CN114219799A - Intelligent manufacturing defective product analysis method and system - Google Patents
Intelligent manufacturing defective product analysis method and system Download PDFInfo
- Publication number
- CN114219799A CN114219799A CN202111580128.6A CN202111580128A CN114219799A CN 114219799 A CN114219799 A CN 114219799A CN 202111580128 A CN202111580128 A CN 202111580128A CN 114219799 A CN114219799 A CN 114219799A
- Authority
- CN
- China
- Prior art keywords
- product
- appearance image
- detected
- image information
- information
- 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.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 158
- 230000002950 deficient Effects 0.000 title claims abstract description 89
- 238000004458 analytical method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 110
- 238000007689 inspection Methods 0.000 claims abstract description 91
- 230000008569 process Effects 0.000 claims abstract description 59
- 238000007619 statistical method Methods 0.000 claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 22
- 230000007547 defect Effects 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000007639 printing Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 28
- 238000012216 screening Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011179 visual inspection 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The application relates to a method and a system for analyzing substandard products for intelligent manufacturing, wherein the method comprises the following steps: establishing a defective product inspection and analysis platform, and inputting product information of a product to be detected; acquiring appearance image information of a product to be detected, and judging the validity of the appearance image information; comparing and analyzing the appearance image information of the product to be detected, which is judged by validity, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not; if the product to be detected is unqualified, marking the difference points on the appearance image information of the product to be detected, and determining a difference point generation process; continuously carrying out statistical analysis on the different point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal. This application has the effect of high-efficient sieve preface substandard product and intelligent analysis substandard product reason, helps improving product production quality.
Description
Technical Field
The application relates to the field of intelligent manufacturing defective product analysis, in particular to a defective product analysis method and system for intelligent manufacturing.
Background
Intelligent manufacturing refers to the generic name of advanced manufacturing processes, systems and models with the functions of information self-perception, self-decision, self-execution, etc. The method is specifically embodied in the deep fusion of each link of the manufacturing process and a new generation of information technology, such as the Internet of things, big data, cloud computing, artificial intelligence and the like. Smart manufacturing generally has four major features: the intelligent factory is used as a carrier, the intellectualization of a key manufacturing link is used as a core, an end-to-end data flow is used as a base, and the internet communication is used as a support. However, in industrial production, no matter how fine the production equipment is and how advanced the production process is, the appearance of unqualified products cannot be avoided.
At present, different detection schemes are provided for different products in various fields of various industries, and the detection schemes are often not universal due to different shapes and the like of the products, so that a manufacturer needs to be provided with a plurality of detection devices, and the detection cost is high. In addition, many industries use manual visual inspection to detect products, and the detection method has high labor cost and high omission factor, and easily causes unqualified products to be mixed into qualified products, thereby reducing the product quality. Even if the defective products are detected successfully, the intelligent and effective analysis on the defective products is still lacked, and the reason for generating the defective products cannot be found by tracing the source in time. Particularly, in some continuous processing production type processing modes, a plurality of production devices often process raw materials according to a specific sequence, such as stamping production, printing production, engraving production and the like, and defective products are often generated due to the failure of one production device in one processing link.
Aiming at the related technologies, the inventor thinks that even if the inferior-quality products are successfully detected in the existing product inspection process, the intelligent and effective analysis on the inferior-quality products is still lacked, and the reason for generating the inferior-quality products cannot be found by tracing the source in time.
Disclosure of Invention
In order to solve the problems that even though the defective products are successfully detected in the existing product inspection process, the intelligent and effective analysis on the defective products is still lacked, and the reason for generating the defective products cannot be found by tracing the source in time, the application provides a defective product analysis method and system for intelligent manufacturing.
In a first aspect, the present application provides an intelligent manufacturing defective product analysis method, which adopts the following technical scheme:
a method for analyzing substandard products for intelligent manufacturing comprises the following steps:
establishing a defective product inspection analysis platform, and inputting product information of a product to be detected, wherein the product information comprises product name information, product type information, product standard appearance image information, product process information and product inspection point information;
acquiring appearance image information of a product to be detected, carrying out primary identification on the acquired appearance image information of the product to be detected, and judging the validity of the appearance image information;
comparing and analyzing the appearance image information of the product to be detected, which is judged by validity, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not;
if the product to be detected is unqualified, marking the difference points on the appearance image information of the product to be detected, and determining a difference point generating process according to the difference points on the appearance image information of the unqualified product;
continuously carrying out statistical analysis on the different point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal.
By adopting the technical scheme, a defective product inspection and analysis platform is established, product information of a product to be detected is input, appearance image information of the product to be detected is obtained, the appearance image information of the product to be detected is preliminarily identified, the effectiveness of the appearance image information of the product to be detected is ensured, the effective appearance image information of the product to be detected is contrasted and analyzed, and the effect of efficiently screening defective products is realized; and furthermore, the generation reasons of the defective products are subjected to statistical analysis, the reasons and the processes of the defective products are intelligently judged, alarm information is generated to inform a manager, the effects of efficiently screening the defective products and intelligently analyzing the reasons of the defective products are achieved, and the production quality of products is improved.
Preferably, the product standard appearance image information includes a product overall standard appearance image and standard appearance images of each product inspection point, and the product standard appearance image information specifically includes the following acquisition steps:
acquiring image information of standard and qualified products for multiple times through preset image acquisition equipment, and generating an integral standard appearance image of the product by using the image information of the standard and qualified products acquired for multiple times through a statistical average method;
acquiring high-definition amplified image information of each inspection point on a standard qualified product for multiple times through preset image acquisition equipment, and sequentially generating a standard appearance image of each product inspection point on multiple high-definition amplified images of each inspection point by adopting a statistical average method;
and splicing the standard appearance images of the product inspection points to generate a high-definition amplified integral appearance image of the product, zooming the high-definition amplified integral appearance image of the product to the same proportion of the integral standard appearance image of the product, performing superposition comparison to obtain a similarity value, judging that the image acquisition is successful if the similarity value is greater than a preset similarity threshold value, and packaging the integral standard appearance image of the product and the standard appearance images of the product inspection points to generate standard appearance image information of the product.
By adopting the technical scheme, the whole standard appearance image of the product and the standard appearance image of each product inspection point are obtained by collecting the standard qualified samples for multiple times, so that the accuracy of the standard appearance image information of the product is ensured, and the defective products can be conveniently, efficiently and accurately screened out. And after the product overall standard appearance image and the standard appearance images of the product inspection points are generated, the correctness of the product overall standard appearance image is verified by splicing and zooming the standard appearance images of the product inspection points, and the accuracy of the product standard appearance image information is further effectively improved.
Preferably, the obtaining of the appearance image information of the product to be detected, the preliminary identification of the obtained appearance image information of the product to be detected, and the determining of the validity of the appearance image information specifically include the following steps:
the method comprises the steps that appearance image information of a product to be detected is acquired through preset image acquisition equipment, wherein the appearance image information of the product to be detected comprises an integral appearance image of the product to be detected and appearance images of all inspection points of the product to be detected;
preliminarily identifying the overall appearance image of the product to be detected, carrying out coordinate positioning on the overall appearance image of the product to be detected, judging whether the acquired acquisition angle of the overall appearance image of the product to be detected is consistent with a preset acquisition angle or not, and if so, enabling the overall appearance image of the product to be detected to be effective;
numbering the appearance images of all inspection points of the product to be detected according to inspection point numbers in the product inspection point information, judging whether the appearance images are missing or not, if not, performing coordinate positioning on the appearance images of all inspection points of the product to be detected, judging whether the collected collection angle of the appearance images of all inspection points of the product to be detected is consistent with a preset collection angle or not, and if so, enabling the appearance images of all inspection points of the product to be detected to be effective.
By adopting the technical scheme, the appearance image information of the product to be detected is preliminarily identified, the effectiveness of the appearance image information of the product to be detected is ensured, the phenomenon that the acquired invalid image information is analyzed and compared to obtain an incorrect comparison result is avoided, the comparison analysis operation resources are saved, and the effect of efficiently and accurately screening out the defective products is achieved.
Preferably, the step of comparing and analyzing the appearance image information of the product to be tested, which is judged by validity, with the product standard appearance image information to judge whether the appearance image information of the product to be tested is qualified specifically includes the following steps:
comparing and analyzing the overall appearance image information of the product to be detected with the overall standard appearance image information of the product to obtain a comparison similarity value;
comparing and analyzing the appearance image of each inspection point of the product to be tested with the standard appearance image of each inspection point of the product one by one through the serial number to obtain image defect information;
and if the contrast similarity value is larger than the preset threshold value and the image defect information does not exist, judging that the appearance image information of the product to be detected is qualified, otherwise, judging that the appearance image information of the product to be detected is unqualified.
By adopting the technical scheme, the whole appearance image information of the product to be detected and the appearance image of each inspection point are subjected to contrastive analysis in sequence, the whole contrast similarity and the image defect information of the product are obtained, whether the product to be detected is qualified or not is judged according to the whole appearance image information and the appearance image of each inspection point, the inspection accuracy of the product to be detected is improved, and the effect of intelligently inspecting the product to be detected is realized.
Preferably, the image defect information is set by a manager according to product information, and the image defect information includes, but is not limited to, a point defect, a different color point, a color difference, orange peel, air bubbles, screen offset, poor printing, scratches, burrs, and burrs.
By adopting the technical scheme, the management personnel can set the image defect information of the demand screening according to the actual production demand of the product, the defective products can be conveniently and intelligently and accurately screened, the defective product screening efficiency is improved, the analysis on the causes of the defective products is facilitated, the management personnel can conveniently and timely find the equipment or the process which causes the defective products to be produced, and the improvement on the process and the product production quality of the management personnel are facilitated.
Preferably, the step of labeling the difference points on the appearance image information of the product to be detected if the product to be detected is unqualified, and the step of determining the difference point generating procedure according to the difference points on the appearance image information of the unqualified product specifically comprises the following steps:
if the product to be detected is unqualified, marking difference points on the appearance image information of the product, wherein the difference points comprise image defect information and image comparison difference points;
determining product positions of the difference points according to position information of the difference points on the appearance image information of the unqualified product;
and determining a processing generation procedure of the product part, namely a difference point generation procedure according to the product process flow information, wherein the difference point generation procedure comprises a processing procedure for directly generating the part and an upper layer processing procedure necessary for generating the part.
By adopting the technical scheme, the production process causing each defective product is determined by carrying out statistical analysis on the difference points on the defective products, so that root tracing and source tracing are conveniently carried out on the causes of the defective products, managers can find and correct production defects in time, and the effect of effectively improving the production efficiency and the production quality is achieved.
Preferably, the continuously performing statistical analysis on the difference point generating processes of the unqualified products of the same production line, confirming the operation status of the production equipment of each production process, and sending alarm information to the manager when the operation status of the production equipment of a certain production process is abnormal specifically includes the following steps:
continuously carrying out statistical analysis on the difference point generating processes of unqualified products of the same production line in the same production period according to a preset production period, and calculating the difference point generating occupation ratio of each process according to a preset difference process calculation formula;
if the occupation ratio of the difference points of a certain process is larger than a preset difference occupation ratio threshold value, judging that the operation state of the production equipment of the process is abnormal, and sending alarm information to a manager
Counting the number of defective products and the number of produced products in the same production period according to a preset production period, and calculating the yield in real time;
and if the yield is less than a preset yield threshold value, generating proportion integration generation alarm information of the difference points of each production process, and sending the proportion integration generation alarm information to a manager.
By adopting the technical scheme, through the statistical analysis of the production processes of the difference points and the monitoring of the product yield, a plurality of production processes which lead to the production of defective products can be timely provided for the management personnel when the product yield is abnormal, the management personnel can conveniently adjust and correct in time, and the effect of effectively improving the production efficiency and the production quality is achieved. And when the occupation ratio generated at the difference point of a certain process is larger than the preset difference occupation ratio threshold value, the abnormal operation state of the production process is judged, alarm information is sent out in time to inform a manager, the reason for producing defective products is more intelligently and accurately pointed out for the manager, the efficiency of the manager for improving and adjusting production equipment is further improved, and the effects of effectively improving the production efficiency and the production quality are achieved.
Preferably, the preset difference procedure calculation formula is Y = X/a × 100%, where X is the number of times of generating difference points in a certain processing procedure, and a is the total number of difference points of an unqualified product.
By adopting the technical scheme, the proportion generated by calculating the difference points of each production process is convenient for judging that the operation state of the production process is abnormal when the proportion generated by the difference points of a certain process is larger than the preset difference proportion threshold value, and timely sending alarm information to inform a manager, so that the manager can be intelligently and accurately pointed out the reason for the defective products, the efficiency of the manager in improving and adjusting production equipment is further improved, and the effect of effectively improving the production efficiency and the production quality is achieved.
In a second aspect, the present application provides an intelligent manufacturing defective product analysis system, which adopts the following technical scheme:
an intelligent manufacturing shoddy analysis system, comprising:
the server module is used for establishing a defective product inspection analysis platform and inputting product information of a product to be detected, wherein the product information comprises product name information, product type information, product standard appearance image information, product process flow information and product inspection point information;
the image acquisition module is used for acquiring appearance image information of a product to be detected;
the preliminary inspection module is used for preliminarily identifying the acquired appearance image information of the product to be detected and judging the validity of the appearance image information;
the image comparison module is used for comparing and analyzing the appearance image information of the product to be detected, which is judged through effectiveness, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not;
the difference point analysis module is used for marking difference points on the appearance image information of the product to be detected when the product to be detected is unqualified, and determining a difference point generation process according to the difference points on the appearance image information of the unqualified product;
the equipment monitoring module is used for continuously carrying out statistical analysis on the difference point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal;
the server module, the image acquisition module, the preliminary inspection module, the image comparison module, the difference point analysis module and the equipment monitoring module are in communication connection with each other.
By adopting the technical scheme, a defective product inspection and analysis platform is established, product information of a product to be detected is input, appearance image information of the product to be detected is obtained, the appearance image information of the product to be detected is preliminarily identified, the effectiveness of the appearance image information of the product to be detected is ensured, the effective appearance image information of the product to be detected is contrasted and analyzed, and the effect of efficiently screening defective products is realized; and furthermore, the generation reasons of the defective products are subjected to statistical analysis, the reasons and the processes of the defective products are intelligently judged, alarm information is generated to inform a manager, the effects of efficiently screening the defective products and intelligently analyzing the reasons of the defective products are achieved, and the production quality of products is improved.
In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium, storing a computer program that can be loaded by a processor and that performs any of the methods described above.
By adopting the technical scheme, a defective product inspection and analysis platform is established, product information of a product to be detected is input, appearance image information of the product to be detected is obtained, the appearance image information of the product to be detected is preliminarily identified, the effectiveness of the appearance image information of the product to be detected is ensured, the effective appearance image information of the product to be detected is contrasted and analyzed, and the effect of efficiently screening defective products is realized; and furthermore, the generation reasons of the defective products are subjected to statistical analysis, the reasons and the processes of the defective products are intelligently judged, alarm information is generated to inform a manager, the effects of efficiently screening the defective products and intelligently analyzing the reasons of the defective products are achieved, and the production quality of products is improved.
In summary, the present application includes at least one of the following beneficial technical effects:
1. establishing a defective product inspection and analysis platform, inputting product information of a product to be detected, acquiring appearance image information of the product to be detected, primarily identifying the appearance image information of the product to be detected to ensure the effectiveness of the appearance image information of the product to be detected, and performing comparative analysis on the effective appearance image information of the product to be detected to realize the effect of efficiently screening defective products; furthermore, the generation reasons of the defective products are statistically analyzed, the reasons and the working procedures of the defective products are intelligently judged, alarm information is generated to inform a manager, the effects of efficiently screening the defective products and intelligently analyzing the reasons of the defective products are achieved, and the production quality of products is improved;
2. through the statistical analysis of the generation processes of the difference points and the monitoring of the good product rate, a plurality of production processes which cause the generation of defective products can be provided for managers in time when the good product rate is abnormal, so that the managers can adjust and correct in time conveniently, and the effect of effectively improving the production efficiency and the production quality is achieved; when the occupation ratio generated at the difference point of a certain process is larger than the preset difference occupation ratio threshold value, the abnormal operation state of the production process is judged, alarm information is sent out in time to inform a manager, the reason for generating defective products is more intelligently and accurately pointed out for the manager, the efficiency of the manager for improving and adjusting production equipment is further improved, and the effects of effectively improving the production efficiency and the production quality are achieved;
3. the whole appearance image information of the product to be detected and the appearance image of each inspection point are compared and analyzed in sequence, the whole contrast similarity and the image defect information of the product are obtained, whether the product to be detected is qualified or not is judged according to the whole appearance image information and the appearance image of each inspection point, the inspection accuracy of the product to be detected is improved, and the intelligent inspection effect of the product to be detected is achieved.
Drawings
FIG. 1 is a block diagram of a method for analyzing a defect in an intelligent manufacturing apparatus according to an embodiment of the present invention;
FIG. 2 is a block diagram of a method for generating standard appearance image information in an embodiment of the present application;
FIG. 3 is a block diagram of a method for determining validity of appearance image information of a product to be detected in an embodiment of the present application;
FIG. 4 is a block diagram of a method for determining whether appearance image information of a product to be tested is qualified in an embodiment of the present application;
FIG. 5 is a block diagram of a method for determining a product differentiation point generation procedure in an embodiment of the present application;
FIG. 6 is a block diagram of a method for analyzing the cause of defective products in the embodiment of the present application;
fig. 7 is a system block diagram of an intelligent manufacturing defect analyzing system in the embodiment of the present application.
Description of reference numerals: 1. a server module; 2. an image acquisition module; 3. a preliminary inspection module; 4. an image comparison module; 5. difference point analysis module 6, equipment monitoring module.
Detailed Description
The present application is described in further detail below with reference to figures 1-7.
The embodiment of the application discloses a substandard product analysis method for intelligent manufacturing. Referring to fig. 1, a method for analyzing a defective product for smart manufacturing includes the steps of:
s1, recording product information of the product to be detected: establishing a defective product inspection analysis platform, and inputting product information of a product to be detected, wherein the product information comprises product name information, product type information, product standard appearance image information, product process information and product inspection point information;
s2, judging validity of the appearance image information: acquiring appearance image information of a product to be detected, carrying out primary identification on the acquired appearance image information of the product to be detected, and judging the validity of the appearance image information;
s3, judging whether the appearance image information of the product to be detected is qualified: comparing and analyzing the appearance image information of the product to be detected, which is judged by validity, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not;
s4, determining the difference points of the unqualified products: if the product to be detected is unqualified, marking the difference points on the appearance image information of the product to be detected, and determining a difference point generating process according to the difference points on the appearance image information of the unqualified product;
s5, continuously carrying out statistical analysis on the difference point generation process: continuously carrying out statistical analysis on the different point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal. And establishing a defective product inspection analysis platform, inputting product information of the product to be detected, acquiring appearance image information of the product to be detected, and initially identifying the appearance image information of the product to be detected to ensure the validity of the appearance image information of the product to be detected. And then, the effective appearance image information of the product to be detected is contrasted and analyzed, so that the effect of efficiently screening the defective products is realized. And furthermore, the generation reasons of the defective products are subjected to statistical analysis, the reasons and the processes of the defective products are intelligently judged, alarm information is generated to inform a manager, the effects of efficiently screening the defective products and intelligently analyzing the reasons of the defective products are achieved, and the production quality of products is improved.
Referring to fig. 2, the product standard appearance image information includes a product overall standard appearance image and standard appearance images of each product inspection point, and the product standard appearance image information specifically includes the following acquisition steps:
a1, generating an integral standard appearance image of the product: acquiring image information of standard and qualified products for multiple times through preset image acquisition equipment, and generating an integral standard appearance image of the product by using the image information of the standard and qualified products acquired for multiple times through a statistical average method;
a2, generating standard appearance images of the check points of the products: acquiring high-definition amplified image information of each inspection point on a standard qualified product for multiple times through preset image acquisition equipment, and sequentially generating a standard appearance image of each product inspection point on multiple high-definition amplified images of each inspection point by adopting a statistical average method;
a3, packaging to generate product standard appearance image information: and splicing the standard appearance images of the product inspection points to generate a high-definition amplified integral appearance image of the product, zooming the high-definition amplified integral appearance image of the product to the same proportion of the integral standard appearance image of the product, performing superposition comparison to obtain a similarity value, judging that the image acquisition is successful if the similarity value is greater than a preset similarity threshold value, and packaging the integral standard appearance image of the product and the standard appearance images of the product inspection points to generate standard appearance image information of the product. The whole standard appearance image of the product and the standard appearance image of each product inspection point are obtained by collecting the standard qualified samples for multiple times, so that the accuracy of the standard appearance image information of the product is ensured, and the defective products can be conveniently and accurately screened out in a high-efficiency manner. And after the product overall standard appearance image and the standard appearance images of the product inspection points are generated, the correctness of the product overall standard appearance image is verified by splicing and zooming the standard appearance images of the product inspection points, and the accuracy of the product standard appearance image information is further effectively improved.
Referring to fig. 3, the obtaining of the appearance image information of the to-be-detected product in step S2, performing preliminary identification on the obtained appearance image information of the to-be-detected product, and determining the validity of the appearance image information specifically include the following steps:
b1, collecting the appearance image information of the product to be detected: the method comprises the steps that appearance image information of a product to be detected is acquired through preset image acquisition equipment, wherein the appearance image information of the product to be detected comprises an integral appearance image of the product to be detected and appearance images of all inspection points of the product to be detected;
b2, identifying and verifying the overall appearance image of the product to be detected: preliminarily identifying the overall appearance image of the product to be detected, carrying out coordinate positioning on the overall appearance image of the product to be detected, judging whether the acquired acquisition angle of the overall appearance image of the product to be detected is consistent with a preset acquisition angle or not, and if so, enabling the overall appearance image of the product to be detected to be effective;
b3, identifying and verifying the appearance images of each inspection point of the product to be tested: numbering the appearance images of all inspection points of the product to be detected according to inspection point numbers in the product inspection point information, judging whether the appearance images are missing or not, if not, performing coordinate positioning on the appearance images of all inspection points of the product to be detected, judging whether the collected collection angle of the appearance images of all inspection points of the product to be detected is consistent with a preset collection angle or not, and if so, enabling the appearance images of all inspection points of the product to be detected to be effective. The appearance image information of the product to be detected is preliminarily identified, the effectiveness of the appearance image information of the product to be detected is ensured, the phenomenon that the collected invalid image information is analyzed and compared to obtain an incorrect comparison result is avoided, the comparison analysis operation resources are saved, and the effect of efficiently and accurately screening out the defective products is achieved.
Referring to fig. 4, the step S3 of comparing and analyzing the external image information of the product to be tested, which is determined by validity, with the standard external image information of the product to determine whether the external image information of the product to be tested is qualified specifically includes the following steps:
c1, obtaining contrast similarity value: comparing and analyzing the overall appearance image information of the product to be detected with the overall standard appearance image information of the product to obtain a comparison similarity value;
c2, acquiring image defect information: comparing and analyzing the appearance image of each inspection point of the product to be tested with the standard appearance image of each inspection point of the product one by one through the serial number to obtain image defect information;
c3, judging whether the appearance image information of the product to be detected is qualified: and if the contrast similarity value is larger than the preset threshold value and the image defect information does not exist, judging that the appearance image information of the product to be detected is qualified, otherwise, judging that the appearance image information of the product to be detected is unqualified. The preset threshold is set by a manager. It should be noted that the algorithm for obtaining the contrast similarity value through image contrast analysis is not described in detail in the prior art. The whole appearance image information of the product to be detected and the appearance image of each inspection point are compared and analyzed in sequence, the whole contrast similarity and the image defect information of the product are obtained, whether the product to be detected is qualified or not is judged according to the whole appearance image information and the appearance image of each inspection point, the inspection accuracy of the product to be detected is improved, and the intelligent inspection effect of the product to be detected is achieved.
The image defect information is set by a manager according to product information, and includes, but is not limited to, point defects, abnormal color points, color differences, orange peel, bubbles, screen offset, poor printing, scratches, burrs, and burrs. The image defect information that the demand was screened can be set for to the managers according to the actual production demand of product, and the substandard product is selected to the intelligence of being convenient for accurately, improves substandard product screening efficiency, helps producing the reason to the substandard product and carries out the analysis, and the managers of being convenient for in time discover the equipment or the process that lead to the substandard product to produce, helps managers to improve technology and improve product production quality.
Referring to fig. 5, the step S4 of labeling the difference points on the appearance image information of the product to be tested if the product to be tested is unqualified, and the step of determining the difference points according to the difference points on the appearance image information of the unqualified product includes the following steps:
d1, labeling the difference points: if the product to be detected is unqualified, marking difference points on the appearance image information of the product, wherein the difference points comprise image defect information and image comparison difference points;
d2, determining the product part of the difference point: determining product positions of the difference points according to position information of the difference points on the appearance image information of the unqualified product;
d3, determining difference points: and determining a processing generation procedure of the product part, namely a difference point generation procedure according to the product process flow information, wherein the difference point generation procedure comprises a processing procedure for directly generating the part and an upper layer processing procedure necessary for generating the part. By carrying out statistical analysis on the difference points on the defective products, the production process causing each defective product is determined, root tracing and source tracing are conveniently carried out on the causes of the defective products, management personnel can find and correct production defects in time, and the effect of effectively improving the production efficiency and the production quality is achieved.
Referring to fig. 6, the continuously performing statistical analysis on the difference point generating processes of the rejected products of the same production line in step S5 to confirm the operation status of the production equipment of each production process, and sending an alarm message to the manager when the operation status of the production equipment of a certain production process is abnormal specifically includes the following steps:
e1, calculating the difference of each process to generate the ratio: continuously carrying out statistical analysis on the difference point generating processes of unqualified products of the same production line in the same production period according to a preset production period, and calculating the difference point generating occupation ratio of each process according to a preset difference process calculation formula;
the preset difference procedure calculation formula is Y = X/A100%, wherein X is the number of times of generating difference points in a certain processing procedure, and A is the total number of the difference points of unqualified products;
e2, judging the operation state of the production equipment in the production process: if the occupation ratio of the difference points of a certain process is larger than a preset difference occupation ratio threshold value, judging that the operation state of the production equipment of the process is abnormal, and sending alarm information to a manager
E3, calculating the yield in real time: counting the number of defective products and the number of produced products in the same production period according to a preset production period, and calculating the yield in real time;
e4, generating alarm information when the yield is less than the preset yield threshold: and if the yield is less than a preset yield threshold value, generating proportion integration generation alarm information of the difference points of each production process, and sending the proportion integration generation alarm information to a manager. The difference ratio threshold value and the yield threshold value are both set by management personnel, in the embodiment, the difference ratio threshold value is set to be 50%, and the yield threshold value is set to be 99%. Through the statistical analysis of the production processes of the difference points and the monitoring of the product yield, a plurality of production processes which lead to the generation of defective products can be timely provided for management personnel when the product yield is abnormal, the management personnel can conveniently and timely adjust and correct the production processes, and the effect of effectively improving the production efficiency and the production quality is achieved. And when the occupation ratio generated at the difference point of a certain process is larger than the preset difference occupation ratio threshold value, the abnormal operation state of the production process is judged, alarm information is sent out in time to inform a manager, the reason for producing defective products is more intelligently and accurately pointed out for the manager, the efficiency of the manager for improving and adjusting production equipment is further improved, and the effects of effectively improving the production efficiency and the production quality are achieved.
The embodiment of the application also discloses a substandard product analysis system for intelligent manufacturing. Referring to fig. 7, a system for analyzing a defective product for smart manufacturing includes:
the server module 1 is used for establishing a defective product inspection analysis platform and inputting product information of a product to be detected, wherein the product information comprises product name information, product type information, product standard appearance image information, product process flow information and product inspection point information;
the image acquisition module 2 is used for acquiring appearance image information of a product to be detected;
the preliminary inspection module 3 is used for preliminarily identifying the acquired appearance image information of the product to be detected and judging the validity of the appearance image information;
the image comparison module 4 is used for comparing and analyzing the appearance image information of the product to be detected, which is judged by validity, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not;
the difference point analysis module 5 is used for labeling the difference points on the appearance image information of the product to be detected when the product to be detected is unqualified, and determining a difference point generation process according to the difference points on the appearance image information of the unqualified product;
the equipment monitoring module 6 is used for continuously carrying out statistical analysis on the difference point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal;
the server module 1, the image acquisition module 2, the preliminary inspection module 3, the image comparison module 4, the difference point analysis module 5 and the equipment monitoring module 6 are in communication connection with each other. The method comprises the steps of establishing a defective product inspection and analysis platform, inputting product information of a product to be detected, acquiring appearance image information of the product to be detected, preliminarily identifying the appearance image information of the product to be detected, ensuring the effectiveness of the appearance image information of the product to be detected, carrying out contrastive analysis on the effective appearance image information of the product to be detected, and achieving the effect of efficiently screening defective products. And furthermore, the generation reasons of the defective products are subjected to statistical analysis, the reasons and the processes of the defective products are intelligently judged, alarm information is generated to inform a manager, the effects of efficiently screening the defective products and intelligently analyzing the reasons of the defective products are achieved, and the production quality of products is improved.
The embodiment of the present application further discloses a computer-readable storage medium, which stores a computer program that can be loaded by a processor and executed in the method as described above, and the computer-readable storage medium includes, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above examples are only used to illustrate the technical solutions of the present invention, and do not limit the scope of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from these embodiments without making any inventive step, fall within the scope of the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art may still make various combinations, additions, deletions or other modifications of the features of the embodiments of the present invention according to the situation without conflict, so as to obtain different technical solutions without substantially departing from the spirit of the present invention, and these technical solutions also fall within the protection scope of the present invention.
Claims (10)
1. The intelligent manufacturing defective product analysis method is characterized by comprising the following steps: the method comprises the following steps:
establishing a defective product inspection analysis platform, and inputting product information of a product to be detected, wherein the product information comprises product name information, product type information, product standard appearance image information, product process information and product inspection point information;
acquiring appearance image information of a product to be detected, carrying out primary identification on the acquired appearance image information of the product to be detected, and judging the validity of the appearance image information;
comparing and analyzing the appearance image information of the product to be detected, which is judged by validity, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not;
if the product to be detected is unqualified, marking the difference points on the appearance image information of the product to be detected, and determining a difference point generating process according to the difference points on the appearance image information of the unqualified product;
continuously carrying out statistical analysis on the different point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal.
2. The intelligent manufacturing defective product analysis method according to claim 1, wherein the product standard appearance image information includes a product overall standard appearance image and a product inspection point standard appearance image, and the product standard appearance image information specifically includes the following acquisition steps:
acquiring image information of standard and qualified products for multiple times through preset image acquisition equipment, and generating an integral standard appearance image of the product by using the image information of the standard and qualified products acquired for multiple times through a statistical average method;
acquiring high-definition amplified image information of each inspection point on a standard qualified product for multiple times through preset image acquisition equipment, and sequentially generating a standard appearance image of each product inspection point on multiple high-definition amplified images of each inspection point by adopting a statistical average method;
and splicing the standard appearance images of the product inspection points to generate a high-definition amplified integral appearance image of the product, zooming the high-definition amplified integral appearance image of the product to the same proportion of the integral standard appearance image of the product, performing superposition comparison to obtain a similarity value, judging that the image acquisition is successful if the similarity value is greater than a preset similarity threshold value, and packaging the integral standard appearance image of the product and the standard appearance images of the product inspection points to generate standard appearance image information of the product.
3. The intelligent manufacturing defective product analysis method according to claim 2, wherein the step of acquiring the appearance image information of the product to be tested, the step of preliminarily identifying the acquired appearance image information of the product to be tested, and the step of judging the validity of the appearance image information specifically comprise the steps of:
the method comprises the steps that appearance image information of a product to be detected is acquired through preset image acquisition equipment, wherein the appearance image information of the product to be detected comprises an integral appearance image of the product to be detected and appearance images of all inspection points of the product to be detected;
preliminarily identifying the overall appearance image of the product to be detected, carrying out coordinate positioning on the overall appearance image of the product to be detected, judging whether the acquired acquisition angle of the overall appearance image of the product to be detected is consistent with a preset acquisition angle or not, and if so, enabling the overall appearance image of the product to be detected to be effective;
numbering the appearance images of all inspection points of the product to be detected according to inspection point numbers in the product inspection point information, judging whether the appearance images are missing or not, if not, performing coordinate positioning on the appearance images of all inspection points of the product to be detected, judging whether the collected collection angle of the appearance images of all inspection points of the product to be detected is consistent with a preset collection angle or not, and if so, enabling the appearance images of all inspection points of the product to be detected to be effective.
4. The intelligent manufacturing defective product analysis method according to claim 3, wherein the step of comparing the image information of the appearance of the product to be tested, which is judged by validity, with the image information of the standard appearance of the product to judge whether the image information of the appearance of the product to be tested is qualified specifically comprises the steps of:
comparing and analyzing the overall appearance image information of the product to be detected with the overall standard appearance image information of the product to obtain a comparison similarity value;
comparing and analyzing the appearance image of each inspection point of the product to be tested with the standard appearance image of each inspection point of the product one by one through the serial number to obtain image defect information;
and if the contrast similarity value is larger than the preset threshold value and the image defect information does not exist, judging that the appearance image information of the product to be detected is qualified, otherwise, judging that the appearance image information of the product to be detected is unqualified.
5. The intelligent manufacturing defect analysis method according to claim 4, wherein: the image defect information is set by a manager according to product information, and includes, but is not limited to, point defects, abnormal color points, color differences, orange peel, bubbles, screen offset, poor printing, scratches, burrs, and burrs.
6. The method according to claim 4, wherein the step of labeling the difference points on the appearance image information of the product to be tested if the product is unqualified and the step of determining the difference points according to the difference points on the appearance image information of the unqualified product comprises the following steps:
if the product to be detected is unqualified, marking difference points on the appearance image information of the product, wherein the difference points comprise image defect information and image comparison difference points;
determining product positions of the difference points according to position information of the difference points on the appearance image information of the unqualified product;
and determining a processing generation procedure of the product part, namely a difference point generation procedure according to the product process flow information, wherein the difference point generation procedure comprises a processing procedure for directly generating the part and an upper layer processing procedure necessary for generating the part.
7. The method according to claim 1, wherein the step of continuously performing statistical analysis on the difference point generation processes of the defective products in the same production line, confirming the operation status of the production equipment in each production process, and sending an alarm message to a manager when the operation status of the production equipment in a certain production process is abnormal specifically comprises the steps of:
continuously carrying out statistical analysis on the difference point generating processes of unqualified products of the same production line in the same production period according to a preset production period, and calculating the difference point generating occupation ratio of each process according to a preset difference process calculation formula;
if the occupation ratio of the difference points of a certain process is larger than a preset difference occupation ratio threshold value, judging that the operation state of the production equipment of the process is abnormal, and sending alarm information to a manager
Counting the number of defective products and the number of produced products in the same production period according to a preset production period, and calculating the yield in real time;
and if the yield is less than a preset yield threshold value, generating proportion integration generation alarm information of the difference points of each production process, and sending the proportion integration generation alarm information to a manager.
8. The intelligent manufacturing defect analysis method according to claim 7, wherein: the preset difference procedure calculation formula is Y = X/A100%, wherein X is the number of times of generating difference points in a certain processing procedure, and A is the total number of the difference points of unqualified products.
9. The utility model provides an intelligent manufacturing is with substandard product analytic system which characterized in that includes:
the server module (1) is used for establishing a defective product inspection analysis platform and inputting product information of a product to be detected, wherein the product information comprises product name information, product type information, product standard appearance image information, product process flow information and product inspection point information;
the image acquisition module (2) is used for acquiring appearance image information of a product to be detected;
the preliminary inspection module (3) is used for preliminarily identifying the acquired appearance image information of the product to be detected and judging the validity of the appearance image information;
the image comparison module (4) is used for comparing and analyzing the appearance image information of the product to be detected, which is judged through effectiveness, with the standard appearance image information of the product, and judging whether the appearance image information of the product to be detected is qualified or not;
the difference point analysis module (5) is used for marking the difference points on the appearance image information of the product to be detected when the product to be detected is unqualified, and determining a difference point generation process according to the difference points on the appearance image information of the unqualified product;
the equipment monitoring module (6) is used for continuously carrying out statistical analysis on the difference point generating processes of unqualified products of the same production line, confirming the operation condition of the production equipment of each production process, and sending alarm information to a manager when the operation condition of the production equipment of a certain production process is abnormal;
the device comprises a server module (1), an image acquisition module (2), a preliminary inspection module (3), an image comparison module (4), a difference point analysis module (5) and a device monitoring module (6) which are in communication connection with each other.
10. A computer-readable storage medium characterized by: a computer program which can be loaded by a processor and which performs the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111580128.6A CN114219799A (en) | 2021-12-22 | 2021-12-22 | Intelligent manufacturing defective product analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111580128.6A CN114219799A (en) | 2021-12-22 | 2021-12-22 | Intelligent manufacturing defective product analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114219799A true CN114219799A (en) | 2022-03-22 |
Family
ID=80704992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111580128.6A Pending CN114219799A (en) | 2021-12-22 | 2021-12-22 | Intelligent manufacturing defective product analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219799A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114879621A (en) * | 2022-07-11 | 2022-08-09 | 佛山市木木生活家具有限公司 | Furniture spraying processing control method, system and device |
| CN115660596A (en) * | 2022-11-03 | 2023-01-31 | 创启科技(广州)有限公司 | Data interaction method of mobile terminal and mobile terminal |
| CN116258424A (en) * | 2023-05-16 | 2023-06-13 | 宁德时代新能源科技股份有限公司 | Product analysis method, battery product analysis method, device, equipment and medium |
| CN116342606A (en) * | 2023-05-30 | 2023-06-27 | 中色创新研究院(天津)有限公司 | Defect traceability analysis method based on copper alloy processing finished product |
| CN117516868A (en) * | 2023-10-24 | 2024-02-06 | 江苏俊知传感技术有限公司 | Intelligent detection system of optical divider |
| CN117686516A (en) * | 2024-01-29 | 2024-03-12 | 江苏优众微纳半导体科技有限公司 | Automatic chip appearance defect detection system based on machine vision |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060191622A1 (en) * | 2005-02-28 | 2006-08-31 | The Boeing Company | Real-time infrared thermography inspection and control for automated composite material layup |
| CN101666616A (en) * | 2008-09-01 | 2010-03-10 | 比亚迪股份有限公司 | Appearance detecting method |
| CN101762231A (en) * | 2008-12-26 | 2010-06-30 | 比亚迪股份有限公司 | Device and method for detecting appearance of mobile phone keys |
| CN106886989A (en) * | 2015-12-11 | 2017-06-23 | 东莞东聚电子电讯制品有限公司 | The automatic optical detection method of keyboard |
| CN109949291A (en) * | 2019-03-19 | 2019-06-28 | 苏州润智和智能科技有限公司 | A kind of defect inspection method of Cast Aluminum Auto-parts Abroad radioscopic image |
| CN110619620A (en) * | 2018-06-04 | 2019-12-27 | 杭州海康威视数字技术股份有限公司 | Method, device and system for positioning abnormity causing surface defects and electronic equipment |
| CN112465809A (en) * | 2020-12-15 | 2021-03-09 | 北京市计算中心 | Mold defect detection method based on image recognition, computer-readable storage medium and device |
| CN112964736A (en) * | 2021-02-04 | 2021-06-15 | 杭州富庆纸制品有限公司 | Printing quality control system and method for printing machine, intelligent terminal and storage medium |
-
2021
- 2021-12-22 CN CN202111580128.6A patent/CN114219799A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060191622A1 (en) * | 2005-02-28 | 2006-08-31 | The Boeing Company | Real-time infrared thermography inspection and control for automated composite material layup |
| CN101666616A (en) * | 2008-09-01 | 2010-03-10 | 比亚迪股份有限公司 | Appearance detecting method |
| CN101762231A (en) * | 2008-12-26 | 2010-06-30 | 比亚迪股份有限公司 | Device and method for detecting appearance of mobile phone keys |
| CN106886989A (en) * | 2015-12-11 | 2017-06-23 | 东莞东聚电子电讯制品有限公司 | The automatic optical detection method of keyboard |
| CN110619620A (en) * | 2018-06-04 | 2019-12-27 | 杭州海康威视数字技术股份有限公司 | Method, device and system for positioning abnormity causing surface defects and electronic equipment |
| CN109949291A (en) * | 2019-03-19 | 2019-06-28 | 苏州润智和智能科技有限公司 | A kind of defect inspection method of Cast Aluminum Auto-parts Abroad radioscopic image |
| CN112465809A (en) * | 2020-12-15 | 2021-03-09 | 北京市计算中心 | Mold defect detection method based on image recognition, computer-readable storage medium and device |
| CN112964736A (en) * | 2021-02-04 | 2021-06-15 | 杭州富庆纸制品有限公司 | Printing quality control system and method for printing machine, intelligent terminal and storage medium |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114879621A (en) * | 2022-07-11 | 2022-08-09 | 佛山市木木生活家具有限公司 | Furniture spraying processing control method, system and device |
| CN114879621B (en) * | 2022-07-11 | 2022-09-27 | 佛山市木木生活家具有限公司 | Furniture spraying machining control method, system and device |
| CN115660596A (en) * | 2022-11-03 | 2023-01-31 | 创启科技(广州)有限公司 | Data interaction method of mobile terminal and mobile terminal |
| CN116258424A (en) * | 2023-05-16 | 2023-06-13 | 宁德时代新能源科技股份有限公司 | Product analysis method, battery product analysis method, device, equipment and medium |
| CN116258424B (en) * | 2023-05-16 | 2023-09-29 | 宁德时代新能源科技股份有限公司 | Product analysis method, battery product analysis method, device, equipment and medium |
| CN116342606A (en) * | 2023-05-30 | 2023-06-27 | 中色创新研究院(天津)有限公司 | Defect traceability analysis method based on copper alloy processing finished product |
| CN116342606B (en) * | 2023-05-30 | 2023-10-17 | 中色创新研究院(天津)有限公司 | Defect traceability analysis method based on copper alloy processing finished product |
| CN117516868A (en) * | 2023-10-24 | 2024-02-06 | 江苏俊知传感技术有限公司 | Intelligent detection system of optical divider |
| CN117686516A (en) * | 2024-01-29 | 2024-03-12 | 江苏优众微纳半导体科技有限公司 | Automatic chip appearance defect detection system based on machine vision |
| CN117686516B (en) * | 2024-01-29 | 2024-05-10 | 江苏优众微纳半导体科技有限公司 | Automatic chip appearance defect detection system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114219799A (en) | Intelligent manufacturing defective product analysis method and system | |
| CN111539923A (en) | Digital ray detection method and system for weld defects and server | |
| CN116337868B (en) | Surface defect detection method and detection system | |
| CN109283182A (en) | A kind of detection method of battery welding point defect, apparatus and system | |
| CN111103307A (en) | Pcb defect detection method based on deep learning | |
| CN113888480A (en) | MES-based quality tracing method and system | |
| CN114895634A (en) | Product production line automatic control system based on machine vision | |
| CN112330233A (en) | Injection molding product quality detection method based on data model | |
| CN113758524A (en) | Circuit board processing monitoring system | |
| CN109584208B (en) | Inspection method for intelligent identification model of industrial structure defects | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN116308070B (en) | Method for collecting and managing inferior goods and related equipment | |
| CN113837178A (en) | Deep learning-based automatic positioning and unified segmentation method for meter of transformer substation | |
| CN110992333B (en) | COF Film defect AITraining database and application | |
| CN113222950A (en) | Surface defect detection model training method, surface defect detection method and system | |
| CN112184691A (en) | Defect mode analysis method based on poor Map | |
| CN117686516B (en) | Automatic chip appearance defect detection system based on machine vision | |
| CN110703730A (en) | Data acquisition testing method and device based on MES | |
| CN110796187A (en) | Method and device for classifying defects | |
| CN115830403B (en) | Automatic defect classification system and method based on deep learning | |
| CN112506749B (en) | On-site distinguishing method and system for error reporting information of hard disk | |
| CN117115114B (en) | YOLO-based power electronic device production process target identification and defect detection method | |
| CN111724352B (en) | Patch LED flaw labeling method based on kernel density estimation | |
| CN112085722B (en) | Training sample image acquisition method and device | |
| CN108242053B (en) | Defect image classification and collection method based on VAI surface detection system |
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 |