CN116309378B - Electronic product intelligent detection system based on artificial intelligence - Google Patents
Electronic product intelligent detection system based on artificial intelligence Download PDFInfo
- Publication number
- CN116309378B CN116309378B CN202310162120.0A CN202310162120A CN116309378B CN 116309378 B CN116309378 B CN 116309378B CN 202310162120 A CN202310162120 A CN 202310162120A CN 116309378 B CN116309378 B CN 116309378B
- Authority
- CN
- China
- Prior art keywords
- analysis
- detection
- electronic product
- preset
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 274
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 280
- 230000000007 visual effect Effects 0.000 claims abstract description 110
- 230000000737 periodic effect Effects 0.000 claims abstract description 86
- 230000007613 environmental effect Effects 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000013500 data storage Methods 0.000 claims abstract description 34
- 230000000694 effects Effects 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 230000007547 defect Effects 0.000 claims description 108
- 238000004364 calculation method Methods 0.000 claims description 36
- 238000011179 visual inspection Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 8
- 239000000428 dust Substances 0.000 claims description 7
- 238000001035 drying Methods 0.000 claims description 5
- 230000035515 penetration Effects 0.000 claims description 2
- 238000012797 qualification Methods 0.000 claims 5
- 238000004891 communication Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 12
- 238000012423 maintenance Methods 0.000 description 7
- 230000002950 deficient Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000002411 adverse Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- 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)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention belongs to the technical field of electronic product detection, in particular to an electronic product intelligent detection system based on artificial intelligence, which comprises an artificial intelligent detection and analysis platform, wherein the artificial intelligent detection and analysis platform comprises a server, and the server is in communication connection with a data storage module, an electronic product visual analysis module, an environment interference monitoring module, an electronic product batch feedback module and an equipment state analysis module; according to the invention, the electronic product visual analysis module is used for carrying out visual analysis on the corresponding electronic product, the electronic product batch feedback module is used for carrying out batch effect analysis, the environmental interference monitoring module is used for carrying out environmental interference analysis, effective combination of product visual detection analysis, environmental interference analysis and batch feedback is realized, the analysis process is more comprehensive, and the subsequent efficient and stable operation of the corresponding electronic product visual detection equipment is ensured through comprehensive analysis of the equipment state analysis module and the periodic uniformity detection module.
Description
Technical Field
The invention relates to the technical field of electronic product detection, in particular to an electronic product intelligent detection system based on artificial intelligence.
Background
The electronic product is a related product based on electric energy and mainly comprises a smart phone, a television, a flat panel, a video recorder, a radio, a sound recorder and the like, wherein in the processing process of the electronic product, the appearance defect inspection of the electronic product is an essential link, especially in the processing of a mobile phone screen, a flat panel and a liquid crystal panel, the appearance inspection of the electronic product such as the mobile phone screen, the flat panel and the liquid crystal panel is conventionally carried out mainly by manually carrying out naked eye observation and judging whether the corresponding appearance defect exists or not, and the detection process is carried out by manually judging that the accuracy of a detection result is poor;
At present, visual detection is performed on related electronic products mainly through electronic product visual detection equipment and whether defects exist in the appearance of the products are judged, but product visual detection analysis, environmental interference analysis and batch feedback cannot be combined in the prior art, so that stable and smooth performance of a product detection analysis process is difficult to ensure, further improvement of detection efficiency and accuracy of detection results of the electronic products is not facilitated, periodic state analysis and periodic uniformity analysis are difficult to perform on all electronic product visual detection equipment in a supervision range, supervision staff is not facilitated to perform equipment adjustment and maintenance, and improvement is required.
Disclosure of Invention
The invention aims to provide an electronic product intelligent detection system based on artificial intelligence, which solves the problems that in the prior art, product visual detection analysis, environmental interference analysis and batch feedback cannot be combined, the detection efficiency and the detection result accuracy of electronic products are not facilitated to be further improved, the periodic state analysis and the periodic uniformity analysis are difficult to be carried out on all electronic product visual detection equipment in a supervision range, and the equipment adjustment and maintenance by supervision staff are not facilitated.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an electronic product intelligent detection system based on artificial intelligence comprises an artificial intelligent detection analysis platform, wherein the artificial intelligent detection analysis platform comprises a server, a data storage module, an electronic product visual analysis module, an environment interference monitoring module, an electronic product batch feedback module and an equipment state analysis module;
The electronic product visual detection equipment is used for carrying out visual detection on the electronic product and sending the visual detection picture of the electronic product to the visual analysis module of the electronic product through the server; the electronic product visual analysis module is used for performing visual analysis on the corresponding electronic product, marking the corresponding electronic product as a superior product, a primary defect product, a secondary defect product or a tertiary defect product, and sending grading information of the corresponding electronic product to the server;
the environment interference monitoring module is used for judging whether the corresponding detection environment is normal or not through environment interference analysis and generating an environment interference qualified signal or an environment interference unqualified signal when the electronic product visual detection equipment detects the electronic product, and sending the environment interference qualified signal or the environment interference unqualified signal to the server; the method comprises the steps that when a server receives an environment drying disqualification signal, an environment interference early warning signal is generated and sent to a supervision terminal;
the electronic product batch feedback module is used for carrying out batch effect analysis after the detection of the electronic products in the corresponding batch is finished, marking the corresponding batch as an equal batch, a equal batch or a three-equal batch, and sending the corresponding batch and the marking information of the corresponding batch to the supervision terminal through the server; the device state analysis module is used for carrying out periodic state analysis on the electronic product visual detection devices in the supervision range, and judging whether the periodic detection of the corresponding electronic product visual detection devices is qualified or not according to the periodic state analysis.
Further, the specific operation process of the electronic product visual analysis module comprises the following steps:
Acquiring an electronic product visual detection picture sent by corresponding electronic product visual detection equipment, calling an electronic product standard picture through a data storage module, dividing the electronic product visual picture into a plurality of sub analysis areas and marking the sub analysis areas as analysis subsets i, i=1, 2, …, n, n represents the number of the sub analysis areas and n is a positive integer larger than 3;
Comparing the analysis subset i with the corresponding picture area of the electronic product standard picture, if the analysis subset i is consistent with the appearance of the corresponding picture area of the electronic product standard picture, judging that the corresponding analysis subset i has small appearance visual defects, and marking the corresponding analysis subset i as a defect-free subset; if the appearance of the analysis subset i is inconsistent with the appearance of the corresponding picture area of the electronic product standard picture, judging that the appearance visual defect of the corresponding analysis subset i is highly likely, and marking the corresponding analysis subset i as a defect subset;
Acquiring all defect-free subsets and all defect subsets in the corresponding electronic product visual inspection picture, marking the corresponding electronic product as a superior product if the defect subsets do not exist in the corresponding electronic product visual inspection picture, otherwise acquiring the number of the defect-free subsets and the number of the defect subsets in the corresponding electronic product visual inspection picture, and carrying out ratio calculation on the number of the defect subsets and the number of the defect-free subsets to acquire a product defect coefficient;
And (3) calling a preset product defect coefficient range through a data storage module, comparing the product defect coefficient with the preset product defect coefficient range in numerical value, marking the corresponding electronic product as a first-level defect product if the product defect coefficient is larger than or equal to the maximum value of the preset product defect coefficient range, marking the corresponding electronic product as a second-level defect product if the product defect coefficient is in the preset product defect coefficient range, and marking the corresponding electronic product as a third-level defect product if the product defect coefficient is smaller than or equal to the minimum value of the preset product defect coefficient range.
Further, the specific operation process of the electronic product batch feedback module comprises the following steps:
Obtaining grading information of all detected electronic products in the electronic products of the corresponding batch, counting the number of the superior products, the number of the primary defect products, the number of the secondary defect products and the number of the tertiary defect products in the electronic products of the corresponding batch, and carrying out numerical calculation on the number of the superior products, the number of the primary defect products, the number of the secondary defect products and the number of the tertiary defect products to obtain batch representation values of the electronic products of the corresponding batch;
And (3) calling a preset batch expression range through the data storage module, comparing the batch expression value with the preset batch expression range in a numerical mode, marking the corresponding batch as an equal-class batch if the batch expression value is larger than or equal to the maximum value of the preset batch expression range, marking the corresponding batch as an equal-class batch if the batch expression value is in the preset batch expression range, and marking the corresponding batch as a three-class batch if the batch expression value is smaller than or equal to the minimum value of the preset batch expression range.
Further, the specific operation process of the environmental interference monitoring module includes:
Acquiring a product detection area corresponding to the electronic product visual detection equipment, marking the product detection area as an analysis area, acquiring temperature and humidity performance data, ring transmission performance data and environmental vibration data of the analysis area corresponding to the detection period, and carrying out numerical calculation on the temperature and humidity performance data, the ring transmission performance data and the environmental vibration data to acquire an environmental interference coefficient of the analysis area of the electronic product visual detection equipment corresponding to the detection period;
The method comprises the steps of calling a preset environmental interference coefficient threshold value through a data storage module, comparing the environmental interference coefficient with the preset environmental interference coefficient threshold value, judging that the environmental interference degree of the analysis area of the visual inspection equipment of the corresponding electronic product is small and generating an environmental interference qualified signal if the environmental interference coefficient is smaller than or equal to the preset environmental interference coefficient threshold value, and judging that the environmental interference degree of the analysis area of the visual inspection equipment of the corresponding electronic product is large and generating an environmental interference unqualified signal if the environmental interference coefficient is larger than the preset environmental interference coefficient threshold value.
Further, the specific analysis and acquisition method of the temperature and humidity performance data is as follows:
acquiring the temperature and the humidity of a corresponding analysis area, calling a preset proper temperature range and a preset proper humidity range through a data storage module, carrying out average value calculation on the maximum value and the minimum value of the preset proper temperature range to acquire a preset medium temperature value, carrying out difference value calculation on the temperature of the corresponding analysis area and the preset medium temperature value, acquiring temperature data by taking an absolute value, acquiring humidity data in the same way, and carrying out numerical calculation on the temperature data and the humidity data of the corresponding analysis area to acquire temperature and humidity performance data.
Further, the specific analysis and acquisition method of the ring transmission performance data and the environmental vibration data is as follows:
Acquiring a brightness value and a dust concentration value of a corresponding analysis area, calling a preset proper brightness range through a data storage module, carrying out mean value calculation on the maximum value and the minimum value of the preset proper brightness range to acquire brightness data, and carrying out numerical calculation on the brightness data and the dust concentration value to acquire ring penetration expression data; obtaining a vibration frequency value and a vibration amplitude value of a product bearing part corresponding to the analysis area equipment, and carrying out numerical calculation on the vibration frequency value and the vibration amplitude value to obtain environmental vibration data of the corresponding analysis area.
Further, the specific operation process of the device state analysis module includes:
The method comprises the steps of obtaining electronic product visual detection equipment in a supervision range, marking the electronic product visual detection equipment as an analysis object g, g=1, 2, …, k, wherein k represents the number of the electronic product visual detection equipment and k is a positive integer greater than 3; setting a device state analysis period, obtaining the number of the electronic products detected by the corresponding analysis object g in the device state analysis period, and marking the number as a period detection coefficient;
and the data storage module is used for retrieving a preset period detection coefficient threshold value, carrying out numerical comparison on the period detection coefficient and the preset period detection coefficient threshold value, judging that the period detection of the corresponding analysis object g is qualified if the period detection coefficient is larger than or equal to the preset period detection coefficient threshold value, and judging that the period detection of the corresponding analysis object g is unqualified if the period detection coefficient is smaller than the preset period detection coefficient threshold value.
Further, if the analysis object g with unqualified period detection exists, generating a unqualified period detection signal, and transmitting the unqualified period detection signal and the corresponding analysis object g to the supervision terminal through the server; if the analysis objects g with unqualified period detection do not exist, performing equipment effect difference analysis on all the analysis objects g, generating equipment effect difference qualified signals or equipment effect difference unqualified signals, and sending the equipment effect difference qualified signals or the equipment effect difference unqualified signals to a supervision terminal through a server.
Further, the specific analysis process of the equipment efficiency difference analysis is as follows:
The method comprises the steps of obtaining periodic detection quantity coefficients of all analysis objects g, establishing periodic detection quantity sets of the periodic detection quantity coefficients of all analysis objects g, carrying out variance calculation on the periodic detection quantity sets to obtain equipment efficiency difference coefficients, calling a preset efficiency difference coefficient threshold value through a data storage module, carrying out numerical comparison on the equipment efficiency difference coefficients and the preset efficiency difference coefficient threshold value, generating equipment efficiency difference unqualified signals if the equipment efficiency difference coefficients are larger than or equal to the preset efficiency difference coefficient threshold value, and generating equipment efficiency difference qualified signals if the equipment efficiency difference coefficients are smaller than the preset efficiency difference coefficient threshold value.
Further, the server is in communication connection with the periodic uniformity detection module, the server generates a periodic uniformity analysis signal and sends the periodic uniformity analysis signal and an analysis object g qualified by corresponding periodic detection to the periodic uniformity detection module, the periodic uniformity detection module receives the periodic uniformity analysis signal and then carries out periodic uniformity analysis on the analysis object g qualified by corresponding periodic detection to generate a periodic uniformity qualified signal or a periodic uniformity disqualified signal, and the periodic uniformity qualified signal or the periodic uniformity disqualified signal and the corresponding analysis object g are sent to the supervision terminal through the server.
Further, the specific analysis procedure of the cycle uniformity analysis is as follows:
Dividing the equipment state analysis period into a plurality of groups of analysis sub-periods, marking the analysis sub-periods as h, h=1, 2, …, j, j representing the number of the analysis sub-periods and j being a positive integer greater than 5; acquiring the number of the electronic products detected by the corresponding analysis equipment g in the analysis sub-period h, marking the number as a period detection coefficient, establishing a period detection set by using the period detection coefficients of all the analysis sub-periods of the corresponding analysis equipment g, and performing variance calculation on the period detection set of the corresponding analysis equipment g to acquire a period detection deviation value of the corresponding analysis equipment g;
and the data storage module is used for calling a preset period detection amount deviation threshold value, comparing the period detection amount deviation value with the preset period detection amount deviation threshold value in a numerical mode, judging that the period uniformity of the corresponding analysis equipment g is unqualified and generating a period uniformity unqualified signal if the period detection amount deviation value is larger than or equal to the preset period detection amount deviation threshold value, and judging that the period uniformity of the corresponding analysis equipment g is qualified and generating a period uniformity qualified signal if the period detection amount deviation value is smaller than the preset period detection amount deviation threshold value.
Compared with the prior art, the invention has the beneficial effects that:
1. The electronic product visual analysis module is used for carrying out visual analysis on the corresponding electronic products, grading the appearance effect and quality of the electronic products is realized, the subsequent processing of related electronic products is facilitated, the batch effect analysis is carried out after the detection of the corresponding batch of electronic products is finished through the electronic product batch feedback module, supervision personnel can master the batch quality of the electronic products in detail and carry out corresponding management on operators and processing equipment of the corresponding electronic product processing procedures, the environment interference monitoring module is used for carrying out environment interference analysis and generating environment interference qualified signals or environment interference unqualified signals in the electronic product detection process, the server is used for generating environment interference early warning signals when receiving environment drying unqualified signals, and the supervision personnel can correspondingly regulate the detection environment of the electronic product visual detection equipment in time when receiving environment interference early warning, so that the detection process can be continuously carried out in a stable and favorable environment, and adverse effects of the detection environment on the detection effect and efficiency of the electronic products are reduced;
2. The invention also carries out periodic state analysis on the electronic product visual detection equipment in the supervision range through the equipment state analysis module, generates a periodic detection unqualified signal and an equipment effect difference unqualified signal or an equipment effect difference qualified signal, and timely carries out reason investigation and maintenance and overhaul on the corresponding electronic product visual detection equipment according to the need when the supervision personnel receives the periodic detection unqualified signal or the equipment effect difference unqualified signal; and the periodic uniformity detection module is used for carrying out periodic uniformity analysis on the analysis object which is qualified in corresponding periodic detection, so that a periodic uniformity qualified signal or a periodic uniformity unqualified signal is generated, thereby being beneficial to maintenance and overhaul of related electronic product visual detection equipment by supervisory personnel and keeping stable detection efficiency of subsequent corresponding electronic product visual detection equipment.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is an overall system block diagram of the present invention;
FIG. 2 is a system block diagram of an artificial intelligence detection analysis platform according to the present invention;
Fig. 3 is a system block diagram of the second and third embodiments of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
As shown in fig. 1-2, the electronic product intelligent detection system based on artificial intelligence provided by the invention comprises an artificial intelligent detection analysis platform, wherein the artificial intelligent detection analysis platform is in communication connection with a supervision terminal and a plurality of groups of electronic product visual detection devices, the artificial intelligent detection analysis platform comprises a server, the server is in communication connection with a data storage module, an electronic product visual analysis module, an environment interference monitoring module and an electronic product batch feedback module, and the electronic product visual detection devices are used for carrying out visual detection on electronic products and sending visual detection pictures of the electronic products to the electronic product visual analysis module through the server;
in the visual detection process of the electronic product, the electronic product visual analysis module performs visual analysis on the corresponding electronic product, and the specific analysis process of the visual analysis is as follows:
step S1, acquiring an electronic product visual detection picture sent by corresponding electronic product visual detection equipment, and calling an electronic product standard picture through a data storage module, wherein the electronic product standard picture is screened in advance by an operator, input and stored in the data storage module, the electronic product visual picture is divided into a plurality of sub analysis areas and marked as an analysis subset i, i=1, 2, …, n and n represent the number of the sub analysis areas and n is a positive integer larger than 3;
S2, comparing the analysis subset i with a corresponding picture area of a standard picture of the electronic product, and judging whether the corresponding picture area of the analysis subset i has corresponding appearance defects through comparison analysis, wherein appearance defect items required to be compared and resolved by the electronic product mainly comprise cracks, scratches, pits, rust dirt and the like; if the analysis subset i is consistent with the appearance of the corresponding picture area of the standard picture of the electronic product, judging that the corresponding analysis subset i has small appearance visual defects, namely the picture area corresponding to the corresponding analysis subset i is normal, and marking the corresponding analysis subset i as a defect-free subset;
If the appearance of the picture area corresponding to the analysis subset i is inconsistent with that of the picture area corresponding to the standard picture of the electronic product, judging that the appearance visual defect of the corresponding analysis subset i is likely to be high, namely, the picture area corresponding to the corresponding analysis subset i is abnormal, and marking the corresponding analysis subset i as a defect subset; it should be noted that, the more the number of defect subsets in the visual inspection picture of the corresponding electronic product is, the worse the visual inspection result of the corresponding electronic product is represented, and the worse the appearance effect and quality of the corresponding electronic product are;
Step S3, obtaining all defect subsets and all defect subsets in the corresponding electronic product visual inspection picture, and marking the corresponding electronic product as a superior product if the defect subsets do not exist in the corresponding electronic product visual inspection picture, which indicates that the appearance of the corresponding electronic product is normal; otherwise, obtaining the number of defect-free subsets and the number of defect subsets in the corresponding electronic product visual inspection picture and marking the defect-free subsets as WQ and QX respectively; wq+qx=n;
Through a ratio formula Calculating the ratio of the number of defect subsets to obtain a product defect coefficient CQx; wherein trf is a pre-correction factor for correcting the formula result, and the value of trf is greater than 0.5 and less than 1, preferably, the value of trf is 0.837; it should be noted that, the larger the numerical value of the product defect coefficient CQx is, the worse the appearance effect and quality of the corresponding electronic product are indicated;
and S4, a preset product defect coefficient range is called through a data storage module, the product defect coefficient CQx is compared with the preset product defect coefficient range in numerical value, if the product defect coefficient CQx is larger than or equal to the maximum value of the preset product defect coefficient range, the corresponding electronic product is marked as a first-level defect product, if the product defect coefficient CQx is positioned in the preset product defect coefficient range, the corresponding electronic product is marked as a second-level defect product, and if the product defect coefficient CQx is smaller than or equal to the minimum value of the preset product defect coefficient range, the corresponding electronic product is marked as a third-level defect product.
It should be noted that, the appearance defect degree of the first-level defect product is greater than the appearance defect degree of the second-level defect product, the appearance defect degree of the second-level defect product is greater than the appearance defect degree of the third-level defect product, the appearance defect degree of the third-level defect product is greater than the quality product, and the data storage module performs data storage on the grading information of the electronic product.
The electronic product visual analysis module performs visual analysis on the corresponding electronic product and marks the electronic product as a superior product, a primary defect product, a secondary defect product or a tertiary defect product, and transmits grading information of the corresponding electronic product to the server, so that visual analysis on the electronic product is realized, an analysis result is more accurate, grading of the appearance effect and quality of the electronic product is realized, and subsequent processing on related electronic products is facilitated; preferably, the electronic product visual detection equipment conveys electronic products of different grades out through different conveying channels, so that classified conveying of the electronic products is realized, and operators are facilitated to carry out corresponding processing on related electronic products.
In the visual detection process of the electronic product, the environment interference monitoring module judges whether the corresponding detection environment is normal or not through environment interference analysis, and the specific analysis process of the environment interference analysis is as follows:
Step M1, acquiring a product detection area corresponding to the electronic product visual detection equipment and marking the product detection area as an analysis area, acquiring the temperature WD and the humidity SD of the analysis area corresponding to the detection period, acquiring a preset proper temperature range (W1, W2) and a preset proper humidity range (D1, D2) through a data storage module, carrying out average value calculation on the maximum value W2 and the minimum value W1 of the preset proper temperature range to acquire a preset medium temperature value ZW, carrying out difference value calculation on the temperature of the corresponding analysis area and the preset medium temperature value, acquiring absolute value to acquire temperature data HG, namely HG= |WD- (W1+W2)/2|, and acquiring humidity data SG in the same way;
Numerical calculation is carried out by substituting temperature data HG and humidity data SG of a corresponding analysis area through a formula WS=a1+a2, and temperature and humidity performance data WS of the corresponding analysis area is obtained after the numerical calculation; wherein a1 and a2 are preset weight coefficients, the values of a1 and a2 are both larger than zero, and a1 is larger than a2; the larger the value of the temperature and humidity performance data WS is, the larger the deviation degree of the actual temperature and humidity condition of the analysis area of the visual detection equipment of the corresponding electronic product is compared with the preset detection suitable temperature and humidity environment, and the product detection is more unfavorable;
Step M2, obtaining a luminance value LD and a dust concentration value FD of a corresponding analysis area, wherein the ambient luminance condition and the dust concentration condition directly affect the definition of the collected picture, and calling a preset proper luminance range (L1, L2) through a data storage module, and performing average calculation on a maximum value L2 and a minimum value L1 of the preset proper luminance range to obtain luminance data LS, namely ls= |ld- (l1+l2)/2|;
Calculating the numerical value by using the formula HT=a3+a4, substituting the brightness data LS and the dust concentration value FD, and obtaining the ring transmission performance data HT of the analysis area corresponding to the electronic product visual detection equipment corresponding to the detection period through the numerical value calculation; wherein a3 and a4 are preset weight coefficients, the values of a3 and a4 are both larger than zero, and a3 is larger than a4;
M3, obtaining a vibration frequency value ZP and a vibration amplitude value ZF of a product bearing part corresponding to the analysis area equipment, wherein the vibration frequency value ZP is a data value representing the average vibration frequency of the detection period, and the vibration amplitude value ZF is a data value representing the average vibration amplitude of the detection period;
Numerical calculation is performed by substituting the vibration frequency value ZP and the vibration amplitude value ZF through the formula hz=a5×zp+a6×zf; obtaining environmental vibration data HZ of a corresponding analysis area after numerical calculation, wherein a5 and a6 are preset weight coefficients, the values of a5 and a6 are both larger than zero, and a5 is larger than a6;
M4, carrying out numerical calculation on the temperature and humidity performance data WS, the ring transmission performance data HT and the environmental vibration data HZ through an environmental interference analysis formula, and obtaining an environmental interference coefficient GRx of an analysis area corresponding to the electronic product visual detection equipment corresponding to the detection period after the numerical calculation;
And M5, calling a preset environmental interference coefficient threshold value through the data storage module, comparing the environmental interference coefficient with the preset environmental interference coefficient threshold value, judging that the environmental interference degree of the analysis area of the visual inspection equipment of the corresponding electronic product is small and generating an environmental interference qualified signal if the environmental interference coefficient is smaller than or equal to the preset environmental interference coefficient threshold value, and judging that the environmental interference degree of the analysis area of the visual inspection equipment of the corresponding electronic product is large and generating an environmental interference unqualified signal if the environmental interference coefficient is larger than the preset environmental interference coefficient threshold value.
The environment interference monitoring module is used for carrying out environment interference analysis and generating an environment interference qualified signal or an environment interference unqualified signal, the environment interference qualified signal or the environment interference unqualified signal is sent to the server, the server is used for generating an environment interference early warning signal and sending the environment interference early warning signal to the monitoring terminal when receiving the environment drying unqualified signal, and monitoring personnel of the monitoring terminal should correspondingly adjust the detection environment of the electronic product visual detection device according to the requirement when receiving the environment interference early warning, so that the detection process can be continuously carried out in a stable and favorable environment, smooth operation of the visual detection process is ensured, accuracy of visual detection results is ensured, and adverse effects of the detection environment on the detection effect and efficiency of the electronic product are reduced.
The electronic product batch feedback module performs batch effect analysis after the detection of the electronic products in the corresponding batch is finished, and the specific analysis process of the batch effect analysis is as follows:
Acquiring grading information of all detected electronic products in the electronic products of the corresponding batch, counting the number of the superior products, the number of the primary defect products, the number of the secondary defect products and the number of the tertiary defect products in the electronic products of the corresponding batch, and marking the number of the superior products, the number of the primary defect products, the number of the secondary defect products and the number of the tertiary defect products in the electronic products of the corresponding batch as YM, QM, EM, SM respectively;
By the formula Substituting the number of the superior products YM, the number of the primary defective products QM, the number of the secondary defective products EM and the number of the tertiary defective products SM for numerical calculation, and obtaining a batch representation value PBz of the electronic products of the corresponding batch after the numerical calculation; wherein, tu1, tu2, tu3 and tu4 are preset proportionality coefficients, the values of tu1, tu2, tu3 and tu4 are all more than 1, and tu2 > tu3 > tu4 > tu1;
It should be noted that, the numerical value of the batch representation value PBz is in a direct proportion relation with the number of superior products YM, and in an inverse proportion relation with the number of primary defective products QM, the number of secondary defective products EM and the number of tertiary defective products SM, the larger the numerical value of the batch representation value PBz is, the better the overall appearance effect and the overall quality of the electronic products of the corresponding batch are indicated;
The method comprises the steps of calling a preset batch expression range through a data storage module, comparing a batch expression value PBz with the preset batch expression range in a numerical mode, marking the corresponding batch as an equal batch if the batch expression value PBz is larger than or equal to the maximum value of the preset batch expression range, marking the corresponding batch as an equal batch if the batch expression value PBz is in the preset batch expression range, marking the corresponding batch as an equal batch if the batch expression value PBz is smaller than or equal to the minimum value of the preset batch expression range, and marking the corresponding batch as a three-equal batch.
And after the detection of the electronic products in the corresponding batches is finished, carrying out batch effect analysis by the electronic product batch feedback module, marking the corresponding batches as first-class batches, second-class batches or third-class batches, sending the marking information of the corresponding batches and the corresponding batches to the supervision terminal through the server, wherein the supervision terminal does not need to carry out relevant feedback when receiving the first-class batches, can selectively strengthen the management and training of operators of the electronic product processing procedures related to the corresponding batches when receiving the second-class batches, and strengthen the equipment management and personnel training of the electronic product processing procedures related to the corresponding batches when receiving the third-class batches, and carry out maintenance and overhaul on relevant equipment of the related electronic product processing procedures, thereby being beneficial to guaranteeing the quality of the electronic products processed subsequently.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
Embodiment two:
As shown in fig. 3, the difference between the present embodiment and embodiment 1 is that the server is communicatively connected to the device state analysis module, and the device state analysis module performs periodic state analysis on the electronic product visual detection devices within the supervision range, and determines that the corresponding electronic product visual detection devices are qualified in periodic detection or unqualified in periodic detection through the periodic state analysis; the cycle state analysis process is specifically as follows:
The method comprises the steps of obtaining electronic product visual detection equipment in a supervision range, marking the electronic product visual detection equipment as an analysis object g, g=1, 2, …, k, wherein k represents the number of the electronic product visual detection equipment and k is a positive integer greater than 3; setting a device state analysis period, obtaining the number of the electronic products detected by the corresponding analysis object g in the device state analysis period, and marking the number as a period detection coefficient ZJg;
The method comprises the steps of calling a preset cycle check coefficient threshold value through a data storage module, comparing the cycle check coefficient ZJg with the preset cycle check coefficient threshold value in a numerical mode, judging that the cycle detection of a corresponding analysis object g is qualified if the cycle check coefficient ZJg is larger than or equal to the preset cycle check coefficient threshold value, and judging that the cycle detection of the corresponding analysis object g is unqualified if the cycle check coefficient ZJg is smaller than the preset cycle check coefficient threshold value;
if the analysis object g with unqualified periodic detection exists, generating a unqualified periodic detection signal, and sending the unqualified periodic detection signal and the corresponding analysis object g to a supervision terminal through a server, wherein supervision personnel of the supervision terminal should maintain and overhaul corresponding electronic product visual detection equipment in time so as to ensure that the detection efficiency of the subsequent corresponding electronic product visual detection equipment is stably improved;
if no analysis object g with unqualified period detection exists, obtaining period detection quantity coefficients ZJg of all the analysis objects g, establishing a period detection quantity set of period detection quantity coefficients ZJg of all the analysis objects g, performing variance calculation on the period detection quantity set to obtain an equipment efficiency difference coefficient SX, calling a preset efficiency difference coefficient threshold through a data storage module, and performing numerical comparison on the equipment efficiency difference coefficient SX and the preset efficiency difference coefficient threshold; it should be noted that, the numerical value of the equipment efficiency difference coefficient SX reflects the difference condition of the detection efficiency between all the electronic product visual detection equipment in the supervision range, and the larger the numerical value of the equipment efficiency difference coefficient SX is, the larger the difference of the detection efficiency between each group of electronic product visual detection equipment is;
If the equipment efficiency difference coefficient is larger than or equal to a preset efficiency difference coefficient threshold value, generating an equipment efficiency difference unqualified signal, if the equipment efficiency difference coefficient is smaller than the preset efficiency difference coefficient threshold value, generating an equipment efficiency difference qualified signal, sending the equipment efficiency difference qualified signal or the equipment efficiency difference unqualified signal to a supervision terminal through a server, and carrying out cause investigation in time and carrying out maintenance and overhaul on corresponding electronic product visual detection equipment according to requirements when supervision personnel of the supervision terminal receive the equipment efficiency difference unqualified signal so as to ensure that the detection efficiency of the subsequent corresponding electronic product visual detection equipment is stably improved.
Embodiment III:
as shown in fig. 3, the difference between the present embodiment and embodiments 1 and 2 is that the server is communicatively connected to the periodic uniformity detection module, the server generates a periodic uniformity analysis signal and sends the periodic uniformity analysis signal and the analysis object g qualified for corresponding periodic detection to the periodic uniformity detection module, the periodic uniformity detection module performs the periodic uniformity analysis on the analysis object g qualified for corresponding periodic detection after receiving the periodic uniformity analysis signal, and the specific analysis process of the periodic uniformity analysis is as follows:
Dividing the equipment state analysis period into a plurality of groups of analysis sub-periods, marking the analysis sub-periods as h, h=1, 2, …, j, j representing the number of the analysis sub-periods and j being a positive integer greater than 5; acquiring the number of the electronic products detected by the corresponding analysis equipment g in the analysis sub-period h, marking the number as a period detection coefficient SJgh, establishing a period detection set by using the period detection coefficients of all the analysis sub-periods of the corresponding analysis equipment g, and performing variance calculation on the period detection set of the corresponding analysis equipment g to acquire a period detection deviation value SPg of the corresponding analysis equipment g;
It should be noted that, the period detection amount deviation value SPg represents a data value of a uniformity condition of detection efficiency of the electronic product visual detection device in a device state analysis period, wherein the smaller the value of the period detection amount deviation value SPg is, the more stable the detection efficiency of the corresponding electronic product visual detection device in the device state analysis period is, and the better the uniformity of the detection efficiency is; otherwise, the larger the fluctuation of the detection efficiency of the corresponding electronic product visual detection equipment in the equipment state analysis period is, the worse the uniformity of the detection efficiency is;
and the data storage module is used for calling a preset period detection quantity deviation threshold value, the period detection quantity deviation value SPg is compared with the preset period detection quantity deviation threshold value in a numerical mode, if the period detection quantity deviation value SPg is larger than or equal to the preset period detection quantity deviation threshold value, the period uniformity of the corresponding analysis equipment g is judged to be unqualified and a period uniformity unqualified signal is generated, and if the period detection quantity deviation value SPg is smaller than the preset period detection quantity deviation threshold value, the period uniformity of the corresponding analysis equipment g is judged to be qualified and a period uniformity qualified signal is generated.
And the periodic uniformity detection module is used for carrying out periodic uniformity analysis on the analysis object g which is qualified in corresponding periodic detection, generating a periodic uniformity qualified signal or a periodic uniformity unqualified signal, sending the periodic uniformity qualified signal or the periodic uniformity unqualified signal and the corresponding analysis object g to the supervision terminal through the server, and carrying out continuous important attention on the corresponding electronic product visual detection equipment when the supervision personnel of the supervision terminal receive the periodic uniformity unqualified signal, carrying out cause investigation and judgment, and carrying out maintenance and overhaul on the corresponding electronic product visual detection equipment according to the need, thereby being beneficial to ensuring that the subsequent corresponding electronic product visual detection equipment can be stably detected.
When the electronic product visual analysis system is used, the electronic product visual analysis module is used for carrying out visual analysis on the corresponding electronic product and marking the electronic product as a superior product, a primary defect product, a secondary defect product or a tertiary defect product, so that the analysis result is more accurate, the classification of the appearance effect and the quality of the electronic product is realized, and the subsequent treatment of related electronic products is facilitated; the batch effect analysis is carried out after the detection of the electronic products in the corresponding batches is finished through the electronic product batch feedback module, and the corresponding batches and the corresponding batch marking information are sent to the supervision terminal through the server, so that the supervision personnel of the supervision terminal can master the batch quality of the electronic products in detail and can carry out corresponding management on operators and processing equipment of the corresponding electronic product processing procedures;
The environment interference monitoring module is used for carrying out environment interference analysis and generating an environment interference qualified signal or an environment interference unqualified signal in the detection process of the electronic product, the server is used for generating an environment interference early warning signal when receiving the environment drying unqualified signal, and a supervisory person of the supervision terminal is used for correspondingly adjusting the detection environment of the visual detection equipment of the electronic product according to the requirement when receiving the environment interference early warning, so that the detection process can be continuously carried out in a stable and favorable environment, and the adverse effect of the detection environment on the detection effect and efficiency of the electronic product is reduced; and the device state analysis module is used for carrying out periodic state analysis on the electronic product visual detection device in the supervision range, and the periodic uniformity detection module is used for carrying out periodic uniformity analysis on the analysis object qualified by the corresponding periodic detection, so that the supervision personnel can be helped to maintain and overhaul the related electronic product visual detection device, and the follow-up efficient and stable operation of the corresponding electronic product visual detection device is ensured.
Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (9)
1. The electronic product intelligent detection system based on the artificial intelligence is characterized by comprising an artificial intelligent detection analysis platform, wherein the artificial intelligent detection analysis platform comprises a server, a data storage module, an electronic product visual analysis module, an environment interference monitoring module, an electronic product batch feedback module and an equipment state analysis module;
The electronic product visual detection equipment is used for carrying out visual detection on the electronic product and sending the visual detection picture of the electronic product to the visual analysis module of the electronic product through the server; the electronic product visual analysis module is used for performing visual analysis on the corresponding electronic product, marking the corresponding electronic product as a superior product, a primary defect product, a secondary defect product or a tertiary defect product, and sending grading information of the corresponding electronic product to the server;
the environment interference monitoring module is used for judging whether the corresponding detection environment is normal or not through environment interference analysis and generating an environment interference qualified signal or an environment interference unqualified signal when the electronic product visual detection equipment detects the electronic product, and sending the environment interference qualified signal or the environment interference unqualified signal to the server; the method comprises the steps that when a server receives an environment drying disqualification signal, an environment interference early warning signal is generated and sent to a supervision terminal;
The electronic product batch feedback module is used for carrying out batch effect analysis after the detection of the electronic products in the corresponding batch is finished, marking the corresponding batch as an equal batch, a equal batch or a three-equal batch, and sending the corresponding batch and the marking information of the corresponding batch to the supervision terminal through the server; the device state analysis module is used for carrying out periodic state analysis on the electronic product visual detection devices in the supervision range, and judging whether the periodic detection of the corresponding electronic product visual detection devices is qualified or not according to the periodic state analysis;
The specific operation process of the electronic product vision analysis module comprises the following steps:
acquiring an electronic product visual detection picture sent by corresponding electronic product visual detection equipment, calling an electronic product standard picture through a data storage module, dividing the electronic product visual picture into a plurality of sub analysis areas and marking the sub analysis areas as analysis subsets i, i=1, 2, …, n, n represents the number of the sub analysis areas and n is a positive integer larger than 3;
Comparing the analysis subset i with the corresponding picture area of the electronic product standard picture, if the analysis subset i is consistent with the appearance of the corresponding picture area of the electronic product standard picture, judging that the corresponding analysis subset i has small appearance visual defects, and marking the corresponding analysis subset i as a defect-free subset; if the appearance of the analysis subset i is inconsistent with the appearance of the corresponding picture area of the electronic product standard picture, judging that the appearance visual defect of the corresponding analysis subset i is highly likely, and marking the corresponding analysis subset i as a defect subset;
Acquiring all defect-free subsets and all defect subsets in the corresponding electronic product visual inspection picture, marking the corresponding electronic product as a superior product if the defect subsets do not exist in the corresponding electronic product visual inspection picture, otherwise acquiring the number of the defect-free subsets and the number of the defect subsets in the corresponding electronic product visual inspection picture, and carrying out ratio calculation on the number of the defect subsets and the number of the defect-free subsets to acquire a product defect coefficient;
And (3) calling a preset product defect coefficient range through a data storage module, comparing the product defect coefficient with the preset product defect coefficient range in numerical value, marking the corresponding electronic product as a first-level defect product if the product defect coefficient is larger than or equal to the maximum value of the preset product defect coefficient range, marking the corresponding electronic product as a second-level defect product if the product defect coefficient is in the preset product defect coefficient range, and marking the corresponding electronic product as a third-level defect product if the product defect coefficient is smaller than or equal to the minimum value of the preset product defect coefficient range.
2. The intelligent electronic product detection system based on artificial intelligence according to claim 1, wherein the specific operation process of the electronic product batch feedback module comprises:
Obtaining grading information of all detected electronic products in the electronic products of the corresponding batch, counting the number of the superior products, the number of the primary defect products, the number of the secondary defect products and the number of the tertiary defect products in the electronic products of the corresponding batch, and carrying out numerical calculation on the number of the superior products, the number of the primary defect products, the number of the secondary defect products and the number of the tertiary defect products to obtain batch representation values of the electronic products of the corresponding batch;
And (3) calling a preset batch expression range through the data storage module, comparing the batch expression value with the preset batch expression range in a numerical mode, marking the corresponding batch as an equal-class batch if the batch expression value is larger than or equal to the maximum value of the preset batch expression range, marking the corresponding batch as an equal-class batch if the batch expression value is in the preset batch expression range, and marking the corresponding batch as a three-class batch if the batch expression value is smaller than or equal to the minimum value of the preset batch expression range.
3. The intelligent electronic product detection system based on artificial intelligence according to claim 2, wherein the specific operation process of the environmental interference monitoring module comprises:
Acquiring a product detection area corresponding to the electronic product visual detection equipment, marking the product detection area as an analysis area, acquiring temperature and humidity performance data, ring transmission performance data and environmental vibration data of the analysis area corresponding to the detection period, and carrying out numerical calculation on the temperature and humidity performance data, the ring transmission performance data and the environmental vibration data to acquire an environmental interference coefficient of the analysis area of the electronic product visual detection equipment corresponding to the detection period;
The method comprises the steps of calling a preset environmental interference coefficient threshold value through a data storage module, comparing the environmental interference coefficient with the preset environmental interference coefficient threshold value, judging that the environmental interference degree of the analysis area of the visual inspection equipment of the corresponding electronic product is small and generating an environmental interference qualified signal if the environmental interference coefficient is smaller than or equal to the preset environmental interference coefficient threshold value, and judging that the environmental interference degree of the analysis area of the visual inspection equipment of the corresponding electronic product is large and generating an environmental interference unqualified signal if the environmental interference coefficient is larger than the preset environmental interference coefficient threshold value.
4. The intelligent electronic product detection system based on artificial intelligence according to claim 3, wherein the specific analysis and acquisition method of the temperature and humidity performance data is as follows:
Acquiring the temperature and the humidity of a corresponding analysis area, calling a preset proper temperature range and a preset proper humidity range through a data storage module, carrying out average value calculation on the maximum value and the minimum value of the preset proper temperature range to acquire a preset medium temperature value, carrying out difference value calculation on the temperature of the corresponding analysis area and the preset medium temperature value, acquiring temperature data by taking an absolute value, acquiring humidity data in the same way, and carrying out numerical calculation on the temperature data and the humidity data of the corresponding analysis area to acquire temperature-humidity performance data;
The specific analysis and acquisition method of the ring transmission performance data and the environmental vibration data is as follows:
Acquiring a brightness value and a dust concentration value of a corresponding analysis area, calling a preset proper brightness range through a data storage module, carrying out mean value calculation on the maximum value and the minimum value of the preset proper brightness range to acquire brightness data, and carrying out numerical calculation on the brightness data and the dust concentration value to acquire ring penetration expression data; obtaining a vibration frequency value and a vibration amplitude value of a product bearing part corresponding to the analysis area equipment, and carrying out numerical calculation on the vibration frequency value and the vibration amplitude value to obtain environmental vibration data of the corresponding analysis area.
5. The intelligent electronic product detection system based on artificial intelligence according to claim 1, wherein the specific operation process of the device state analysis module comprises:
The method comprises the steps of obtaining electronic product visual detection equipment in a supervision range, marking the electronic product visual detection equipment as an analysis object g, g=1, 2, …, k, wherein k represents the number of the electronic product visual detection equipment and k is a positive integer greater than 3; setting a device state analysis period, obtaining the number of the electronic products detected by the corresponding analysis object g in the device state analysis period, and marking the number as a period detection coefficient;
and the data storage module is used for retrieving a preset period detection coefficient threshold value, carrying out numerical comparison on the period detection coefficient and the preset period detection coefficient threshold value, judging that the period detection of the corresponding analysis object g is qualified if the period detection coefficient is larger than or equal to the preset period detection coefficient threshold value, and judging that the period detection of the corresponding analysis object g is unqualified if the period detection coefficient is smaller than the preset period detection coefficient threshold value.
6. The intelligent electronic product detection system based on artificial intelligence according to claim 5, wherein if an analysis object g with unqualified periodic detection exists, a unqualified periodic detection signal is generated, and the unqualified periodic detection signal and the corresponding analysis object g are sent to a supervision terminal through a server; if the analysis objects g with unqualified period detection do not exist, performing equipment effect difference analysis on all the analysis objects g, generating equipment effect difference qualified signals or equipment effect difference unqualified signals, and sending the equipment effect difference qualified signals or the equipment effect difference unqualified signals to a supervision terminal through a server.
7. The intelligent electronic product detection system based on artificial intelligence according to claim 6, wherein the specific analysis process of the equipment efficiency difference analysis is as follows:
The method comprises the steps of obtaining periodic detection quantity coefficients of all analysis objects g, establishing periodic detection quantity sets of the periodic detection quantity coefficients of all analysis objects g, carrying out variance calculation on the periodic detection quantity sets to obtain equipment efficiency difference coefficients, calling a preset efficiency difference coefficient threshold value through a data storage module, carrying out numerical comparison on the equipment efficiency difference coefficients and the preset efficiency difference coefficient threshold value, generating equipment efficiency difference unqualified signals if the equipment efficiency difference coefficients are larger than or equal to the preset efficiency difference coefficient threshold value, and generating equipment efficiency difference qualified signals if the equipment efficiency difference coefficients are smaller than the preset efficiency difference coefficient threshold value.
8. The intelligent electronic product detection system based on artificial intelligence according to claim 6, wherein the server is communicatively connected to the periodic uniformity detection module, the server generates a periodic uniformity analysis signal and transmits the periodic uniformity analysis signal and the analysis object g corresponding to the periodic detection qualification to the periodic uniformity detection module, the periodic uniformity detection module performs periodic uniformity analysis on the analysis object g corresponding to the periodic detection qualification after receiving the periodic uniformity analysis signal, generates a periodic uniformity qualification signal or a periodic uniformity disqualification signal, and transmits the periodic uniformity qualification signal or the periodic uniformity disqualification signal and the analysis object g corresponding to the periodic uniformity qualification signal to the supervision terminal via the server.
9. The intelligent electronic product detection system based on artificial intelligence according to claim 8, wherein the specific analysis process of the cycle uniformity analysis is as follows:
Dividing the equipment state analysis period into a plurality of groups of analysis sub-periods, marking the analysis sub-periods as h, h=1, 2, …, j, j representing the number of the analysis sub-periods and j being a positive integer greater than 5; acquiring the number of the electronic products detected by the corresponding analysis equipment g in the analysis sub-period h, marking the number as a period detection coefficient, establishing a period detection set by using the period detection coefficients of all the analysis sub-periods of the corresponding analysis equipment g, and performing variance calculation on the period detection set of the corresponding analysis equipment g to acquire a period detection deviation value of the corresponding analysis equipment g;
and the data storage module is used for calling a preset period detection amount deviation threshold value, comparing the period detection amount deviation value with the preset period detection amount deviation threshold value in a numerical mode, judging that the period uniformity of the corresponding analysis equipment g is unqualified and generating a period uniformity unqualified signal if the period detection amount deviation value is larger than or equal to the preset period detection amount deviation threshold value, and judging that the period uniformity of the corresponding analysis equipment g is qualified and generating a period uniformity qualified signal if the period detection amount deviation value is smaller than the preset period detection amount deviation threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310162120.0A CN116309378B (en) | 2023-02-24 | 2023-02-24 | Electronic product intelligent detection system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310162120.0A CN116309378B (en) | 2023-02-24 | 2023-02-24 | Electronic product intelligent detection system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116309378A CN116309378A (en) | 2023-06-23 |
| CN116309378B true CN116309378B (en) | 2024-04-26 |
Family
ID=86829839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310162120.0A Active CN116309378B (en) | 2023-02-24 | 2023-02-24 | Electronic product intelligent detection system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309378B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117190887B (en) * | 2023-11-06 | 2024-01-30 | 深圳市磐锋精密技术有限公司 | Aerogel thickness automatic detection system for mobile phone production |
| CN117214650B (en) * | 2023-11-09 | 2024-01-26 | 深圳市美鸿电子有限公司 | Intelligent detection method and system for comprehensive performance of diode |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| CN113362575A (en) * | 2021-06-07 | 2021-09-07 | 中国地质大学（北京） | Mine environment intelligent monitoring system based on artificial intelligence |
| CN114627118A (en) * | 2022-05-13 | 2022-06-14 | 江苏裕荣光电科技有限公司 | Method and system for identifying insulation defects of optical fiber cable |
| CN114897825A (en) * | 2022-05-10 | 2022-08-12 | 曹占坡 | Solid wood floor sorting method and system based on computer vision |
| CN115393340A (en) * | 2022-09-06 | 2022-11-25 | 明瑞达(苏州)人工智能科技有限公司 | AI vision product quality detection system based on 5G algorithm |
| CN115528810A (en) * | 2022-09-28 | 2022-12-27 | 杭州集联科技有限公司 | Temperature measurement data operation, inspection, analysis and management system based on power equipment |
| WO2023279558A1 (en) * | 2021-07-09 | 2023-01-12 | 长鑫存储技术有限公司 | Defect detection method and apparatus, device and storage medium |
| CN115639207A (en) * | 2022-12-26 | 2023-01-24 | 广东省农业科学院设施农业研究所 | Machine vision detection method and system for simultaneously detecting multiple products |
-
2023
- 2023-02-24 CN CN202310162120.0A patent/CN116309378B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| CN113362575A (en) * | 2021-06-07 | 2021-09-07 | 中国地质大学（北京） | Mine environment intelligent monitoring system based on artificial intelligence |
| WO2023279558A1 (en) * | 2021-07-09 | 2023-01-12 | 长鑫存储技术有限公司 | Defect detection method and apparatus, device and storage medium |
| CN115661021A (en) * | 2021-07-09 | 2023-01-31 | 长鑫存储技术有限公司 | Defect detection method, device, equipment and storage medium |
| CN114897825A (en) * | 2022-05-10 | 2022-08-12 | 曹占坡 | Solid wood floor sorting method and system based on computer vision |
| CN114627118A (en) * | 2022-05-13 | 2022-06-14 | 江苏裕荣光电科技有限公司 | Method and system for identifying insulation defects of optical fiber cable |
| CN115393340A (en) * | 2022-09-06 | 2022-11-25 | 明瑞达(苏州)人工智能科技有限公司 | AI vision product quality detection system based on 5G algorithm |
| CN115528810A (en) * | 2022-09-28 | 2022-12-27 | 杭州集联科技有限公司 | Temperature measurement data operation, inspection, analysis and management system based on power equipment |
| CN115639207A (en) * | 2022-12-26 | 2023-01-24 | 广东省农业科学院设施农业研究所 | Machine vision detection method and system for simultaneously detecting multiple products |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116309378A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116309378B (en) | Electronic product intelligent detection system based on artificial intelligence | |
| CN107045863B (en) | The GTG method of adjustment and device of a kind of display panel | |
| US20240087104A1 (en) | Method for monitoring manufacture of assembly units | |
| CN116049863B (en) | System, method and application for generating stripe light by LCD display screen | |
| CN105609086A (en) | Brightness adjustment method and device of display interface | |
| CN116885858B (en) | Power distribution network fault processing method and system based on digital twin technology | |
| CN103913150B (en) | Intelligent electric energy meter electronic devices and components consistency detecting method | |
| CN114895634A (en) | Product production line automatic control system based on machine vision | |
| CN114858806A (en) | Cigarette quality inspection data analysis system and method | |
| CN114708584A (en) | Big data based cigarette product quality defect prevention and control learning system and method | |
| CN116165220B (en) | AOI (automated optical inspection) internal view detection device and method based on artificial intelligence | |
| CN111353713B (en) | Product quality authentication management system for factory production | |
| CN116578049B (en) | Digital transformation method based on industrial Internet | |
| US20230074247A1 (en) | Method for monitoring products for defects, electronic device, and storage medium | |
| CN116559713A (en) | Intelligent monitoring method and device for power supply of communication base station | |
| CN114445411A (en) | Unmanned aerial vehicle line patrol defect identification system and control method | |
| CN115456984A (en) | High-speed image recognition defect detection system based on two-dimensional code | |
| CN111028289B (en) | Method for positioning foreign matters in equipment in transformer substation based on template matching | |
| CN112949666B (en) | Image recognition method for fault cathode plate of zinc stripping machine | |
| CN113962924A (en) | Video monitoring quality evaluation method containing pan-tilt movement and mosaic detection | |
| CN111556106A (en) | Electric power online communication optimization system based on cloud computing | |
| CN116708633B (en) | Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis | |
| CN115809187B (en) | Method for processing waste products of frameless flat panel display based on big data screening | |
| CN110689058B (en) | AI algorithm-based environment detection method | |
| CN116245962B (en) | Data extraction system and method for wireless transmission to blockchain server |
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 |