CN113034496A - PCB testing system - Google Patents
PCB testing system Download PDFInfo
- Publication number
- CN113034496A CN113034496A CN202110436037.9A CN202110436037A CN113034496A CN 113034496 A CN113034496 A CN 113034496A CN 202110436037 A CN202110436037 A CN 202110436037A CN 113034496 A CN113034496 A CN 113034496A
- Authority
- CN
- China
- Prior art keywords
- image
- picture
- detected
- wiring
- welding spot
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 44
- 238000003466 welding Methods 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000003709 image segmentation Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 238000003702 image correction Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 229910000679 solder Inorganic materials 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 13
- 238000005259 measurement Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 238000011990 functional testing Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a PCB testing system, and relates to the field of printed circuit boards. The invention comprises the following steps: acquiring an image to be detected, and preprocessing the image to be detected; carrying out image recognition on the image to be detected, comparing the image to be detected with a sample image, and screening out a first qualified image; collecting an RGB image of the first qualified image by using an image sensor, and dividing the RGB image into a wiring picture, a welding spot picture and a background picture; and comparing the wiring picture, the welding spot picture and the background picture with the wiring picture, the welding spot picture and the background picture of the sample image one by one, wherein the wiring picture, the welding spot picture and the background picture are all matched, and the image to be detected is qualified. The invention flexibly utilizes the data information to test the PCB, thereby saving material resources and manpower.
Description
Technical Field
The invention relates to the field of printed circuit boards, in particular to a PCB testing system.
Background
At present, the PCB board test mainly comprises the following modes:
1. manual visual inspection of PCB
Inspection using a magnifying glass or calibrated microscope, using visual inspection by an operator, determines whether a circuit board is acceptable or unacceptable, and determines when a corrective action is required, which is the most conventional method of inspection. Its main advantages are low pre-cost and no test fixture, while its main disadvantages are human subjective error, high long-term cost, discontinuous defect detection, difficult data collection, etc. This approach is becoming increasingly impractical due to the increased PCB yield and the reduced pitch of the traces and component volume on the PCB.
2. PCB on-line test
There are several testing methods, such as a needle bed type tester and a flying needle tester, which find out manufacturing defects and test analog, digital and mixed signal elements by detecting electrical properties to ensure that they meet specifications. The main advantages are low test cost per board, high digital and functional test capability, fast and thorough short and open circuit test, programming firmware, high defect coverage, easy programming, etc. The main defects are that the clamp needs to be tested, the programming and debugging time is long, the cost for manufacturing the clamp is high, the use difficulty is high, and the like.
3. PCB function test
The functional system test is to utilize special test equipment at the middle stage and the tail end of the production line to comprehensively test the functional modules of the circuit board so as to confirm the quality of the circuit board. Functional testing is the earliest automatic test principle, which can be performed with a variety of devices, based on a specific board or a specific unit. There are types of end product testing, up-to-date mockups, and heap testing. Functional testing generally does not provide deep data for pin-level and component-level diagnostics for process improvement, and requires specialized equipment and specially designed test procedures, which are complicated to program, and therefore not suitable for most circuit board production lines.
4. Automated optical inspection
The method is also called automatic visual inspection, is based on optical principle, comprehensively adopts a plurality of technologies such as image analysis, computer, automatic control and the like, detects and processes the defects encountered in the production, and is a newer method for confirming the manufacturing defects. AOI is generally used before and after reflow and before electrical testing, which improves the yield of electrical processing or functional testing, and the cost for correcting defects is far lower than the cost after final testing, often reaching dozens of times.
5. Automated X-ray examination
The different absorption rates of different substances to X-ray are utilized to see through the part to be detected and find the defect. The method is mainly used for detecting defects of the superfine-spacing and ultrahigh-density circuit board, bridging, missing, poor alignment and the like generated in the assembling process, and can also be used for detecting internal defects of the IC chip by utilizing the tomography technology. It is the only method for testing the welding quality of ball grid array and the shielded tin ball. The main advantages are that the BGA welding quality and embedded type elements can be detected, and the cost of the fixture is saved; the main disadvantages are slow speed, high failure rate, difficulty in detecting rework solder joints, high cost, and long program development time, which are newer detection methods and yet to be further studied.
6. Laser detection system
It is a recent development in PCB testing technology. It scans the printed board with a laser beam, collects all the measurement data and compares the actual measurement values with preset qualification limits. This technique has been demonstrated on a bare board, being considered for assembled board testing, at speeds sufficient for mass production lines. Fast output, no requirement for fixtures and visual non-covering access are its main advantages; the high initial cost and maintenance and use problems are major drawbacks.
7. Size detection
And measuring the sizes of hole positions, length, width, position degree and the like by using a quadratic element image measuring instrument. Because the PCB belongs to a small thin and soft product, the contact type measurement is easy to deform so as to cause inaccurate measurement, and the quadratic element image measuring instrument becomes an optimal high-precision dimension measuring instrument. After the image measuring instrument for the semeri measurement is programmed, the full-automatic measurement can be realized, the measurement precision is high, the measurement time is greatly shortened, and the measurement efficiency is improved.
The various PCB detection modes have various defects, and are time-consuming, labor-consuming, high in labor cost and low in precision of detection results.
Disclosure of Invention
In view of this, the present invention provides a PCB testing system, which flexibly utilizes data information to test a PCB, thereby saving physical resources and manpower.
In order to achieve the purpose, the invention adopts the following technical scheme:
a PCB board test system is characterized by comprising the following modules:
the image preprocessing module is used for acquiring an image to be detected and preprocessing the image to be detected;
the image screening module is used for carrying out image identification on the image to be detected and comparing the image to be detected with a sample image to screen out a first qualified image;
the image segmentation module is used for acquiring the RGB image of the first qualified image by using an image sensor and segmenting the RGB image into a wiring picture, a welding spot picture and a background picture;
and the image testing module is used for comparing the wiring picture, the welding spot picture and the background picture with the wiring picture, the welding spot picture and the background picture of the sample image one by one, and the wiring picture, the welding spot picture and the background picture are all matched, so that the image to be detected is qualified.
Preferably, the image segmentation module further comprises performing feature extraction on the first qualified image, extracting routing features, welding spot features and background features, wherein the feature extraction adopts an LBP feature algorithm; and comparing the wiring characteristics, the welding spot characteristics and the background characteristics with the wiring characteristics, the welding spot characteristics and the background characteristics of the sample image one by one, and if the wiring characteristics, the welding spot characteristics and the background characteristics are all matched, determining that the image to be detected is qualified.
Preferably, the system further comprises a fault marking module for marking the fault position of the PCB.
Preferably, the image screening module adopts a semi-supervised learning algorithm and performs incremental updating processing and hierarchical classification processing simultaneously.
Preferably, the image screening module screens the images by adopting an enhanced display technology and utilizing multimedia, three-dimensional modeling, real-time image display and control and scene fusion.
Preferably, the image preprocessing module comprises image noise reduction, image enhancement and image correction.
Preferably, the image segmentation module performs segmentation by using a clustering algorithm, performs clustering for multiple times, and selects the best clustering result.
According to the technical scheme, compared with the prior art, the PCB testing system disclosed by the invention has the following beneficial effects:
the invention can efficiently detect the fault position of the PCB and effectively mark the fault position. Meanwhile, the invention realizes the effect of flexible detection through a semi-supervised learning algorithm, and the segmentation algorithm and the feature extraction algorithm effectively improve the accuracy of the test.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a schematic flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a PCB testing system, which comprises the following modules as shown in figure 1:
the image preprocessing module is used for acquiring an image to be detected and preprocessing the image to be detected;
the image screening module is used for carrying out image identification on the image to be detected and comparing the image to be detected with the sample image to screen out a first qualified image;
the image segmentation module is used for acquiring an RGB image of the first qualified image by using the image sensor and segmenting the RGB image into a wiring picture, a welding spot picture and a background picture;
and the image testing module is used for comparing the wiring picture, the welding spot picture and the background picture with the wiring picture, the welding spot picture and the background picture of the sample image one by one, and the wiring picture, the welding spot picture and the background picture are all matched, so that the image to be detected is qualified.
The image segmentation module also comprises a step of extracting the characteristics of the first qualified image, namely extracting the wiring characteristics, the welding spot characteristics and the background characteristics, wherein the characteristics are extracted by adopting an LBP characteristic algorithm; and comparing the wiring characteristics, the welding spot characteristics and the background characteristics with those of the sample image one by one, and if the wiring characteristics, the welding spot characteristics and the background characteristics are all matched, determining that the image to be detected is qualified.
The PCB fault location marking device further comprises a fault marking module used for marking the fault location of the PCB.
The image screening module adopts a semi-supervised learning algorithm and simultaneously performs incremental updating processing and hierarchical classification processing.
The image screening module screens images by adopting an enhanced display technology and utilizing multimedia, three-dimensional modeling, real-time image display and control and scene fusion.
The image preprocessing module comprises image denoising, image enhancement and image correction.
The image segmentation module is used for segmenting by adopting a clustering algorithm, clustering for multiple times and selecting the best clustering result.
A PCB testing method specifically comprises the following steps as shown in FIG. 2:
acquiring an image to be detected, and preprocessing the image to be detected;
carrying out image recognition on an image to be detected, comparing the image to be detected with a sample image, and screening out a first qualified image;
collecting an RGB image of the first qualified image by using an image sensor, and dividing the RGB image into a wiring picture, a welding spot picture and a background picture;
and comparing the wiring picture, the welding spot picture and the background picture with the wiring picture, the welding spot picture and the background picture of the sample image one by one, wherein the wiring picture, the welding spot picture and the background picture are all matched, and the image to be detected is qualified.
In addition, a feature extraction algorithm, such as an LBP algorithm, can be used to extract trace features, solder joint features, and background features, and compare the extracted features with the sample features, and if all the features are matched, the PCB is qualified.
If the PCB has defects, the positions of the corresponding defects can be marked.
The first qualified images are screened by adopting a semi-supervised learning algorithm, incremental updating processing and hierarchical classification processing are carried out at the same time, and the generator and the discriminator are used for training, so that the data of specific labels can be generated, the quality of the generated data can be improved, and the images are effectively screened.
In addition, the first qualified image is screened by adopting an enhanced display technology and using multimedia, three-dimensional modeling, real-time image display and control and scene fusion modes. Compared with a semi-supervised learning algorithm, the AR technology is more intuitive and convenient to observe.
In this embodiment, the image to be detected is preprocessed, including image noise reduction, image enhancement, and image correction.
The RGB image segmentation adopts a clustering algorithm to segment, and clustering is carried out for multiple times, and the clustering effect is the best in the fifth time through the test of the invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A PCB board test system is characterized by comprising the following modules:
the image preprocessing module is used for acquiring an image to be detected and preprocessing the image to be detected;
the image screening module is used for carrying out image identification on the image to be detected and comparing the image to be detected with a sample image to screen out a first qualified image;
the image segmentation module is used for acquiring the RGB image of the first qualified image by using an image sensor and segmenting the RGB image into a wiring picture, a welding spot picture and a background picture;
and the image testing module is used for comparing the wiring picture, the welding spot picture and the background picture with the wiring picture, the welding spot picture and the background picture of the sample image one by one, and the wiring picture, the welding spot picture and the background picture are all matched, so that the image to be detected is qualified.
2. The PCB testing system of claim 1, wherein the image segmentation module further comprises performing feature extraction on the first qualified image, extracting trace features, solder joint features and background features, wherein the feature extraction adopts an LBP feature algorithm; and comparing the wiring characteristics, the welding spot characteristics and the background characteristics with the wiring characteristics, the welding spot characteristics and the background characteristics of the sample image one by one, and if the wiring characteristics, the welding spot characteristics and the background characteristics are all matched, determining that the image to be detected is qualified.
3. The PCB testing system of claim 1, further comprising a fault marking module for marking a fault location of the PCB.
4. The PCB testing system of claim 1, wherein the image screening module adopts a semi-supervised learning algorithm and performs the incremental updating process and the hierarchical classification process simultaneously.
5. The PCB testing system of claim 1, wherein the image screening module screens the images by means of multimedia, three-dimensional modeling, real-time image display and control, and scene fusion by using an enhanced display technology.
6. The PCB board testing system of claim 1, wherein the image preprocessing module comprises image denoising, image enhancement and image correction.
7. The PCB testing system of claim 1, wherein the image segmentation module performs segmentation by a clustering algorithm, performs clustering for a plurality of times, and selects the best clustering result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110436037.9A CN113034496A (en) | 2021-04-22 | 2021-04-22 | PCB testing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110436037.9A CN113034496A (en) | 2021-04-22 | 2021-04-22 | PCB testing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113034496A true CN113034496A (en) | 2021-06-25 |
Family
ID=76457431
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110436037.9A Pending CN113034496A (en) | 2021-04-22 | 2021-04-22 | PCB testing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113034496A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117929975A (en) * | 2024-03-25 | 2024-04-26 | 四川易景智能终端有限公司 | PCBA board testing method |
-
2021
- 2021-04-22 CN CN202110436037.9A patent/CN113034496A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117929975A (en) * | 2024-03-25 | 2024-04-26 | 四川易景智能终端有限公司 | PCBA board testing method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110659662B (en) | Flaw detection system and method using artificial intelligence | |
CN112053318B (en) | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning | |
CN104730078A (en) | Thermal infrared imager-based AOI circuit board detection method | |
CN101706458A (en) | Automatic detection system and detection method of high resolution printed circuit board | |
CN103500459B (en) | Printed circuit board defect detecting method based on regularization parameters | |
CN113454445A (en) | Compensating for reference misalignment during part inspection | |
TWI618940B (en) | Device and method for detecting blind hole of printed circuit board | |
TW202001795A (en) | Labeling system and method for defect classification | |
CN106980099B (en) | A kind of calibration method and system of Automatic Testing System of Circuit Board | |
CN113111903A (en) | Intelligent production line monitoring system and monitoring method | |
CN113034496A (en) | PCB testing system | |
Anitha et al. | SMT component inspection in PCBA’s using image processing techniques | |
CN114842275A (en) | Circuit board defect judging method, training method, device, equipment and storage medium | |
US20220292661A1 (en) | Automated inspection system and operating method thereof | |
US20050274802A1 (en) | Circuit board inspection apparatus | |
CN112702905B (en) | Method and system for tracing yield and error rate of printed circuit board | |
CN113933309B (en) | Method for retesting blind hole Kong Nabu of AOI machine | |
TW201522949A (en) | Inspection method for image data | |
CN110286269B (en) | Automatic acquisition and analysis method for impedance information of PCB (printed circuit board) | |
JPH09203765A (en) | Substrate inspecting device which includes visual inspection | |
CN111539164A (en) | Method for automatically generating LCD circuit design drawing by shooting image | |
CN115439459A (en) | Circuit board fault determination method based on infrared thermal imaging | |
US6951000B2 (en) | Simulated voltage contrasted image generator and comparator | |
Terra et al. | PCBA analysis using X-ray images with processing tools. | |
CN117788412A (en) | PCB defect detection method based on AOI |
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 |