CN116188440A - Production analysis optimization method, equipment and medium for bearing retainer - Google Patents
Production analysis optimization method, equipment and medium for bearing retainer Download PDFInfo
- Publication number
- CN116188440A CN116188440A CN202310207193.7A CN202310207193A CN116188440A CN 116188440 A CN116188440 A CN 116188440A CN 202310207193 A CN202310207193 A CN 202310207193A CN 116188440 A CN116188440 A CN 116188440A
- Authority
- CN
- China
- Prior art keywords
- production
- product
- parameters
- specified
- image
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 310
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000005457 optimization Methods 0.000 title claims abstract description 41
- 238000004458 analytical method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 100
- 230000008569 process Effects 0.000 claims abstract description 25
- 239000000047 product Substances 0.000 claims description 226
- 230000000875 corresponding effect Effects 0.000 claims description 62
- 230000008859 change Effects 0.000 claims description 23
- 238000013507 mapping Methods 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000010191 image analysis Methods 0.000 claims description 16
- 239000002994 raw material Substances 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 8
- 239000012467 final product Substances 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 238000004080 punching Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 239000002184 metal Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
- 238000010008 shearing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Factory Administration (AREA)
Abstract
The application discloses a production analysis optimization method, equipment and medium of a bearing retainer, which relate to the field of data processing systems or methods for supervision or prediction purposes and comprise the following steps: determining specified product parameters which do not meet preset requirements; calling product processing images corresponding to all production equipment; determining a plurality of first production devices corresponding to the specified product parameters, and acquiring first product processing images corresponding to the specified product parameters; extracting to obtain a plurality of original image features with production orders; obtaining standard image characteristics; and according to the variation value of the standard image characteristics under the production sequence, analyzing and optimizing the production parameters of each first production device. The image characteristics obtained by analyzing the product processing image are used for determining which production equipment needs to be adjusted, so that manual optimization is not needed, the accuracy in the production parameter optimization process is ensured, and the production working efficiency is improved.
Description
Technical Field
The application relates to the field of data processing systems or methods for supervision or prediction purposes, in particular to a production analysis optimization method, equipment and medium for a bearing retainer.
Background
Bearings are an important component in contemporary mechanical devices. Conventionally, a bearing holder production line is required to use various production equipment, such as a coil winder for winding materials, a leveling machine for leveling, a punching machine for punching to obtain intermediate members, and the like.
The existing production line often adopts an automatic control system to automatically control and produce various production equipment, and once produced products do not meet the specifications, production parameters are required to be manually optimized, so that time and labor are wasted, and the optimization effect is difficult to be satisfactory.
Disclosure of Invention
In order to solve the above problems, the present application proposes a production analysis optimization method of a bearing cage, including:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
In another aspect, the present application also proposes a production analysis optimizing apparatus of a bearing cage, comprising:
at least one processor; the method comprises the steps of,
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 operations such as:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
In another aspect, the present application also proposes a non-volatile computer storage medium storing computer-executable instructions configured to:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
The production analysis optimization method of the bearing retainer provided by the application can bring about the following
The beneficial effects are that:
if the finally produced bearing retainer does not meet the preset requirement, corresponding product processing images can be obtained in an automatic mode, and whether production equipment needs to be adjusted is determined by analyzing the image characteristics obtained by analyzing the product processing images, so that production parameters of the production equipment are optimized, manual optimization is not needed any more, accuracy in the process of optimizing the production parameters is guaranteed, and production working efficiency is improved.
In the traditional production analysis optimization method, the optimization is often performed based on manual experience, so that the method has no universality and poor optimization precision. In the production analysis optimization provided in the embodiment of the specification, various product parameters of the bearing retainer are represented by analyzing image characteristics, and the product parameters are associated with production equipment, so that the production parameters of the most-adapted production equipment can be optimized, and an automatic and scientific analysis optimization process is realized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of a method for optimizing production analysis of a bearing cage according to an embodiment of the present application;
fig. 2 is a schematic view of a production analysis optimizing apparatus of a bearing cage in an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present application provides a production analysis optimization method of a bearing cage, including:
s101: when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer.
The failure to meet the preset requirement may include that the yield of the produced bearing retainer does not meet the preset requirement, or that the product parameters (such as the product size, etc.) of the produced bearing retainer do not meet the preset requirement, or that the product parameters and the requirements of a certain bearing retainer are quite different.
The production facility may include: travelling crane, coil stock machine, evener, punching machine, subtracting material machine, bottom cutting machine, piercing press, conveyer etc.. The travelling crane is used for hanging the metal plate to a corresponding processing position, and the coiling machine and the leveling machine are respectively used for coiling and leveling the metal plate. The punching machine is used for carrying out punching separation on the metal plate to obtain bowl-shaped parts, the bottom cutting machine is used for cutting the bottom of the bowl-shaped parts, the punching machine is used for punching, the material reducing machine is used for shearing the residual materials after the punching separation, and the conveying device is used for conveying the metal plate, the residual materials, the bowl-shaped parts, finished products and the like.
The working state of the bearing retainer can be determined by monitoring the operation parameters of the production equipment, for example, the operation time length, the operation frequency, the fault alarm information, the equipment aging degree and the like of the production equipment are monitored, if the working state is not abnormal, the condition that the finally obtained bearing retainer does not meet the preset requirement is indicated as the result of the setting of the production parameters. The judging rule is most often suitable for the situation that the product parameters (such as the product size and the like) do not meet the preset requirements.
When a plurality of specified bearing retainers which do not meet the preset requirements are provided, the comprehensive analysis can be performed by comprehensively considering all the specified product parameters collected, or the independent analysis can be performed by respectively collecting the specified product parameters for each specified bearing retainer.
S102: and taking a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece.
The product pieces may refer to metal plates of raw materials, machining remnants of metal plates, intermediate pieces of machined semi-finished products, bearing holders of finished products, etc., collectively referred to herein as product pieces.
In the bearing retainer production line, an image acquisition device (possibly one or more based on actual requirements) is arranged around each production device, and the image acquisition device can monitor the production device, the product pieces before entering the production device and the product pieces after being processed by the production device and acquire images.
S103: and determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively.
The mapping relationship is preset, and can show which product parameters can be influenced by each production device. For example, the leveling machine needs to flatten the raw material in the working process, and the thickness of the metal plate can be influenced at the moment, and of course, in the subsequent working process, the punching machine and other devices can also influence the thickness of the product, but the two devices are relatively independent working behaviors, and the influence of the leveling machine on the thickness of the product is larger, so that in the mapping relationship, the following contents can be included: there is a mapping relationship between the leveler, the punch and the product thickness, and the level of influence of the leveler is higher than the punch. When the specified product parameter is the product thickness, the selected first production equipment at least comprises a leveling machine and a punching machine.
Typically, each product parameter corresponds to a plurality of production devices, and the more production devices that follow, the more product parameters that are associated, so typically each product parameter is associated with a plurality of production devices in a mapping relationship.
Specifically, for a complete production process of a single bearing cage, various initial product parameters of the bearing cage are determined, and a set of product parameters is generated. For example, when the product parameters include the outer edge dimension of the product, the inner edge dimension of the product, the thickness of the product, the angle of the side wall of the product, the number of perforations, and the perforation dimensions, the product parameter set a= {0, H, 0}, where 0 indicates that the product has not been separated alone, the corresponding value cannot be measured, and H is the thickness of the raw material plate.
And acquiring a product processing image processed by each production device, updating initial product parameters according to the extracted image characteristics in each product processing image, and obtaining an updated product parameter set. For example, after the raw material plate is leveled by the leveling machine, the thickness is reduced from H to H, at this time, based on a product processing image corresponding to the leveling machine, image analysis is performed to obtain a corresponding H value, and the product parameter set A is updated as follows: a= {0, h, 0}. After the finished product is finally processed by all production equipment, a final product parameter set A can be obtained.
For each production device, the product parameter sets A corresponding to different bearing retainers are averaged to obtain the final product parameter set corresponding to the production device, and the mapping relation between the production device and each product parameter is determined according to the final product parameter set corresponding to the production device compared with the increment of the final product parameter set corresponding to the last production device in the production sequence. The corresponding mapping relationship is thus obtained for subsequent determination of the first production facility by specifying the product parameters.
Further, at this time, the influence degree between each production device and the specified product parameter is determined according to the mapping relation, and a plurality of production devices with the highest influence degree are selected as the first production devices. The influence degree is also preset, and can be obtained based on the product parameter set A, wherein the more the increment of a certain product parameter in the product parameter set A is, the higher the influence degree is.
If the number of the selected production devices exceeds the preset threshold, screening is performed in the production devices, and if the difference between the association degrees of the plurality of production devices is lower than the preset threshold in the screening process, the influence degrees of the two production devices on the designated production parameters are approximately equal, while the more the product parameters associated with the production devices with the later production order are, the more the production devices with the later production order are screened, so that the production devices with the smaller influence are screened.
S104: and sequentially carrying out image analysis on the plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters.
In the image analysis process, the product processing images obtained for different shooting parameters (such as shooting angles, shooting positions and the like) are different, however, for the same production equipment, the corresponding product processing images are relatively fixed, so that when the image analysis is carried out for different production equipment according to different specified product parameters, the adopted mode is relatively fixed, the image analysis can be carried out through SIFT algorithm, SURF algorithm, MESR algorithm, convolutional neural network model and the like, and corresponding image characteristics are obtained. The image features are also based on the production order of the production equipment, with corresponding production orders.
S105: and carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics.
The original image features can be able to adj ust the product parameters but may not be conducive to accurate analysis because of the lack of uniform criteria. For example, in a plurality of different production facilities, image acquisition devices are provided from the side and oblique side, respectively, which, when corresponding to the size-dependent raw image features, respectively analyze the corresponding pixel values as raw image features. However, at this time, since the collecting directions of the two are different, if the pixel values are directly compared, the pixel values have a certain error, and therefore, the pixel values are subjected to standardization processing to obtain standard image characteristics. For example, the original image features are scaled to obtain the corresponding standard image features by taking a certain direction as a reference value.
S106: and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
If the finally produced bearing retainer does not meet the preset requirement, corresponding product processing images can be obtained in an automatic mode, and whether production equipment needs to be adjusted is determined by analyzing the image characteristics obtained by analyzing the product processing images, so that production parameters of the production equipment are optimized, manual optimization is not needed any more, accuracy in the process of optimizing the production parameters is guaranteed, and production working efficiency is improved.
In the traditional production analysis optimization method, the optimization is often performed based on manual experience, so that the method has no universality and poor optimization precision. In the production analysis optimization provided in the embodiment of the specification, various product parameters of the bearing retainer are represented by analyzing image characteristics, and the product parameters are associated with production equipment, so that the production parameters of the most-adapted production equipment can be optimized, and an automatic and scientific analysis optimization process is realized.
Further, since the first production apparatus is not necessarily an adjacent production apparatus, other apparatuses other than the first production apparatus may have some influence on the specified processing parameters, however, since other apparatuses are not analyzed, the influence thereof may be classified into the first production apparatus.
Based on the above, according to the production sequence, determining a second production device which is adjacent to and not belonging to the first production device, and correcting the standard image characteristics corresponding to the first production device according to the production parameters of the second production device. For example, the production parameters of the second production apparatus have a positive influence on the standard image characteristics to some extent, and at this time, negative adjustment is performed according to the influence, thereby completing correction. Of course, if the production parameters of the first production apparatus, which are adjacent to the first production apparatus, or the adjacent second production apparatus, have no influence, no correction is required. And determining a change value of the corrected standard image features in the production sequence, and determining original image features which do not meet the preset requirements according to the change value. When determining according to the change values, firstly, determining a plurality of specified change values with the largest change values in the change values. The larger the variation value, the more pronounced the variation in the image features. For example, if the specified change value is higher than a preset threshold (indicating that the change amplitude of the product parameter corresponding to the image feature is too large at this time and exceeds an abnormal critical value, so that the product is not in compliance with the requirement), or if the value after summing all the specified change values and all the previous change values is higher than the preset threshold (indicating that the product is not in compliance with the requirement after the previous times of accumulation of the change although the change amplitude does not reach the abnormal critical value at this time), the standard image feature corresponding to the specified change value is determined to be not in compliance with the preset requirement.
In this case, in the correction process, it is necessary to determine, according to the production process corresponding to each production device, a process influence level of the second production device on the first production device, where the process influence level may affect the production state of the first production device when the production parameters of the second production device change, for example, the second production device may press, after the production parameters of the second production device change, the middle part obtained by pressing and separating naturally changes, at this time, the production state of the subsequent first production device (such as a punching machine) naturally affects, and at this time, although the specified product parameters corresponding to the first production device do not meet the requirements, it is likely to be due to the influence of the second production device. Therefore, when the standard image feature is obtained and determined, the influence of the second production equipment needs to be eliminated, so that the correction coefficient is obtained and corrected according to the process influence level. Wherein, the higher the process influence level is, the larger the correction coefficient is.
In one embodiment, during the production process of the bearing cage production line, accidents may occur with the use of the apparatus, for example, an image acquisition device for capturing a first product processing image may be abnormal during the use, so that the captured first product processing image may be abnormal, which may affect the subsequent image analysis.
The usual solution can be by manually inspecting the image, but this approach is time consuming, labor intensive and increases human resources. Alternatively, by monitoring the parameters of the image acquisition apparatus, some anomalies are difficult to manifest in their operational parameters, such as focus failure due to external forces.
Based on this, after the first product processed image is acquired, a part of the first product processed image is randomly selected, and then abnormality analysis is performed on the part of the image. For each first product processing image in the part of images, shooting parameters which can best embody specified product parameters are determined, wherein the shooting parameters comprise view projection directions, shooting distances, shooting focal lengths and the like, are preset, and can be obtained by pulling the mapping relation. For example, for an image of a bowl, the shooting parameters that can be most reflected should include two images, where the projection direction of one image is a top view, the shooting distance and the shooting focal length can be set based on the actual situation of the image acquisition device, so as to obtain the shape and the diameter of the bowl, the projection direction of the other image is a side view, and the shooting distance and the shooting focal length can be set based on the actual situation of the image acquisition device, so as to obtain the depth of the bowl. Of course, the two images may be provided as two portions of one image, thereby facilitating subsequent analysis.
According to the production order, among the previous first product processing images, other first product processing images whose shooting parameters are closest to those of the first product processing image are determined (of course, a determination condition may be added at this time, for example, the other first product processing images correspond to images in which the first product processing image is an adjacent production apparatus). The projection direction has the largest duty ratio, and only when the projection directions are identical, whether the shooting distance and the shooting focal length are close or not is considered.
If the proximity exceeds the preset degree (usually, the shooting parameters are completely consistent, the subsequent analysis is performed), it is indicated that the shooting parameters of the two are basically consistent, the shooting parameters are consistent for reflecting the specified product parameters, the specified product parameters corresponding to the two are similar, or at least belong to the same projection direction, that is, the product parameters corresponding to the processing technology are similar when the production equipment corresponding to the two processes the bearing retainer to process the bearing retainer, that is, the influence of the processing technology of the two processes on the product parameters except the specified product parameters is smaller, and the change of other product parameters is smaller.
At this time, image analysis is performed on the two (the first product processed image and the other first product processed image) according to other product parameters, so as to obtain corresponding first image features and second image features respectively. If the difference between the first image feature and the second image feature is higher than the preset threshold, the difference between the first image feature and the second image feature is larger, and the difference is inconsistent with the actual situation. At this time, the following may exist: the image acquisition devices corresponding to the two are abnormal, the production equipment corresponding to the two is abnormal, and then the image corresponding to the two is abnormal in either case, so that the investigation can be performed manually.
In one embodiment, a historical optimization record for production parameters of a specified first production facility is collected during optimization of the production parameters. Of course, the collection may be performed separately for different designated first production facilities.
Generating a multidimensional vector according to the historical optimization record, wherein a first dimension and a second dimension in the multidimensional vector are discrete variables, the first dimension represents a production parameter before optimization, the second dimension represents an optimized variable of the time, and the third dimension is a natural language variable and represents the optimized quality of the time.
In particular, the optimized quality may include multiple levels, such as excellent, good, general, poor, etc. The optimization quality is positively correlated with the variation amplitude of the optimized specified product parameters to the preset requirement, and the larger the variation amplitude is, the more excellent the optimization variable adjustment is. And the variation amplitude of the optimized other product parameters is inversely related, and the larger the variation amplitude is, the larger the influence on the other product parameters is. Therefore, the optimal variable which is the most balanced is selected between the two, and the optimization of the production parameters is realized after the optimal variables of all the product parameters are integrated.
Deep training is performed according to the multidimensional vector to obtain a deep learning model, for example, a deep learning method such as a neural network can be used for optimizing production parameters of the designated first production equipment.
As shown in fig. 2, an embodiment of the present application further provides a production analysis optimizing apparatus for a bearing cage, including:
at least one processor; the method comprises the steps of,
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 operations such as:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
The embodiments also provide a non-volatile computer storage medium storing computer executable instructions configured to:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
The devices and media provided in the embodiments of the present application are in one-to-one correspondence with the methods, so that the devices and media also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media are not described in detail herein.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A method of production analysis optimization of a bearing cage, comprising:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
2. The method according to claim 1, wherein the analysis of the production parameters of each first production apparatus according to the variation value of the standard image features in the production order, specifically comprises:
determining a second production device which is positioned in front of the first production device and is not belonging to the first production device according to the production sequence;
correcting standard image features corresponding to the first production equipment according to the production parameters of the second production equipment;
determining a change value of the corrected standard image features in the production sequence;
and determining standard image characteristics which do not meet the preset requirement, original image characteristics corresponding to the standard image characteristics and designated first production equipment corresponding to the original image characteristics according to the change values.
3. The production analysis optimization method of the bearing retainer according to claim 2, wherein the correction of the standard image features corresponding to the first production equipment according to the production parameters of the second production equipment specifically comprises:
determining the process influence level of the second production equipment on the first production equipment according to the corresponding production process of each production equipment;
and obtaining a correction coefficient according to the production parameters of the second production equipment and the process influence level, and correcting the standard image characteristics corresponding to the first production equipment according to the correction coefficient.
4. The production analysis optimization method of the bearing retainer according to claim 2, wherein determining standard image features that do not meet the preset requirement according to the variation value specifically includes:
among the variation values, determining a plurality of specified variation values with the maximum variation values;
and if the specified change value is higher than a preset threshold value, or the value obtained by summing the specified change value and all the previous change values is higher than the preset threshold value, determining that the standard image characteristic corresponding to the specified change value does not meet the preset requirement.
5. The method of optimizing production analysis of a bearing cage according to claim 1, wherein before determining a plurality of first production apparatuses having the greatest influence on the specified product parameters according to a preset mapping relationship, the method further comprises:
for a single bearing retainer, determining various initial product parameters of the bearing retainer, and generating a product parameter set;
acquiring a product processing image processed by each production device, and updating the initial product parameters according to the extracted image characteristics in each product processing image to obtain an updated product parameter set;
and aiming at corresponding product parameter sets of each production device in different bearing retainers, solving an average value to obtain a final product parameter set corresponding to the production device, determining the influence degree between the production device and each product parameter according to the final product parameter set corresponding to the production device, comparing the increment of the final product parameter set corresponding to the last production device in the production sequence with the increment of the final product parameter set corresponding to the last production device, and establishing a mapping relation between the production device and the product parameter according to the influence degree.
6. The production analysis optimizing method of a bearing retainer according to claim 5, wherein determining a plurality of first production apparatuses having the greatest influence on the specified product parameters according to a preset mapping relation, specifically comprises:
determining the influence degree of each production device on the specified product parameters according to the mapping relation, and selecting a plurality of production devices with the highest influence degree as first production devices;
and screening out the production equipment with a later production sequence if the correlation degree difference of the plurality of production equipment is lower than the preset threshold value in the screening-out process.
7. The production analysis optimizing method of a bearing retainer according to claim 1, wherein after acquiring the first product processing images respectively corresponding to the plurality of first production apparatuses, the method further comprises:
randomly selecting part of the first product processing images, and carrying out anomaly analysis on the selected part of the first product processing images;
wherein the anomaly analysis process comprises:
determining shooting parameters which can best embody the specified product parameters aiming at each first product processing image in the selected partial first product processing images, wherein the shooting parameters comprise at least one of view projection direction, shooting distance and shooting focal length;
according to the production sequence, in the first product processing images before the first product processing images, determining other first product processing images with the shooting parameters closest to the shooting parameters of the first product processing images and the approaching degree exceeding the preset degree;
performing image analysis on the first product processing image and the other first product processing images through other product parameters except the specified product parameters to obtain a first image feature and a second image feature which are used for adjectively accommodating the other product parameters;
and if the difference value between the first image feature and the second image feature is higher than a preset threshold value, the first product processing image and/or the other product processing images are considered to be abnormal.
8. The method for optimizing production analysis of a bearing cage according to claim 1, wherein optimizing production parameters of a specified first production facility comprises:
collecting a history optimization record of production parameters for the specified first production equipment;
generating a multidimensional vector according to the historical optimization record, wherein a first dimension and a second dimension in the multidimensional vector are discrete variables, the first dimension represents production parameters before optimization, the second dimension represents an optimization variable in the historical optimization record, and a third dimension is a natural language variable and represents optimization quality in the historical optimization record; wherein, the optimized quality is positively correlated with the variation amplitude of the optimized specified product parameter to the preset requirement, and is negatively correlated with the variation amplitude of other optimized product parameters;
and performing deep training according to the multidimensional vector to obtain a deep learning model for optimizing the production parameters of the specified first production equipment, wherein the input of the deep learning model is the production parameters before optimization, and the output of the deep learning model is an optimization variable.
9. A production analysis optimizing apparatus of a bearing cage, comprising:
at least one processor; the method comprises the steps of,
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 operations such as:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
10. A non-transitory computer storage medium storing computer-executable instructions, the computer-executable instructions configured to:
when the working state of each production device contained in the bearing retainer production line is not abnormal, if the produced specified bearing retainer does not meet the preset requirement, determining specified product parameters which do not meet the preset requirement in the specified bearing retainer;
the method comprises the steps of calling a product processing image corresponding to each production device in the production process of the appointed bearing retainer, wherein the product processing image comprises an image of each production device after processing a product piece, and the product piece comprises a raw material, a middle piece and a finished product piece;
determining a plurality of first production devices with the largest influence on the specified product parameters according to a preset mapping relation, and acquiring first product processing images corresponding to the plurality of first production devices respectively;
sequentially carrying out image analysis on a plurality of first product processing images according to the specified product parameters, and extracting to obtain a plurality of original image features with production orders, wherein the original image features are used for adjectively specifying the specified product parameters;
carrying out standardization processing on the original image characteristics according to the specified product parameters to obtain standard image characteristics;
and analyzing the production parameters of each first production device according to the variation value of the standard image characteristics in the production sequence so as to optimize the production parameters of the designated first production device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310207193.7A CN116188440B (en) | 2023-02-28 | 2023-02-28 | Production analysis optimization method, equipment and medium for bearing retainer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310207193.7A CN116188440B (en) | 2023-02-28 | 2023-02-28 | Production analysis optimization method, equipment and medium for bearing retainer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116188440A true CN116188440A (en) | 2023-05-30 |
| CN116188440B CN116188440B (en) | 2023-08-29 |
Family
ID=86438239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310207193.7A Active CN116188440B (en) | 2023-02-28 | 2023-02-28 | Production analysis optimization method, equipment and medium for bearing retainer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116188440B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN117647962A (en) * | 2024-01-29 | 2024-03-05 | 山东国泰民安玻璃科技有限公司 | Production control method, equipment and medium for injection bottle |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019174544A1 (en) * | 2018-03-14 | 2019-09-19 | Oppo广东移动通信有限公司 | Image synthesis method and apparatus, and computer storage medium and electronic device |
| CN114004974A (en) * | 2021-11-03 | 2022-02-01 | 中国银行股份有限公司 | Method and device for optimizing images shot in low-light environment |
| CN114332445A (en) * | 2021-12-30 | 2022-04-12 | 神思电子技术股份有限公司 | Screen-folding information acquisition method, device and medium |
| CN114615495A (en) * | 2020-12-09 | 2022-06-10 | Oppo广东移动通信有限公司 | Model quantization method, device, terminal and storage medium |
| WO2022121531A1 (en) * | 2020-12-09 | 2022-06-16 | 歌尔股份有限公司 | Product defect detection method and apparatus |
| CN114998695A (en) * | 2022-07-18 | 2022-09-02 | 深圳市前海泽金产融科技有限公司 | Method and system for improving image recognition speed |
| CN115187949A (en) * | 2022-09-07 | 2022-10-14 | 山东金宇信息科技集团有限公司 | Method, device and medium for detecting road surface state of tunnel entrance |
| 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 |
| CN115526839A (en) * | 2022-09-06 | 2022-12-27 | 浪潮工业互联网股份有限公司 | Flower drying control method, device and medium based on neural network |
| WO2023274097A1 (en) * | 2021-06-28 | 2023-01-05 | 歌尔股份有限公司 | Qr code image processing method and apparatus |
-
2023
- 2023-02-28 CN CN202310207193.7A patent/CN116188440B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019174544A1 (en) * | 2018-03-14 | 2019-09-19 | Oppo广东移动通信有限公司 | Image synthesis method and apparatus, and computer storage medium and electronic device |
| CN114615495A (en) * | 2020-12-09 | 2022-06-10 | Oppo广东移动通信有限公司 | Model quantization method, device, terminal and storage medium |
| WO2022121531A1 (en) * | 2020-12-09 | 2022-06-16 | 歌尔股份有限公司 | Product defect detection method and apparatus |
| WO2023274097A1 (en) * | 2021-06-28 | 2023-01-05 | 歌尔股份有限公司 | Qr code image processing method and apparatus |
| CN114004974A (en) * | 2021-11-03 | 2022-02-01 | 中国银行股份有限公司 | Method and device for optimizing images shot in low-light environment |
| CN114332445A (en) * | 2021-12-30 | 2022-04-12 | 神思电子技术股份有限公司 | Screen-folding information acquisition method, device and medium |
| CN114998695A (en) * | 2022-07-18 | 2022-09-02 | 深圳市前海泽金产融科技有限公司 | Method and system for improving image recognition speed |
| CN115526839A (en) * | 2022-09-06 | 2022-12-27 | 浪潮工业互联网股份有限公司 | Flower drying control method, device and medium based on neural network |
| CN115187949A (en) * | 2022-09-07 | 2022-10-14 | 山东金宇信息科技集团有限公司 | Method, device and medium for detecting road surface state of tunnel entrance |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 蔡亚军;陈书宏;王宇;: "工艺产品加工质量监测优化", 科学技术与工程, no. 18 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN117647962A (en) * | 2024-01-29 | 2024-03-05 | 山东国泰民安玻璃科技有限公司 | Production control method, equipment and medium for injection bottle |
| CN117647962B (en) * | 2024-01-29 | 2024-04-12 | 山东国泰民安玻璃科技有限公司 | Production control method, equipment and medium for injection bottle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116188440B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116188440B (en) | Production analysis optimization method, equipment and medium for bearing retainer | |
| CN115393363B (en) | Production early warning method, equipment and medium for bearing retainer | |
| CN115993807B (en) | Production monitoring optimization control method and system for silicon carbide | |
| CN116009463B (en) | Bearing retainer production monitoring method, equipment and medium based on industrial Internet | |
| CN115774652B (en) | Cluster control equipment health monitoring method, equipment and medium based on clustering algorithm | |
| CN114493204A (en) | Industrial equipment monitoring method and equipment based on industrial Internet | |
| CN110991495A (en) | Method, system, medium, and apparatus for predicting product quality in manufacturing process | |
| CN115330989A (en) | Control method for laser beam cutting | |
| KR102464891B1 (en) | Apparatus and method for controlling metal part intelligent processing | |
| JP2020042669A (en) | Inspection apparatus and machine learning method | |
| CN116519707A (en) | Lithium battery defect detection method and device based on machine vision and electronic equipment | |
| CN113487607A (en) | Defect detection method and device based on multi-view-field image | |
| KR20220084303A (en) | manufacturing method | |
| JP2020042668A (en) | Inspection apparatus and machine learning method | |
| CN117274245A (en) | AOI optical detection method and system based on image processing technology | |
| CN116341839B (en) | Order pushing method, equipment and medium for household service personnel | |
| CN109407630B (en) | Parameter calculation method, device, terminal and readable storage medium | |
| CN116405775A (en) | Automatic focusing method and device, electronic equipment and shooting system | |
| CN116586925B (en) | Large-scale bearing retainer production method, equipment and medium based on images | |
| CN115147236A (en) | Processing method, processing device and electronic equipment | |
| CN114399209A (en) | Drilling operation risk prediction method, system and equipment based on edge cloud integration | |
| CN117350984B (en) | Method and device for detecting shoulder-opening and fork-opening of monocrystalline silicon | |
| CN118083604B (en) | Automatic unstacking method and system for formed parts based on 3D vision | |
| CN118095971B (en) | AD calcium milk beverage processing technology assessment method, system and medium | |
| CN114971599B (en) | Food manufacturing processing technological parameter setting method, device, equipment and medium |
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 |