quantitative characterization method for segregation degree of continuous casting billet | |
| CN115937218B (en) | Surface defect detection method and system for cold stamping part | |
| KR101562988B1 (en) | Apparatus and method for detecting surface defects of hot billet | |
| CN111626104A (en) | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery | |
| CN113302009A (en) | Thermal imaging inspection of molds in foundry | |
| KR101309649B1 (en) | Apparatus for measuring amount of wear and tear for refractory in tapping hole sleeve of converter and method for the same | |
| Shankar et al. | Burning Zone Temperature Estimation of Rotary Kiln Using Flame Image Analysis in Cement Plants | |
| CN112501367A (en) | Method and system for quantitatively estimating content of silicon and sulfur in molten iron during blast furnace tapping | |
| Sangeetha et al. | Mathematical relationship between hotspot temperature, emissivity and distance in thermographs for condition monitoring of electrical equipments | |
| CN117351007B (en) | Furnace internal defect identification system based on infrared equipment | |
| CN115272269A (en) | Raw material blank furnace-entering positioning detection method, device and system | |
| CN110084780B (en) | Ceramic tile identification lane dividing method | |
| CN114048828B (en) | Furnace tube image processing method |
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 |