PCB (Printed Circuit Board) defect optical detection monitoring method and device, computer equipment and storage medium

Abstract

The invention provides a PCB defect optical detection monitoring method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring board surface optical defect identification parameters of a PCB (Printed Circuit Board); carrying out filtering likelihood loss processing on the plate surface optical defect identification parameter and a preset defect identification parameter to obtain a plate surface defect loss amount; and sending a defect filtering loss signal to an AOI automatic detection system according to the plate surface defect loss amount so as to adjust a defect filtering mode on the PCB. After board optical defect identification parameters are collected, the current optical defect forming state of the PCB is determined, then the board optical defect identification parameters are compared with standard defect identification parameters, the defect identification difference condition of the optical defect forming state of the PCB is conveniently determined, and finally, according to the defect identification difference condition, the optical defect forming state of the PCB is identified according to the defect identification difference condition. And the defect filtering mode of the PCB is adjusted, so that non-defects of the PCB can be filtered in time.

Description

Technical Field

[0001] This disclosure relates to the field of PCB board technology, and in particular to a method, apparatus, computer equipment, and storage medium for optical inspection and monitoring of PCB board defects. Background Technology

[0002] Currently, many common defects occur during the PCB manufacturing process, such as cold solder joints, solder pad corrosion, drilling errors, solder short circuits, solder ball defects, drill residue, solder paste overflow, insulation layer cracks, circuit breaks, and poor packaging. Therefore, PCBs must undergo quality inspection after production. In existing technologies, quality inspection of post-production PCBs relies solely on manual methods, visually identifying defects. The reliability, accuracy, false positive rate, and speed of this inspection method are all limited by human experience and operational efficiency.

[0003] With the development of information technology, the advantages of advanced technologies such as machine learning and artificial intelligence have gradually spread to various industries. Advances in computer vision technology have made it possible for machine inspection to replace manual inspection. Automated Optical Inspection (AOI) technology is a process technology based on optical principles to detect common defects encountered in production, characterized by high-speed and high-precision visual processing. However, traditional AOI technology only marks possible defects on the board surface and cannot accurately distinguish actual defects. It often mistakenly identifies normal holes and positioning slots / lines on the board as defects, resulting in an excessively high rework rate for PCB boards. Ultimately, manual re-inspection is still required, leading to low PCB board production efficiency. Summary of the Invention

[0004] The purpose of this disclosure is to overcome the shortcomings of the prior art and provide a method, apparatus, computer equipment, and storage medium for optical inspection and monitoring of PCB board defects that effectively improves the inspection efficiency of PCB boards.

[0005] The purpose of this disclosure is achieved through the following technical solution: A method for optical inspection and monitoring of defects in PCB boards, the method comprising: Obtain the optical defect identification parameters of the PCB board surface; The optical defect identification parameters of the board surface and the preset defect identification parameters are subjected to defect filtering likelihood loss processing to obtain the defect loss amount of the board surface. Based on the amount of defect loss on the board surface, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board.

[0006] In one embodiment, obtaining optical defect identification parameters of the PCB board surface includes: obtaining the maximum width of pits and cracks on the PCB board.

[0007] In one embodiment, the optical defect identification parameters of the board surface and the preset defect identification parameters are subjected to defect likelihood loss processing to obtain the defect loss amount of the board surface, including: calculating the width likelihood loss between the maximum width of the pit and the preset width to obtain the width loss of the pit and crack of the board surface.

[0008] In one embodiment, a defect filtering failure signal is sent to the AOI automatic inspection system based on the amount of board surface defect loss to adjust the defect filtering mode on the PCB board, including: detecting whether the width loss of the board surface pits and cracks is greater than or equal to a preset width loss; when the width loss of the board surface pits and cracks is greater than or equal to the preset width loss, a pit and crack defect filtering failure signal is sent to the AOI automatic inspection system.

[0009] In one embodiment, obtaining optical defect identification parameters of the PCB board surface includes: obtaining the area of ​​laser black spots on the PCB board.

[0010] In one embodiment, the optical defect identification parameters of the board surface and the preset defect identification parameters are subjected to defect filtering likelihood loss processing to obtain the board surface defect loss amount, including: calculating the area likelihood loss of the laser black spot area and the preset area to obtain the black spot area loss of the board surface.

[0011] In one embodiment, a defect filtering failure signal is sent to the AOI automatic inspection system according to the amount of board surface defect loss, so as to adjust the defect filtering mode on the PCB board, including: detecting whether the black spot surface loss of the board surface is greater than or equal to a preset surface loss; when the black spot surface loss of the board surface is less than the preset surface loss, a black spot defect filtering enable signal is sent to the AOI automatic inspection system.

[0012] A PCB board defect optical inspection and monitoring device, wherein the PCB board defect optical inspection and monitoring device adopts the PCB board defect optical inspection and monitoring method described in any of the above embodiments, comprising: a board surface defect acquisition module, a defect loss processing module, and a defect filtering and control module; the board surface defect acquisition module is used to acquire board surface optical defect identification parameters of the PCB board; the defect loss processing module is used to perform defect likelihood loss processing on the board surface optical defect identification parameters and preset defect identification parameters to obtain the board surface defect loss amount; the defect filtering and control module is used to send a defect filtering failure signal to the AOI automatic inspection system according to the board surface defect loss amount to adjust the defect filtering mode on the PCB board.

[0013] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps: Obtain the optical defect identification parameters of the PCB board surface; The optical defect identification parameters of the board surface and the preset defect identification parameters are subjected to defect filtering likelihood loss processing to obtain the defect loss amount of the board surface. Based on the amount of defect loss on the board surface, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board.

[0014] A computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, performs the following steps: Obtain the optical defect identification parameters of the PCB board surface; The optical defect identification parameters of the board surface and the preset defect identification parameters are subjected to defect filtering likelihood loss processing to obtain the defect loss amount of the board surface. Based on the amount of defect loss on the board surface, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board.

[0015] Compared with the prior art, this disclosure has at least the following advantages: After collecting the optical defect identification parameters of the PCB board, the current optical defect formation state of the PCB board is determined. Then, the optical defect identification parameters of the PCB board are compared with the standard defect identification parameters to determine the defect identification differences of the optical defect formation state of the PCB board. Finally, based on the above defect identification differences, the defect filtering mode of the PCB board is adjusted to provide feedback adjustment of the defect filtering method of the PCB board, so as to facilitate timely filtering of non-defects on the PCB board and effectively improve the PCB board inspection efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a PCB board defect optical inspection and monitoring method in one embodiment; Figure 2 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0018] To facilitate understanding of this disclosure, a more complete description will be given below with reference to the accompanying drawings, which illustrate preferred embodiments of the present disclosure. However, this disclosure can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure.

[0019] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] This disclosure relates to a method for optical inspection and monitoring of defects in PCB boards. In one embodiment, the method includes acquiring optical defect identification parameters of the PCB board surface; performing a filtering likelihood loss process on the optical defect identification parameters and preset defect identification parameters to obtain a defect loss amount; and sending a defect filtering failure signal to an AOI (Automated Optical Inspection) system based on the defect loss amount to adjust the defect filtering mode on the PCB board. After acquiring the optical defect identification parameters, the current optical defect formation state of the PCB board is determined. Then, the optical defect identification parameters are compared with standard defect identification parameters to determine the defect identification differences in the optical defect formation state of the PCB board. Finally, based on the defect identification differences, the defect filtering mode of the PCB board is adjusted to provide feedback adjustment for the defect filtering method, facilitating timely filtering of non-defects on the PCB board and effectively improving the PCB board inspection efficiency.

[0022] Please see Figure 1 This is a flowchart of a PCB board defect optical detection and monitoring method according to an embodiment of the present disclosure. The PCB board defect optical detection and monitoring method includes some or all of the following steps.

[0023] S100: Obtain the optical defect identification parameters of the PCB board surface.

[0024] In this embodiment, the optical defect identification parameters are the identification types and distribution data of the optical defects on the PCB board. That is, the optical defect identification parameters are the optical defect status of the PCB board, and the optical defect identification parameters correspond to the optical defect feedback of the PCB board. By collecting the optical defect identification parameters, it is easy to determine the degree of defects on the PCB board during the optical inspection process.

[0025] S200: Perform a filter-likelihood loss process on the optical defect identification parameters of the board surface and the preset defect identification parameters to obtain the defect loss amount of the board surface.

[0026] In this embodiment, the optical defect identification parameters refer to the types and distribution data of optical defects on the PCB board. In other words, the optical defect identification parameters represent the optical defect state of the PCB board, and correspond to the optical defect feedback of the PCB board. Collecting these parameters facilitates the determination of the degree of defects on the PCB board during the optical inspection process. The preset defect identification parameters refer to the standard optical defect types and distribution data on the PCB board. In other words, the preset defect identification parameters represent a specified optical defect state on the PCB board, and correspond to a reference optical defect feedback of the PCB board. By applying a filtering likelihood loss process to the optical defect identification parameters and the preset defect identification parameters, the difference in defect degree between the two parameters is determined.

[0027] S300: Send a defect filtering failure signal to the AOI automatic detection system according to the amount of defect loss on the board surface, so as to adjust the defect filtering mode on the PCB board.

[0028] In this embodiment, the loss amount of board surface defects is obtained based on the board surface optical defect identification parameters and the preset defect identification parameters. The board surface optical defect identification parameters are the identification types and distribution data of board surface defects on the PCB board, that is, the board surface optical defect identification parameters are the board surface optical defect state of the PCB board, and the board surface optical defect identification parameters correspond to the board surface optical defect feedback of the PCB board. By collecting the board surface optical defect identification parameters, it is easy to determine the degree of board surface defects of the PCB board during the optical inspection process. The preset defect identification parameters are the standard board surface defect identification types and distribution data on the PCB board, that is, the preset defect identification parameters are the specified board surface optical defect state of the PCB board, and the preset defect identification parameters correspond to the reference board surface optical defect feedback of the PCB board. By performing filtering likelihood loss processing on the board surface optical defect identification parameters and the preset defect identification parameters, the difference in defect degree between the board surface optical defect identification parameters and the preset defect identification parameters is determined. After obtaining the amount of defect loss on the board surface, the defect situation on the PCB board surface can be determined, which facilitates the accurate identification of defects on the PCB board surface. At this time, by sending a defect filtering failure signal to the AOI automatic detection system, the defect filtering mode on the PCB board is adjusted so that the real defects of the PCB board are screened out, while non-defect information is filtered out.

[0029] In the above embodiments, after collecting the optical defect identification parameters of the board surface, the current optical defect formation state of the PCB board is determined. Then, the optical defect identification parameters of the board surface are compared with the standard defect identification parameters to determine the defect identification differences of the optical defect formation state of the PCB board. Finally, based on the above defect identification differences, the defect filtering mode of the PCB board is adjusted to provide feedback adjustment of the defect filtering method of the PCB board, so as to facilitate timely filtering of non-defects on the PCB board and effectively improve the PCB board inspection efficiency.

[0030] In one embodiment, obtaining optical defect identification parameters for the PCB board surface includes: obtaining the maximum width of pits and cracks on the PCB board. In this embodiment, the optical defect identification parameters are the identification types and distribution data of surface defects on the PCB board, that is, the optical defect identification parameters are the optical defect state of the PCB board surface, and the optical defect identification parameters correspond to the optical defect feedback of the PCB board surface. By collecting the optical defect identification parameters, it is easy to determine the degree of surface defects of the PCB board during the optical inspection process. The optical defect identification parameters for the PCB board surface include the maximum width of pits and cracks on the PCB board, which is the maximum width of the surface pits and cracks on the PCB board. By collecting the maximum width of pits and cracks on the PCB board surface, it is easy to determine the degree of cracking of the surface pits and cracks on the PCB board surface.

[0031] Further, the optical defect identification parameters of the PCB surface are subjected to a filtering likelihood loss process with the preset defect identification parameters to obtain the PCB surface defect loss amount. This includes: calculating the width likelihood loss between the maximum width of the pit and the preset width to obtain the width loss of the pit and crack. In this embodiment, the optical defect identification parameters of the PCB surface are the identification types and distribution data of the PCB surface defects, that is, the optical defect identification parameters of the PCB surface are the optical defect state of the PCB surface, and the optical defect identification parameters of the PCB surface correspond to the optical defect feedback of the PCB surface. By collecting the optical defect identification parameters of the PCB surface, it is convenient to determine the degree of PCB surface defects during the optical inspection process. The preset defect identification parameters are the standard PCB surface defect identification types and distribution data of the PCB surface, that is, the preset defect identification parameters are the specified optical defect state of the PCB surface, and the preset defect identification parameters correspond to the reference optical defect feedback of the PCB surface. By applying a filtering likelihood loss to the optical defect identification parameters and the preset defect identification parameters, the difference in defect severity between the optical defect identification parameters and the preset defect identification parameters is determined. The optical defect identification parameters of the PCB board include the maximum width of the PCB board's pits and cracks. The maximum width of the PCB board's pits and cracks is the maximum width of the surface concave cracks. Collecting the maximum width of the PCB board's pits and cracks facilitates the determination of the cracking severity of the surface concave cracks. The preset width is the upper limit of the width of the surface concave cracks on the PCB board. By calculating the width likelihood loss between the maximum width of the pits and cracks and the preset width, the difference between the maximum width of the pits and cracks and the standard width crack width distribution is obtained. Specifically, the width likelihood loss is calculated by minimizing the negative logarithmic likelihood loss.

[0032] Furthermore, based on the amount of board surface defect loss, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board. This includes: detecting whether the width loss of the board surface pits and cracks is greater than or equal to a preset width loss; when the width loss of the board surface pits and cracks is greater than or equal to the preset width loss, sending a pit and crack defect filtering failure signal to the AOI automatic inspection system. In this embodiment, the amount of board surface defect loss is obtained based on the board surface optical defect identification parameters and the preset defect identification parameters. The board surface optical defect identification parameters are the identification types and distribution data of board surface defects on the PCB board, that is, the board surface optical defect identification parameters are the board surface optical defect state of the PCB board, that is, the board surface optical defect identification parameters correspond to the board surface optical defect feedback of the PCB board. By collecting the board surface optical defect identification parameters, it is convenient to determine the degree of board surface defects of the PCB board during the optical inspection process. The preset defect identification parameters are the standard board surface defect identification types and distribution data on the PCB board. Specifically, the preset defect identification parameters represent the specified optical defect state of the PCB board, corresponding to the feedback of the reference board surface optical defects. By applying a filtering likelihood loss process to the board surface optical defect identification parameters and the preset defect identification parameters, the difference in defect severity between them is determined. After obtaining the board surface defect loss, the defects present on the PCB board are determined, facilitating accurate identification of PCB board defects. At this point, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board, allowing true defects to be filtered out while non-defect information is removed. The optical defect identification parameters for the PCB board include the maximum width of the pit / crack, which is the maximum width of the surface concave crack. Collecting the maximum width of the pit / crack facilitates the determination of the cracking degree. The preset width is the upper limit of the width of the surface concave crack. The difference between the maximum width and the preset width is calculated using the width likelihood loss, specifically by minimizing the negative logarithmic likelihood loss. If the surface concave crack width loss is greater than or equal to the preset width loss, it indicates that the crack width exceeds the predetermined width, meaning the surface concave crack is a genuine defect. By sending a pit / crack defect filtering disabling signal to the AOI automatic inspection system, genuine defects in the surface concave crack of the PCB board are filtered out, avoiding incorrect filtering.

[0033] In another embodiment, when the width of the pit crack on the board surface is less than the preset width loss, a pit crack defect filtering enable signal is sent to the AOI automatic detection system. At this time, the pit crack on the PCB board surface is a false defect, that is, these positions are normal board holes and grooves of the PCB board, and they are filtered out in time.

[0034] In one embodiment, obtaining optical defect identification parameters for the PCB board surface includes: obtaining the area of ​​laser black spots on the PCB board. In this embodiment, the optical defect identification parameters are the identification types and distribution data of surface defects on the PCB board, that is, the optical defect identification parameters are the optical defect state of the PCB board surface, and the optical defect identification parameters correspond to the optical defect feedback of the PCB board surface. By collecting the optical defect identification parameters, it is easy to determine the degree of surface defects of the PCB board during the optical inspection process. The optical defect identification parameters for the PCB board surface include the area of ​​laser black spots on the PCB board, which is the area of ​​the laser black spots on the PCB board surface. By collecting the area of ​​the laser black spots on the PCB board surface, it is easy to determine the degree of cracking of the laser black spots on the PCB board surface.

[0035] Further, the optical defect identification parameters of the PCB board are subjected to a filtering likelihood loss process with the preset defect identification parameters to obtain the PCB board defect loss amount. This includes: calculating the area likelihood loss between the laser black spot area and the preset area to obtain the black spot area loss. In this embodiment, the optical defect identification parameters of the PCB board are the identification types and distribution data of the PCB board defects, that is, the optical defect identification parameters of the PCB board are the optical defect state of the PCB board, and the optical defect identification parameters of the PCB board correspond to the optical defect feedback of the PCB board. By collecting the optical defect identification parameters of the PCB board, it is convenient to determine the degree of PCB board defects during the optical inspection process. The preset defect identification parameters are the standard PCB board defect identification types and distribution data, that is, the preset defect identification parameters are the specified PCB board optical defect state, and the preset defect identification parameters correspond to the reference PCB board optical defect feedback of the PCB board. By applying a filtered likelihood loss to the optical defect identification parameters and the preset defect identification parameters, the difference in defect severity between the two parameters is determined. The optical defect identification parameters of the PCB board include the area of ​​laser-induced black spots, which is the maximum area of ​​laser-induced black spots on the PCB board surface. Collecting the area of ​​these laser-induced black spots facilitates the determination of the cracking degree. The preset area is the area of ​​the laser-induced black spots on the PCB board surface. Calculating the area likelihood loss between the laser-induced black spot area and the preset area helps to determine the difference in crack area distribution between the laser-induced black spot area and the standard area. Specifically, the area likelihood loss is calculated by minimizing the negative logarithmic likelihood loss.

[0036] Furthermore, based on the amount of board surface defect loss, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board. This includes: detecting whether the black spot surface loss is greater than or equal to a preset surface loss; and when the black spot surface loss is less than the preset surface loss, sending a black spot defect filtering enable signal to the AOI automatic inspection system. In this embodiment, the amount of board surface defect loss is obtained based on the board surface optical defect identification parameters and the preset defect identification parameters. The board surface optical defect identification parameters are the board surface defect identification types and distribution data on the PCB board, that is, the board surface optical defect identification parameters are the board surface optical defect state of the PCB board, and the board surface optical defect identification parameters correspond to the board surface optical defect feedback situation of the PCB board. By collecting the board surface optical defect identification parameters, it is convenient to determine the degree of board surface defects of the PCB board during the optical inspection process. The preset defect identification parameters are the standard board surface defect identification types and distribution data on the PCB board. Specifically, the preset defect identification parameters represent the specified optical defect state of the PCB board, corresponding to the feedback of the reference optical defect on the PCB board. By performing a filtering likelihood loss process on the board surface optical defect identification parameters and the preset defect identification parameters, the difference in defect severity between the two parameters is determined. After obtaining the board surface defect loss, the defects present on the PCB board are determined, facilitating accurate identification of PCB board defects. At this point, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board, allowing true defects to be filtered out while non-defect information is filtered out. The board surface optical defect identification parameters include the laser black spot area of ​​the PCB board, which is the maximum area of ​​the laser black spots on the PCB board surface. Collecting the laser black spot area facilitates the determination of the cracking degree of the laser black spots on the PCB board surface. The preset area is the upper limit of the area of ​​the laser black spots on the PCB board. By calculating the area likelihood loss between the laser black spot area and the preset area, the difference between the crack area distribution of the laser black spot area and the standard area is obtained. Specifically, the area likelihood loss is calculated by minimizing the negative logarithmic likelihood loss. If the area loss of the black spots on the board is less than the preset width loss, it indicates that the crack area of ​​the laser black spots on the PCB board is small, that is, it indicates that the laser black spots on the PCB board are false defects. By sending a pit and crack defect filtering enable signal to the AOI automatic inspection system, the false defects of the PCB board are filtered out.

[0037] In another embodiment, if the surface area loss of the black spot on the board is greater than or equal to the preset width loss, it indicates that the cracked area of ​​the laser black spot on the PCB board exceeds the predetermined area, which means that the laser black spot on the PCB board is a real defect. By sending a pit and crack defect filtering disabling signal to the AOI automatic detection system, the real defects of the laser black spot on the PCB board can be screened out, avoiding incorrect filtering.

[0038] In another embodiment, the PCB board defect optical inspection and monitoring method is an AOI automatic inspection method based on AI filtering technology. It adopts deep learning algorithms and trains a large amount of PCB image data to automatically identify and classify various defects on the PCB. By filtering the detection results through AI algorithms, the accuracy of the inspection system can be greatly improved, false detections and missed detections can be reduced, and the overall performance of the AOI inspection system can be optimized.

[0039] In actual inspection of PCB board defects using automated optical filtering, PCB board defects are often small and isolated, leading to misjudgments of small-diameter copper-plated vias or positioning holes. To improve the accuracy of filtering non-defect information on the PCB board surface, a defect filtering failure signal is sent to the AOI automated inspection system based on the amount of defect loss, adjusting the defect filtering mode on the PCB board. This process includes the following steps: Obtain the diameter of the defective hole on the PCB board and the gray level inside the defective hole, wherein the gray level inside the defective hole corresponds to the diameter of the defective hole on the board. Detect whether the diameter of the defective hole on the plate surface is less than or equal to the preset hole diameter; When the diameter of the defect hole on the board surface is less than or equal to the preset hole diameter, it is detected whether the gray value inside the defect hole on the board surface is greater than or equal to the preset hole gray value. When the gray level inside the defective hole on the plate surface is greater than or equal to the preset gray level inside the hole, a hole non-defect filtering signal is sent to the AOI automatic detection system.

[0040] In this embodiment, the aperture of the board surface defect is the aperture initially tentatively identified as a defect, meaning that the aperture is determined based on the size of the defect pre-identified according to the board surface optical defect identification parameters. The grayscale value within the board surface defect aperture corresponds one-to-one with the aperture diameter, meaning that the grayscale value within the board surface defect aperture and the aperture diameter represent the same information tentatively identified as a defect. The grayscale value within the board surface defect aperture reflects the internal grayscale changes of the tentatively identified defect. If the aperture diameter is less than or equal to the preset aperture diameter, it indicates that the aperture initially tentatively identified as a defect is smaller than the specified aperture diameter, meaning that the aperture initially tentatively identified as a defect is too small, and that there is a possibility of misidentification of the initially tentatively identified defect as a defect. Next, if the gray level inside the defect hole on the board surface is greater than or equal to the preset gray level inside the hole, it indicates that the gray level inside the initially tentatively determined defect is too high, which means that the internal space of the initially tentatively determined defect is smooth, and that the initially tentatively determined defect is a false defect and belongs to non-defect. At this time, a hole non-defect filtering signal is sent to the AOI automatic detection system to filter out normal holes with small diameter in advance, so as to avoid misjudging such information as defects.

[0041] In another embodiment, when the gray level inside the defect hole on the plate surface is less than the preset gray level inside the hole, step S300 is executed.

[0042] Further, the process includes detecting whether the diameter of the defective hole on the plate surface is less than or equal to a preset hole diameter, followed by: The length of the defect boundary and the reflectivity within the boundary of the PCB board are obtained, wherein the length of the defect boundary corresponds to the length of the defect edge. Detect whether the length of the defect boundary on the plate surface is greater than or equal to a preset boundary length; When the length of the defect boundary on the plate is less than or equal to the preset boundary length, it is detected whether the reflective brightness within the boundary is greater than or equal to the preset brightness. When the reflective brightness within the boundary is greater than or equal to the preset brightness, a pad non-missing filter signal is sent to the AOI automatic detection system.

[0043] In this embodiment, the length of the board surface defect boundary is the edge length initially tentatively identified as a defect. That is, the edge length of the board surface defect is the length of the defect pre-determined based on the board surface optical defect identification parameters. The board surface defect boundary length and the edge length of the board surface defect correspond one-to-one; that is, the board surface defect boundary length and the edge length of the board surface defect are the same information for tentatively identifying a defect. The board surface defect boundary length is used to reflect the change in the perimeter of the edge tentatively identified as a defect. If the board surface defect boundary length is less than or equal to the preset boundary length, it indicates that the edge length initially tentatively identified as a defect is less than the specified edge length, which means that the edge length initially tentatively identified as a defect is too small, and therefore, there is a possibility that the initially tentatively identified defect may have been misidentified as a defect. Next, if the reflective brightness within the boundary is greater than or equal to the preset brightness, it indicates that the reflective brightness within the initially tentative defect boundary is too strong, which means that there is a highly reflective medium inside the initially tentative defect. In other words, it means that the initially tentative defect is a location with metal foil, such as a solder pad, and is not a defect. At this time, a non-defect filtering signal for solder pads is sent to the AOI automatic detection system to filter out solder pads with metal foil in advance, so as to avoid misjudging normal information such as solder pads as defects.

[0044] In another embodiment, when the length of the defect boundary on the plate surface is greater than the preset boundary length, or the reflective brightness within the boundary is less than the preset brightness, step S300 is executed.

[0045] All the above-mentioned preset variables are set in the database for easy retrieval. Different preset variables are placed in different storage units, i.e., in different storage stacks. Furthermore, the aperture of the board surface defect, the gray level inside the board surface defect hole, the length of the board surface defect boundary, and the reflective brightness within the boundary can be acquired by the corresponding processor, for example, by the AOI automatic optical inspection instrument of the board surface defect acquisition module.

[0046] In one embodiment, this disclosure also relates to a PCB board defect optical inspection and monitoring device, which employs the PCB board defect optical inspection and monitoring method described in any of the above embodiments, including: a board surface defect acquisition module, a defect loss processing module, and a defect filtering and control module; the board surface defect acquisition module is used to acquire board surface optical defect identification parameters of the PCB board; the defect loss processing module is used to perform filter likelihood loss processing on the board surface optical defect identification parameters and preset defect identification parameters to obtain the board surface defect loss amount; the defect filtering and control module is used to send a defect filtering failure signal to the AOI automatic inspection system according to the board surface defect loss amount to adjust the defect filtering mode on the PCB board.

[0047] In this embodiment, after the board surface defect acquisition module acquires the optical defect recognition parameters of the board surface, it determines the current optical defect formation state of the PCB board. Then, the defect loss processing module compares the optical defect recognition parameters of the board surface with the standard defect recognition parameters to determine the defect recognition differences in the optical defect formation state of the PCB board. Finally, the defect filtering control module adjusts the defect filtering mode of the PCB board according to the above defect recognition differences to provide feedback adjustment of the defect filtering method of the PCB board, so as to facilitate timely filtering of non-defects on the PCB board and effectively improve the PCB board inspection efficiency.

[0048] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 2 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data such as optical defect identification parameters for the PCB board, preset defect identification parameters, and defect filtering failure signals. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for optical inspection and monitoring of PCB board defects.

[0049] Those skilled in the art will understand that Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0050] In one embodiment, this application also provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0051] In one embodiment, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0052] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0053] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A method for optical inspection and monitoring of defects in PCB boards, characterized in that, include: Obtain the optical defect identification parameters of the PCB board surface; The optical defect identification parameters of the board surface and the preset defect identification parameters are subjected to defect filtering likelihood loss processing to obtain the defect loss amount of the board surface. Based on the amount of defect loss on the board surface, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board.

2. The PCB board defect optical inspection and monitoring method according to claim 1, characterized in that, Obtain the optical defect identification parameters of the PCB board surface, including: Get the maximum width of the pits / cracks on the PCB board.

3. The PCB board defect optical inspection and monitoring method according to claim 2, characterized in that, The optical defect identification parameters of the board surface are compared with preset defect identification parameters by performing a defect filtering likelihood loss process to obtain the board surface defect loss amount, including: The width likelihood loss between the maximum width of the pit and the preset width is calculated to obtain the width loss of the pit on the board surface.

4. The PCB board defect optical detection and monitoring method according to claim 3, characterized in that, Based on the amount of defect loss on the board surface, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board, including: Detect whether the width loss of the pits and cracks on the board surface is greater than or equal to the preset width loss; When the width loss of the pits and cracks on the plate surface is greater than or equal to the preset width loss, a pit and crack defect filtering failure signal is sent to the AOI automatic detection system.

5. The PCB board defect optical inspection and monitoring method according to claim 1, characterized in that, Obtain the optical defect identification parameters of the PCB board surface, including: Obtain the area of ​​the laser black dots on the PCB board.

6. The PCB board defect optical detection and monitoring method according to claim 5, characterized in that, The optical defect identification parameters of the board surface are compared with preset defect identification parameters by performing a defect filtering likelihood loss process to obtain the board surface defect loss amount, including: The area likelihood loss between the laser black spot area and the preset area is calculated to obtain the black spot area loss on the board surface.

7. The PCB board defect optical inspection and monitoring method according to claim 6, characterized in that, Based on the amount of defect loss on the board surface, a defect filtering failure signal is sent to the AOI automatic inspection system to adjust the defect filtering mode on the PCB board, including: Detect whether the surface damage of the black spots on the board is greater than or equal to the preset surface damage; When the surface damage of black spots on the board is less than the preset surface damage, a black spot defect filtering enable signal is sent to the AOI automatic detection system.

8. A PCB board defect optical inspection and monitoring device, wherein the PCB board defect optical inspection and monitoring device adopts the PCB board defect optical inspection and monitoring method as described in any one of claims 1 to 7, characterized in that, include: A board surface defect acquisition module is used to acquire optical defect identification parameters of the PCB board surface. The defect loss processing module is used to perform filter-likelihood loss processing on the optical defect identification parameters of the board surface and the preset defect identification parameters to obtain the defect loss amount of the board surface. The defect filtering control module is used to send a defect filtering failure signal to the AOI automatic detection system according to the amount of defect loss on the board surface, so as to adjust the defect filtering mode on the PCB board.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images