CN113034496A

CN113034496A - PCB testing system

Info

Publication number: CN113034496A
Application number: CN202110436037.9A
Authority: CN
Inventors: 谢顺铁
Original assignee: Wanan Yuwei Electronics Co Ltd
Current assignee: Wanan Yuwei Electronics Co Ltd
Priority date: 2021-04-22
Filing date: 2021-04-22
Publication date: 2021-06-25

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

PCB testing system

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 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;

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

1. A PCB board test system is characterized by comprising the following modules:

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.