CN110865087A - PCBA quality detection method based on artificial intelligence - Google Patents
PCBA quality detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN110865087A CN110865087A CN201911179923.7A CN201911179923A CN110865087A CN 110865087 A CN110865087 A CN 110865087A CN 201911179923 A CN201911179923 A CN 201911179923A CN 110865087 A CN110865087 A CN 110865087A
- Authority
- CN
- China
- Prior art keywords
- pcba
- data
- picture
- artificial intelligence
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- RVCKCEDKBVEEHL-UHFFFAOYSA-N 2,3,4,5,6-pentachlorobenzyl alcohol Chemical compound OCC1=C(Cl)C(Cl)=C(Cl)C(Cl)=C1Cl RVCKCEDKBVEEHL-UHFFFAOYSA-N 0.000 title claims abstract description 69
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 63
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 238000013135 deep learning Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000003860 storage Methods 0.000 claims abstract description 11
- 238000005516 engineering process Methods 0.000 claims description 19
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 claims description 18
- 230000007547 defect Effects 0.000 claims description 18
- 238000003466 welding Methods 0.000 claims description 7
- 239000011324 bead Substances 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 5
- -1 leakage paste Chemical compound 0.000 claims description 4
- 230000007306 turnover Effects 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000019771 cognition Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000013441 quality evaluation Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 230000008901 benefit Effects 0.000 abstract description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 150000003071 polychlorinated biphenyls Chemical class 0.000 description 1
- 238000005476 soldering Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
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
- G01N21/956—Inspecting patterns on the surface of objects
- G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/28—Testing of electronic circuits, e.g. by signal tracer
- G01R31/2801—Testing of printed circuits, backplanes, motherboards, hybrid circuits or carriers for multichip packages [MCP]
-
- 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
- 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
- G01N2021/95646—Soldering
-
- 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
- G01N2021/95661—Inspecting patterns on the surface of objects for PCB's for leads, e.g. position, curvature
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
A PCBA quality detection method based on artificial intelligence comprises a picture storage module and a marking module; the picture storage module is internally stored with a plurality of fault pictures of the PCBA, and the circuit board comprises fault pictures of open circuit, short circuit and the like of the copper-clad wire; the implementation method comprises the following steps: marking data by a marking module, matching qualified product picture data corresponding to the fault picture data in a one-to-one manner, and dividing the qualified product picture data into a training set and a test set; the second step is that: designing a proper artificial intelligence deep learning type; the third step: training the model; the fourth step: testing whether the model is correct or not by using the test set; the fifth step: testing PCBA specific fault data to be detected; and a sixth step: and continuously optimizing the empirical model. The AI model applied by the invention has self-adaptive learning capability, can still normally work under the condition of maintaining the capacity expansion of a production line, improves the productivity and has wide market application. The invention has the advantages of high detection speed and high precision, saves labor and improves the economic benefit of a production party.
Description
Technical Field
The invention relates to the technical field of detection, in particular to a PCBA quality detection method based on artificial intelligence.
Background
PCBA is a circuit board on which various electronic components are mounted by SMT (surface mount technology) and DIP (drilling technology). In the actual production of the existing manufacturer, the quality of the PCBA needs to be detected in order to ensure the product quality, and then whether the quality of the circuit board is in a problem or not and whether the position of an installed component is correct or not are judged. At present, one of the detection technologies for the PCBA is detection by manual visual inspection, and because the visual angle of a person is limited (for example, desoldering between small patch elements, polarity inversion and the like cannot be effectively observed), the detection speed is slow, the accuracy is not high, and the detection effect is not good, so that the mode is gradually used less and less. The other way is to judge through an AOI system (automatic optical detection, which is a device for detecting common defects encountered in welding production based on an optical principle); although the AOI system adopts an optical principle, uses an optical lens to replace human eyes, and performs image amplification in the shooting process, so as to obtain a relatively clear device image, the current AOI system has a defect that the method for judging whether a detection point is faulty is manually based on a standard digital image stored in the AOI system to compare and judge with an actually detected image, that is, manual visual comparison and detection are also needed, so that the defects of low detection speed, missing detection and low accuracy exist.
With the development of artificial intelligence technology, artificial intelligence deep learning methods are also applied to detection technology. In the prior art, the quality of electronic equipment is detected based on an artificial intelligence deep learning method, which is limited by technology, only the quality of parts with uncomplicated structure in a plane state can be detected, and the method is mainly used for detecting the appearance quality of a PCB (printed circuit board (PCB), i.e. a printed circuit board without various electronic parts, and the like, for example, detecting whether a copper-clad wire of the PCB has open circuit, short circuit and the like; because the PCB is not provided with elements and is in a flat state, and the number of detected items is small, the quality of the PCB can be detected by the conventional artificial intelligence deep learning method. In practical situations, a large number of electronic components are mounted on the PCBA, so that the content to be detected is not limited to detecting whether the copper-clad wire in a planar state has open circuit or short circuit, but also detecting whether electronic components in a three-dimensional state and different heights are soldered in a missing manner, are not mounted in place, are soldered in a weak manner, and the like; therefore, the quality of the PCBs can not be detected based on the artificial intelligence deep learning method, and the technology for detecting the PCBA quality based on the artificial intelligence deep learning method is blank.
Disclosure of Invention
In order to overcome the defects existing in the technology that an AOI system is adopted to detect the PCBA quality and the existing method for detecting the PCBA quality based on the artificial intelligence deep learning cannot be used for the PCBA quality detection, the invention provides the technology blank which can fill the technical blank of detecting the PCBA quality based on the artificial intelligence deep learning method, uses a large number of PCBA pictures as a picture database on the basis of obtaining product pictures by using the AOI system, introduces the artificial intelligence deep learning method, adopts the artificial intelligence humanoid brain neural network algorithm to realize that various quality problems of the PCBA and the like can still be accurately found under the conditions of interference and changeability, can cover main quality detection items of PCBA such as missed sticking, turned sticking, wrong sticking, side sticking, multi-sticking, tin bead, tin breaking, few tin, cold welding, virtual welding, short circuit, tombstone, offset, damage, reversed polarity, foreign matter, pin warping and the like, and can detect whether the circuit board has an open circuit, a copper wire or not by self, and can be detected, Appearance quality defects such as short circuit and the like, and a reasonable software framework is designed, so that the system has good capacity expansion and self-adaptive learning capabilities, and the PCBA quality detection method based on artificial intelligence is high in detection speed and detection precision, saves labor and improves economic benefits of a production party.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a PCBA quality detection method based on artificial intelligence is characterized by comprising a picture storage module and a marking module in a PC; PCBA including leakage paste, turnover paste, wrong paste, side paste, multiple paste, tin beads, tin break, less tin, cold welding, short circuit, tombstone, offset, damage, reversed polarity, foreign matters, pin warping and other fault pictures are stored in the picture storage module, and the circuit board comprises open circuit, short circuit and other fault pictures of copper-clad wires; the implementation method comprises the following steps: firstly, the characteristics of the known fault picture of the PCBA are based on an artificial intelligence deep learning technology, data labeling is carried out through a marking module, picture data of a qualified product corresponding to the fault picture data in a one-to-one mode are matched, and the data are divided into a training set and a testing set according to a certain proportion; the second step is that: designing a proper artificial intelligence deep learning type aiming at the PCBA fault picture characteristics based on an artificial intelligence deep learning technology; the third step: training the model by using the marked picture data; the fourth step: testing whether the generated demonstration model on the artificial intelligence platform based on artificial intelligence deep learning is correct or not by using a test set; the fifth step: when the PCBA is tested to be specific fault data, the picture to be tested is input into the model, and the model can automatically give out the data of the PCBA picture, so that a tester can visually judge whether the data of the PCBA picture is qualified or not according to the obtained data; and a sixth step: and continuously optimizing the demonstration model to form N perception cognition models based on faults, positioning, quality evaluation and the like of industrial picture imaging.
Furthermore, the picture storage module is stored with a large amount of picture characteristic data of known faults of the PCBA and picture characteristic data of qualified PCBA products which are in one-to-one correspondence with the faults.
Further, in the first step, the characteristics of the known fault picture of the PCBA are based on an artificial intelligence deep learning technology, and the fault data accumulation is better and better in the process of data marking through the marking module.
Further, in the first step, the training set and the test set have both fault data and qualified data of the PCBA picture.
Further, in the third step, the labeled picture data is the training set in the first step.
Furthermore, in the fifth step, when PCBA specific fault data to be detected is tested, the defect data can enter the AI center, the AI platform automatically learns and then generates an updated version, the model algorithm can be fed back to the AI end side, the AI end side is updated, in practical application, the defect data can be continuously increased, the AI end side algorithm can be continuously updated, and the detection accuracy is enhanced.
The invention has the beneficial effects that: the AI (artificial intelligence) model applied by the invention has self-adaptive learning capability, can still normally work under the condition of capacity expansion of a production line, greatly improves the production efficiency and has wide market application. The invention fills the technical blank of detecting the quality of the PCBA based on the artificial intelligence deep learning method, adopts a large number of PCBA pictures as a picture database on the basis of acquiring product pictures by using the AOI system, introduces the artificial intelligence based deep learning method (one type of machine learning), realizes the detection of the quality of the PCBA under the conditions of interference and changeability by using the artificial intelligence simulated human brain neural network algorithm, can still accurately find various quality problems of the PCBA and the like, can cover main fault detection items of leakage sticking, turnover sticking, wrong sticking, side sticking, multiple sticking, tin bead, tin breaking, little tin, cold welding, insufficient soldering, short circuit, tombstoning, deviation, damage, reversed polarity, foreign matter, pin tilting and the like of the PCBA, meanwhile, whether the circuit board has appearance quality defects such as open circuit, short circuit and the like including the copper-clad wire can be detected, and a reasonable software architecture is designed, so that the system has good capacity expansion and self-adaptive learning capacity. The invention has the advantages of high detection speed and high detection precision, saves labor and improves the economic benefit of a production party. Based on the above, the invention has good application prospect.
Drawings
The invention is further illustrated below with reference to the figures and examples.
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
As shown in fig. 1, a PCBA quality detection method based on artificial intelligence includes a picture storage module and a marking module in a PC; PCBA including leakage paste, turnover paste, wrong paste, side paste, multiple paste, tin beads, tin break, less tin, cold welding, short circuit, tombstone, offset, damage, reversed polarity, foreign matters, pin warping and other fault pictures are stored in the picture storage module, and the circuit board comprises open circuit, short circuit and other fault pictures of copper-clad wires; the picture storage module is stored with a large amount of picture characteristic data of known faults of the PCBA and picture characteristic data of qualified PCBA products which are in one-to-one correspondence with the faults. The implementation method comprises the following steps: firstly, the characteristics of the known fault picture of the PCBA are based on an artificial intelligence deep learning technology, data labeling is carried out through a marking module, picture data of a qualified product corresponding to the fault picture data in a one-to-one mode are matched, and the data are divided into a training set and a testing set according to a certain proportion; in the first step, the more and better the fault data accumulation is in the data marking process of the marking module based on the characteristics of the known fault picture of the PCBA on the basis of the artificial intelligence deep learning technology; in the first step, the training set and the test set simultaneously have fault data and qualified data of the PCBA picture. The second step is that: designing a proper artificial intelligence deep learning type aiming at the PCBA fault picture characteristics based on an artificial intelligence deep learning technology; the third step: training the model by using the marked picture data; in the third step, the labeled picture data is the training set in the first step. The fourth step: testing whether the generated demonstration model on the artificial intelligence platform based on artificial intelligence deep learning is correct or not by using a test set; the fifth step: when the PCBA is tested to be specific fault data, the picture to be tested is input into the model, and the model can automatically give out the data of the picture to be tested, so that a tester can visually judge whether the data of the picture to be tested is qualified (the pictures are not required to be compared one by one) according to the obtained data; and fifthly, when PCBA specific fault data to be detected is tested, the fault data can enter the AI center, the AI platform automatically learns and then generates an updated version, the model algorithm can be fed back to the AI end side to upgrade the AI end side, the defect data can be continuously increased in practical application, the AI end side algorithm can be continuously updated, and the detection accuracy is improved. And a sixth step: and continuously optimizing the demonstration model to form N perception cognition models based on faults, positioning, quality evaluation and the like of industrial picture imaging.
As shown in fig. 1, the AI (artificial intelligence) model applied in the present invention has adaptive learning capability, and can still work normally and greatly improve production efficiency under the condition of capacity expansion of the production line, and has wide market application. The invention fills the technical blank of detecting the quality of the PCBA based on the artificial intelligence deep learning method, adopts a large number of PCBA pictures as a picture database on the basis of acquiring product pictures by using an AOI system, introduces the artificial intelligence deep learning method (one type of machine learning), realizes that various quality problems of the PCBA and the like can still be accurately found under the condition of interference and changeability by using an artificial intelligence humanoid neural network algorithm, can cover main fault detection items of PCBA missing pasting, turning pasting, wrong pasting, side pasting, multi-pasting, tin bead, tin breaking, tin lacking, cold welding, virtual welding, short circuit, tombstoning, deviation, damage, reversed polarity, foreign matter, pin warping and the like, and can detect whether the circuit board has appearance quality defects of open circuit, short circuit and the like including a copper-coated wire. In the invention, the characteristic that the product defects can still be accurately found under the changeable condition is realized by using the convolution neural network algorithm based on artificial intelligence, the detection speed is high, the labor cost of a factory is reduced, the production efficiency is improved, the economic benefit is increased, and the root cause analysis of quality problems can be carried out and the yield is improved because an AI platform has defect data; and has reasonable software architecture, so that the system has good capacity expansion and self-adaptive learning capacity. The invention has good application prospect.
The following table is a detailed classification of the major defects of the PCBA and the analysis of the causes of the defects according to the present invention. With respect to the existing data, the defect pictures can be divided into more than one hundred types of commonly used 17 types of defects of the components, and the types are specifically divided as follows:
the PCBA picture quality detection technology adopted by the AI of the invention is a nondestructive detection mode which collects and analyzes picture signals containing information such as the state, the size and the process of an object to be detected, particularly defects and the like, and then utilizes an artificial intelligent algorithm to quickly and accurately realize fault identification, thereby being suitable for quality detection of PCBAs by various electronic manufacturers and having considerable market prospect.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (6)
1. A PCBA quality detection method based on artificial intelligence is characterized by comprising a picture storage module and a marking module in a PC; PCBA including leakage paste, turnover paste, error paste, side paste, multiple paste, tin bead, tin break, less tin, cold welding, short circuit, stele, offset, damage, reversed polarity, foreign matter and pin upwarp fault pictures are stored in the picture storage module, and the circuit board comprises copper-clad wire open circuit and short circuit fault pictures; the implementation method comprises the following steps: firstly, the characteristics of the known fault picture of the PCBA are based on an artificial intelligence deep learning technology, data labeling is carried out through a marking module, picture data of a qualified product corresponding to the fault picture data in a one-to-one mode are matched, and the data are divided into a training set and a testing set according to a certain proportion; the second step is that: designing a proper artificial intelligence deep learning type aiming at the PCBA fault picture characteristics based on an artificial intelligence deep learning technology; the third step: training the model by using the marked picture data; the fourth step: testing whether the generated demonstration model on the artificial intelligence platform based on artificial intelligence deep learning is correct or not by using a test set; the fifth step: when the PCBA is tested to be specific fault data, the picture to be tested is input into the model, and the model can automatically give out the data of the PCBA picture, so that a tester can visually judge whether the data of the PCBA picture is qualified or not according to the obtained data; and a sixth step: and continuously optimizing the demonstration model to form N models of fault, positioning and quality evaluation perception cognition based on industrial picture imaging.
2. The PCBA quality detection method based on artificial intelligence as recited in claim 1, wherein the picture storage module stores a plurality of picture characteristic data of known faults of the PCBA and picture characteristic data of qualified PCBA products corresponding to the faults in a one-to-one manner.
3. The PCBA quality detection method based on artificial intelligence as recited in claim 1, wherein in the first step, the characteristics of the known fault pictures of the PCBA are based on artificial intelligence deep learning technology, and the fault data accumulation is better and better in data labeling through a labeling module.
4. The PCBA quality detection method based on artificial intelligence as recited in claim 1, wherein in the first step, the training set and the test set have both PCBA picture failure data and qualified data.
5. The PCBA quality detection method based on artificial intelligence as recited in claim 1, wherein in the third step, the labeled picture data is the training set in the first step.
6. The PCBA quality detection method based on artificial intelligence as recited in claim 1, wherein in the fifth step, when the PCBA is tested to detect the fault data, the fault data enters the AI center, the AI platform automatically learns and then generates an updated version, the model algorithm can be fed back to the AI end side to upgrade the AI end side, in practical application, the defect data can be continuously increased, the AI end side algorithm can be continuously updated, and the detection accuracy is enhanced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911179923.7A CN110865087A (en) | 2019-11-27 | 2019-11-27 | PCBA quality detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911179923.7A CN110865087A (en) | 2019-11-27 | 2019-11-27 | PCBA quality detection method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110865087A true CN110865087A (en) | 2020-03-06 |
Family
ID=69656471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911179923.7A Pending CN110865087A (en) | 2019-11-27 | 2019-11-27 | PCBA quality detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110865087A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112730460A (en) * | 2020-12-08 | 2021-04-30 | 北京航天云路有限公司 | Welding defect and intensive rosin joint detection technology for communication IC chip |
| CN113591965A (en) * | 2021-07-26 | 2021-11-02 | 格力电器(南京)有限公司 | AOI detection image processing method and device, storage medium and computer equipment |
| CN114255231A (en) * | 2021-12-30 | 2022-03-29 | 南京晓庄学院 | PCBA gap detection method based on comparison of front and rear values |
| CN115713499A (en) * | 2022-11-08 | 2023-02-24 | 哈尔滨工业大学 | Quality detection method for surface mounted components |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5751910A (en) * | 1995-05-22 | 1998-05-12 | Eastman Kodak Company | Neural network solder paste inspection system |
| CN106651802A (en) * | 2016-12-24 | 2017-05-10 | 大连日佳电子有限公司 | Machine vision tin soldering location detection method |
| CN109738455A (en) * | 2019-02-28 | 2019-05-10 | 燊赛(上海)智能科技有限公司 | A kind of packaging belt detection system and interaction control method based on deep learning |
| CN109859164A (en) * | 2018-12-21 | 2019-06-07 | 苏州绿控传动科技股份有限公司 | A method of by Quick-type convolutional neural networks to PCBA appearance test |
| CN109886590A (en) * | 2019-02-28 | 2019-06-14 | 燊赛(上海)智能科技有限公司 | A kind of product package quality detection system based on deep learning |
| CN110473170A (en) * | 2019-07-10 | 2019-11-19 | 苏州卓融新能源科技有限公司 | A kind of artificial intelligence detection method suitable for the true and false determining defects of pcb board |
-
2019
- 2019-11-27 CN CN201911179923.7A patent/CN110865087A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5751910A (en) * | 1995-05-22 | 1998-05-12 | Eastman Kodak Company | Neural network solder paste inspection system |
| CN106651802A (en) * | 2016-12-24 | 2017-05-10 | 大连日佳电子有限公司 | Machine vision tin soldering location detection method |
| CN109859164A (en) * | 2018-12-21 | 2019-06-07 | 苏州绿控传动科技股份有限公司 | A method of by Quick-type convolutional neural networks to PCBA appearance test |
| CN109738455A (en) * | 2019-02-28 | 2019-05-10 | 燊赛(上海)智能科技有限公司 | A kind of packaging belt detection system and interaction control method based on deep learning |
| CN109886590A (en) * | 2019-02-28 | 2019-06-14 | 燊赛(上海)智能科技有限公司 | A kind of product package quality detection system based on deep learning |
| CN110473170A (en) * | 2019-07-10 | 2019-11-19 | 苏州卓融新能源科技有限公司 | A kind of artificial intelligence detection method suitable for the true and false determining defects of pcb board |
Non-Patent Citations (1)
| Title |
|---|
| 谷斌 等: "书籍《数据仓库与数据挖掘实物》", 31 August 2014, 北京邮电大学出版社, pages: 147 - 150 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112730460A (en) * | 2020-12-08 | 2021-04-30 | 北京航天云路有限公司 | Welding defect and intensive rosin joint detection technology for communication IC chip |
| CN113591965A (en) * | 2021-07-26 | 2021-11-02 | 格力电器(南京)有限公司 | AOI detection image processing method and device, storage medium and computer equipment |
| CN114255231A (en) * | 2021-12-30 | 2022-03-29 | 南京晓庄学院 | PCBA gap detection method based on comparison of front and rear values |
| CN115713499A (en) * | 2022-11-08 | 2023-02-24 | 哈尔滨工业大学 | Quality detection method for surface mounted components |
| CN115713499B (en) * | 2022-11-08 | 2023-07-14 | 哈尔滨工业大学 | Quality detection method for mounted patch element |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110865087A (en) | PCBA quality detection method based on artificial intelligence | |
| CN1318839C (en) | Automatic optical detecting system for blemish assembly on printed circuit board | |
| CN111915604A (en) | Internet artificial intelligence electron accessories discernment and detecting system | |
| CN104730078A (en) | Thermal infrared imager-based AOI circuit board detection method | |
| CN113344929B (en) | Welding spot visual detection and identification method, readable storage medium and equipment | |
| CN206038549U (en) | SMT production real -time management system | |
| CN113409250A (en) | Solder joint detection method based on convolutional neural network | |
| CN104568985A (en) | AOI (automatic optic inspection) equipment | |
| CN107271447A (en) | A kind of PLC outward appearances and LED status detection means based on machine vision | |
| CN111443509A (en) | Method for detecting L CD liquid crystal screen black and white spots and flicker defects | |
| CN117269731A (en) | PCBA performance automatic test system based on Internet of things | |
| CN112718552A (en) | Automatic quality defect inspection device for LED circuit board and working method thereof | |
| CN107346641B (en) | Manufacturing method of large display screen photoelectric glass | |
| US7134599B2 (en) | Circuit board inspection apparatus | |
| CN111899248A (en) | Automatic PCB soldering paste defect detection method based on machine learning | |
| CN106526448A (en) | Automatic detecting system and detection method for power supply drive board | |
| CN114965481B (en) | Automatic optical detection defect detection method, system and equipment | |
| CN109634005A (en) | Method for repairing and mending in array substrate manufacturing process | |
| CN112102252B (en) | Method and device for detecting appearance defects of welding spots of microstrip antenna | |
| CN115546140A (en) | Display panel detection method and system and electronic device | |
| CN103424407B (en) | Auxiliary alignment method and system for object to be tested | |
| CN110231351A (en) | AOI detection method | |
| CN113933309A (en) | Method for retesting defects in blind hole by AOI machine | |
| CN113034496A (en) | PCB testing system | |
| CN209992413U (en) | Automatic optical detection device |
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: 20200306 |