CN115953397A - Method and equipment for monitoring process preparation flow of conical bearing retainer - Google Patents
Method and equipment for monitoring process preparation flow of conical bearing retainer Download PDFInfo
- Publication number
- CN115953397A CN115953397A CN202310231627.7A CN202310231627A CN115953397A CN 115953397 A CN115953397 A CN 115953397A CN 202310231627 A CN202310231627 A CN 202310231627A CN 115953397 A CN115953397 A CN 115953397A
- Authority
- CN
- China
- Prior art keywords
- image
- conical bearing
- bearing retainer
- defective
- workpiece
- 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
Images
Classifications
-
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method and equipment for monitoring a process preparation flow of a conical bearing retainer, belongs to the technical field of image processing, and is used for solving the technical problems that in the process preparation flow of the existing conical bearing retainer, defective goods in each flow link are difficult to identify, the whole process preparation flow is easily affected, and the qualified rate of finished products is reduced. The method comprises the following steps: carrying out anomaly detection on the edge thickness of the prefabricated metal plate, and then carrying out metal surface crack characteristic extraction on the image of the conical bowl-shaped workpiece to obtain a first defective image; performing image shape matching processing on the initial conical bearing retainer image to determine a second defective image; performing surface defect characteristic image recognition on the finish machining conical bearing retainer image to determine a third defective image; and carrying out abnormity marking on the abnormal workpieces corresponding to the first, second and third defective images to obtain marked workpiece information.
Description
Technical Field
The application relates to the field of image processing and linkage control, in particular to a method and equipment for monitoring a process preparation flow of a conical bearing retainer.
Background
The main function of the conical bearing cage is to avoid direct contact between the rolling bodies, to space them apart from each other and to guide them to roll. The conventional conical bearing holder is generally manufactured by machining or integral pressing.
The existing conical bearing retainer is easy to have certain negative effects on the aspects of precision, roundness, cost and the like when a single preparation method is adopted, meanwhile, in the process preparation flow of the conical bearing retainer, real-time quality monitoring is difficult to be carried out on each flow link, so that a workpiece with problems can be operated all the time, the manufacturing cost of the retainer is increased, the finished product qualification rate of the conical bearing retainer is reduced, and in the whole process flow, because the process flow is carried out relatively quickly, defective products of each link are difficult to be accurately identified, subsequent process links can be possibly influenced, and unnecessary loss on some process flows is caused.
Disclosure of Invention
The embodiment of the application provides a method and equipment for monitoring a process preparation flow of a conical bearing retainer, which are used for solving the following technical problems: in the process preparation flow of the existing conical bearing retainer, defective products in each flow link are difficult to identify, the whole process preparation flow is easy to be influenced, and the finished product qualification rate of the conical bearing retainer is reduced.
The embodiment of the application adopts the following technical scheme:
in one aspect, an embodiment of the present application provides a method for monitoring a process preparation flow of a conical bearing retainer, including: acquiring an image of the edge thickness of the prefabricated metal plate by a preset area array CCD camera; carrying out abnormity detection on the edge thickness image to obtain a plate edge detection result of the edge thickness image; the prefabricated metal plate is a metal material to be processed for preparing the conical bearing retainer; based on the plate edge detection result, performing metal surface crack feature extraction on a punched and formed conical bowl-shaped workpiece image acquired by a preset camera to obtain crack image features; according to a preset classification recognition model, performing classification recognition on fracture types of the fracture image features to obtain a first defective image; carrying out hole milling on the rest conical bowl-shaped workpiece to obtain an initial conical bearing retainer; matching the image shape of the pre-acquired initial conical bearing retainer image according to a preset image shape matching template library to determine a second defective image; wherein the rest conical bowl-shaped workpiece is a conical bowl-shaped workpiece without defective work; carrying out surface sand blasting on the rest initial conical bearing retainer to obtain a finish machining conical bearing retainer; performing image recognition on relevant surface defect characteristics on the pre-acquired fine machining conical bearing retainer image to determine a third defective image; wherein the remaining initial conical bearing retainers are initial conical bearing retainers having no inferior details; carrying out abnormity marking on abnormal workpieces corresponding to the first, second and third defective images to obtain marked workpiece information; and classifying all the workpieces in the conveying belt according to the marked workpiece information to obtain a plurality of pieces of finished product conical bearing retainer information meeting the standard.
According to the embodiment of the application, the edge thickness of the metal material to be processed of the conical bearing retainer is detected, the image of the defective workpiece is detected on the unfinished workpiece in the technological processes of stretching, stamping, turning, vehicle bottom, hole milling, surface treatment and the like in the main technological preparation process, the image of the unfinished workpiece obtained in each link in the conical bearing retainer is combined with image recognition and detection of relevant sizes and easily-damaged parts, the defective product in each process link can be better recognized accurately in the technological preparation process, meanwhile, the recognized defective product is not subjected to subsequent link treatment any more, and is allowed to move along with a conveying belt, so that the whole technological process is smoother, the process cannot be suspended midway, and the influence on the whole technological preparation process is minimized. Meanwhile, the marks of the defective products are used for identification, the recording and classification identification of the finished conical bearing retainers can be better realized, and the finished product qualification rate of the conical bearing retainers is greatly improved.
In a feasible implementation mode, the prefabricated metal plate is subjected to edge thickness image acquisition through a preset area array CCD camera; and carrying out abnormity detection on the edge thickness image to obtain a plate edge detection result of the edge thickness image, and specifically comprising the following steps: shooting the side edge area of the prefabricated metal plate at multiple angles through a plurality of area array CCD cameras to obtain an edge thickness image; the edge thickness image is a plurality of edge port images of the prefabricated metal plate; acquiring a planar pixel image related to the thickness of the prefabricated metal plate in the edge port image; carrying out gray processing on the plane pixel image to obtain an initial gray contrast image, and carrying out point location identification on boundary points of a plurality of different pixel gray values in the initial gray contrast image through a preset linear fitting function to obtain a boundary point coordinate set in the initial gray contrast image; according to the boundary point coordinate set, point location curve fitting is carried out on the plurality of boundary points to obtain a gray value boundary curve; judging the curvature of the gray value boundary curve; if the curvature value of the gray value boundary curve is a false score, the side edge area of the prefabricated metal plate is a warped head area; if the curvature value of the gray value boundary curve is a true score, the side edge area of the prefabricated metal plate is a buckle tail area; determining the head warping area or the tail buckling area as an edge abnormal area, and determining the edge areas of the rest plates as edge normal areas; wherein, the panel edge detection result includes: the edge abnormal region and the edge normal region.
The embodiment of the application identifies the edge thickness of the prefabricated metal plate in the earlier-stage preparation process of the conical bearing retainer, so that the accurate detection and identification can be better carried out on the head warping and tail buckling conditions of the metal plate in the blanking process, the subsequent abnormal processing of the edge abnormal areas is avoided, and the yield of the conical bearing retainer is improved.
In a feasible implementation manner, based on the plate edge detection result, performing metal surface crack feature extraction on a stamped conical bowl-shaped workpiece image acquired by a preset camera to obtain crack image features, specifically including: stretching the metal plate corresponding to the normal edge region in the plate edge detection result by a preset metal hydraulic stretcher, and stamping the stretched metal plate in a conical bowl shape by a preset metal stamping machine to obtain a conical bowl-shaped workpiece; shooting the workpiece surface of the conical bowl-shaped workpiece through a preset camera to obtain an image of the conical bowl-shaped workpiece; acquiring a bowl wall image of a relevant bowl body area in the conical bowl-shaped workpiece image; wherein the bowl wall image comprises: an inner bowl wall image and an outer bowl wall image; performing pixel gray processing on the bowl wall image, and performing metal surface crack feature extraction on the bowl wall image subjected to gray processing in each direction pixel through Gabor image transformation to obtain texture structure features and abnormal curve features of the bowl wall image; wherein the respective directions include: transverse, longitudinal and diagonal directions; according to a preset Grouplet kurtosis algorithm, identifying irregular texture features of the bowl wall image to obtain abnormal texture features; carrying out weighted association on the abnormal texture structure features according to coefficient transformation of an associated domain in the group kurtosis to obtain coefficients based on the abnormal texture structure feature associated domain; and correspondingly associating the coefficient with each pixel point in the abnormal curve characteristic to determine the fracture image characteristic in the bowl wall image.
In a feasible implementation manner, according to a preset classification recognition model, performing classification recognition on fracture types on fracture image features to obtain a first defective image, specifically including: classifying, identifying and judging the fracture types in the fracture image features through a pre-trained KNN classification model: judging the depth of the pixel color of the gray pixel area corresponding to the fracture image characteristic; if a plurality of light-color areas exist in the gray-scale pixel area, the fracture image feature is a fracture image feature, and a fracture image corresponding to the fracture image feature is determined as a first defective image; based on the position of a hole milling window preset in the conical bowl-shaped workpiece, judging the position of a pixel dense area according to the crack pixel length and the crack pixel width corresponding to the crack image characteristics; if the position of the pixel dense area and the position of the hole milling window are in an overlapped state, and the length of the crack pixel and the width of the crack pixel are smaller than or equal to the size of the hole milling window, determining the crack image corresponding to the crack image characteristic as a first normal image; wherein the milled hole window size comprises: window height and window width; and if the position of the pixel dense area and the position of the hole milling window are not in an overlapped state, or the length of the crack pixel and the width of the crack pixel are greater than the size of the hole milling window, determining the crack image as a first defective image.
This application embodiment is through the image recognition to the metal crack condition of circular cone bowl shape work piece, and the qualification condition of this unfinished product work piece of monitoring that can be better is realized through handling to some tiny cracks or the tiny crackle that does not influence follow-up hole milling, car limit and vehicle bottom condition simultaneously, and the qualification condition of product has been guaranteed to the at utmost, has compromise again simultaneously with the saving on the cost, has improved the qualification rate of final product.
In a possible embodiment, the remaining conical bowl-shaped workpiece is subjected to a hole milling process, resulting in an initial conical bearing holder; and according to a preset image shape matching template library, carrying out image shape matching processing on the pre-acquired initial conical bearing retainer image to determine a second inferior image, and specifically comprising the following steps: determining a plurality of conical bowl-shaped workpieces corresponding to the first defective image as first defective workpieces, and determining the remaining conical bowl-shaped workpieces as normal conical bowl-shaped workpieces according to the identified first defective workpieces; performing hole milling treatment on the normal conical bowl-shaped workpiece through a preset machining lathe to obtain the initial conical bearing retainer; wherein the first defective workpiece is not subjected to hole milling treatment; acquiring an initial conical bearing retainer image and the size of the initial conical bearing retainer image through a camera pre-installed above a conveying belt; wherein the initial conical bearing retainer image size comprises: image length and image width; according to a preset rectangular frame, carrying out unified image interception on a window, a window beam and an end ring in the initial conical bearing retainer image to obtain a first cutting image; judging the gray variance of the window of the first cutting image; wherein the gray variance of the window is the gray pixel range inside the window; if the gray variance is smaller than or equal to a first preset threshold value, the first cut image is a normal window image; otherwise, the first cutting image is an abnormal window image; acquiring the number of pixels of the window beam in the first cutting image to obtain a window beam pixel value; performing circumferential function fitting on end ring pixel points in the first cutting image to obtain a circumferential function curve based on the end ring pixel points, and determining the circumferential curvature of the end ring of the function curve; based on different models of the initial conical bearing holder, acquiring a normal window image set, a window beam pixel value set and an end ring circumferential curvature set which are in one-to-one correspondence with multiple postures according to the multiple postures of the initial conical bearing holder under the standard size, and establishing an image shape matching template library based on the initial conical bearing holder under the standard size; matching the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing retainer image with the corresponding standard size in the image shape matching template library to obtain a matching result; and if the matching is consistent, determining the initial conical bearing retainer image as a second normal image, and if the matching is inconsistent or the first cutting image is an abnormal window image, determining the initial conical bearing retainer image as a second defective image.
According to the embodiment of the application, the defective products in the process stage can be quickly and accurately monitored by monitoring the window, the window beam and the roundness of the initial conical bearing retainer after hole milling and matching the template based on the standard image shape.
In a possible implementation, matching the normal window image, the window beam pixel values, and the end ring circumference ratio in the initial conical bearing holder image with corresponding standard sizes in the image shape matching template library to obtain a matching result, specifically including: extracting a normal window image set, a window beam pixel value set and an end ring circumference curvature set in the image shape matching template library based on an HALCON algorithm in the image shape matching template library, and determining a plurality of original shape matching templates according to template operators in the HALCON algorithm; generating a template by the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing retainer image to obtain a target shape matching template; and performing coverage matching of a data layer on the target shape matching template and the plurality of original shape matching templates, and determining a matching result according to the similarity degree of data coverage.
In a possible embodiment, the remaining initial conical bearing holder is surface blasted resulting in a finished conical bearing holder; and carrying out image recognition of relevant surface defect characteristics on the pre-acquired fine machining conical bearing retainer image, and determining a third defective image, wherein the image recognition specifically comprises the following steps: determining a plurality of initial conical bearing retainers corresponding to the second inferior image as second inferior workpieces, and determining the remaining initial conical bearing retainers as normal initial conical bearing retainers according to the identified second inferior workpieces; carrying out sand blasting on the normal initial conical bearing retainer through a sand blasting machine with a preset multi-angle to obtain a finish machining conical bearing retainer; the second defective workpiece and the first defective workpiece are not subjected to sand blasting treatment; acquiring images of the finish machining conical bearing retainer at multiple angles through a preset camera according to the multi-angle irradiation of the adjustable light source system; performing gray level processing on the image of the finish machining conical bearing retainer to obtain a gray level image of the finish machining conical bearing retainer; identifying edge information of the gray level image through an image edge detection differential operator to obtain edge characteristics; carrying out non-maximum suppression interpolation processing on the gray level image according to the central edge operator of the edge feature and the edge convolution differential in the gray level image, and obtaining a gray level histogram based on the gray level image based on the gradient distribution characteristic of a Gaussian function; according to a preset pixel gray level, performing region division of an upper threshold value and a lower threshold value on the gray histogram to determine an average gray value of the gray image; comparing the average gray value with a first preset threshold value to determine the third defective image; wherein the third afterimage is a finished conical bearing holder image having surface defect characteristics.
The identification of the multi-angle surface defect characteristics of the workpiece subjected to sand blasting is favorable for identifying the surface defect, namely the identification of the defective workpiece generated in the sand blasting process, the qualification rate of subsequent finished workpieces can be further ensured, meanwhile, hidden defect blind spots can be well monitored based on the multi-angle sand blasting and the identification of the surface defect characteristics, and the identification and the judgment can be more accurately and rapidly carried out based on the threshold division of the gray level histogram.
In a feasible implementation manner, the abnormal workpiece corresponding to the first, second, and third defective images is subjected to abnormal marking to obtain marked workpiece information, which specifically includes: generating and processing serial numbers of the workpieces in a binary system form by using a plurality of abnormal conical bowl-shaped workpieces corresponding to the first defective image, a plurality of abnormal initial conical bearing retainers corresponding to the second defective image and a plurality of abnormal finish conical bearing retainers corresponding to the third defective image to obtain a workpiece marking serial number; generating an even number in a decimal form corresponding to the workpiece mark number; and marking an abnormal serial number of the abnormal workpiece according to the even serial number, and determining the marked workpiece information corresponding to the abnormal workpiece.
The problem of solving logical operation that this application embodiment can be better is through marking with the work piece serial number of binary system form earlier, further expands into mathematical figure operation, and the complicated environment in adaptation workshop that can be better has stronger interference and reliability, is favorable to carrying out preliminary mark to unusual work piece, later turns into the decimal even serial number that is favorable to the staff to look over again, forms directly perceived easily unusual serial number promptly, then finally regenerates the mark work piece information of unusual work piece.
In a possible implementation manner, according to the marked workpiece information, the finished workpieces are classified for all workpieces in the conveyor belt, and a plurality of pieces of finished conical bearing holder information meeting the standard are obtained, which specifically includes: according to a preset 3D object tracking algorithm, tracking the information of the marked workpieces in real time, and determining the real-time position of each abnormal workpiece; laser marking the real-time position of each abnormal workpiece through a laser guidance system to obtain laser marked workpiece information; based on a preset time interval, classifying and eliminating the laser marking workpiece information in the conveying belt to screen out corresponding finished workpieces and obtain a plurality of pieces of finished conical bearing retainer information meeting the standard.
On the other hand, the embodiment of the present application further provides a monitoring device for a process preparation flow of a conical bearing retainer, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of monitoring a process preparation flow of a conical bearing holder according to any of the embodiments described above.
According to the embodiment of the application, the edge thickness of the metal material to be processed of the conical bearing retainer is detected, the image of the defective workpiece is detected on the unfinished workpiece in the technological processes of stretching stamping, edge turning, vehicle bottom, hole milling, surface treatment and the like in the main technological preparation process, the image of the unfinished workpiece obtained in each link in the conical bearing retainer is combined with image identification and detection of relevant sizes and easily damaged parts, the defective product in each process link can be identified accurately in the technological preparation process, meanwhile, the identified defective product is not subjected to subsequent link treatment any more, and is made to move along with a conveying belt, so that the whole technological process is smoother, the process cannot be suspended midway, and the influence of the whole technological preparation process is reduced to the minimum. Meanwhile, the marks of the defective products are used for identification, the recording and classification identification of the finished conical bearing retainers can be better, and the finished product qualification rate of the conical bearing retainers is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
fig. 1 is a flowchart of a monitoring method for a process manufacturing flow of a conical bearing retainer according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a monitoring device of a process preparation flow of a conical bearing retainer according to an embodiment of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
The embodiment of the application provides a method for monitoring a process preparation flow of a conical bearing retainer, and as shown in fig. 1, the method for monitoring the process preparation flow of the conical bearing retainer specifically comprises the following steps of S101-S106:
s101, acquiring an image of the edge thickness of the prefabricated metal plate through a preset area array CCD camera. And carrying out abnormity detection on the edge thickness image to obtain a plate edge detection result of the edge thickness image. Wherein the prefabricated metal plate is a metal material to be processed for preparing the conical bearing retainer.
Specifically, the side edge area of the prefabricated metal plate is shot in multiple angles through a plurality of area array CCD cameras to obtain an edge thickness image. Wherein the edge thickness image is a plurality of edge port images of the prefabricated metal plate. And acquiring a planar pixel image related to the thickness of the prefabricated metal plate in the edge port image. Carrying out gray processing on the plane pixel image to obtain an initial gray contrast image, and carrying out point location identification on demarcation points of a plurality of different pixel gray values in the initial gray contrast image through a preset linear fitting function to obtain a demarcation point coordinate set in the initial gray contrast image.
And further, performing point-to-point curve fitting on the plurality of boundary points according to the boundary point coordinate set to obtain a gray value boundary curve. And judging the curvature of the gray value boundary curve. And if the curvature value of the gray value boundary curve is a false score, the edge area of the side surface of the prefabricated metal plate is a warped area. And if the curvature value of the gray value boundary curve is the true fraction, the side edge area of the prefabricated metal plate is the buckle tail area. And determining the head warping area or the tail buckling area as an edge abnormal area, and determining the edge area of the rest plates as an edge normal area.
Wherein, panel edge detection result includes: edge anomaly regions and edge normality regions.
In one embodiment, curve detection of the edge thickness of a metal plate is performed on the metal plate placed in the laser blanking machine through a plurality of area array CCD cameras in the laser blanking machine, point location identification is performed on boundary points of a plurality of different pixel gray values in an image according to an obtained plane pixel image related to the thickness of the metal plate to obtain a coordinate set of the boundary points of different pixels, then a gray value boundary curve is constructed, whether the edge of the metal plate has head warping or tail buckling is obtained according to the curvature value of the curve, and edge image areas corresponding to the abnormal curvature values are determined to be edge abnormal areas.
S102, based on the plate edge detection result, extracting the metal surface crack characteristics of the punched and formed conical bowl-shaped workpiece image collected by a preset camera to obtain the crack image characteristics. And according to a preset classification recognition model, performing classification recognition on fracture types on the fracture image characteristics to obtain a first defective image.
Specifically, through presetting a metal hydraulic drawing machine, the metal plate corresponding to the normal region of the edge in the plate edge detection result is drawn, and through presetting a metal punching machine, the drawn metal plate is punched in a conical bowl shape, so that a conical bowl-shaped workpiece is obtained. And photographing the workpiece surface of the conical bowl-shaped workpiece by a preset camera to obtain an image of the conical bowl-shaped workpiece. And acquiring a bowl wall image of the bowl body area in the conical bowl-shaped workpiece image. Wherein the bowl wall image comprises: an inner bowl wall image and an outer bowl wall image. Performing pixel gray processing on the bowl wall image, and performing metal surface crack feature extraction on the bowl wall image subjected to the gray processing in each direction pixel through Gabor image transformation to obtain texture structure features and abnormal curve features of the bowl wall image. Wherein each direction comprises: transverse, longitudinal, and diagonal directions.
Further, according to a preset Grouplet kurtosis algorithm, identifying irregular texture structure features of the bowl wall image to obtain the abnormal texture structure features. And according to coefficient transformation of the associated domain in the group kurtosis, weighting and associating the abnormal texture structure features to obtain coefficients based on the associated domain of the abnormal texture structure features. And correspondingly associating the coefficient with each pixel point in the abnormal curve characteristic to determine the crack image characteristic in the bowl wall image.
Further, through a pre-trained KNN classification model, classification, identification and judgment are carried out on crack types in the crack image features: and judging the depth of the pixel color of the gray pixel area corresponding to the fracture image characteristic. And if the gray-scale pixel area has a plurality of light-color areas, the fracture image feature is a fracture image feature, and the fracture image corresponding to the fracture image feature is determined as a first defective image.
Based on the position of a hole milling window preset in the conical bowl-shaped workpiece, judging the position of a pixel dense region by using the crack pixel length and the crack pixel width corresponding to the crack image characteristics:
and if the position of the pixel dense region and the position of the milling hole window are in an overlapped state, and the length of the crack pixel and the width of the crack pixel are less than or equal to the size of the milling hole window, determining a crack image corresponding to the crack image characteristic as a first normal image. Wherein, the milling bore window size includes: window height and window width.
And if the position of the pixel dense area and the position of the milling hole window are not in an overlapped state, or the length of the crack pixel and the width of the crack pixel are greater than the size of the milling hole window, determining the crack image as a first defective image.
In one embodiment, a metal hydraulic stretcher is used for punching a stretched metal plate in a conical bowl shape to obtain a conical bowl-shaped workpiece, a preset camera is used for shooting the conical bowl-shaped workpiece to obtain a conical bowl-shaped workpiece image, then the type identification of metal surface crack characteristics is carried out on the obtained inner bowl wall image and the metal surface image corresponding to the outer bowl wall image to judge different crack image characteristics, then the pixel color depth judgment is carried out on a gray pixel area corresponding to the crack image characteristics based on a KNN classification model to determine whether a fracture or a crack exists in the crack image, the images are determined to be a first defective image, namely a defective workpiece, then the length of the crack pixel and the position of a hole milling window are determined to determine whether the metal crack belongs to an irrelevant crack, if the subsequent hole milling process is not affected, the crack image is determined to be a normal image, the subsequent process is continued, and if the subsequent hole milling process is affected, the metal crack image which cannot be added continuously is determined to be the first defective image.
And S103, performing hole milling on the residual conical bowl-shaped workpiece to obtain the initial conical bearing retainer. And according to a preset image shape matching template library, carrying out image shape matching processing on the pre-acquired initial conical bearing retainer image to determine a second defective image. Wherein, the rest conical bowl-shaped workpiece is a conical bowl-shaped workpiece without defective work.
Specifically, a plurality of conical bowl-shaped workpieces corresponding to the first defective image are determined as first defective workpieces, and the remaining conical bowl-shaped workpieces are determined as normal conical bowl-shaped workpieces according to the identified first defective workpieces. And (3) carrying out hole milling treatment on the normal conical bowl-shaped workpiece through a preset machining lathe to obtain the initial conical bearing retainer. Wherein, the first defective workpiece is not subjected to hole milling treatment. An initial conical bearing holder image and an initial conical bearing holder image size are acquired by a camera pre-mounted above the conveyor belt. Wherein the initial conical bearing retainer image size comprises: image length and image width.
Further, according to a preset rectangular frame, carrying out unified image interception on the window, the window beam and the end ring in the initial conical bearing retainer image to obtain a first cutting image. And judging the gray variance of the window of the first cutting image. Wherein the grayscale variance of the window is the grayscale pixel range inside the window. And if the gray variance is smaller than or equal to a first preset threshold value, the first cutting image is a normal window image. Otherwise, the first cutting image is an abnormal window image. And acquiring the pixel quantity of the window beam in the first cutting image to obtain a window beam pixel value. And performing circumference function fitting on the end ring pixel points in the first cutting image to obtain a circumference function curve based on the end ring pixel points, and determining the circumference curvature of the end ring of the function curve.
Further, based on different models of the initial conical bearing holder, according to multiple postures of the initial conical bearing holder under the standard size, a normal window image set, a window beam pixel value set and an end ring circumference curvature set which are in one-to-one correspondence with the multiple postures are obtained, and an image shape matching template base based on the initial conical bearing holder under the standard size is established.
Further, matching the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing retainer image with the corresponding standard size in the image shape matching template library to obtain a matching result. And if the matching is consistent, determining the initial conical bearing retainer image as a second normal image, and if the matching is inconsistent or the first cutting image is an abnormal window image, determining the initial conical bearing retainer image as a second inferior image.
The method comprises the steps of extracting a normal window image set, a window beam pixel value set and an end ring circumference curvature set in an image shape matching template library based on a HALCON algorithm in the image shape matching template library, and determining a plurality of original shape matching templates according to template operators in the HALCON algorithm. And generating a template by using a normal window image, a window beam pixel value and an end ring circumference ratio in the initial conical bearing retainer image to obtain a target shape matching template. And performing coverage matching on the data layer by using the target shape matching template and the plurality of original shape matching templates, and determining a matching result according to the similarity degree of data coverage.
In one embodiment, the first cropped image includes: step 1: inputting an initial conical bearing retainer image I0 with a size of
. Step 2: is measured by the size>
The rectangular frame of (1) cuts out the initial conical bearing holder image I0, and the rectangular frame includes the window a, the window beam b, and the end ring c in the initial conical bearing holder image in the longitudinal direction. And step 3: and taking the upper left corner of the initial conical bearing retainer image as an origin, the image width as an abscissa and the length as an ordinate. Setting the initial ordinate of the top end of the rectangular frame as S, wherein S generally meets the following condition: s = (W0-W1)/2, the grayscale variance of the grayscale pixel range inside the window with ordinate S is calculated. And 4, step 4: judging whether the clipping is normal (that is, whether the gray pixel value inside the window meets the preset threshold value) according to the gray variance) And performing the next operation, wherein if the gray variance is less than or equal to a first preset threshold value, the first cutting image is a normal window image. Otherwise, the first cropping image is an abnormal window image.
In one embodiment, the machining lathe is used for performing edge turning, vehicle bottom milling and hole milling operations on a normal conical bowl-shaped workpiece identified in the previous process, the conical bowl-shaped workpiece corresponding to a first incomplete image is not subjected to any operation, the conical bowl-shaped workpiece continues to move along with a conveying belt, the machining lathe is only used for performing subsequent processing on the normal conical bowl-shaped workpiece, then an initial conical bearing retainer is obtained, the initial conical bearing retainer is photographed according to a preset monitoring camera to obtain an initial conical bearing retainer image, then the initial conical bearing retainer image is cut according to a preset rectangular frame, then the gray variance of a window is judged, whether the window size in the initial conical bearing retainer image meets a preset standard or not is judged, then the window Liang Xiangsu value and the end ring circumference curvature are obtained, then the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing retainer image are subjected to data level coverage matching with a plurality of original shape matching templates based on a template operator in a HALCON algorithm, the degree of matching between the normal window image, the window beam pixel value and the end ring circumference ratio are determined to be inconsistent with the initial conical bearing retainer image, and the initial conical bearing retainer image is determined as a second incomplete image.
In one embodiment, according to different types of conical bearing holders, the initial conical bearing holder is subjected to slope pressing treatment on the window beam, then an initial conical bearing holder image subjected to slope pressing treatment is obtained again, a pixel coordinate system corresponding to slope inclination in the image is identified and judged, the initial conical bearing holder image which does not meet the slope inclination requirement is also judged as a second defective image, all the initial conical bearing holders corresponding to the qualified initial conical bearing holder images are remained to continue the subsequent surface treatment process, and the initial conical bearing holders corresponding to the second defective image do not participate in the subsequent surface blasting treatment process and move along with the conveying belt until the abnormal workpieces are judged to be classified.
And S104, performing surface sand blasting on the rest initial conical bearing retainer to obtain a finish conical bearing retainer. And carrying out image recognition on relevant surface defect characteristics on the pre-acquired image of the finish machining conical bearing retainer to determine a third defective image. Wherein the remaining initial conical bearing retainers are initial conical bearing retainers having no remnants.
Specifically, a plurality of initial conical bearing holders corresponding to the second inferior image are determined as a second inferior workpiece, and the remaining initial conical bearing holders are determined as normal initial conical bearing holders according to the identified second inferior workpiece. And (3) carrying out sand blasting on the normal initial conical bearing retainer through a sand blasting machine with a preset multi-angle to obtain the finish machining conical bearing retainer. And the second defective workpiece and the first defective workpiece are not subjected to sand blasting treatment.
Further, according to the multi-angle irradiation of the adjustable light source system, a finished conical bearing retainer image under multiple angles is obtained through a preset camera. And carrying out gray level processing on the image of the finish machining conical bearing retainer to obtain a gray level image of the finish machining conical bearing retainer. And identifying the edge information of the gray level image through an image edge detection differential operator to obtain edge characteristics.
Further, according to the central edge operator of the edge feature and the edge convolution differential in the gray level image, the non-maximum suppression interpolation processing of the gray level image is carried out, and the gray level histogram based on the gray level image is obtained based on the gradient distribution characteristic of the Gaussian function.
Further, according to the preset pixel gray level, the gray histogram is subjected to region division of an upper threshold value and a lower threshold value, and the average gray value of the gray map is determined. And comparing the average gray value with a first preset threshold value to determine a third defective image. Wherein the third residual image is a finished conical bearing holder image having surface defect characteristics.
In an embodiment, before the sand blasting is performed on the initial conical bearing retainer, the window hole can be optionally expanded, then the sand blasting is performed, then an image edge detection differential operator is performed on a finished conical bearing retainer image, the edge feature of a gray scale image is identified, then the gray scale histogram is subjected to region division of upper and lower limit thresholds according to a preset pixel gray level, the average gray scale value of the gray scale image is determined, when the average gray scale value is larger than a first preset threshold, it can be determined that the finished conical bearing retainer image has a surface defect feature, and the finished conical bearing retainer image is determined as a third residual image, otherwise, the finished conical bearing retainer image is a normal image of the workpiece. And selecting secondary sand blasting for the finish machining conical bearing retainer corresponding to the third defective image, continuing to perform image identification related to the surface defect characteristics according to the central edge operator of the edge characteristics and the edge convolution differential in the gray-scale image, and automatically ending the sand blasting if the image is still the third defective image, and performing subsequent processes.
And S105, carrying out abnormity marking on the abnormal workpieces corresponding to the first, second and third defective images to obtain marked workpiece information.
Specifically, a plurality of abnormal conical bowl-shaped workpieces corresponding to the first defective image, a plurality of abnormal initial conical bearing retainers corresponding to the second defective image and a plurality of abnormal finish conical bearing retainers corresponding to the third defective image are subjected to binary workpiece serial number generation processing to obtain workpiece mark serial numbers. An even number corresponding to the workpiece mark number in a decimal form is generated.
Furthermore, according to the even serial number, the abnormal workpieces are marked with abnormal serial numbers, and the marked workpiece information corresponding to the abnormal workpieces is determined.
In one embodiment, after the sand blasting treatment, a plurality of abnormal conical bowl-shaped workpieces corresponding to the first defective image, a plurality of abnormal initial conical bearing holders corresponding to the second defective image and a plurality of abnormal finish conical bearing holders corresponding to the third defective image are reserved in the conveying belt, which are collectively referred to as abnormal workpieces, then the abnormal workpieces are subjected to generation treatment of binary-form workpiece serial numbers, and then the abnormal workpieces are converted into binary-form workpiece serial numbers which are easy for a worker to check, and finally the marked workpiece information corresponding to the abnormal workpieces is determined.
And S106, classifying all the workpieces in the conveying belt according to the marked workpiece information to obtain a plurality of pieces of finished product conical bearing retainer information meeting the standard.
Specifically, according to a preset 3D object tracking algorithm, information of a plurality of marked workpieces is tracked in real time, and the real-time position of each abnormal workpiece is determined. And laser marking is carried out on the real-time position of each abnormal workpiece through a laser guidance system, so that the information of the laser marked workpiece is obtained.
Further, based on a preset time interval, classifying and eliminating the laser marked workpiece information in the conveying belt to screen out corresponding finished workpieces, and obtaining a plurality of pieces of finished conical bearing retainer information meeting the standard.
In one embodiment, the laser guidance system performs laser marking on the abnormal workpieces and generates corresponding laser marked workpiece information, then a worker can screen each abnormal workpiece according to the laser marked workpiece information, and finally only a plurality of pieces of finished conical bearing retainer information meeting the standard are reserved in the conveying belt and the corresponding system.
In addition, an embodiment of the present application further provides a monitoring device for a process preparation flow of a conical bearing retainer, as shown in fig. 2, the monitoring device 200 for the process preparation flow of the conical bearing retainer specifically includes:
at least one processor 201. And a memory 202 communicatively coupled to the at least one processor 201; wherein the memory 202 stores instructions executable by the at least one processor 201 to enable the at least one processor 201 to:
acquiring an image of the edge thickness of the prefabricated metal plate by a preset area array CCD camera; carrying out abnormity detection on the edge thickness image to obtain a plate edge detection result of the edge thickness image; the prefabricated metal plate is a metal material to be processed for preparing the conical bearing retainer;
based on the plate edge detection result, performing metal surface crack feature extraction on a punched and formed conical bowl-shaped workpiece image collected by a preset camera to obtain crack image features; classifying and identifying the crack types of the features of the crack image according to a preset classification and identification model to obtain a first defective image;
milling the residual conical bowl-shaped workpiece to obtain an initial conical bearing retainer; matching the image shape of the pre-acquired initial conical bearing retainer image according to a preset image shape matching template library to determine a second defective image; wherein, the rest conical bowl-shaped workpieces are conical bowl-shaped workpieces without defective work order;
carrying out surface sand blasting on the rest initial conical bearing retainer to obtain a finish machining conical bearing retainer; performing image recognition related to surface defect characteristics on the pre-acquired image of the finish machining conical bearing retainer to determine a third defective image; wherein the remaining initial conical bearing retainers are initial conical bearing retainers having no inferior rank;
carrying out abnormity marking on abnormal workpieces corresponding to the first defective image, the second defective image and the third defective image to obtain marked workpiece information;
and classifying all the workpieces in the conveying belt according to the marked workpiece information to obtain a plurality of pieces of finished product conical bearing retainer information meeting the standard.
According to the embodiment of the application, the edge thickness of the metal material to be processed of the conical bearing retainer is detected, the image of the defective workpiece is detected on the unfinished workpiece in the technological processes of stretching stamping, edge turning, vehicle bottom, hole milling, surface treatment and the like in the main technological preparation process, the image of the unfinished workpiece obtained in each link in the conical bearing retainer is combined with image identification and detection of relevant sizes and easily damaged parts, the defective product in each process link can be identified accurately in the technological preparation process, meanwhile, the identified defective product is not subjected to subsequent link treatment any more, and is made to move along with a conveying belt, so that the whole technological process is smoother, the process cannot be suspended midway, and the influence of the whole technological preparation process is reduced to the minimum. Meanwhile, the marks of the defective products are used for identification, the recording and classification identification of the finished conical bearing retainers can be better, and the finished product qualification rate of the conical bearing retainers is greatly improved.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the embodiments of the present application pertain. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the embodiments of the present application shall be included in the scope of the claims of the present application.
Claims (10)
1. A method for monitoring a process preparation flow of a conical bearing retainer, the method comprising:
acquiring an image of the edge thickness of the prefabricated metal plate by a preset area array CCD camera; carrying out abnormity detection on the edge thickness image to obtain a plate edge detection result of the edge thickness image; the prefabricated metal plate is a metal material to be processed for preparing the conical bearing retainer;
based on the plate edge detection result, performing metal surface crack feature extraction on a punched conical bowl-shaped workpiece image acquired by a preset camera to obtain crack image features; according to a preset classification recognition model, performing classification recognition on the crack image characteristics to obtain a first defective image;
milling the residual conical bowl-shaped workpiece to obtain an initial conical bearing retainer; matching the image shape of the pre-acquired initial conical bearing retainer image according to a preset image shape matching template library to determine a second defective image; wherein the rest conical bowl-shaped workpiece is a conical bowl-shaped workpiece without defective work;
carrying out surface sand blasting on the rest initial conical bearing retainer to obtain a finish machining conical bearing retainer; performing image recognition related to surface defect characteristics on the pre-acquired image of the finish machining conical bearing retainer to determine a third defective image; wherein the remaining initial conical bearing retainers are initial conical bearing retainers having no inferior details;
carrying out abnormity marking on the abnormal workpieces corresponding to the first, second and third defective images to obtain marked workpiece information;
and classifying all the workpieces in the conveying belt according to the marked workpiece information to obtain a plurality of pieces of finished product conical bearing retainer information meeting the standard.
2. The method for monitoring the process preparation flow of the conical bearing retainer according to claim 1, wherein the image acquisition of the edge thickness of the prefabricated metal plate is performed by a preset area array CCD camera; and carrying out abnormity detection on the edge thickness image to obtain a plate edge detection result of the edge thickness image, and specifically comprising the following steps:
shooting the side edge area of the prefabricated metal plate at multiple angles through a plurality of area array CCD cameras to obtain an edge thickness image; the edge thickness image is a plurality of edge port images of the prefabricated metal plate;
acquiring a planar pixel image related to the thickness of the prefabricated metal plate in the edge port image;
carrying out gray processing on the plane pixel image to obtain an initial gray contrast image, and carrying out point location identification on boundary points of a plurality of different pixel gray values in the initial gray contrast image through a preset linear fitting function to obtain a boundary point coordinate set in the initial gray contrast image;
according to the boundary point coordinate set, point location curve fitting is carried out on the plurality of boundary points to obtain a gray value boundary curve; judging the curvature of the gray value boundary curve;
if the curvature value of the gray value boundary curve is a false score, the edge area of the side surface of the prefabricated metal plate is a warped area; if the curvature value of the gray value dividing curve is a true score, the edge area of the side surface of the prefabricated metal plate is a buckle tail area;
determining the head warping area or the tail buckling area as an edge abnormal area, and determining the edge areas of the rest plates as edge normal areas;
wherein, the panel edge detection result includes: the edge abnormal region and the edge normal region.
3. The method for monitoring the process preparation flow of the conical bearing retainer according to claim 1, wherein based on the plate edge detection result, metal surface crack feature extraction is performed on a conical bowl-shaped workpiece image which is obtained by stamping and formed by a preset camera to obtain crack image features, and specifically comprises:
performing plate stretching on a metal plate corresponding to an edge normal area in the plate edge detection result through a preset metal hydraulic stretcher, and performing conical bowl-shaped stamping on the stretched metal plate through a preset metal stamping machine to obtain a conical bowl-shaped workpiece; shooting the workpiece surface of the conical bowl-shaped workpiece through a preset camera to obtain an image of the conical bowl-shaped workpiece;
acquiring a bowl wall image of a relevant bowl body area in the conical bowl-shaped workpiece image; wherein the bowl wall image comprises: an inner bowl wall image and an outer bowl wall image;
performing pixel gray processing on the bowl wall image, and performing metal surface crack feature extraction on the bowl wall image subjected to gray processing in each direction pixel through Gabor image transformation to obtain texture structure features and abnormal curve features of the bowl wall image; wherein the respective directions include: transverse, longitudinal and diagonal directions;
according to a preset Grouplet kurtosis algorithm, identifying irregular texture structure features of the bowl wall image to obtain abnormal texture structure features; carrying out weighted association on the abnormal texture structure features according to coefficient transformation of an associated domain in the group kurtosis to obtain coefficients based on the abnormal texture structure feature associated domain;
and correspondingly associating the coefficient with each pixel point in the abnormal curve characteristic to determine the fracture image characteristic in the bowl wall image.
4. The method for monitoring the process preparation flow of the conical bearing retainer according to claim 1, wherein the step of performing classification recognition of the crack type on the crack image features according to a preset classification recognition model to obtain a first defective image specifically comprises:
classifying, identifying and judging the types of cracks in the crack image features through a pre-trained KNN classification model;
judging the depth of the pixel color of the gray pixel area corresponding to the fracture image characteristic; if a plurality of light-color areas exist in the gray-scale pixel area, the crack image feature is a split image feature, and a crack image corresponding to the split image feature is determined as a first defective image;
based on the position of a hole milling window preset in the conical bowl-shaped workpiece, judging the position of a pixel dense area according to the crack pixel length and the crack pixel width corresponding to the crack image characteristics;
if the position of the pixel dense area and the position of the hole milling window are in an overlapped state, and the length of the crack pixel and the width of the crack pixel are smaller than or equal to the size of the hole milling window, determining the crack image corresponding to the crack image characteristic as a first normal image; wherein the milled hole window size comprises: window height and window width;
and if the position of the pixel dense area and the position of the hole milling window are not in an overlapped state, or the length of the crack pixel and the width of the crack pixel are greater than the size of the hole milling window, determining the crack image as a first defective image.
5. The method for monitoring the process preparation flow of the conical bearing retainer according to claim 1, wherein the remaining conical bowl-shaped workpiece is subjected to hole milling to obtain an initial conical bearing retainer; and according to a preset image shape matching template library, carrying out image shape matching processing on the pre-acquired initial conical bearing retainer image to determine a second inferior image, and specifically comprising the following steps:
determining a plurality of conical bowl-shaped workpieces corresponding to the first defective image as first defective workpieces, and determining the remaining conical bowl-shaped workpieces as normal conical bowl-shaped workpieces according to the identified first defective workpieces;
performing hole milling treatment on the normal conical bowl-shaped workpiece through a preset machining lathe to obtain the initial conical bearing retainer; wherein the first defective workpiece is not subjected to hole milling treatment;
acquiring an initial conical bearing retainer image and the size of the initial conical bearing retainer image through a camera pre-installed above a conveying belt; wherein the initial conical bearing retainer image size comprises: image length and image width;
according to a preset rectangular frame, carrying out unified image interception on a window, a window beam and an end ring in the initial conical bearing retainer image to obtain a first cutting image; judging the gray variance of the window of the first cutting image; wherein the gray variance of the window is the gray pixel range inside the window;
if the gray variance is smaller than or equal to a first preset threshold value, the first cutting image is a normal window image; otherwise, the first cutting image is an abnormal window image;
acquiring the number of pixels of the window beam in the first cutting image to obtain a window beam pixel value;
performing circumferential function fitting on end ring pixel points in the first cutting image to obtain a circumferential function curve based on the end ring pixel points, and determining the circumferential curvature of the end ring of the function curve;
based on different models of the initial conical bearing holder, acquiring a normal window image set, a window beam pixel value set and an end ring circumference curvature set which are in one-to-one correspondence with multiple postures according to the multiple postures of the initial conical bearing holder under the standard size, and establishing an image shape matching template library based on the initial conical bearing holder under the standard size;
matching the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing retainer image with the corresponding standard size in the image shape matching template library to obtain a matching result; and if the matching is consistent, determining the initial conical bearing retainer image as a second normal image, and if the matching is inconsistent or the first cutting image is an abnormal window image, determining the initial conical bearing retainer image as a second defective image.
6. The method for monitoring a process preparation flow of a conical bearing holder according to claim 5, wherein matching of a shape template is performed on the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing holder image and a corresponding standard size in the image shape matching template library to obtain a matching result, specifically comprising:
extracting a normal window image set, a window beam pixel value set and an end ring circumference curvature set in the image shape matching template library based on an HALCON algorithm in the image shape matching template library, and determining a plurality of original shape matching templates according to template operators in the HALCON algorithm;
generating a template by the normal window image, the window beam pixel value and the end ring circumference ratio in the initial conical bearing retainer image to obtain a target shape matching template;
and performing coverage matching of a data layer on the target shape matching template and the plurality of original shape matching templates, and determining a matching result according to the similarity degree of data coverage.
7. A method for monitoring a process preparation flow of a conical bearing holder according to claim 1, characterized in that the remaining initial conical bearing holder is surface blasted resulting in a finished conical bearing holder; and carrying out image recognition of relevant surface defect characteristics on the pre-acquired fine machining conical bearing retainer image, and determining a third defective image, wherein the image recognition specifically comprises the following steps:
determining a plurality of initial conical bearing retainers corresponding to the second inferior image as second inferior workpieces, and determining the remaining initial conical bearing retainers as normal initial conical bearing retainers according to the identified second inferior workpieces;
carrying out sand blasting on the normal initial conical bearing retainer through a sand blasting machine with a preset multi-angle to obtain a finish machining conical bearing retainer; the second defective workpiece and the first defective workpiece are not subjected to sand blasting treatment;
acquiring images of the finish machining conical bearing retainer at multiple angles through a preset camera according to the multi-angle irradiation of the adjustable light source system; performing gray level processing on the image of the finish machining conical bearing retainer to obtain a gray level image of the finish machining conical bearing retainer;
identifying edge information of the gray level image through an image edge detection differential operator to obtain edge characteristics;
carrying out non-maximum suppression interpolation processing on the gray level image according to the central edge operator of the edge feature and the edge convolution differential in the gray level image, and obtaining a gray level histogram based on the gray level image based on the gradient distribution characteristic of a Gaussian function;
according to a preset pixel gray level, performing region division of an upper threshold value and a lower threshold value on the gray histogram to determine an average gray value of the gray image;
comparing the average gray value with a first preset threshold value to determine the third defective image; wherein the third afterimage is a finished conical bearing holder image having surface defect characteristics.
8. The method for monitoring a process preparation flow of a conical bearing retainer according to claim 1, wherein the step of abnormally marking the abnormal workpiece corresponding to the first, second and third defective images to obtain marked workpiece information specifically comprises:
generating and processing serial numbers of the workpieces in a binary system form by using a plurality of abnormal conical bowl-shaped workpieces corresponding to the first defective image, a plurality of abnormal initial conical bearing retainers corresponding to the second defective image and a plurality of abnormal finish conical bearing retainers corresponding to the third defective image to obtain a workpiece marking serial number;
generating an even number in a decimal form corresponding to the workpiece mark number;
and marking an abnormal serial number of the abnormal workpiece according to the even serial number, and determining the marked workpiece information corresponding to the abnormal workpiece.
9. The method for monitoring the process preparation flow of a conical bearing retainer according to claim 1, wherein the step of classifying all workpieces in a conveyor belt into finished workpieces according to the marked workpiece information to obtain a plurality of pieces of finished conical bearing retainer information meeting a standard specifically comprises the steps of:
according to a preset 3D object tracking algorithm, tracking the information of the marked workpieces in real time, and determining the real-time position of each abnormal workpiece;
laser marking is carried out on the real-time position of each abnormal workpiece through a laser guidance system, and laser marking workpiece information is obtained;
and based on a preset time interval, classifying and eliminating the laser marking workpiece information in the conveying belt to screen out the corresponding finished workpiece, and obtaining a plurality of pieces of finished conical bearing retainer information meeting the standard.
10. Monitoring device of a process preparation flow of a conical bearing holder, characterized in that the device comprises:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of monitoring a process preparation flow of a conical bearing holder according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310231627.7A CN115953397B (en) | 2023-03-13 | 2023-03-13 | Method and equipment for monitoring process preparation flow of conical bearing retainer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310231627.7A CN115953397B (en) | 2023-03-13 | 2023-03-13 | Method and equipment for monitoring process preparation flow of conical bearing retainer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115953397A true CN115953397A (en) | 2023-04-11 |
| CN115953397B CN115953397B (en) | 2023-06-02 |
Family
ID=85896310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310231627.7A Active CN115953397B (en) | 2023-03-13 | 2023-03-13 | Method and equipment for monitoring process preparation flow of conical bearing retainer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115953397B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109633A (en) * | 2023-04-12 | 2023-05-12 | 山东金帝精密机械科技股份有限公司 | Window detection method and device for bearing retainer |
| CN116586925A (en) * | 2023-07-19 | 2023-08-15 | 山东金帝精密机械科技股份有限公司 | Large-scale bearing retainer production method, equipment and medium based on images |
| CN116665138A (en) * | 2023-08-01 | 2023-08-29 | 临朐弘泰汽车配件有限公司 | Visual detection method and system for stamping processing of automobile parts |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724126A (en) * | 2020-06-12 | 2020-09-29 | 北京科技大学顺德研究生院 | Accurate tracing method and system for process flow quality abnormity |
| CN112837302A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Mold state monitoring method and device, industrial personal computer, storage medium and system |
| CN113591790A (en) * | 2021-08-16 | 2021-11-02 | 上海铂端科技有限公司 | System, method and device for realizing production line assembly flow behavior monitoring based on computer vision, processor and storage medium thereof |
| WO2022065621A1 (en) * | 2020-09-28 | 2022-03-31 | (주)미래융합정보기술 | Vision inspection system using distance learning of product defect image |
| CN115359053A (en) * | 2022-10-19 | 2022-11-18 | 江苏万森绿建装配式建筑有限公司 | Intelligent detection method and system for defects of metal plate |
| CN115393363A (en) * | 2022-10-31 | 2022-11-25 | 山东金帝精密机械科技股份有限公司 | Production early warning method, equipment and medium for bearing retainer |
| CN115493843A (en) * | 2022-11-18 | 2022-12-20 | 聊城市义和轴承配件有限公司 | Quality monitoring method and equipment based on bearing retainer |
-
2023
- 2023-03-13 CN CN202310231627.7A patent/CN115953397B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724126A (en) * | 2020-06-12 | 2020-09-29 | 北京科技大学顺德研究生院 | Accurate tracing method and system for process flow quality abnormity |
| WO2022065621A1 (en) * | 2020-09-28 | 2022-03-31 | (주)미래융합정보기술 | Vision inspection system using distance learning of product defect image |
| CN112837302A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Mold state monitoring method and device, industrial personal computer, storage medium and system |
| CN113591790A (en) * | 2021-08-16 | 2021-11-02 | 上海铂端科技有限公司 | System, method and device for realizing production line assembly flow behavior monitoring based on computer vision, processor and storage medium thereof |
| CN115359053A (en) * | 2022-10-19 | 2022-11-18 | 江苏万森绿建装配式建筑有限公司 | Intelligent detection method and system for defects of metal plate |
| CN115393363A (en) * | 2022-10-31 | 2022-11-25 | 山东金帝精密机械科技股份有限公司 | Production early warning method, equipment and medium for bearing retainer |
| CN115493843A (en) * | 2022-11-18 | 2022-12-20 | 聊城市义和轴承配件有限公司 | Quality monitoring method and equipment based on bearing retainer |
Non-Patent Citations (2)
| Title |
|---|
| YA. M. KLEBANOV ET.AL: "Dynamic Loading in High-Speed Ball Bearings", 《RUSSIAN ENGINEERING RESEARCH》 * |
| 石炜;王涛;: "基于Canny算法的列车轴承内圈外表面缺陷检测", 数字技术与应用 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109633A (en) * | 2023-04-12 | 2023-05-12 | 山东金帝精密机械科技股份有限公司 | Window detection method and device for bearing retainer |
| CN116586925A (en) * | 2023-07-19 | 2023-08-15 | 山东金帝精密机械科技股份有限公司 | Large-scale bearing retainer production method, equipment and medium based on images |
| CN116586925B (en) * | 2023-07-19 | 2023-09-19 | 山东金帝精密机械科技股份有限公司 | Large-scale bearing retainer production method, equipment and medium based on images |
| CN116665138A (en) * | 2023-08-01 | 2023-08-29 | 临朐弘泰汽车配件有限公司 | Visual detection method and system for stamping processing of automobile parts |
| CN116665138B (en) * | 2023-08-01 | 2023-11-07 | 临朐弘泰汽车配件有限公司 | Visual detection method and system for stamping processing of automobile parts |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115953397B (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115953397B (en) | Method and equipment for monitoring process preparation flow of conical bearing retainer | |
| CN111951237B (en) | Visual appearance detection method | |
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN111292305A (en) | Improved YOLO-V3 metal processing surface defect detection method | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| US9230318B2 (en) | Analysis of the digital image of the external surface of a tyre and processing of false measurement points | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN115880248B (en) | Surface scratch defect identification method and visual detection equipment | |
| CN111402238A (en) | Defect identification system realized through machine vision | |
| CN114092403A (en) | Grinding wheel wear detection method and system based on machine vision | |
| CN113012098B (en) | Iron tower angle steel punching defect detection method based on BP neural network | |
| CN115984271A (en) | Metal burr identification method based on angular point detection | |
| CN113752086A (en) | Method and device for detecting state of numerical control machine tool cutter | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| CN116128873A (en) | Bearing retainer detection method, device and medium based on image recognition | |
| CN111539927A (en) | Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device | |
| CN115035092A (en) | Image-based bottle detection method, device, equipment and storage medium | |
| CN114820612A (en) | Roller surface defect detection method and system based on machine vision | |
| CN114463314A (en) | Wafer defect detection method and system based on color difference shadow model | |
| CN115239728A (en) | Fire-fighting equipment identification method | |
| CN116051460A (en) | Online detection method for abrasion of brazing diamond grinding head based on machine vision | |
| CN115493843A (en) | Quality monitoring method and equipment based on bearing retainer | |
| CN113139943B (en) | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium | |
| CN109584212B (en) | MATLAB-based SLM powder bed powder laying image scratch defect identification method | |
| CN115753791A (en) | Defect detection method, device and system based on machine vision |
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 |