CN117372426B - Rigid PCB metal hole copper-embedded structure visual detection system - Google Patents
Rigid PCB metal hole copper-embedded structure visual detection system Download PDFInfo
- Publication number
- CN117372426B CN117372426B CN202311652332.3A CN202311652332A CN117372426B CN 117372426 B CN117372426 B CN 117372426B CN 202311652332 A CN202311652332 A CN 202311652332A CN 117372426 B CN117372426 B CN 117372426B
- Authority
- CN
- China
- Prior art keywords
- copper
- metal hole
- circuit board
- embedded
- gap
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002184 metal Substances 0.000 title claims abstract description 258
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 258
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 230000000007 visual effect Effects 0.000 title abstract description 6
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims abstract description 168
- 229910052802 copper Inorganic materials 0.000 claims abstract description 162
- 239000010949 copper Substances 0.000 claims abstract description 162
- 230000007547 defect Effects 0.000 claims abstract description 52
- 239000011148 porous material Substances 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims description 26
- 238000011179 visual inspection Methods 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 239000011800 void material Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000003466 welding Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000017525 heat dissipation Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
- 238000005476 soldering Methods 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01N21/95623—Inspecting patterns on the surface of objects using a spatial filtering method
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- 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
- G01N2021/95646—Soldering
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Abstract
The invention relates to the technical field of image processing, in particular to a visual detection system for a rigid PCB metal hole copper-embedded structure. The system comprises: acquiring a printed circuit board image, acquiring a suspected metal hole area according to the printed circuit board image, calculating a copper embedding characteristic index of the suspected metal hole area, determining a metal hole copper embedding structure, acquiring a gap connecting line, calculating an annular gap interval index and an annular pore gradient of the metal hole copper embedding structure, combining the copper embedding characteristic index of the metal hole copper embedding structure, acquiring the defect degree of the circuit board, and dividing the defect degree of the printed circuit board into four grades of no defect, slight degree, moderate degree and severe degree. The invention aims to solve the problem that the existing defect detection technology is difficult to detect the defect of the copper embedded structure of the metal hole of the rigid PCB due to the fact that a printed circuit board comprises a plurality of complex circuit elements, circuits, welding points and the like.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a visual detection system for a rigid PCB metal hole copper-embedded structure.
Background
The PCB, i.e. the printed circuit board, is one of the important components of the electronic industry, and as the volume of electronic products is smaller and smaller, the volume of the printed circuit board is continuously reduced, and the circuit design is more and more dense. Because the power density of the components is improved, the heat dissipation capacity of the printed circuit board is too large, thereby influencing the service life, aging, failure of the components and the like. The copper block has high heat conduction performance, heat generated by components can be quickly transferred to the copper block in the using process of the printed circuit board, then the heat is dissipated into the air through the copper block, so that the rigid PCB metal hole copper embedding technology is introduced in the industry, and the printed circuit board metal hole copper embedding structure has the characteristics of high heat conduction, high heat dissipation, board space saving and the like, and the heat dissipation problem of high-power electronic components is effectively solved.
Because the production and manufacturing process of the rigid PCB metal hole copper-embedded structure is affected by a plurality of uncertain factors, the metal hole copper-embedded structure may have defects, such as defects are not timely detected, and hidden dangers are likely to be left in the debugging and using processes of the PCB. However, the PCB board generally includes many complex circuit elements, circuits, soldering points, etc., and these elements are tightly and complexly laid out, which makes it difficult to perform defect detection on the copper-embedded structure of the metal hole of the rigid PCB by using the existing defect detection technology.
Disclosure of Invention
In order to solve the technical problem that the existing defect detection technology is difficult to detect defects of the copper embedded structure of the metal hole of the rigid PCB due to the fact that a plurality of complex circuit elements, circuits, welding points and the like are contained on the printed circuit board, the invention provides a visual detection system of the copper embedded structure of the metal hole of the rigid PCB, and the adopted technical scheme is as follows:
the invention provides a visual detection system for a copper-embedded structure of a rigid PCB metal hole, which comprises the following modules:
the printed circuit board image acquisition module is used for acquiring a printed circuit board image containing a metal hole copper-embedded structure;
the metal hole copper-embedded structure acquisition module is used for acquiring a printed circuit board binary image and a suspected metal hole area according to the printed circuit board image; acquiring a circumferential ring, an inner ring and an outer ring according to the suspected metal hole area; calculating the copper embedding characteristic index of the suspected metal hole area according to the circumferential ring, the inner ring and the outer ring; determining a copper embedding structure of the metal hole according to the copper embedding characteristic index of the suspected metal hole area;
the annular gap interval index acquisition module is used for acquiring copper block edge points and metal hole edge points according to the metal hole copper embedding structure and the printed circuit board binary image; acquiring a gap connecting line according to the edge points of the copper block and the edge points of the metal hole, and calculating a gap interval index of the gap connecting line by combining gray values of all pixel points in the copper embedded structure of the metal hole; acquiring annular gap interval indexes of the metal hole copper-embedded structure according to the gap interval indexes of all gap connecting wires in the metal hole copper-embedded structure;
the annular pore gradient acquisition module is used for acquiring the annular pore gradient of the metal hole copper-embedded structure according to the gap interval indexes of all the gap connecting lines in the metal hole copper-embedded structure;
and the circuit board defect detection module is used for acquiring the defect degree of the circuit board according to the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the metal hole copper embedding structure and dividing the defect degree of the printed circuit board into four grades of defect-free, slight, moderate and severe.
Preferably, the method for obtaining the binary image and the suspected metal hole area of the printed circuit board according to the printed circuit board image comprises the following steps:
acquiring edge information of the printed circuit board image by using an edge detection operator to obtain a printed circuit board binary image;
acquiring a Hough parameter space of a binary image of the printed circuit board by using Hough circle transformation, wherein the Hough parameter space is a three-dimensional matrix, and three dimensions comprise a circle center abscissa, a circle center ordinate and a radius;
and when the element value determined by the circular abscissa, the circular ordinate and the radius in the Hough parameter space is larger than a preset circular judgment threshold value, judging that a circular area on the printed circuit board image represented by the circular abscissa, the circular ordinate and the radius is a suspected metal hole area.
Preferably, the method for obtaining the circumferential ring, the inner ring and the outer ring according to the suspected metal hole area comprises the following steps:
the radius of the suspected metal hole area is marked as a standard radius;
the sum of the standard radius and twice the preset circumference radius is recorded as an outer radius;
the sum of the standard radius and the preset circumference radius is recorded as the circumference radius;
the difference value between the standard radius and the preset circumference radius is recorded as an inner radius;
the outer radius replaces the radius of the suspected metal hole area, and outer concentric circles of the suspected metal hole area are obtained;
substituting the radius of the suspected metal hole area with the circumference radius to obtain circumference concentric circles of the suspected metal hole area;
replacing the radius of the suspected metal hole area with the inner radius to obtain an inner concentric circle of the suspected metal hole area;
the closed area surrounded by the edges of the outer concentric circle and the circumferential concentric circle is marked as an outer circular ring;
the closed area formed by surrounding the circumference concentric circle and the edge of the suspected metal hole area is marked as a circumference ring;
and (5) marking a closed area surrounded by the inner concentric circle and the edge of the suspected metal hole area as an inner circular ring.
Preferably, the method for calculating the copper embedding characteristic index of the suspected metal hole area according to the circumferential ring, the inner ring and the outer ring comprises the following steps:
the average value of the gray values of all the pixel points in the circumference ring is recorded as the circumference gray average value;
the average value of the gray values of all the pixel points in the inner circular ring is recorded as the average value of the gray values in the circular ring;
the average value of the gray values of all pixel points in the outer circular ring is recorded as the average value of the gray values outside the circular ring;
the absolute value of the difference between the circumference gray average value and the in-circle gray average value is recorded as a first absolute value;
the absolute value of the difference between the circumference gray average value and the out-of-circle gray average value is recorded as a second absolute value;
the sum of the first absolute value and the second absolute value is recorded as a first accumulated sum;
the standard deviation of gray values of all pixel points in the circumferential ring is recorded as a first standard deviation;
the ratio of the first accumulated sum to the first standard deviation is recorded as a first ratio;
and recording the normalized value of the first ratio as the copper embedding characteristic index of the suspected metal hole area.
Preferably, the method for determining the copper embedding structure of the metal hole according to the copper embedding characteristic index of the suspected metal hole area comprises the following steps:
and marking the suspected metal hole area with the copper embedding characteristic index larger than the preset flattening threshold value as a metal hole copper embedding structure.
Preferably, the method for obtaining the edge points of the copper block and the edge points of the metal hole according to the metal hole copper embedding structure and the binary image of the printed circuit board comprises the following steps:
calculating gradient values and gradient directions of all pixel points in the copper embedded metal hole structure;
constructing a neighborhood window with a preset window length as a side length by taking a pixel point as a center;
the average value of the gradient values of all the pixel points in the neighborhood window is recorded as the neighborhood gradient of the pixel point;
marking a first preset number of pixel points with the largest neighborhood gradient in the copper-embedded metal hole structure as copper block edge points;
marking the pixel point with the pixel value of 1 as the edge pixel point in the binary image of the printed circuit board;
starting from the copper block edge point, the first edge pixel point in the gradient direction of the copper block edge point in the metal hole embedded copper structure is marked as the metal hole edge point of the copper block edge point.
Preferably, the method for calculating the gap interval index of the gap connecting line according to the gray values of all pixel points in the copper embedded structure of the metal hole by acquiring the gap connecting line according to the edge points of the copper block and the edge points of the metal hole comprises the following steps:
the line segment connecting the edge point of the copper block and the edge point of the metal hole is marked as a gap connecting line;
the Euclidean distance between the edge point of the copper block and the edge point of the metal hole is recorded as the length of a gap connecting line;
the gray value average value of all pixel points in the copper-embedded metal hole structure is recorded as a first gray value average value;
the absolute value of the difference value between the gray value of the pixel point and the first gray average value is recorded as the gray difference of the pixel point;
the gray level difference of all pixel points on the gap connecting line of the metal hole copper-embedded structure is recorded as a second accumulation sum;
and (3) recording the product of the length of the gap connecting line and the second accumulated sum as a gap interval index of the gap connecting line.
Preferably, the method for obtaining the annular gap interval index comprises the following steps:
and (3) marking the sum of gap interval indexes of all gap connecting lines of the metal hole copper-embedded structure as an annular gap interval index of the metal hole copper-embedded structure.
Preferably, the method for obtaining the inclination of the annular aperture comprises the following steps:
the extremely poor of gap interval indexes of all gap connecting lines in the copper-embedded metal hole structure is recorded as gap characteristic difference;
the extreme difference of the lengths of all the gap connecting lines in the copper-embedded metal hole structure is recorded as the gap length difference;
the sum of the gap characteristic difference and the gap length difference is recorded as a third accumulated sum;
and (3) recording the ratio of the third accumulated sum to the number of the gap connecting lines in the metal hole copper-embedded structure as the annular pore gradient of the metal hole copper-embedded structure.
Preferably, the method for obtaining the defect degree of the circuit board according to the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the copper embedding structure of the metal hole comprises the following steps:
the product of the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the metal pore copper embedding structure is recorded as the pore defect degree of the metal pore copper embedding structure;
the sum of the pore defect degrees of all the metal hole copper-embedded structures in the printed circuit board image is recorded as a fourth accumulated sum;
and recording the normalized value of the fourth accumulated sum as the defect degree of the circuit board.
The invention has the following beneficial effects: according to the method, a binary image and a suspected metal hole area of the printed circuit board are acquired according to the image of the printed circuit board, the copper embedding characteristic index of the suspected metal hole area is calculated, the metal hole copper embedding structure is determined, and only the metal hole copper embedding structure is analyzed later, so that the defect detection speed of the metal hole copper embedding structure of the printed circuit board is improved; according to the unique characteristics of the copper embedded metal hole structure when defects are generated, the annular gap interval index and the annular gap gradient of the copper embedded metal hole structure are calculated, the copper embedded metal hole structure is distinguished from circuit elements, circuits, welding points and the like on the surface of a printed circuit board, the defect degree of the circuit board is obtained according to the copper embedded characteristic index, the annular gap gradient and the annular gap interval index of the copper embedded metal hole structure, the defect degree of the copper embedded metal hole structure of the printed circuit board is divided into four grades of defect-free, light, moderate and severe, the reliability of defect detection of the copper embedded metal hole structure of the printed circuit board is improved, and the problem that the defect detection of the copper embedded metal hole structure of the rigid PCB is difficult in the conventional defect detection technology due to the fact that a plurality of complex circuit elements, circuits, welding points and the like are contained on the printed circuit board is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a visual inspection system for a copper-embedded structure of a metal hole of a rigid PCB according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a defect of a copper-embedded structure of a metal hole of a printed circuit board;
fig. 3 is a schematic diagram of gap spacing.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a visual inspection system for a copper-embedded structure of a metal hole of a rigid PCB according to an embodiment of the invention is shown, the system includes: the device comprises a printed circuit board image acquisition module, a metal hole copper-embedded structure acquisition module, an annular gap interval index acquisition module, an annular gap gradient acquisition module and a circuit board defect detection module.
And the printed circuit board image acquisition module is used for acquiring the printed circuit board image containing the metal hole copper embedded structure.
In order to reduce the influence of light irradiation when the printed circuit board is analyzed, the printed circuit board is placed on a flat and light-sufficient workbench so as to ensure that the details of the printed circuit board can be clearly captured, a CCD camera is placed right above the printed circuit board, the printed circuit board is photographed, and the printed circuit board image is acquired. Because random disturbance can be generated in the process of shooting the printed circuit board image, the printed circuit board image has certain noise, in order to eliminate the noise in the image, the average filtering is used for smoothing the printed circuit board image before the printed circuit board is analyzed, and then the gray processing is carried out on the printed circuit board image.
Thereby obtaining a printed circuit board image.
The metal hole copper-embedded structure acquisition module is used for acquiring a printed circuit board binary image and a suspected metal hole area according to the printed circuit board image; acquiring a circumferential ring, an inner ring and an outer ring according to the suspected metal hole area; calculating the copper embedding characteristic index of the suspected metal hole area according to the circumferential ring, the inner ring and the outer ring; and determining the copper embedding structure of the metal hole according to the copper embedding characteristic index of the suspected metal hole area.
If the copper block is too small, after the copper block is embedded into the metal hole, the copper block cannot be in close contact with the hole wall of the metal hole, and the copper block can possibly fall off in the subsequent debugging and use processes of the printed circuit board; if the copper block is too large, damage to the hole wall and the copper block can be caused. Therefore, the defect detection needs to be performed on the copper-embedded structure of the rigid PCB according to the characteristics around the wall of the copper-embedded structure of the metal hole of the rigid PCB, so as to prevent the printed circuit board from malfunctioning in the using process, thereby causing larger loss.
On the surface of a printed circuit board, many complex circuit elements, lines, pins, solder joints, etc. are usually included, these elements are closely laid out and are similar to the metal hole copper embedded structure, which is primarily distinguished from the rest of the elements on the surface of the printed circuit board according to the characteristic that the metal holes are usually circular.
When the diameter of the copper block is too small, after the copper block is embedded into the metal hole, the copper block cannot be in close contact with the hole wall of the metal hole, gaps can appear in the middle area of the copper block and the hole wall, and in order to completely divide the metal hole area, expansion corrosion is performed on the printed circuit board image, so that the influence of the gaps inside the metal hole is avoided.
Then using a canny edge detection operator to obtain edge information of the printed circuit board image, obtaining a printed circuit board binary image, marking pixel points with pixel values of number 1 in the printed circuit board binary image as edge pixel points, using Hough circle transformation to obtain Hough parameter space of the printed circuit board binary image, and setting a circular judgment threshold valueWhen the element value in Hough straight line space +.>Greater than the circular judgment threshold->At the time, it is determined that +.>Is used as the center of a circle and is>A round area with radius is a suspected metal hole area, and a round judgment threshold value is +.>The value is the perimeter of the metal hole of the printed circuit board, and the empirical value of the perimeter of the metal hole of the printed circuit board is 10.
Copper blocks are generally embedded into metal holes of a printed circuit board in an interference fit mode, because the size of the copper blocks is larger than the aperture of the metal holes of the printed circuit board, the right-angle edges are subjected to large resistance, deflection or serious abrasion are easy to occur, the periphery of the hole walls of the metal holes of the printed circuit board are raised or gaps are generated, the flatness of the printed circuit board is reduced, and a defect schematic diagram of the copper embedding structure of the metal holes of the printed circuit board is shown in fig. 2.
When a bulge is generated around the hole wall or a gap is generated inside the hole wall, the distance between the outer side area of the hole wall and other areas is different from the distance between the outer side area of the hole wall and the camera, and the pixel value of the outer side area of the hole wall in the printed circuit board image is higher than the pixel value of the surrounding areas due to the shielding effect of the outer side area of the hole wall on the other areas.
The circle center of the suspected metal hole area isRadius is->Will radius +.>The concentric circles of the suspected metal hole regions are marked as inner concentric circles, and the radius is +.>The concentric circles of the suspected metal hole areas are marked as circumference concentric circles, and the radius is +.>The concentric circles of the suspected metal hole areas of (2) are marked as outer concentric circles, < >>Is the empirical value of the radius of the suspected metal hole region +.>I.e. +.>. Forming an inner circular ring by the inner concentric circle and the edge of the suspected metal hole area, forming a circumferential circular ring by the circumferential concentric circle and the edge of the suspected metal hole area, and forming an outer circular ring by the circumferential concentric circle and the edge of the suspected metal hole areaThe edges of the concentric circles form an outer ring.
According to the difference of the gray values of the pixel points of the circumferential ring, the inner ring and the outer ring and the distribution condition of the gray values of the pixel points in the circumferential ring, the copper embedding characteristic indexes of the suspected metal hole areas are expressed as follows:
wherein,copper-embedded characteristic index of suspected metal hole area, < ->As an exponential function based on natural constants, < +.>Is the average value of gray values of all pixel points in the circumference ring, < >>The average value of gray values of all pixel points in the inner circular ring is obtained; />Is the average value of gray values of all pixel points in the outer circular ring, +.>The standard deviation of gray values of all pixel points in the circumferential ring.
When the gray values of the pixels of the circumferential ring, the inner ring and the outer ring are different more and the distribution is more uneven, the more likely to generate bulges or gaps at the edges of the suspected metal hole areas, the larger the copper embedding characteristic index value of the suspected metal hole areas.
The periphery of the metal hole is relatively flat, or the surface of the rigid PCB is other elements except the metal hole copper embedding structure, or the metal hole copper embedding structure with lower defect degree is adopted, and only suspected metal hole areas with higher copper embedding characteristic indexes are subjected to the following stepsThe domain is analyzed. The characteristic index of embedded copper is larger than the flattening threshold valueThe suspected metal hole area of (2) is marked as a metal hole copper-embedded structure, and the flattening threshold value is +.>The empirical value was 0.6.
Thus, a copper-embedded structure of the metal hole is obtained.
The annular gap interval index acquisition module is used for acquiring copper block edge points and metal hole edge points according to the metal hole copper embedding structure and the printed circuit board binary image; acquiring a gap connecting line according to the edge points of the copper block and the edge points of the metal hole, and calculating a gap interval index of the gap connecting line by combining gray values of all pixel points in the copper embedded structure of the metal hole; and obtaining the annular gap interval index of the metal hole copper-embedded structure according to the gap interval indexes of all the gap connecting wires inside the metal hole copper-embedded structure.
The copper block is easy to deform when being pressed into the rigid PCB, so that the contact area between the copper block and the rigid PCB is reduced, and the copper block is easy to fall off from the rigid PCB. When the diameter of the copper block is too small, after the copper block is embedded into the metal hole, the copper block cannot be in close contact with the hole wall of the metal hole, and gaps appear in the middle area of the copper block and the hole wall, and the copper block is in an irregular ring shape.
Calculating gradient values and gradient directions of all pixel points in the metal hole copper embedded structure, and constructing the metal hole copper embedded structure with the pixel points as centers to obtain the metal hole copper embedded structure with the size ofThe average value of gradient values of all pixel points in the neighborhood window is recorded as the neighborhood gradient of the pixel points, and the number of the edge pixel points of the metal hole copper embedded structure is +.>Embedding metal hole into copper structure with maximum neighborhood gradient>The pixel points are marked as copper block edge points, < >>The number of the edge pixel points of the empirically-valued metal hole copper-embedded structure is 0.8 times that of the edge pixel points, and the side length of a neighborhood window is +.>The empirical value was 5.
The average value of the neighborhood gradients of all copper block edge points in the metal hole copper embedding structure is recorded as the gradient average value, and a gap gradient threshold value is setWhen the gradient mean value is smaller than the gap gradient threshold value +.>When the metal hole copper-embedded structure is in the copper-embedded structure, judging that the metal hole copper-embedded structure has no defect; otherwise, for each copper block edge point inside the metal hole copper embedding structure, starting from the copper block edge point, marking a first edge pixel point along the gradient direction of the copper block edge point as a metal hole edge point of the copper block edge point, wherein the gap gradient threshold value is equal to the gradient threshold value>The empirical value was 20 and the gap spacing is schematically shown in figure 3.
The line segment connecting the copper block edge point and the corresponding metal hole edge point is marked as a gap connecting line, and the gap interval index of the gap connecting line is expressed as follows according to the difference of gray values of pixel points and surrounding areas on the gap connecting line and the length of the gap connecting line:
wherein,the +.>Strip gap connectionGap interval index of wiring->The inside of the copper embedded structure is embedded with the metal hole>Coordinates of edge points of the copper block, +.>The +.>Coordinates of edge points of the individual metal holes, +.>Indicating that the Euclidean distance between two coordinate points is taken,/->The +.>The number of pixel points on the slit connecting line, < >>The +.>The first part of the slit connecting line>Individual pixel dot->Gray value of +.>The gray value average value of all pixel points in the copper embedded structure of the metal hole is obtained.
When the gray value difference between the pixel points on the gap connecting line of the metal hole copper embedding structure and the pixel points in the surrounding area is larger, the depth of the gap is deeper, the gap interval index value of the gap connecting line is larger, the copper block is less tightly connected with the metal hole, and the gap interval index value of the gap connecting line is larger; when the distance between the edge point of the copper block and the edge point of the metal hole in the copper embedded structure of the metal hole is larger, the wider the gap is, the less tightly the copper block is connected with the metal hole, and the larger the gap interval index value of the gap connecting line is.
The sum of gap interval indexes of all gap connecting lines of the metal hole copper-embedded structure is recorded as an annular gap interval index of the metal hole copper-embedded structure。
Thus, the annular gap interval index of the metal hole copper-embedded structure is obtained.
And the annular pore gradient acquisition module is used for acquiring the annular pore gradient of the metal hole copper-embedded structure according to the gap interval indexes of all the gap connecting lines inside the metal hole copper-embedded structure.
After the copper block is pressed into the metal hole on the surface of the printed circuit board, if the copper block is tightly attached to a part of the metal hole, uneven stress of the copper block can be caused when gaps exist in other areas, and the copper block can fall off from the metal hole more easily. Inside the copper structure is inlayed to the metal hole, copper block edge point and gap connecting wire one-to-one, according to the gap interval index of all gap connecting wires inside the copper structure is inlayed to the metal hole, with the annular pore gradient of copper structure is inlayed to the metal hole as follows:
wherein,annular pore gradient of copper-embedded structure for metal hole, +.>The number of the internal gap connecting lines of the copper embedded structure for the metal holes is +.>Maximum value of gap interval index of all gap connecting lines in metal hole copper embedded structure, +.>For the minimum value of the gap interval index of all gap connecting lines in the metal hole copper embedded structure, +.>Maximum value of the length of all gap connecting lines in the copper-embedded metal hole structure, < >>The minimum value of the lengths of all gap connecting lines in the copper embedded structure of the metal hole.
When the length of the gap connecting line and the gap interval index difference in the metal hole copper-embedded structure are larger, the inclination degree of the gap is higher, and the inclination value of the annular pore of the metal hole copper-embedded structure is larger.
Thus, the inclination of the annular pore of the metal pore copper-embedded structure is obtained.
And the circuit board defect detection module is used for acquiring the defect degree of the circuit board according to the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the metal hole copper embedding structure and dividing the defect degree of the printed circuit board into four grades of defect-free, slight, moderate and severe.
According to the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the metal pore copper embedding structure, the defect degree of the circuit board is expressed as follows:
wherein,for the defect degree of the circuit board, +.>As an exponential function based on natural constants, < +.>The number of copper embedded structures for metal holes on the printed circuit board is +.>Copper-embedded characteristic index for metal hole copper-embedded structure, < ->Annular void interval index for copper-embedded metal hole structure, < >>The inclination of the annular pore is that of a metal pore copper embedding structure.
When the copper embedded characteristic index of the metal hole copper embedded structure is larger, the metal hole copper embedded structure is more likely to generate bulges at the edge or gaps inside; when the inclination of the annular pore and the interval index of the annular pore of the metal hole copper-embedded structure are larger, the depth and the width of the gap in the metal hole copper-embedded structure are larger, the inclination degree is higher, and the defect degree of the circuit board is higher.
When the defect degree of the circuit board is smaller than the light threshold valueWhen the copper embedded structure of the metal hole of the printed circuit board is judged to be defect-free; when the defect degree of the circuit board is more than or equal to the slight threshold value +.>While being smaller than the medium threshold +.>When the defect degree of the copper embedding structure of the metal hole of the printed circuit board is judged to be mild; when the defect degree of the circuit board is more than or equal to the middle threshold value +.>At the same time less than the severe threshold->When determining the printed circuit board metalThe defect degree of the copper embedded structure is moderate; when the defect degree of the circuit board is more than or equal to the severe threshold valueWhen the defect degree of the copper embedded structure of the metal hole of the printed circuit board is judged to be severe, the slight threshold value is +.>The empirical value is 0.3, the medium threshold value +.>The empirical value is 0.5, the severe threshold value +.>The empirical value was 0.8.
Thus, the defect detection of the copper embedded structure of the metal hole of the rigid PCB is completed.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (8)
1. A rigid PCB metal hole copper-embedded structure visual inspection system, comprising the following modules:
the printed circuit board image acquisition module is used for acquiring a printed circuit board image containing a metal hole copper-embedded structure;
the metal hole copper-embedded structure acquisition module is used for acquiring a printed circuit board binary image and a suspected metal hole area according to the printed circuit board image; acquiring a circumferential ring, an inner ring and an outer ring according to the suspected metal hole area; calculating the copper embedding characteristic index of the suspected metal hole area according to the circumferential ring, the inner ring and the outer ring; determining a copper embedding structure of the metal hole according to the copper embedding characteristic index of the suspected metal hole area;
the annular gap interval index acquisition module is used for acquiring copper block edge points and metal hole edge points according to the metal hole copper embedding structure and the printed circuit board binary image; acquiring a gap connecting line according to the edge points of the copper block and the edge points of the metal hole, and calculating a gap interval index of the gap connecting line by combining gray values of all pixel points in the copper embedded structure of the metal hole; acquiring annular gap interval indexes of the metal hole copper-embedded structure according to the gap interval indexes of all gap connecting wires in the metal hole copper-embedded structure;
the annular pore gradient acquisition module is used for acquiring the annular pore gradient of the metal hole copper-embedded structure according to the gap interval indexes of all the gap connecting lines in the metal hole copper-embedded structure;
the circuit board defect detection module is used for obtaining the defect degree of the circuit board according to the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the metal hole copper embedding structure and dividing the defect degree of the printed circuit board into four grades of defect-free, slight, moderate and severe;
the method for obtaining the annular gap interval index comprises the following steps: the sum of gap interval indexes of all gap connecting lines of the metal hole copper-embedded structure is recorded as an annular gap interval index of the metal hole copper-embedded structure;
the method for obtaining the inclination of the annular pore comprises the following steps: the extremely poor of gap interval indexes of all gap connecting lines in the copper-embedded metal hole structure is recorded as gap characteristic difference; the extreme difference of the lengths of all the gap connecting lines in the copper-embedded metal hole structure is recorded as the gap length difference; the sum of the gap characteristic difference and the gap length difference is recorded as a third accumulated sum; and (3) recording the ratio of the third accumulated sum to the number of the gap connecting lines in the metal hole copper-embedded structure as the annular pore gradient of the metal hole copper-embedded structure.
2. The visual inspection system of copper-embedded structure of rigid PCB metal holes of claim 1, wherein the method for obtaining the binary image of the PCB and the suspected metal hole area from the image of the PCB comprises:
acquiring edge information of the printed circuit board image by using an edge detection operator to obtain a printed circuit board binary image;
acquiring a Hough parameter space of a binary image of the printed circuit board by using Hough circle transformation, wherein the Hough parameter space is a three-dimensional matrix, and three dimensions comprise a circle center abscissa, a circle center ordinate and a radius;
and when the element value determined by the circular abscissa, the circular ordinate and the radius in the Hough parameter space is larger than a preset circular judgment threshold value, judging that a circular area on the printed circuit board image represented by the circular abscissa, the circular ordinate and the radius is a suspected metal hole area.
3. The visual inspection system of copper-embedded structure of metal hole of rigid PCB of claim 1, wherein the method for obtaining the circumferential ring, the inner ring and the outer ring according to the suspected metal hole area comprises:
the radius of the suspected metal hole area is marked as a standard radius;
the sum of the standard radius and twice the preset circumference radius is recorded as an outer radius;
the sum of the standard radius and the preset circumference radius is recorded as the circumference radius;
the difference value between the standard radius and the preset circumference radius is recorded as an inner radius;
the outer radius replaces the radius of the suspected metal hole area, and outer concentric circles of the suspected metal hole area are obtained;
substituting the radius of the suspected metal hole area with the circumference radius to obtain circumference concentric circles of the suspected metal hole area;
replacing the radius of the suspected metal hole area with the inner radius to obtain an inner concentric circle of the suspected metal hole area;
the closed area surrounded by the edges of the outer concentric circle and the circumferential concentric circle is marked as an outer circular ring;
the closed area formed by surrounding the circumference concentric circle and the edge of the suspected metal hole area is marked as a circumference ring;
and (5) marking a closed area surrounded by the inner concentric circle and the edge of the suspected metal hole area as an inner circular ring.
4. The visual inspection system of copper embedded structure of a rigid PCB metal hole according to claim 1, wherein the method for calculating the copper embedded characteristic index of the suspected metal hole area according to the circumferential ring, the inner ring and the outer ring comprises the following steps:
the average value of the gray values of all the pixel points in the circumference ring is recorded as the circumference gray average value;
the average value of the gray values of all the pixel points in the inner circular ring is recorded as the average value of the gray values in the circular ring;
the average value of the gray values of all pixel points in the outer circular ring is recorded as the average value of the gray values outside the circular ring;
the absolute value of the difference between the circumference gray average value and the in-circle gray average value is recorded as a first absolute value;
the absolute value of the difference between the circumference gray average value and the out-of-circle gray average value is recorded as a second absolute value;
the sum of the first absolute value and the second absolute value is recorded as a first accumulated sum;
the standard deviation of gray values of all pixel points in the circumferential ring is recorded as a first standard deviation;
the ratio of the first accumulated sum to the first standard deviation is recorded as a first ratio;
and recording the normalized value of the first ratio as the copper embedding characteristic index of the suspected metal hole area.
5. The visual inspection system of copper-embedded structure of metal holes of rigid PCB according to claim 1, wherein the method for determining copper-embedded structure of metal holes according to the copper-embedded characteristic index of suspected metal hole area comprises:
and marking the suspected metal hole area with the copper embedding characteristic index larger than the preset flattening threshold value as a metal hole copper embedding structure.
6. The visual inspection system of a copper-embedded structure of a rigid PCB metal hole according to claim 5, wherein the method for obtaining the edge points of the copper block and the edge points of the metal hole according to the binary images of the copper-embedded structure of the metal hole and the printed circuit board comprises the following steps:
calculating gradient values and gradient directions of all pixel points in the copper embedded metal hole structure;
constructing a neighborhood window with a preset window length as a side length by taking a pixel point as a center;
the average value of the gradient values of all the pixel points in the neighborhood window is recorded as the neighborhood gradient of the pixel point;
marking a first preset number of pixel points with the largest neighborhood gradient in the copper-embedded metal hole structure as copper block edge points;
marking the pixel point with the pixel value of 1 as the edge pixel point in the binary image of the printed circuit board;
starting from the copper block edge point, the first edge pixel point in the gradient direction of the copper block edge point in the metal hole embedded copper structure is marked as the metal hole edge point of the copper block edge point.
7. The visual inspection system of a copper-embedded structure of a rigid PCB metal hole according to claim 1, wherein the method for obtaining the gap connecting line according to the edge points of the copper block and the edge points of the metal hole, and combining the gray values of all the pixel points in the copper-embedded structure of the metal hole, the method for calculating the gap interval index of the gap connecting line is as follows:
the line segment connecting the edge point of the copper block and the edge point of the metal hole is marked as a gap connecting line;
the Euclidean distance between the edge point of the copper block and the edge point of the metal hole is recorded as the length of a gap connecting line;
the gray value average value of all pixel points in the copper-embedded metal hole structure is recorded as a first gray value average value;
the absolute value of the difference value between the gray value of the pixel point and the first gray average value is recorded as the gray difference of the pixel point;
the gray level difference of all pixel points on the gap connecting line of the metal hole copper-embedded structure is recorded as a second accumulation sum;
and (3) recording the product of the length of the gap connecting line and the second accumulated sum as a gap interval index of the gap connecting line.
8. The visual inspection system of a copper-embedded structure of a rigid PCB metal hole according to claim 1, wherein the method for obtaining the defect level of the circuit board according to the copper-embedded characteristic index, the annular pore gradient and the annular void interval index of the copper-embedded structure of the metal hole comprises the following steps:
the product of the copper embedding characteristic index, the annular pore gradient and the annular pore interval index of the metal pore copper embedding structure is recorded as the pore defect degree of the metal pore copper embedding structure;
the sum of the pore defect degrees of all the metal hole copper-embedded structures in the printed circuit board image is recorded as a fourth accumulated sum;
and recording the normalized value of the fourth accumulated sum as the defect degree of the circuit board.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311652332.3A CN117372426B (en) | 2023-12-05 | 2023-12-05 | Rigid PCB metal hole copper-embedded structure visual detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311652332.3A CN117372426B (en) | 2023-12-05 | 2023-12-05 | Rigid PCB metal hole copper-embedded structure visual detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117372426A CN117372426A (en) | 2024-01-09 |
| CN117372426B true CN117372426B (en) | 2024-03-29 |
Family
ID=89393236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311652332.3A Active CN117372426B (en) | 2023-12-05 | 2023-12-05 | Rigid PCB metal hole copper-embedded structure visual detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117372426B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108982512A (en) * | 2018-06-28 | 2018-12-11 | 芜湖新尚捷智能信息科技有限公司 | A kind of circuit board detecting system and method based on machine vision |
| CN114424053A (en) * | 2019-07-12 | 2022-04-29 | 布鲁克纳米公司 | Method and system for detecting defect of equipment by using X-ray |
| CN115311262A (en) * | 2022-10-09 | 2022-11-08 | 南通如东依航电子研发有限公司 | Printed circuit board defect identification method |
| CN115802614A (en) * | 2022-11-23 | 2023-03-14 | 金禄电子科技股份有限公司 | Copper block embedded circuit board and preparation method thereof |
| CN115866933A (en) * | 2022-12-28 | 2023-03-28 | 九江明阳电路科技有限公司 | Copper-embedded block plate manufacturing method and copper-embedded block plate |
| CN116433666A (en) * | 2023-06-14 | 2023-07-14 | 江西萤火虫微电子科技有限公司 | Board card line defect online identification method, system, electronic equipment and storage medium |
-
2023
- 2023-12-05 CN CN202311652332.3A patent/CN117372426B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108982512A (en) * | 2018-06-28 | 2018-12-11 | 芜湖新尚捷智能信息科技有限公司 | A kind of circuit board detecting system and method based on machine vision |
| CN114424053A (en) * | 2019-07-12 | 2022-04-29 | 布鲁克纳米公司 | Method and system for detecting defect of equipment by using X-ray |
| CN115311262A (en) * | 2022-10-09 | 2022-11-08 | 南通如东依航电子研发有限公司 | Printed circuit board defect identification method |
| CN115802614A (en) * | 2022-11-23 | 2023-03-14 | 金禄电子科技股份有限公司 | Copper block embedded circuit board and preparation method thereof |
| CN115866933A (en) * | 2022-12-28 | 2023-03-28 | 九江明阳电路科技有限公司 | Copper-embedded block plate manufacturing method and copper-embedded block plate |
| CN116433666A (en) * | 2023-06-14 | 2023-07-14 | 江西萤火虫微电子科技有限公司 | Board card line defect online identification method, system, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 机器学习建模流程中的一些基本数学原理;郑凯;;科技经济导刊(第24期);120-122 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117372426A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113989280B (en) | Steel structure welding crack defect detection method based on image processing technology | |
| CN107084666B (en) | Comprehensive detection method for size of brake pad based on machine vision | |
| US20060018534A1 (en) | Technique for detecting a defect of an object by area segmentation of a color image of the object | |
| US20150153726A1 (en) | Method for inspecting a manufacturing device | |
| Anoop et al. | A review of PCB defect detection using image processing | |
| CN115020267A (en) | Semiconductor surface defect detection method | |
| CN106683040B (en) | Infrared panoramic image splicing method based on NCC algorithm | |
| CN115965623A (en) | Surface flaw detection method and system in transformer production | |
| Said et al. | Automated void detection in solder balls in the presence of vias and other artifacts | |
| CN117372426B (en) | Rigid PCB metal hole copper-embedded structure visual detection system | |
| CN114549530A (en) | PCB welding quality evaluation method based on image processing | |
| CN107967679B (en) | Method for automatically selecting positioning core based on vector graph of PCB product | |
| CN112801948B (en) | Method, system and storage medium for detecting board line defect of printed circuit board | |
| JP6253490B2 (en) | Winding inspection method and winding inspection apparatus | |
| JP4841819B2 (en) | Defect detection by color image of an object | |
| CN117269179A (en) | High-precision detection method and system for edge defects of contact lens based on machine vision | |
| CN110766649B (en) | Defect judging device and method for automatic repair system | |
| CN115375679B (en) | Edge-finding and point-searching positioning method and device for defective chip | |
| CN109376770B (en) | Grid area identification method and device applied to negative film inspection machine | |
| CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN115100095A (en) | PCB detection method based on unsupervised algorithm | |
| JP6114559B2 (en) | Automatic unevenness detector for flat panel display | |
| JP6202739B2 (en) | Method for inspecting scattered solder balls on boards | |
| CN112529902A (en) | Hole checking method of PCB (printed circuit board) | |
| CN117611528A (en) | PCB image detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |