WO2021027184A1 - Pcb maintenance system and maintenance method based on false point defect detection - Google Patents

Pcb maintenance system and maintenance method based on false point defect detection Download PDF

Info

Publication number
WO2021027184A1
WO2021027184A1 PCT/CN2019/121165 CN2019121165W WO2021027184A1 WO 2021027184 A1 WO2021027184 A1 WO 2021027184A1 CN 2019121165 W CN2019121165 W CN 2019121165W WO 2021027184 A1 WO2021027184 A1 WO 2021027184A1
Authority
WO
WIPO (PCT)
Prior art keywords
defect
false point
preliminarily determined
inspection
defects
Prior art date
Application number
PCT/CN2019/121165
Other languages
French (fr)
Chinese (zh)
Inventor
弗依斯沃瑟·诺尼
柯布兰·凡
胡冰峰
陈朋飞
Original Assignee
苏州康代智能科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州康代智能科技股份有限公司 filed Critical 苏州康代智能科技股份有限公司
Priority to KR1020227007669A priority Critical patent/KR20220041212A/en
Publication of WO2021027184A1 publication Critical patent/WO2021027184A1/en

Links

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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956—Inspecting patterns on the surface of objects
    • G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06T7/0008—Industrial image inspection checking presence/absence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854—Grading and classifying of flaws
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854—Grading and classifying of flaws
    • G01N2021/888—Marking defects
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
    • 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
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • 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
    • G01N2021/95615—Inspecting patterns on the surface of objects using a comparative method with stored comparision signal
    • 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
    • G01N2201/00—Features of devices classified in G01N21/00
    • G01N2201/12—Circuits of general importance; Signal processing
    • G01N2201/129—Using chemometrical methods
    • G01N2201/1296—Using chemometrical methods using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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]

Definitions

  • the invention relates to the field of circuit board inspection and repair, in particular to a PCB inspection and repair system and method based on false point defect detection.
  • PCBs printed circuit boards
  • Printed circuit boards may have short circuit or open circuit defects during the production process, and the quality of the printed circuit board determines the qualification of the corresponding electronic device product. Therefore, the quality inspection and maintenance of the printed circuit board is extremely important.
  • AOI Automatic optical inspection equipment
  • PCB moves to the inspection equipment. According to the defect coordinates, the defects are inspected one by one through the inspection equipment manually. In this process, data transmission, PCB board handling, and defect point inspection and repair will be costly. plenty of time.
  • the prior art lacks a solution to improve PCB defect detection and repair.
  • the present invention provides a PCB repair system and repair method based on false point defect detection, which greatly improves the efficiency of PCB defect detection and repair.
  • the technical solution is as follows:
  • the present invention provides a PCB inspection and repair system based on false point defect detection, including automatic optical inspection equipment, a database server, and inspection equipment.
  • the inspection equipment is equipped with a defect virtual inspection module for verifying false point defects.
  • the automatic optical inspection equipment and the defect virtual inspection module are both in communication connection with the database server;
  • the automatic optical inspection equipment is used to scan the printed circuit board to be inspected to obtain the scanned image, and compare it with the corresponding standard image loaded through the database server to construct a defect list, the defect list containing corresponding to the Defect coordinate information of the preliminarily determined defect of the scanned image;
  • the database server is used to store the scanned image output by the automatic optical inspection device and the corresponding defect list
  • the defect virtual detection module of the overhaul equipment can load the scanned image and the corresponding defect list through the database server, and perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list If the re-inspection defect is a false point defect, the defect is deleted from the defect list, and the repairing equipment inspects and repairs the defect at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
  • the re-examination of the preliminarily determined defect includes: extracting a partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the short circuit feature or the open circuit feature, wherein the short circuit
  • the feature includes a straight line connecting two cables, and the disconnection feature includes a gap on the cable. If any one of the features is satisfied, the defect is determined to be a real defect, otherwise the defect is determined to be a false point defect.
  • the re-inspection of the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image meets the following conditions at the same time: non-linear, irregular and isolated If the existing pattern meets the above characteristics at the same time, the defect is determined to be a false point defect.
  • the re-inspection of the preliminarily determined defects includes:
  • the preliminarily determined defect is determined to be a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, the preliminarily determined defect is determined The defect is a false point defect.
  • the re-inspection of the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, inputting it into the trained neural network model, and outputting according to the neural network model As a result, determine whether the defect is a real defect or a false point defect.
  • scanning the printed circuit board to be inspected includes scanning the PCB with different perspective angles to obtain different perspective views, and the perspective views include a two-dimensional perspective view and a three-dimensional perspective view.
  • the maintenance equipment further includes a movable camera device that can be moved to the remaining defect coordinates in the defect list corresponding to the printed circuit board, and the defects at the defect coordinates are enlarged and displayed, For manual overhaul.
  • the number of the database server is one, the number of the automatic optical inspection equipment and the maintenance equipment is multiple, and the numbers of the automatic optical inspection equipment and the maintenance equipment are the same or different.
  • the present invention provides a PCB inspection and repair method based on false point defect detection, which includes the following steps:
  • the defect list containing the defect coordinate information of the preliminary judged defect corresponding to the scanned image
  • each preliminarily determined defect includes the following steps:
  • the first way is to determine whether the partial image meets the short-circuit feature or the open-circuit feature, wherein the short-circuit feature includes a straight line connecting two cables, and the open-circuit feature includes a gap in the cable. Feature, the defect is judged to be a real defect, otherwise the defect is judged to be a false point defect;
  • the second method is to judge whether the partial image meets the following conditions at the same time: a non-linear, irregular and isolated figure, if the above characteristics are met at the same time, then the defect is judged to be a false point defect;
  • the third method is to compare the similarity between the partial image and several preset defect template images calibrated as real defects or false point defects, and determine the defect as a real defect based on the calibration of the defect template image with the highest similarity It's still a fake point defect;
  • the fourth method is to input the partial image into the trained neural network model, and determine whether the defect is a real defect or a false point defect according to the output result of the neural network model.
  • the maintenance equipment is equipped with a movable camera device to locate and magnify the real defects after the false point defects are eliminated, so as to improve the efficiency of manual maintenance;
  • Multiple AOI devices are equipped with a set of database server to connect to multiple maintenance devices, saving space and cost.
  • FIG. 1 is a schematic structural diagram of a PCB inspection and repair system based on false point defect detection provided by an embodiment of the present invention
  • FIG. 2 is a characteristic schematic diagram of a real short-circuit defect scanned image provided by an embodiment of the present invention
  • FIG. 3 is a schematic diagram of features of a false point defect scanned image provided by an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of the structure of a single database server corresponding to multiple AOIs and multiple VVRs according to an embodiment of the present invention
  • FIG. 5 is a two-dimensional perspective view obtained by scanning a PCB with a two-dimensional perspective according to an embodiment of the present invention
  • FIG. 6 is a three-dimensional perspective view obtained by scanning a PCB with a three-dimensional perspective provided by an embodiment of the present invention
  • FIG. 7 is a flowchart of a PCB inspection and repair method based on false point defect detection provided by an embodiment of the present invention.
  • the PCB inspection system based on false point defect detection includes automatic optical inspection equipment (hereinafter referred to as AOI), database server and Maintenance equipment, which is equipped with a defect virtual detection module (also called virtual verification detection module, VVR) for verifying false point defects, and the automatic optical detection equipment and the defect virtual detection module communicate with the database server connection;
  • AOI automatic optical inspection equipment
  • VVR virtual verification detection module
  • the automatic optical inspection equipment is used to scan the printed circuit board to be inspected to obtain the scanned image, and compare it with the corresponding standard image loaded through the database server, and use the difference obtained by the comparison as the preliminary determined defect to construct a defect list ,
  • the defect list includes defect coordinate information corresponding to the preliminarily determined defect of the scanned image;
  • the database server is used to store the scanned image output by the automatic optical inspection device and the corresponding defect list
  • the defect virtual detection module of the overhaul equipment can load the scanned image and the corresponding defect list through the database server, and perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list If the re-inspection defect is a false point defect, the defect is deleted from the defect list, and the repairing equipment inspects and repairs the defect at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
  • the AOI equipment can obtain the overall layout picture of the defect after scanning the PCB board, and can accurately calibrate the coordinates of the corresponding defect point in the picture. In the AOI equipment system, it also has the function of determining the defect type. , Such as circuit board missed soldering, multiple soldering and soldering errors.
  • Connected to AOI is a database server with data storage function. The database server can accurately store the information input after AOI scanning.
  • the VVR system of overhauling equipment Connected to the database server is the VVR system of overhauling equipment. VVR collects defect information of corresponding plates in the database server.
  • different viewing angles can be used to scan the PCB to obtain different viewing angles, such as a two-dimensional view of a certain contrast, saturation, and hue (such as Figure 5) or a 3D visual image (such as Figure 6), especially the 3D scanning vision shown in Figure 6, can accurately determine "false points” and “true points”, improve the accuracy of judgment, and will not delete "false points” by mistake, and It can also provide image reference for subsequent manual repair, which is more convenient for manual repair.
  • the re-examination of the preliminarily determined defect by the elimination method includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the short-circuit feature or the open-circuit feature, wherein,
  • the short circuit feature includes a straight line connecting two cables (as shown in FIG. 2), and the open circuit feature includes a gap (not shown) on the cable. If any one of the features is satisfied, the defect is determined It is a real defect, otherwise the defect is judged to be a false point defect. "True defects" need to be manually repaired point by point, as shown in Figure 2 with multiple welded narrow seams, which will cause a short circuit in the PCB. At this time, the narrow seam needs to be manually removed.
  • using the feature correspondence method to re-examine the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the following conditions at the same time: non-straight, Irregular and isolated graphics (as shown in Figure 3), if the above characteristics are satisfied at the same time, the defect is determined to be a false point defect.
  • the "fake spot defects” can be dust, stains, fingerprints, etc., which will exist in large quantities in the PCB board, and will be judged as defective points during AOI scanning. If it is not eliminated intelligently, it will cost a lot of labor during subsequent maintenance. For these large number of "false point defects", the embodiment of the present invention introduces a VVR system, which can greatly reduce the time spent in this aspect.
  • using the similarity matching method to re-examine the preliminarily determined defects include:
  • the preliminarily determined defect is determined to be a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, the preliminarily determined defect is determined The defect is a false point defect.
  • the re-inspection of the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, inputting it into the trained neural network model, and outputting according to the neural network model As a result, determine whether the defect is a real defect or a false point defect.
  • the neural network model can be a deep neural network in the prior art, combined with a back propagation algorithm and a stochastic gradient descent method to train the neural network.
  • One of the above four optional technical solutions can be selected for defect re-inspection, or multiple or even all of them can be re-inspected. For example, it is preferable to perform the preliminary judgment in the order of mode 1 ⁇ mode 2 ⁇ mode 3 ⁇ mode 4. Defects are re-inspected to maximize the elimination of false point defects, reduce the amount of work wasted on the processing of "false points", and improve work efficiency.
  • the overhaul equipment further includes a movable camera device, which can move to the remaining defect coordinates in the defect list corresponding to the printed circuit board, and check the defect coordinates
  • the defects at the location are enlarged and displayed for manual inspection and repair.
  • the camera device has two functions. The first is to move to the relative position of the defect currently to be inspected to prompt the maintenance personnel to inspect and repair the PCB at the current relative position of the camera; The device can perform a high-magnification display of the current defect area, so that the maintenance personnel can clearly and quickly determine the current defect to be overhauled, and avoid false inspection and repair.
  • the number of the database server is one, the number of the automatic optical inspection equipment and the maintenance equipment is multiple, and the number of the automatic optical inspection equipment and the maintenance equipment
  • the quantity is the same or different.
  • the database server can only use one set at the customer's site. It can work with multiple AOIs and VVRs at the same time.
  • the database server can not only collect single chips or multiple It can also collect multiple AOIs to scan the PCB defect information. In this way, a system that can work through a set of database servers can save space and costs for customers.
  • a PCB repair method based on false point defect detection is provided. As shown in FIG. 7, the repair method includes the following steps:
  • the re-inspection of each preliminarily determined defect includes the following steps:
  • the first way is to determine whether the partial image meets the short-circuit feature or the open-circuit feature, wherein the short-circuit feature includes a straight line connecting two cables, and the open-circuit feature includes a gap in the cable. Feature, the defect is judged to be a real defect, otherwise the defect is judged to be a false point defect;
  • the second method is to judge whether the partial image meets the following conditions at the same time: a non-linear, irregular and isolated figure, if the above characteristics are met at the same time, then the defect is judged to be a false point defect;
  • the third method is to compare the similarity between the partial image and several preset defect template images calibrated as real defects or false point defects, and determine the defect as a real defect based on the calibration of the defect template image with the highest similarity It's still a fake point defect;
  • the fourth method is to input the partial image into the trained neural network model, and determine whether the defect is a real defect or a false point defect according to the output result of the neural network model.
  • the present invention connects the defect coordinates and scanned images (preferably, the pre-judgment type of the defect) detected by AOI to the maintenance equipment through the database server.
  • the maintenance equipment is also equipped with a high-end defect virtual detection module.
  • the defect virtual detection module automatically screens the defect points.
  • the system classifies all gray-scale defect images (defective scanned images) as "real" or "false".
  • the "false" defect is deleted, and the "false” defect may be Dust, dirt, etc., can be deleted from the repair defect list; or through manual inspection of the gray-scale defect map provided by AOI, false defects can be deleted from the repair defect list.
  • the present invention checks the false point defects detected by AOI, eliminates false point defects that do not need to be repaired, and then performs repairs, which greatly improves the repair efficiency; connects the AOI to the repair equipment through the database server to realize efficient data transmission; and sets the repair equipment.
  • the movable camera device locates and enlarges the real defects after eliminating the false point defects to improve the efficiency of manual maintenance; multiple AOI devices are equipped with a database server to connect to multiple maintenance devices, saving space and cost.
  • any reference signs placed between parentheses shall not be regarded as restrictive claims.
  • the word “comprising” does not exclude the existence of other elements or steps listed in the claims.
  • the term “a” or “an” as used herein is defined as one or more than one.
  • the use of introductory phrases such as “at least one” and “one or more” in a claim statement should not be interpreted as implying that the introduction of the indefinite article "a” or “an” into another claim element will include such introduction.

Abstract

A PCB maintenance system and maintenance method based on false point defect detection, wherein the system comprises an automatic optical detection device, a database server and a maintenance device, wherein the automatic optical detection device is used for scanning a printed circuit board to be detected to obtain a scanned image and comparing the scanned image with a corresponding standard image loaded by the database server to construct a defect list containing defect coordinate information corresponding to preliminarily determined defects of the scanned image; the maintenance device can load the scanned image and the corresponding defect list through the database server, and recheck the preliminarily determined defects of the scanned image at each defect coordinate in the defect list, and if the rechecked defect is a false point defect, the defect is deleted from the defect list, and the maintenance device repairs the remaining defects at the defect coordinate in the defect list corresponding to the printed circuit board. Through the recheck and repair of false point defects detected by the automatic optical detection device, the maintenance efficiency is greatly improved.

Description

一种基于假点缺陷检测的PCB检修***及检修方法A PCB inspection system and inspection method based on false point defect detection 技术领域Technical field
本发明涉及电路板检测检修领域，尤其涉及一种基于假点缺陷检测的PCB检修***及检修方法。The invention relates to the field of circuit board inspection and repair, in particular to a PCB inspection and repair system and method based on false point defect detection.
背景技术Background technique
现如今在高度发展的电子工业时代，印刷电路板(Printed Circuit Board，简称PCB)已成为计算机、电子通信等产品上必不可缺的一样重要部件之一。印刷电路板在生产过程中会有线路短路或者断路的缺陷，而印刷电路板的好坏决定着相应电子器件产品的合格与否，因此，印刷电路板的质量检测与检修显得格外重要。Nowadays, in the era of the highly developed electronics industry, printed circuit boards (PCBs for short) have become an indispensable and important component of computers, electronic communications and other products. Printed circuit boards may have short circuit or open circuit defects during the production process, and the quality of the printed circuit board determines the qualification of the corresponding electronic device product. Therefore, the quality inspection and maintenance of the printed circuit board is extremely important.
现有技术中，自动光学检测设备(Automated Optical Inspection，简称AOI)在电路板生产过程中运用较为普遍，AOI能够检测PCB上的缺陷，然后人工根据AOI检测到的缺陷进行检修。现今客户不仅对AOI自身的工作效率有要求，而且对AOI检测后完成检修的工作效率要求也越来越高，目前，市场上的普遍的AOI供应商，仅能提供单独的AOI设备，被检测的PCB从AOI设备上得到缺陷坐标后，移动到检修设备，根据该缺陷坐标，人工通过检修设备对缺陷逐个进行检修，这个过程中，在数据传输、PCB板材搬运、逐个缺陷点检修等都会耗费大量的时间。In the prior art, automatic optical inspection equipment (Automated Optical Inspection, AOI for short) is commonly used in the circuit board production process. AOI can detect defects on the PCB, and then manually perform inspections based on the defects detected by the AOI. Nowadays, customers not only have requirements for AOI's own work efficiency, but also have higher and higher work efficiency requirements for the completion of maintenance after AOI inspection. At present, common AOI suppliers in the market can only provide individual AOI equipment, which is tested After getting the defect coordinates from the AOI equipment, the PCB moves to the inspection equipment. According to the defect coordinates, the defects are inspected one by one through the inspection equipment manually. In this process, data transmission, PCB board handling, and defect point inspection and repair will be costly. plenty of time.
现有技术中缺少一种提高PCB缺陷检测及检修的解决方案。The prior art lacks a solution to improve PCB defect detection and repair.
发明内容Summary of the invention
为了解决现有技术的问题，本发明提供了一种基于假点缺陷检测的PCB检修***及检修方法，大大提高PCB缺陷检测及检修效率，所述技术方案如下：In order to solve the problems of the prior art, the present invention provides a PCB repair system and repair method based on false point defect detection, which greatly improves the efficiency of PCB defect detection and repair. The technical solution is as follows:
一方面，本发明提供了一种基于假点缺陷检测的PCB检修***，包括自动光学检测设备、数据库服务器和检修设备，所述检修设备上配置有用于验证假 点缺陷的缺陷虚拟检测模块，所述自动光学检测设备、缺陷虚拟检测模块均与所述数据库服务器通信连接；On the one hand, the present invention provides a PCB inspection and repair system based on false point defect detection, including automatic optical inspection equipment, a database server, and inspection equipment. The inspection equipment is equipped with a defect virtual inspection module for verifying false point defects. The automatic optical inspection equipment and the defect virtual inspection module are both in communication connection with the database server;
所述自动光学检测设备用于对待检测的印刷电路板进行扫描得到扫描图像，并将其与通过数据库服务器加载的对应标准图像作比较，以构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息；The automatic optical inspection equipment is used to scan the printed circuit board to be inspected to obtain the scanned image, and compare it with the corresponding standard image loaded through the database server to construct a defect list, the defect list containing corresponding to the Defect coordinate information of the preliminarily determined defect of the scanned image;
所述数据库服务器用于存储所述自动光学检测设备输出的扫描图像及对应的缺陷列表；The database server is used to store the scanned image output by the automatic optical inspection device and the corresponding defect list;
所述检修设备的缺陷虚拟检测模块能够通过所述数据库服务器加载扫描图像及对应的缺陷列表，并对所述扫描图像在缺陷列表中的每个缺陷坐标处的初步判定的缺陷进行一一复检，若复检缺陷为假点缺陷，则将该缺陷从所述缺陷列表中删除，所述检修设备对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修。The defect virtual detection module of the overhaul equipment can load the scanned image and the corresponding defect list through the database server, and perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list If the re-inspection defect is a false point defect, the defect is deleted from the defect list, and the repairing equipment inspects and repairs the defect at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
作为第一种可选技术方案，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排线上存在缺口，若满足任意一个特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷。As a first optional technical solution, the re-examination of the preliminarily determined defect includes: extracting a partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the short circuit feature or the open circuit feature, wherein the short circuit The feature includes a straight line connecting two cables, and the disconnection feature includes a gap on the cable. If any one of the features is satisfied, the defect is determined to be a real defect, otherwise the defect is determined to be a false point defect.
作为第二种可选技术方案，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上特征，则判定所述缺陷为假点缺陷。As a second optional technical solution, the re-inspection of the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image meets the following conditions at the same time: non-linear, irregular and isolated If the existing pattern meets the above characteristics at the same time, the defect is determined to be a false point defect.
作为第三种可选技术方案，对初步判定的缺陷进行复检包括：As the third optional technical solution, the re-inspection of the preliminarily determined defects includes:
通过数据库服务器加载预设的若干个缺陷模板图像，所述缺陷模板图像被标定为真实缺陷或假点缺陷；Load several preset defect template images through the database server, and the defect template images are calibrated as real defects or false point defects;
提取初步判定的缺陷对应的缺陷坐标处的局部图像，并将其与所述缺陷模板图像进行相似度比较，找到与之相似度最高的缺陷模板图像；Extract the partial image at the defect coordinate corresponding to the preliminarily determined defect, compare it with the defect template image for similarity, and find the defect template image with the highest similarity;
若所述相似度最高的缺陷模板图像被标定为真实缺陷，则判定该初步判定的缺陷为真实缺陷；若所述相似度最高的缺陷模板图像被标定为假点缺陷，则判定该初步判定的缺陷为假点缺陷。If the defect template image with the highest similarity is calibrated as a real defect, the preliminarily determined defect is determined to be a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, the preliminarily determined defect is determined The defect is a false point defect.
作为第四种可选技术方案，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，将其输入完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷。As a fourth optional technical solution, the re-inspection of the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, inputting it into the trained neural network model, and outputting according to the neural network model As a result, determine whether the defect is a real defect or a false point defect.
进一步地，对待检测的印刷电路板进行扫描包括采用不同视角角度对PCB进行扫描，得到不同视角视图，所述视角视图包括二维视角视图和三维视角视图。Further, scanning the printed circuit board to be inspected includes scanning the PCB with different perspective angles to obtain different perspective views, and the perspective views include a two-dimensional perspective view and a three-dimensional perspective view.
进一步地，所述检修设备还包括可移动的摄像装置，所述摄像装置能够移动到所述印刷电路板对应缺陷列表中剩余的缺陷坐标处，并对所述缺陷坐标处的缺陷进行放大显示，以供进行人工检修。Further, the maintenance equipment further includes a movable camera device that can be moved to the remaining defect coordinates in the defect list corresponding to the printed circuit board, and the defects at the defect coordinates are enlarged and displayed, For manual overhaul.
进一步地，所述数据库服务器的数量为一个，所述自动光学检测设备和检修设备的数量为多个，所述自动光学检测设备和检修设备的数量相同或者不同。Further, the number of the database server is one, the number of the automatic optical inspection equipment and the maintenance equipment is multiple, and the numbers of the automatic optical inspection equipment and the maintenance equipment are the same or different.
另一方面，本发明提供了一种基于假点缺陷检测的PCB检修方法，包括以下步骤：On the other hand, the present invention provides a PCB inspection and repair method based on false point defect detection, which includes the following steps:
对待检测的印刷电路板进行扫描得到扫描图像；Scan the printed circuit board to be tested to obtain a scanned image;
将其与印刷电路板的标准图像作比较，将差异作为初步判定的缺陷并构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息；Comparing it with the standard image of the printed circuit board, taking the difference as a preliminary judged defect and constructing a defect list, the defect list containing the defect coordinate information of the preliminary judged defect corresponding to the scanned image;
对所述扫描图像在缺陷列表中的每个缺陷坐标处的初步判定的缺陷进行一一复检，若复检缺陷为假点缺陷，则将该缺陷从所述缺陷列表中删除；Perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list, and if the re-examined defect is a false point defect, delete the defect from the defect list;
对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修。Check and repair the defects at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
进一步地，对每一个初步判定的缺陷进行复检包括以下步骤：Further, the re-inspection of each preliminarily determined defect includes the following steps:
提取初步判定的缺陷对应的缺陷坐标处的局部图像，并对所述局部图像按照以下任意一种方式进行判断：Extract the partial image at the defect coordinate corresponding to the preliminarily judged defect, and judge the partial image according to any of the following methods:
第一种方式为判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排线上存在缺口，若满足任意一个特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷；The first way is to determine whether the partial image meets the short-circuit feature or the open-circuit feature, wherein the short-circuit feature includes a straight line connecting two cables, and the open-circuit feature includes a gap in the cable. Feature, the defect is judged to be a real defect, otherwise the defect is judged to be a false point defect;
第二种方式为判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上特征，则判定所述缺陷为假点缺陷；The second method is to judge whether the partial image meets the following conditions at the same time: a non-linear, irregular and isolated figure, if the above characteristics are met at the same time, then the defect is judged to be a false point defect;
第三种方式为将该局部图像与预设的若干个标定为真实缺陷或假点缺陷的缺陷模板图像进行相似度比较，根据相似度最高的缺陷模板图像的标定来判定所述缺陷为真实缺陷还是假点缺陷；The third method is to compare the similarity between the partial image and several preset defect template images calibrated as real defects or false point defects, and determine the defect as a real defect based on the calibration of the defect template image with the highest similarity It's still a fake point defect;
第四种方式为将该局部图像输入至完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷。The fourth method is to input the partial image into the trained neural network model, and determine whether the defect is a real defect or a false point defect according to the output result of the neural network model.
本发明具有如下有益效果：The present invention has the following beneficial effects:
a.将AOI检测到的假点缺陷进行排查，排除不需要检修的假点缺陷后再进行检修，大大提高检修效率；a. Check the false point defects detected by AOI, eliminate the false point defects that do not need to be repaired, and then perform inspections, which greatly improves the efficiency of inspection and repair;
b.通过数据库服务器将AOI与检修设备连接，实现高效的数据传输；b. Connect the AOI to the maintenance equipment through the database server to realize efficient data transmission;
c.检修设备设置可移动的摄像装置，对排除假点缺陷后的真实缺陷进行定位并放大显示，提高人工检修效率；c. The maintenance equipment is equipped with a movable camera device to locate and magnify the real defects after the false point defects are eliminated, so as to improve the efficiency of manual maintenance;
d.多台AOI设备配置一套数据库服务器与多台检修设备连接，节约空间和成本。d. Multiple AOI devices are equipped with a set of database server to connect to multiple maintenance devices, saving space and cost.
附图说明Description of the drawings
被视为本发明的主题在说明书的结论部分中被特别指出并清楚地主张权利。然而，当结合附图一起参阅时，通过参考以下详细描述可以最佳地理解本发明的组织、操作方法，以及主题、特征和优点，其中：The subject matter deemed to be the present invention is specifically pointed out and clearly claimed in the concluding part of the specification. However, when referenced in conjunction with the accompanying drawings, the organization, operating methods, as well as themes, features and advantages of the present invention can be best understood by referring to the following detailed description, in which:
图1是本发明实施例提供的基于假点缺陷检测的PCB检修***的结构示意图；FIG. 1 is a schematic structural diagram of a PCB inspection and repair system based on false point defect detection provided by an embodiment of the present invention;
图2是本发明实施例提供的真实短路缺陷扫描图像的特征示意图；2 is a characteristic schematic diagram of a real short-circuit defect scanned image provided by an embodiment of the present invention;
图3是本发明实施例提供的假点缺陷扫描图像的特征示意图；3 is a schematic diagram of features of a false point defect scanned image provided by an embodiment of the present invention;
图4是本发明实施例提供的多AOI、多VVR对应单数据库服务器的结构示意图；4 is a schematic diagram of the structure of a single database server corresponding to multiple AOIs and multiple VVRs according to an embodiment of the present invention;
图5是本发明实施例提供的采用二维视角扫描PCB得到的二维视角视图；FIG. 5 is a two-dimensional perspective view obtained by scanning a PCB with a two-dimensional perspective according to an embodiment of the present invention;
图6是本发明实施例提供的采用三维视角扫描PCB得到的三维视角视图；FIG. 6 is a three-dimensional perspective view obtained by scanning a PCB with a three-dimensional perspective provided by an embodiment of the present invention;
图7是本发明实施例提供的基于假点缺陷检测的PCB检修方法的流程图。FIG. 7 is a flowchart of a PCB inspection and repair method based on false point defect detection provided by an embodiment of the present invention.
具体实施方式detailed description
在以下详细描述中，阐述了许多具体细节以便提供对本发明的透彻理解。然而，本领域技术人员将理解，可以在没有这些具体细节的情况下实践本发明。在其他情况下，没有详细描述众所周知的方法，过程和组件，以免模糊本发明。In the following detailed description, many specific details are set forth in order to provide a thorough understanding of the present invention. However, those skilled in the art will understand that the present invention can be practiced without these specific details. In other cases, well-known methods, procedures and components have not been described in detail so as not to obscure the present invention.
被视为本发明的主题在说明书的结论部分中被特别指出并清楚地主张权利。然而，当结合附图一起参阅时，通过参考以下详细描述可以最佳地理解本发明的组织、操作方法，以及主题、特征和优点。The subject matter deemed to be the present invention is specifically pointed out and clearly claimed in the concluding part of the specification. However, when referred to in conjunction with the accompanying drawings, the organization, operating methods, and themes, features, and advantages of the present invention can be best understood by referring to the following detailed description.
应当理解，为了说明的简单和清楚，图中所示的元件不一定按比例绘制。例如，为了清楚起见，一些元件的尺寸可能相对于其他元件被放大。It should be understood that, for simplicity and clarity of description, the elements shown in the figures are not necessarily drawn to scale. For example, the size of some elements may be exaggerated relative to other elements for clarity.
由于本发明的说明性实施例在很大程度上可使用本领域技术人员熟知的电子元件和电路来实施，如上文所述，在认为必要的范围之外，不会对细节作更大的解释，以便理解和体会本发明的基本概念，以免混淆或分散本发明的教导。Since the illustrative embodiments of the present invention can be implemented to a large extent using electronic components and circuits well known to those skilled in the art, as described above, the details will not be explained further beyond the scope deemed necessary. In order to understand and appreciate the basic concepts of the present invention, so as not to confuse or distract the teaching of the present invention.
本文中提供了一种基于假点缺陷检测的PCB检修***，参见图1，所述基于假点缺陷检测的PCB检修***包括自动光学检测设备(以下简称AOI)、数据库服务器(data base Server)和检修设备，所述检修设备上配置有用于验证假点缺陷的缺陷虚拟检测模块(又称虚拟验证检测模块，简称VVR)，所述自动光学检测设备、缺陷虚拟检测模块均与所述数据库服务器通信连接；This article provides a PCB inspection system based on false point defect detection. See Figure 1. The PCB inspection system based on false point defect detection includes automatic optical inspection equipment (hereinafter referred to as AOI), database server and Maintenance equipment, which is equipped with a defect virtual detection module (also called virtual verification detection module, VVR) for verifying false point defects, and the automatic optical detection equipment and the defect virtual detection module communicate with the database server connection;
所述自动光学检测设备用于对待检测的印刷电路板进行扫描得到扫描图像，并将其与通过数据库服务器加载的对应标准图像作比较，将比较得到的差异点作为初步判定的缺陷，构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息；The automatic optical inspection equipment is used to scan the printed circuit board to be inspected to obtain the scanned image, and compare it with the corresponding standard image loaded through the database server, and use the difference obtained by the comparison as the preliminary determined defect to construct a defect list , The defect list includes defect coordinate information corresponding to the preliminarily determined defect of the scanned image;
所述数据库服务器用于存储所述自动光学检测设备输出的扫描图像及对应的缺陷列表；The database server is used to store the scanned image output by the automatic optical inspection device and the corresponding defect list;
所述检修设备的缺陷虚拟检测模块能够通过所述数据库服务器加载扫描图像及对应的缺陷列表，并对所述扫描图像在缺陷列表中的每个缺陷坐标处的初步判定的缺陷进行一一复检，若复检缺陷为假点缺陷，则将该缺陷从所述缺陷列表中删除，所述检修设备对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修。The defect virtual detection module of the overhaul equipment can load the scanned image and the corresponding defect list through the database server, and perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list If the re-inspection defect is a false point defect, the defect is deleted from the defect list, and the repairing equipment inspects and repairs the defect at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
如图1所示，AOI设备其在扫描PCB板后，可以得到缺陷的整体布局图片，并能在图片中准确的标定对应缺陷点的坐标，在AOI设备***中，还具有判定 缺陷类型的功能，例如线路板漏焊、多焊和焊接错误等。与AOI连接的是带有数据储存功能的数据库服务器，该数据库服务器可以准确地存储AOI扫描后输入的信息，与数据库服务器连接的是检修设备的VVR***，VVR采集数据库服务器中对应板材的缺陷信息，通过自身的智能判定***或者人工图片验视，可以准确地判断出缺陷信息中“假点”信息和“假点”坐标信息，然后通过操作可以删除判断出来的“假点”信息，在删除“假点”后，通过VVR设备上的Video移动到对应“真点”缺陷坐标位置处进行人工检修。As shown in Figure 1, the AOI equipment can obtain the overall layout picture of the defect after scanning the PCB board, and can accurately calibrate the coordinates of the corresponding defect point in the picture. In the AOI equipment system, it also has the function of determining the defect type. , Such as circuit board missed soldering, multiple soldering and soldering errors. Connected to AOI is a database server with data storage function. The database server can accurately store the information input after AOI scanning. Connected to the database server is the VVR system of overhauling equipment. VVR collects defect information of corresponding plates in the database server. , Through its own intelligent judgment system or manual picture inspection, you can accurately determine the "false point" information and the "false point" coordinate information in the defect information, and then delete the judged "false point" information through the operation. After the "false point", move to the coordinate position corresponding to the "true point" defect through the Video on the VVR device for manual inspection.
相比较之前所有的由AOI扫描出的缺陷点，均需要由单独的检修设备，通过人工对缺陷点逐个检修的方法，减少了大量的工作浪费在“假点”的处理上，不仅提高了工作效率，而且避免了了人工在检修“假点”误判。Compared with all the defect points scanned by AOI before, separate inspection and repair equipment is required to manually inspect and repair the defect points one by one, which reduces a lot of work wasted on the processing of "false points" and not only improves the work It is efficient, and it avoids the misjudgment of artificial “false points” in overhauling.
在本发明的一个优选实施例中，可采用不同视角角度对PCB进行扫描，得到不同视角视图，比如某一对比度、饱和度、色调的二维视图(比如图5)或3D视觉的图像(比如图6)，尤其如图6所示的3D扫描视觉，可以准确地判断出“假点”、“真点”，提高了判断的准确性，不会出现误删“假点”的情况，而且还可以为后续的人工修复提供图像参考，更加方便人工检修。In a preferred embodiment of the present invention, different viewing angles can be used to scan the PCB to obtain different viewing angles, such as a two-dimensional view of a certain contrast, saturation, and hue (such as Figure 5) or a 3D visual image (such as Figure 6), especially the 3D scanning vision shown in Figure 6, can accurately determine "false points" and "true points", improve the accuracy of judgment, and will not delete "false points" by mistake, and It can also provide image reference for subsequent manual repair, which is more convenient for manual repair.
作为第一种可选技术方案，利用排除法对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线(如图2所示)，所述断路特征包括在排线上存在缺口(未图示)，若满足任意一个特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷。“真实缺陷”是需要人工逐个点检修的，如图2中的多焊接的窄缝，会导致PCB短路，这时就需要人工将该窄缝去除。As a first optional technical solution, the re-examination of the preliminarily determined defect by the elimination method includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the short-circuit feature or the open-circuit feature, wherein, The short circuit feature includes a straight line connecting two cables (as shown in FIG. 2), and the open circuit feature includes a gap (not shown) on the cable. If any one of the features is satisfied, the defect is determined It is a real defect, otherwise the defect is judged to be a false point defect. "True defects" need to be manually repaired point by point, as shown in Figure 2 with multiple welded narrow seams, which will cause a short circuit in the PCB. At this time, the narrow seam needs to be manually removed.
作为第二种可选技术方案，利用特征对应法对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形(如图3所示)，若同时满足以上特征，则判定所述缺陷为假点缺陷。所述“假点缺陷”可以是灰尘，污点，或者指纹等，在PCB板材中会大量存在，在AOI扫描时候均会判定为缺陷点，若不智能排除，在后续检修时候，将花费大量人工在这些大量的“假点缺陷”上面，本发明实施例引入VVR***，可以大大减少该方面的时间花费。As a second optional technical solution, using the feature correspondence method to re-examine the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the following conditions at the same time: non-straight, Irregular and isolated graphics (as shown in Figure 3), if the above characteristics are satisfied at the same time, the defect is determined to be a false point defect. The "fake spot defects" can be dust, stains, fingerprints, etc., which will exist in large quantities in the PCB board, and will be judged as defective points during AOI scanning. If it is not eliminated intelligently, it will cost a lot of labor during subsequent maintenance. For these large number of "false point defects", the embodiment of the present invention introduces a VVR system, which can greatly reduce the time spent in this aspect.
作为第三种可选技术方案，利用相似度匹配法对初步判定的缺陷进行复检包括：As a third optional technical solution, using the similarity matching method to re-examine the preliminarily determined defects include:
通过数据库服务器加载预设的若干个缺陷模板图像，所述缺陷模板图像被标定为真实缺陷或假点缺陷；Load several preset defect template images through the database server, and the defect template images are calibrated as real defects or false point defects;
提取初步判定的缺陷对应的缺陷坐标处的局部图像，并将其与所述缺陷模板图像进行相似度比较，找到与之相似度最高的缺陷模板图像；Extract the partial image at the defect coordinate corresponding to the preliminarily determined defect, compare it with the defect template image for similarity, and find the defect template image with the highest similarity;
若所述相似度最高的缺陷模板图像被标定为真实缺陷，则判定该初步判定的缺陷为真实缺陷；若所述相似度最高的缺陷模板图像被标定为假点缺陷，则判定该初步判定的缺陷为假点缺陷。If the defect template image with the highest similarity is calibrated as a real defect, the preliminarily determined defect is determined to be a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, the preliminarily determined defect is determined The defect is a false point defect.
作为第四种可选技术方案，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，将其输入完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷。其中，所述神经网络模型可采用现有技术中的深度神经网络，结合反向传播算法及随机梯度下降法对该神经网络进行训练。As a fourth optional technical solution, the re-inspection of the preliminarily determined defect includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, inputting it into the trained neural network model, and outputting according to the neural network model As a result, determine whether the defect is a real defect or a false point defect. Wherein, the neural network model can be a deep neural network in the prior art, combined with a back propagation algorithm and a stochastic gradient descent method to train the neural network.
对以上四种可选技术方案可以择一进行缺陷复检，也可以选择其中多种甚至全部进行复检，比如优选按照方式一→方式二→方式三→方式四的先后执行顺序对初步判定的缺陷进行复检，最大化地排除假点缺陷，减少浪费在“假点”的处理上的大量工作，提高工作效率。One of the above four optional technical solutions can be selected for defect re-inspection, or multiple or even all of them can be re-inspected. For example, it is preferable to perform the preliminary judgment in the order of mode 1→mode 2→mode 3→mode 4. Defects are re-inspected to maximize the elimination of false point defects, reduce the amount of work wasted on the processing of "false points", and improve work efficiency.
在本发明的一个优选实施例中，所述检修设备还包括可移动的摄像装置，所述摄像装置能够移动到所述印刷电路板对应缺陷列表中剩余的缺陷坐标处，并对所述缺陷坐标处的缺陷进行放大显示，以供进行人工检修。在本实施例中，所述摄像装置有两个作用，第一是移动到当前待检修的缺陷的相对位置处，以提示检修人员对摄像装置当前相对位置处的PCB进行检修；第二是摄像装置能够对当前缺陷区域进行高倍率放大显示，以使检修人员清楚、快速地确定当前要检修的缺陷，避免误检修。In a preferred embodiment of the present invention, the overhaul equipment further includes a movable camera device, which can move to the remaining defect coordinates in the defect list corresponding to the printed circuit board, and check the defect coordinates The defects at the location are enlarged and displayed for manual inspection and repair. In this embodiment, the camera device has two functions. The first is to move to the relative position of the defect currently to be inspected to prompt the maintenance personnel to inspect and repair the PCB at the current relative position of the camera; The device can perform a high-magnification display of the current defect area, so that the maintenance personnel can clearly and quickly determine the current defect to be overhauled, and avoid false inspection and repair.
在本发明的一个优选实施例中，如图4所示，所述数据库服务器的数量为一个，所述自动光学检测设备和检修设备的数量为多个，所述自动光学检测设备和检修设备的数量相同或者不同。为多台AOI设备配置一套数据库服务器与多台VVR***连接，数据库服务器在客户处可以只使用一套即可，其可以配合 多台AOI与VVR同时工作，数据库服务器不仅可以收集单片或者多片PCB缺陷信息，还可以收集多台AOI扫描PCB缺陷信息，这样通过一套数据库服务器就可以工作的***可以节省客户处的空间和成本。In a preferred embodiment of the present invention, as shown in FIG. 4, the number of the database server is one, the number of the automatic optical inspection equipment and the maintenance equipment is multiple, and the number of the automatic optical inspection equipment and the maintenance equipment The quantity is the same or different. Configure one database server for multiple AOI devices to connect to multiple VVR systems. The database server can only use one set at the customer's site. It can work with multiple AOIs and VVRs at the same time. The database server can not only collect single chips or multiple It can also collect multiple AOIs to scan the PCB defect information. In this way, a system that can work through a set of database servers can save space and costs for customers.
在本发明的一个实施例中，提供了一种基于假点缺陷检测的PCB检修方法，如图7所示，所述检修方法包括以下步骤：In an embodiment of the present invention, a PCB repair method based on false point defect detection is provided. As shown in FIG. 7, the repair method includes the following steps:
S1、对待检测的印刷电路板进行扫描得到扫描图像；S1. Scan the printed circuit board to be tested to obtain a scanned image;
S2、将其与印刷电路板的标准图像作比较，将差异作为初步判定的缺陷并构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息；S2. Compare it with the standard image of the printed circuit board, take the difference as a preliminary judged defect, and construct a defect list, the defect list containing the defect coordinate information of the preliminary judged defect corresponding to the scanned image;
S3、开始遍历缺陷列表，比如按序对第一个缺陷坐标处的初步判定的缺陷进行复检；S3. Start traversing the defect list, such as re-inspecting the preliminarily determined defects at the first defect coordinate in order;
S4、若复检的结果为该缺陷为假点缺陷，则执行S5，否则执行S6；S4. If the result of the re-inspection is that the defect is a false point defect, execute S5, otherwise execute S6;
S5、将复检得到的假点缺陷从所述缺陷列表中删除；S5. Delete the false point defect obtained by the re-inspection from the defect list;
S6、判断是否完成对缺陷列表中的缺陷的遍历，若完成，执行S7，否则，遍历缺陷列表中的下一个缺陷坐标处的缺陷并继续执行S4；S6. Judge whether the traversal of the defects in the defect list is completed, if it is completed, execute S7, otherwise, traverse the defect at the next defect coordinate in the defect list and continue to execute S4;
S7、对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修。S7. Check and repair the defects at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
如上述实施例所述，对每一个初步判定的缺陷进行复检包括以下步骤：As described in the above embodiment, the re-inspection of each preliminarily determined defect includes the following steps:
提取初步判定的缺陷对应的缺陷坐标处的局部图像，并对所述局部图像按照以下任意一种或多种方式进行判断：Extract the partial image at the defect coordinate corresponding to the preliminarily judged defect, and judge the partial image according to any one or more of the following methods:
第一种方式为判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排线上存在缺口，若满足任意一个特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷；The first way is to determine whether the partial image meets the short-circuit feature or the open-circuit feature, wherein the short-circuit feature includes a straight line connecting two cables, and the open-circuit feature includes a gap in the cable. Feature, the defect is judged to be a real defect, otherwise the defect is judged to be a false point defect;
第二种方式为判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上特征，则判定所述缺陷为假点缺陷；The second method is to judge whether the partial image meets the following conditions at the same time: a non-linear, irregular and isolated figure, if the above characteristics are met at the same time, then the defect is judged to be a false point defect;
第三种方式为将该局部图像与预设的若干个标定为真实缺陷或假点缺陷的缺陷模板图像进行相似度比较，根据相似度最高的缺陷模板图像的标定来判定所述缺陷为真实缺陷还是假点缺陷；The third method is to compare the similarity between the partial image and several preset defect template images calibrated as real defects or false point defects, and determine the defect as a real defect based on the calibration of the defect template image with the highest similarity It's still a fake point defect;
第四种方式为将该局部图像输入至完成训练的神经网络模型，根据所述神 经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷。The fourth method is to input the partial image into the trained neural network model, and determine whether the defect is a real defect or a false point defect according to the output result of the neural network model.
以上四种方式参见上述实施例详述，在此不再赘述。本发明是将AOI检测后的缺陷坐标、扫描图像(优选地，还包括缺陷的预判类型)通过数据库服务器连接在检修设备上，该检修设备上同时配置有高端的缺陷虚拟检测模块，通过该缺陷虚拟检测模块自动筛选缺陷点，该***将所有的灰阶缺陷图像(有缺陷的扫描图像)分类为“真实”，或者“假”，“假”缺陷被删除，该“假”缺陷可能为灰尘、污垢等，从而可以从检修缺陷列表中删除；或者通过人工验视AOI所提供的灰阶缺陷图，将假的缺陷从检修缺陷列表中删除。然后“真实”的缺陷将被通过摄像机放大，并通过人工进行验收，从而可以节省检修设备对“假”缺陷点进行检测时间。实现工业4.0的转变，不仅节省了大量人工检修时间，减少了人力成本，而且还降低了人工的误判的概率。For the above four methods, please refer to the above-mentioned embodiments for details, and will not be repeated here. The present invention connects the defect coordinates and scanned images (preferably, the pre-judgment type of the defect) detected by AOI to the maintenance equipment through the database server. The maintenance equipment is also equipped with a high-end defect virtual detection module. The defect virtual detection module automatically screens the defect points. The system classifies all gray-scale defect images (defective scanned images) as "real" or "false". The "false" defect is deleted, and the "false" defect may be Dust, dirt, etc., can be deleted from the repair defect list; or through manual inspection of the gray-scale defect map provided by AOI, false defects can be deleted from the repair defect list. Then the "real" defects will be magnified by the camera and accepted manually, which can save the inspection time for the "fake" defects by the maintenance equipment. Realizing the transformation of Industry 4.0 not only saves a lot of manual maintenance time, reduces labor costs, but also reduces the probability of manual misjudgment.
本发明将AOI检测到的假点缺陷进行排查，排除不需要检修的假点缺陷后再进行检修，大大提高检修效率；通过数据库服务器将AOI与检修设备连接，实现高效的数据传输；检修设备设置可移动的摄像装置，对排除假点缺陷后的真实缺陷进行定位并放大显示，提高人工检修效率；多台AOI设备配置一套数据库服务器与多台检修设备连接，节约空间和成本。The present invention checks the false point defects detected by AOI, eliminates false point defects that do not need to be repaired, and then performs repairs, which greatly improves the repair efficiency; connects the AOI to the repair equipment through the database server to realize efficient data transmission; and sets the repair equipment. The movable camera device locates and enlarges the real defects after eliminating the false point defects to improve the efficiency of manual maintenance; multiple AOI devices are equipped with a database server to connect to multiple maintenance devices, saving space and cost.
此外，本领域技术人员将意识到，上述操作之间的界限仅为示例性的。多个操作可以合并为单个操作，单个操作可以分布于额外操作中，且可在至少部分重叠的时间下执行操作。此外，可选实施例可包括特定操作的多个举例说明，并且操作顺序可在各种其他实施例中变化。In addition, those skilled in the art will realize that the boundaries between the above operations are merely exemplary. Multiple operations can be combined into a single operation, a single operation can be distributed in additional operations, and operations can be performed at least partially overlapping times. In addition, alternative embodiments may include multiple illustrations of specific operations, and the order of operations may be changed in various other embodiments.
然而，其他修改、变化及替代也是可能的。因此，应在示例性意义上而非限制性意义上看待说明书及附图。However, other modifications, changes, and substitutions are also possible. Therefore, the description and drawings should be viewed in an exemplary rather than restrictive sense.
在权利要求声明中，置于圆括号之间的任何参考符号不应被视为限制请求项。词语“包括”并不排除那些列在权利要求声明中的其他元件或步骤的存在。此外，本文所使用的术语“一”或“一个”，被定义为一个或多于一个。而且，引言短语例如权利要求声明中的“至少一个”及“一个或多个”的使用不应该解释为暗示不定冠词“一”或“一个”引入另一个权利要求要素将包含这种引入的权利要求的任何特定权利要求限制于仅包含一个这样的要素的发明，即使同一权利要求包括引言短语“一个或多个”或“至少一个”和不定冠词，如“一 个”或“一个”。使用定冠词也是如此。除非另有说明，否则诸如“第一”和“第二”之类的术语用于任意区分这些术语所描述的元素。因此，这些术语不一定旨在表示这些元素的时间或其他优先级。在彼此不同的权利要求中叙述某些措施的仅有事实并不表示这些措施的组合不能加以利用。In the claim statement, any reference signs placed between parentheses shall not be regarded as restrictive claims. The word "comprising" does not exclude the existence of other elements or steps listed in the claims. In addition, the term "a" or "an" as used herein is defined as one or more than one. Moreover, the use of introductory phrases such as "at least one" and "one or more" in a claim statement should not be interpreted as implying that the introduction of the indefinite article "a" or "an" into another claim element will include such introduction. Any particular claim of a claim is limited to an invention that contains only one such element, even if the same claim includes the introductory phrase "one or more" or "at least one" and an indefinite article such as "a" or "an." The same is true for the use of definite articles. Unless otherwise stated, terms such as "first" and "second" are used to arbitrarily distinguish the elements described by these terms. Therefore, these terms are not necessarily intended to indicate the timing or other priority of these elements. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used.
虽然本文已经说明和描述了本发明的某些特征，但是本领域普通技术人员现在将想到许多修改、替换、改变和等同物。因此，应该理解，所附权利要求旨在覆盖落入本发明的真正精神内的所有这些修改和变化。Although certain features of the present invention have been illustrated and described herein, those of ordinary skill in the art will now think of many modifications, substitutions, changes and equivalents. Therefore, it should be understood that the appended claims are intended to cover all these modifications and changes that fall within the true spirit of the present invention.

Claims (16)

  1. 一种基于假点缺陷检测的PCB检修***，其特征在于，包括自动光学检测设备、数据库服务器和检修设备，所述检修设备上配置有用于验证假点缺陷的缺陷虚拟检测模块，所述自动光学检测设备、缺陷虚拟检测模块均与所述数据库服务器通信连接；A PCB inspection and repair system based on false point defect detection, which is characterized in that it includes an automatic optical inspection device, a database server, and an inspection equipment. The inspection equipment is equipped with a defect virtual inspection module for verifying false point defects. Both the detection equipment and the defect virtual detection module are in communication connection with the database server;
    所述自动光学检测设备用于对待检测的印刷电路板进行扫描得到扫描图像，并将其与通过数据库服务器加载的对应标准图像作比较，以构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息；The automatic optical inspection equipment is used to scan the printed circuit board to be inspected to obtain the scanned image, and compare it with the corresponding standard image loaded through the database server to construct a defect list, the defect list containing corresponding to the Defect coordinate information of the preliminarily determined defect of the scanned image;
    所述数据库服务器用于存储所述自动光学检测设备输出的扫描图像及对应的缺陷列表；The database server is used to store the scanned image output by the automatic optical inspection device and the corresponding defect list;
    所述检修设备的缺陷虚拟检测模块能够通过所述数据库服务器加载扫描图像及对应的缺陷列表，并对所述扫描图像在缺陷列表中的每个缺陷坐标处的初步判定的缺陷进行一一复检，若复检缺陷为假点缺陷，则将该缺陷从所述缺陷列表中删除，所述检修设备对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修。The defect virtual detection module of the overhaul equipment can load the scanned image and the corresponding defect list through the database server, and perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list If the re-inspection defect is a false point defect, the defect is deleted from the defect list, and the repairing equipment inspects and repairs the defect at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
  2. 根据权利要求1所述的基于假点缺陷检测的PCB检修***，其特征在于，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排线上存在缺口，若满足任意一个特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷。The PCB inspection system based on false point defect detection according to claim 1, wherein the re-inspection of the preliminarily determined defect comprises: extracting a partial image at the defect coordinate corresponding to the preliminarily determined defect, and determining whether the partial image is Satisfies the short-circuit characteristic or the open-circuit characteristic, wherein the short-circuit characteristic includes a straight line connecting two cables, and the open-circuit characteristic includes a gap in the cable. If any one of the characteristics is satisfied, the defect is determined to be a real defect , Otherwise it is determined that the defect is a false point defect.
  3. 根据权利要求1所述的基于假点缺陷检测的PCB检修***，其特征在于，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上特征，则判定所述缺陷为假点缺陷。The PCB inspection system based on false point defect detection according to claim 1, wherein the re-inspection of the preliminarily determined defect comprises: extracting a partial image at the defect coordinate corresponding to the preliminarily determined defect, and determining whether the partial image is At the same time, the following conditions are met: non-linear, irregular and isolated graphics. If the above characteristics are met at the same time, the defect is determined to be a false point defect.
  4. 根据权利要求1所述的基于假点缺陷检测的PCB检修***，其特征在于，对初步判定的缺陷进行复检包括：The PCB maintenance system based on false point defect detection according to claim 1, wherein the re-inspection of the preliminarily determined defect comprises:
    通过数据库服务器加载预设的若干个缺陷模板图像，所述缺陷模板图像被标定为真实缺陷或假点缺陷；Load several preset defect template images through the database server, and the defect template images are calibrated as real defects or false point defects;
    提取初步判定的缺陷对应的缺陷坐标处的局部图像，并将其与所述缺陷模板图像进行相似度比较，找到与之相似度最高的缺陷模板图像；Extract the partial image at the defect coordinate corresponding to the preliminarily determined defect, compare it with the defect template image for similarity, and find the defect template image with the highest similarity;
    若所述相似度最高的缺陷模板图像被标定为真实缺陷，则判定该初步判定的缺陷为真实缺陷；若所述相似度最高的缺陷模板图像被标定为假点缺陷，则判定该初步判定的缺陷为假点缺陷。If the defect template image with the highest similarity is calibrated as a real defect, the preliminarily determined defect is determined to be a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, the preliminarily determined defect is determined The defect is a false point defect.
  5. 根据权利要求1所述的基于假点缺陷检测的PCB检修***，其特征在于，对初步判定的缺陷进行复检包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，将其输入完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷。The PCB maintenance system based on false point defect detection according to claim 1, wherein the re-inspection of the preliminarily determined defect comprises: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect and inputting it to complete the training According to the neural network model output by the neural network model, it is determined whether the defect is a real defect or a false point defect.
  6. 根据权利要求1所述的基于假点缺陷检测的PCB检修***，其特征在于，对待检测的印刷电路板进行扫描包括采用不同视角角度对PCB进行扫描，得到不同视角视图，所述视角视图包括二维视角视图和三维视角视图。The PCB inspection system based on false point defect detection according to claim 1, wherein scanning the printed circuit board to be inspected comprises scanning the PCB with different viewing angles to obtain different viewing angle views, and the viewing angle views include two Three-dimensional perspective view and three-dimensional perspective view.
  7. 根据权利要求1所述的基于假点缺陷检测的PCB检修***，其特征在于，所述检修设备还包括可移动的摄像装置，所述摄像装置能够移动到所述印刷电路板对应缺陷列表中剩余的缺陷坐标处。The PCB repair system based on false point defect detection according to claim 1, wherein the repair equipment further comprises a movable camera device, the camera device can be moved to the remaining defect list corresponding to the printed circuit board The coordinates of the defect.
  8. 根据权利要求7所述的基于假点缺陷检测的PCB检修***，其特征在于，所述摄像装置还用于对所述缺陷坐标处的缺陷进行放大显示，以供进行人工检修。The PCB inspection and repair system based on false point defect detection according to claim 7, wherein the camera device is also used to enlarge and display the defects at the defect coordinates for manual inspection and repair.
  9. 根据权利要求1-8中任意一项所述的基于假点缺陷检测的PCB检修***，其特征在于，所述数据库服务器的数量为一个，所述自动光学检测设备和 检修设备的数量为多个，所述自动光学检测设备和检修设备的数量相同或者不同。The PCB repair system based on false point defect detection according to any one of claims 1-8, wherein the number of the database server is one, and the number of the automatic optical inspection equipment and the repair equipment is multiple , The number of the automatic optical inspection equipment and the maintenance equipment is the same or different.
  10. 一种基于假点缺陷检测的PCB检修方法，其特征在于，包括以下步骤：A PCB inspection and repair method based on false point defect detection is characterized in that it includes the following steps:
    对待检测的印刷电路板进行扫描得到扫描图像；Scan the printed circuit board to be tested to obtain a scanned image;
    将其与印刷电路板的标准图像作比较，将差异作为初步判定的缺陷并构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息；Comparing it with the standard image of the printed circuit board, taking the difference as a preliminary judged defect and constructing a defect list, the defect list containing the defect coordinate information of the preliminary judged defect corresponding to the scanned image;
    对所述扫描图像在缺陷列表中的每个缺陷坐标处的初步判定的缺陷进行一一复检，若复检缺陷为假点缺陷，则将该缺陷从所述缺陷列表中删除；Perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list, and if the re-examined defect is a false point defect, delete the defect from the defect list;
    对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修。Check and repair the defects at the remaining defect coordinates in the defect list corresponding to the printed circuit board.
  11. 根据权利要求10所述的基于假点缺陷检测的PCB检修方法，其特征在于，对每一个初步判定的缺陷进行复检包括以下步骤：The PCB repair method based on false point defect detection according to claim 10, wherein the re-inspection of each preliminarily determined defect comprises the following steps:
    提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排线上存在缺口，若满足任意一个特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷。Extract the partial image at the defect coordinates corresponding to the preliminarily determined defect, and determine whether the partial image satisfies the short-circuit feature or the open-circuit feature, where the short-circuit feature includes a straight line connecting two rows of lines, and the open-circuit feature includes There is a gap on the line, if any one of the characteristics is satisfied, the defect is determined to be a real defect, otherwise the defect is determined to be a false point defect.
  12. 根据权利要求10所述的基于假点缺陷检测的PCB检修方法，其特征在于，对每一个初步判定的缺陷进行复检包括以下步骤：The PCB repair method based on false point defect detection according to claim 10, wherein the re-inspection of each preliminarily determined defect comprises the following steps:
    提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上特征，则判定所述缺陷为假点缺陷。Extract the partial image at the defect coordinate corresponding to the preliminarily judged defect, and judge whether the partial image satisfies the following conditions at the same time: a non-linear, irregular and isolated figure. If the above characteristics are met at the same time, the defect is judged to be a false point defect .
  13. 根据权利要求10所述的基于假点缺陷检测的PCB检修方法，其特征在于，对每一个初步判定的缺陷进行复检包括以下步骤：The PCB repair method based on false point defect detection according to claim 10, wherein the re-inspection of each preliminarily determined defect comprises the following steps:
    提取初步判定的缺陷对应的缺陷坐标处的局部图像，将该局部图像与预设的若干个标定为真实缺陷或假点缺陷的缺陷模板图像进行相似度比较，根据相 似度最高的缺陷模板图像的标定来判定所述缺陷为真实缺陷还是假点缺陷。Extract the partial image at the defect coordinate corresponding to the preliminarily judged defect, compare this partial image with a number of preset defect template images calibrated as real defects or false point defects, and compare the similarity according to the defect template image with the highest similarity. Calibration is used to determine whether the defect is a real defect or a false point defect.
  14. 根据权利要求10所述的基于假点缺陷检测的PCB检修方法，其特征在于，对每一个初步判定的缺陷进行复检包括以下步骤：The PCB repair method based on false point defect detection according to claim 10, wherein the re-inspection of each preliminarily determined defect comprises the following steps:
    提取初步判定的缺陷对应的缺陷坐标处的局部图像，将该局部图像输入至完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷。The partial image at the defect coordinate corresponding to the preliminarily determined defect is extracted, and the partial image is input to the trained neural network model, and according to the output result of the neural network model, it is determined whether the defect is a real defect or a false point defect.
  15. 一种基于假点缺陷检测的PCB检修***，其特征在于，包括自动光学检测设备、数据库服务器和检修设备，所述检修设备上配置有用于验证假点缺陷的缺陷虚拟检测模块，所述自动光学检测设备、缺陷虚拟检测模块均与所述数据库服务器通信连接；A PCB inspection and repair system based on false point defect detection, which is characterized in that it includes an automatic optical inspection device, a database server, and an inspection equipment. The inspection equipment is equipped with a defect virtual inspection module for verifying false point defects. Both the detection equipment and the defect virtual detection module are in communication connection with the database server;
    所述自动光学检测设备用于采用不同视角角度对待检测的印刷电路板进行扫描得到不同视角的扫描图像，并将其与通过数据库服务器加载的对应标准图像作比较，将比较得到的差异点作为初步判定的缺陷，构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息及其缺陷类型，所述缺陷类型包括线路板漏焊、多焊和焊接错误；The automatic optical inspection equipment is used to scan the printed circuit board to be inspected with different viewing angles to obtain scanned images of different viewing angles, and compare them with the corresponding standard images loaded through the database server, and use the difference points obtained from the comparison as preliminary Determined defects, constructing a defect list, the defect list contains the defect coordinate information and defect types of the preliminary determined defects corresponding to the scanned image, and the defect types include circuit board missed soldering, multiple soldering, and soldering errors;
    所述数据库服务器用于存储所述自动光学检测设备输出的扫描图像及对应的缺陷列表；The database server is used to store the scanned image output by the automatic optical inspection device and the corresponding defect list;
    所述检修设备的缺陷虚拟检测模块能够通过所述数据库服务器加载扫描图像及对应的缺陷列表，并对所述扫描图像在缺陷列表中的每个缺陷坐标处的初步判定的缺陷进行一一复检，若复检缺陷为假点缺陷，则将该缺陷从所述缺陷列表中删除，所述检修设备对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修；The defect virtual detection module of the overhaul equipment can load the scanned image and the corresponding defect list through the database server, and perform one-by-one re-examination of the preliminarily determined defects of the scanned image at each defect coordinate in the defect list , If the re-inspection defect is a false point defect, the defect is deleted from the defect list, and the repairing equipment inspects the defect at the remaining defect coordinates in the defect list corresponding to the printed circuit board;
    所述缺陷虚拟检测模块结合以下四种方式对每个缺陷坐标处的初步判定的缺陷进行一一复检：The defect virtual detection module combines the following four methods to re-check the preliminarily determined defects at each defect coordinate:
    利用排除法对初步判定的缺陷进行复检，包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排 线上存在缺口，若满足短路特征或者断路特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷；The re-examination of the preliminarily determined defect by the elimination method includes: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the short circuit feature or the open circuit feature, wherein the short circuit feature includes Two straight lines of the cable, the disconnection feature includes a gap in the cable, if the short-circuit feature or the disconnection feature is satisfied, the defect is determined to be a real defect, otherwise the defect is determined to be a false point defect;
    利用特征对应法对初步判定的缺陷进行复检，包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上条件，则判定所述缺陷为假点缺陷；Using feature correspondence method to re-examine the preliminarily determined defect, including: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the following conditions at the same time: non-linear, irregular and isolated graphics, If the above conditions are met at the same time, the defect is judged to be a false point defect;
    利用相似度匹配法对初步判定的缺陷进行复检，包括：通过数据库服务器加载预设的若干个缺陷模板图像，所述缺陷模板图像被标定为真实缺陷或假点缺陷；提取初步判定的缺陷对应的缺陷坐标处的局部图像，并将其与所述缺陷模板图像进行相似度比较，找到与之相似度最高的缺陷模板图像；若所述相似度最高的缺陷模板图像被标定为真实缺陷，则判定该初步判定的缺陷为真实缺陷；若所述相似度最高的缺陷模板图像被标定为假点缺陷，则判定该初步判定的缺陷为假点缺陷；Using the similarity matching method to re-examine the preliminarily determined defects, including: loading several preset defect template images through the database server, the defect template images are calibrated as real defects or false point defects; extracting the corresponding defects of the preliminary judgment And compare it with the defect template image to find the defect template image with the highest similarity; if the defect template image with the highest similarity is calibrated as a real defect, Determine that the preliminarily determined defect is a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, then determine that the preliminarily determined defect is a false point defect;
    利用神经网络模型对初步判定的缺陷进行复检，包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，将其输入完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷，其中，所述神经网络模型为深度神经网络，结合反向传播算法及随机梯度下降法进行训练而得到。Using a neural network model to re-examine the preliminarily determined defect, including: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, inputting it into the trained neural network model, and determining according to the output result of the neural network model Whether the defect is a real defect or a false point defect, wherein the neural network model is a deep neural network, which is obtained by training in combination with a back propagation algorithm and a stochastic gradient descent method.
  16. 一种基于假点缺陷检测的PCB检修方法，其特征在于，包括以下步骤：A PCB inspection and repair method based on false point defect detection is characterized in that it includes the following steps:
    S1、采用不同视角角度对待检测的印刷电路板进行扫描得到不同视角的扫描图像；S1. Scanning the printed circuit board to be tested with different viewing angles to obtain scanned images of different viewing angles;
    S2、将其与印刷电路板的标准图像作比较，将差异作为初步判定的缺陷并构建缺陷列表，所述缺陷列表中包含对应于所述扫描图像的初步判定的缺陷的缺陷坐标信息及其缺陷类型，所述缺陷类型包括线路板漏焊、多焊和焊接错误；S2. Compare it with the standard image of the printed circuit board, take the difference as a preliminary judged defect, and construct a defect list, which contains the defect coordinate information of the preliminary judged defect corresponding to the scanned image and its defect Type, the defect type includes missing soldering, multiple soldering and soldering errors on the circuit board;
    S3、开始遍历缺陷列表，按序对第一个缺陷坐标处的初步判定的缺陷进行复检；S3. Start to traverse the defect list, and re-check the preliminarily determined defects at the first defect coordinate in order;
    S4、若复检的结果为该缺陷为假点缺陷，则执行S5，否则执行S6；S4. If the result of the re-inspection is that the defect is a false point defect, execute S5, otherwise execute S6;
    S5、将复检得到的假点缺陷从所述缺陷列表中删除；S5. Delete the false point defect obtained by the re-inspection from the defect list;
    S6、判断是否完成对缺陷列表中的缺陷的遍历，若完成，执行S7，否则，遍历缺陷列表中的下一个缺陷坐标处的缺陷并继续执行S4；S6. Judge whether the traversal of the defects in the defect list is completed, if it is completed, execute S7, otherwise, traverse the defect at the next defect coordinate in the defect list and continue to execute S4;
    S7、对所述印刷电路板对应缺陷列表中剩余的缺陷坐标处的缺陷进行检修；S7. Check and repair the defects at the remaining defect coordinates in the defect list corresponding to the printed circuit board;
    其中，步骤S3中对缺陷坐标处的初步判定的缺陷进行复检的方式包括：Wherein, the method of re-inspecting the preliminary determined defect at the defect coordinate in step S3 includes:
    先利用排除法对初步判定的缺陷进行复检，包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否满足短路特征或者断路特征，其中，所述短路特征包括具有连接着两根排线的直线，所述断路特征包括在排线上存在缺口，若满足短路特征或者断路特征，则判定所述缺陷为真实缺陷，否则判定所述缺陷为假点缺陷；First use the elimination method to re-examine the preliminarily determined defect, including: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image satisfies the short circuit feature or the open circuit feature, wherein the short circuit feature includes If the short circuit feature or the open circuit feature is satisfied, the defect is judged to be a real defect, otherwise the defect is judged to be a false point defect;
    后利用特征对应法对初步判定的缺陷进行复检，包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，判断该局部图像是否同时满足以下条件：非直线、不规则且孤立存在的图形，若同时满足以上条件，则判定所述缺陷为假点缺陷；The feature correspondence method is then used to re-examine the preliminarily determined defect, including: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, and judging whether the partial image meets the following conditions at the same time: non-linear, irregular and isolated graphics , If the above conditions are met at the same time, the defect is judged to be a false point defect;
    再利用相似度匹配法对初步判定的缺陷进行复检，包括：通过数据库服务器加载预设的若干个缺陷模板图像，所述缺陷模板图像被标定为真实缺陷或假点缺陷；提取初步判定的缺陷对应的缺陷坐标处的局部图像，并将其与所述缺陷模板图像进行相似度比较，找到与之相似度最高的缺陷模板图像；若所述相似度最高的缺陷模板图像被标定为真实缺陷，则判定该初步判定的缺陷为真实缺陷；若所述相似度最高的缺陷模板图像被标定为假点缺陷，则判定该初步判定的缺陷为假点缺陷；Re-check the preliminarily determined defects by using the similarity matching method, including: loading a number of preset defect template images through the database server, the defect template images are calibrated as real defects or false point defects; extracting the preliminarily determined defects The corresponding partial image at the defect coordinates, and compare it with the defect template image to find the defect template image with the highest similarity; if the defect template image with the highest similarity is calibrated as a real defect, Determine that the preliminarily determined defect is a real defect; if the defect template image with the highest similarity is calibrated as a false point defect, then determine that the preliminarily determined defect is a false point defect;
    最后利用神经网络模型对初步判定的缺陷进行复检，包括：提取初步判定的缺陷对应的缺陷坐标处的局部图像，将其输入完成训练的神经网络模型，根据所述神经网络模型输出的结果，判定所述缺陷为真实缺陷还是假点缺陷，其中，所述神经网络模型为深度神经网络，结合反向传播算法及随机梯度下降法进行训练而得到。Finally, the neural network model is used to re-examine the preliminarily determined defect, including: extracting the partial image at the defect coordinate corresponding to the preliminarily determined defect, inputting it into the trained neural network model, and according to the output result of the neural network model, It is determined whether the defect is a real defect or a false point defect, wherein the neural network model is a deep neural network, which is obtained by training in combination with a back propagation algorithm and a stochastic gradient descent method.
PCT/CN2019/121165 2019-08-09 2019-11-27 Pcb maintenance system and maintenance method based on false point defect detection WO2021027184A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020227007669A KR20220041212A (en) 2019-08-09 2019-11-27 PCB maintenance system and maintenance method based on false point defect detection

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910732889.5A CN110579479A (en) 2019-08-09 2019-08-09 PCB maintenance system and maintenance method based on false point defect detection
CN201910732889.5 2019-08-09

Publications (1)

Publication Number Publication Date
WO2021027184A1 true WO2021027184A1 (en) 2021-02-18

Family

ID=68810656

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/121165 WO2021027184A1 (en) 2019-08-09 2019-11-27 Pcb maintenance system and maintenance method based on false point defect detection

Country Status (4)

Country Link
KR (1) KR20220041212A (en)
CN (1) CN110579479A (en)
TW (1) TWI757825B (en)
WO (1) WO2021027184A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113538341A (en) * 2021-03-31 2021-10-22 联合汽车电子有限公司 Automatic optical detection auxiliary method, device and storage medium
CN113609897A (en) * 2021-06-23 2021-11-05 阿里巴巴新加坡控股有限公司 Defect detection method and defect detection system
CN114280079A (en) * 2021-12-27 2022-04-05 昆山柏特电子有限公司 Improvement method of AOI test process for printed circuit board production
EP4057230A1 (en) * 2021-03-12 2022-09-14 AT&S (Chongqing) Company Limited Manufacturing method of a component carrier, handling system, computer program and system architecture
CN115063286A (en) * 2022-08-08 2022-09-16 江苏时代新能源科技有限公司 Detection system and image processing method
CN117409261A (en) * 2023-12-14 2024-01-16 成都数之联科技股份有限公司 Element angle classification method and system based on classification model

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111353983B (en) * 2020-02-28 2023-05-23 腾讯科技（深圳）有限公司 Defect detection identification method, device, computer readable medium and electronic equipment
CN111768371A (en) * 2020-06-05 2020-10-13 上海展华电子(南通)有限公司 AOI intelligent maintenance method and device, computer equipment and storage medium
CN111812118A (en) * 2020-06-24 2020-10-23 阿丘机器人科技(苏州)有限公司 PCB detection method, device, equipment and computer readable storage medium
CN111707677A (en) * 2020-06-24 2020-09-25 江西景旺精密电路有限公司 PCB appearance detection method and device
CN111808367B (en) * 2020-07-09 2023-05-30 浙江七色鹿色母粒有限公司 Improvement method for plastic PPR silver grain whitening defect
CN114441554B (en) * 2020-11-06 2023-09-29 李明苍 Detection method
KR20230078729A (en) * 2020-11-18 2023-06-02 심스 쑤저우 컴퍼니 리미티드 Printed circuit board remote optical maintenance method and system
CN112415973B (en) * 2020-11-24 2022-05-17 广州广合科技股份有限公司 Intelligent control method and system for inner layer AOI (automated optical inspection) process
CN113012097B (en) * 2021-01-19 2023-12-29 富泰华工业（深圳）有限公司 Image rechecking method, computer device and storage medium
CN112964737A (en) * 2021-02-04 2021-06-15 鼎勤科技(深圳)有限公司 Double-sided appearance detection method of circuit board
TWI745256B (en) * 2021-04-12 2021-11-01 南亞塑膠工業股份有限公司 Operation management system
CN113138529B (en) * 2021-04-23 2024-04-09 成都路维光电有限公司 Mask defect detection method and system based on AOI system
CN113030123B (en) * 2021-05-27 2021-08-24 安福得鑫智能设备有限公司 AOI detection feedback system based on Internet of things
CN113554626A (en) * 2021-07-26 2021-10-26 朗华全能自控设备（上海）股份有限公司 Method and device for detecting defects of flexible circuit board
TWI786894B (en) * 2021-10-20 2022-12-11 國立清華大學 Detection method
CN114782431B (en) * 2022-06-20 2022-10-14 苏州康代智能科技股份有限公司 Printed circuit board defect detection model training method and defect detection method
CN115754670B (en) * 2022-11-15 2023-07-18 广东炬森智能装备有限公司 Repairing and rechecking method and device for short circuit defect of PCB
CN116967615B (en) * 2023-07-31 2024-04-12 上海感图网络科技有限公司 Circuit board reinspection marking method, device, equipment and storage medium
CN117372368A (en) * 2023-10-17 2024-01-09 苏州真目人工智能科技有限公司 Appearance detection device and method based on cascade closed-loop deep learning algorithm

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003344309A (en) * 2002-05-30 2003-12-03 Olympus Optical Co Ltd Method of setting parameter for inspection equipment
CN201440128U (en) * 2009-07-13 2010-04-21 北京航星科技有限公司 Automatic optical detection system for PCB defect detection
CN103926254A (en) * 2014-05-08 2014-07-16 康代影像科技(苏州)有限公司 Statistical system and method used for PCB defect detection
CN106897994A (en) * 2017-01-20 2017-06-27 北京京仪仪器仪表研究总院有限公司 A kind of pcb board defect detecting system and method based on layered image
CN107093174A (en) * 2017-04-05 2017-08-25 湖北工业大学 A kind of PCB design defect inspection method
CN207908385U (en) * 2017-12-13 2018-09-25 深圳市光速达机器人科技有限公司 A kind of pcb board weld defect self-checking system that view-based access control model is differentiated
CN109752392A (en) * 2018-12-24 2019-05-14 苏州江奥光电科技有限公司 A kind of pcb board defect type detection system and method
CN109936927A (en) * 2019-04-10 2019-06-25 奥蒂玛光学科技（深圳）有限公司 Circuit board renovation method and system
CN110006903A (en) * 2018-01-05 2019-07-12 皓琪科技股份有限公司 Printed circuit board rechecks system, marker method and reinspection method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2000270373A1 (en) * 2000-09-10 2002-03-22 Orbotech Ltd. Reduction of false alarms in pcb inspection
US8290239B2 (en) * 2005-10-21 2012-10-16 Orbotech Ltd. Automatic repair of electric circuits
US20080002874A1 (en) * 2006-06-29 2008-01-03 Peter Fiekowsky Distinguishing reference image errors in optical inspections
TWI703514B (en) * 2018-05-24 2020-09-01 牧德科技股份有限公司 Artificial intelligence recheck system and method thereof

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003344309A (en) * 2002-05-30 2003-12-03 Olympus Optical Co Ltd Method of setting parameter for inspection equipment
CN201440128U (en) * 2009-07-13 2010-04-21 北京航星科技有限公司 Automatic optical detection system for PCB defect detection
CN103926254A (en) * 2014-05-08 2014-07-16 康代影像科技(苏州)有限公司 Statistical system and method used for PCB defect detection
CN106897994A (en) * 2017-01-20 2017-06-27 北京京仪仪器仪表研究总院有限公司 A kind of pcb board defect detecting system and method based on layered image
CN107093174A (en) * 2017-04-05 2017-08-25 湖北工业大学 A kind of PCB design defect inspection method
CN207908385U (en) * 2017-12-13 2018-09-25 深圳市光速达机器人科技有限公司 A kind of pcb board weld defect self-checking system that view-based access control model is differentiated
CN110006903A (en) * 2018-01-05 2019-07-12 皓琪科技股份有限公司 Printed circuit board rechecks system, marker method and reinspection method
CN109752392A (en) * 2018-12-24 2019-05-14 苏州江奥光电科技有限公司 A kind of pcb board defect type detection system and method
CN109936927A (en) * 2019-04-10 2019-06-25 奥蒂玛光学科技（深圳）有限公司 Circuit board renovation method and system

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4057230A1 (en) * 2021-03-12 2022-09-14 AT&S (Chongqing) Company Limited Manufacturing method of a component carrier, handling system, computer program and system architecture
CN113538341A (en) * 2021-03-31 2021-10-22 联合汽车电子有限公司 Automatic optical detection auxiliary method, device and storage medium
CN113538341B (en) * 2021-03-31 2024-04-30 联合汽车电子有限公司 Automatic optical detection assisting method, device and storage medium
CN113609897A (en) * 2021-06-23 2021-11-05 阿里巴巴新加坡控股有限公司 Defect detection method and defect detection system
CN114280079A (en) * 2021-12-27 2022-04-05 昆山柏特电子有限公司 Improvement method of AOI test process for printed circuit board production
CN115063286A (en) * 2022-08-08 2022-09-16 江苏时代新能源科技有限公司 Detection system and image processing method
CN117409261A (en) * 2023-12-14 2024-01-16 成都数之联科技股份有限公司 Element angle classification method and system based on classification model
CN117409261B (en) * 2023-12-14 2024-02-20 成都数之联科技股份有限公司 Element angle classification method and system based on classification model

Also Published As

Publication number Publication date
CN110579479A (en) 2019-12-17
KR20220041212A (en) 2022-03-31
TWI757825B (en) 2022-03-11
TW202107073A (en) 2021-02-16

Similar Documents

Publication Publication Date Title
WO2021027184A1 (en) Pcb maintenance system and maintenance method based on false point defect detection
TWI667575B (en) Defect inspection system and method using artificil intelligence
JP6988499B2 (en) Inspection management system, inspection management device, inspection management method
Janóczki et al. Automatic optical inspection of soldering
Sanz et al. Machine-vision techniques for inspection of printed wiring boards and thick-film circuits
CN109142380A (en) The fault detection method of circuit board, device and system
CN106501978B (en) A kind of analysis method and analytical equipment of display panel flame
KR20040107439A (en) Apparatus for inspecting printed wiring boards for mounting electronic component and method of verifing a bad pattern
JP2007285880A (en) Sample image registration method in board inspection, and sample image producing system
JP2002277412A (en) Inspection screen displaying method and substrate inspection system
TWI244359B (en) Automatic optical detecting system for defect components on printed circuit board
JP2006251561A (en) Defective pixel repairing method
Malge et al. A survey: Automated visual pcb inspection algorithm
CN115511791A (en) Liquid crystal grating function detection method and system
JP2008186879A (en) Substrate inspection method
CN110763703A (en) Projection type system for assisting printed circuit board in quick positioning, fixed-point amplification and observation
JP6027717B2 (en) Visual inspection apparatus provided with gaze position specifying means
CN214201239U (en) Remote optical maintenance system for printed circuit board
JPH0964600A (en) Method for indicating checked output
TWI769688B (en) A method and system for remote optical overhaul of printed circuit board
JP4507785B2 (en) Substrate inspection device, parameter setting method and parameter setting device
CN216870414U (en) Device for detecting appearance defects of whole plate element
KR102321444B1 (en) Wiring product inspection support apparatus
CN110196504B (en) Interference stain shielding method and system applied to AOI (automated optical inspection) test of LCD (liquid Crystal display) glass
TW202134634A (en) Attached re-inspection system, and attached re-inspection method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19941315

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20227007669

Country of ref document: KR

Kind code of ref document: A

122 Ep: pct application non-entry in european phase

Ref document number: 19941315

Country of ref document: EP

Kind code of ref document: A1