JP7224048B2 - Substrate defect inspection device and method - Google Patents

Description

The embodiments disclosed herein relate to an apparatus and method for inspecting defects in a board, and more particularly, to an apparatus and method for inspecting board defects that do not require reconfirmation of defects in a board such as a printed circuit board. It is a thing.

Products such as printed circuit boards (PCBs) are subjected to various types of inspections because they may have various types of defects due to shipment. In this regard, Korean Patent Publication No. 10-2005-0103525, which is a prior art document, prevents excessive contact between a pattern formed on the bottom surface of a PCB and probe pins before inspection. A PCB inspection and sorting apparatus is disclosed.

In order to test a printed circuit board, a rule-based test is performed in addition to the electrical test as in the prior art. In such rule-based inspection, an inspector directly applies predetermined rules to the printed circuit board to perform the inspection.

This kind of rule-based inspection inspects according to the rules determined by the inspector, so it detects foreign matter and contamination that are not defects as defects, and rules are set excessively to increase the probability of defect detection. , errors in normal specifications may also be recognized and detected as defects. In order to prevent such a situation, there is a problem in that it is necessary to additionally identify whether the PCB is normal or defective by using additional equipment for inspecting the PCB. .

In addition, due to PCB inspection, it is not possible to maintain a certain level of inspection standards for each worker. I had a problem with it.

Therefore, there is a need for a technique for solving the above-described problems.

On the other hand, the above-mentioned background art is technical information that the inventor possessed for derivation of the present invention or learned during the derivation process of the present invention. technology.

Korean Patent Publication No. 10-2005-0103525

An object of the embodiments disclosed in this specification is to provide a board defect inspection apparatus and method for automating inspection processes by operators.

The embodiments disclosed in this specification aim to present a substrate defect inspection apparatus and method that does not require additional equipment or additional inspections for the inspector.

The embodiments disclosed in this specification aim to provide a substrate defect inspection apparatus and method that can maintain consistency in substrate inspection results.

An object of the embodiments disclosed in this specification is to provide a substrate defect inspection apparatus and method capable of improving the yield of products by automating substrate inspection.

As a technical means for achieving the above-described technical problem, according to one embodiment, a board defect inspection apparatus includes a movable worktable for moving a board to a position for inspection, and a illumination for irradiating a substrate with predetermined light; at least one line scan camera for capturing images of the substrate in units of predetermined lines; at least one area camera for capturing images of the substrate in units of predetermined areas; and a database for storing images for detecting, moving the position of the substrate using the movable workbench, controlling the lighting, and photographing the plated portion of the substrate from the line scan camera and the solder resist An image obtained by photographing a part is acquired, and the state of the substrate is determined as one of normal, defective, and re-inspected from the acquired image to detect a primary failure, and for the substrate determined to be re-inspected. a control unit for controlling the illumination to obtain a board image of the board photographed by an area camera, determining the status of the board as normal or defective from the obtained board image, and detecting a secondary defect; including.

According to another embodiment, the board defect inspection method performed by the board defect inspection apparatus controls the illumination for irradiating the board with light, and captures an image of the plated part of the board and the solder resist part with a line scan camera. determining the state of the board as one of normal, defective, and re-inspected from the acquired image to detect a primary defect; Obtaining a substrate image obtained by photographing the substrate with an area camera by controlling lighting; and detecting a secondary failure by determining one of normality and failure from the obtained substrate image and the state of the substrate. .

According to still another embodiment, there is provided a computer-readable recording medium storing a program for performing a board defect inspection method, wherein the board defect inspection method controls illumination for irradiating light onto a board and uses a line scan camera. acquiring an image of the plated part of the board and an image of the solder resist part, and determining one of normal, defective, and re-inspection from the acquired image and the state of the board to determine the first defect. obtaining a board image obtained by photographing the board with an area camera by controlling lighting for the board determined to be re-inspected; obtaining one of normal and defective board images from the obtained board image; and determining the condition to detect secondary failures.

According to still another embodiment, a computer program stored in a medium for performing a substrate inspection method performed by a substrate inspection apparatus, the substrate inspection method comprising irradiating a substrate with light. Obtaining an image of a plated part of a board and an image of a solder resist part by a line scan camera by controlling illumination, and one of normal, defective, and re-inspection from the obtained images and the state of the board. Detecting a first defect by determining , obtaining a board image of the board photographed by an area camera by controlling lighting for the board determined to be re-inspected, and obtaining a normal board image from the obtained board image and determining one of the defects and the state of the substrate to detect a secondary defect.

According to any one of the above-described means for solving the problems of the present invention, it is possible to provide a substrate defect inspection apparatus and method for automating an inspection process by an operator.

According to any one of the means for solving the problems of the present invention, it is possible to present a substrate defect inspection apparatus and method that do not require additional equipment or additional inspection for an inspector.

According to any one of the means for solving the problems of the present invention, it is possible to provide a substrate defect inspection apparatus and method capable of maintaining consistency in substrate inspection results.

According to any one of the means for solving the problems of the present invention, it is an object of the present invention to provide a board defect inspection apparatus and method capable of improving the yield of products by automating the board inspection.

The effects obtained by the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art in the technical field to which the present invention belongs from the following description. .

1 is a block diagram showing a board defect inspection apparatus according to one embodiment; FIG. 1 is a cross-sectional view showing a substrate defect inspection apparatus according to an embodiment; FIG. FIG. 4 is a diagram for explaining imaging of a substrate using a line scan camera according to one embodiment; FIG. 4 is a diagram for explaining imaging of a substrate using an area camera according to one embodiment; 4 is a flow chart for explaining a board defect inspection operation performed by the board defect inspection apparatus according to one embodiment; 6 is a flowchart for explaining an operation of determining a defect using an image captured by a line scan camera according to an embodiment; 4 is a flowchart for explaining an operation of determining a defect using an image captured by an area camera according to an embodiment;

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In addition, in order to clearly describe the present invention, parts that are not related to the description are omitted from the drawings, and similar parts are denoted by similar reference numerals throughout the specification.

Throughout the specification, when it is said that one part is "connected" to another part, this is not limited to "directly connected", but also "electrically connected" with another element interposed therebetween. "Including cases where In addition, when a part "includes" a certain component, it does not exclude other components, but means that it can further include other components, unless otherwise specified.

An embodiment will be described in detail below with reference to the accompanying drawings.

Prior to describing the embodiments, the meanings of the terms used below are defined.

A 'substrate' is a substrate that reproduces electrical wiring that connects circuit parts based on circuit design in the form of an electrical conductor on an insulator, such as a printed circuit board (hereinafter referred to as 'PCB') and a flexible printed circuit. A substrate (FPCB: Flexible Printed Circuit Board) may be included. A board means an object or object to be inspected by a board defect inspection apparatus, which will be described later. Therefore, the substrate can be a display panel, a PCB panel, a liquid crystal display (LCD), an organic light emitting diode (OLED), a solar panel, a fabric, or a It can also be replaced with metals and other products that can be inspected by acquiring images.

FIG. 1 is a block diagram showing a board defect inspection apparatus according to one embodiment.

As shown in FIG. 1, the substrate defect inspection apparatus 100 includes a mobile workbench 110, a lighting 120, a database 130, an alignment camera 140, a line scan camera 150, an area camera 160, an input/output unit 170, and a control unit 180. be able to.

A mobile worktable 110 moves the substrate into position for inspection. The mobile workbench 110 may include a boat on which substrates to be inspected are mounted and rails to which the boat is coupled to move. Also, a strip for fixing the substrate may be positioned on the upper end of the boat.

The mobile workbench 110 may include a flipper for flipping the substrate when both sides of the substrate are to be inspected, if necessary. The mobile workbench 110 may also include a storage tray for sorting and storing the inspected substrates.

The lighting 120 may be positioned around one or more cameras, such as the line scan camera 150 or the area camera 160, that acquire an image of the substrate for inspection, and may illuminate the substrate positioned on the boat. can. Therefore, if the number of line scan cameras 150 and area cameras 160 for inspection increases, the number of illuminations 120 can also increase. The lighting 120 can adjust the brightness by controlling the lighting value, and can generate various images by adjusting the brightness. Two or more lights 120 can be used at the same time to acquire one image when photographing a substrate. Illumination 120, when corresponding to area camera 160, may have a predetermined illumination value (or a predetermined brightness) that allows for classification according to substrate failure characteristics.

Various types of data such as files or programs can be embedded and stored in the database 130 . Data stored in the database 130 can be accessed and used by the controller 180, which will be described later, or new data can be stored by the controller 180. FIG. Also, the database 130 may store programs executable by the control unit 180 .

Database 130 may store data about defective substrates. For example, the database 130 can store defective substrate images from which defective substrates can be determined. Here, the defective board image stored in the database 130 is data learned by artificial intelligence, and can be used to inspect the defective board.

The database 130 can store files for inspection of defective substrates. The database 130 can store a program capable of classifying defective substrates and even detecting types of defects of the classified defective substrates. In particular, the database 130 is a computer program embodying artificial intelligence (AI) that performs deep learning to learn defective image data and uses the learned defective image data to detect defective images in order to inspect defective substrates. can be saved.

Alignment camera 140 photographs the board to be inspected. The alignment camera 140 may provide the captured image to the controller 180 . Alignment camera 140 can be positioned within a predetermined distance from each of line scan camera 150 and area camera 160 . Accordingly, the alignment camera 140 captures images necessary for aligning the images captured by the line scan camera 150 or the area camera 160 for inspection.

The line scan camera 150 is a camera that photographs the substrate in units of lines of a predetermined length using a line-type image sensor. The line scan camera 150 can provide imaging data to the controller 180 in order to determine defects in the imaged substrate. Since the line scan camera 150 captures images in line form, it is possible to capture images even when the substrate is moving.

The area camera 160 is a camera that captures an image of the substrate in units of areas within a predetermined range. The area camera 160 can image the substrate and provide the imaging data to the controller 180 for determining defects in the substrate imaged.

The alignment camera 140, the line scan camera 150, and the area camera 160 are attached to some fixed structures of the substrate defect inspection apparatus 100, and are driven by motors that move in mutually perpendicular X-axis, Y-axis, and Z-axis directions. can contain or be attached to it. For example, if the X-axis is horizontal, the Y-axis can be vertical, and the Z-axis can be depth into the substrate (ie, toward or away from the substrate). Here, the X-axis and Y-axis may be parallel to the ground, and the Z-axis may be perpendicular to the ground. The alignment camera 140, the line scan camera 150, and the area camera 160 can capture an image of the substrate for inspection by adjusting the positions of the cameras based on three axes.

Accordingly, each of the alignment camera 140, the line scan camera 150, and the area camera 160 can be set to a predetermined magnification for capturing an image of the substrate under the control of the controller 180, for example, 5 μm to 15 μm. A magnification can be set to detect even minute defects having a size.

The input/output unit 170 may include an input unit for receiving input from a user, i.e., an inspector, and an output unit for displaying information such as the result of work performed or the status of the board defect inspection apparatus 100 . can. For example, the input/output unit 170 may include an operation panel for receiving user input and a display panel for displaying screens.

Specifically, the input unit may include devices capable of receiving user input in various forms, such as a keyboard, physical buttons, a touch screen, a camera, or a microphone. Also, the output unit may include a display panel, a speaker, or the like. However, without being limited thereto, the input/output unit 170 may include a configuration that supports various inputs/outputs.

The control unit 180 controls the overall operation of the board defect inspection apparatus 100 and may include a processor such as a CPU. The control unit 180 may control other components included in the board defect inspection apparatus 100 to perform operations corresponding to user inputs received through the input/output unit 170 .

The controller 180 can control the movable workbench 110 so that the board inserted into the board defect inspection apparatus 100 can be moved to each position for inspection.

The controller 180 can control the illumination 120 corresponding to the line scan camera 150 for defect detection. For example, the controller 180 can adjust the brightness of the illumination 120 in two steps. Here, the control unit 180 can control the illumination 120 to the illumination value for inspection of the portion where the circuit is generated, and control the illumination 120 to the illumination value for inspection of the plated portion. Thus, the controller 180 can control the lighting 120 corresponding to the line scan camera 150 twice.

The control unit 180 adjusts the brightness of the lighting 120 in two stages, and shoots an image of the plated portion of the board and an image of the portion where the circuit is generated (for example, the solder resist (SR) portion). The line scan camera 150 can be controlled to do so. Here, the image of the plated part and the solder resist part is the brightness image. Accordingly, the control unit 180 aligns the photographed image of the plating portion and the photographed image of the solder resist portion, and judges the state of the board by matching the aligned images as one of normal, defective (intrinsic defect), and re-inspection. can do. Also, the line scan camera 150 may be a color line scan camera capable of capturing color images.

Since the resolution of the line scan camera 150 is lower than the resolution of the area camera 160, the control unit 180 cannot perform an accurate inspection for defect determination for defects smaller than a preset predetermined size (length or area). may be necessary. In this way, the control unit 180 can determine that defects smaller than a predetermined size should be re-inspected. In addition, the control unit 180 can also determine to re-inspect defects that are determined to require more accurate classification of defect determination.

The controller 180 may primarily detect defects in the substrate using an image acquired through the line scan camera 150 . The control unit 180 can also determine the type of defect for a board determined to be defective, ie, an intrinsic defect. For example, it is possible to distinguish between circuit failures and plating failures. Here, circuit defects include open circuit, short circuit, upper scratch, lower scratch, foreign matter, metallic foreign matter, solder resist (SR) peeling, AOI (Automated Optical Inspection) failure, unetched, SR residue, Detail defects for cracks, discoloration, lifting, and staining can be included. In addition, plating defects include detailed defects such as plating open, plating short, plating lump, scratch, foreign matter, puncture, impression, hole, SR residue, discoloration, nickel (Ni) exposure, copper (Cu) exposure, protrusion, and chipping. can include Therefore, the control unit 180 determines one of the circuit failure and the plating failure with respect to the board determined as the intrinsic failure, and determines the types of detailed failures corresponding to the circuit failure and the plating failure. can be done.

The controller 180 may use a deep learning-based algorithm for detecting the location of irregularly occurring defects. The control unit 180 can classify the above-described circuit failure and plating failure into one of about 30 kinds of failures according to the type of failure using a deep learning algorithm.

After that, the control unit 180 can detect defects in the board determined to be re-inspected. The controller 180 can adjust the brightness of the illumination 120 corresponding to the area camera 160 for defect detection. For example, the controller 180 can adjust the brightness of the lighting 120 in three levels. Here, the control unit 180 controls the illumination 120 to an illumination value for inspection of the portion where the circuit is generated, controls the illumination 120 to an illumination value for inspection according to the defect characteristics, height deviation or layer by layer. Illumination 120 can be controlled to an illumination value for inspection of defects that occur in . Thus, the controller 180 can control the lighting corresponding to the area camera 160 three times.

The control unit 180 can control the area camera 160 so that the brightness of the lighting 120 can be adjusted to three levels and three images can be captured. The controller 180 may align the three images acquired from the area camera 160 into a single image to determine a defect. The controller 180 can determine the state of the substrate as normal or defective (intrinsic defect) using the aligned image. Also, the area camera 160 may be a color area camera capable of capturing color images.

The control unit 180 may secondarily detect defects of the board using an image acquired using the area camera 160 . For example, the control unit 180 may determine that the state of the corresponding substrate, in which there are foreign matter, dust, and permissible defects as defective specifications, is normal from the acquired image.

The controller 180 can employ deep learning based algorithms for use in fast defect determination and fast object classification. The control unit 180 can determine failure using a deep learning algorithm.

As described above, the board defect inspection apparatus 100 can detect board defects in two steps classified into a primary inspection and a secondary inspection, thereby automating the board inspection process. Accordingly, the substrate defect inspection apparatus 100 can automatically inspect the substrate for defects without continuous monitoring by an administrator.

The board defect inspection apparatus 100 does not require additional equipment or inspection for the inspector, and can maintain the consistency of the board inspection result by inspecting the board using artificial intelligence. In addition, the board defect inspection apparatus 100 can improve the yield of products by automating the board inspection.

FIG. 2 is a cross-sectional view showing a board defect inspection apparatus according to one embodiment.

As shown in FIG. 2, the board defect inspection apparatus 100 may include a movable workbench composed of rails 210, 220, 230, 240, 250, 260, and 270. As shown in FIG.

The first rail 210 may include a stacker 211 on which substrates awaiting inspection are located. The first rail 210 can move the substrate positioned on the stacker 211 in the direction of arrow 1 and position it on the boat 221 positioned on the second rail 220 .

A cleaner 222 for treating the surface of the substrate may be positioned on the second rail 220 . A camera moving structure 223 may be positioned around the second rail 220 to capture an image for inspecting the board. A line scan camera 224 and an alignment camera 225 may be combined or attached to the camera movement structure 223 . Here, the camera moving structure 223 can move the camera in the X-axis, Y-axis and Z-axis directions. Here, the X-axis, the Y-axis and the Z-axis are perpendicular to each other, with the horizontal direction being the X-axis and the vertical direction being the Y-axis. On the other hand, the depth direction of the drawing is the Z axis. In particular, the camera moving structure 223 can also function to adjust the magnification of the camera when moving in the depth direction, and can detect even minute defects smaller than a predetermined size by adjusting the magnification.

When the boat 221 on which the board is positioned on the second rail 220 moves in the direction of the second arrow, the line scan camera 224 and the alignment camera 225 adjust their positions to capture images of the board. Therefore, the primary inspection can be performed using the image captured on the second rail 220 .

After completing the image capturing of the board on the second rail 220 , it can move along the first rail 210 . Here, if the board has to wait for inspection, the board can be placed in the buffer 212 located on the first rail 210 and wait for the inspection on the third rail 230 .

On the third rail 230, the alignment camera 231 and the area camera 232 can photograph the board using a moving structure. A secondary inspection may be performed using the image captured on the third rail 230 . A board determined to be normal or defective on the second rail 220 may be moved to the fourth rail 240 without taking an image for board inspection on the third rail 230 .

The fourth rail 240 may include a flipper for flipping the front and rear surfaces of the substrate. The flipper can flip the substrate in the direction of arrow number 5 and position it in the boat on the fifth rail 250 .

A cleaner 251 is positioned on the fifth rail 250 to wipe the surface of the substrate. When the boat on which the board is positioned on the fifth rail 250 moves in the direction of the sixth arrow, the alignment camera 252 and the line scan camera 253 adjust their positions to capture images of the board.

The sixth rail 260 moves the substrates in the direction of the seventh arrow, placing the substrates determined to be in a normal state on the normal substrate stacking portion 261 and placing the substrates determined to be in a defective state on the defective substrate stacking portion 262 . Then, the board determined to be re-inspected can be placed on the re-inspection board stacking unit 263 .

A retest board can be placed in a boat on the seventh rail 270 . While the board is moved in the direction of the eighth arrow using the boat of the seventh rail 270, the area camera 271 and the alignment camera 272 adjust their positions to capture images of the board.

When the inspection is completed on the seventh rail 270 , the board is moved in the direction of the ninth arrow on the sixth rail 260 , and the board that has been judged as defective is placed on the normal board loading section 261 and the defective board loading section 262 . , and the re-inspection substrate loading section 263 .

The board defect inspection apparatus 100 can directly inspect the board for defects without additional work by the operator 10, and the board defect inspection apparatus 100 that inspects both sides of the board will be described as an example. It can also be embodied so as to inspect only one side of the substrate. Here, the substrate defect inspection apparatus 100 may not include components corresponding to the fifth, sixth, eighth, and ninth arrows.

FIG. 3 is a diagram for explaining imaging of a substrate using a line scan camera according to one embodiment.

As shown in FIG. 3, at a, a substrate 321 is positioned on top of a boat 320 positioned on rails 310 .

At b, a boat 320 located on rails 310 can be moved for inspection near where linescan camera 330 and alignment camera 340 are located.

In c, d, and e, the line scan camera 330 and the alignment camera 340 can capture images while moving in the X-axis, Y-axis, and Z-axis directions. Here, the boat 320 can also move along.

After changing the lighting, steps f, g, h, and i, which are the same operations as b, c, d, and e, may be performed to photograph another image with the lighting adjusted. When the image capturing is completed, the boat returns to its original position as in j, and the board can be moved to the next inspection position.

FIG. 4 is a diagram for explaining imaging of a substrate using an area camera according to one embodiment.

As shown in FIG. 4, at a, a substrate 421 is positioned on top of a boat 420 positioned on rails 410 .

At b, a boat 420 located on rail 410 can be moved for inspection near where linescan camera 430 and alignment camera 440 are located.

In c, an image can be captured while the line scan camera 430 and the alignment camera 440 move in the X-axis, Y-axis, and Z-axis directions. Here, the boat 420 can also move along.

After changing the illumination, the alignment camera 440 can capture images while moving in the X-axis, Y-axis, and Z-axis directions at d and e. Here, the boat 420 can also move along.

When the image capturing is completed, the boat 420 returns to its original position and the board can be moved to the next inspection position as in f.

FIG. 5 is a flow chart for explaining the board defect inspection operation performed by the board defect inspection apparatus according to the embodiment.

As shown in FIG. 5, the board defect inspection apparatus 100 may control lighting and capture an image with a line scan camera (S510). Here, the substrate defect inspection apparatus 100 can separately photograph the plated portion and the solder resist portion by controlling illumination.

The board defect inspection apparatus 100 can determine board defects using the captured image. The board defect inspection apparatus 100 can determine the status of the board as normal, defective, and re-inspected (S520). Here, the substrate defect inspection apparatus 100 can use defect image data stored in a database and subjected to deep learning, and can determine defects by comparing defect image data corresponding to captured images. .

The board defect inspection apparatus 100 checks whether the board needs to be re-inspected according to the defect determination (S530).

As a result of checking in step S530, if the corresponding board is determined to be normal or defective according to the defect determination, and the board defect inspection apparatus 100 does not need to be retested, the board defect inspection apparatus 100 proceeds to step S560.

As a result of checking in step S530, if it is necessary to re-inspect the corresponding board according to the determination of the defect, the board defect inspection apparatus 100 proceeds to step S540.

The board defect inspection apparatus 100 can control the illumination and take an image with the area camera if re-inspection is required due to the defect determination (S540). Here, the substrate defect inspection apparatus 100 may acquire coordinate values of a portion that needs to be re-inspected, and use the acquired coordinate values to determine the defect of the re-inspected substrate.

The board defect inspection apparatus 100 may determine a defect of the re-inspection target board using the image captured by the area camera (S550). Here, the substrate defect inspection apparatus 100 can finally determine that the reinspection target substrate is normal or defective. Here, the substrate defect inspection apparatus 100 can use defect image data stored in a database and subjected to deep learning, and can determine defects by comparing defect image data corresponding to captured images. .

The board defect inspection apparatus 100 can output the result of board defect determination (S560). The board defect inspection apparatus 100 can detect the presence or absence of a defect in a board to be inspected as well as information on the type of defect.

The board defect inspection apparatus 100 can learn the defect image data stored in the database by deep learning (S570).

Board defect inspection apparatus 100 determines whether to end the inspection (S580). As a result of the determination in step S580, if the inspection is to be terminated, the board defect inspection apparatus 100 terminates its operation. However, if it is determined in step S580 that the inspection is not completed, the board defect inspection apparatus 100 proceeds to step S510, and can inspect the next board for defects.

FIG. 6 is a flow chart for explaining the operation of determining a defect using an image captured by a line scan camera according to an embodiment.

As shown in FIG. 6, the board defect inspection apparatus 100 can acquire normal images stored in the database (S611). Here, the normal image is an image corresponding to a normal substrate without defects, and can also be called a master image. Here, the substrate defect inspection apparatus 100 can also acquire parameters for defect inspection from the database. Meanwhile, the board defect inspection apparatus 100 can acquire normal images or parameters before the line scan camera captures images.

The board defect inspection apparatus 100 can convert the image captured by the line scan camera into the same coordinate system as the normal image (S613).

The board defect inspection apparatus 100 may divide the inspection interval area in the image captured by the line scan camera (S615). The board defect inspection apparatus 100 divides an image captured by a line scan camera into a plurality of sections for inspection.

The board defect inspection apparatus 100 may generate a difference image from the image captured by the line scan camera based on the normal image (S617).

The board defect inspection apparatus 100 may align the two images acquired by the illumination control (S619).

The board defect inspection apparatus 100 performs board defect inspection using the aligned image (S621). The board defect inspection apparatus 100 can utilize artificial intelligence based on deep learning to inspect board defects, and can also use the difference image acquired in step S617.

The board defect inspection apparatus 100 can detect a suspected defect area (S623). For example, the board defect inspection apparatus 100 may crop the area suspected of being defective, extract only the information of the suspected defect detection area, or remove the rest of the area where the defect detection is not suspected. .

The board defect inspection apparatus 100 may perform a defect re-inspection on the suspected defect area (S625). The board defect inspection apparatus 100 can utilize artificial intelligence based on deep learning to re-inspect the board for defects. The first artificial intelligence in step S621 and the second artificial intelligence in step S625 may be composed of different algorithms, the first artificial intelligence having a function specializing in detection, and the second artificial intelligence specializing in determination. It can have an integrated function.

The board defect inspection apparatus 100 may determine the state of the board as one of normal, defective, and re-inspection, and proceed to step S530 (S627).

FIG. 7 is a flow chart for explaining the operation of determining a defect using an image captured by an area camera according to an embodiment.

As shown in FIG. 7, the substrate defect inspection apparatus 100 can acquire normal images stored in the database (S611). Again, the normal image is an image corresponding to a normal board with no defects. Here, the board defect inspection apparatus 100 can also acquire parameters for defect inspection from the database. Meanwhile, the substrate defect inspection apparatus 100 can acquire normal images or parameters before the area scan camera captures images.

The substrate defect inspection apparatus 100 can detect defective portions (S713). For example, the board defect inspection apparatus 100 may crop the area suspected of being defective, extract only the information of the suspected defect detection area, or remove the rest of the area where the defect detection is not suspected. .

The substrate defect inspection apparatus 100 can transform the image captured by the area camera into the same coordinate system as the normal image (S715).

The board defect inspection apparatus 100 may generate a difference image from the image captured by the area camera based on the normal image (S717).

The board defect inspection apparatus 100 can match the three video images captured by lighting control (S719).

The board defect inspection apparatus 100 performs a board defect inspection using the aligned image (S721). The board defect inspection apparatus 100 can utilize artificial intelligence based on deep learning for the board defect inspection, and can also use the difference image obtained in step S717. Here, the substrate defect inspection apparatus 100 can perform the defect inspection using the artificial intelligence used in step S621 of FIG.

The board defect inspection apparatus 100 can perform defect determination by defect inspection (S723). The substrate defect inspection apparatus 100 can perform one of normal, defective, and re-inspection and defect determination.

The board defect inspection apparatus 100 can confirm whether the board is determined to be re-inspected according to the defect determination (S725).

As a result of the determination in step S725, if it is not determined to be a re-inspection, the substrate defect inspection apparatus 100 may proceed to step S560 and output the inspection result of the substrate.

As a result of the determination in step S725, if it is determined to be a re-inspection, the board defect inspection apparatus 100 may proceed to step S727.

The board defect inspection apparatus 100 may classify and filter the defect type using the set parameters for the inspection result (S727).

The board defect inspection apparatus 100 can determine defects by confirming defects by measurement (S729). The board defect inspection apparatus 100 may proceed to step S560 to output the determined result.

The term 'unit' used in this embodiment means software or a hardware component such as FPGA (field programmable gate array) or ASIC, and 'unit' performs a predetermined role. However, 'something' is not meant to be limited to software or hardware. The 'section' can also be configured to reside on an addressable recording medium and can be configured to be played back by one or more processors. Thus, by way of example, 'section' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program proprietary code, Includes drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

The functionality provided within a component and 'section' may be combined with a smaller number of components and 'section' or separated from additional components and 'section'.

In addition, the components and 'units' can also be embodied to play one or more CPUs in the device or secure multimedia card.

Also, the method of providing cooking contents according to an embodiment of the present invention can be embodied as a computer program (or computer program product) including instructions executable by a computer. A computer program includes a programmable machine instruction language processed by a processor, and is embodied in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language. can Also, the computer program can be recorded on any type of computer-readable recording medium (eg, memory, hard disk, magnetic/optical medium, SSD (Solid-State Drive), etc.).

Therefore, the substrate defect inspection method according to an embodiment of the present invention can be implemented by executing the computer program as described above by a computer device. A computing device may include at least a portion of a processor, a memory, a storage device, a high speed interface connecting to the memory and the high speed expansion port, and a low speed interface connecting to the low speed bus and the storage device. Each such component is connected to each other using various buses and can be mounted on a common motherboard or attached in any other suitable manner.

Here, the processor can process instructions within the computer device. Such commands may be stored in a memory or storage device to display graphic information for providing a GUI (Graphical User Interface) on an external input and output device such as a display connected to a high-speed interface. can have a command word As another example, multiple processors and/or multiple buses may suitably be used with multiple memories and memory configurations. Also, the processor may be embodied in a chipset consisting of chips containing multiple independent analog and/or digital processors.

The memory also stores information within the computing device. As an example, the memory can consist of volatile memory units or collections thereof. As another example, the memory may consist of non-volatile memory units or collections thereof. The memory may also be other forms of computer-readable media, such as magnetic or optical disks.

And the storage device can provide a large amount of storage space for the computer device. The storage device may be a computer-readable medium or a configuration that includes such a medium, and may include, for example, devices in a SAN (Storage Area Network) or other configuration, such as a floppy disk device, hard disk device, It may be an optical disk drive, or a tape drive, flash memory, or other similar semiconductor memory device or array of devices.

The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art to which the present invention pertains may find other specific forms without changing the technical idea or essential features of the present invention. can be easily transformed into Accordingly, the embodiments described above are to be considered in all respects as illustrative and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and likewise, components described as distributed may also be implemented in a combined form.

The scope of the invention is determined by the appended claims rather than by the foregoing detailed description, and all modifications or variations deriving from the meaning and scope of the claims and their equivalent concepts are included within the scope of the invention. must be interpreted as

REFERENCE SIGNS LIST 100 substrate defect inspection device 110 mobile workbench 120 illumination 130 database 140 alignment camera 150 line scan camera 160 area scan camera 170 input/output unit 180 control unit

Claims (11)

a mobile workbench for moving the board to a position for inspection;
lighting for irradiating the substrate with predetermined light to obtain a photographed image;
at least one line scan camera for photographing the substrate in predetermined line units;
at least one area camera for capturing an image of the substrate in units of a predetermined area;
a database for storing images for detecting defects from the substrate;
The position of the board is moved using the movable workbench, the lighting is controlled, and an image of the plating part and the solder resist part of the board are acquired from the line scan camera, and the obtained images are obtained. One of normal, defective, and re-inspection is determined from the obtained image to detect a primary defect, and the area camera controls the illumination for the substrate determined to be re-inspected. a controller for obtaining a substrate image obtained by photographing the substrate, determining one of normality and failure from the obtained substrate image, and detecting a secondary failure by determining a state of the substrate;
The control unit
The illumination is controlled a plurality of times for the board determined to be re-inspected, the board image is obtained by photographing the board a plurality of times, and the obtained board images are matched to determine the state of the board. as one of normal and defective to detect secondary defects . further comprising at least one alignment camera positioned within a predetermined distance from the line scan camera and the area camera and capturing an image for aligning the position of the substrate;
2. The board defect inspection apparatus of claim 1, wherein the controller adjusts the position of at least one of the line scan camera, the area camera, and the board using an image captured by the alignment camera. 2. The board defect inspection apparatus of claim 1, wherein the control unit uses defect image data stored in the database and subjected to deep learning to inspect the primary defect and the secondary defect. 4. The board defect of claim 3, wherein the controller learns the defect image data using the image of the board determined to be defective when the primary defect or the secondary defect is detected. inspection equipment. A board defect inspection method performed by a board defect inspection apparatus,
obtaining an image of a plated portion of the substrate and an image of a solder resist portion of the substrate by a line scan camera by controlling lighting for irradiating light onto the substrate;
determining one of normal, defective, and re-inspection from the acquired image and the state of the substrate to detect a primary failure;
obtaining a substrate image of the substrate determined to be re-inspected by controlling the illumination and photographing the substrate with an area camera;
detecting a secondary failure by determining one of normality and failure from the acquired image of the substrate and the status of the substrate;
The step of detecting the secondary failure includes:
The illumination is controlled a plurality of times for the board determined to be re-inspected, the board image is obtained by photographing the board a plurality of times, and the obtained board images are matched to determine the state of the board. as one of normal and defective to detect secondary defects . obtaining an image of the plated portion of the substrate and an image of the solder resist portion of the substrate by the line scan camera;
6. The board defect inspection of claim 5 , further comprising capturing an image for aligning the position of the board, and adjusting the position of at least one of the line scan camera and the board using the captured image. Method. Obtaining an image of the substrate photographed by the area camera includes: photographing an image for aligning the position of the substrate; and using the photographed image, position at least one of the area camera and the substrate. 6. The board defect inspection method according to claim 5 , comprising the step of adjusting . 6. The board defect inspection method of claim 5 , wherein the step of detecting the primary defect and the step of detecting the secondary defect use defect image data stored in a database and subjected to deep learning. 9. The board defect inspection of claim 8 , further comprising learning the defect image data using the image of the board determined to be defective after detecting the primary defect and the secondary defect. Method. A computer-readable recording medium in which a program for performing the method according to claim 5 is recorded. A computer program stored in a recording medium for performing the method of claim 5 , performed by a board defect inspection apparatus.

Images