CN110455822A - A kind of detection method of pcb board defect - Google Patents

A kind of detection method of pcb board defect Download PDF

Info

Publication number
CN110455822A
CN110455822A CN201910622093.4A CN201910622093A CN110455822A CN 110455822 A CN110455822 A CN 110455822A CN 201910622093 A CN201910622093 A CN 201910622093A CN 110455822 A CN110455822 A CN 110455822A
Authority
CN
China
Prior art keywords
defect
picture
information
detection
pcb board
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
Application number
CN201910622093.4A
Other languages
Chinese (zh)
Inventor
李延奇
盛宇清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SUZHOU ZHUORONG NEW ENERGY TECHNOLOGY Co Ltd
Original Assignee
SUZHOU ZHUORONG NEW ENERGY TECHNOLOGY Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by SUZHOU ZHUORONG NEW ENERGY TECHNOLOGY Co Ltd filed Critical SUZHOU ZHUORONG NEW ENERGY TECHNOLOGY Co Ltd
Priority to CN201910622093.4A priority Critical patent/CN110455822A/en
Publication of CN110455822A publication Critical patent/CN110455822A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956—Inspecting patterns on the surface of objects
    • G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/55—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • 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
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956—Inspecting patterns on the surface of objects
    • G01N2021/95638—Inspecting patterns on the surface of objects for PCB's
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30141—Printed circuit board [PCB]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The present invention relates to a kind of detection methods of pcb board defect, include the following steps: the first step, Preliminary detection, capture of taking pictures is carried out to pcb board by AOI or AVI, and carry out samples pictures comparative analysis detection, it is positioned according to the modes output test result such as systematicness defect and non-rule property defect, and by output detection defect result according to coordinate, systematicness defect pictorial information is transferred to reinspection system later；Second step sentences the picture transfer of the irregularity defect part of calibration to AI artificial intelligence again, and AOI or AVI detection output defect picture is compared in artificial intelligence, judges true and false defect and defect type, the information of true defect is then transferred to reinspection system；Third step, reinspection system arrange artificial reinspection verification after receiving systematicness defect information and irregularity true defect information；The influence that AOI or AVI detection Artifact can be eliminated, reduces artificial nucleus' positive activity amount, improves detection efficiency and accuracy.

Description

A kind of detection method of pcb board defect
Technical field
The present invention relates to pcb board detection field more particularly to a kind of detection methods of pcb board defect.
Background technique
PCB industry mostly uses greatly AOI(appearance inspection machine at present) and AVI(optowire check machine) detected, still Using above-mentioned detection method carry out algorithm detection when, there is a problem of it is very much, only to systematicness template matching defect (repeat, Missing) it detects accurately, it for irregularity defect, such as opens a way, short circuit, residual copper, notch, inclined hole aoxidizes, flash, glass putty, tin Slag, consent wipe flower, hundreds of detection such as green oil the case where being easy to appear relatively large Artifact, it is therefore desirable to manually recheck into Row defect verification causes efficiency and accuracy low.
Summary of the invention
The object of the present invention is to provide a kind of detection methods of pcb board defect, cooperate AOI or AVI real using artificial intelligence Existing PCB defects detection can sentence again the AOI or AVI irregularity defect detected again, eliminate the shadow of Artifact It rings, reduces artificial verification workload, improve detection efficiency and accuracy.
In order to achieve the goal above, the technical solution adopted by the present invention are as follows: a kind of detection method of pcb board defect, including Following steps:
The first step, Preliminary detection carry out capture of taking pictures to pcb board by AOI or AVI, and carry out samples pictures contrasting detection, press According to systematicness defect and irregularity defect output test result, and by systematicness defect and irregularity defect according to coordinate into Rower is fixed, and the information of systematicness defect is transferred to reinspection system later；
Second step gives the picture transfer of the irregularity defect part of calibration to AI artificial intelligence, and artificial intelligence is by irregularity Defect picture is compared with the Test database that training is formed, and judges the true and false defect defect type of irregularity, then will be true The information of defect is transferred to reinspection system；
Third step, reinspection system arrange artificial reinspection core after receiving systematicness defect information and irregularity true defect information It is right, statistic op- timization is carried out to defective data, completes the defects detection of pcb board.
Preferably, in second step, AI artificial intelligence detect the step of it is as follows:
1., building and training AI model, the AI to classify according to defect is trained by the method for artificial intelligence deep learning Model；
2., artificial intelligence detection, AOI or AVI the defect picture detected are transferred to trained AI model, according to having trained Good AI model calculates the defect image data transmitted, judges true and false defect and defect type, and really lacking judgement It is trapped into capable classification；
3., result feedback, the true defect after classification is counted, and is expressed in a manner of information feedback, and is fed back To client.
Preferably, step 3. in information feedback system include but is not limited to form data, histogram information and sector diagram Information.
Preferably, the defect of AI model training will 1. step constructs and training AI model includes the following steps, 1), be used for Pcb board is fabricated to mark picture, forms training pictures, and be no less than a label according to a trained picture and be labeled, When carrying out label for labelling, classify according to the classification of defect, and form tranining database；2) it, is selected from tranining database The defective data of corresponding standard is taken, the model training collection of artificial intelligence detection is constituted；3), by model training collection be transmitted to AI model into Row training, and the AI model of the standard is generated, model database is stored in for calling.
Preferably, in step 1), when training picture making, defective pcb board is first fabricated to mark picture by the first step, Second step confines defect part with box or round frame in picture, and mixes corresponding label and be labeled, third step The picture pixels information that calibrated picture mark is saved using the format of including but not limited to XML, JSON, CSV, demarcates box Four co-ordinate position informations or calibration round frame centre coordinate location information, the road where defect type information, and corresponding picture Diameter information obtains label file, and the 4th step corresponds label file name prefix and picture file name prefix, completes training Data creating.
Preferably, in step 1), by label according to defect category classification after, for the other different defect ranks of same class Classification calibration is carried out again.
The invention has the benefit that
1, lacking for the two is compensated for the advantages of cooperating AOI or AVI to realize PCB defects detection using artificial intelligence, the former is utilized Point can sentence again the AOI or AVI irregularity defect detected again, eliminate the influence of Artifact, reduce artificial nucleus Positive activity amount improves detection efficiency and accuracy.
2, analysis is carried out using the big data of system output by AI artificial intelligence and exportable irregularity true defect is asked Statistical report form is inscribed, client can correspond to preceding processing procedure product processing procedure and quality for statistical report form content optimization, and can be according to difference Item number corresponds to report content and forms traceable data and classification problem picture, so that it is traceable to reach quality problem digitization.
3, when training picture carries out label calibration, classification processing is carried out to label, of a sort defect is made to constitute one Defective data group, database are made of multiple data groups, when in use, be can choose any number of data group and are carried out testing number According to the building in library, it can so be applicable in different manufacturers difference and the artificial intelligence of standard is required to detect, reduce Test database building Workload.
4, when pcb board defects detection, there are many small defect, and small defect accounts for the very little that the ratio of picture has, current PC B Plate is not confined target according to the method for convolutional neural networks Direct Classification, will cause very high defect leak rate and False Rate, and application documents confine target, can reduce defect leak rate and False Rate.
5, it after defect classification, is classified to defect, it, so can be with if burr can be divided with burr grade Different manufacturers demand is preferably adapted to, the wider array of artificial intelligence Test database of adaptability is constructed.
6, it after the completion of artificial intelligence model database, may be selected to execute AOI or AVI to samples pictures detection more stringent After standard, meeting output phase judges true and false defect to artificial intelligence AI to more defect pictures, can promote AOI or AVI tradition above Algorithm judgment accuracy.
Specific embodiment
In order to make those skilled in the art more fully understand technical solution of the present invention, the present invention is retouched in detail below State, the description of this part be only it is exemplary and explanatory, should not have any restriction effect to protection scope of the present invention.
Artificial intelligence detection model database is constructed first, the specific steps are as follows:
1, output after the detection of AVI, AOI equipment is first had the pcb board of true defect to be fabricated to by training picture and forming label, the first step Picture, second step carry out defect part box, circle to confine mark in picture, and mix corresponding labeling classification It is demarcated, third step saves the picture pixels for having demarcated picture mark using the format for including but is not limited to XML, JSON, CSV Information demarcates four co-ordinate position informations of box or round calibration information, the road where defect type information, and corresponding picture Diameter information obtains label file, and the 4th step corresponds label file name prefix and picture file name prefix, completes training Data are manufactured；
2, the training picture and label that selection is able to satisfy different clients demand are transmitted to AI model and are trained, and by multiple AI models Collection unifies a model database；
Label file includes the corresponding training of directory name (such as train_images file), the label file where training picture Picture name (such as defect .jpg), training picture path (such as C: Users admin Desktop train_images defect .jpg), picture pixels information (such as wide by 400, high by 400, bit depth 3), defect kind name (can be used any English alphabet to indicate defect Type can such as be indicated with S short circuit, N can be with indication notch), calibration frame top left co-ordinate position (such as x:142, y:118), Demarcate the length and width (such as w:179, h:160) of frame.
, can be there are many division mode during being grouped classification, for example be rigid requirement defect and non-rigid It is required that defect, says that rigid requirement defect uniformly divides a sorting group into, requires defect to be individually grouped and be classified for non-rigid, such as may be used The building of grouping classification based training database can preferably be played.
Embodiment 1
Only open-circuit, short circuit, residual copper, notch and inclined hole defect have standard requirements to first client, are directed to first client, a kind of pcb board The detection method of defect, includes the following steps:
The first step, Preliminary detection carry out capture of taking pictures to pcb board by AOI or AVI, and carry out samples pictures contrasting detection, press According to systematicness defect and irregularity defect output test result, and by systematicness defect and irregularity shape defect according to coordinate It is demarcated, the information of systematicness defect is transferred to reinspection system later；
Second step will recall about open circuit, short circuit, residual copper, notch, inclined hole and the data of oxidation in tranining database and be allowed to collect It closes, forms the training data of first client, training data is transmitted to AI model and is trained, and is trained suitable for first client's Artificial intelligence detects AI model；The AOI or AVI defect picture detected is transferred to the trained AI mould suitable for first client Type calculates the defect image data that transmits according to the AI model, judges true and false defect and defect type, and by judgement True defect is sorted out according to open circuit, short circuit, residual copper, notch and inclined hole；True defect after classification is counted, with table Mode shows, and table is fed back to reinspection system；
Third step, reinspection system arrange artificial reinspection after receiving regular shape defect information and the information of irregularity true defect, Statistic op- timization is carried out to defective data, completes the defects detection of pcb board,
Client can be for the corresponding preceding processing procedure product processing procedure of statistical table content optimization and quality, and can be corresponded to according to different item numbers Report content forms traceable data and classification problem picture, so that it is traceable to reach quality problem digitization.
Embodiment 2
Only open-circuit, short circuit, residual copper, notch, oxidation, scruff, consent and wiping flower defect have standard requirements to second client, are directed to second A kind of client, detection method of pcb board defect, includes the following steps:
The first step, Preliminary detection take pictures to pcb board by AOI or AVI, and carry out samples pictures contrasting detection, according to nothing Defect, systematicness defect and irregularity defect output test result, and by systematicness defect and irregularity shape defect according to Coordinate is demarcated, and the information of systematicness defect is transferred to reinspection system later；
Second step recalls the data in tranining database about open circuit, short circuit, residual copper, notch, scruff, consent and wiping flower simultaneously It is allowed to gather, forms the training data of first client, training data is transmitted to AI model and is trained, is trained suitable for second client Artificial intelligence detect AI model, AOI or AVI the defect picture detected are transferred to the trained AI suitable for second client Model calculates the defect image data transmitted according to the AI model, judges true and false defect and defect type, and will judgement True defect according to open circuit, short circuit, residual copper, notch, oxidation, scruff, consent and wipe flower defect sorted out；It will be true after classification Defect is counted, and is shown in a manner of histogram, and table is fed back to reinspection system；
Third step, reinspection system arrange artificial reinspection after receiving regular shape defect information and the information of irregularity true defect, Statistic op- timization is carried out to defective data, completes the defects detection of pcb board,
Processing procedure product processing procedure and quality before client can be corresponded to for statistics histogram content optimization, and can be according to different item numbers pair Report content is answered to form traceable data and classification problem picture, so that it is traceable to reach quality problem digitization.
Embodiment 3
The third client defect that only open-circuit, short circuit, residual copper, notch and flash defect reach 3 grades or more has standard requirements, for In the third client, a kind of detection method of pcb board defect includes the following steps:
The first step, Preliminary detection take pictures to pcb board by AOI or AVI, and carry out samples pictures contrasting detection, according to nothing Defect, systematicness defect and irregularity defect output test result, and by systematicness defect and irregularity shape defect according to Coordinate is demarcated, and the information of systematicness defect is transferred to reinspection system later；
Second step will reach 3 grades or more of defect about open circuit, short circuit, residual copper, notch and veining defect in tranining database It recalls and is allowed to gather, form the training data of the third client, training data is transmitted to AI model and is trained, trains and is suitable for The artificial intelligence of third client detects AI model；AOI or AVI the defect picture detected are transferred to and trained are suitable for the third visitor The AI model at family calculates the defect image data that transmits according to the AI model, judges true and false defect, and by the true of judgement Defect is sorted out according to open circuit, short circuit, residual copper, notch and flash, while the different defect ranks in same category being carried out Classification；By after classification true defect classification and grade count, with sector diagram display defect classification information, shown often with table The corresponding quantity information of different brackets is fed back to reinspection system in a classification；
Third step, reinspection system arrange artificial reinspection after receiving regular shape defect information and the information of irregularity true defect, Statistic op- timization is carried out to defective data, completes the defects detection of pcb board,
Processing procedure product processing procedure and quality before client can be corresponded to for statistics sector diagram and table content optimization, and can be according to difference Item number corresponds to report content and forms traceable data and classification problem picture, so that it is traceable to reach quality problem digitization.
Embodiment 4
Fourth client only open-circuit, short circuit, residual copper, notch, flash, glass putty reach 5 grades or more, scruff, consent reach 2 or more and The defect for wiping flower has standard requirements, is directed to fourth client, a kind of detection method of pcb board defect includes the following steps:
The first step, Preliminary detection take pictures to pcb board by AOI or AVI, and carry out samples pictures contrasting detection, according to nothing Defect, systematicness defect and irregularity defect output test result, and by systematicness defect and irregularity shape defect according to Coordinate is demarcated, and the information of systematicness defect is transferred to reinspection system later；
Second step will reach 5 grades or more, scruff, plug about open circuit, short circuit, residual copper, notch, flash, glass putty in tranining database The defect that hole reaches the defect of 2 or more and wiping flower recalls and is allowed to gather, and the training data of fourth client is formed, by training data It is transmitted to AI model to be trained, trains and detect AI model suitable for the artificial intelligence of fourth client；It is lacked what AOI or AVI was detected Picture transfer is fallen into the trained AI model suitable for fourth client, the defect picture transmitted is calculated according to the AI model Data judge true and false defect, and by the true defect of judgement according to open circuit, short circuit, residual copper, notch, flash, glass putty, scruff, plug Hole and wiping flower are sorted out, while the different defect ranks in same category being classified；By the true defect classification after classification And grade is counted, and with histogram display defect classification information, shows that different brackets is corresponding in each classification with sector diagram Quantity information is fed back to reinspection system；
Third step, reinspection system arrange artificial reinspection after receiving regular shape defect information and the information of irregularity true defect, Statistic op- timization is carried out to defective data, completes the defects detection of pcb board,
Processing procedure product processing procedure and quality before client can be corresponded to for statistics sector diagram and table content optimization, and can be according to difference Item number corresponds to report content and forms traceable data and classification problem picture, so that it is traceable to reach quality problem digitization.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row His property includes, so that the process, method, article or equipment for including a series of elements not only includes those elements, and And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic Element.
Used herein a specific example illustrates the principle and implementation of the invention, the explanation of above example Method and its core concept of the invention are merely used to help understand, the above is only a preferred embodiment of the present invention, are answered When pointing out due to the finiteness of literal expression, and objectively there is unlimited specific structure, for the common skill of the art For art personnel, without departing from the principle of the present invention, several improvement, retouching or variation can also be made, can also incited somebody to action Above-mentioned technical characteristic is combined in the right way；These improve retouching, variation or combination, or the not improved structure by invention Think and technical solution directly applies to other occasions, is regarded as protection scope of the present invention.

Claims (6)

1. a kind of detection method of pcb board defect, which comprises the steps of:
The first step, Preliminary detection carry out capture of taking pictures to pcb board by AOI or AVI, and carry out samples pictures contrasting detection, press According to systematicness defect and irregularity defect output test result, and by systematicness defect and irregularity defect according to coordinate into Rower is fixed, and the information of systematicness defect is transferred to reinspection system later；
Second step gives the picture transfer of the irregularity defect part of calibration to AI artificial intelligence, and artificial intelligence is by irregularity Defect picture is compared with the Test database that training is formed, and judges the true and false defect defect type of irregularity, then will be true The information of defect is transferred to reinspection system；
Third step, reinspection system arrange artificial reinspection core after receiving systematicness defect information and irregularity true defect information It is right, statistic op- timization is carried out to defective data, completes the defects detection of pcb board.
2. a kind of detection method of pcb board defect according to claim 1, which is characterized in that in second step, the artificial intelligence of AI The step of capable of detecting, is as follows:
1., building and training AI model, the AI to classify according to defect is trained by the method for artificial intelligence deep learning Model；
2., artificial intelligence detection, AOI or AVI the defect picture detected are transferred to trained AI model, according to having trained Good AI model calculates the defect image data transmitted, judges true and false defect and defect type, and really lacking judgement It is trapped into capable classification；
3., result feedback, the true defect after classification is counted, and is expressed in a manner of information feedback, and is fed back To client.
3. a kind of detection method of pcb board defect according to claim 2, which is characterized in that step 3. in information it is anti- Feedback mode includes but is not limited to form data, histogram information and sector diagram information.
4. a kind of detection method of pcb board defect according to claim 2, which is characterized in that 1. step constructs pattern number According to including the following steps for library, step 1. construct and training AI model include the following steps, 1), will be used for AI model training lack Sunken pcb board is fabricated to mark picture, forms training pictures, and be no less than a label according to a trained picture and marked Note, when carrying out label for labelling, classifies, and form tranining database according to the classification of defect；2), from tranining database The defective data for choosing corresponding standard, constitutes the model training collection of artificial intelligence detection；3) model training collection, is transmitted to AI model It is trained, and generates the AI model of the standard, be stored in model database for calling.
5. a kind of detection method of pcb board defect according to claim 4, which is characterized in that in step 1), training picture When production, in step 1), when training picture making, defective pcb board is first fabricated to mark picture by the first step, and second step exists Defect part is confined with box or round frame in picture, and mixes corresponding label and is labeled, third step, which uses, includes But the format for being not limited to XML, JSON, CSV saves the picture pixels information of calibrated picture mark, demarcates four coordinates of box Location information or calibration round frame centre coordinate location information, the routing information where defect type information, and corresponding picture, obtain To label file, the 4th step corresponds label file name prefix and picture file name prefix, completes training data production.
6. a kind of detection method of pcb board defect according to claim 4, which is characterized in that in step 1), label is pressed After defect category classification, classification calibration is carried out again for the other different defect ranks of same class.
CN201910622093.4A 2019-07-10 2019-07-10 A kind of detection method of pcb board defect Pending CN110455822A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910622093.4A CN110455822A (en) 2019-07-10 2019-07-10 A kind of detection method of pcb board defect

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910622093.4A CN110455822A (en) 2019-07-10 2019-07-10 A kind of detection method of pcb board defect

Publications (1)

Publication Number Publication Date
CN110455822A true CN110455822A (en) 2019-11-15

Family

ID=68482661

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910622093.4A Pending CN110455822A (en) 2019-07-10 2019-07-10 A kind of detection method of pcb board defect

Country Status (1)

Country Link
CN (1) CN110455822A (en)

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992333A (en) * 2019-11-29 2020-04-10 合肥奕斯伟材料技术有限公司 COF Film defect AITraining database and application
CN110990488A (en) * 2019-12-02 2020-04-10 东莞西尼自动化科技有限公司 Artificial intelligence sample graph management method based on database
CN111079564A (en) * 2019-11-27 2020-04-28 奥特斯科技(重庆)有限公司 Method for handling a component carrier, optical inspection apparatus and computer-readable medium
CN111179241A (en) * 2019-12-25 2020-05-19 成都数之联科技有限公司 Panel defect detection and classification method and system
CN111768371A (en) * 2020-06-05 2020-10-13 上海展华电子(南通)有限公司 AOI intelligent maintenance method and device, computer equipment and storage medium
CN111812118A (en) * 2020-06-24 2020-10-23 阿丘机器人科技(苏州)有限公司 PCB detection method, device, equipment and computer readable storage medium
CN111968084A (en) * 2020-08-08 2020-11-20 西北工业大学 Method for quickly and accurately identifying defects of aero-engine blade based on artificial intelligence
CN112017150A (en) * 2020-04-30 2020-12-01 河南爱比特科技有限公司 Intelligent visual detection method and equipment for surface defects of lithium ion battery pole piece
CN112669272A (en) * 2020-12-22 2021-04-16 广州广合科技股份有限公司 AOI rapid detection method and rapid detection system
CN112730434A (en) * 2020-12-26 2021-04-30 深圳市磐锋精密技术有限公司 Data monitoring method applied to AOI detection
CN112964737A (en) * 2021-02-04 2021-06-15 鼎勤科技(深圳)有限公司 Double-sided appearance detection method of circuit board
CN113012097A (en) * 2021-01-19 2021-06-22 富泰华工业（深圳）有限公司 Image rechecking method, computer device, and storage medium
CN113310997A (en) * 2021-07-30 2021-08-27 苏州维嘉科技股份有限公司 PCB defect confirmation method and device, automatic optical detection equipment and storage medium
CN113379686A (en) * 2021-05-26 2021-09-10 广东炬森智能装备有限公司 PCB defect detection method and device
CN113420853A (en) * 2021-06-17 2021-09-21 深圳森科智能系统技术有限公司 PCB detection, identification and positioning method and system
CN113516650A (en) * 2021-07-30 2021-10-19 深圳康微视觉技术有限公司 Circuit board hole plugging defect detection method and device based on deep learning
CN113538341A (en) * 2021-03-31 2021-10-22 联合汽车电子有限公司 Automatic optical detection auxiliary method, device and storage medium
JP2021180309A (en) * 2020-05-15 2021-11-18 清華大学Tsinghua University Two-dimensional pcb appearance defect real-time automatic detection technology based on deep learning
CN115239635A (en) * 2022-06-28 2022-10-25 苏州康代智能科技股份有限公司 PCB defect detection method, device, equipment and medium
CN115266744A (en) * 2022-06-17 2022-11-01 格力电器（武汉）有限公司 Detection system and method for product in production line

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003317082A (en) * 2002-04-25 2003-11-07 Dainippon Screen Mfg Co Ltd Classification assisting apparatus, classifying apparatus, and program
CN103926254A (en) * 2014-05-08 2014-07-16 康代影像科技(苏州)有限公司 Statistical system and method used for PCB defect detection
CN104359915A (en) * 2014-12-08 2015-02-18 合肥京东方光电科技有限公司 Coated glue detection method and device
CN104551301A (en) * 2014-12-30 2015-04-29 东莞市合易自动化科技有限公司 Full-automatic intelligent-welding assembly line
CN104867144A (en) * 2015-05-15 2015-08-26 广东工业大学 IC element solder joint defect detection method based on Gaussian mixture model
CN106530284A (en) * 2016-10-21 2017-03-22 广州视源电子科技股份有限公司 Welding spot type detection and device based on image recognition
CN107389701A (en) * 2017-08-22 2017-11-24 西北工业大学 A kind of PCB visual defects automatic checkout system and method based on image
CN108827970A (en) * 2018-03-28 2018-11-16 武汉精测电子集团股份有限公司 Adaptation different panels defect based on AOI system the methods of sentences automatically and system
CN108882543A (en) * 2018-10-17 2018-11-23 快克智能装备股份有限公司 A kind of automatic AOI repair welding system and method
CN109001230A (en) * 2018-05-28 2018-12-14 中兵国铁（广东）科技有限公司 Welding point defect detection method based on machine vision
CN109444172A (en) * 2018-12-13 2019-03-08 苏州卓融新能源科技有限公司 A kind of automatic optical detection device and its method suitable for artificial intelligence detection PCB
CN109540901A (en) * 2018-11-02 2019-03-29 英业达(重庆)有限公司 Automatic optics inspection flame feedback system and method
CN109919925A (en) * 2019-03-04 2019-06-21 联觉(深圳)科技有限公司 Printed circuit board intelligent detecting method, system, electronic device and storage medium
CN109936927A (en) * 2019-04-10 2019-06-25 奥蒂玛光学科技（深圳）有限公司 Circuit board renovation method and system
CN109934814A (en) * 2019-03-15 2019-06-25 英业达科技有限公司 Surface defect detecting system and its method

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003317082A (en) * 2002-04-25 2003-11-07 Dainippon Screen Mfg Co Ltd Classification assisting apparatus, classifying apparatus, and program
CN103926254A (en) * 2014-05-08 2014-07-16 康代影像科技(苏州)有限公司 Statistical system and method used for PCB defect detection
CN104359915A (en) * 2014-12-08 2015-02-18 合肥京东方光电科技有限公司 Coated glue detection method and device
CN104551301A (en) * 2014-12-30 2015-04-29 东莞市合易自动化科技有限公司 Full-automatic intelligent-welding assembly line
CN104867144A (en) * 2015-05-15 2015-08-26 广东工业大学 IC element solder joint defect detection method based on Gaussian mixture model
CN106530284A (en) * 2016-10-21 2017-03-22 广州视源电子科技股份有限公司 Welding spot type detection and device based on image recognition
CN107389701A (en) * 2017-08-22 2017-11-24 西北工业大学 A kind of PCB visual defects automatic checkout system and method based on image
CN108827970A (en) * 2018-03-28 2018-11-16 武汉精测电子集团股份有限公司 Adaptation different panels defect based on AOI system the methods of sentences automatically and system
CN109001230A (en) * 2018-05-28 2018-12-14 中兵国铁（广东）科技有限公司 Welding point defect detection method based on machine vision
CN108882543A (en) * 2018-10-17 2018-11-23 快克智能装备股份有限公司 A kind of automatic AOI repair welding system and method
CN109540901A (en) * 2018-11-02 2019-03-29 英业达(重庆)有限公司 Automatic optics inspection flame feedback system and method
CN109444172A (en) * 2018-12-13 2019-03-08 苏州卓融新能源科技有限公司 A kind of automatic optical detection device and its method suitable for artificial intelligence detection PCB
CN109919925A (en) * 2019-03-04 2019-06-21 联觉(深圳)科技有限公司 Printed circuit board intelligent detecting method, system, electronic device and storage medium
CN109934814A (en) * 2019-03-15 2019-06-25 英业达科技有限公司 Surface defect detecting system and its method
CN109936927A (en) * 2019-04-10 2019-06-25 奥蒂玛光学科技（深圳）有限公司 Circuit board renovation method and system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘国富主编: "《SMT设备操作与维护》", 31 August 2015, 北京理工大学出版社 *
卢荣胜 等: "自动光学(视觉)检测技术及其在缺陷检测中的应用综述", 《光学学报》 *
詹跃明: "《表面组装技术》", 30 September 2018, 重庆大学出版社 *

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111079564A (en) * 2019-11-27 2020-04-28 奥特斯科技(重庆)有限公司 Method for handling a component carrier, optical inspection apparatus and computer-readable medium
CN113378665A (en) * 2019-11-27 2021-09-10 奥特斯科技(重庆)有限公司 Method for handling a component carrier, optical inspection apparatus and computer-readable medium
CN111079564B (en) * 2019-11-27 2021-06-01 奥特斯科技(重庆)有限公司 Method for handling a component carrier, optical inspection apparatus and computer-readable medium
US11935221B2 (en) 2019-11-27 2024-03-19 AT&S (Chongqing) Company Limited User interface for judgment concerning quality classification of displayed arrays of component carriers
CN110992333A (en) * 2019-11-29 2020-04-10 合肥奕斯伟材料技术有限公司 COF Film defect AITraining database and application
CN110992333B (en) * 2019-11-29 2023-03-24 合肥颀材科技有限公司 COF Film defect AITraining database and application
CN110990488A (en) * 2019-12-02 2020-04-10 东莞西尼自动化科技有限公司 Artificial intelligence sample graph management method based on database
CN111179241A (en) * 2019-12-25 2020-05-19 成都数之联科技有限公司 Panel defect detection and classification method and system
CN112017150A (en) * 2020-04-30 2020-12-01 河南爱比特科技有限公司 Intelligent visual detection method and equipment for surface defects of lithium ion battery pole piece
JP7347836B2 (en) 2020-05-15 2023-09-20 清華大学 Real-time automatic detection method for 2D PCB appearance defects based on deep learning
TWI796681B (en) * 2020-05-15 2023-03-21 清華大學 A method for real-time automatic detection of two-dimensional PCB appearance defects based on deep learning
JP2021180309A (en) * 2020-05-15 2021-11-18 清華大学Tsinghua University Two-dimensional pcb appearance defect real-time automatic detection technology based on deep learning
CN111768371A (en) * 2020-06-05 2020-10-13 上海展华电子(南通)有限公司 AOI intelligent maintenance method and device, computer equipment and storage medium
CN111812118A (en) * 2020-06-24 2020-10-23 阿丘机器人科技(苏州)有限公司 PCB detection method, device, equipment and computer readable storage medium
CN111968084A (en) * 2020-08-08 2020-11-20 西北工业大学 Method for quickly and accurately identifying defects of aero-engine blade based on artificial intelligence
CN112669272A (en) * 2020-12-22 2021-04-16 广州广合科技股份有限公司 AOI rapid detection method and rapid detection system
CN112669272B (en) * 2020-12-22 2024-09-06 广州广合科技股份有限公司 AOI rapid detection method and rapid detection system
CN112730434B (en) * 2020-12-26 2021-10-29 深圳市磐锋精密技术有限公司 Data monitoring method applied to AOI detection
CN112730434A (en) * 2020-12-26 2021-04-30 深圳市磐锋精密技术有限公司 Data monitoring method applied to AOI detection
CN113012097A (en) * 2021-01-19 2021-06-22 富泰华工业（深圳）有限公司 Image rechecking method, computer device, and storage medium
TWI780580B (en) * 2021-01-19 2022-10-11 大陸商富泰華工業（深圳）有限公司 Image reinspection method, computer device, and storage medium
CN113012097B (en) * 2021-01-19 2023-12-29 富泰华工业（深圳）有限公司 Image rechecking method, computer device and storage medium
CN112964737A (en) * 2021-02-04 2021-06-15 鼎勤科技(深圳)有限公司 Double-sided appearance detection method of circuit board
CN113538341A (en) * 2021-03-31 2021-10-22 联合汽车电子有限公司 Automatic optical detection auxiliary method, device and storage medium
CN113538341B (en) * 2021-03-31 2024-04-30 联合汽车电子有限公司 Automatic optical detection assisting method, device and storage medium
CN113379686A (en) * 2021-05-26 2021-09-10 广东炬森智能装备有限公司 PCB defect detection method and device
CN113379686B (en) * 2021-05-26 2024-07-19 广东炬森智能装备有限公司 PCB defect detection method and device
CN113420853A (en) * 2021-06-17 2021-09-21 深圳森科智能系统技术有限公司 PCB detection, identification and positioning method and system
CN113516650B (en) * 2021-07-30 2023-08-25 深圳康微视觉技术有限公司 Circuit board hole plugging defect detection method and device based on deep learning
CN113310997A (en) * 2021-07-30 2021-08-27 苏州维嘉科技股份有限公司 PCB defect confirmation method and device, automatic optical detection equipment and storage medium
CN113516650A (en) * 2021-07-30 2021-10-19 深圳康微视觉技术有限公司 Circuit board hole plugging defect detection method and device based on deep learning
CN115266744A (en) * 2022-06-17 2022-11-01 格力电器（武汉）有限公司 Detection system and method for product in production line
CN115239635A (en) * 2022-06-28 2022-10-25 苏州康代智能科技股份有限公司 PCB defect detection method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN110455822A (en) A kind of detection method of pcb board defect
CN110473170A (en) A kind of artificial intelligence detection method suitable for the true and false determining defects of pcb board
CN109239102A (en) A kind of flexible circuit board open defect detection method based on CNN
CN108686978B (en) ARM-based fruit category and color sorting method and system
CN105588840B (en) Electronic component positioning method and device
CN109064454A (en) Product defects detection method and system
AU2023201724A1 (en) System for counting number of game tokens
CN108416765A (en) A kind of character defect automatic testing method and system
CN106127746A (en) Circuit board element missing part detection method and system
CN112651966A (en) Printed circuit board micro-defect detection method based on ACYOLOV4_ CSP
CN105334224B (en) Automate quality testing cloud platform
CN107886131A (en) One kind is based on convolutional neural networks detection circuit board element polarity method and apparatus
CN111103307A (en) Pcb defect detection method based on deep learning
CN110458196A (en) A kind of database construction method suitable for the detection of pcb board artificial intelligence
CN114066848A (en) FPCA appearance defect visual inspection system
CN105478364B (en) A kind of defective products detection classification method and system
CN116309427A (en) PCB surface defect detection method based on improved YOLOv5 algorithm
CN110940672A (en) Automatic generation method and device for intelligent optical detection sample characteristic and flaw AI model
CN112819780A (en) Method and system for detecting surface defects of silk ingots and silk ingot grading system
CN112907562A (en) MobileNet-based SMT defect classification algorithm
CN107633508A (en) One kind metering product printed substrate outward appearance verification method and system
CN114858806A (en) Cigarette quality inspection data analysis system and method
Melnyk et al. Contacts detection in PCB image by thinning, clustering and flood-filling
CN116580026B (en) Automatic optical detection method, equipment and storage medium for appearance defects of precision parts
CN109376738A (en) Altering detecting method based on vehicle VIN code start-stop symbol type

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20191115

RJ01 Rejection of invention patent application after publication