CN116343115B - PCB welding defect detection method - Google Patents
PCB welding defect detection method Download PDFInfo
- Publication number
- CN116343115B CN116343115B CN202310249014.6A CN202310249014A CN116343115B CN 116343115 B CN116343115 B CN 116343115B CN 202310249014 A CN202310249014 A CN 202310249014A CN 116343115 B CN116343115 B CN 116343115B
- Authority
- CN
- China
- Prior art keywords
- welding
- pcb
- defect
- images
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003466 welding Methods 0.000 title claims abstract description 374
- 230000007547 defect Effects 0.000 title claims abstract description 172
- 238000001514 detection method Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 229910000679 solder Inorganic materials 0.000 claims description 44
- 230000004907 flux Effects 0.000 claims description 26
- 239000003086 colorant Substances 0.000 claims description 17
- 230000002093 peripheral effect Effects 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 12
- RSWGJHLUYNHPMX-UHFFFAOYSA-N Abietic-Saeure Natural products C12CCC(C(C)C)=CC2=CCC2C1(C)CCCC2(C)C(O)=O RSWGJHLUYNHPMX-UHFFFAOYSA-N 0.000 claims description 10
- KHPCPRHQVVSZAH-HUOMCSJISA-N Rosin Natural products O(C/C=C/c1ccccc1)[C@H]1[C@H](O)[C@@H](O)[C@@H](O)[C@@H](CO)O1 KHPCPRHQVVSZAH-HUOMCSJISA-N 0.000 claims description 10
- KHPCPRHQVVSZAH-UHFFFAOYSA-N trans-cinnamyl beta-D-glucopyranoside Natural products OC1C(O)C(O)C(CO)OC1OCC=CC1=CC=CC=C1 KHPCPRHQVVSZAH-UHFFFAOYSA-N 0.000 claims description 10
- 239000002932 luster Substances 0.000 claims description 7
- 230000002950 deficient Effects 0.000 claims description 6
- 238000005476 soldering Methods 0.000 claims description 6
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 5
- 239000011889 copper foil Substances 0.000 claims description 5
- 230000007704 transition Effects 0.000 claims description 5
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 claims description 4
- 238000013021 overheating Methods 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 4
- 238000009825 accumulation Methods 0.000 description 6
- 239000002184 metal Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002893 slag Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—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
-
- 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
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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]
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a PCB welding defect detection method, which comprises the following steps of: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, and storing the information obtained by analysis and the corresponding PCB welding defect images in a database after the information is corresponding to the PCB welding defect images; the invention acquires images of defects with different problems and analyzes the images to obtain specific welding spot size and shape information, acquires the specific welding spot size and shape of the detected PCB welding, acquires similar defect images through information in the comparison process, performs depth comparison by combining the welding spot size and shape with image information, and finally compares the corresponding defect images with the welding spot size and shape, and displays the defect images and the welding spot size and shape through a display screen.
Description
Technical Field
The invention relates to the technical field of circuit board processing, in particular to a PCB welding defect detection method.
Background
The PCB, called a printed circuit board, is an important electronic component, is a support for electronic components, and is a carrier for electrical interconnection of electronic components. It is called a "printed" circuit board because it is made using electronic printing.
In order to ensure that the quality of the PCB needs to be detected for welding defects in the production link, the traditional detection mode is carried out through direct image comparison, and the defect of the welding of the PCB can be identified in the comparison process, but the specific situation of the defect of the PCB cannot be obtained, so that the circuit boards with the defects detected are inspected one by one, and the subsequent reworking efficiency is very influenced.
Therefore, a PCB welding defect detection method is provided to solve the problem.
Disclosure of Invention
The invention aims to provide a PCB welding defect detection method, which solves the problem that the existing PCB defect detection method cannot obtain the specific situation of defects of a PCB.
In order to achieve the above purpose, the present invention provides the following technical solutions: a PCB welding defect detection method comprises the following steps:
step 1: defect image acquisition: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, and storing the information obtained by analysis and the corresponding PCB welding defect images in a database after the information is corresponding to the PCB welding defect images;
step 2: and (3) collecting detected PCB images: collecting all welding position images of the detected PCB, wherein the collection of the welding images of the detected PCB comprises welding points of all welding positions, and the collection of single welding points is that the shape of four sides of the detected PCB, the area of the welding points and the color of the periphery of the welding points;
step 3: identifying a welding image: the method comprises the steps that an image recognition device is used for recognizing a collected image of a welding point of a detected PCB, the four side surfaces of the welding point are recognized, the welding area of the welding point and the peripheral welding color of the welding point are recognized, and specific welding information of the welding point of the detected PCB is obtained after the recognition is completed;
step 4: matching defects: inputting the obtained specific information of the welding of the detected PCB into a database, screening similar defect images in the database according to the obtained identification information of the welding point of the detected PCB, extracting the screened images, analyzing the corresponding information of the welding defect of the stored PCB defect images in advance, and matching the acquired PCB welding point images, and simultaneously extracting normal welding point welding images to wait for matching.
Preferably, in step 1, the welding defect information of the PCB defect image is analyzed, specifically, displayed in text form, specifically, the size and color of each image defect.
Preferably, in step 2, the PCB solder defect image includes dummy solder, solder build-up, solder overmuch, solder overlittle, rosin solder, and solder over heat.
Preferably, in step 2, the specific information of the PCB welding defect image includes the following steps that the virtual welding is that the solder and the lead of the component or the copper foil have obvious black boundary lines, the solder is sunken towards the boundary lines, defects exist in different colors, the solder is piled up, the welding spot structure is loose, white and matt, defects exist in different colors, and the solder is too many: the welding flux is convex, the side surface shape is different and has defects, the welding area is less than 80% of the welding pad, the welding flux does not form a smooth transition surface, the welding area is different and has defects, rosin residues are clamped in the welding seam, the welding color is different and has defects, and the welding spot is white, has no metallic luster and has defects in different colors.
Preferably, in step 3, the specific information of the identification device for identifying the collected detected PCB welding point image is that the specific size and color of the shape, area and color of the detected PCB welding point are displayed in the form of character shapes.
Preferably, in step 4, the screening of the database is performed by searching for the size and shape of the welding spot given by the inspected image and the size and shape of the specific welding spot analyzed by the defect image in the database, and extracting the welding spot.
Preferably, in step 4, the database is further screened to extract the PCB solder images and the defect images after comparing the PCB solder images and the defect images one by one in similarity.
Preferably, in step 4, when the shape of the four welding sides of the welding point of the detected PCB is matched with the shape of the defective welding image, an image overlapping algorithm is adopted to perform overlapping comparison, so as to obtain a welding height difference between the welding point of the detected PCB and the welding height difference between the defective image, and then the welding point sizes and shapes of the two images are compared, so that the similarity ratio of the two images is finally obtained.
Preferably, in step 4, the image area of the defective solder joint includes an image smaller than the normal solder area and an image larger than the normal solder area, and under the solder joint size and shape given by the normal solder image, the solder area of the inspected PCB solder joint is determined to be over-solder and less than 20% is determined to be under-solder.
Preferably, in step 4, when detecting the welding area of the detected PCB welding point, it is not necessary to perform image comparison, it can be determined whether there is a defect in the welding area of the detected PCB welding point directly through text comparison, and finally when matching the welding peripheral color of the detected PCB welding point, the color matching also adopts the size and shape comparison of the welding point, the peripheral color text of the detected PCB welding point and the welding peripheral color of the normal PCB welding point cannot be overlapped to directly determine as the defect welding, and then the comparison is performed on the analysis text of the corresponding image of the defect, thereby determining what kind of defect is specifically, and if the overlapping is qualified.
Compared with the prior art, the invention has the beneficial effects that:
the invention acquires images of defects with different problems and analyzes the images to obtain specific character size and color information, acquires specific welding spot size and shape of the detected PCB welding, acquires similar defect images through character or image information in the comparison process, performs depth comparison by combining the welding spot size and shape with the image information and the defect images, and finally compares the corresponding defect images with the welding spot size and shape to display through a display screen.
Detailed Description
The invention will now be described in more detail by way of examples which are illustrative only and are not intended to limit the scope of the invention in any way.
The invention provides a technical scheme that: a PCB welding defect detection method comprises the following steps:
step 1: defect image acquisition: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, and storing the information obtained by analysis and the corresponding PCB welding defect images in a database after the information is corresponding to the PCB welding defect images;
step 2: and (3) collecting detected PCB images: collecting all welding position images of the detected PCB, wherein the collection of the welding images of the detected PCB comprises welding points of all welding positions, and the collection of single welding points is that the shape of four sides of the detected PCB, the area of the welding points and the color of the periphery of the welding points;
step 3: identifying a welding image: the method comprises the steps that an image recognition device is used for recognizing a collected image of a welding point of a detected PCB, the four side surfaces of the welding point are recognized, the welding area of the welding point and the peripheral welding color of the welding point are recognized, and specific welding information of the welding point of the detected PCB is obtained after the recognition is completed;
step 4: matching defects: inputting the obtained specific information of the welding of the detected PCB into a database, screening similar defect images in the database according to the obtained identification information of the welding point of the detected PCB, extracting the screened images, analyzing the corresponding information of the welding defect of the stored PCB defect images in advance, and matching the acquired PCB welding point images, and simultaneously extracting normal welding point welding images to wait for matching.
Embodiment one:
defect image acquisition: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, correspondingly storing the information obtained by analysis and the corresponding PCB welding defect images in a database, and collecting detected PCB images: collecting all welding position images of the detected PCB, wherein the collection of the welding images of the detected PCB comprises welding points of all welding positions, and the collection of single welding points is that the welding images are identified by four side shapes of the detected PCB, the area of the welding points and the color of the periphery of the welding points: the method comprises the steps of identifying acquired detected PCB welding point images through an image identification device, identifying four side shapes, welding areas and peripheral welding colors of welding points, wherein the four side shapes, the welding areas and the peripheral welding colors of the welding points are formed by single welding point welding, obtaining specific welding information of the detected PCB welding points after the identification is completed, and matching defects: inputting the obtained specific information of the welding of the detected PCB into a database, screening similar defect images in the database according to the obtained identification information of the welding point of the detected PCB, extracting the screened images, analyzing the corresponding information of the welding defect of the stored PCB defect images in advance, and matching the acquired PCB welding point images, and simultaneously extracting normal welding point welding images to wait for matching.
Embodiment two:
in the first embodiment, the following steps are added:
in step 1, the welding defect information of the PCB defect image is analyzed, specifically, the welding defect information is displayed in a text form, specifically, the size and the color of each image defect.
In step 2, the PCB welding defect image comprises false soldering, solder accumulation, excessive solder, insufficient solder, rosin soldering and overheating, and in step 2, the specific information of the PCB welding defect image comprises that the false soldering comprises obvious black boundary lines between soldering tin and component leads or copper foil, the soldering tin is sunken towards the boundary lines, the colors are different, the solder accumulation comprises loose, white and matt solder joint structures, the colors are different, the defects are different, and the solder is excessive: the welding flux is convex, the side surface shape is different and has defects, the welding area is less than 80% of the welding pad, the welding flux does not form a smooth transition surface, the welding area is different and has defects, rosin residues are clamped in the welding seam, the welding color is different and has defects, and the welding spot is white, has no metallic luster and has defects in different colors.
Defect image acquisition: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, correspondingly storing the information obtained by analysis and the corresponding PCB welding defect images in a database, displaying the welding defect information of the analyzed PCB defect images in a text form, specifically, the size and the color of each image defect, and collecting detected PCB images: collecting all welding position images of a detected PCB, wherein the collection of the welding images of the detected PCB comprises welding points of all welding positions, the collection of single welding points comprises four side surfaces of the detected PCB, the area of the welding points and the color of the periphery of the welding points, the welding defect images of the PCB comprise virtual welding, welding flux accumulation, excessive welding flux, too little welding flux, rosin welding and overheating welding, in the step 2, the specific information of the welding defect images of the PCB comprises the virtual welding that the welding flux has obvious black boundary lines with component leads or copper foils, the welding flux is sunken towards the boundary lines, the color difference has defects, the welding flux accumulation comprises loose welding point structures, white color, no luster, the color difference has defects, and the welding flux is too much: the welding flux is convex, the side surface shape is different and has defects, the welding area is less than 80% of the welding pad, the welding flux does not form a smooth transition surface, the welding area is different and has defects, rosin slag is clamped in the welding seam, the welding color is different and has defects, the welding spot is whitened, the metal luster is not generated, the color is different and has defects, and the welding image is identified: the method comprises the steps of identifying acquired detected PCB welding point images through an image identification device, identifying four side shapes, welding areas and peripheral welding colors of welding points, wherein the four side shapes, the welding areas and the peripheral welding colors of the welding points are formed by single welding point welding, obtaining specific welding information of the detected PCB welding points after the identification is completed, and matching defects: inputting the obtained specific information of the welding of the detected PCB into a database, screening similar defect images in the database according to the obtained identification information of the welding point of the detected PCB, extracting the screened images, analyzing the corresponding information of the welding defect of the stored PCB defect images in advance, and matching the acquired PCB welding point images, and simultaneously extracting normal welding point welding images to wait for matching.
Embodiment III:
in the second embodiment, the following steps are added:
in step 3, the specific letter welding information of the recognition device for recognizing the collected detected PCB welding point image is that the specific size and color of the shape, the area and the color of the detected PCB welding point are displayed in a character form.
In step 4, the screening of the database is to extract the specific welding spot size and shape obtained by searching the detected image to be similar to the specific welding spot size and shape obtained by analyzing the defect image in the database, the screening of the database is to extract the detected PCB welding image and defect image after comparing the detected PCB welding image and defect image one by one in similarity, when the four welding side surfaces of the detected PCB welding spot are matched, the image overlapping algorithm is adopted to carry out overlapping comparison, thereby obtaining the welding height difference between the detected PCB welding spot and the defect image, then the welding spot size and shape of the two images are compared, finally the similar proportion of the two images is obtained, the image area of the defect welding spot comprises an image smaller than the normal welding area and an image larger than the normal welding area, under the welding spot size and shape obtained by the normal welding image, the welding area of the detected PCB is more than 20% of the welding flux, the judgment of less than 20% is the welding area is too less, the welding area of the detected PCB is detected, the image is compared, the welding area of the detected PCB is not required to be detected, the welding point is directly detected, the welding color is not coincident with the corresponding welding point, the corresponding welding defect size of the detected PCB is not detected, and the welding defect is not coincident, and the color is not coincident, and the welding defect is determined.
Defect image acquisition: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, correspondingly storing the information obtained by analysis and the corresponding PCB welding defect images in a database, displaying the welding defect information of the analyzed PCB defect images in a text form, specifically, the size and the color of each image defect, and collecting detected PCB images: collecting all welding position images of a detected PCB, wherein the collection of the welding images of the detected PCB comprises welding points of all welding positions, the collection of single welding points comprises four side surfaces of the detected PCB, the area of the welding points and the color of the periphery of the welding points, the welding defect images of the PCB comprise virtual welding, welding flux accumulation, excessive welding flux, too little welding flux, rosin welding and overheating welding, in the step 2, the specific information of the welding defect images of the PCB comprises the virtual welding that the welding flux has obvious black boundary lines with component leads or copper foils, the welding flux is sunken towards the boundary lines, the color difference has defects, the welding flux accumulation comprises loose welding point structures, white color, no luster, the color difference has defects, and the welding flux is too much: the welding flux is convex, the side surface shape is different and has defects, the welding area is less than 80% of the welding pad, the welding flux does not form a smooth transition surface, the welding area is different and has defects, rosin slag is clamped in the welding seam, the welding color is different and has defects, the welding spot is whitened, the metal luster is not generated, the color is different and has defects, and the welding image is identified: the method comprises the steps that an image recognition device is used for recognizing an acquired image of a welding point of a detected PCB, the recognition comprises four side shapes of single welding point welding, the welding area of the welding point and the peripheral welding color of the welding point, specific welding information of the welding point of the detected PCB is obtained after the recognition is finished, the recognition device is used for recognizing the acquired image of the welding point of the detected PCB, the specific size and the specific color of the shape, the area and the color of the welding point of the detected PCB are displayed in a character form, and the defects are matched: inputting the obtained specific information of the welding of the detected PCB into a database, screening similar defect images in the database according to the obtained identification information of the welding point of the detected PCB, extracting the screened images, analyzing the corresponding information of the welding defect of the stored PCB defect images in advance, matching the acquired PCB welding point images, extracting normal welding point welding images, waiting for matching, wherein the matching process comprises the steps of firstly matching four welding side shapes of a single welding point of the detected PCB with the defect welding images, secondly detecting the welding area of the welding point of the detected PCB, finally matching the welding peripheral colors of the welding point of the detected PCB, directly displaying the matched defect images and information through a display screen, and entering the next step if the matched defect images and information are not matched, the screening of the database is that the specific welding spot size and shape given by the checked image and the specific welding spot size and shape analyzed by the defect image in the database are searched and similar, the screening of the database is that the welding spot size and shape given by the checked image and the defect image are extracted after being compared one by one, when the four welding side surface shapes of the welding spot of the checked PCB and the defect welding image are matched, the overlapping comparison is carried out by adopting an image overlapping algorithm, so as to obtain the welding height difference between the welding height of the welding spot of the checked PCB and the welding height difference between the defect image, then the welding spot sizes and shapes of the two images are compared, finally, the similarity ratio of the welding spot size and the welding spot size is obtained, the image area of the defect welding spot welding comprises an image smaller than the normal welding area and an image larger than the normal welding area, the method comprises the steps that the welding area of a detected PCB welding point is 20% larger than the normal welding area, the welding area of the detected PCB welding point is too much, the welding area of the detected PCB welding point is less than 20% and is detected, image comparison is not needed, whether the welding area of the detected PCB welding point is defective or not can be determined directly through character comparison, finally, when the welding peripheral colors of the detected PCB welding point are matched, the welding point size and shape comparison is adopted in color matching, the welding peripheral color characters of the detected PCB welding point and the welding peripheral colors of the normal PCB welding point cannot be overlapped to be directly judged to be defective welding, then, the comparison is carried out on the welding area of the detected PCB welding point and the analysis characters of the corresponding images of the defects, and therefore the specific defect is determined, and the overlapping is qualified.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. A PCB welding defect detection method is characterized in that: the method comprises the following steps:
step 1: defect image acquisition: collecting PCB welding defect images and normal welding images, analyzing welding defect information of the PCB defect images, correspondingly inputting the information obtained by analysis and the corresponding PCB welding defect images into a database for storage, and displaying the welding defect information of the PCB defect images in a text form, namely the size and the color of each image defect;
step 2: and (3) collecting detected PCB images: collecting all welding position images of the detected PCB, wherein the collection of the welding images of the detected PCB comprises welding points of all welding positions, and the collection of single welding points is that the shape of four sides of the detected PCB, the area of the welding points and the color of the periphery of the welding points;
step 3: identifying a welding image: the method comprises the steps that an image recognition device is used for recognizing a collected image of a welding point of a detected PCB, the recognition comprises four side shapes of single welding points, welding areas of the welding points and peripheral welding colors of the welding points, specific welding information of the welding points of the detected PCB is obtained after the recognition is completed, and the recognition device is used for displaying the specific information of the shape, the area and the specific size and the specific color of the welding points of the detected PCB in a text font mode;
step 4: matching defects: inputting the obtained specific information of the welding of the detected PCB into a database, screening similar defect images in the database according to the obtained identification information of the welding points of the detected PCB, extracting the screened images, analyzing the welding defect corresponding information of the stored welding defect images of the PCB in advance, and collecting the images of the welding points of the PCB to be matched, and simultaneously extracting normal welding point welding images to wait for matching. Thereby determining what kind of defect is specified, and if the coincidence is qualified.
2. The method for detecting a soldering defect of a PCB according to claim 1, wherein: in step 2, the PCB solder defect image includes cold solder joint, solder build-up, solder overmuch, solder overlittle, rosin joint, and solder overheating.
3. The method for detecting the welding defect of the PCB according to claim 1, wherein the method comprises the following steps: in the step 2, the specific information of the PCB welding defect image comprises that the virtual welding tin and the lead of the component or the copper foil are provided with obvious black boundary lines, the tin is sunken towards the boundary lines, defects exist in different colors, the welding spots are piled up, the welding spots are loose in structure, white and matt, defects exist in different colors, and the welding flux is too much: the welding flux is convex, the side surface shape is different and has defects, the welding area is less than 80% of the welding pad, the welding flux does not form a smooth transition surface, the welding area is different and has defects, rosin residues are clamped in the welding seam, the welding color is different and has defects, and the welding spot is white, has no metallic luster and has defects in different colors.
4. The method for detecting the welding defect of the PCB according to claim 1, wherein the method comprises the following steps: in step 4, the screening of the database is to search for the similar size and shape of the welding spot given by the checked image and the specific welding spot size and shape of the defect image analysis in the database, and then extract the welding spot.
5. The method for detecting the welding defect of the PCB according to claim 1, wherein the method comprises the following steps: in step 4, the database is also screened to extract the PCB solder images and the defect images which are checked for similarity one by one.
6. The method for detecting the welding defect of the PCB according to claim 1, wherein the method comprises the following steps: in step 4, the image area of the defective solder joint includes an image smaller than the normal solder area and an image larger than the normal solder area, and under the size and shape of the solder joint given by the normal solder image, the solder area of the inspected PCB solder joint is determined to be larger than 20% of the normal solder area, and the solder is determined to be too much and less than 20%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249014.6A CN116343115B (en) | 2023-03-15 | 2023-03-15 | PCB welding defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249014.6A CN116343115B (en) | 2023-03-15 | 2023-03-15 | PCB welding defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116343115A CN116343115A (en) | 2023-06-27 |
| CN116343115B true CN116343115B (en) | 2024-01-26 |
Family
ID=86883280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310249014.6A Active CN116343115B (en) | 2023-03-15 | 2023-03-15 | PCB welding defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116343115B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117182379B (en) * | 2023-08-28 | 2024-04-12 | 惠州欧鹏电子科技有限公司 | Bluetooth sound box chip welding quality detection method and related device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781486A (en) * | 2021-11-15 | 2021-12-10 | 新恒汇电子股份有限公司 | IC card image defect detection method |
| WO2022154787A1 (en) * | 2021-01-13 | 2022-07-21 | Hewlett-Packard Development Company, L.P. | Image region of interest defect detection |
| CN114842275A (en) * | 2022-07-06 | 2022-08-02 | 成都数之联科技股份有限公司 | Circuit board defect judging method, training method, device, equipment and storage medium |
| CN115452938A (en) * | 2022-10-11 | 2022-12-09 | 国家石油天然气管网集团有限公司 | Detection equipment for pipeline weld defects |
| CN115617994A (en) * | 2022-10-13 | 2023-01-17 | 四川川云智慧智能科技有限公司 | Transformer substation equipment defect type identification method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10480862B2 (en) * | 2013-05-23 | 2019-11-19 | Crc-Evans Pipeline International, Inc. | Systems and methods for use in welding pipe segments of a pipeline |
-
2023
- 2023-03-15 CN CN202310249014.6A patent/CN116343115B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022154787A1 (en) * | 2021-01-13 | 2022-07-21 | Hewlett-Packard Development Company, L.P. | Image region of interest defect detection |
| CN113781486A (en) * | 2021-11-15 | 2021-12-10 | 新恒汇电子股份有限公司 | IC card image defect detection method |
| CN114842275A (en) * | 2022-07-06 | 2022-08-02 | 成都数之联科技股份有限公司 | Circuit board defect judging method, training method, device, equipment and storage medium |
| CN115452938A (en) * | 2022-10-11 | 2022-12-09 | 国家石油天然气管网集团有限公司 | Detection equipment for pipeline weld defects |
| CN115617994A (en) * | 2022-10-13 | 2023-01-17 | 四川川云智慧智能科技有限公司 | Transformer substation equipment defect type identification method and system |
Non-Patent Citations (6)
| Title |
|---|
| PCB自动光学检测中元器件特征建模与检查算法研究;贺珍真;《万方数据库》;第12-62页 * |
| Stacked Cross Attention for Image-Text Matching;Kuang-Huei Lee等;《European Conference on Computer Vision: Computer Vision - ECCV 2018》;第212-218页 * |
| State of the Art in Defect Detection Based on Machine Vision;Zhonghe Ren等;《International Journal of Precision Engineering and Manufacturing-Green Technology》;第661-691页 * |
| 基于改进Tiny-YOLOv3网络的航天电子焊点缺陷主动红外检测研究;韩航迪等;《仪器仪表学报》;第41卷(第11期);第42-49页 * |
| 挠性印制电路板焊盘表面缺陷的检测;黄杰贤等;《光学精密工程》;第18卷(第11期);第2443-2453页 * |
| 管道环焊缝缺陷漏磁检测信号仿真分析;苏林等;《焊接》(第3期);第10-16页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116343115A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107945184B (en) | Surface-mounted component detection method based on color image segmentation and gradient projection positioning | |
| Anitha et al. | A survey on defect detection in bare PCB and assembled PCB using image processing techniques | |
| CN116343115B (en) | PCB welding defect detection method | |
| JP3960346B2 (en) | Image processing method, substrate inspection method, substrate inspection apparatus, and inspection data creation method for substrate inspection | |
| CN105510348A (en) | Flaw detection method and device of printed circuit board and detection equipment | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| CN112387604B (en) | Method for detecting packaging substrate through AVI (automatic voltage indicator) detector and automatic point finder in networking mode | |
| CN108596829A (en) | A kind of PCB bare boards picture method for registering and device | |
| CN115359047A (en) | Abnormal defect detection method for intelligent welding of PCB (printed circuit board) | |
| CN113256598A (en) | Visual detection system for chip production | |
| CN116168218A (en) | Circuit board fault diagnosis method based on image recognition technology | |
| CN115775246A (en) | Method for detecting defects of PCB (printed circuit board) components | |
| Anitha et al. | SMT component inspection in PCBA’s using image processing techniques | |
| CN114612423A (en) | Chip packaging defect detection method | |
| CN108254380B (en) | PCB template comparison method based on digital image processing | |
| Leta et al. | Computer vision system for printed circuit board inspection | |
| JPH08210820A (en) | Method and device for recognizing part to be inspected in visual inspection device of parts-mounted board | |
| CN111307817B (en) | Online detection method and system for PCB production process of intelligent production line | |
| CN116337869A (en) | Machine vision-based detection system for production of double-sided circuit board | |
| KR20230126163A (en) | Training data generation apparatus, training data generation method, and program recorded on recording medium | |
| KR20040042775A (en) | Inspection Status Display Method | |
| CN112116591B (en) | Method for detecting open circuit of etching circuit | |
| JP3919207B2 (en) | Appearance inspection device | |
| CN111273155A (en) | Chip burning detection method and system and computer readable storage medium | |
| CN112288782A (en) | PCB defect detection method based on boundary segment number value |
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 |